spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:34:18.853Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:34:18.858Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}4{"parentUuid":null,"isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":"Begin"},"uuid":"252c69bd-6088-47b6-aed8-ee978e3f840c","timestamp":"2026-10-30T05:34:18.861Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","timestamp":"2026-10-30T05:34:18.873Z","version":"2.1.314","shape":{"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude, running within the Claude Agent SDK."},{"type":"text","text":"CWD: /Users/simon-pierreboucher/wp29/runs/RT0015\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/<timestamp>.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n\nSEPARATE REVIEW (additional)\n- After the gate passes, a separate reviewer session that has not seen your work in progress will examine `TASK.md` and everything under `out/` and may return a list of issues (file `out/review/review.json`). You will then be resumed once to address them: fix what is justified, explain in `out/report.md` (Limitations and open issues) what you disagree with, re-run the gate, and update `out/claims.json` and `out/state/phases.json`. The reviewer has no reference answers; its role is to challenge unsupported claims, violated information rules, unverified computations, and inconsistencies between your report and your results.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"4250517c-6fe4-4b93-b20a-66c1ecc42c33","timestamp":"2026-10-30T05:34:18.873Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"522bbd927138a6b0367e1ae1a99fc74ae6f1cf5fa9f2daf6e83ccdd80f5ef61c"}8{"parentUuid":"252c69bd-6088-47b6-aed8-ee978e3f840c","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"e768004a-8a59-4420-b225-140afd007891","timestamp":"2026-10-30T05:34:18.866Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"e768004a-8a59-4420-b225-140afd007891","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"babc436e-5946-480b-948b-31731c0491d3","timestamp":"2026-10-30T05:34:18.866Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"babc436e-5946-480b-948b-31731c0491d3","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"90b88fcd-9f74-41d8-adbe-fd4561da9c6d","timestamp":"2026-10-30T05:34:18.866Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}12{"parentUuid":"90b88fcd-9f74-41d8-adbe-fd4561da9c6d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqYVhJxGMRJk2tF6CW","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":135,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":488,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsqYDLBv83yDVNpCQWX","requestRef":"4250517c-6fe4-4b93-b20a-66c1ecc42c33","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b00c5225-a464-4130-a9c1-8da38dc8ca7e","timestamp":"2026-10-30T05:34:22.810Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"b00c5225-a464-4130-a9c1-8da38dc8ca7e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqYVhJxGMRJk2tF6CW","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01AJoATJe6kbfJ6qnGaXgwzd","name":"Bash","input":{"command":"cat TASK.md; ls -laR | head -50; cat out/state/* 2>/dev/null | head -50","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":135,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsqYDLBv83yDVNpCQWX","requestRef":"4250517c-6fe4-4b93-b20a-66c1ecc42c33","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2592d442-0531-48d9-aa76-92a63596c1bd","timestamp":"2026-10-30T05:34:23.340Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"2592d442-0531-48d9-aa76-92a63596c1bd","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01AJoATJe6kbfJ6qnGaXgwzd","type":"tool_result","content":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n  - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n  - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n  - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 40\ndrwxr-xr-x    6 simon-pierreboucher  staff    192 oct.  30 00:09 .\ndrwxr-xr-x  182 simon-pierreboucher  staff   5824 oct.  30 01:34 ..\n-rw-r--r--    1 simon-pierreboucher  staff   3082 oct.  30 00:09 bundle.json\ndrwxr-xr-x    7 simon-pierreboucher  staff    224 oct.  30 00:05 data\n-rw-r--r--    1 simon-pierreboucher  staff   3191 oct.  30 00:05 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  10330 oct.  30 00:05 TASK.md\n\n./data:\ntotal 80\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 .\ndrwxr-xr-x   6 simon-pierreboucher  staff    192 oct.  30 00:09 ..\n-rw-r--r--   1 simon-pierreboucher  staff   1384 oct.  30 00:05 first_release.csv\n-rw-r--r--   1 simon-pierreboucher  staff   9546 oct.  30 00:05 README.md\n-rw-r--r--   1 simon-pierreboucher  staff   7529 oct.  30 00:05 RSAFS_current.csv\n-rw-r--r--   1 simon-pierreboucher  staff  13438 oct.  30 00:05 UMCSENT.csv\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 vintages\n\n./data/vintages:\ntotal 560\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 .\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 ..\n-rw-r--r--   1 simon-pierreboucher  staff  18180 oct.  30 00:05 PAYEMS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18198 oct.  30 00:05 PAYEMS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18234 oct.  30 00:05 PAYEMS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18252 oct.  30 00:05 PAYEMS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18270 oct.  30 00:05 PAYEMS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18288 oct.  30 00:05 PAYEMS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18306 oct.  30 00:05 PAYEMS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18324 oct.  30 00:05 PAYEMS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18342 oct.  30 00:05 PAYEMS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18360 oct.  30 00:05 PAYEMS_vintage_2026-07-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7304 oct.  30 00:05 RSAFS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7322 oct.  30 00:05 RSAFS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7340 oct.  30 00:05 RSAFS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7358 oct.  30 00:05 RSAFS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7376 oct.  30 00:05 RSAFS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7394 oct.  30 00:05 RSAFS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7430 oct.  30 00:05 RSAFS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7448 oct.  30 00:05 RSAFS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7466 oct.  30 00:05 RSAFS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7484 oct.  30 00:05 RSAFS_vintage_2026-07-31.csv\n(eval):1: no matches found: out/state/*","is_error":false}]},"uuid":"246c9eeb-2a6e-42bf-b010-5c7934531a7f","timestamp":"2026-10-30T05:34:23.402Z","toolUseResult":{"stdout":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n  - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n  - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n  - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 40\ndrwxr-xr-x    6 simon-pierreboucher  staff    192 oct.  30 00:09 .\ndrwxr-xr-x  182 simon-pierreboucher  staff   5824 oct.  30 01:34 ..\n-rw-r--r--    1 simon-pierreboucher  staff   3082 oct.  30 00:09 bundle.json\ndrwxr-xr-x    7 simon-pierreboucher  staff    224 oct.  30 00:05 data\n-rw-r--r--    1 simon-pierreboucher  staff   3191 oct.  30 00:05 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  10330 oct.  30 00:05 TASK.md\n\n./data:\ntotal 80\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 .\ndrwxr-xr-x   6 simon-pierreboucher  staff    192 oct.  30 00:09 ..\n-rw-r--r--   1 simon-pierreboucher  staff   1384 oct.  30 00:05 first_release.csv\n-rw-r--r--   1 simon-pierreboucher  staff   9546 oct.  30 00:05 README.md\n-rw-r--r--   1 simon-pierreboucher  staff   7529 oct.  30 00:05 RSAFS_current.csv\n-rw-r--r--   1 simon-pierreboucher  staff  13438 oct.  30 00:05 UMCSENT.csv\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 vintages\n\n./data/vintages:\ntotal 560\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 .\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 ..\n-rw-r--r--   1 simon-pierreboucher  staff  18180 oct.  30 00:05 PAYEMS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18198 oct.  30 00:05 PAYEMS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18234 oct.  30 00:05 PAYEMS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18252 oct.  30 00:05 PAYEMS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18270 oct.  30 00:05 PAYEMS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18288 oct.  30 00:05 PAYEMS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18306 oct.  30 00:05 PAYEMS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18324 oct.  30 00:05 PAYEMS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18342 oct.  30 00:05 PAYEMS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18360 oct.  30 00:05 PAYEMS_vintage_2026-07-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7304 oct.  30 00:05 RSAFS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7322 oct.  30 00:05 RSAFS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7340 oct.  30 00:05 RSAFS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7358 oct.  30 00:05 RSAFS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7376 oct.  30 00:05 RSAFS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7394 oct.  30 00:05 RSAFS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7430 oct.  30 00:05 RSAFS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7448 oct.  30 00:05 RSAFS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7466 oct.  30 00:05 RSAFS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7484 oct.  30 00:05 RSAFS_vintage_2026-07-31.csv\n(eval):1: no matches found: out/state/*","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2592d442-0531-48d9-aa76-92a63596c1bd","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"04878791a4ae5a01edee17954b71c97fd56de0f9109491e66262bbc3c6bb3485","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01AJoATJe6kbfJ6qnGaXgwzd","name":"Bash","input":{"command":"cat TASK.md; ls -laR | head -50; cat out/state/* 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"6d64b642-057c-4ad7-a152-d03264da42bc","timestamp":"2026-10-30T05:34:23.405Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"4250517c-6fe4-4b93-b20a-66c1ecc42c33","keep":2,"tail":["04878791a4ae5a01edee17954b71c97fd56de0f9109491e66262bbc3c6bb3485","a7d51a14689c736bdc6134253af204c3366f1278290aea513914a90dd76bbb7a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"681f5a5877a1027a6414f8f55184c06c2521c7577dcf9d9a8a74347d821e27f8"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"246c9eeb-2a6e-42bf-b010-5c7934531a7f","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}18{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}19{"parentUuid":"246c9eeb-2a6e-42bf-b010-5c7934531a7f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqfYcbCiGJhenepsQS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ApQspKheX9JDEx1iZJKnMH","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json; cat bundle.json; cat data/first_release.csv; for f in data/vintages/RSAFS*; do echo $f; head -2 $f; tail -3 $f; wc -l < $f; done","description":"Read README, gate spec, first release, vintage tails"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5995,"cache_read_input_tokens":4315,"output_tokens":166,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5995},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsqezsFaNrcCk87xFRm","requestRef":"6d64b642-057c-4ad7-a152-d03264da42bc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e46b32af-b449-4757-b4f8-aaee89689a7a","timestamp":"2026-10-30T05:34:25.192Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"e46b32af-b449-4757-b4f8-aaee89689a7a","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ApQspKheX9JDEx1iZJKnMH","type":"tool_result","content":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\n{\n  \"task_id\": \"T1-forecast\",\n  \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/forecasts.csv\", \"out/table1.csv\", \"out/figure1.png\"],\n  \"results_keys\": {\n    \"task_id\": {\"type\": \"string\", \"nullable\": false},\n    \"model_name\": {\"type\": \"string\", \"nullable\": false},\n    \"model_description\": {\"type\": \"string\", \"nullable\": false},\n    \"n_origins\": {\"type\": \"integer\", \"nullable\": false},\n    \"first_origin\": {\"type\": \"string\", \"nullable\": false},\n    \"last_origin\": {\"type\": \"string\", \"nullable\": false},\n    \"rmse_naive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_naive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_snaive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_snaive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_ar1_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_ar1_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_model_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_model_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rel_improvement_rmse_h1\": {\"type\": \"number\", \"nullable\": false}, \"rel_improvement_rmse_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"dm_stat_h1\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"dm_stat_h3\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"conclusion_code_h1\": {\"type\": \"string\", \"nullable\": false}, \"conclusion_code_h3\": {\"type\": \"string\", \"nullable\": false},\n    \"mean_abs_revision_h1_targets\": {\"type\": \"number\", \"nullable\": false},\n    \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n    \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n    \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n    \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n    \"n_analysed\": {\"type\": \"integer\", \"nullable\": true},\n    \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n  },\n  \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n  \"family_checks\": [\"chronology\", \"forecasts_csv_chronology\", \"positive_se\", \"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n  \"ci_pairs\": [],\n  \"positive_keys\": [\"rmse_naive_h1\", \"rmse_naive_h3\", \"rmse_snaive_h1\", \"rmse_snaive_h3\", \"rmse_ar1_h1\", \"rmse_ar1_h3\", \"rmse_model_h1\", \"rmse_model_h3\"],\n  \"chronology_pairs\": [[\"first_origin\", \"last_origin\"]],\n  \"forecasts_csv\": {\"path\": \"out/forecasts.csv\", \"origin_col\": \"origin_date\", \"target_col\": \"target_date\", \"vintage_col\": \"vintage_used\", \"rule\": \"vintage_used <= origin_date < target_date\", \"expected_rows\": 80},\n  \"analysis_timeout_s\": 600,\n  \"reproducibility_tolerance_rel\": 1e-6\n}\n{\n  \"task_id\": \"T1-forecast\",\n  \"family\": \"T1\",\n  \"split\": \"transfer\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T04:09:07.391993+00:00\",\n  \"files\": {\n    \"TASK.md\": \"61cc57c0306ab4de71be29fc9e750be7f9ccd90b84a09c46af9ce71d01ac4faa\",\n    \"data/README.md\": \"10d4c51e4318444b5599fb0c4ca8fe9ec611882c7609689b68ba09513841f069\",\n    \"data/RSAFS_current.csv\": \"627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f\",\n    \"data/UMCSENT.csv\": \"3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46\",\n    \"data/first_release.csv\": \"1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4\",\n    \"data/vintages/PAYEMS_vintage_2025-10-31.csv\": \"d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60\",\n    \"data/vintages/PAYEMS_vintage_2025-11-30.csv\": \"a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77\",\n    \"data/vintages/PAYEMS_vintage_2025-12-31.csv\": \"829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031\",\n    \"data/vintages/PAYEMS_vintage_2026-01-31.csv\": \"8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7\",\n    \"data/vintages/PAYEMS_vintage_2026-02-28.csv\": \"4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3\",\n    \"data/vintages/PAYEMS_vintage_2026-03-31.csv\": \"919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e\",\n    \"data/vintages/PAYEMS_vintage_2026-04-30.csv\": \"06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a\",\n    \"data/vintages/PAYEMS_vintage_2026-05-31.csv\": \"e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d\",\n    \"data/vintages/PAYEMS_vintage_2026-06-30.csv\": \"19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a\",\n    \"data/vintages/PAYEMS_vintage_2026-07-31.csv\": \"3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41\",\n    \"data/vintages/RSAFS_vintage_2025-10-31.csv\": \"3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36\",\n    \"data/vintages/RSAFS_vintage_2025-11-30.csv\": \"4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4\",\n    \"data/vintages/RSAFS_vintage_2025-12-31.csv\": \"436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd\",\n    \"data/vintages/RSAFS_vintage_2026-01-31.csv\": \"b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e\",\n    \"data/vintages/RSAFS_vintage_2026-02-28.csv\": \"2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77\",\n    \"data/vintages/RSAFS_vintage_2026-03-31.csv\": \"0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f\",\n    \"data/vintages/RSAFS_vintage_2026-04-30.csv\": \"02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f\",\n    \"data/vintages/RSAFS_vintage_2026-05-31.csv\": \"8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b\",\n    \"data/vintages/RSAFS_vintage_2026-06-30.csv\": \"2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524\",\n    \"data/vintages/RSAFS_vintage_2026-07-31.csv\": \"52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2\",\n    \"gate_spec.json\": \"460c09d75917d708aabc0aad9e6571175ca5180d698d7ab7f11c92827d727354\"\n  }\n}target_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\ndata/vintages/RSAFS_vintage_2025-10-31.csv\nobservation_date,RSAFS_20251031\n1992-01-01,159177\n2025-06-01,723033\n2025-07-01,727414\n2025-08-01,732010\n     405\ndata/vintages/RSAFS_vintage_2025-11-30.csv\nobservation_date,RSAFS_20251130\n1992-01-01,159177\n2025-07-01,727727\n2025-08-01,732059\n2025-09-01,733258\n     406\ndata/vintages/RSAFS_vintage_2025-12-31.csv\nobservation_date,RSAFS_20251231\n1992-01-01,159177\n2025-08-01,731700\n2025-09-01,732444\n2025-10-01,732633\n     407\ndata/vintages/RSAFS_vintage_2026-01-31.csv\nobservation_date,RSAFS_20260131\n1992-01-01,159177\n2025-09-01,732192\n2025-10-01,731412\n2025-11-01,735904\n     408\ndata/vintages/RSAFS_vintage_2026-02-28.csv\nobservation_date,RSAFS_20260228\n1992-01-01,159177\n2025-10-01,731051\n2025-11-01,735085\n2025-12-01,734967\n     409\ndata/vintages/RSAFS_vintage_2026-03-31.csv\nobservation_date,RSAFS_20260331\n1992-01-01,159177\n2025-11-01,734718\n2025-12-01,734685\n2026-01-01,733537\n     410\ndata/vintages/RSAFS_vintage_2026-04-30.csv\nobservation_date,RSAFS_20260430\n1992-01-01,159177\n2026-01-01,734503\n2026-02-01,739772\n2026-03-01,752063\n     412\ndata/vintages/RSAFS_vintage_2026-05-31.csv\nobservation_date,RSAFS_20260531\n1992-01-01,159177\n2026-02-01,741278\n2026-03-01,753370\n2026-04-01,757085\n     413\ndata/vintages/RSAFS_vintage_2026-06-30.csv\nobservation_date,RSAFS_20260630\n1992-01-01,159177\n2026-03-01,754013\n2026-04-01,757036\n2026-05-01,763705\n     414\ndata/vintages/RSAFS_vintage_2026-07-31.csv\nobservation_date,RSAFS_20260731\n1992-01-01,159177\n2026-04-01,759097\n2026-05-01,766876\n2026-06-01,768553\n     415","is_error":false}]},"uuid":"d2fe0909-0a73-488a-9532-a4440699e10f","timestamp":"2026-10-30T05:34:25.266Z","toolUseResult":{"stdout":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\n{\n  \"task_id\": \"T1-forecast\",\n  \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/forecasts.csv\", \"out/table1.csv\", \"out/figure1.png\"],\n  \"results_keys\": {\n    \"task_id\": {\"type\": \"string\", \"nullable\": false},\n    \"model_name\": {\"type\": \"string\", \"nullable\": false},\n    \"model_description\": {\"type\": \"string\", \"nullable\": false},\n    \"n_origins\": {\"type\": \"integer\", \"nullable\": false},\n    \"first_origin\": {\"type\": \"string\", \"nullable\": false},\n    \"last_origin\": {\"type\": \"string\", \"nullable\": false},\n    \"rmse_naive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_naive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_naive_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_snaive_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_snaive_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_snaive_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_ar1_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_ar1_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_ar1_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_model_h1\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"rmse_model_h3\": {\"type\": \"number\", \"nullable\": false}, \"mae_model_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"rel_improvement_rmse_h1\": {\"type\": \"number\", \"nullable\": false}, \"rel_improvement_rmse_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"dm_stat_h1\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h1\": {\"type\": \"number\", \"nullable\": false},\n    \"dm_stat_h3\": {\"type\": \"number\", \"nullable\": false}, \"dm_pvalue_h3\": {\"type\": \"number\", \"nullable\": false},\n    \"conclusion_code_h1\": {\"type\": \"string\", \"nullable\": false}, \"conclusion_code_h3\": {\"type\": \"string\", \"nullable\": false},\n    \"mean_abs_revision_h1_targets\": {\"type\": \"number\", \"nullable\": false},\n    \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n    \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n    \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n    \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n    \"n_analysed\": {\"type\": \"integer\", \"nullable\": true},\n    \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n  },\n  \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n  \"family_checks\": [\"chronology\", \"forecasts_csv_chronology\", \"positive_se\", \"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n  \"ci_pairs\": [],\n  \"positive_keys\": [\"rmse_naive_h1\", \"rmse_naive_h3\", \"rmse_snaive_h1\", \"rmse_snaive_h3\", \"rmse_ar1_h1\", \"rmse_ar1_h3\", \"rmse_model_h1\", \"rmse_model_h3\"],\n  \"chronology_pairs\": [[\"first_origin\", \"last_origin\"]],\n  \"forecasts_csv\": {\"path\": \"out/forecasts.csv\", \"origin_col\": \"origin_date\", \"target_col\": \"target_date\", \"vintage_col\": \"vintage_used\", \"rule\": \"vintage_used <= origin_date < target_date\", \"expected_rows\": 80},\n  \"analysis_timeout_s\": 600,\n  \"reproducibility_tolerance_rel\": 1e-6\n}\n{\n  \"task_id\": \"T1-forecast\",\n  \"family\": \"T1\",\n  \"split\": \"transfer\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T04:09:07.391993+00:00\",\n  \"files\": {\n    \"TASK.md\": \"61cc57c0306ab4de71be29fc9e750be7f9ccd90b84a09c46af9ce71d01ac4faa\",\n    \"data/README.md\": \"10d4c51e4318444b5599fb0c4ca8fe9ec611882c7609689b68ba09513841f069\",\n    \"data/RSAFS_current.csv\": \"627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f\",\n    \"data/UMCSENT.csv\": \"3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46\",\n    \"data/first_release.csv\": \"1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4\",\n    \"data/vintages/PAYEMS_vintage_2025-10-31.csv\": \"d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60\",\n    \"data/vintages/PAYEMS_vintage_2025-11-30.csv\": \"a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77\",\n    \"data/vintages/PAYEMS_vintage_2025-12-31.csv\": \"829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031\",\n    \"data/vintages/PAYEMS_vintage_2026-01-31.csv\": \"8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7\",\n    \"data/vintages/PAYEMS_vintage_2026-02-28.csv\": \"4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3\",\n    \"data/vintages/PAYEMS_vintage_2026-03-31.csv\": \"919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e\",\n    \"data/vintages/PAYEMS_vintage_2026-04-30.csv\": \"06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a\",\n    \"data/vintages/PAYEMS_vintage_2026-05-31.csv\": \"e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d\",\n    \"data/vintages/PAYEMS_vintage_2026-06-30.csv\": \"19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a\",\n    \"data/vintages/PAYEMS_vintage_2026-07-31.csv\": \"3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41\",\n    \"data/vintages/RSAFS_vintage_2025-10-31.csv\": \"3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36\",\n    \"data/vintages/RSAFS_vintage_2025-11-30.csv\": \"4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4\",\n    \"data/vintages/RSAFS_vintage_2025-12-31.csv\": \"436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd\",\n    \"data/vintages/RSAFS_vintage_2026-01-31.csv\": \"b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e\",\n    \"data/vintages/RSAFS_vintage_2026-02-28.csv\": \"2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77\",\n    \"data/vintages/RSAFS_vintage_2026-03-31.csv\": \"0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f\",\n    \"data/vintages/RSAFS_vintage_2026-04-30.csv\": \"02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f\",\n    \"data/vintages/RSAFS_vintage_2026-05-31.csv\": \"8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b\",\n    \"data/vintages/RSAFS_vintage_2026-06-30.csv\": \"2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524\",\n    \"data/vintages/RSAFS_vintage_2026-07-31.csv\": \"52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2\",\n    \"gate_spec.json\": \"460c09d75917d708aabc0aad9e6571175ca5180d698d7ab7f11c92827d727354\"\n  }\n}target_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\ndata/vintages/RSAFS_vintage_2025-10-31.csv\nobservation_date,RSAFS_20251031\n1992-01-01,159177\n2025-06-01,723033\n2025-07-01,727414\n2025-08-01,732010\n     405\ndata/vintages/RSAFS_vintage_2025-11-30.csv\nobservation_date,RSAFS_20251130\n1992-01-01,159177\n2025-07-01,727727\n2025-08-01,732059\n2025-09-01,733258\n     406\ndata/vintages/RSAFS_vintage_2025-12-31.csv\nobservation_date,RSAFS_20251231\n1992-01-01,159177\n2025-08-01,731700\n2025-09-01,732444\n2025-10-01,732633\n     407\ndata/vintages/RSAFS_vintage_2026-01-31.csv\nobservation_date,RSAFS_20260131\n1992-01-01,159177\n2025-09-01,732192\n2025-10-01,731412\n2025-11-01,735904\n     408\ndata/vintages/RSAFS_vintage_2026-02-28.csv\nobservation_date,RSAFS_20260228\n1992-01-01,159177\n2025-10-01,731051\n2025-11-01,735085\n2025-12-01,734967\n     409\ndata/vintages/RSAFS_vintage_2026-03-31.csv\nobservation_date,RSAFS_20260331\n1992-01-01,159177\n2025-11-01,734718\n2025-12-01,734685\n2026-01-01,733537\n     410\ndata/vintages/RSAFS_vintage_2026-04-30.csv\nobservation_date,RSAFS_20260430\n1992-01-01,159177\n2026-01-01,734503\n2026-02-01,739772\n2026-03-01,752063\n     412\ndata/vintages/RSAFS_vintage_2026-05-31.csv\nobservation_date,RSAFS_20260531\n1992-01-01,159177\n2026-02-01,741278\n2026-03-01,753370\n2026-04-01,757085\n     413\ndata/vintages/RSAFS_vintage_2026-06-30.csv\nobservation_date,RSAFS_20260630\n1992-01-01,159177\n2026-03-01,754013\n2026-04-01,757036\n2026-05-01,763705\n     414\ndata/vintages/RSAFS_vintage_2026-07-31.csv\nobservation_date,RSAFS_20260731\n1992-01-01,159177\n2026-04-01,759097\n2026-05-01,766876\n2026-06-01,768553\n     415","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e46b32af-b449-4757-b4f8-aaee89689a7a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"67645ec020e1e6b6bbfd1a2d7ba54e4644fbed933698bc45c466458dd88b9c73","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01ApQspKheX9JDEx1iZJKnMH","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json; cat bundle.json; cat data/first_release.csv; for f in data/vintages/RSAFS*; do echo $f; head -2 $f; tail -3 $f; wc -l < $f; done","description":"Read README, gate spec, first release, vintage tails"}}]}}22{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"86d0ff6c-2b19-46db-ad97-c85bca918c0b","timestamp":"2026-10-30T05:34:25.269Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"6d64b642-057c-4ad7-a152-d03264da42bc","keep":4,"tail":["67645ec020e1e6b6bbfd1a2d7ba54e4644fbed933698bc45c466458dd88b9c73","a6ef24966278b81b849f44d54ae9a650d0bc17a9c34b8398fc371569ba8f7f6a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"bc58cfbad579e327f71b9f2186c9d23bece1d9c5e87b4567eff0a746fa50bcaf"}23{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d2fe0909-0a73-488a-9532-a4440699e10f","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}24{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}25{"parentUuid":"d2fe0909-0a73-488a-9532-a4440699e10f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqoGCc8vAgVCUk2daS","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":9895,"cache_read_input_tokens":10310,"output_tokens":952,"output_tokens_details":{"thinking_tokens":762},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":9895},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6195,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsqny6HqcxwCbYjqq77","requestRef":"86d0ff6c-2b19-46db-ad97-c85bca918c0b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ba589115-e781-4968-b826-5e8952c45823","timestamp":"2026-10-30T05:34:32.496Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"ba589115-e781-4968-b826-5e8952c45823","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqoGCc8vAgVCUk2daS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LRqwoK3ngzYwwNfogjdAMQ","name":"Bash","input":{"command":"tail -30 data/RSAFS_current.csv; tail -15 data/UMCSENT.csv; for f in data/vintages/PAYEMS*; do echo $f $(tail -1 $f); done; grep -c ',$' data/vintages/*.csv data/*.csv","description":"Inspect current RSAFS, UMCSENT, PAYEMS tails, empty values"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":9895,"cache_read_input_tokens":10310,"output_tokens":952,"output_tokens_details":{"thinking_tokens":762},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":9895},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsqny6HqcxwCbYjqq77","requestRef":"86d0ff6c-2b19-46db-ad97-c85bca918c0b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ef8f9e74-420b-4aa9-8709-0d335488cadd","timestamp":"2026-10-30T05:34:33.839Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"ef8f9e74-420b-4aa9-8709-0d335488cadd","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LRqwoK3ngzYwwNfogjdAMQ","type":"tool_result","content":"2024-04-01,664858\n2024-05-01,667659\n2024-06-01,666040\n2024-07-01,673662\n2024-08-01,670668\n2024-09-01,676005\n2024-10-01,681808\n2024-11-01,685709\n2024-12-01,691794\n2025-01-01,687058\n2025-02-01,683772\n2025-03-01,694750\n2025-04-01,695464\n2025-05-01,685488\n2025-06-01,691883\n2025-07-01,698280\n2025-08-01,700407\n2025-09-01,700948\n2025-10-01,700790\n2025-11-01,705453\n2025-12-01,706264\n2026-01-01,701860\n2026-02-01,707959\n2026-03-01,719700\n2026-04-01,723921\n2026-05-01,731415\n2026-06-01,732898\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n2025-07-01,61.7\n2025-08-01,58.2\n2025-09-01,55.1\n2025-10-01,53.6\n2025-11-01,51.0\n2025-12-01,52.9\n2026-01-01,56.4\n2026-02-01,56.6\n2026-03-01,53.3\n2026-04-01,49.8\n2026-05-01,44.8\n2026-06-01,49.5\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\ndata/vintages/PAYEMS_vintage_2025-10-31.csv 2025-08-01,159540\ndata/vintages/PAYEMS_vintage_2025-11-30.csv 2025-09-01,159626\ndata/vintages/PAYEMS_vintage_2025-12-31.csv 2025-11-01,159552\ndata/vintages/PAYEMS_vintage_2026-01-31.csv 2025-12-01,159526\ndata/vintages/PAYEMS_vintage_2026-02-28.csv 2026-01-01,158627\ndata/vintages/PAYEMS_vintage_2026-03-31.csv 2026-02-01,158466\ndata/vintages/PAYEMS_vintage_2026-04-30.csv 2026-03-01,158637\ndata/vintages/PAYEMS_vintage_2026-05-31.csv 2026-04-01,158736\ndata/vintages/PAYEMS_vintage_2026-06-30.csv 2026-05-01,159001\ndata/vintages/PAYEMS_vintage_2026-07-31.csv 2026-06-01,158984\ndata/vintages/PAYEMS_vintage_2025-10-31.csv:0\ndata/vintages/PAYEMS_vintage_2025-11-30.csv:0\ndata/vintages/PAYEMS_vintage_2025-12-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-01-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-02-28.csv:0\ndata/vintages/PAYEMS_vintage_2026-03-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-04-30.csv:0\ndata/vintages/PAYEMS_vintage_2026-05-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-06-30.csv:0\ndata/vintages/PAYEMS_vintage_2026-07-31.csv:0\ndata/vintages/RSAFS_vintage_2025-10-31.csv:0\ndata/vintages/RSAFS_vintage_2025-11-30.csv:0\ndata/vintages/RSAFS_vintage_2025-12-31.csv:0\ndata/vintages/RSAFS_vintage_2026-01-31.csv:0\ndata/vintages/RSAFS_vintage_2026-02-28.csv:0\ndata/vintages/RSAFS_vintage_2026-03-31.csv:0\ndata/vintages/RSAFS_vintage_2026-04-30.csv:0\ndata/vintages/RSAFS_vintage_2026-05-31.csv:0\ndata/vintages/RSAFS_vintage_2026-06-30.csv:0\ndata/vintages/RSAFS_vintage_2026-07-31.csv:0\ndata/first_release.csv:0\ndata/RSAFS_current.csv:0\ndata/UMCSENT.csv:210","is_error":false}]},"uuid":"6e764149-a88a-45bb-8927-0de493e8cb49","timestamp":"2026-10-30T05:34:33.870Z","toolUseResult":{"stdout":"2024-04-01,664858\n2024-05-01,667659\n2024-06-01,666040\n2024-07-01,673662\n2024-08-01,670668\n2024-09-01,676005\n2024-10-01,681808\n2024-11-01,685709\n2024-12-01,691794\n2025-01-01,687058\n2025-02-01,683772\n2025-03-01,694750\n2025-04-01,695464\n2025-05-01,685488\n2025-06-01,691883\n2025-07-01,698280\n2025-08-01,700407\n2025-09-01,700948\n2025-10-01,700790\n2025-11-01,705453\n2025-12-01,706264\n2026-01-01,701860\n2026-02-01,707959\n2026-03-01,719700\n2026-04-01,723921\n2026-05-01,731415\n2026-06-01,732898\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n2025-07-01,61.7\n2025-08-01,58.2\n2025-09-01,55.1\n2025-10-01,53.6\n2025-11-01,51.0\n2025-12-01,52.9\n2026-01-01,56.4\n2026-02-01,56.6\n2026-03-01,53.3\n2026-04-01,49.8\n2026-05-01,44.8\n2026-06-01,49.5\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\ndata/vintages/PAYEMS_vintage_2025-10-31.csv 2025-08-01,159540\ndata/vintages/PAYEMS_vintage_2025-11-30.csv 2025-09-01,159626\ndata/vintages/PAYEMS_vintage_2025-12-31.csv 2025-11-01,159552\ndata/vintages/PAYEMS_vintage_2026-01-31.csv 2025-12-01,159526\ndata/vintages/PAYEMS_vintage_2026-02-28.csv 2026-01-01,158627\ndata/vintages/PAYEMS_vintage_2026-03-31.csv 2026-02-01,158466\ndata/vintages/PAYEMS_vintage_2026-04-30.csv 2026-03-01,158637\ndata/vintages/PAYEMS_vintage_2026-05-31.csv 2026-04-01,158736\ndata/vintages/PAYEMS_vintage_2026-06-30.csv 2026-05-01,159001\ndata/vintages/PAYEMS_vintage_2026-07-31.csv 2026-06-01,158984\ndata/vintages/PAYEMS_vintage_2025-10-31.csv:0\ndata/vintages/PAYEMS_vintage_2025-11-30.csv:0\ndata/vintages/PAYEMS_vintage_2025-12-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-01-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-02-28.csv:0\ndata/vintages/PAYEMS_vintage_2026-03-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-04-30.csv:0\ndata/vintages/PAYEMS_vintage_2026-05-31.csv:0\ndata/vintages/PAYEMS_vintage_2026-06-30.csv:0\ndata/vintages/PAYEMS_vintage_2026-07-31.csv:0\ndata/vintages/RSAFS_vintage_2025-10-31.csv:0\ndata/vintages/RSAFS_vintage_2025-11-30.csv:0\ndata/vintages/RSAFS_vintage_2025-12-31.csv:0\ndata/vintages/RSAFS_vintage_2026-01-31.csv:0\ndata/vintages/RSAFS_vintage_2026-02-28.csv:0\ndata/vintages/RSAFS_vintage_2026-03-31.csv:0\ndata/vintages/RSAFS_vintage_2026-04-30.csv:0\ndata/vintages/RSAFS_vintage_2026-05-31.csv:0\ndata/vintages/RSAFS_vintage_2026-06-30.csv:0\ndata/vintages/RSAFS_vintage_2026-07-31.csv:0\ndata/first_release.csv:0\ndata/RSAFS_current.csv:0\ndata/UMCSENT.csv:210","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ef8f9e74-420b-4aa9-8709-0d335488cadd","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}28{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"26897bed99aabf52dc29eb67a806b5b73b3bb40973d7695916f0b058c6b6b46e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LRqwoK3ngzYwwNfogjdAMQ","name":"Bash","input":{"command":"tail -30 data/RSAFS_current.csv; tail -15 data/UMCSENT.csv; for f in data/vintages/PAYEMS*; do echo $f $(tail -1 $f); done; grep -c ',$' data/vintages/*.csv data/*.csv","description":"Inspect current RSAFS, UMCSENT, PAYEMS tails, empty values"}}]}}29{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"1dc11941-a0eb-45ec-a839-e8c6ad0d1b67","timestamp":"2026-10-30T05:34:33.872Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"86d0ff6c-2b19-46db-ad97-c85bca918c0b","keep":6,"tail":["26897bed99aabf52dc29eb67a806b5b73b3bb40973d7695916f0b058c6b6b46e","aa32db0fd1bed6030d6194201b6d54fa681cb875900210deea09062c8ef639f3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"91957d31ba4b1f28280cb091a67762e5388f74a21ae2bf7b5f52ffa0d44481ab"}30{"parentUuid":"6e764149-a88a-45bb-8927-0de493e8cb49","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsrRy4rmJ1SycQgHutU","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2401,"cache_read_input_tokens":20205,"output_tokens":2964,"output_tokens_details":{"thinking_tokens":1897},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2401},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":19251,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsrRmfSZRxkxeAm8jEZ","requestRef":"1dc11941-a0eb-45ec-a839-e8c6ad0d1b67","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"55a9741e-becf-413f-945a-fc5db03983a3","timestamp":"2026-10-30T05:34:54.046Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"55a9741e-becf-413f-945a-fc5db03983a3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsrRy4rmJ1SycQgHutU","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Qy5WfrKDFp5kNLCYNeuaKJ","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — T1-forecast\n\n**Question.** How accurately could US retail & food services sales YoY growth (g_m = 100 ln(L_m/L_{m-12}), RSAFS) be forecast in real time, h = 1 and h = 3 months beyond the last published month last(V), at 10 month-end origins V (2025-10-31 … 2026-07-31), and does my own model beat the naive (no-change) forecast when errors are measured against the first-release YoY of the target month (`data/first_release.csv`)?\n\n**Estimands** (per h in {1,3}, over 10 origins):\n(a) RMSE and MAE vs first release for naive, seasonal naive, AR(1) (OLS on g, 1993-02..last(V), iterated) and my model;\n(b) 1 - RMSE_model/RMSE_naive;\n(c) DM statistic model vs naive, squared loss, d_t = e²_naive - e²_model, Bartlett LRV with lag h-1, no HLN correction, two-sided normal p-value;\n(d) mean over the 10 h=1 targets of |g_current_T - yoy_first_release_T|.\nMeaningful under: the target definition (first release at month-end granularity), real-time data only, n = 10 (very small; DM asymptotics are weak; h=3 errors overlap).\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (all keys of TASK.md table), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md (6 sections), out/analysis.py, out/claims.json; plus protocol files (state/, exclusions.csv).\n\n**Availability rules.** At origin V use only RSAFS vintage V, PAYEMS vintage V, UMCSENT months <= month(V). RSAFS_current only for (d). Target = last(V)+h, where last(V) is the last row in the vintage (publication delays exist).\n\n**Invalidating conditions.** Any target missing from first_release.csv; use of current/future data in forecasts; model tuned on evaluation outcomes; negative/zero long-run variance in DM.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read completely\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > log.md","description":"Write contract, phase ledger, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2401,"cache_read_input_tokens":20205,"output_tokens":2964,"output_tokens_details":{"thinking_tokens":1897},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2401},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsrRmfSZRxkxeAm8jEZ","requestRef":"1dc11941-a0eb-45ec-a839-e8c6ad0d1b67","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"714efe5d-d5c3-49f6-8b7d-5b43aa11fbed","timestamp":"2026-10-30T05:35:02.735Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"714efe5d-d5c3-49f6-8b7d-5b43aa11fbed","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Qy5WfrKDFp5kNLCYNeuaKJ","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"de8aebbd-99af-4758-802a-c29dc74c00db","timestamp":"2026-10-30T05:35:02.772Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"714efe5d-d5c3-49f6-8b7d-5b43aa11fbed","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"e9b597b63d6d61e2a108b0a3b377981481cd48476571fae5bcd7cda014aa2ba1","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Qy5WfrKDFp5kNLCYNeuaKJ","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — T1-forecast\n\n**Question.** How accurately could US retail & food services sales YoY growth (g_m = 100 ln(L_m/L_{m-12}), RSAFS) be forecast in real time, h = 1 and h = 3 months beyond the last published month last(V), at 10 month-end origins V (2025-10-31 … 2026-07-31), and does my own model beat the naive (no-change) forecast when errors are measured against the first-release YoY of the target month (`data/first_release.csv`)?\n\n**Estimands** (per h in {1,3}, over 10 origins):\n(a) RMSE and MAE vs first release for naive, seasonal naive, AR(1) (OLS on g, 1993-02..last(V), iterated) and my model;\n(b) 1 - RMSE_model/RMSE_naive;\n(c) DM statistic model vs naive, squared loss, d_t = e²_naive - e²_model, Bartlett LRV with lag h-1, no HLN correction, two-sided normal p-value;\n(d) mean over the 10 h=1 targets of |g_current_T - yoy_first_release_T|.\nMeaningful under: the target definition (first release at month-end granularity), real-time data only, n = 10 (very small; DM asymptotics are weak; h=3 errors overlap).\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (all keys of TASK.md table), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md (6 sections), out/analysis.py, out/claims.json; plus protocol files (state/, exclusions.csv).\n\n**Availability rules.** At origin V use only RSAFS vintage V, PAYEMS vintage V, UMCSENT months <= month(V). RSAFS_current only for (d). Target = last(V)+h, where last(V) is the last row in the vintage (publication delays exist).\n\n**Invalidating conditions.** Any target missing from first_release.csv; use of current/future data in forecasts; model tuned on evaluation outcomes; negative/zero long-run variance in DM.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read completely\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > log.md","description":"Write contract, phase ledger, log"}}]}}34{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"ae5590d6-0d4b-4996-815f-2cc654b68da7","timestamp":"2026-10-30T05:35:02.775Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"1dc11941-a0eb-45ec-a839-e8c6ad0d1b67","keep":8,"tail":["e9b597b63d6d61e2a108b0a3b377981481cd48476571fae5bcd7cda014aa2ba1","d8df8fb025e14680b38a82962e087bed4123cf76f9942811826f76fb86b4f5d3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2ea04801f577533620fdb37bdcc818f257f392edb7b2951aba6c5b31af7b964f"}35{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"de8aebbd-99af-4758-802a-c29dc74c00db","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}36{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}37{"parentUuid":"de8aebbd-99af-4758-802a-c29dc74c00db","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstZeF5UqwmmK6mff9S","type":"message","role":"assistant","content":[{"type":"text","text":"Now the data audit."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2979,"cache_read_input_tokens":22606,"output_tokens":797,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2979},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXstZMPAQD9nvynWnJCu","requestRef":"ae5590d6-0d4b-4996-815f-2cc654b68da7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cbaea11d-0cd8-472f-b78a-4a7d3d3fbdca","timestamp":"2026-10-30T05:35:03.505Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}38{"parentUuid":"cbaea11d-0cd8-472f-b78a-4a7d3d3fbdca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstZeF5UqwmmK6mff9S","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BwjJoxEEbCoQhUMKcWXqnt","name":"Bash","input":{"command":"cat > /tmp/audit.py <<'EOF'\nimport pandas as pd, numpy as np, hashlib, glob, os\nfiles = sorted(glob.glob('data/*.csv')+glob.glob('data/vintages/*.csv'))\nfor f in files:\n    h=hashlib.sha256(open(f,'rb').read()).hexdigest()\n    d=pd.read_csv(f)\n    dc=d.columns[0]; dt=pd.to_datetime(d[dc])\n    vc=d.columns[-1]\n    gaps = (dt.dt.to_period('M').astype('int64').diff().dropna()!=1).sum()\n    print(f\"| {f} | {h[:16]}… | {len(d)} | {len(d.columns)} | {list(d.columns)} | {dt.min().date()}..{dt.max().date()} | NA={d.isna().sum().sum()} | dup={d[dc].duplicated().sum()} | gaps={gaps} |\")\n# UMCSENT missing after 1978?\nu=pd.read_csv('data/UMCSENT.csv',parse_dates=['observation_date'])\nprint('UMCSENT missing after 1978-01:', u[(u.observation_date>='1978-01-01')&u.UMCSENT.isna()].shape[0])\n# vintage last months and revisions\nfor f in sorted(glob.glob('data/vintages/RSAFS*')):\n    d=pd.read_csv(f); print(os.path.basename(f), d.iloc[-1,0], len(d))\ncur=pd.read_csv('data/RSAFS_current.csv',index_col=0)\nv=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',index_col=0)\nr=(v.iloc[:,0]/cur.iloc[:,0].reindex(v.index)).dropna()\nprint('ratio vintage0731/current last 5 & first 3', r.tail(5).round(4).tolist(), r.head(3).round(4).tolist(), r.loc['2015-01-01'])\nEOF\n~/wp29/venv/bin/python /tmp/audit.py","description":"Audit all data files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2979,"cache_read_input_tokens":22606,"output_tokens":797,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2979},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXstZMPAQD9nvynWnJCu","requestRef":"ae5590d6-0d4b-4996-815f-2cc654b68da7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e4a2f2c7-a1ca-485c-a319-0cf58db3e7cb","timestamp":"2026-10-30T05:35:09.631Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}39{"parentUuid":"e4a2f2c7-a1ca-485c-a319-0cf58db3e7cb","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n  File \"/tmp/audit.py\", line 11, in <module>\n    u=pd.read_csv('data/UMCSENT.csv',parse_dates=['observation_date'])\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n    return _read(filepath_or_buffer, kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n    parser = TextFileReader(filepath_or_buffer, **kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n    self._engine = self._make_engine(f, self.engine)\n                   ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n    self.handles = get_handle(\n                   ~~~~~~~~~~^\n        f,\n        ^^\n    ...<6 lines>...\n        storage_options=self.options.get(\"storage_options\", None),\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n    handle = open(\n        handle,\n    ...<3 lines>...\n        newline=\"\",\n    )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/UMCSENT.csv'","is_error":true,"tool_use_id":"toolu_01BwjJoxEEbCoQhUMKcWXqnt"}]},"uuid":"36d6362d-bed7-4d82-8774-31c8923e9fb6","timestamp":"2026-10-30T05:35:09.853Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n  File \"/tmp/audit.py\", line 11, in <module>\n    u=pd.read_csv('data/UMCSENT.csv',parse_dates=['observation_date'])\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n    return _read(filepath_or_buffer, kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n    parser = TextFileReader(filepath_or_buffer, **kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n    self._engine = self._make_engine(f, self.engine)\n                   ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n    self.handles = get_handle(\n                   ~~~~~~~~~~^\n        f,\n        ^^\n    ...<6 lines>...\n        storage_options=self.options.get(\"storage_options\", None),\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n    handle = open(\n        handle,\n    ...<3 lines>...\n        newline=\"\",\n    )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/UMCSENT.csv'","sandboxed":false,"sourceToolAssistantUUID":"e4a2f2c7-a1ca-485c-a319-0cf58db3e7cb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}40{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"bc753158b9b6d471a9ecba192f61b8f943bc75e484eab039a6621abe3575ba69","message":{"role":"assistant","content":[{"type":"text","text":"Now the data audit."},{"type":"tool_use","id":"toolu_01BwjJoxEEbCoQhUMKcWXqnt","name":"Bash","input":{"command":"cat > /tmp/audit.py <<'EOF'\nimport pandas as pd, numpy as np, hashlib, glob, os\nfiles = sorted(glob.glob('data/*.csv')+glob.glob('data/vintages/*.csv'))\nfor f in files:\n    h=hashlib.sha256(open(f,'rb').read()).hexdigest()\n    d=pd.read_csv(f)\n    dc=d.columns[0]; dt=pd.to_datetime(d[dc])\n    vc=d.columns[-1]\n    gaps = (dt.dt.to_period('M').astype('int64').diff().dropna()!=1).sum()\n    print(f\"| {f} | {h[:16]}… | {len(d)} | {len(d.columns)} | {list(d.columns)} | {dt.min().date()}..{dt.max().date()} | NA={d.isna().sum().sum()} | dup={d[dc].duplicated().sum()} | gaps={gaps} |\")\n# UMCSENT missing after 1978?\nu=pd.read_csv('data/UMCSENT.csv',parse_dates=['observation_date'])\nprint('UMCSENT missing after 1978-01:', u[(u.observation_date>='1978-01-01')&u.UMCSENT.isna()].shape[0])\n# vintage last months and revisions\nfor f in sorted(glob.glob('data/vintages/RSAFS*')):\n    d=pd.read_csv(f); print(os.path.basename(f), d.iloc[-1,0], len(d))\ncur=pd.read_csv('data/RSAFS_current.csv',index_col=0)\nv=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',index_col=0)\nr=(v.iloc[:,0]/cur.iloc[:,0].reindex(v.index)).dropna()\nprint('ratio vintage0731/current last 5 & first 3', r.tail(5).round(4).tolist(), r.head(3).round(4).tolist(), r.loc['2015-01-01'])\nEOF\n~/wp29/venv/bin/python /tmp/audit.py","description":"Audit all data files"}}]}}41{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"41c037a7-72e2-479f-b609-1fc180541010","timestamp":"2026-10-30T05:35:09.856Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"ae5590d6-0d4b-4996-815f-2cc654b68da7","keep":10,"tail":["bc753158b9b6d471a9ecba192f61b8f943bc75e484eab039a6621abe3575ba69","6a199b89984bce3fe4100ae24cd5f3550cec54925daa41b8ef883159b2d340e6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"05cde36a9b7c2dd7890de78c7fb295dd2112ad89bdb11ad4a961578440cafc0f"}42{"parentUuid":"36d6362d-bed7-4d82-8774-31c8923e9fb6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsu5vPrF1tcWuvypHjP","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSlAYKEAgTGAI4AUIIdGhpbmtpbmcSDJtzSfa3tXJjMxdkhhoMtNLANTwMre/mU5tWIjD/OHSKINoBtB5QxWNTZWCDuLoSjt7lnL7vmkItVdqlenRDF2CfGaAzoknU5Uan3SIqsQUihj+jrS/iPNRbRebu1zPa4B7CR+8/Kj15LXDS9/eI1HLiBNsAObMnQ5Kn5V25K5VnjT+/DYKgOpd4NN6c0CSMRMzCGZQsdS2k16RRmKr4sy8EoxhFnyiAdvAexL61Yg9j/nnQUazjO126qt9R3zUu+M4eMf5oOQz+IjBHYEXAubo190AsO0Gnr4ePFIgHHHCllTqum5Gt49wvEFhqnPsQ8V/57J2IxeinFBBXeAmfooa4P5lIf3bNq3dOiUFvA2dHl1cJqP4Xm9SMLctFMOZjJpYki0BzXfMHAMiatJnfgHLt479gu0/eC2871quRMKfJ/at+ORvGV1L7xv/611AyYKjH+40Kj6b28fnannegWbRWQhoCTRwFykBWziC9i4He8QTPPMO1CVnYpjtugFewPa7X2tDeZO7pQYjUVe3BUEDeWKVKaeVSHizw4q6g3LVJvFJGq18iseP5pT/5+jL4IPrg/dtQH/p+w3xAmxyjou/OtP9FfjmbVwZoFadfd503tjyebogeD3u+yYA/PvfBofnI4mV6Xj+fZrR+wpBWP3qvCv+sjFL8g3elQl9XV8TKOEVPmJX0qXYO7OZfDp4Jqb5k8qE/jYL+nUiUaDd/kPmenlqf4cnJJCltfoO3IYYh3TKxYpEmUYveQRFIrgIZUeTCsqx3e9kbp6diV7KwbGEyYjiXrcHsqUtw/vMef8GZmOBFCFPyb61aSvqut//ny+oe1QX/RJcCCv5eTg7qVAcDcmNN1fUfhXniLFWOvSV+94HABrwFzuO7TUzKmolMsS4M7s2ZDHFoO3Ibvx+qljK3j90V12YrVmUgnmR5PtHfNfnVm2Yjzb7rGhB05SoWJuzpY7u9NptP5jpU4d7uJYILR5TTed3/NJuCRPJ/8z4Ojghvo32Alg0NcKe1MVrpgxgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1501,"cache_read_input_tokens":25585,"output_tokens":148,"output_tokens_details":{"thinking_tokens":20},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1501},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":386,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsu5enGA56iYbAuLRMJ","requestRef":"41c037a7-72e2-479f-b609-1fc180541010","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a92ad0ee-1944-4359-8e2d-2f7b160b9c66","timestamp":"2026-10-30T05:35:10.973Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}43{"parentUuid":"a92ad0ee-1944-4359-8e2d-2f7b160b9c66","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsu5vPrF1tcWuvypHjP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MtHFqn7Sc7WVRtY9yes77o","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0015 && ~/wp29/venv/bin/python /tmp/audit.py","description":"Run audit from workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1501,"cache_read_input_tokens":25585,"output_tokens":148,"output_tokens_details":{"thinking_tokens":20},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1501},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsu5enGA56iYbAuLRMJ","requestRef":"41c037a7-72e2-479f-b609-1fc180541010","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"60324c69-531d-405e-afaf-97b3313bda42","timestamp":"2026-10-30T05:35:11.426Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}44{"parentUuid":"60324c69-531d-405e-afaf-97b3313bda42","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MtHFqn7Sc7WVRtY9yes77o","type":"tool_result","content":"| data/RSAFS_current.csv | 627d8bb386ac80f4… | 417 | 2 | ['observation_date', 'RSAFS'] | 1992-01-01..2026-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/UMCSENT.csv | 3076277f9f21f4bd… | 887 | 2 | ['observation_date', 'UMCSENT'] | 1952-11-01..2026-09-01 | NA=210 | dup=0 | gaps=0 |\n| data/first_release.csv | 1d1ae8b3cacf7799… | 28 | 5 | ['target_month', 'first_release_vintage', 'level_first_release', 'level_prev_year_same_vintage', 'yoy_first_release'] | 2024-06-01..2026-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2025-10-31.csv | d4b4c909ed321fbf… | 1040 | 2 | ['observation_date', 'PAYEMS_20251031'] | 1939-01-01..2025-08-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2025-11-30.csv | a05ef7fc50cfc339… | 1041 | 2 | ['observation_date', 'PAYEMS_20251130'] | 1939-01-01..2025-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2025-12-31.csv | 829dae087af61916… | 1043 | 2 | ['observation_date', 'PAYEMS_20251231'] | 1939-01-01..2025-11-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-01-31.csv | 8fd01c5d2740e869… | 1044 | 2 | ['observation_date', 'PAYEMS_20260131'] | 1939-01-01..2025-12-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-02-28.csv | 4a913e67ac5ffbb4… | 1045 | 2 | ['observation_date', 'PAYEMS_20260228'] | 1939-01-01..2026-01-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-03-31.csv | 919de86b07be9046… | 1046 | 2 | ['observation_date', 'PAYEMS_20260331'] | 1939-01-01..2026-02-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-04-30.csv | 06a8d663d9aaa61c… | 1047 | 2 | ['observation_date', 'PAYEMS_20260430'] | 1939-01-01..2026-03-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-05-31.csv | e2a152e874139acd… | 1048 | 2 | ['observation_date', 'PAYEMS_20260531'] | 1939-01-01..2026-04-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-06-30.csv | 19fbc6cd3547ffad… | 1049 | 2 | ['observation_date', 'PAYEMS_20260630'] | 1939-01-01..2026-05-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-07-31.csv | 3a3a6603fcc31c6e… | 1050 | 2 | ['observation_date', 'PAYEMS_20260731'] | 1939-01-01..2026-06-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2025-10-31.csv | 3ecb0832a391e726… | 404 | 2 | ['observation_date', 'RSAFS_20251031'] | 1992-01-01..2025-08-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2025-11-30.csv | 4a683d85374690f1… | 405 | 2 | ['observation_date', 'RSAFS_20251130'] | 1992-01-01..2025-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2025-12-31.csv | 436df4b5509b1dfe… | 406 | 2 | ['observation_date', 'RSAFS_20251231'] | 1992-01-01..2025-10-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-01-31.csv | b92ab6a5c1dbdc56… | 407 | 2 | ['observation_date', 'RSAFS_20260131'] | 1992-01-01..2025-11-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-02-28.csv | 2af0a3aaeeba81ef… | 408 | 2 | ['observation_date', 'RSAFS_20260228'] | 1992-01-01..2025-12-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-03-31.csv | 0316fdf238d55d9f… | 409 | 2 | ['observation_date', 'RSAFS_20260331'] | 1992-01-01..2026-01-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-04-30.csv | 02dcc697a1db3475… | 411 | 2 | ['observation_date', 'RSAFS_20260430'] | 1992-01-01..2026-03-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-05-31.csv | 8c3fe35302135896… | 412 | 2 | ['observation_date', 'RSAFS_20260531'] | 1992-01-01..2026-04-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-06-30.csv | 2f103157f4a9b7a3… | 413 | 2 | ['observation_date', 'RSAFS_20260630'] | 1992-01-01..2026-05-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-07-31.csv | 52c04a8fce2effa7… | 414 | 2 | ['observation_date', 'RSAFS_20260731'] | 1992-01-01..2026-06-01 | NA=0 | dup=0 | gaps=0 |\nUMCSENT missing after 1978-01: 0\nRSAFS_vintage_2025-10-31.csv 2025-08-01 404\nRSAFS_vintage_2025-11-30.csv 2025-09-01 405\nRSAFS_vintage_2025-12-31.csv 2025-10-01 406\nRSAFS_vintage_2026-01-31.csv 2025-11-01 407\nRSAFS_vintage_2026-02-28.csv 2025-12-01 408\nRSAFS_vintage_2026-03-31.csv 2026-01-01 409\nRSAFS_vintage_2026-04-30.csv 2026-03-01 411\nRSAFS_vintage_2026-05-31.csv 2026-04-01 412\nRSAFS_vintage_2026-06-30.csv 2026-05-01 413\nRSAFS_vintage_2026-07-31.csv 2026-06-01 414\nratio vintage0731/current last 5 & first 3 [1.0471, 1.0477, 1.0486, 1.0485, 1.0486] [1.0, 1.0, 1.0] 1.000051379540667","is_error":false}]},"uuid":"7b1be75c-a0c6-4407-839c-e11085095496","timestamp":"2026-10-30T05:35:11.664Z","toolUseResult":{"stdout":"| data/RSAFS_current.csv | 627d8bb386ac80f4… | 417 | 2 | ['observation_date', 'RSAFS'] | 1992-01-01..2026-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/UMCSENT.csv | 3076277f9f21f4bd… | 887 | 2 | ['observation_date', 'UMCSENT'] | 1952-11-01..2026-09-01 | NA=210 | dup=0 | gaps=0 |\n| data/first_release.csv | 1d1ae8b3cacf7799… | 28 | 5 | ['target_month', 'first_release_vintage', 'level_first_release', 'level_prev_year_same_vintage', 'yoy_first_release'] | 2024-06-01..2026-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2025-10-31.csv | d4b4c909ed321fbf… | 1040 | 2 | ['observation_date', 'PAYEMS_20251031'] | 1939-01-01..2025-08-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2025-11-30.csv | a05ef7fc50cfc339… | 1041 | 2 | ['observation_date', 'PAYEMS_20251130'] | 1939-01-01..2025-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2025-12-31.csv | 829dae087af61916… | 1043 | 2 | ['observation_date', 'PAYEMS_20251231'] | 1939-01-01..2025-11-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-01-31.csv | 8fd01c5d2740e869… | 1044 | 2 | ['observation_date', 'PAYEMS_20260131'] | 1939-01-01..2025-12-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-02-28.csv | 4a913e67ac5ffbb4… | 1045 | 2 | ['observation_date', 'PAYEMS_20260228'] | 1939-01-01..2026-01-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-03-31.csv | 919de86b07be9046… | 1046 | 2 | ['observation_date', 'PAYEMS_20260331'] | 1939-01-01..2026-02-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-04-30.csv | 06a8d663d9aaa61c… | 1047 | 2 | ['observation_date', 'PAYEMS_20260430'] | 1939-01-01..2026-03-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-05-31.csv | e2a152e874139acd… | 1048 | 2 | ['observation_date', 'PAYEMS_20260531'] | 1939-01-01..2026-04-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-06-30.csv | 19fbc6cd3547ffad… | 1049 | 2 | ['observation_date', 'PAYEMS_20260630'] | 1939-01-01..2026-05-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/PAYEMS_vintage_2026-07-31.csv | 3a3a6603fcc31c6e… | 1050 | 2 | ['observation_date', 'PAYEMS_20260731'] | 1939-01-01..2026-06-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2025-10-31.csv | 3ecb0832a391e726… | 404 | 2 | ['observation_date', 'RSAFS_20251031'] | 1992-01-01..2025-08-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2025-11-30.csv | 4a683d85374690f1… | 405 | 2 | ['observation_date', 'RSAFS_20251130'] | 1992-01-01..2025-09-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2025-12-31.csv | 436df4b5509b1dfe… | 406 | 2 | ['observation_date', 'RSAFS_20251231'] | 1992-01-01..2025-10-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-01-31.csv | b92ab6a5c1dbdc56… | 407 | 2 | ['observation_date', 'RSAFS_20260131'] | 1992-01-01..2025-11-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-02-28.csv | 2af0a3aaeeba81ef… | 408 | 2 | ['observation_date', 'RSAFS_20260228'] | 1992-01-01..2025-12-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-03-31.csv | 0316fdf238d55d9f… | 409 | 2 | ['observation_date', 'RSAFS_20260331'] | 1992-01-01..2026-01-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-04-30.csv | 02dcc697a1db3475… | 411 | 2 | ['observation_date', 'RSAFS_20260430'] | 1992-01-01..2026-03-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-05-31.csv | 8c3fe35302135896… | 412 | 2 | ['observation_date', 'RSAFS_20260531'] | 1992-01-01..2026-04-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-06-30.csv | 2f103157f4a9b7a3… | 413 | 2 | ['observation_date', 'RSAFS_20260630'] | 1992-01-01..2026-05-01 | NA=0 | dup=0 | gaps=0 |\n| data/vintages/RSAFS_vintage_2026-07-31.csv | 52c04a8fce2effa7… | 414 | 2 | ['observation_date', 'RSAFS_20260731'] | 1992-01-01..2026-06-01 | NA=0 | dup=0 | gaps=0 |\nUMCSENT missing after 1978-01: 0\nRSAFS_vintage_2025-10-31.csv 2025-08-01 404\nRSAFS_vintage_2025-11-30.csv 2025-09-01 405\nRSAFS_vintage_2025-12-31.csv 2025-10-01 406\nRSAFS_vintage_2026-01-31.csv 2025-11-01 407\nRSAFS_vintage_2026-02-28.csv 2025-12-01 408\nRSAFS_vintage_2026-03-31.csv 2026-01-01 409\nRSAFS_vintage_2026-04-30.csv 2026-03-01 411\nRSAFS_vintage_2026-05-31.csv 2026-04-01 412\nRSAFS_vintage_2026-06-30.csv 2026-05-01 413\nRSAFS_vintage_2026-07-31.csv 2026-06-01 414\nratio vintage0731/current last 5 & first 3 [1.0471, 1.0477, 1.0486, 1.0485, 1.0486] [1.0, 1.0, 1.0] 1.000051379540667","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"60324c69-531d-405e-afaf-97b3313bda42","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}45{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"5b0b2fe7db51b85d8c7a0f0d389209d3128fcf53fd6ec552859f9cdb01bb192a","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01MtHFqn7Sc7WVRtY9yes77o","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0015 && ~/wp29/venv/bin/python /tmp/audit.py","description":"Run audit from workspace root"}}]}}46{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"7564ff90-c80b-45d6-9729-413982b4568f","timestamp":"2026-10-30T05:35:11.667Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"41c037a7-72e2-479f-b609-1fc180541010","keep":12,"tail":["5b0b2fe7db51b85d8c7a0f0d389209d3128fcf53fd6ec552859f9cdb01bb192a","4571087a023e3c02e0f3c32c654ff09a213fa4b2ecee853efb7631ab7ec65240"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f54dceab2dfbf3e641f4fa85b1aa997ca1a3af945b700f767b3472b69473e0f9"}47{"parentUuid":"7b1be75c-a0c6-4407-839c-e11085095496","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsuDcW8RyUNFZxdxnND","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2977,"cache_read_input_tokens":27086,"output_tokens":713,"output_tokens_details":{"thinking_tokens":317},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2977},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2334,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsuDLdXukDyKwek95Pe","requestRef":"7564ff90-c80b-45d6-9729-413982b4568f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"166c344b-242a-47b2-ab6f-332f720ac17c","timestamp":"2026-10-30T05:35:15.050Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"166c344b-242a-47b2-ab6f-332f720ac17c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsuDcW8RyUNFZxdxnND","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DZWzEnvpGYsmiL5e2NYLsC","name":"Bash","input":{"command":"{ echo \"# Data audit (P1)\"; echo; echo \"All SHA-256 below were computed and match data/README.md and bundle.json (first 16 hex shown; full hashes recomputed in analysis is unnecessary — checked here with hashlib).\"; echo; echo \"| file | sha256 | rows | cols | columns | date range | missing | duplicate dates | month gaps |\"; echo \"|---|---|---|---|---|---|---|---|---|\"; ~/wp29/venv/bin/python /tmp/audit.py | grep '^|'; } > out/state/data_audit.md\nfor f in data/*.csv data/vintages/*.csv; do h=$(shasum -a 256 $f | cut -c1-64); grep -q $h data/README.md && echo \"OK $f\" || echo \"MISMATCH $f\"; done | sort | uniq -c | head; ","description":"Write audit table and verify hashes against README"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2977,"cache_read_input_tokens":27086,"output_tokens":713,"output_tokens_details":{"thinking_tokens":317},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2977},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsuDLdXukDyKwek95Pe","requestRef":"7564ff90-c80b-45d6-9729-413982b4568f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"50eaec19-cb18-44fa-a3a9-58169510a09f","timestamp":"2026-10-30T05:35:18.239Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}49{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"50eaec19-cb18-44fa-a3a9-58169510a09f","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}50{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}51{"parentUuid":"50eaec19-cb18-44fa-a3a9-58169510a09f","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DZWzEnvpGYsmiL5e2NYLsC","type":"tool_result","content":"   1 OK data/first_release.csv\n   1 OK data/RSAFS_current.csv\n   1 OK data/UMCSENT.csv\n   1 OK data/vintages/PAYEMS_vintage_2025-10-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2025-11-30.csv\n   1 OK data/vintages/PAYEMS_vintage_2025-12-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-01-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-02-28.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-03-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-04-30.csv","is_error":false}]},"uuid":"1fe118ae-ff5b-4b78-9631-c20937d6dffb","timestamp":"2026-10-30T05:35:18.707Z","toolUseResult":{"stdout":"   1 OK data/first_release.csv\n   1 OK data/RSAFS_current.csv\n   1 OK data/UMCSENT.csv\n   1 OK data/vintages/PAYEMS_vintage_2025-10-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2025-11-30.csv\n   1 OK data/vintages/PAYEMS_vintage_2025-12-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-01-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-02-28.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-03-31.csv\n   1 OK data/vintages/PAYEMS_vintage_2026-04-30.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"50eaec19-cb18-44fa-a3a9-58169510a09f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}52{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"077c1c01064471c735bac30f8fe60723ac6ff0920ac226b6423d50f36a568fc0","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01DZWzEnvpGYsmiL5e2NYLsC","name":"Bash","input":{"command":"{ echo \"# Data audit (P1)\"; echo; echo \"All SHA-256 below were computed and match data/README.md and bundle.json (first 16 hex shown; full hashes recomputed in analysis is unnecessary — checked here with hashlib).\"; echo; echo \"| file | sha256 | rows | cols | columns | date range | missing | duplicate dates | month gaps |\"; echo \"|---|---|---|---|---|---|---|---|---|\"; ~/wp29/venv/bin/python /tmp/audit.py | grep '^|'; } > out/state/data_audit.md\nfor f in data/*.csv data/vintages/*.csv; do h=$(shasum -a 256 $f | cut -c1-64); grep -q $h data/README.md && echo \"OK $f\" || echo \"MISMATCH $f\"; done | sort | uniq -c | head; ","description":"Write audit table and verify hashes against README"}}]}}53{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"e3624f36-4e40-4133-9c19-a9b4adee2e55","timestamp":"2026-10-30T05:35:18.710Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"7564ff90-c80b-45d6-9729-413982b4568f","keep":14,"tail":["077c1c01064471c735bac30f8fe60723ac6ff0920ac226b6423d50f36a568fc0","48d55cd02e38850f67f6a1d32facfc38a0d4f6df8da2db2ae3ff0d2b9ad4be1a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3b61743b87be58cb64688e4f637e139656cbeff6d1a70d796490846c4eeaca7a"}54{"parentUuid":"1fe118ae-ff5b-4b78-9631-c20937d6dffb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsujkVJS4hWBSBbAnHq","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018pc721ZCcLHtpBiXLXDE3C","name":"Bash","input":{"command":"for f in data/*.csv data/vintages/*.csv; do h=$(shasum -a 256 $f | cut -c1-64); grep -q $h data/README.md && echo \"OK\" || echo \"MISMATCH $f\"; done | sort | uniq -c\ncat >> out/state/data_audit.md <<'EOF'\n\nAll 23 CSV SHA-256 hashes match `data/README.md` (23 OK, 0 mismatch; shasum check run in P1). Row counts match README.\n\n## Units\nRSAFS: millions of USD, SA. PAYEMS: thousands of persons, SA. UMCSENT: index 1966Q1=100. first_release.yoy_first_release: percent (100·log ratio).\n\n## Real-time design: last(V) per origin (publication delays)\n| origin V | last(V) RSAFS | lag (months before V's month) | h=1 target | h=3 target | PAYEMS last |\n|---|---|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2 (delay; Oct-2025 federal shutdown) | 2025-09 | 2025-11 | 2025-08 |\n| 2025-11-30 | 2025-09 | 2 | 2025-10 | 2025-12 | 2025-09 |\n| 2025-12-31 | 2025-10 | 2 | 2025-11 | 2026-01 | 2025-11 |\n| 2026-01-31 | 2025-11 | 2 | 2025-12 | 2026-02 | 2025-12 |\n| 2026-02-28 | 2025-12 | 2 | 2026-01 | 2026-03 | 2026-01 |\n| 2026-03-31 | 2026-01 | 2 | 2026-02 | 2026-04 | 2026-02 |\n| 2026-04-30 | 2026-03 | 1 (caught up: two months added at once) | 2026-04 | 2026-06 | 2026-03 |\n| 2026-05-31 | 2026-04 | 1 | 2026-05 | 2026-07 | 2026-04 |\n| 2026-06-30 | 2026-05 | 1 | 2026-06 | 2026-08 | 2026-05 |\n| 2026-07-31 | 2026-06 | 1 | 2026-07 | 2026-09 | 2026-06 |\nAll 20 targets (2025-09 … 2026-09) exist in first_release.csv.\n\n## Anomalies\n1. Irregular RSAFS publication timing (table above): last(V) lags V by 2 months for the first six origins, 1 month thereafter. Handled by defining targets relative to last(V) as TASK requires.\n2. first_release vintages: 2025-09 first appears only in the 2025-11-30 vintage; 2026-02 and 2026-03 both first appear in 2026-04-30 (so 2026-02's \"first release\" is its second Census estimate, not the advance). Handled: used as provided (task definition), documented.\n3. Large level revision: RSAFS levels in the current file are ≈4.7–4.9% below the 2026-07-31 vintage for 2025–2026 (ratio ≈1.0000 for 1992 and 2015). first_release rows for 2026-08/2026-09 use prev-year levels on the revised basis (e.g. 2025-08: 700218 vs 732010 earlier). Because YoY growth is computed within a single vintage, levels are never mixed across vintages; the revision only enters estimand (d).\n4. UMCSENT: 210 empty values, all before 1978 (quarterly survey era); none after 1978-01. UMCSENT is not used by my model (decision in log), so no handling needed.\n5. PAYEMS vintages show a benchmark revision (level drop around the 2026-02-28 vintage). PAYEMS not used by my model.\n6. No duplicate dates, no gaps, no missing values in RSAFS/PAYEMS vintages or first_release.\n\n## Information-availability\nRSAFS_current.csv violates the forecast-time availability rule by construction; it is read only in the revision block (estimand d). UMCSENT current vintage: allowed with months <= month(V); not used. No other violations.\nEOF\nprintf 'step,rule,n_before,n_after,n_removed,rationale\\n1,\"candidate model forecast-actual pairs: 10 origins x 2 horizons; drop pairs whose target month is missing from first_release.csv\",20,20,0,\"all 20 targets (2025-09..2026-09) present in first_release.csv\"\\n2,\"drop pairs with non-finite forecast or actual\",20,20,0,\"no missing values in vintages or first_release\"\\n' > out/exclusions.csv; cat out/exclusions.csv","description":"Finish audit notes and exclusion ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":962,"cache_read_input_tokens":30063,"output_tokens":1657,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":962},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsujSsf2JGHSbHQqFzY","requestRef":"e3624f36-4e40-4133-9c19-a9b4adee2e55","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"84c4d263-b033-4f70-a824-657ca72c4862","timestamp":"2026-10-30T05:35:32.899Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}55{"parentUuid":"84c4d263-b033-4f70-a824-657ca72c4862","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018pc721ZCcLHtpBiXLXDE3C","type":"tool_result","content":"  23 OK\nstep,rule,n_before,n_after,n_removed,rationale\n1,\"candidate model forecast-actual pairs: 10 origins x 2 horizons; drop pairs whose target month is missing from first_release.csv\",20,20,0,\"all 20 targets (2025-09..2026-09) present in first_release.csv\"\n2,\"drop pairs with non-finite forecast or actual\",20,20,0,\"no missing values in vintages or first_release\"","is_error":false}]},"uuid":"e6382428-2be8-4d45-a7a8-453068b1059a","timestamp":"2026-10-30T05:35:33.189Z","toolUseResult":{"stdout":"  23 OK\nstep,rule,n_before,n_after,n_removed,rationale\n1,\"candidate model forecast-actual pairs: 10 origins x 2 horizons; drop pairs whose target month is missing from first_release.csv\",20,20,0,\"all 20 targets (2025-09..2026-09) present in first_release.csv\"\n2,\"drop pairs with non-finite forecast or actual\",20,20,0,\"no missing values in vintages or first_release\"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"84c4d263-b033-4f70-a824-657ca72c4862","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}56{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"ac1078a7db89035243fe0eb0e4892aec26402f59a226c5f06db9ce1f0737db54","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_018pc721ZCcLHtpBiXLXDE3C","name":"Bash","input":{"command":"for f in data/*.csv data/vintages/*.csv; do h=$(shasum -a 256 $f | cut -c1-64); grep -q $h data/README.md && echo \"OK\" || echo \"MISMATCH $f\"; done | sort | uniq -c\ncat >> out/state/data_audit.md <<'EOF'\n\nAll 23 CSV SHA-256 hashes match `data/README.md` (23 OK, 0 mismatch; shasum check run in P1). Row counts match README.\n\n## Units\nRSAFS: millions of USD, SA. PAYEMS: thousands of persons, SA. UMCSENT: index 1966Q1=100. first_release.yoy_first_release: percent (100·log ratio).\n\n## Real-time design: last(V) per origin (publication delays)\n| origin V | last(V) RSAFS | lag (months before V's month) | h=1 target | h=3 target | PAYEMS last |\n|---|---|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2 (delay; Oct-2025 federal shutdown) | 2025-09 | 2025-11 | 2025-08 |\n| 2025-11-30 | 2025-09 | 2 | 2025-10 | 2025-12 | 2025-09 |\n| 2025-12-31 | 2025-10 | 2 | 2025-11 | 2026-01 | 2025-11 |\n| 2026-01-31 | 2025-11 | 2 | 2025-12 | 2026-02 | 2025-12 |\n| 2026-02-28 | 2025-12 | 2 | 2026-01 | 2026-03 | 2026-01 |\n| 2026-03-31 | 2026-01 | 2 | 2026-02 | 2026-04 | 2026-02 |\n| 2026-04-30 | 2026-03 | 1 (caught up: two months added at once) | 2026-04 | 2026-06 | 2026-03 |\n| 2026-05-31 | 2026-04 | 1 | 2026-05 | 2026-07 | 2026-04 |\n| 2026-06-30 | 2026-05 | 1 | 2026-06 | 2026-08 | 2026-05 |\n| 2026-07-31 | 2026-06 | 1 | 2026-07 | 2026-09 | 2026-06 |\nAll 20 targets (2025-09 … 2026-09) exist in first_release.csv.\n\n## Anomalies\n1. Irregular RSAFS publication timing (table above): last(V) lags V by 2 months for the first six origins, 1 month thereafter. Handled by defining targets relative to last(V) as TASK requires.\n2. first_release vintages: 2025-09 first appears only in the 2025-11-30 vintage; 2026-02 and 2026-03 both first appear in 2026-04-30 (so 2026-02's \"first release\" is its second Census estimate, not the advance). Handled: used as provided (task definition), documented.\n3. Large level revision: RSAFS levels in the current file are ≈4.7–4.9% below the 2026-07-31 vintage for 2025–2026 (ratio ≈1.0000 for 1992 and 2015). first_release rows for 2026-08/2026-09 use prev-year levels on the revised basis (e.g. 2025-08: 700218 vs 732010 earlier). Because YoY growth is computed within a single vintage, levels are never mixed across vintages; the revision only enters estimand (d).\n4. UMCSENT: 210 empty values, all before 1978 (quarterly survey era); none after 1978-01. UMCSENT is not used by my model (decision in log), so no handling needed.\n5. PAYEMS vintages show a benchmark revision (level drop around the 2026-02-28 vintage). PAYEMS not used by my model.\n6. No duplicate dates, no gaps, no missing values in RSAFS/PAYEMS vintages or first_release.\n\n## Information-availability\nRSAFS_current.csv violates the forecast-time availability rule by construction; it is read only in the revision block (estimand d). UMCSENT current vintage: allowed with months <= month(V); not used. No other violations.\nEOF\nprintf 'step,rule,n_before,n_after,n_removed,rationale\\n1,\"candidate model forecast-actual pairs: 10 origins x 2 horizons; drop pairs whose target month is missing from first_release.csv\",20,20,0,\"all 20 targets (2025-09..2026-09) present in first_release.csv\"\\n2,\"drop pairs with non-finite forecast or actual\",20,20,0,\"no missing values in vintages or first_release\"\\n' > out/exclusions.csv; cat out/exclusions.csv","description":"Finish audit notes and exclusion ledger"}}]}}57{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"469ed134-85b4-42b2-b1fb-b2f47b1b6252","timestamp":"2026-10-30T05:35:33.192Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"e3624f36-4e40-4133-9c19-a9b4adee2e55","keep":16,"tail":["ac1078a7db89035243fe0eb0e4892aec26402f59a226c5f06db9ce1f0737db54","480fca72b530dc30874131f72df36f35d22e8cdef41dcd9dec219843028dbb12"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ba8b4bfd6beae5157bfd444ddf4bc86052189d632c6d11c7b4e1972dfc433ad6"}58{"parentUuid":"e6382428-2be8-4d45-a7a8-453068b1059a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvocBfmLc4fTEnH1g7","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1814,"cache_read_input_tokens":31025,"output_tokens":703,"output_tokens_details":{"thinking_tokens":154},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1814},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1761,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsvoMYawNuz2QJZqgb3","requestRef":"469ed134-85b4-42b2-b1fb-b2f47b1b6252","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"df6cad31-42db-4312-b3e7-6aa01cfb157b","timestamp":"2026-10-30T05:35:35.879Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}59{"parentUuid":"df6cad31-42db-4312-b3e7-6aa01cfb157b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvocBfmLc4fTEnH1g7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019UEMAviXKFt9Vk152M1b4n","name":"Bash","input":{"command":"cd out/state && sed -i '' 's/ (delay; Oct-2025 federal shutdown)/ (publication delay)/; s/^5\\. PAYEMS vintages show a benchmark revision (level drop around the 2026-02-28 vintage)\\. PAYEMS not used by my model\\./5. PAYEMS vintages were checked for gaps\\/missing only (none); PAYEMS is not used by my model, so its revisions were not analysed./' data_audit.md && grep -n \"^5\\.\\|2025-10-31 |\" data_audit.md\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of 23 CSVs recomputed: 23 match README\",\"row/col counts, date ranges, NA, duplicates, gaps computed (data_audit.md)\",\"last(V) per origin tabulated; all 20 targets present in first_release.csv\",\"exclusions.csv written: 20-0=20\"],\"notes\":\"RSAFS_current used only for estimand (d)\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P1 passed: audit done; decision: model uses RSAFS vintage only (PAYEMS/UMCSENT not used), pre-specified before any evaluation metric computed.\" >> log.md","description":"Fix audit wording, update ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1814,"cache_read_input_tokens":31025,"output_tokens":703,"output_tokens_details":{"thinking_tokens":154},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1814},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsvoMYawNuz2QJZqgb3","requestRef":"469ed134-85b4-42b2-b1fb-b2f47b1b6252","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b837a198-6eab-41ea-97b3-2b4e65a2606f","timestamp":"2026-10-30T05:35:40.549Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}60{"parentUuid":"b837a198-6eab-41ea-97b3-2b4e65a2606f","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019UEMAviXKFt9Vk152M1b4n","type":"tool_result","content":"39:| 2025-10-31 | 2025-08 | 2 (publication delay) | 2025-09 | 2025-11 | 2025-08 |\n56:5. PAYEMS vintages were checked for gaps/missing only (none); PAYEMS is not used by my model, so its revisions were not analysed.","is_error":false}]},"uuid":"25db8ca9-2dbb-41af-8c53-c522fb42d8fb","timestamp":"2026-10-30T05:35:40.600Z","toolUseResult":{"stdout":"39:| 2025-10-31 | 2025-08 | 2 (publication delay) | 2025-09 | 2025-11 | 2025-08 |\n56:5. PAYEMS vintages were checked for gaps/missing only (none); PAYEMS is not used by my model, so its revisions were not analysed.","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b837a198-6eab-41ea-97b3-2b4e65a2606f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}61{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"ab0d9c4f8993aeb5e0b13c227da44486801a79c02e774601087566d8fbe35d53","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019UEMAviXKFt9Vk152M1b4n","name":"Bash","input":{"command":"cd out/state && sed -i '' 's/ (delay; Oct-2025 federal shutdown)/ (publication delay)/; s/^5\\. PAYEMS vintages show a benchmark revision (level drop around the 2026-02-28 vintage)\\. PAYEMS not used by my model\\./5. PAYEMS vintages were checked for gaps\\/missing only (none); PAYEMS is not used by my model, so its revisions were not analysed./' data_audit.md && grep -n \"^5\\.\\|2025-10-31 |\" data_audit.md\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of 23 CSVs recomputed: 23 match README\",\"row/col counts, date ranges, NA, duplicates, gaps computed (data_audit.md)\",\"last(V) per origin tabulated; all 20 targets present in first_release.csv\",\"exclusions.csv written: 20-0=20\"],\"notes\":\"RSAFS_current used only for estimand (d)\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P1 passed: audit done; decision: model uses RSAFS vintage only (PAYEMS/UMCSENT not used), pre-specified before any evaluation metric computed.\" >> log.md","description":"Fix audit wording, update ledger"}}]}}62{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"c9d401b1-ce88-4f2e-893d-7ce67198a6b9","timestamp":"2026-10-30T05:35:40.602Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"469ed134-85b4-42b2-b1fb-b2f47b1b6252","keep":18,"tail":["ab0d9c4f8993aeb5e0b13c227da44486801a79c02e774601087566d8fbe35d53","5461167802ec2d50f13e8460192843c68521194bc802e650976d621662dd096d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"6d24096e4c3adc7fee39a2153f63cb8b2df59c9dffa8907f4e0cc6cb6a132130"}63{"parentUuid":"25db8ca9-2dbb-41af-8c53-c522fb42d8fb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswMLQbCYUYiqwm82JY","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":810,"cache_read_input_tokens":32839,"output_tokens":5312,"output_tokens_details":{"thinking_tokens":386},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":810},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3643,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXswM2YcDqV5KC1C9JQX","requestRef":"c9d401b1-ce88-4f2e-893d-7ce67198a6b9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"91be9960-2bd6-42b9-a386-135c8c973bab","timestamp":"2026-10-30T05:35:45.217Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}64{"parentUuid":"91be9960-2bd6-42b9-a386-135c8c973bab","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswMLQbCYUYiqwm82JY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XpRLuQcyaZMU7e2dXZNYC3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail sales YoY growth (RSAFS).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png.\nDeterministic: no random numbers are used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\nMODEL_NAME = \"rw_drift_base_effect\"\nMODEL_DESCRIPTION = (\n    \"Random walk with drift for the log level of RSAFS, translated into YoY growth so that the known \"\n    \"'base effects' (the monthly changes that drop out of the 12-month window) are used. At origin V, \"\n    \"with x_m = ln L_m from the RSAFS vintage dated V and l = last(V): drift d = (x_l - x_{l-12})/12 \"\n    \"(mean monthly log change over the last 12 published months, i.e. a rolling 12-month estimation window); \"\n    \"forecast of the log level x_{l+h} = x_l + h*d; forecast YoY g_{l+h} = 100*(x_l + h*d - x_{l+h-12}), \"\n    \"where x_{l+h-12} (h<=3) is already published in vintage V. Uses only the RSAFS vintage dated V; \"\n    \"PAYEMS and UMCSENT are not used. The specification (including the 12-month drift window) was fixed \"\n    \"before any forecast error was computed; no parameter was tuned on the evaluation targets.\")\n\n\ndef ms(s):  # month start Timestamp\n    return pd.Timestamp(s).to_period(\"M\").to_timestamp()\n\n\ndef read_series(path):\n    d = pd.read_csv(path)\n    s = pd.Series(d.iloc[:, 1].values.astype(float), index=pd.to_datetime(d.iloc[:, 0]))\n    return s, len(d)\n\n\ndef yoy(level):\n    x = np.log(level)\n    return 100.0 * (x - x.shift(12, freq=\"MS\")).reindex(level.index)\n\n\nn_input_rows = {}\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\nn_input_rows[\"first_release.csv\"] = len(fr)\nactual = fr.set_index(\"target_month\")[\"yoy_first_release\"]\n\nrows, data_issues_auto = [], []\nlast_months = {}\nfor V in ORIGINS:\n    lv, n = read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/RSAFS_vintage_{V}.csv\"] = n\n    # PAYEMS vintage is read only for the row count/audit; not used in any forecast.\n    _, npay = read_series(os.path.join(DATA, \"vintages\", f\"PAYEMS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/PAYEMS_vintage_{V}.csv\"] = npay\n    assert lv.index.max() <= pd.Timestamp(V), \"vintage contains months after origin\"\n    assert not lv.isna().any()\n    last = lv.index.max()\n    last_months[V] = last\n    g = yoy(lv)\n    x = np.log(lv)\n    # AR(1): OLS of g_m on const, g_{m-1}, 1993-02 <= m <= last\n    gs = g.loc[\"1993-01-01\":last]\n    y = gs.loc[\"1993-02-01\":].values\n    ylag = gs.shift(1).loc[\"1993-02-01\":].values\n    X = np.column_stack([np.ones_like(ylag), ylag])\n    a, b = np.linalg.lstsq(X, y, rcond=None)[0]\n    d = (x[last] - x[last - pd.DateOffset(months=12)]) / 12.0\n    for h in HORIZONS:\n        T = last + pd.DateOffset(months=h)\n        T12 = T - pd.DateOffset(months=12)\n        f = {}\n        f[\"naive\"] = g[last]\n        f[\"snaive\"] = g[T12]\n        fa = g[last]\n        for _ in range(h):\n            fa = a + b * fa\n        f[\"ar1\"] = fa\n        f[\"model\"] = 100.0 * (x[last] + h * d - x[T12])\n        for m in MODELS:\n            rows.append(dict(origin_date=V, target_date=T.strftime(\"%Y-%m-%d\"), horizon=h,\n                             forecast=float(f[m]), actual_first_release=float(actual[T]),\n                             model=m, vintage_used=V))\n\nfc = pd.DataFrame(rows)\nfc = fc.sort_values([\"horizon\", \"model\", \"origin_date\"]).reset_index(drop=True)\nfc[\"error\"] = fc[\"actual_first_release\"] - fc[\"forecast\"]\nfc.drop(columns=\"error\").to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False, float_format=\"%.6f\")\n\nres = {\"task_id\": \"T1-forecast\", \"model_name\": MODEL_NAME, \"model_description\": MODEL_DESCRIPTION,\n       \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\ntab = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)][\"error\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        tab.append(dict(model=m, horizon=h, rmse=rmse, mae=mae, n=len(e)))\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n\ndef dm_test(e_naive, e_model, h):\n    dd = e_naive ** 2 - e_model ** 2\n    n = len(dd)\n    dbar = dd.mean()\n    dc = dd - dbar\n    lrv = np.sum(dc * dc) / n\n    for j in range(1, h):  # Bartlett weights, truncation lag h-1\n        w = 1.0 - j / h\n        lrv += 2.0 * w * np.sum(dc[j:] * dc[:-j]) / n\n    stat = dbar / np.sqrt(lrv / n)\n    p = 2.0 * (1.0 - stats.norm.cdf(abs(stat)))\n    return float(stat), float(p), float(lrv), float(dbar)\n\n\ndm_extra = {}\nfor h in HORIZONS:\n    en = fc[(fc.model == \"naive\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    em = fc[(fc.model == \"model\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    res[f\"rel_improvement_rmse_h{h}\"] = 1.0 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    s, p, lrv, dbar = dm_test(en, em, h)\n    assert lrv > 0\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = s, p\n    dm_extra[h] = (lrv, dbar)\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    sig = \"significant\" if p < 0.05 else \"not_significant\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n\n# (d) revision: current vintage growth vs first release, h=1 targets (RSAFS_current used ONLY here)\ncur, ncur = read_series(os.path.join(DATA, \"RSAFS_current.csv\"))\nn_input_rows[\"RSAFS_current.csv\"] = ncur\ngcur = yoy(cur)\nt1 = fc[(fc.model == \"naive\") & (fc.horizon == 1)][\"target_date\"].map(pd.Timestamp)\nrev = pd.DataFrame({\"target\": t1.values, \"g_current\": gcur.reindex(t1.values).values,\n                    \"first_release\": actual.reindex(t1.values).values})\nrev[\"abs_rev\"] = (rev.g_current - rev.first_release).abs()\nres[\"mean_abs_revision_h1_targets\"] = float(rev[\"abs_rev\"].mean())\n\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nlag = {V: (pd.Timestamp(V).to_period(\"M\") - last_months[V].to_period(\"M\")).n for V in ORIGINS}\nres[\"data_issues\"] = [\n    {\"issue\": \"Irregular RSAFS publication timing: last(V) is 2 months before the origin month for origins \"\n              + \", \".join(V for V in ORIGINS if lag[V] == 2) + \" and 1 month for the others; the 2026-04-30 vintage added two months at once.\",\n     \"handling\": \"Targets defined as last(V)+h exactly as TASK.md requires; each forecast uses only the vintage dated V (vintage_used = origin_date).\"},\n    {\"issue\": \"First-release dating is at month-end granularity: 2025-09 first appears in the 2025-11-30 vintage, and 2026-02 and 2026-03 both first appear in the 2026-04-30 vintage (so the 2026-02 'first release' is not the advance estimate).\",\n     \"handling\": \"first_release.csv used as provided (task definition of the actual); documented in the report.\"},\n    {\"issue\": \"Large level revision: RSAFS levels in the current vintage are about 4.7-4.9% below those of the 2026-07-31 vintage for 2025-2026 months (first_release rows for 2026-08/09 already use the revised base).\",\n     \"handling\": \"YoY growth is always computed within a single vintage (levels never mixed across vintages); the revision enters only estimand (d).\"},\n    {\"issue\": \"UMCSENT has 210 empty values, all before 1978 (quarterly survey era).\",\n     \"handling\": \"UMCSENT not used by the model; no imputation needed.\"},\n    {\"issue\": \"RSAFS_current.csv contains information not available at any forecast origin.\",\n     \"handling\": \"Read only in the revision block for estimand (d), after all forecasts are produced.\"},\n]\nn_input_rows[\"UMCSENT.csv\"] = len(pd.read_csv(os.path.join(DATA, \"UMCSENT.csv\")))  # audited, not used in forecasts\nres[\"n_input_rows\"] = dict(sorted(n_input_rows.items()))\nres[\"n_analysed\"] = int(len(fc[fc.model == \"model\"]))\nres[\"random_seed\"] = None\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\n# auxiliary (non-required) diagnostics for the report\naux = {\"dm_long_run_variance\": {f\"h{h}\": dm_extra[h][0] for h in HORIZONS},\n       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},\n       \"revision_by_target\": rev.assign(target=rev.target.dt.strftime(\"%Y-%m\")).round(6).to_dict(\"records\"),\n       \"last_month_by_origin\": {V: last_months[V].strftime(\"%Y-%m\") for V in ORIGINS}}\nos.makedirs(os.path.join(OUT, \"state\"), exist_ok=True)\nwith open(os.path.join(OUT, \"state\", \"aux_diagnostics.json\"), \"w\") as fh:\n    json.dump(aux, fh, indent=2)\n\n# Figure\nfig, axes = plt.subplots(2, 1, figsize=(8, 7), sharex=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc[fc.horizon == h]\n    a_ = sub[sub.model == \"naive\"].sort_values(\"target_date\")\n    ax.plot(pd.to_datetime(a_.target_date), a_.actual_first_release, \"k-o\", label=\"first release (actual)\")\n    for m, st in [(\"naive\", \"C0--s\"), (\"model\", \"C3-^\"), (\"ar1\", \"C2:x\")]:\n        s_ = sub[sub.model == m].sort_values(\"target_date\")\n        ax.plot(pd.to_datetime(s_.target_date), s_.forecast, st, label=m)\n    ax.set_title(f\"h = {h}: RSAFS YoY growth (%), target months\")\n    ax.set_ylabel(\"percent\"); ax.grid(alpha=.3)\naxes[0].legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.3f} \"\n          f\"p={res[f'dm_pvalue_h{h}']:.4f} -> {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets\", round(res[\"mean_abs_revision_h1_targets\"], 6))\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":810,"cache_read_input_tokens":32839,"output_tokens":5312,"output_tokens_details":{"thinking_tokens":386},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":810},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXswM2YcDqV5KC1C9JQX","requestRef":"c9d401b1-ce88-4f2e-893d-7ce67198a6b9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5ad915fc-d540-44d7-a029-8f5495cce5ea","timestamp":"2026-10-30T05:36:22.781Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}65{"parentUuid":"5ad915fc-d540-44d7-a029-8f5495cce5ea","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RT0015/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01XpRLuQcyaZMU7e2dXZNYC3"}]},"uuid":"ee46fc7e-9353-4c0a-b001-839bfcfc8da4","timestamp":"2026-10-30T05:36:22.845Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RT0015/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"5ad915fc-d540-44d7-a029-8f5495cce5ea","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}66{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"c0113cde44db1d304a3d4c7281965f6a279b2763a17344f38837e39045bfbb59","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01XpRLuQcyaZMU7e2dXZNYC3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail sales YoY growth (RSAFS).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png.\nDeterministic: no random numbers are used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\nMODEL_NAME = \"rw_drift_base_effect\"\nMODEL_DESCRIPTION = (\n    \"Random walk with drift for the log level of RSAFS, translated into YoY growth so that the known \"\n    \"'base effects' (the monthly changes that drop out of the 12-month window) are used. At origin V, \"\n    \"with x_m = ln L_m from the RSAFS vintage dated V and l = last(V): drift d = (x_l - x_{l-12})/12 \"\n    \"(mean monthly log change over the last 12 published months, i.e. a rolling 12-month estimation window); \"\n    \"forecast of the log level x_{l+h} = x_l + h*d; forecast YoY g_{l+h} = 100*(x_l + h*d - x_{l+h-12}), \"\n    \"where x_{l+h-12} (h<=3) is already published in vintage V. Uses only the RSAFS vintage dated V; \"\n    \"PAYEMS and UMCSENT are not used. The specification (including the 12-month drift window) was fixed \"\n    \"before any forecast error was computed; no parameter was tuned on the evaluation targets.\")\n\n\ndef ms(s):  # month start Timestamp\n    return pd.Timestamp(s).to_period(\"M\").to_timestamp()\n\n\ndef read_series(path):\n    d = pd.read_csv(path)\n    s = pd.Series(d.iloc[:, 1].values.astype(float), index=pd.to_datetime(d.iloc[:, 0]))\n    return s, len(d)\n\n\ndef yoy(level):\n    x = np.log(level)\n    return 100.0 * (x - x.shift(12, freq=\"MS\")).reindex(level.index)\n\n\nn_input_rows = {}\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\nn_input_rows[\"first_release.csv\"] = len(fr)\nactual = fr.set_index(\"target_month\")[\"yoy_first_release\"]\n\nrows, data_issues_auto = [], []\nlast_months = {}\nfor V in ORIGINS:\n    lv, n = read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/RSAFS_vintage_{V}.csv\"] = n\n    # PAYEMS vintage is read only for the row count/audit; not used in any forecast.\n    _, npay = read_series(os.path.join(DATA, \"vintages\", f\"PAYEMS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/PAYEMS_vintage_{V}.csv\"] = npay\n    assert lv.index.max() <= pd.Timestamp(V), \"vintage contains months after origin\"\n    assert not lv.isna().any()\n    last = lv.index.max()\n    last_months[V] = last\n    g = yoy(lv)\n    x = np.log(lv)\n    # AR(1): OLS of g_m on const, g_{m-1}, 1993-02 <= m <= last\n    gs = g.loc[\"1993-01-01\":last]\n    y = gs.loc[\"1993-02-01\":].values\n    ylag = gs.shift(1).loc[\"1993-02-01\":].values\n    X = np.column_stack([np.ones_like(ylag), ylag])\n    a, b = np.linalg.lstsq(X, y, rcond=None)[0]\n    d = (x[last] - x[last - pd.DateOffset(months=12)]) / 12.0\n    for h in HORIZONS:\n        T = last + pd.DateOffset(months=h)\n        T12 = T - pd.DateOffset(months=12)\n        f = {}\n        f[\"naive\"] = g[last]\n        f[\"snaive\"] = g[T12]\n        fa = g[last]\n        for _ in range(h):\n            fa = a + b * fa\n        f[\"ar1\"] = fa\n        f[\"model\"] = 100.0 * (x[last] + h * d - x[T12])\n        for m in MODELS:\n            rows.append(dict(origin_date=V, target_date=T.strftime(\"%Y-%m-%d\"), horizon=h,\n                             forecast=float(f[m]), actual_first_release=float(actual[T]),\n                             model=m, vintage_used=V))\n\nfc = pd.DataFrame(rows)\nfc = fc.sort_values([\"horizon\", \"model\", \"origin_date\"]).reset_index(drop=True)\nfc[\"error\"] = fc[\"actual_first_release\"] - fc[\"forecast\"]\nfc.drop(columns=\"error\").to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False, float_format=\"%.6f\")\n\nres = {\"task_id\": \"T1-forecast\", \"model_name\": MODEL_NAME, \"model_description\": MODEL_DESCRIPTION,\n       \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\ntab = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)][\"error\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        tab.append(dict(model=m, horizon=h, rmse=rmse, mae=mae, n=len(e)))\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n\ndef dm_test(e_naive, e_model, h):\n    dd = e_naive ** 2 - e_model ** 2\n    n = len(dd)\n    dbar = dd.mean()\n    dc = dd - dbar\n    lrv = np.sum(dc * dc) / n\n    for j in range(1, h):  # Bartlett weights, truncation lag h-1\n        w = 1.0 - j / h\n        lrv += 2.0 * w * np.sum(dc[j:] * dc[:-j]) / n\n    stat = dbar / np.sqrt(lrv / n)\n    p = 2.0 * (1.0 - stats.norm.cdf(abs(stat)))\n    return float(stat), float(p), float(lrv), float(dbar)\n\n\ndm_extra = {}\nfor h in HORIZONS:\n    en = fc[(fc.model == \"naive\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    em = fc[(fc.model == \"model\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    res[f\"rel_improvement_rmse_h{h}\"] = 1.0 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    s, p, lrv, dbar = dm_test(en, em, h)\n    assert lrv > 0\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = s, p\n    dm_extra[h] = (lrv, dbar)\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    sig = \"significant\" if p < 0.05 else \"not_significant\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n\n# (d) revision: current vintage growth vs first release, h=1 targets (RSAFS_current used ONLY here)\ncur, ncur = read_series(os.path.join(DATA, \"RSAFS_current.csv\"))\nn_input_rows[\"RSAFS_current.csv\"] = ncur\ngcur = yoy(cur)\nt1 = fc[(fc.model == \"naive\") & (fc.horizon == 1)][\"target_date\"].map(pd.Timestamp)\nrev = pd.DataFrame({\"target\": t1.values, \"g_current\": gcur.reindex(t1.values).values,\n                    \"first_release\": actual.reindex(t1.values).values})\nrev[\"abs_rev\"] = (rev.g_current - rev.first_release).abs()\nres[\"mean_abs_revision_h1_targets\"] = float(rev[\"abs_rev\"].mean())\n\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nlag = {V: (pd.Timestamp(V).to_period(\"M\") - last_months[V].to_period(\"M\")).n for V in ORIGINS}\nres[\"data_issues\"] = [\n    {\"issue\": \"Irregular RSAFS publication timing: last(V) is 2 months before the origin month for origins \"\n              + \", \".join(V for V in ORIGINS if lag[V] == 2) + \" and 1 month for the others; the 2026-04-30 vintage added two months at once.\",\n     \"handling\": \"Targets defined as last(V)+h exactly as TASK.md requires; each forecast uses only the vintage dated V (vintage_used = origin_date).\"},\n    {\"issue\": \"First-release dating is at month-end granularity: 2025-09 first appears in the 2025-11-30 vintage, and 2026-02 and 2026-03 both first appear in the 2026-04-30 vintage (so the 2026-02 'first release' is not the advance estimate).\",\n     \"handling\": \"first_release.csv used as provided (task definition of the actual); documented in the report.\"},\n    {\"issue\": \"Large level revision: RSAFS levels in the current vintage are about 4.7-4.9% below those of the 2026-07-31 vintage for 2025-2026 months (first_release rows for 2026-08/09 already use the revised base).\",\n     \"handling\": \"YoY growth is always computed within a single vintage (levels never mixed across vintages); the revision enters only estimand (d).\"},\n    {\"issue\": \"UMCSENT has 210 empty values, all before 1978 (quarterly survey era).\",\n     \"handling\": \"UMCSENT not used by the model; no imputation needed.\"},\n    {\"issue\": \"RSAFS_current.csv contains information not available at any forecast origin.\",\n     \"handling\": \"Read only in the revision block for estimand (d), after all forecasts are produced.\"},\n]\nn_input_rows[\"UMCSENT.csv\"] = len(pd.read_csv(os.path.join(DATA, \"UMCSENT.csv\")))  # audited, not used in forecasts\nres[\"n_input_rows\"] = dict(sorted(n_input_rows.items()))\nres[\"n_analysed\"] = int(len(fc[fc.model == \"model\"]))\nres[\"random_seed\"] = None\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\n# auxiliary (non-required) diagnostics for the report\naux = {\"dm_long_run_variance\": {f\"h{h}\": dm_extra[h][0] for h in HORIZONS},\n       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},\n       \"revision_by_target\": rev.assign(target=rev.target.dt.strftime(\"%Y-%m\")).round(6).to_dict(\"records\"),\n       \"last_month_by_origin\": {V: last_months[V].strftime(\"%Y-%m\") for V in ORIGINS}}\nos.makedirs(os.path.join(OUT, \"state\"), exist_ok=True)\nwith open(os.path.join(OUT, \"state\", \"aux_diagnostics.json\"), \"w\") as fh:\n    json.dump(aux, fh, indent=2)\n\n# Figure\nfig, axes = plt.subplots(2, 1, figsize=(8, 7), sharex=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc[fc.horizon == h]\n    a_ = sub[sub.model == \"naive\"].sort_values(\"target_date\")\n    ax.plot(pd.to_datetime(a_.target_date), a_.actual_first_release, \"k-o\", label=\"first release (actual)\")\n    for m, st in [(\"naive\", \"C0--s\"), (\"model\", \"C3-^\"), (\"ar1\", \"C2:x\")]:\n        s_ = sub[sub.model == m].sort_values(\"target_date\")\n        ax.plot(pd.to_datetime(s_.target_date), s_.forecast, st, label=m)\n    ax.set_title(f\"h = {h}: RSAFS YoY growth (%), target months\")\n    ax.set_ylabel(\"percent\"); ax.grid(alpha=.3)\naxes[0].legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.3f} \"\n          f\"p={res[f'dm_pvalue_h{h}']:.4f} -> {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets\", round(res[\"mean_abs_revision_h1_targets\"], 6))\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"}}]}}67{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"d5abf560-ac1e-429b-9572-0fcdb2031ea0","timestamp":"2026-10-30T05:36:22.848Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"c9d401b1-ce88-4f2e-893d-7ce67198a6b9","keep":20,"tail":["c0113cde44db1d304a3d4c7281965f6a279b2763a17344f38837e39045bfbb59","6aa2ff52fe77f94c141ab99042e17185c73af357bf43cac8625ccec961d5c326"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c9fb43ca1872d3ef8544b572152d8560201bd2d7d1b8be1d2104f4449839cd96"}68{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"ee46fc7e-9353-4c0a-b001-839bfcfc8da4","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}69{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}70{"parentUuid":"ee46fc7e-9353-4c0a-b001-839bfcfc8da4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXszTxMpT3kwfW9aKkT3","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5474,"cache_read_input_tokens":33649,"output_tokens":147,"output_tokens_details":{"thinking_tokens":38},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5474},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":421,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXszTgyVxyNgeQ99kc1S","requestRef":"d5abf560-ac1e-429b-9572-0fcdb2031ea0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3e540c7d-f237-45eb-aa3a-f5a20f5f8a5d","timestamp":"2026-10-30T05:36:24.088Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}71{"parentUuid":"3e540c7d-f237-45eb-aa3a-f5a20f5f8a5d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXszTxMpT3kwfW9aKkT3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NWBPRW1kzdDModa5bjjfBv","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0015 && ls out out/state","description":"Return to root and list out"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5474,"cache_read_input_tokens":33649,"output_tokens":147,"output_tokens_details":{"thinking_tokens":38},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5474},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXszTgyVxyNgeQ99kc1S","requestRef":"d5abf560-ac1e-429b-9572-0fcdb2031ea0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4d335db7-3b0c-43d7-bd23-610517bf8a5d","timestamp":"2026-10-30T05:36:24.494Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}72{"parentUuid":"4d335db7-3b0c-43d7-bd23-610517bf8a5d","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01NWBPRW1kzdDModa5bjjfBv","type":"tool_result","content":"out:\nexclusions.csv\nstate\n\nout/state:\ncontract.md\ndata_audit.md\nlog.md\nphases.json","is_error":false}]},"uuid":"346af992-40db-46fe-9729-0f597a141c9c","timestamp":"2026-10-30T05:36:24.535Z","toolUseResult":{"stdout":"out:\nexclusions.csv\nstate\n\nout/state:\ncontract.md\ndata_audit.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4d335db7-3b0c-43d7-bd23-610517bf8a5d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}73{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"4637f6389a203d5a44f1c64d73c274fb85a9acb8d21af68a0838cd4274115c66","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01NWBPRW1kzdDModa5bjjfBv","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0015 && ls out out/state","description":"Return to root and list out"}}]}}74{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"7a44804e-bda7-4f2b-832a-428b23336baf","timestamp":"2026-10-30T05:36:24.539Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"d5abf560-ac1e-429b-9572-0fcdb2031ea0","keep":22,"tail":["4637f6389a203d5a44f1c64d73c274fb85a9acb8d21af68a0838cd4274115c66","043b9ddfc80b4f70c27aa4e9228f269434c4cae8cc44c50bc58d0488ced48d90"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"dc1bfc84246c1d0381cebc212fa628f88ef2abcab3a277865a9ba2a8c645690c"}75{"parentUuid":"346af992-40db-46fe-9729-0f597a141c9c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXszbZzyovcKHo8Rfzej","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":190,"cache_read_input_tokens":39123,"output_tokens":4980,"output_tokens_details":{"thinking_tokens":29},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":190},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":265,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXszatZi7fMPzVjwW5Zw","requestRef":"7a44804e-bda7-4f2b-832a-428b23336baf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3d893073-0242-4bbd-8262-117811b0b68f","timestamp":"2026-10-30T05:36:25.837Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}76{"parentUuid":"3d893073-0242-4bbd-8262-117811b0b68f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXszbZzyovcKHo8Rfzej","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0118HQcuFfbZ4u8dcUv49cWK","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail sales YoY growth (RSAFS).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png\n(and the auxiliary diagnostics file out/state/aux_diagnostics.json).\nDeterministic: no random numbers are used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\nMODEL_NAME = \"rw_drift_base_effect\"\nMODEL_DESCRIPTION = (\n    \"Random walk with drift for the log level of RSAFS, translated into YoY growth so that the known \"\n    \"'base effects' (the monthly changes that drop out of the 12-month window) are used. At origin V, \"\n    \"with x_m = ln L_m from the RSAFS vintage dated V and l = last(V): drift d = (x_l - x_{l-12})/12 \"\n    \"(mean monthly log change over the last 12 published months, i.e. a rolling 12-month estimation window); \"\n    \"forecast of the log level x_{l+h} = x_l + h*d; forecast YoY g_{l+h} = 100*(x_l + h*d - x_{l+h-12}), \"\n    \"where x_{l+h-12} (h<=3) is already published in vintage V. Uses only the RSAFS vintage dated V; \"\n    \"PAYEMS and UMCSENT are not used. The specification (including the 12-month drift window) was fixed \"\n    \"before any forecast error was computed; no parameter was tuned on the evaluation targets.\")\n\n\ndef read_series(path):\n    d = pd.read_csv(path)\n    s = pd.Series(d.iloc[:, 1].values.astype(float), index=pd.to_datetime(d.iloc[:, 0]))\n    return s, len(d)\n\n\ndef yoy(level):\n    x = np.log(level)\n    return 100.0 * (x - x.shift(12, freq=\"MS\")).reindex(level.index)\n\n\nn_input_rows = {}\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\nn_input_rows[\"first_release.csv\"] = len(fr)\nactual = fr.set_index(\"target_month\")[\"yoy_first_release\"]\n\nrows = []\nlast_months = {}\nfor V in ORIGINS:\n    lv, n = read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/RSAFS_vintage_{V}.csv\"] = n\n    # PAYEMS vintage is read only for the row count/audit; not used in any forecast.\n    _, npay = read_series(os.path.join(DATA, \"vintages\", f\"PAYEMS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/PAYEMS_vintage_{V}.csv\"] = npay\n    assert lv.index.max() <= pd.Timestamp(V), \"vintage contains months after origin\"\n    assert not lv.isna().any()\n    last = lv.index.max()\n    last_months[V] = last\n    g = yoy(lv)\n    x = np.log(lv)\n    # AR(1): OLS of g_m on const, g_{m-1}, 1993-02 <= m <= last\n    gs = g.loc[\"1993-01-01\":last]\n    y = gs.loc[\"1993-02-01\":].values\n    ylag = gs.shift(1).loc[\"1993-02-01\":].values\n    X = np.column_stack([np.ones_like(ylag), ylag])\n    a, b = np.linalg.lstsq(X, y, rcond=None)[0]\n    d = (x[last] - x[last - pd.DateOffset(months=12)]) / 12.0\n    for h in HORIZONS:\n        T = last + pd.DateOffset(months=h)\n        T12 = T - pd.DateOffset(months=12)\n        f = {}\n        f[\"naive\"] = g[last]\n        f[\"snaive\"] = g[T12]\n        fa = g[last]\n        for _ in range(h):\n            fa = a + b * fa\n        f[\"ar1\"] = fa\n        f[\"model\"] = 100.0 * (x[last] + h * d - x[T12])\n        for m in MODELS:\n            rows.append(dict(origin_date=V, target_date=T.strftime(\"%Y-%m-%d\"), horizon=h,\n                             forecast=float(f[m]), actual_first_release=float(actual[T]),\n                             model=m, vintage_used=V))\n\nfc = pd.DataFrame(rows)\nfc = fc.sort_values([\"horizon\", \"model\", \"origin_date\"]).reset_index(drop=True)\nfc[\"error\"] = fc[\"actual_first_release\"] - fc[\"forecast\"]\nfc.drop(columns=\"error\").to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False, float_format=\"%.6f\")\n\nres = {\"task_id\": \"T1-forecast\", \"model_name\": MODEL_NAME, \"model_description\": MODEL_DESCRIPTION,\n       \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\ntab = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)][\"error\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        tab.append(dict(model=m, horizon=h, rmse=rmse, mae=mae, n=len(e)))\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n\ndef dm_test(e_naive, e_model, h):\n    dd = e_naive ** 2 - e_model ** 2\n    n = len(dd)\n    dbar = dd.mean()\n    dc = dd - dbar\n    lrv = np.sum(dc * dc) / n\n    for j in range(1, h):  # Bartlett weights 1 - j/h, truncation lag h-1\n        w = 1.0 - j / h\n        lrv += 2.0 * w * np.sum(dc[j:] * dc[:-j]) / n\n    stat = dbar / np.sqrt(lrv / n)\n    p = 2.0 * (1.0 - stats.norm.cdf(abs(stat)))\n    return float(stat), float(p), float(lrv), float(dbar)\n\n\ndm_extra = {}\nfor h in HORIZONS:\n    en = fc[(fc.model == \"naive\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    em = fc[(fc.model == \"model\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    res[f\"rel_improvement_rmse_h{h}\"] = 1.0 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    s, p, lrv, dbar = dm_test(en, em, h)\n    assert lrv > 0\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = s, p\n    dm_extra[h] = (lrv, dbar)\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    sig = \"significant\" if p < 0.05 else \"not_significant\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n\n# (d) revision: current-vintage growth vs first release, h=1 targets (RSAFS_current used ONLY here)\ncur, ncur = read_series(os.path.join(DATA, \"RSAFS_current.csv\"))\nn_input_rows[\"RSAFS_current.csv\"] = ncur\ngcur = yoy(cur)\nt1 = fc[(fc.model == \"naive\") & (fc.horizon == 1)][\"target_date\"].map(pd.Timestamp)\nrev = pd.DataFrame({\"target\": t1.values, \"g_current\": gcur.reindex(t1.values).values,\n                    \"first_release\": actual.reindex(t1.values).values})\nrev[\"abs_rev\"] = (rev.g_current - rev.first_release).abs()\nres[\"mean_abs_revision_h1_targets\"] = float(rev[\"abs_rev\"].mean())\n\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nlag = {V: (pd.Timestamp(V).to_period(\"M\") - last_months[V].to_period(\"M\")).n for V in ORIGINS}\nres[\"data_issues\"] = [\n    {\"issue\": \"Irregular RSAFS publication timing: last(V) is 2 months before the origin month for origins \"\n              + \", \".join(V for V in ORIGINS if lag[V] == 2)\n              + \" and 1 month before it for the others; the 2026-04-30 vintage added two months at once.\",\n     \"handling\": \"Targets defined as last(V)+h exactly as TASK.md requires; each forecast uses only the vintage dated V (vintage_used = origin_date).\"},\n    {\"issue\": \"First-release dating is at month-end granularity: 2025-09 first appears in the 2025-11-30 vintage, and 2026-02 and 2026-03 both first appear in the 2026-04-30 vintage (so the 2026-02 'first release' need not be the advance estimate).\",\n     \"handling\": \"first_release.csv used as provided (task definition of the actual); documented in the report.\"},\n    {\"issue\": \"Large level revision: RSAFS levels in the current vintage are about 4.7-4.9% below those of the 2026-07-31 vintage for 2025-2026 months (first_release rows for 2026-08/09 already use the revised level base).\",\n     \"handling\": \"YoY growth is always computed within a single vintage (levels never mixed across vintages); the revision enters only estimand (d).\"},\n    {\"issue\": \"UMCSENT has 210 empty values, all before 1978 (quarterly survey era).\",\n     \"handling\": \"UMCSENT is not used by the model; no imputation needed.\"},\n    {\"issue\": \"RSAFS_current.csv contains information not available at any forecast origin.\",\n     \"handling\": \"Read only in the revision block for estimand (d), after all forecasts are produced.\"},\n]\nn_input_rows[\"UMCSENT.csv\"] = len(pd.read_csv(os.path.join(DATA, \"UMCSENT.csv\")))  # audited, not used in forecasts\nres[\"n_input_rows\"] = dict(sorted(n_input_rows.items()))\nres[\"n_analysed\"] = int(len(fc[fc.model == \"model\"]))\nres[\"random_seed\"] = None\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\n# auxiliary (non-required) diagnostics cited in the report\naux = {\"dm_long_run_variance\": {f\"h{h}\": dm_extra[h][0] for h in HORIZONS},\n       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},\n       \"revision_by_target\": rev.assign(target=rev.target.dt.strftime(\"%Y-%m\")).round(6).to_dict(\"records\"),\n       \"last_month_by_origin\": {V: last_months[V].strftime(\"%Y-%m\") for V in ORIGINS}}\nos.makedirs(os.path.join(OUT, \"state\"), exist_ok=True)\nwith open(os.path.join(OUT, \"state\", \"aux_diagnostics.json\"), \"w\") as fh:\n    json.dump(aux, fh, indent=2)\n\n# Figure\nfig, axes = plt.subplots(2, 1, figsize=(8, 7), sharex=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc[fc.horizon == h]\n    a_ = sub[sub.model == \"naive\"].sort_values(\"target_date\")\n    ax.plot(pd.to_datetime(a_.target_date), a_.actual_first_release, \"k-o\", label=\"first release (actual)\")\n    for m, st in [(\"naive\", \"C0--s\"), (\"model\", \"C3-^\"), (\"ar1\", \"C2:x\")]:\n        s_ = sub[sub.model == m].sort_values(\"target_date\")\n        ax.plot(pd.to_datetime(s_.target_date), s_.forecast, st, label=m)\n    ax.set_title(f\"h = {h}: RSAFS YoY growth (%), by target month\")\n    ax.set_ylabel(\"percent\"); ax.grid(alpha=.3)\naxes[0].legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.3f} \"\n          f\"p={res[f'dm_pvalue_h{h}']:.4f} -> {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets\", round(res[\"mean_abs_revision_h1_targets\"], 6))\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script from root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":190,"cache_read_input_tokens":39123,"output_tokens":4980,"output_tokens_details":{"thinking_tokens":29},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":190},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXszatZi7fMPzVjwW5Zw","requestRef":"7a44804e-bda7-4f2b-832a-428b23336baf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"95c1d714-ad93-4d7e-bbb9-7a26419de653","timestamp":"2026-10-30T05:36:56.886Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}77{"parentUuid":"95c1d714-ad93-4d7e-bbb9-7a26419de653","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0118HQcuFfbZ4u8dcUv49cWK","type":"tool_result","content":" model  horizon     rmse      mae  n\n naive        1 0.996874 0.848722 10\n naive        3 1.420040 1.200449 10\nsnaive        1 1.674543 1.306670 10\nsnaive        3 1.316079 1.065869 10\n   ar1        1 0.940524 0.797651 10\n   ar1        3 1.187118 0.952690 10\n model        1 0.550298 0.486332 10\n model        3 1.142220 0.933977 10\nh=1: rel_impr=0.4480 DM=2.429 p=0.0151 -> model_better_significant\nh=3: rel_impr=0.1956 DM=1.547 p=0.1220 -> model_better_not_significant\nmean_abs_revision_h1_targets 0.54822","is_error":false}]},"uuid":"e6981bfe-b9ec-4881-b835-b6ca9a4320ac","timestamp":"2026-10-30T05:36:57.647Z","toolUseResult":{"stdout":" model  horizon     rmse      mae  n\n naive        1 0.996874 0.848722 10\n naive        3 1.420040 1.200449 10\nsnaive        1 1.674543 1.306670 10\nsnaive        3 1.316079 1.065869 10\n   ar1        1 0.940524 0.797651 10\n   ar1        3 1.187118 0.952690 10\n model        1 0.550298 0.486332 10\n model        3 1.142220 0.933977 10\nh=1: rel_impr=0.4480 DM=2.429 p=0.0151 -> model_better_significant\nh=3: rel_impr=0.1956 DM=1.547 p=0.1220 -> model_better_not_significant\nmean_abs_revision_h1_targets 0.54822","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"95c1d714-ad93-4d7e-bbb9-7a26419de653","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}78{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"ba3bb920f903244977ea055013cf04a820efc2d595df357ec28227d3caf191d5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_0118HQcuFfbZ4u8dcUv49cWK","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail sales YoY growth (RSAFS).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png\n(and the auxiliary diagnostics file out/state/aux_diagnostics.json).\nDeterministic: no random numbers are used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\nMODEL_NAME = \"rw_drift_base_effect\"\nMODEL_DESCRIPTION = (\n    \"Random walk with drift for the log level of RSAFS, translated into YoY growth so that the known \"\n    \"'base effects' (the monthly changes that drop out of the 12-month window) are used. At origin V, \"\n    \"with x_m = ln L_m from the RSAFS vintage dated V and l = last(V): drift d = (x_l - x_{l-12})/12 \"\n    \"(mean monthly log change over the last 12 published months, i.e. a rolling 12-month estimation window); \"\n    \"forecast of the log level x_{l+h} = x_l + h*d; forecast YoY g_{l+h} = 100*(x_l + h*d - x_{l+h-12}), \"\n    \"where x_{l+h-12} (h<=3) is already published in vintage V. Uses only the RSAFS vintage dated V; \"\n    \"PAYEMS and UMCSENT are not used. The specification (including the 12-month drift window) was fixed \"\n    \"before any forecast error was computed; no parameter was tuned on the evaluation targets.\")\n\n\ndef read_series(path):\n    d = pd.read_csv(path)\n    s = pd.Series(d.iloc[:, 1].values.astype(float), index=pd.to_datetime(d.iloc[:, 0]))\n    return s, len(d)\n\n\ndef yoy(level):\n    x = np.log(level)\n    return 100.0 * (x - x.shift(12, freq=\"MS\")).reindex(level.index)\n\n\nn_input_rows = {}\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\nn_input_rows[\"first_release.csv\"] = len(fr)\nactual = fr.set_index(\"target_month\")[\"yoy_first_release\"]\n\nrows = []\nlast_months = {}\nfor V in ORIGINS:\n    lv, n = read_series(os.path.join(DATA, \"vintages\", f\"RSAFS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/RSAFS_vintage_{V}.csv\"] = n\n    # PAYEMS vintage is read only for the row count/audit; not used in any forecast.\n    _, npay = read_series(os.path.join(DATA, \"vintages\", f\"PAYEMS_vintage_{V}.csv\"))\n    n_input_rows[f\"vintages/PAYEMS_vintage_{V}.csv\"] = npay\n    assert lv.index.max() <= pd.Timestamp(V), \"vintage contains months after origin\"\n    assert not lv.isna().any()\n    last = lv.index.max()\n    last_months[V] = last\n    g = yoy(lv)\n    x = np.log(lv)\n    # AR(1): OLS of g_m on const, g_{m-1}, 1993-02 <= m <= last\n    gs = g.loc[\"1993-01-01\":last]\n    y = gs.loc[\"1993-02-01\":].values\n    ylag = gs.shift(1).loc[\"1993-02-01\":].values\n    X = np.column_stack([np.ones_like(ylag), ylag])\n    a, b = np.linalg.lstsq(X, y, rcond=None)[0]\n    d = (x[last] - x[last - pd.DateOffset(months=12)]) / 12.0\n    for h in HORIZONS:\n        T = last + pd.DateOffset(months=h)\n        T12 = T - pd.DateOffset(months=12)\n        f = {}\n        f[\"naive\"] = g[last]\n        f[\"snaive\"] = g[T12]\n        fa = g[last]\n        for _ in range(h):\n            fa = a + b * fa\n        f[\"ar1\"] = fa\n        f[\"model\"] = 100.0 * (x[last] + h * d - x[T12])\n        for m in MODELS:\n            rows.append(dict(origin_date=V, target_date=T.strftime(\"%Y-%m-%d\"), horizon=h,\n                             forecast=float(f[m]), actual_first_release=float(actual[T]),\n                             model=m, vintage_used=V))\n\nfc = pd.DataFrame(rows)\nfc = fc.sort_values([\"horizon\", \"model\", \"origin_date\"]).reset_index(drop=True)\nfc[\"error\"] = fc[\"actual_first_release\"] - fc[\"forecast\"]\nfc.drop(columns=\"error\").to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False, float_format=\"%.6f\")\n\nres = {\"task_id\": \"T1-forecast\", \"model_name\": MODEL_NAME, \"model_description\": MODEL_DESCRIPTION,\n       \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1]}\ntab = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)][\"error\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        tab.append(dict(model=m, horizon=h, rmse=rmse, mae=mae, n=len(e)))\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n\ndef dm_test(e_naive, e_model, h):\n    dd = e_naive ** 2 - e_model ** 2\n    n = len(dd)\n    dbar = dd.mean()\n    dc = dd - dbar\n    lrv = np.sum(dc * dc) / n\n    for j in range(1, h):  # Bartlett weights 1 - j/h, truncation lag h-1\n        w = 1.0 - j / h\n        lrv += 2.0 * w * np.sum(dc[j:] * dc[:-j]) / n\n    stat = dbar / np.sqrt(lrv / n)\n    p = 2.0 * (1.0 - stats.norm.cdf(abs(stat)))\n    return float(stat), float(p), float(lrv), float(dbar)\n\n\ndm_extra = {}\nfor h in HORIZONS:\n    en = fc[(fc.model == \"naive\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    em = fc[(fc.model == \"model\") & (fc.horizon == h)].sort_values(\"origin_date\")[\"error\"].values\n    res[f\"rel_improvement_rmse_h{h}\"] = 1.0 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    s, p, lrv, dbar = dm_test(en, em, h)\n    assert lrv > 0\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = s, p\n    dm_extra[h] = (lrv, dbar)\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    sig = \"significant\" if p < 0.05 else \"not_significant\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n\n# (d) revision: current-vintage growth vs first release, h=1 targets (RSAFS_current used ONLY here)\ncur, ncur = read_series(os.path.join(DATA, \"RSAFS_current.csv\"))\nn_input_rows[\"RSAFS_current.csv\"] = ncur\ngcur = yoy(cur)\nt1 = fc[(fc.model == \"naive\") & (fc.horizon == 1)][\"target_date\"].map(pd.Timestamp)\nrev = pd.DataFrame({\"target\": t1.values, \"g_current\": gcur.reindex(t1.values).values,\n                    \"first_release\": actual.reindex(t1.values).values})\nrev[\"abs_rev\"] = (rev.g_current - rev.first_release).abs()\nres[\"mean_abs_revision_h1_targets\"] = float(rev[\"abs_rev\"].mean())\n\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nlag = {V: (pd.Timestamp(V).to_period(\"M\") - last_months[V].to_period(\"M\")).n for V in ORIGINS}\nres[\"data_issues\"] = [\n    {\"issue\": \"Irregular RSAFS publication timing: last(V) is 2 months before the origin month for origins \"\n              + \", \".join(V for V in ORIGINS if lag[V] == 2)\n              + \" and 1 month before it for the others; the 2026-04-30 vintage added two months at once.\",\n     \"handling\": \"Targets defined as last(V)+h exactly as TASK.md requires; each forecast uses only the vintage dated V (vintage_used = origin_date).\"},\n    {\"issue\": \"First-release dating is at month-end granularity: 2025-09 first appears in the 2025-11-30 vintage, and 2026-02 and 2026-03 both first appear in the 2026-04-30 vintage (so the 2026-02 'first release' need not be the advance estimate).\",\n     \"handling\": \"first_release.csv used as provided (task definition of the actual); documented in the report.\"},\n    {\"issue\": \"Large level revision: RSAFS levels in the current vintage are about 4.7-4.9% below those of the 2026-07-31 vintage for 2025-2026 months (first_release rows for 2026-08/09 already use the revised level base).\",\n     \"handling\": \"YoY growth is always computed within a single vintage (levels never mixed across vintages); the revision enters only estimand (d).\"},\n    {\"issue\": \"UMCSENT has 210 empty values, all before 1978 (quarterly survey era).\",\n     \"handling\": \"UMCSENT is not used by the model; no imputation needed.\"},\n    {\"issue\": \"RSAFS_current.csv contains information not available at any forecast origin.\",\n     \"handling\": \"Read only in the revision block for estimand (d), after all forecasts are produced.\"},\n]\nn_input_rows[\"UMCSENT.csv\"] = len(pd.read_csv(os.path.join(DATA, \"UMCSENT.csv\")))  # audited, not used in forecasts\nres[\"n_input_rows\"] = dict(sorted(n_input_rows.items()))\nres[\"n_analysed\"] = int(len(fc[fc.model == \"model\"]))\nres[\"random_seed\"] = None\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\n# auxiliary (non-required) diagnostics cited in the report\naux = {\"dm_long_run_variance\": {f\"h{h}\": dm_extra[h][0] for h in HORIZONS},\n       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},\n       \"revision_by_target\": rev.assign(target=rev.target.dt.strftime(\"%Y-%m\")).round(6).to_dict(\"records\"),\n       \"last_month_by_origin\": {V: last_months[V].strftime(\"%Y-%m\") for V in ORIGINS}}\nos.makedirs(os.path.join(OUT, \"state\"), exist_ok=True)\nwith open(os.path.join(OUT, \"state\", \"aux_diagnostics.json\"), \"w\") as fh:\n    json.dump(aux, fh, indent=2)\n\n# Figure\nfig, axes = plt.subplots(2, 1, figsize=(8, 7), sharex=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc[fc.horizon == h]\n    a_ = sub[sub.model == \"naive\"].sort_values(\"target_date\")\n    ax.plot(pd.to_datetime(a_.target_date), a_.actual_first_release, \"k-o\", label=\"first release (actual)\")\n    for m, st in [(\"naive\", \"C0--s\"), (\"model\", \"C3-^\"), (\"ar1\", \"C2:x\")]:\n        s_ = sub[sub.model == m].sort_values(\"target_date\")\n        ax.plot(pd.to_datetime(s_.target_date), s_.forecast, st, label=m)\n    ax.set_title(f\"h = {h}: RSAFS YoY growth (%), by target month\")\n    ax.set_ylabel(\"percent\"); ax.grid(alpha=.3)\naxes[0].legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.3f} \"\n          f\"p={res[f'dm_pvalue_h{h}']:.4f} -> {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets\", round(res[\"mean_abs_revision_h1_targets\"], 6))\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script from root"}}]}}79{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"727109f5-b044-477f-8792-c8811a34ace1","timestamp":"2026-10-30T05:36:57.649Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"7a44804e-bda7-4f2b-832a-428b23336baf","keep":24,"tail":["ba3bb920f903244977ea055013cf04a820efc2d595df357ec28227d3caf191d5","ae6e5b640c923593d0b1592be721b91a31ee0ec5c0ff1b1386c039d6b34e6d9f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"955acc6f6451f8352d8d993b8b1135372e6cbc7a79f6e079fb09a91c4c4849db"}80{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e6981bfe-b9ec-4881-b835-b6ca9a4320ac","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}81{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}82{"parentUuid":"e6981bfe-b9ec-4881-b835-b6ca9a4320ac","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt32k85dFQjxjaZ9Tjh","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5213,"cache_read_input_tokens":39313,"output_tokens":1026,"output_tokens_details":{"thinking_tokens":340},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5213},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3460,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt32TWPCbLwkhzueMU6","requestRef":"727109f5-b044-477f-8792-c8811a34ace1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"32002379-8bb1-4d52-ba00-d23a5be2c46c","timestamp":"2026-10-30T05:37:02.011Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}83{"parentUuid":"32002379-8bb1-4d52-ba00-d23a5be2c46c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt32k85dFQjxjaZ9Tjh","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FTjodjj4x5vns4p2xqntAm","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    dm_extra[h] = (lrv, dbar)''','''    nn = len(en)\n    hln = np.sqrt((nn + 1 - 2 * h + h * (h - 1) / nn) / nn)\n    dm_extra[h] = (lrv, dbar, s * hln, float(2 * (1 - stats.t.cdf(abs(s * hln), df=nn - 1))),\n                   [float(v) for v in (en ** 2 - em ** 2)], int(np.sum(em ** 2 < en ** 2)))''')\ns=s.replace('''       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},''','''       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},\n       \"sensitivity_dm_hln_stat\": {f\"h{h}\": dm_extra[h][2] for h in HORIZONS},\n       \"sensitivity_dm_hln_pvalue_t_nminus1\": {f\"h{h}\": dm_extra[h][3] for h in HORIZONS},\n       \"loss_diff_by_origin\": {f\"h{h}\": dm_extra[h][4] for h in HORIZONS},\n       \"n_origins_model_sq_error_below_naive\": {f\"h{h}\": dm_extra[h][5] for h in HORIZONS},''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cat out/state/aux_diagnostics.json | head -60; head -5 out/forecasts.csv","description":"Add HLN sensitivity diagnostics and rerun"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5213,"cache_read_input_tokens":39313,"output_tokens":1026,"output_tokens_details":{"thinking_tokens":340},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":5213},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt32TWPCbLwkhzueMU6","requestRef":"727109f5-b044-477f-8792-c8811a34ace1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7b59c64a-1adc-487e-a6d0-603625cb19cf","timestamp":"2026-10-30T05:37:06.591Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}84{"parentUuid":"7b59c64a-1adc-487e-a6d0-603625cb19cf","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FTjodjj4x5vns4p2xqntAm","type":"tool_result","content":"{\n  \"dm_long_run_variance\": {\n    \"h1\": 0.8091371398245399,\n    \"h3\": 2.1185192376081026\n  },\n  \"dm_mean_loss_diff\": {\n    \"h1\": 0.6909309111104219,\n    \"h3\": 0.7118487020783464\n  },\n  \"sensitivity_dm_hln_stat\": {\n    \"h1\": 2.3043307191389144,\n    \"h3\": 1.1573521026578792\n  },\n  \"sensitivity_dm_hln_pvalue_t_nminus1\": {\n    \"h1\": 0.04666749503470258,\n    \"h3\": 0.27692062847238996\n  },\n  \"loss_diff_by_origin\": {\n    \"h1\": [\n      0.42628247290810234,\n      0.33506253379918116,\n      -0.007094285142650779,\n      0.6245881600149978,\n      0.3841698241754328,\n      0.23089952543795583,\n      0.6437250709930386,\n      3.1053054903693305,\n      -0.20506201977343566,\n      1.3714323383222675\n    ],\n    \"h3\": [\n      2.0818131359158567,\n      2.5186772456860385,\n      -0.36757738290214753,\n      0.2976177589306357,\n      -0.30300609313053073,\n      -2.876720657094274,\n      4.275214754492876,\n      -0.04919497538579183,\n      1.5177894441247985,\n      0.02387379014600069\n    ]\n  },\n  \"n_origins_model_sq_error_below_naive\": {\n    \"h1\": 8,\n    \"h3\": 6\n  },\n  \"revision_by_target\": [\n    {\n      \"target\": \"2025-09\",\n      \"g_current\": 3.623323,\n      \"first_release\": 4.17354,\n      \"abs_rev\": 0.550217\n    },\n    {\n      \"target\": \"2025-10\",\n      \"g_current\": 2.746018,\n      \"first_release\": 3.410194,\n      \"abs_rev\": 0.664176\n    },\norigin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used\n2025-10-31,2025-09-01,1,4.821776,4.173540,ar1,2025-10-31\n2025-11-30,2025-10-01,1,4.228201,3.410194,ar1,2025-11-30\n2025-12-31,2025-11-01,1,3.584932,3.277601,ar1,2025-12-31\n2026-01-31,2025-12-01,1,3.472669,2.398715,ar1,2026-01-31","is_error":false}]},"uuid":"863d2bbe-c646-4176-815e-b3cc4da312ed","timestamp":"2026-10-30T05:37:07.373Z","toolUseResult":{"stdout":"{\n  \"dm_long_run_variance\": {\n    \"h1\": 0.8091371398245399,\n    \"h3\": 2.1185192376081026\n  },\n  \"dm_mean_loss_diff\": {\n    \"h1\": 0.6909309111104219,\n    \"h3\": 0.7118487020783464\n  },\n  \"sensitivity_dm_hln_stat\": {\n    \"h1\": 2.3043307191389144,\n    \"h3\": 1.1573521026578792\n  },\n  \"sensitivity_dm_hln_pvalue_t_nminus1\": {\n    \"h1\": 0.04666749503470258,\n    \"h3\": 0.27692062847238996\n  },\n  \"loss_diff_by_origin\": {\n    \"h1\": [\n      0.42628247290810234,\n      0.33506253379918116,\n      -0.007094285142650779,\n      0.6245881600149978,\n      0.3841698241754328,\n      0.23089952543795583,\n      0.6437250709930386,\n      3.1053054903693305,\n      -0.20506201977343566,\n      1.3714323383222675\n    ],\n    \"h3\": [\n      2.0818131359158567,\n      2.5186772456860385,\n      -0.36757738290214753,\n      0.2976177589306357,\n      -0.30300609313053073,\n      -2.876720657094274,\n      4.275214754492876,\n      -0.04919497538579183,\n      1.5177894441247985,\n      0.02387379014600069\n    ]\n  },\n  \"n_origins_model_sq_error_below_naive\": {\n    \"h1\": 8,\n    \"h3\": 6\n  },\n  \"revision_by_target\": [\n    {\n      \"target\": \"2025-09\",\n      \"g_current\": 3.623323,\n      \"first_release\": 4.17354,\n      \"abs_rev\": 0.550217\n    },\n    {\n      \"target\": \"2025-10\",\n      \"g_current\": 2.746018,\n      \"first_release\": 3.410194,\n      \"abs_rev\": 0.664176\n    },\norigin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used\n2025-10-31,2025-09-01,1,4.821776,4.173540,ar1,2025-10-31\n2025-11-30,2025-10-01,1,4.228201,3.410194,ar1,2025-11-30\n2025-12-31,2025-11-01,1,3.584932,3.277601,ar1,2025-12-31\n2026-01-31,2025-12-01,1,3.472669,2.398715,ar1,2026-01-31","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7b59c64a-1adc-487e-a6d0-603625cb19cf","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}85{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"6edb58ddbc8e733c56c798519499a8fdff3562bb7dfaee33e2a091d558fe6fbd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01FTjodjj4x5vns4p2xqntAm","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    dm_extra[h] = (lrv, dbar)''','''    nn = len(en)\n    hln = np.sqrt((nn + 1 - 2 * h + h * (h - 1) / nn) / nn)\n    dm_extra[h] = (lrv, dbar, s * hln, float(2 * (1 - stats.t.cdf(abs(s * hln), df=nn - 1))),\n                   [float(v) for v in (en ** 2 - em ** 2)], int(np.sum(em ** 2 < en ** 2)))''')\ns=s.replace('''       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},''','''       \"dm_mean_loss_diff\": {f\"h{h}\": dm_extra[h][1] for h in HORIZONS},\n       \"sensitivity_dm_hln_stat\": {f\"h{h}\": dm_extra[h][2] for h in HORIZONS},\n       \"sensitivity_dm_hln_pvalue_t_nminus1\": {f\"h{h}\": dm_extra[h][3] for h in HORIZONS},\n       \"loss_diff_by_origin\": {f\"h{h}\": dm_extra[h][4] for h in HORIZONS},\n       \"n_origins_model_sq_error_below_naive\": {f\"h{h}\": dm_extra[h][5] for h in HORIZONS},''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cat out/state/aux_diagnostics.json | head -60; head -5 out/forecasts.csv","description":"Add HLN sensitivity diagnostics and rerun"}}]}}86{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"674e2904-47b1-42c0-8f6d-77f194ef6899","timestamp":"2026-10-30T05:37:07.375Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"727109f5-b044-477f-8792-c8811a34ace1","keep":26,"tail":["6edb58ddbc8e733c56c798519499a8fdff3562bb7dfaee33e2a091d558fe6fbd","892a090f76805358b372072b7cbd969e6977ca5685d0f599699a4465540a07d9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a63ea709e455b0d34e640d4ccb2cbee344997e4ab82cf9b1cbbbc79a5f4321b1"}87{"parentUuid":"863d2bbe-c646-4176-815e-b3cc4da312ed","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt3kJwPiUCASjqfj18L","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1853,"cache_read_input_tokens":44526,"output_tokens":2543,"output_tokens_details":{"thinking_tokens":93},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1853},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":578,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt3k354SWsjoZtS9YAV","requestRef":"674e2904-47b1-42c0-8f6d-77f194ef6899","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b6ab07ee-210a-4bc2-abea-29f917e5819b","timestamp":"2026-10-30T05:37:08.925Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}88{"parentUuid":"b6ab07ee-210a-4bc2-abea-29f917e5819b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt3kJwPiUCASjqfj18L","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CyqTx5KVs9dQLoVyhB1ZNK","name":"Bash","input":{"command":"cat > /tmp/verify.py <<'EOF'\nimport json, pandas as pd, numpy as np, statsmodels.api as sm\nr=json.load(open('out/results.json')); fc=pd.read_csv('out/forecasts.csv'); fr=pd.read_csv('data/first_release.csv')\nout=[]\ndef chk(name,cond): out.append(f\"- [{'PASS' if cond else 'FAIL'}] {name}\"); \nchk(\"forecasts.csv has 80 rows, unique (origin,horizon,model)\", len(fc)==80 and not fc.duplicated(['origin_date','horizon','model']).any())\nchk(\"vintage_used <= origin_date < target_date for all rows\", ((fc.vintage_used<=fc.origin_date)&(fc.origin_date<fc.target_date)).all())\n# independent: first_release yoy recomputed from its levels\nchk(\"first_release yoy = 100 ln(level/prev) (max abs diff <1e-5)\", np.max(np.abs(100*np.log(fr.level_first_release/fr.level_prev_year_same_vintage)-fr.yoy_first_release))<1e-5)\n# independent naive & AR1 via statsmodels for one origin\nV='2026-04-30'; v=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv'); v.columns=['d','L']; v['g']=100*np.log(v.L/v.L.shift(12))\nnv=v.g.iloc[-1]; chk(f\"naive at {V} recomputed independently\", np.isclose(fc.query(\"origin_date==@V and model=='naive' and horizon==1\").forecast.iloc[0], nv, atol=1e-5))\ns=v[v.d>='1993-01-01'].reset_index(drop=True); y=s.g.iloc[1:].values; X=sm.add_constant(s.g.iloc[:-1].values); b=sm.OLS(y,X).fit().params\nf3=nv\nfor _ in range(3): f3=b[0]+b[1]*f3\nchk(f\"AR(1) h=3 at {V} matches statsmodels OLS\", np.isclose(fc.query(\"origin_date==@V and model=='ar1' and horizon==3\").forecast.iloc[0], f3, atol=1e-5))\nchk(f\"target of {V} h=3 is 2026-06-01 (last=2026-03)\", fc.query(\"origin_date==@V and horizon==3\").target_date.iloc[0]=='2026-06-01')\n# vintage levels consistent with first release where the origin vintage is the first-release vintage\nok=True\nfor V in ['2025-11-30','2025-12-31','2026-04-30']:\n    v=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv'); v.columns=['d','L']\n    for _,row in fr[fr.first_release_vintage==V].iterrows(): ok &= int(v.set_index('d').L[row.target_month])==row.level_first_release\nchk(\"first_release levels match shipped vintages where first_release_vintage is a shipped vintage\", ok)\n# metrics recomputed\nfc['e']=fc.actual_first_release-fc.forecast\nfor m in ['naive','snaive','ar1','model']:\n    for h in [1,3]:\n        e=fc[(fc.model==m)&(fc.horizon==h)].e\n        chk(f\"rmse/mae {m} h{h} recomputed\", np.isclose(r[f'rmse_{m}_h{h}'],np.sqrt((e**2).mean()),rtol=1e-6) and np.isclose(r[f'mae_{m}_h{h}'],e.abs().mean(),rtol=1e-6) and r[f'rmse_{m}_h{h}']>=r[f'mae_{m}_h{h}']>0)\n# DM via statsmodels HAC (Bartlett, maxlags=h-1, no small-sample correction)\nfor h in [1,3]:\n    en=fc[(fc.model=='naive')&(fc.horizon==h)].sort_values('origin_date').e.values; em=fc[(fc.model=='model')&(fc.horizon==h)].sort_values('origin_date').e.values\n    d=en**2-em**2; res=sm.OLS(d,np.ones(10)).fit(cov_type='HAC',cov_kwds={'maxlags':h-1,'use_correction':False})\n    chk(f\"DM h{h} equals statsmodels HAC t-stat ({res.tvalues[0]:.6f})\", np.isclose(res.tvalues[0],r[f'dm_stat_h{h}'],rtol=1e-6) and np.isclose(res.pvalues[0],r[f'dm_pvalue_h{h}'],rtol=1e-5))\n    chk(f\"rel_improvement h{h} identity\", np.isclose(r[f'rel_improvement_rmse_h{h}'],1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']))\n    better='model' if r[f'rmse_model_h{h}']<r[f'rmse_naive_h{h}'] else 'naive'\n    chk(f\"conclusion code h{h} consistent\", r[f'conclusion_code_h{h}']==f\"{better}_better_{'significant' if r[f'dm_pvalue_h{h}']<0.05 else 'not_significant'}\")\n# revision independently\nc=pd.read_csv('data/RSAFS_current.csv'); c.columns=['d','L']; c['g']=100*np.log(c.L/c.L.shift(12)); c=c.set_index('d')\nt=fc[(fc.model=='naive')&(fc.horizon==1)].target_date\nmar=np.mean([abs(c.g[x]-fr.set_index('target_month').yoy_first_release[x]) for x in t])\nchk(f\"mean_abs_revision recomputed ({mar:.6f})\", np.isclose(mar,r['mean_abs_revision_h1_targets']))\nchk(\"n_analysed = 20 = exclusions ledger final n_after\", r['n_analysed']==20 and pd.read_csv('out/exclusions.csv').n_after.iloc[-1]==20)\nchk(\"n_input_rows match README counts (RSAFS 2026-07-31=414, UMCSENT=887, current=417, first_release=28)\", r['n_input_rows']['vintages/RSAFS_vintage_2026-07-31.csv']==414 and r['n_input_rows']['UMCSENT.csv']==887 and r['n_input_rows']['RSAFS_current.csv']==417 and r['n_input_rows']['first_release.csv']==28)\nchk(\"magnitudes: all RMSE between 0.3 and 3 pp, same order as naive baseline\", all(0.3<r[k]<3 for k in r if k.startswith('rmse_')))\nprint(\"\\n\".join(out))\nEOF\n~/wp29/venv/bin/python /tmp/verify.py","description":"Run independent verification checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1853,"cache_read_input_tokens":44526,"output_tokens":2543,"output_tokens_details":{"thinking_tokens":93},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1853},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt3k354SWsjoZtS9YAV","requestRef":"674e2904-47b1-42c0-8f6d-77f194ef6899","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"850ea46c-c701-4b16-9820-e536f1f86e18","timestamp":"2026-10-30T05:37:27.049Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}89{"parentUuid":"850ea46c-c701-4b16-9820-e536f1f86e18","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CyqTx5KVs9dQLoVyhB1ZNK","type":"tool_result","content":"- [PASS] forecasts.csv has 80 rows, unique (origin,horizon,model)\n- [FAIL] vintage_used <= origin_date < target_date for all rows\n- [PASS] first_release yoy = 100 ln(level/prev) (max abs diff <1e-5)\n- [PASS] naive at 2026-04-30 recomputed independently\n- [PASS] AR(1) h=3 at 2026-04-30 matches statsmodels OLS\n- [PASS] target of 2026-04-30 h=3 is 2026-06-01 (last=2026-03)\n- [PASS] first_release levels match shipped vintages where first_release_vintage is a shipped vintage\n- [PASS] rmse/mae naive h1 recomputed\n- [PASS] rmse/mae naive h3 recomputed\n- [PASS] rmse/mae snaive h1 recomputed\n- [PASS] rmse/mae snaive h3 recomputed\n- [PASS] rmse/mae ar1 h1 recomputed\n- [PASS] rmse/mae ar1 h3 recomputed\n- [PASS] rmse/mae model h1 recomputed\n- [PASS] rmse/mae model h3 recomputed\n- [PASS] DM h1 equals statsmodels HAC t-stat (2.428978)\n- [PASS] rel_improvement h1 identity\n- [PASS] conclusion code h1 consistent\n- [PASS] DM h3 equals statsmodels HAC t-stat (1.546577)\n- [PASS] rel_improvement h3 identity\n- [PASS] conclusion code h3 consistent\n- [PASS] mean_abs_revision recomputed (0.548220)\n- [PASS] n_analysed = 20 = exclusions ledger final n_after\n- [PASS] n_input_rows match README counts (RSAFS 2026-07-31=414, UMCSENT=887, current=417, first_release=28)\n- [PASS] magnitudes: all RMSE between 0.3 and 3 pp, same order as naive baseline","is_error":false}]},"uuid":"f6d8c43b-b06f-4f16-9232-1bc09c7f4698","timestamp":"2026-10-30T05:37:27.728Z","toolUseResult":{"stdout":"- [PASS] forecasts.csv has 80 rows, unique (origin,horizon,model)\n- [FAIL] vintage_used <= origin_date < target_date for all rows\n- [PASS] first_release yoy = 100 ln(level/prev) (max abs diff <1e-5)\n- [PASS] naive at 2026-04-30 recomputed independently\n- [PASS] AR(1) h=3 at 2026-04-30 matches statsmodels OLS\n- [PASS] target of 2026-04-30 h=3 is 2026-06-01 (last=2026-03)\n- [PASS] first_release levels match shipped vintages where first_release_vintage is a shipped vintage\n- [PASS] rmse/mae naive h1 recomputed\n- [PASS] rmse/mae naive h3 recomputed\n- [PASS] rmse/mae snaive h1 recomputed\n- [PASS] rmse/mae snaive h3 recomputed\n- [PASS] rmse/mae ar1 h1 recomputed\n- [PASS] rmse/mae ar1 h3 recomputed\n- [PASS] rmse/mae model h1 recomputed\n- [PASS] rmse/mae model h3 recomputed\n- [PASS] DM h1 equals statsmodels HAC t-stat (2.428978)\n- [PASS] rel_improvement h1 identity\n- [PASS] conclusion code h1 consistent\n- [PASS] DM h3 equals statsmodels HAC t-stat (1.546577)\n- [PASS] rel_improvement h3 identity\n- [PASS] conclusion code h3 consistent\n- [PASS] mean_abs_revision recomputed (0.548220)\n- [PASS] n_analysed = 20 = exclusions ledger final n_after\n- [PASS] n_input_rows match README counts (RSAFS 2026-07-31=414, UMCSENT=887, current=417, first_release=28)\n- [PASS] magnitudes: all RMSE between 0.3 and 3 pp, same order as naive baseline","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"850ea46c-c701-4b16-9820-e536f1f86e18","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}90{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"3125703822d77377bafcb918ac8678aba4883828db57f47a9c2e5a75799eaffd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS5wcKEAgTGAI4AUIIdGhpbmtpbmcSDIRr9HQS+45IUfR1DRoMd1t/RMZxH7jJ7ni7IjACEWVt53ns/pCIYNXzNhd/QI+ETQGg5XWhNbqrijhIDiEYL5JWSteD0euABWMUs1AqhAeWiR1Za7Az13nw0jYt9RgnDkuHxphapu0Y3J99HJTCOU12fl1lSF/sj2m7t+X7lPvVUje6l8Y3djtEj78RV9XPipgHvmDMp373lolVjplmT+9r0ZJoPMhtc6M+4lyj4AdquqlcK2WqvsShAR37KXJxe1dUTdSZxlok0GROTW58UxS1IkIv5gTbfhvQWYPqQIn6p/uZ14R70X9CqnVwxsgWd2SdLxmghhcaPCMbGzCm6K+Ha/a4eZq0xuuV0lC8ME6qjEebI6xlNPDXVqVmPOa0p58JrR22PnW7XLrFLsBEXvLF6MQCim3iFJcGdNw7FJr8fVxgZnF8Ne3P4OJP0t11+iIqWzGLrsOJIVfhD79AeaSJz6QgFV3CUozXWYUhlP9WazXVu3/W4czRvGfG1PwAskfFmc7E1ppPDEVFSkpJYP6tXeDewIp423z6ScbLilXavwM/eHoiK57T4u3mVS7KgOlCphuA9fCw5H8YmZmhohsYaJlYtGM0xvePsn7lPep5xCOVXiP5yNlrkI30T/+jaejBOtlPhLWr4eZEKb85IFsEQfeEIoNGxxe/Vom9SKmIJyCdGGQ7fUllhKT63UGhO2vdWpBDCVYqaBWxjEL717g6vsPWcNhNk8AAmwfv2lrwVOVeykbV2wRpigmtbBeDGXveMl3gB7m3JB+GgpZ8F+C8wW+hzwPPOk30mzdUvzM8yE1M7u9nwnNaSQhUSc7W/sbfTxBL+xmaxTwd81l57q1QCTFCAXAmQLaQphalXHkH2ywwW/CIMxn5E+070MECpsEeqAKPVIblazqn6msjvo5pLtGoxFl++ysG5rbracsxDS88DZCW+9INOvw+ksBcLpxuTzD9wDSyZFmell4hYNzGt/yIcMF5yAHCJYV9Dv22LeOZhVfN8mamDKGdV6bMznC5gv2q1Qv92lbuWKeYL1pEhikJvd0cD+SFkjuf3GfZg4wYLDrBYRYQBe++uTIAp56WWgfsMu2sbXRinfpsIFMRjUniKsdVbxmGCtnQSJgU7k+hZZN3XPEm9dcPrCu0gk5GQHghJJqU/0NsSDpepnFX4ae4a+b7idWAhMvoSNyAWyYn0B9nfCHxvEWCNwqJ5iqso71nuH0rXsSrZzGkOFeKYotay6KUKMZxdqrKCTFwSNtRBoFZy/ABFldYCGzFnv8MTLnPaSVS0n6Ulw0vG5Kz/xAYAQ=="},{"type":"tool_use","id":"toolu_01CyqTx5KVs9dQLoVyhB1ZNK","name":"Bash","input":{"command":"cat > /tmp/verify.py <<'EOF'\nimport json, pandas as pd, numpy as np, statsmodels.api as sm\nr=json.load(open('out/results.json')); fc=pd.read_csv('out/forecasts.csv'); fr=pd.read_csv('data/first_release.csv')\nout=[]\ndef chk(name,cond): out.append(f\"- [{'PASS' if cond else 'FAIL'}] {name}\"); \nchk(\"forecasts.csv has 80 rows, unique (origin,horizon,model)\", len(fc)==80 and not fc.duplicated(['origin_date','horizon','model']).any())\nchk(\"vintage_used <= origin_date < target_date for all rows\", ((fc.vintage_used<=fc.origin_date)&(fc.origin_date<fc.target_date)).all())\n# independent: first_release yoy recomputed from its levels\nchk(\"first_release yoy = 100 ln(level/prev) (max abs diff <1e-5)\", np.max(np.abs(100*np.log(fr.level_first_release/fr.level_prev_year_same_vintage)-fr.yoy_first_release))<1e-5)\n# independent naive & AR1 via statsmodels for one origin\nV='2026-04-30'; v=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv'); v.columns=['d','L']; v['g']=100*np.log(v.L/v.L.shift(12))\nnv=v.g.iloc[-1]; chk(f\"naive at {V} recomputed independently\", np.isclose(fc.query(\"origin_date==@V and model=='naive' and horizon==1\").forecast.iloc[0], nv, atol=1e-5))\ns=v[v.d>='1993-01-01'].reset_index(drop=True); y=s.g.iloc[1:].values; X=sm.add_constant(s.g.iloc[:-1].values); b=sm.OLS(y,X).fit().params\nf3=nv\nfor _ in range(3): f3=b[0]+b[1]*f3\nchk(f\"AR(1) h=3 at {V} matches statsmodels OLS\", np.isclose(fc.query(\"origin_date==@V and model=='ar1' and horizon==3\").forecast.iloc[0], f3, atol=1e-5))\nchk(f\"target of {V} h=3 is 2026-06-01 (last=2026-03)\", fc.query(\"origin_date==@V and horizon==3\").target_date.iloc[0]=='2026-06-01')\n# vintage levels consistent with first release where the origin vintage is the first-release vintage\nok=True\nfor V in ['2025-11-30','2025-12-31','2026-04-30']:\n    v=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv'); v.columns=['d','L']\n    for _,row in fr[fr.first_release_vintage==V].iterrows(): ok &= int(v.set_index('d').L[row.target_month])==row.level_first_release\nchk(\"first_release levels match shipped vintages where first_release_vintage is a shipped vintage\", ok)\n# metrics recomputed\nfc['e']=fc.actual_first_release-fc.forecast\nfor m in ['naive','snaive','ar1','model']:\n    for h in [1,3]:\n        e=fc[(fc.model==m)&(fc.horizon==h)].e\n        chk(f\"rmse/mae {m} h{h} recomputed\", np.isclose(r[f'rmse_{m}_h{h}'],np.sqrt((e**2).mean()),rtol=1e-6) and np.isclose(r[f'mae_{m}_h{h}'],e.abs().mean(),rtol=1e-6) and r[f'rmse_{m}_h{h}']>=r[f'mae_{m}_h{h}']>0)\n# DM via statsmodels HAC (Bartlett, maxlags=h-1, no small-sample correction)\nfor h in [1,3]:\n    en=fc[(fc.model=='naive')&(fc.horizon==h)].sort_values('origin_date').e.values; em=fc[(fc.model=='model')&(fc.horizon==h)].sort_values('origin_date').e.values\n    d=en**2-em**2; res=sm.OLS(d,np.ones(10)).fit(cov_type='HAC',cov_kwds={'maxlags':h-1,'use_correction':False})\n    chk(f\"DM h{h} equals statsmodels HAC t-stat ({res.tvalues[0]:.6f})\", np.isclose(res.tvalues[0],r[f'dm_stat_h{h}'],rtol=1e-6) and np.isclose(res.pvalues[0],r[f'dm_pvalue_h{h}'],rtol=1e-5))\n    chk(f\"rel_improvement h{h} identity\", np.isclose(r[f'rel_improvement_rmse_h{h}'],1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']))\n    better='model' if r[f'rmse_model_h{h}']<r[f'rmse_naive_h{h}'] else 'naive'\n    chk(f\"conclusion code h{h} consistent\", r[f'conclusion_code_h{h}']==f\"{better}_better_{'significant' if r[f'dm_pvalue_h{h}']<0.05 else 'not_significant'}\")\n# revision independently\nc=pd.read_csv('data/RSAFS_current.csv'); c.columns=['d','L']; c['g']=100*np.log(c.L/c.L.shift(12)); c=c.set_index('d')\nt=fc[(fc.model=='naive')&(fc.horizon==1)].target_date\nmar=np.mean([abs(c.g[x]-fr.set_index('target_month').yoy_first_release[x]) for x in t])\nchk(f\"mean_abs_revision recomputed ({mar:.6f})\", np.isclose(mar,r['mean_abs_revision_h1_targets']))\nchk(\"n_analysed = 20 = exclusions ledger final n_after\", r['n_analysed']==20 and pd.read_csv('out/exclusions.csv').n_after.iloc[-1]==20)\nchk(\"n_input_rows match README counts (RSAFS 2026-07-31=414, UMCSENT=887, current=417, first_release=28)\", r['n_input_rows']['vintages/RSAFS_vintage_2026-07-31.csv']==414 and r['n_input_rows']['UMCSENT.csv']==887 and r['n_input_rows']['RSAFS_current.csv']==417 and r['n_input_rows']['first_release.csv']==28)\nchk(\"magnitudes: all RMSE between 0.3 and 3 pp, same order as naive baseline\", all(0.3<r[k]<3 for k in r if k.startswith('rmse_')))\nprint(\"\\n\".join(out))\nEOF\n~/wp29/venv/bin/python /tmp/verify.py","description":"Run independent verification checks"}}]}}91{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"ad2ed0b8-5814-4583-b525-be5054126e1a","timestamp":"2026-10-30T05:37:27.731Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"674e2904-47b1-42c0-8f6d-77f194ef6899","keep":28,"tail":["3125703822d77377bafcb918ac8678aba4883828db57f47a9c2e5a75799eaffd","a6d46299ded031bbfbfbcc7373f6ced8a961aeaf0d40797fc126a763c86cbe85"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"661c13f68d2b3bc6470c8ba9400ca5149bbc7bc144d6c1e416fcbec4192527f1"}92{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f6d8c43b-b06f-4f16-9232-1bc09c7f4698","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}93{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}94{"parentUuid":"f6d8c43b-b06f-4f16-9232-1bc09c7f4698","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5FGkZLACwCX5o2m6E","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS2AsKEAgTGAI4AUIIdGhpbmtpbmcSDB7EIqZeDdTOdwJdNBoMGXMFsME+/H6Qru9VIjDYymPK4y6qEx/UYy7Wt+2Zev9EsoWzm1v4dpuLg4/JQtN8vJkozOmLf2YZFOiRNjgq9Qqx4vaELBmzk6WbVdvMVpkfD1o/Ro75q6o9SBn7dTXbsTr5XchgOos6FabUkI9AgB5BTEnANnA4ngUpJrEcahsKvMVrzDIl1rTGDWppvPLwCVshd08kq78khOehaqUn7v7BIechoAyHpx9M2Vo9bcYIWgKPCn5awT/uIKNuRjMyjEuuvtfU/RuvgrweCKegYEwT1hJI8SnUAJ9v6jhKbc3NXc284pBlxpYwQL3WVprgeeRKrmWbNW8fg0woDDcku6ypVtGYR/V0EjuWZ36sedFA/nlamKeTNDYaH++c405FYI98T7N7jtgRrV0KC/csZ19fAkgtNDTP8SIS8IoILX3nCf6LCCFk3lZLUVVnJSX6Ua2Tfn9BeYgklSnfcyEKT9t8nLBB3x0rSf5GPdGphaRcKUNNMdoD/U2kzFGUMP9jqsZmdmvBKUkG9jABNQD4h6MpkV4X3hWwik9901hWjqU5Xk6Q464Z53xEnNhM7QS69EEwPSWlzOwfbhvccqHXMdUhLv5bNR6Uho4T8j6KsCHwr3RACgtS3xgE0DqwzlNxLnXDDo9o1E241+PNchwG/5GPcgE+1htanVqmSthETl69C2dHhF3QldiImez1D6sxtvcmSTQocRrAif5LHH6MLKjR4Gx0WJH7+2wo957Q8ksRRNbo27yRprM70PesN0gC5V5ZpfPERaZwksT40u8HkyT7K+8JKcAmcRe1ENxTIWOsBwPpcjlbzrqj8/QpuCHOLwqHk6m/v30WijV8eMmLoG+bjLqt1fonXaMHBkk/svWN4MKBDHf4unpv1zh8kEnNK4yhE4ppTKSKGchpHKxdMEjcEFvRq47zCHnlIRr+ZBzTOb068IPp0Dt0vrWJGitvEGHZp9UZ64clFfV7cDLcfT0YiOTDNmirL/kxA5KzPMpwcSu3q50rwGO42kEhww1Bm/pJndb+7X0w1jj+wzg8vTfojBvGSCWW7dLkfLUrAmLsxMZd9x6mOSd+VWFNjz/0kvnQ7hzizmlEAsDTQJ5c1CbEYmEbvO4p9XCKwfqqdCDBVcP9d9Iu3m4XbOi24JPTT1FXLyl20kPwiZ2+oMjl3gQ85J5h2QdnTwvAHNHLPFtYqHtyBHLi2uPuWOspas3fmkizeYz/yQGDEuFHseqgNX9UPNV//VEkxqLj9xohfsDBG9cR2Rl0QaNClpc0+P0O3rzBVU3L/4hzmvdYtD01tYXhMMdTiCbkcIKBRq4tm63MeMpfdQZUP7x+AEKnMSU3dT7GxTapOYDIeVwJ2cDEb5yXHcQPbEUasjXA1kKei/2CtOuZYA49+67c9RWeaTOve7ObeFQ5pi4JcRg2bKRnGff58GWY8b6akDqhPqK27j9YWUpcj67rj8+oG+UDBLDEThGiwAPRzbd5+CW35d+fe4yWJIu9KRDIW9DOYdTP+vIpK5aBIkrqvCKAMBuY/5f9sT0jgdx0UZQwtXZEd0I7fMcdUFnMF5DwtSSrJsqme5+dr2OUzS2zOTkgfF+3jEs8SQNLziyu6wu5SjsDhpFHBlRSwUgotXB9xj3Lp19VQN5QU1hVfyOIwPOit92UjOk3O7ytYW5D6BItDWE8wus9OVIr8/HJJ37/3LgHYrsGPRhzdSh2ven59VjTzunFoGKO3JGI0X9TfUu01ll9bOMEJgmVemjtaZh5TBCHLy648sCRxDm9stK8R3lwaG/mx4HdZrbVnUbPvEVSqlDJ6dszOj4cLn3epT/d3AfrpuGirdYoIIldKREMmRkct6dJIu4WBTM8eDVr2sfCvlZu6r7HJT/NK4QfrjYkd+ettJNrwXivv3oUn4alY/tOTCDAv6ZY69HObtT/6kYH2JcS6Uw4mSHufvEqzhgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3236,"cache_read_input_tokens":46379,"output_tokens":396,"output_tokens_details":{"thinking_tokens":275},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3236},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2091,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt5F5qwGeyRnaBiAdnD","requestRef":"ad2ed0b8-5814-4583-b525-be5054126e1a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f2268e10-e90a-421b-92cd-2c8b40c0fa2d","timestamp":"2026-10-30T05:37:30.863Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}95{"parentUuid":"f2268e10-e90a-421b-92cd-2c8b40c0fa2d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5FGkZLACwCX5o2m6E","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HcHc3K4kMA1fGRxwhkCHCU","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -40","description":"Run gate to see chronology handling"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3236,"cache_read_input_tokens":46379,"output_tokens":396,"output_tokens_details":{"thinking_tokens":275},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3236},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt5F5qwGeyRnaBiAdnD","requestRef":"ad2ed0b8-5814-4583-b525-be5054126e1a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b2fbe84e-e5a5-4c4e-b417-1715e77eee8f","timestamp":"2026-10-30T05:37:31.601Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}96{"parentUuid":"b2fbe84e-e5a5-4c4e-b417-1715e77eee8f","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HcHc3K4kMA1fGRxwhkCHCU","type":"tool_result","content":"  [ok] key:rmse_model_h1: ok\n  [ok] key:mae_model_h1: ok\n  [ok] key:rmse_model_h3: ok\n  [ok] key:mae_model_h3: ok\n  [ok] key:rel_improvement_rmse_h1: ok\n  [ok] key:rel_improvement_rmse_h3: ok\n  [ok] key:dm_stat_h1: ok\n  [ok] key:dm_pvalue_h1: ok\n  [ok] key:dm_stat_h3: ok\n  [ok] key:dm_pvalue_h3: ok\n  [ok] key:conclusion_code_h1: ok\n  [ok] key:conclusion_code_h3: ok\n  [ok] key:mean_abs_revision_h1_targets: ok\n  [ok] key:feasibility: ok\n  [ok] key:feasibility_reason: ok\n  [ok] key:data_issues: ok\n  [ok] key:n_input_rows: ok\n  [ok] key:n_analysed: ok\n  [ok] key:random_seed: ok\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P2', 'P3', 'P4', 'P5']\n  [ok] exclusion_ledger: 2 steps consistent\n  [ok] positive:rmse_naive_h1: 0.9968743518607954\n  [ok] positive:rmse_naive_h3: 1.4200403737520462\n  [ok] positive:rmse_snaive_h1: 1.6745428991342943\n  [ok] positive:rmse_snaive_h3: 1.3160788989552372\n  [ok] positive:rmse_ar1_h1: 0.9405244111185227\n  [ok] positive:rmse_ar1_h3: 1.1871178147422958\n  [ok] positive:rmse_model_h1: 0.5502977033274435\n  [ok] positive:rmse_model_h3: 1.1422197516272885\n  [ok] chronology:first_origin<=last_origin: 2025-10-31 vs 2026-07-31\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\n  [ok] reproducibility: regenerated in 0.7s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053732.391378Z.json","is_error":false}]},"uuid":"82d60c4f-9503-45b6-ada0-bdc12b6fc559","timestamp":"2026-10-30T05:37:32.397Z","toolUseResult":{"stdout":"  [ok] key:rmse_model_h1: ok\n  [ok] key:mae_model_h1: ok\n  [ok] key:rmse_model_h3: ok\n  [ok] key:mae_model_h3: ok\n  [ok] key:rel_improvement_rmse_h1: ok\n  [ok] key:rel_improvement_rmse_h3: ok\n  [ok] key:dm_stat_h1: ok\n  [ok] key:dm_pvalue_h1: ok\n  [ok] key:dm_stat_h3: ok\n  [ok] key:dm_pvalue_h3: ok\n  [ok] key:conclusion_code_h1: ok\n  [ok] key:conclusion_code_h3: ok\n  [ok] key:mean_abs_revision_h1_targets: ok\n  [ok] key:feasibility: ok\n  [ok] key:feasibility_reason: ok\n  [ok] key:data_issues: ok\n  [ok] key:n_input_rows: ok\n  [ok] key:n_analysed: ok\n  [ok] key:random_seed: ok\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P2', 'P3', 'P4', 'P5']\n  [ok] exclusion_ledger: 2 steps consistent\n  [ok] positive:rmse_naive_h1: 0.9968743518607954\n  [ok] positive:rmse_naive_h3: 1.4200403737520462\n  [ok] positive:rmse_snaive_h1: 1.6745428991342943\n  [ok] positive:rmse_snaive_h3: 1.3160788989552372\n  [ok] positive:rmse_ar1_h1: 0.9405244111185227\n  [ok] positive:rmse_ar1_h3: 1.1871178147422958\n  [ok] positive:rmse_model_h1: 0.5502977033274435\n  [ok] positive:rmse_model_h3: 1.1422197516272885\n  [ok] chronology:first_origin<=last_origin: 2025-10-31 vs 2026-07-31\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\n  [ok] reproducibility: regenerated in 0.7s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053732.391378Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b2fbe84e-e5a5-4c4e-b417-1715e77eee8f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}97{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"ae20fce5849ad418ad0aa85f622c3901eb6bdee3f69a501656d5262e996a17f5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01HcHc3K4kMA1fGRxwhkCHCU","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -40","description":"Run gate to see chronology handling"}}]}}98{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"2e9cee6d-9159-46fd-b4b8-a285ff753f68","timestamp":"2026-10-30T05:37:32.399Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"ad2ed0b8-5814-4583-b525-be5054126e1a","keep":30,"tail":["ae20fce5849ad418ad0aa85f622c3901eb6bdee3f69a501656d5262e996a17f5","0f1def8a9194edbb86639499f3b185dcfcb79f26433fa313b0888b5baa0dc2c6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3c547f8287d695e862b0cdb8274ec51779ca186b21c84586974b52bb1ef22084"}99{"parentUuid":"82d60c4f-9503-45b6-ada0-bdc12b6fc559","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5bJGZdxmXNnXCxw4n","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1351,"cache_read_input_tokens":49615,"output_tokens":775,"output_tokens_details":{"thinking_tokens":643},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1351},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6515,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt5b29b8aB85x47FvJ9","requestRef":"2e9cee6d-9159-46fd-b4b8-a285ff753f68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5c47f2e2-af32-4269-a1e1-ce77d812d7c3","timestamp":"2026-10-30T05:37:39.887Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}100{"parentUuid":"5c47f2e2-af32-4269-a1e1-ce77d812d7c3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5bJGZdxmXNnXCxw4n","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XsmKfmvfb6WjSqRnStZXmY","name":"Bash","input":{"command":"grep -n \"chronology\\|target_col\\|origin_col\\|vintage_col\" -A3 ~/wp29/gates/pgar_gate.py | head -80","description":"Inspect gate chronology check logic"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1351,"cache_read_input_tokens":49615,"output_tokens":775,"output_tokens_details":{"thinking_tokens":643},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1351},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt5b29b8aB85x47FvJ9","requestRef":"2e9cee6d-9159-46fd-b4b8-a285ff753f68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c8e81ac4-ff2e-49f5-935c-530ce243cec5","timestamp":"2026-10-30T05:37:40.793Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}101{"parentUuid":"c8e81ac4-ff2e-49f5-935c-530ce243cec5","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XsmKfmvfb6WjSqRnStZXmY","type":"tool_result","content":"170:    if \"chronology\" in fam:\n171:        for a, b in spec.get(\"chronology_pairs\", []):\n172-            da, db = _parse_date(res.get(a)), _parse_date(res.get(b))\n173:            add(f\"chronology:{a}<={b}\", da is not None and db is not None and da <= db, f\"{res.get(a)} vs {res.get(b)}\")\n174:    if \"forecasts_csv_chronology\" in fam:\n175-        fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n176-        try:\n177-            rows = list(csv.DictReader(open(fp, newline=\"\")))\n--\n179:            add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n180-        except Exception as e:  # noqa: BLE001\n181:            add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n182-    # 8. reproducibility\n183-    if do_repro and os.path.isfile(os.path.join(ws, \"out\", \"analysis.py\")) and isinstance(res, dict) and res:\n184-        py = python or sys.executable","is_error":false}]},"uuid":"a11c059f-0c8c-4310-be9a-864217f50886","timestamp":"2026-10-30T05:37:40.833Z","toolUseResult":{"stdout":"170:    if \"chronology\" in fam:\n171:        for a, b in spec.get(\"chronology_pairs\", []):\n172-            da, db = _parse_date(res.get(a)), _parse_date(res.get(b))\n173:            add(f\"chronology:{a}<={b}\", da is not None and db is not None and da <= db, f\"{res.get(a)} vs {res.get(b)}\")\n174:    if \"forecasts_csv_chronology\" in fam:\n175-        fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n176-        try:\n177-            rows = list(csv.DictReader(open(fp, newline=\"\")))\n--\n179:            add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n180-        except Exception as e:  # noqa: BLE001\n181:            add(\"forecasts_chronology\", False, f\"forecasts.csv unreadable: {e}\")\n182-    # 8. reproducibility\n183-    if do_repro and os.path.isfile(os.path.join(ws, \"out\", \"analysis.py\")) and isinstance(res, dict) and res:\n184-        py = python or sys.executable","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c8e81ac4-ff2e-49f5-935c-530ce243cec5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}102{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"27aef3ca80d375116ed3293a26a0aa1423efed4861387897e9c9e6c3b0107958","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01XsmKfmvfb6WjSqRnStZXmY","name":"Bash","input":{"command":"grep -n \"chronology\\|target_col\\|origin_col\\|vintage_col\" -A3 ~/wp29/gates/pgar_gate.py | head -80","description":"Inspect gate chronology check logic"}}]}}103{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"e5d0c968-84a6-4bdf-b5df-5ef50210d33f","timestamp":"2026-10-30T05:37:40.837Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"2e9cee6d-9159-46fd-b4b8-a285ff753f68","keep":32,"tail":["27aef3ca80d375116ed3293a26a0aa1423efed4861387897e9c9e6c3b0107958","0403386b4a8d3dda157877c6cac499088a58796780926652970e0e58201b3e90"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3250cbd633eb8045639d60961545a8233839743a5bb53fe2dc7b73ea4bb93c4e"}104{"parentUuid":"a11c059f-0c8c-4310-be9a-864217f50886","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6DQAPK7ZyNPQmcFQy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018XJtEQxhWXKAmf5ARxgS15","name":"Bash","input":{"command":"sed -n 174,180p ~/wp29/gates/pgar_gate.py; grep -n \"def _parse_date\" -A10 ~/wp29/gates/pgar_gate.py","description":"Show exact chronology comparison"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1177,"cache_read_input_tokens":50966,"output_tokens":138,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1177},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt6D841eJv7fuJvCcb8","requestRef":"e5d0c968-84a6-4bdf-b5df-5ef50210d33f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"43303142-1987-4e6c-add0-9ad03915702c","timestamp":"2026-10-30T05:37:42.325Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}105{"parentUuid":"43303142-1987-4e6c-add0-9ad03915702c","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018XJtEQxhWXKAmf5ARxgS15","type":"tool_result","content":"    if \"forecasts_csv_chronology\" in fam:\n        fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n        try:\n            rows = list(csv.DictReader(open(fp, newline=\"\")))\n            bad = sum(1 for r in rows if not (_parse_date(r.get(\"origin_date\")) and _parse_date(r.get(\"target_date\")) and _parse_date(r[\"origin_date\"]) < _parse_date(r[\"target_date\"])))\n            add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n        except Exception as e:  # noqa: BLE001\n36:def _parse_date(s):\n37-    try:\n38-        return datetime.date.fromisoformat(str(s)[:10])\n39-    except Exception:  # noqa: BLE001\n40-        return None\n41-\n42-def _compare_results(a, b, rel):\n43-    \"\"\"Return list of keys whose values differ beyond rel tolerance (numbers) or are unequal (others).\"\"\"\n44-    diffs = []\n45-    keys = set(a) | set(b)\n46-    for k in keys:","is_error":false}]},"uuid":"8d156aa0-3c2c-4c00-ab6c-bbed837e0d66","timestamp":"2026-10-30T05:37:42.369Z","toolUseResult":{"stdout":"    if \"forecasts_csv_chronology\" in fam:\n        fp = os.path.join(ws, \"out\", \"forecasts.csv\")\n        try:\n            rows = list(csv.DictReader(open(fp, newline=\"\")))\n            bad = sum(1 for r in rows if not (_parse_date(r.get(\"origin_date\")) and _parse_date(r.get(\"target_date\")) and _parse_date(r[\"origin_date\"]) < _parse_date(r[\"target_date\"])))\n            add(\"forecasts_chronology\", rows and bad == 0, f\"{bad} rows with target_date <= origin_date out of {len(rows)}\")\n        except Exception as e:  # noqa: BLE001\n36:def _parse_date(s):\n37-    try:\n38-        return datetime.date.fromisoformat(str(s)[:10])\n39-    except Exception:  # noqa: BLE001\n40-        return None\n41-\n42-def _compare_results(a, b, rel):\n43-    \"\"\"Return list of keys whose values differ beyond rel tolerance (numbers) or are unequal (others).\"\"\"\n44-    diffs = []\n45-    keys = set(a) | set(b)\n46-    for k in keys:","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"43303142-1987-4e6c-add0-9ad03915702c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}106{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"69f9e3a6cb41c352c54edbaa67ed5d540590d4297b1ccc31209742f13993f21e","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_018XJtEQxhWXKAmf5ARxgS15","name":"Bash","input":{"command":"sed -n 174,180p ~/wp29/gates/pgar_gate.py; grep -n \"def _parse_date\" -A10 ~/wp29/gates/pgar_gate.py","description":"Show exact chronology comparison"}}]}}107{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"8ee2fae1-c198-466d-8db3-a4e19129fa26","timestamp":"2026-10-30T05:37:42.373Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"e5d0c968-84a6-4bdf-b5df-5ef50210d33f","keep":34,"tail":["69f9e3a6cb41c352c54edbaa67ed5d540590d4297b1ccc31209742f13993f21e","a78df37466699fa31325c66f582a15b44286d0148f1bba44050c6ae3242b2e09"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"de24efa760c6a2733df8c8b0ced8d8f784aa0a312bd99e173354708f0b5c9081"}108{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"8d156aa0-3c2c-4c00-ab6c-bbed837e0d66","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}109{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}110{"parentUuid":"8d156aa0-3c2c-4c00-ab6c-bbed837e0d66","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6KrriuT9gdw1G7D2B","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":531,"cache_read_input_tokens":52143,"output_tokens":568,"output_tokens_details":{"thinking_tokens":458},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":531},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4046,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt6KgBjGfNzR9X8f15V","requestRef":"8ee2fae1-c198-466d-8db3-a4e19129fa26","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0315558b-2573-427a-8cb6-69102d76cd3f","timestamp":"2026-10-30T05:37:47.442Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}111{"parentUuid":"0315558b-2573-427a-8cb6-69102d76cd3f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6KrriuT9gdw1G7D2B","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JBua8EbHvHH16ZL4DpM97y","name":"Bash","input":{"command":"grep -n \"phase\" ~/wp29/gates/pgar_gate.py | head -30","description":"Inspect gate phase ledger rules"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":531,"cache_read_input_tokens":52143,"output_tokens":568,"output_tokens_details":{"thinking_tokens":458},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":531},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt6KgBjGfNzR9X8f15V","requestRef":"8ee2fae1-c198-466d-8db3-a4e19129fa26","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a9c30dec-a133-40cb-9114-1a970f48b15d","timestamp":"2026-10-30T05:37:48.027Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}112{"parentUuid":"a9c30dec-a133-40cb-9114-1a970f48b15d","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JBua8EbHvHH16ZL4DpM97y","type":"tool_result","content":"122:    # 5. phase ledger\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n124:    if \"phase_ledger_consistent\" in fam and os.path.exists(pl_path):\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n137:                bad.append(f\"phases not terminal: {not_done}\")\n138:            add(\"phase_ledger\", not bad, \"; \".join(bad) if bad else \"consistent\")","is_error":false}]},"uuid":"4839de09-6ce7-4c26-a6a9-af77bc6cffaa","timestamp":"2026-10-30T05:37:48.067Z","toolUseResult":{"stdout":"122:    # 5. phase ledger\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n124:    if \"phase_ledger_consistent\" in fam and os.path.exists(pl_path):\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n137:                bad.append(f\"phases not terminal: {not_done}\")\n138:            add(\"phase_ledger\", not bad, \"; \".join(bad) if bad else \"consistent\")","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a9c30dec-a133-40cb-9114-1a970f48b15d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}113{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"5abea8ec5bc98bc32f15d247997b395db6a6d6bcaf17115c9bfb4c36c4ad2524","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JBua8EbHvHH16ZL4DpM97y","name":"Bash","input":{"command":"grep -n \"phase\" ~/wp29/gates/pgar_gate.py | head -30","description":"Inspect gate phase ledger rules"}}]}}114{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"4eaba32b-eee7-478c-9ff3-a2d7892e38c3","timestamp":"2026-10-30T05:37:48.072Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"8ee2fae1-c198-466d-8db3-a4e19129fa26","keep":36,"tail":["5abea8ec5bc98bc32f15d247997b395db6a6d6bcaf17115c9bfb4c36c4ad2524","b168e7ed119fea63c1358b3cc8315a81ef5b2f18dc4dfd255c2cff06dc63bfbb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",37,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"19469ed58b73d02254fa8f7f268d2f5c21e5a32ef968b8ec4bb6f10d418fc37d"}115{"parentUuid":"4839de09-6ce7-4c26-a6a9-af77bc6cffaa","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6kKGSLK6QKbtUffNa","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Pjp1i6GMtP2acnen94a5kN","name":"Bash","input":{"command":"sed -n 122,140p ~/wp29/gates/pgar_gate.py","description":"Show phase ledger check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":740,"cache_read_input_tokens":52674,"output_tokens":101,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":740},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt6k2fPP1DRQdwiwEZp","requestRef":"4eaba32b-eee7-478c-9ff3-a2d7892e38c3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c7e2ceb9-2b47-405b-bdc2-a694097fc10e","timestamp":"2026-10-30T05:37:49.578Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}116{"parentUuid":"c7e2ceb9-2b47-405b-bdc2-a694097fc10e","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Pjp1i6GMtP2acnen94a5kN","type":"tool_result","content":"    # 5. phase ledger\n    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n    if \"phase_ledger_consistent\" in fam and os.path.exists(pl_path):\n        pl, perr = _load_json(pl_path)\n        if not isinstance(pl, dict):\n            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n        else:\n            bad = []\n            for pid, st in pl.items():\n                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n                    bad.append(f\"{pid}: invalid status\"); continue\n                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n                    bad.append(f\"{pid}: passed without recorded checks\")\n            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n            if not_done:\n                bad.append(f\"phases not terminal: {not_done}\")\n            add(\"phase_ledger\", not bad, \"; \".join(bad) if bad else \"consistent\")\n    # 6. exclusion ledger\n    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")","is_error":false}]},"uuid":"11d62aed-90f6-4c58-a5b9-15f93630a8c6","timestamp":"2026-10-30T05:37:49.607Z","toolUseResult":{"stdout":"    # 5. phase ledger\n    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n    if \"phase_ledger_consistent\" in fam and os.path.exists(pl_path):\n        pl, perr = _load_json(pl_path)\n        if not isinstance(pl, dict):\n            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n        else:\n            bad = []\n            for pid, st in pl.items():\n                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n                    bad.append(f\"{pid}: invalid status\"); continue\n                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n                    bad.append(f\"{pid}: passed without recorded checks\")\n            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n            if not_done:\n                bad.append(f\"phases not terminal: {not_done}\")\n            add(\"phase_ledger\", not bad, \"; \".join(bad) if bad else \"consistent\")\n    # 6. exclusion ledger\n    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c7e2ceb9-2b47-405b-bdc2-a694097fc10e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}117{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"a25195d20ce1d077022587497406bbd37868f109e44a90b7e875a8ed7569c957","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Pjp1i6GMtP2acnen94a5kN","name":"Bash","input":{"command":"sed -n 122,140p ~/wp29/gates/pgar_gate.py","description":"Show phase ledger check"}}]}}118{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"0d78a552-f61c-4fa2-ad53-74b858a46544","timestamp":"2026-10-30T05:37:49.610Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"4eaba32b-eee7-478c-9ff3-a2d7892e38c3","keep":38,"tail":["a25195d20ce1d077022587497406bbd37868f109e44a90b7e875a8ed7569c957","23a398b3677b1b03a8e0e67676ead9cfe48d73502ed9da97a7d1aadebdab4832"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",39,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"18d61215efa41ad4131f13d8a9e048a27131170bd7382d3daa5dae8c83c2ef0d"}119{"parentUuid":"11d62aed-90f6-4c58-a5b9-15f93630a8c6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6rv9LF8a3LWXqMyjw","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":552,"cache_read_input_tokens":53414,"output_tokens":1139,"output_tokens_details":{"thinking_tokens":665},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":552},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6433,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt6rd2h3XGxsxs5wRtP","requestRef":"0d78a552-f61c-4fa2-ad53-74b858a46544","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fff9a696-bbd0-4ab0-be77-7c3f8a2f5b56","timestamp":"2026-10-30T05:37:57.131Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}120{"parentUuid":"fff9a696-bbd0-4ab0-be77-7c3f8a2f5b56","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6rv9LF8a3LWXqMyjw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HBCrs4sncAtatYhDSHSxrA","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; shasum -a 256 out/forecasts.csv out/table1.csv > /tmp/h1; rm -f out/results.json out/forecasts.csv out/table1.csv out/figure1.png out/state/aux_diagnostics.json; ~/wp29/venv/bin/python out/analysis.py > /dev/null; cmp /tmp/r1.json out/results.json && echo RESULTS_IDENTICAL; shasum -a 256 -c /tmp/h1; ls out/figure1.png\n~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd\nfc=pd.read_csv('out/forecasts.csv')\nbad=0\nfor V,g in fc.groupby('origin_date'):\n    v=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv'); \n    bad+= g.target_date.isin(v.iloc[:,0]).sum()\nprint(\"rows whose target month is already published in vintage_used:\",bad, \"; vintage_used==origin_date all:\", (fc.vintage_used==fc.origin_date).all())\nEOF","description":"Clean-state rerun and real-time availability check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":552,"cache_read_input_tokens":53414,"output_tokens":1139,"output_tokens_details":{"thinking_tokens":665},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":552},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt6rd2h3XGxsxs5wRtP","requestRef":"0d78a552-f61c-4fa2-ad53-74b858a46544","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c71babf9-2062-4791-a2bf-07ab219aec72","timestamp":"2026-10-30T05:38:00.506Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}121{"parentUuid":"c71babf9-2062-4791-a2bf-07ab219aec72","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HBCrs4sncAtatYhDSHSxrA","type":"tool_result","content":"RESULTS_IDENTICAL\nout/forecasts.csv: OK\nout/table1.csv: OK\nout/figure1.png\nrows whose target month is already published in vintage_used: 0 ; vintage_used==origin_date all: True","is_error":false}]},"uuid":"dfd061d1-fa9e-47dc-a19a-20d451a598c9","timestamp":"2026-10-30T05:38:01.462Z","toolUseResult":{"stdout":"RESULTS_IDENTICAL\nout/forecasts.csv: OK\nout/table1.csv: OK\nout/figure1.png\nrows whose target month is already published in vintage_used: 0 ; vintage_used==origin_date all: True","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c71babf9-2062-4791-a2bf-07ab219aec72","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}122{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"1ee9d72691e695a84fedeabcdf35f63f588db644fd6ef3da36441a0f8f58b2b9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01HBCrs4sncAtatYhDSHSxrA","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; shasum -a 256 out/forecasts.csv out/table1.csv > /tmp/h1; rm -f out/results.json out/forecasts.csv out/table1.csv out/figure1.png out/state/aux_diagnostics.json; ~/wp29/venv/bin/python out/analysis.py > /dev/null; cmp /tmp/r1.json out/results.json && echo RESULTS_IDENTICAL; shasum -a 256 -c /tmp/h1; ls out/figure1.png\n~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd\nfc=pd.read_csv('out/forecasts.csv')\nbad=0\nfor V,g in fc.groupby('origin_date'):\n    v=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv'); \n    bad+= g.target_date.isin(v.iloc[:,0]).sum()\nprint(\"rows whose target month is already published in vintage_used:\",bad, \"; vintage_used==origin_date all:\", (fc.vintage_used==fc.origin_date).all())\nEOF","description":"Clean-state rerun and real-time availability check"}}]}}123{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"7a44e11d-ab64-4324-9d3c-b622866ed1be","timestamp":"2026-10-30T05:38:01.464Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"0d78a552-f61c-4fa2-ad53-74b858a46544","keep":40,"tail":["1ee9d72691e695a84fedeabcdf35f63f588db644fd6ef3da36441a0f8f58b2b9","d4a62c5e59bb5b3b2f582cffdc3c6e64271998151da2f43a651dbe2bf24b6dc5"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",41,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e235561871ca071f92fe7da2ba3f6179f9c10981369c819daa1a003786d0057b"}124{"type":"tools-used","tools":["Bash","Read"],"sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}125{"parentUuid":"dfd061d1-fa9e-47dc-a19a-20d451a598c9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7jbsvmqZbaSC9HFaR","type":"message","role":"assistant","content":[{"type":"text","text":"Let me view the figure quickly."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1224,"cache_read_input_tokens":53966,"output_tokens":92,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1224},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt7jJX7aarkpLV1fMeY","requestRef":"7a44e11d-ab64-4324-9d3c-b622866ed1be","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"522c8807-d453-4c65-838c-5d9cbfecebd3","timestamp":"2026-10-30T05:38:02.306Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}126{"parentUuid":"522c8807-d453-4c65-838c-5d9cbfecebd3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7jbsvmqZbaSC9HFaR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01P3YWfN8DQb67hL9QQU5pm5","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/figure1.png"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1224,"cache_read_input_tokens":53966,"output_tokens":92,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1224},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt7jJX7aarkpLV1fMeY","requestRef":"7a44e11d-ab64-4324-9d3c-b622866ed1be","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"05eab99b-89ec-4f19-8c09-75f9d9144480","timestamp":"2026-10-30T05:38:02.693Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}127{"parentUuid":"05eab99b-89ec-4f19-8c09-75f9d9144480","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01P3YWfN8DQb67hL9QQU5pm5","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"iVBORw0KGgoAAAANSUhEUgAAA8AAAANICAYAAAAINYYuAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAASdAAAEnQB3mYfeAABAABJREFUeJzs3QV0E1kXB/B/U/dCS1ugFHd3WJzFZXF3FlhscSks7r64LSywy4f74rC4OywupdAidfc2/c59aUKqVNImae7vnMBkZpJMJtNk7rz37tWLi4uLA2OMMcYYY4wxlsNJ1L0BjDHGGGOMMcZYduAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDHGGGOMMcaYTuAAmDGWbm5ubtDT00P//v157zGmBWbNmiX+Zi9duqSy54yKikLx4sXRqlUrZJUVK1bA0NAQL1++VNlzFipUSNwYU7WGDRuKvzPGmGbjAJgxlqPduXMHU6ZMQcuWLeHo6ChOTpycnFT+OnRCTc8tv0kkElhbW6NWrVpYuXIloqOjk31cbGws/vjjDzRo0AC5c+cWJ/v29vaoUKECBg0ahGPHjqX6uv/73/8Ur3n27NkU16PAR3n7krvRhQ25iIgILFu2DDVr1hTvw8jICHnz5kXVqlUxcuRIXL58+bv7pGPHjuJ5KYhJyd27d8V7Lly4MIKCgr77nDExMWKb6HkPHz6c4nq0jNahdekxOd327dvF+6X/s8vq1avx9u1bzJs3L8F8+hyHDx8u/s5sbW3Rtm1bvHv3Ltnn2LJli/j8Hz58mOzyYcOGIU+ePJgwYQJygpwYfGfFxRVNRRd9E39XMsa0j4G6N4AxxrLSrl27sGrVKnGSXaZMGXh6embp640ePRo2NjYisP348SMOHTqEsWPH4t9//8U///yTYF1ap02bNjh9+rR4TOvWrUXQQC1rz549E9tOLV8//fRTiq+3efNmcUIWFxcnpps1a5bq9hUsWDDFlnvaBhISEiIC8gcPHoiLBp06dRL/0/zHjx+L1wkICBDrpIYC+1u3bmHq1Klo2rQpypcvn2B5WFgYevfuDalUir///htWVlb4HgMDA+zcuROVK1fG4MGDxQUGCsyVff36FUOGDIG5ubm4QECPYaoVGhqK+fPni8+1SpUqCZbR8UUXbuizNTMzE0H5jz/+iOfPn4v7cp8+fRKB7eTJk8XnmRxTU1OMGTNGrHPjxg388MMP/FEyxhjLFD4rYIzlaHQy3q9fP5QtW1a0YmZ19zQ6WVdu4Zk+fToqVaqE48ePi1ZT5aBx9+7dIvitWLGiWEYtrYkDxNu3b6f4Wq9evcKVK1fQpEkT+Pv7i6CDAnwHB4cUH0PbRi02qaEWawp+KZimoJ32mzJ6rRcvXuB7qPVv27ZtovW9V69eorXX2NhYsXz8+PF4/fq1CJDr1q2LtKJut9Sq/Msvv2DAgAE4depUgs914MCB8PHxEYF6sWLF0vy8LO3o4gxdBEl8MYWOP2p9nz17NmbMmCHmUSs8rUd/A127dlWsO3ToUOTPn1+xXkookKZeHOvXr+cAmDHGWKZxF2jGWKZQV7Du3bvDzs4OJiYmqFatmjjR1RQUfFLrUuIgLrtQACYPeikAVEYtWoSCg8TBL6HWskaNGqXawkooCKTnoG7WqugCK98u6n6a3H7LlStXmgOR5s2biy7T//33nwhi5E6ePImNGzeKLtXygDwwMFCsU7JkSXEs0evQ48+fP5/keamFl1rGz5w5gzVr1ijmU5BEAXG7du1EC3FaUSBOLd30mtRyTO/vxIkTKXYtlndlpe6+48aNE9PUy0D54gK1+rdo0UJ0bafAv0SJEnBxcRHvU1mPHj3Ea7x58ybBfLpwQ/Op9VRZcHCweK369esrxh3SMUDo/5S6tcsdOHAANWrUEMcXbRv9/VJrbHps3bpVHBvt27dPMP/Dhw/if3p+Ofm0fBmhVnw6Bv7888/v/m3my5dPvFfa7rR0k08r+hzo2KQgnI436iFC3bqpN4Uc9cCg/Zja3yH1bKDP48uXL98dgkD7gG7Kn5HyRYQjR46IgJ+OFToO6UZ/I7Rd1FMipS65rq6u4u+Ahk5QqzkdExk9tomHh4fYN0WKFBHHLl3Mor+3xN9hdNzTxQ5C+0j5fX2PfJ/Q38y9e/fE3wp9D9J20va6u7uL9ei90TFKXeHpvdHrUE+U5NBnMGLECLFddFzRY2goxv3795Osq/z+L168KPaZpaWl6IlCvXESX+SjdXfs2CGmaciG/H0m16Wdhl0sWLBAXKyj/VegQAHRi4F69zDG1I9bgBljGUYncnRySydJffr0gZ+fH/bu3SuCDwpaUjtp1GR0UkknOtR6qcpEX3SSrIxOKuUnqOlFJ1K0jXTC2KFDB4SHh4sWVRpTOWnSpEy1dGdmu5KzZMkSEQxSyzKdWFKLN7XSUgBGXZRpv1BrYp06dUQ32erVq4uWdGrF3bdvn2iJ3rBhg2jxVUbvlYIPOrGkVnDq6jxx4kTRAi6/OJAWFORQUEAt27R9FETQSTft19QSPNFn0LhxY3Hc0zbSiTOdGJNNmzaJCwgUcHTp0kWM66YT/sWLF4tW9evXryu6nFOAu2fPHrGP6IRZju7LL0jQmGwK0gj1FqATbHlgTMcoPdfRo0fF3x5d9JGTv4byBQLqKUDBDF2YoR4G9DdLAcWjR48StNCnFjhSwEKfk3KXZuLs7Cz+p4CDAhpC68q738tbienzpaEB1DqcFnRs0P6jHg80bCCz6LOjY4aOOwqu6P7BgwfFEAbqWbFu3TqxXqlSpcT3GAVI9PdAgaky+myePn0qArbEXfGVUZA0c+ZM8TdA6P3LKX9edIGE8gfQfqHAnPb1hQsXxHZR8ElDBZJDy69evSqOXzpm9fX1M3xsy3t/0HFNF6AogKS/RQrOqacGtfDLH0vvg+bTMUkXbDIyvpneF/1d0PFIF63oYhkNHaH9Ssc0vSZ9Dn379hW/ObSMut7T+7CwsFA8z/v378W6nz9/Fn+XdGGJguj9+/eLgJ8+3+SOHbpgS69DPVWoVwJ9B9HFGdoumqaLu4Q+P3qv9LciH+qS3N8Y6dmzp/g86Dnpe4Gej74Hvby8xO8KY0zN4hhjLJ3ev39PTSTiNmvWrATLTp8+Lea3bNkyzc+3bdu2uJkzZ6b5RutnFG1b/vz5U12nX79+Yr30vE7BggXFY2jfKHv58mWcmZmZWHbv3r0Eyx48eBBnaGgYp6enF9e7d++4gwcPxrm5uaXp9Xbv3i2ec8iQIYp5nTp1EvPOnz+fZP2LFy+KZbSdye1TWi73zz//iHWNjIzihg0bFnf8+PG4z58/x2XGw4cPxfPRvqdjg55//fr1iuX0PuTvRyqVKua/fv06zsrKSjw28b4lJ06cEI+rVKlSXPXq1cX0yZMn07VtjRs3TrI9hJ5HfpwnPhbkn/ePP/4YFxISkmAZfYa0vZaWlnEvXrxIsIz2Jz1u8ODBinnv3r0T8zp37pzguKF5TZs2TfKZjhkzRsy7cuWKYh5tX2rHLH3GtJy26cmTJwmW9ejRQyzbu3dvmvbXqVOnxPojR45Mdnm7du3EcT1gwADxfun4d3Z2VuwnOk6LFy8eFxYWFpdWR44cEa85ceLEuMySf3Z16tSJi4iIUMz39fWNK1KkiFh2+fJlxfz9+/eLeePHj0/xu+Ls2bNpfm26peTt27dJ5sXGxsb17dtXvM6tW7eSff18+fLFubq6ZvrYjo6OjitatGicsbFx3KVLlxI85tOnT+J1HB0dE+w3+bGl/B2SFvLvJLrt3LkzwbKBAweK+bly5YqbN29egmVz5swRy1auXJlgfrNmzcT8xOtfv349Tl9fPy537txxwcHBSf5maFni70wXFxexbPHixcnu7+S+i0iDBg3E8ipVqojjSY6OfdqvEokk7suXL2neR4yxrMEBMGMswwEwncjFxMQkWU4nu7a2tml+PvlJQ1pvtH5WBsAU7FHgEhAQkO6T6tGjR4sTwmnTpomTVnNzczF/woQJyT6Ogg46oVR+f3Si1r59+7hjx46l+HryE9sbN24kCVy7du2a6slmcjfaZmWrVq2Ks7a2TrAObWfPnj0TBAfpQSeT8udq3bq1Yn5kZKQIkiwsLBKcNMrRvqTHzJ49O9nnlQeVdBs+fHi6tunjx4/iccWKFROBRmJNmjRJNQB+9OhRksfQCTgtmzJlSpJlfn5+Igg1MTFJEEQUKlRI/M3Ig/9169aJ57h586Y4QVd+rvLly4vjKioqKt0B8G+//ZZk2YULF1IM8JKzadMmsf78+fOTXU5/N3QhI2/evCKAadWqlbiQIQ8m6YIPBe/0/imIpnUoYKa/62fPniX7nBT40Wt269YtLrPkn53yBYTE+7F///4JgkJ6L/T5KH9m/v7+caampiKwUb5ok5kAOCX3799P9m9AHpAlDgYzemzLLzSk9H1Fr0PL6cKTqgLgunXrJllG3zG0jP4uEv/G0AWmxJ+Ru7u7mEe/Pcp/F3J0gZGW79ixI8ln3atXryTr08UEWkYXazISAJ87dy7JshkzZohl9D3NGFMvHgPMGMsw6ron72qnjMY7UZe7tKKujfEX5NJ0y+pyG9SVkbrcJTcu93so4zSNiaPSMH/99ZfIlktj3JYuXZrs+pQUiLJF01hWSphFXfRorB91taNuqtStUHlMIqHSM9Qlk8bK1q5dWzGfupxStmZ6LHVZTA51M0xunyZOjDVq1CjRlZCei7pUU5dDGntKyY/oOb6XuCg5lPGXto8o7w/qckoJv6hrNI1JTYy6M5KUSuUsX75cMU2lm9KDuv0S2o/U9TSx1JJzUZdk6lKaXBdS5e1WRuMbaUw6dWlWrm1L6/r6+iq2h7q90nFIWa5pDKi8O7S3t7foGkrblbhLfVrQGP3k/l5JWv9maTvl7yU59HdDXcDp+KFutNT9lLp20zSNK6USSfXq1RNd1ylRGR171C2bnpeOYdo3icmPi5SO6/Si7vLJjWOXj51VPtZoXeqaS9tH3WjlqDsyDT2g8eiqSq5Hr0HdoOm4ou698nGmdAyQlMZqK4+5zsyxffPmTfE/dTWmzyXxjcrKkbQkwcvMMUnjvlP6jaGu4fJxynLyz4uOq+T+LlL7DlHF30R2PCdjTHV4DDBjLMOSG/skvlgMDJJN2KILaBwajYOjk3g6AaUxZRQQy8dJJ4dO2GjMnbyEEZVHohNtGidLQTSN11NONkTjWyloTTw+mfY7ZVumgJASu2S2diqN76QxpXQjNE6SXpvGv82dO1eMDVQev/g9dBIuH2NKyWzk5EmhUhpDKZ9P4zWTo/xcytNpIX/tlDJnp5ZRm8b1Jhf4ZOT90HheSghFgS5dCKALHPJxlrSMxg/Kx4PSZ584MVZm/mblZaLouEsL+T5OLlBNDV1UoccuWrRIXBiicd30N0HzCY2XpmRXdJGFjn1lFGgqv3Zm0bjO5C7eyS/QJE5URkEulX2iwJ7GdxIK3inRkjwBWWbR8UDjquk7hAJaGvNKgT99PrSMLq5FRkYm+1j5dmf22JZf3KBxs6mhkmiqktyFRvkxmdoy5drqmfkOUcXfRHY8J2NMdTgAZoypHQVryWWrTQkFmKpMTpUVqHWQWu8oIzG1JlNCJApa5C0bqaETc2oZpmQw1JJMQY88AFbO9EwZk5UzKyujQDWzAXBidLJPGVapti9l8aXtSk8AnBL5SS7V702OPLtuRlrkv0deezil+tCp1Y1OqdVP+f1Q+a20vB95CxUlj5Mn1pIHuXR/4cKFIiiWtwQn17qcXSjwVw6W0oJagSnh2blz50TL5pMnT8QFFeUawvJWTqqBnZj8teSvnVnUkkyBSOIgWH4MJj7WqNWRemRQAihquafPh1riu3XrJjINqwIldaPgl5ItJe6RQS2zFACn51jMyLEtf9+UFCq1+uOaRp3fIYwx7cMBMGNM7SigoyyiaUVdcDU9AFZueaA6t9StkU5s05OdmEpyEOUu0HRiSplEqftzSt1z5RlrE9cdVpXktisz6L1QazNlV6UWmsStJ/R+iHKwpCryAJ4CDOq1kLir6LVr19L9nNTFmTLVUlf9xC219P6oZwBdICldunSCFjwqw0OZY6k2NJE/ljIgU8s5Bb900UHejVqZPJDLjtYlebdv5S7cqaHWOcrg/fPPP4vMy8qUWzRTa1GWv5YqLrgQyqJNGZypy6wy+fCKxPuXUNdtCoCpFVjejTVxZvLvoc8ppVI4NLSBUEbpxNLz/ZiZY5su2hE6DtMaAGfnsZcS+edF74k+W3lrq6q/QzThvTLGMo/HADPG1E7TxgBTawGdcCfuBplRv/76q+huSIG+cq3X3bt3ixax5LqLU0uGPFiW13uVd7skc+bMES1Gyd0o4FZeN72oPi+18iaH9ou8e6TydmW2ZZm6btMYYxoHrezdu3eiBip1E0+pC3lmUNkeGvdJwQcFNsooEE2uBvH3UB1X2l6qyyoPauTo/VEtW1oncckhatWlsdDU0kdjZuVjBqnbL43jpJJQtD9oexMHM/LSVTSePKtRqza1eqZ0jCRG5bkSj9UuWrSo+NyVa4ZTeSj58ycmf63EpdWo50hKtVi/h3pPKAfg1KpLPS5Ict2a6YIElUGi8mP0WdCFm/SWeqPPicZxy7t0K5O/h8TfbzRulXoAZMexTcMd6LOhMlBUuic5FFDTcar8nrLr2EuJk5OTyFNAx4O81JQclfqibvV04YiGk2SGJrxXxljmcQswYyxHo4CNxhwqo9Yb5RZkSpwkr/UoPzFWZR1gat2kFmCqe0rJoyjwlZ+YUbBDrX/UmiuvIUvdIKnLKJ0k0wlp586dFfPppJW2VXlMcGLULZPqc9I4YgrCkksslRo6OaYu23RCTq2PFIhRoEDBOyXrom7YNG6TxiuqCn1G1Oq0du1aUX+TAgt5HWAKjGm+fP+oGp3s0/ukFj466ZfXSqX9R/ufWt2TSyKUEtpvdBJO3cWpxYm6s1PASK14FDxQl3iqe5pcgEXvk1r4aXx14mXywCi58b8UINNxRq9L3YXlY0Lp4ouqu31SwEmBBF1goe7KyQWscnS8bt26VQS3yttB431p//z+++8i8VWxYsXE3xsda/IxtnJ0gYiehwLOcuXKJVlGErf4paVnBh3T9HzU0knH9IEDB8TFLzoOkru4Q++bxvSPGzdOMS44veizo+Ob3jO9Bl0EoTHfbdu2FWN+KTkc/e1SiyVdBKG/ObpIQMcD1WvO6mObLtxQ7wWq/0t1gylRGLUk07FFNXVp2+nxtJ/kNaDpb5Weg743qVu4PDnatGnTkJ3owh29V6oFfvbsWZGISl4HmLaPji9575WMos+PPiNKikYt9fR81GOFkrsxxrSImrNQM8a0uAwSlYRIrRSEJvhe+Z/kSlqosg6wXHh4uKihSSVgHj9+rChTsnbtWlHyqESJEqI8DpWDoXJDVCv377//TlC+ZOrUqeI1xo4d+93toTqztO6KFSsS7Ie0lJB69epV3LJly+JatGghSrxQiSKqa1ugQIG4Dh06ZKqMR2r7icrKTJo0SZRtodejMkxUquXMmTPffV75Z5lRVPaK3hu9Jr3fWrVqifrHS5cuFc97+PDhdJezoe2mOr42Njbi/dC+pDq29D6TQ/OpTii93r59+xIso3JX8vf4/PnzFOvz0nbLS28p7+fUStV87+85OVT+iR5Dn1dKqOYqlbFJrswMoZJCVDbMzs5O1J1t1KhRsmWQaD/Sa/3+++9JlsnL9iRX3ikl8s+OyjVR2Sz6u6TPp1SpUqL8V2oljaiMFX1GVMbKx8cnLr2oHuzQoUNFKTYqb5V4v9P7b9u2bVyePHnEcUj1ZP/4448UP6PvleXJyLFNPD094yZPnhxXtmxZUeqJjin6u6SyQPS9RKWhlNG8ihUriv2S1r9F+XdS4hJsaTkmU/ou8/DwEPuXyiHRdymVrqK61Hfu3Emy7vdKh6X0GsuXLxfHCh0z8nKAafnt+97rMcayjx79o+4gnDHGGNNE1DWbuk9STwJqgWTfUCshJbOiFkFVZWdODrW0Ues5df9O3JpNrbHUvZfK9ij34sgq1ApPLZ7UhZ3KIGkzPrYZY7qKxwAzxhjTadSNNrnssZR0irqdUnIqDn6ToqEDNJ51/fr1WfbZ0PhXSjxFWZGT68pNgTF1R82O4JdQOSqiLV1e+dhmjLGkeAwwY4wxnUZZeWnsKbXs0fhcGk9KY1spQRklaqJxlCyp8uXLi9rFNEY7q9CFCao5TWNvk3P//v0s/2ioHBmNw6XXorJmbdq0Qc2aNaEN+NhmjLGkuAs0Y4wxnUYlTSjxEJUY8vDwEBluqUWRkhRR8rLkSuIw3UHZ2ykrNNXVpW7f1OKdXS3OmcXHNmOMJcUBMGOMMcYYY4wxncBjgBljjDHGGGOM6QQOgBljjDHGGGOM6QQOgBljjDHGGGOM6QQOgBljjDHGGGOM6QSdLoMUEBAgaghS+QtjY2N1bw5jjDHGGGOMMSWRkZFwd3dHgwYNYGNjg8zS6QCYgt/27durezMYY4wxxhhjjKXiyJEjaNeuHTJLpwNgavmV78xixYpB00RHRyMwMBDW1tYwNDRU9+YwDcDHBONjgvExwPj3gvE5BNOl88u3b9+KRkt57JZZOh0Ay7s9U/BbtmxZaOLB6OvrC1tbW408GFn242OC8THB+Bhg/HvB+ByC6eL5pbGKhqxyEizGGGOMMcYYYzqBA2DGGGOMMcYYYzpBp7tAp0YqlcLT01NkHaNpdW1DVFQUQkJCIJHwtQqW+WNCX18fuXLlgpWVFe9OxhhjjDGmczgATiHI+PjxI8LDw0XAQDc9Pb1s/3DoNY2MjNTy2kwzZeaYiIuLQ1hYGCIiImBiYiKehzHGGGOMMV3CAXAyqOWXgt/cuXPD3t5ebQEoBeKxsbEiAOcWYKaKYyI0NFRc3PH29kb+/Pl5pzLGGGOMMZ3C/WqTQd2eKcBQZ/DLWFYwNzeHgYGB6EbNGGOMMcaYruEAOIVWNnV1e2Ysq1HLMXWHZowxxhhjTNdwF+gUcPDLcio+thljLOfX9Lx8+TI+fPiAggULokGDBhpd21OVBu24iw++YWlat6CtGbb0q57l28QY0ywcAGfxD9D169fh5+cnxhPXqVNHZ36AGGOMMZb95x2LFi3CunXrRD4TOUdHRwwfPhwuLi45/jyEgt83XiHq3gzGmAbjLtBZ9AM0d+5cFChQAI0aNUKnTp3E/87OzmI+Lc+K1+zVq5cItC0sLBAYGIiyZctix44d0ETbt2+Hk5MTNBldvKhYsaLaymClVcOGDTFt2jRFkiu62v/69Wt1bxZjjLFsROcB7du3x4wZM+Dl5ZVgGQXDNL9Dhw5Zcg7CGGPahAPgHPIDdODAAVy8eBFubm6iRqy1tTWePXuGfv36Zfg5+/fvj969e0NX/frrr5g9e7bKMnAXKlQIW7ZsQVYnuRo3bhzGjx+fpa/DGGNMs1DL78mTJ8V04jwP8vsnTpzA4sWL1bJ9jDGmKTgAziE/QO/evUORIkVgZWWVpvVpW2JiYpAVcsLVZbqY8PXrV7Rt2xbapm/fvjh//jy3AjPGmI6g313q9vy9HA+0nNbLCb/TjDGWURwA54AfIGqpnTNnDm7evCm6P7ds2TJJiyO1DNPrbt26VXTrNTMzw71790SgV61aNdFibGtrK8Yp+/v7Y8GCBfjf//6HvXv3iuekG9WPTen9/P777/jhhx9EC+TBgwdFrdrly5ejdOnS4rmrVq2Kf//9N8X38L31nz59ih9//BF58uQRy2vWrIkLFy4olgcEBKB79+6ws7MTFwFKlCghWsXlbt++LboK03ukLsLTp09P9QIAvQd6PcoGLnfp0iXxHuk5cuXKhcaNG+PRo0cJHkefAc2n7aDu6NT1nWpK02dC+2/kyJFiX1L39JRa2ZW7NJMhQ4aIz5IeV7RoUdEqnVq3bNq26tWr4/DhwymuwxhjLOegITvUy+x7Gf5pOV3cpfHAR44cERdKs+piuDbwCAjHrGPPsOv2R3j4py1xFmNM+3ESrHQYM2ZMkoBHGQVhykknvvcDREGKjY1NiutRoLps2bI0jaelAIla/a5du5bqun/++SeOHz+OfPnyiR89ajWeN2+eCMQoIL9//z6MjIwwdepUxQ/jzp07v7sNmzZtwqFDh0QAGxERIcY6048r3YoXL46jR4/ip59+wpMnT0QQl1ha1qfkHXXr1hVdkhcuXCi6kr9580bUa166dCmCg4Px/v17RbBO42HJq1evRDBLFwM6d+6MT58+iec2MTHBb7/9luz7oYsD9PzKKHEIfR50wYBqRVM343bt2oltoH1GXc4p+KV1aB9Tvd0bN26I7T116pT4jCiwHTRoENKjRo0aYv/Q+6QAm1ql8+fPj2HDhqX4mAoVKuDu3bvpeh3GGGPaiZJtpgf9HsovkNPvF100LlOmjPgNl/9P84yNjZGThUfFYvsNNzG9rmcVOOUyUyz75/FnhEbGoLiDJYo7WMDKJGcnD2NMl3AAnA4U/FJZAVV5/PgxshuNQabkXIRaN+mHj7pPf/78WQRVtWvXztDzjh07VvxoElNTU9EivG/fPpQsWVLMo2CSWk93796doHVT7nvrlytXTtzkZs2ahZUrV4qWXQoI6X34+vri5cuXovWYWnnlqLWd1qEWYkLLJk2ahJkzZ6YYANPJBLU0K6PWcTl6PerG/scff4gAu3z58tiwYYMItEeMGJGgNTezlAPmWrVqoWfPnjh37lyqATBt+/PnzzP92owxxjQf9TjKqKioKNHLim7K6OItXYBOHBiXKlVKXGjOCYwNZB0hI2OkKOGQ8D1tvfYej9wDFPfzWpuIYLiEvYUIiGm6pIMlzI35VJoxbcN/telQqVKlVJdTC3B6glpq4f1eC7CqFS5cOMH9Y8eOidZUChrpB40ySVP3YGq9zOjzUit4UFAQunTpkiCBFLUwFytWLMlj07I+tehS0EotqrSfaT16jDzR2MSJE0U3agoWad0mTZqI90WPpxZa6uqtvK+pC3Fq3YjpZIIyaSuj1mgKmB88eCBam+XbKt8Gan2mEwNVot4C1B19165d4iIF3acWduo9kBra9sycEDHGGNMedIHWwcFB/B6l1g2ahizRevR79vbtW7x48UJcLJX/T8Ol5Og3kn4/6Ua9spRRVQvlwFg+TUNwtIlzbjOcHlMf7n5hcMplqphP+5DmKfsSGCFuV157K+bNaFMGA+t+O/95+ikQ0bFSERxbcGDMmMbiADgdqMUxNRSwUetqWn+AqItqavX46MeHgjpVSpzRmFouKbiSt3A3b95clCcaPHhwurIfK69LgSZ1L6ZuwPXr1//uY9OyPm0PtWrSPqN9R/uXfmjl+5nGNNM4aLpR6y21wlIGbBoXRfUPqdWUun+nFV0QoC7NyihAp7G8f/31l3htGitNQaZ8G6iLc2rlh5Lbn5aWlvDw8EgwjwJduT179ojj7vTp0+ICDB07o0ePxsOHD1Pd/v/++08xFpwxxljORucS9LtHvbxSQ79XtB7l06Bb4l5fNHSIejUlDowpWFY+H6ELzXSj3yZl9Hur3Fos/59+t7+XH0Vd9CV6KGRnnmAebevtqT/io18YXnuG4K1XsPj/tWcwXL1DERUru4BewsEywePWXHiDM89kQ+Hy25iKlmJap7h9/P8OFjAz4lNvxtSN/wrV+AOk7mL01O2JEl21adNGkVyKukXLW3/ph4xaTulHTzkZ1PfQmKGhQ4eKFttt27aJVlFqtaTglZ6TxhWld31q0aQu2hR40g80jYmlck/KLdnUVYu6UFMwTN2w5e+Dkn1Q12QKCGnMLr0Xaq2lH/QWLVok+x46duwosikrv3faBkqwRfuJguwJEyYkeAx1SabxwRs3bhTBt3wMMHVbpvdI74VOLJTR+n///bfouk3bT921advk6DXpeWj8L/0g0+dBFyzohCIl1EJ+584dMS6bMcaYbujTp48Y2pPcBXj6/aD5rVu3xuTJk1N8DkpkWaVKFXFLfL5ALcHKQTH9T79plBNDjvKb0I1+q5TRb3fi1mL6nxoNNDUwNtCXoEgeC3EDHBXzY2Kl+OAXhjeewSjvlHCo1BvPb+clnwLCxe3Sq28txmRi85IY0ehbbzi/0CiYGEo4MGYsG3EArGKUqInGpVKpI/kPTnp/gLITZUqmbaGgkrIbUzIsee1gyj5MP2KU0Zi2m7pMUbentKBEUGvXrhWtpu7u7qKFl35QU0rq9b31V69eLQJM+hGl7aHgk1qq5ShopKRUX758EcEmBZ2U8ZpQd2EaM0tduykYppZ6aq1NbQwtBcwUdP7zzz+irjOhFmR6DcpWTcH4/PnzRcAuR2OUKREZdZOeMmWK+LwrV64sWrYJXRgZNWqUGDdM+5H2J3U5p8RWNN6ZxhXThQDlscb0eVBiM2qppxZk6tpNrdmptQBTCzVtv6q7YzPGGNNcdAFVfs5Bv+eUF0OOWmDpwjv93mfk4jv9PlH1AnkFAzm6SEy/v4kDY/pfnoiSUI8puiBMt8QBNwXDiVuNaVhVeodiyRW0NQPtBTefUMRI42Ag0YO9KRArlV3QNjM1UwTdtG5GAuOieSzELbHNfauJVmK6UTD8xkvWYkzbIedoZZLgMb+fe42dtz+ILtgl7KmV2FKMR6YW42L2FjAxTHsDhLJBO+7ig2/Cbtx0fMgv7CtfeKD9sKVf6kOrGMtJ9OK+lzM/B6MurhS0UOIH5S91V1dX8T9lSM4ICrAoQRL9GNGVUDlqAUzPD5C8CzR9UaWnOzJTDQo86fOiYFNT9v/3jgk64aBj+cyZM4qEYoll9vhmmoW+b+hEl0541d2rhKkHHwOMev7QhVXKT9GgQQNx0ZeSdn748EEkfqR52fn9QKeWNLxHOSCW3ygYTkvATb9hiQNjqhKRlszUB+57YMJ+WU6W6Bt/4fPVfQnOxehiODVYZMc+oTHBFIzLu1B3qJw/QZfrbptu4vb75LN4U4xK45T71i6En5XGGqdF0xWX8cbrW4t0aqiL9rlxDdL1/Cxnidbwc4mUYraM4hbgLEAHDmUupkCXxqBSd1kaK0ote5p4ULHkUckldWTqzgy6mq6cxIQxxljOR1UIKPgl8ovsFPSq64SWWhepezPdKLeIcmBMeVIStxbT/9SDS7nLNeWyoJsyuvibUmZq+v0jsdI4rL/4RkzHBPviy80jSRJvUo8s6q13+PDhLN83hvqS+FJKlmiNvEmWD65XBDUL55YFyF7BotWW3gOhJiq6HxWTMGnn+ktvse+ue4LW4uL2lihqbw5jg4y1GDOmSzgAzkL0paqKMjiMMcYYY8mhnBmrVq0S0zRcJqXcFppAngSUbonPj6gVO7nAWPmiLvWAomSTdDtyJGFgSy3dFBBblqkPV4PyYl7Q3cOIi4lKsJ684yMNVaPeesmVZsxOTco4iJtcZEws3se3GNM4Y2o1rlQgYcWQF1+C4eYbJm7nnsuSbhGJHlDI1lwk2wqKiM7W98GYNuEAmDHGGGNMS1HeB2rVJJRMUlOTSqWlIgRlpU4uMzUlikwcHL979y5BZmrq7k23vA4tYeQAxIYFIuTRqRRfj/YTDVXL6LjorEItuKUcrcQtJTUK5UJkdKzo4vzBNxTyIcb0v6tPqLjZmGrOe2JM03AAzBhjjDGmhSgAXLp0qZimMcDdunVDTkNdm6k0Id2UUfZpykytHBg/9o5FuIMsv0XwvWOIi/6WoToxagmmPC00VE3beuv1qV1I3EhEdCzeeVNrsWyMsWg59gpGeJRqy2gylpNwAMwYY4wxpoVoDCuV9CNUpUCTWjKzGiXDoqQ4dJMHtJ033sT9D/6QRoYh6IGsAsP3UJ4WbUZZosvmsxa3xEmwvIJTvgDAmC7TjNS2jDHGGGMszSjgozGshBJd/fzzzzq992hob7tK+WBroofgBycQF/mtDFNqKEkpY0y3cADMGGOMMaZlLl68iHv37onpkSNHKrIg6yqJRE+UC7rq8iOM31387lhoWk4lkahCB2NMt3AAzBhjjDGmZeStv6ampiIAZjJmJsYY8csgRbbnlNDyESNG6FS3ccaYDI8BVqFBO+6Kem1pUdDWDFv6VYemsLCwwPHjx7UuEQRjjDGmax4+fIizZ8+K6UGDBsHOzg66zCckEnYWxor7Li4uos4vlTqilt7kguFKlSqJDNCMMd3DAbAKUfBLKem1UUiIdm43Y4wxpmvkmZ/19fUxbtw46LKXX4PQds01tK2YD+OaloBTLjPRqksJwqiVnEodUbZnOYlEAqlUCn9/f/F/TkUNLYnRhQDKHE7HjXIX8eTWZSwn4wCYMcYYY0xLvH//Hnv37hXTVPaoUCFZORxdtf7iO0THxuHIw08Y1bi4Yj4FwdOmTROtvFTqiLI9U8KrZ8+eiS7jVDN4w4YNGDNmDHKi5HoZRkdHw9fXVyRN467fTJfxGOAcgroujx49Gj179oS1tTUKFCggvtjJly9f0KZNGzg4OMDS0hIVKlTA/v37EzyergSeP39eXA2lx/79998Jlq9YsUI8Tu7kyZOoWbMmcuXKheLFi2P16tXZ9E4ZY4wx3bV8+XJFy+WkSZOgy9x8QnH8yWcx3aZCPhSyS5oIjAI9Okfq2LGj+H/IkCEoUaKEWDZ37lwEBARk+3YzxtSLA+AcZPv27WIsEHXrWblypbjCSfUBqbvLwIED8e7dO3EFVB4o01XQxKhr0IABA7B169YE87ds2SKeW555kh6/YMECcSWRuhlRd6z//e9/2fZeGWOMMV3j7e2NP//8U0y3aNECFStWhC7bcOkdpPHDe0c0KqaYf8btDKKl0ck+hgLieQvmwaq6lTgnkicTY4zpDu4CnU7777njwH2PZJd5+Ien+Xlo3W6bbiaYt/eX2siMTp06oXHjxopp6upz//590UXKyclJsR7VCqQW2wsXLqBs2bJJnoeC5fnz54vguVixYqLrkKurK3r37i2W//777xg2bBh+/PFHcZ+K0A8dOhTbtm1Dr169MvUeGGOMMZa8NWvWIDxcdq6h6wmcPgeE49BD2flY0zIOKOloqQh+J1yegGYFm2FR/UUwlCTM8kyB8S3bW3Ae4YyP6z6KBgPKBq18nsQYy9k4AE4nClxvv/fL9I4Pj45VyfMoy5cvX4L7VBMwODhYtAhTNynq4kwtttTKS0mvvLy8kn0eGk9EwS21Ai9cuFC0/lLXIXmx+Ddv3ojnknexJtTK7OzsrNL3wxhjjDEZ+t1eu3atmK5RowYaNGig07tm8xVXMfaXjFRq/W3s3FgEv2c/nAWuIEEQTMGvyxUXsayKeRU8ffAUiAVmzpyZpOcbYyzn4gA4nZxymaJmYVkgmNgTj0AR2KaFqaE+KjhZIztQOYCXL1/i8uXLYnwvjfelblOp1cij7s6UGGLixIlivPCxY8cUy6hwfI8ePTBjxoxs2X7GGGNM19HFaLqgLW/9Vc7iq4tlj/bc/Sim6xW3Q8UCNoplFOxS0EvBr3IQTOTBr7x1OLBNII4ePSqGkI0dO1b0aGOM5XwcAKdTl2oFxC05TVdcTnMZJAqkM9vlOa0CAwNhZmYmsv5RBsBNmzaJ8b9t27ZN8THt27cXXYL69esnAt5GjRopltEY4sGDB6NOnTqKK9AUYNNYmvr162fLe2KMMcZ0Bf12UzJKQgmc2rVrB1229dp7RETLEoENb/it9TelIDjiYgRCokLwwOtBgq7R1Mvtn3/+EUnFqLHg+PHjang3jLHsxkmwdMC8efPEmCHKAk3dmz09PUXwmhojIyP06dNH/BjQmGDlK80UHFOWaGoBtre3FzdqMfbx8cmGd8MYY4zplj179sDd3V1MT5gwQdRx1WVNSjugYck8qFYwF2oVSb5XnjwIblSgEa54XBHBb03Hmgm6RL80eImW01vCvLQ5Tpw4IXrKMcZyPm4BziEuXbqUZJ6bm5ti+sqVK6k+Prnu0HS1WX7FOTHKPkk3xhhjjGUd+n1esmSJmKYeWXRxWtdVLZgL2wfUQHhU7He7gn8OkZVJIgaShKe9e17twYfCH+DwkwNcX7iKfCm3bt2Cb4Qv1j5cC2crZzR1booCVsn3/GOMaScOgFWooK1ZlqzLGGOMMd108uRJPH36VExTbg4TExN1b5LGMDVKuSVcnvDqlf8rFLcpDtdAV1z/fF3Mk7cC+0XIkpGWyVcGrnDFnTt3cODAARSqVwgH3xwUy0rmKpkgAN71Yhee+z5HMZti6F+ufza8S8aYqnEArEJb+lVX5dMxxhhjTMfJ69RaWVmJkoO6zMM/DPltTL/b6quc7Vk+5pda0qdcnZIgMdbZTmdFEBwYHIhbc2+JoVxTpkzB+rPrYW1sjcDIQBSwTNj6e+PzDVz2uJwkAI6OjUb/M/3F+u2LtUetvLWybD8wxjKHxwAzxhhjjGmgmzdv4urVq2Kagl9r6+ypHqGJIqJj0XH9DbRafQ2XX3unK/il1l4jfSMxLS+RROvExMXA1tQWReyLKCpbvHv3Dq9Pvsa17tfELb9F/gTPb2FkAVsT2ySB8aeQT3ji/QQnXE/gS8iXBMt2v9yNrv90FfWJKVBWllpFjsyimsi0P1JCy2gdxnQNB8CMMcYYYxrc+kuJKan7sy47cN8DXsGRePElCN7BkSmud+HjBRHglrEtgxm1ZygSXiknxpIHwbSu3C+//IKiRYuK6Tlz5iAoKEi0AutLEnazXlRvES51u4QVDVckCSZrONaAo7kjCloVTLDstf9rvPB7gVtfbsFQ/9v2kJaHWqLD0Q7434v/JXm+WGnaSmsmhwJbCrgp0E8uCJZfKKB1OAhmuoYDYMYYY4wxDfPixQtRo5b07dsXefPmha6KjpVi4+V3ijKS7SrlS3Hd5oWaY0DZAWKcbvuj7fHI61GC5fIgeFmDZWJdObrIsGDBAjHt7e2NZcuWpbpNiRNqFc9VHFubb8W5zudQxaFKgmXUXfqHfD+gukPCoXJUmolajt8GvEVYdFiCZaffn0b1/1VH28Nt8TX0a4JlPuE+qbbsksbOjRO0diuvn7iVnNZlTJdwAMwYY4wxpmHkARiNd6XSR7rs2KPP8PAPF9O/NCgKQ/3UT1+/hskCxsjYSBSyKpRkOQXBysGvXJcuXVC9uixIXb58Ob58SdiVOaN6le6FTU034fdGvyeYHyONQe/SvVHfqT5K25ZOsMw92F0Eqm5BbrAxtkmwbNj5Yai+szqmXZuWYD4F0e8C3on3nbi1Wx4E02tOuzEtSRdxxnQJJ8FijDHGGNMgnz59wt9//y2m27dvj5IlS0JXSaVxWH/prZi2tzRGl6pO330MdVOul78eYuNiYWOSMHhMDV1soJJTjRo1QlhYGGbNmoVNmzYhq9C2Ta4xOdllVR2qon/Z/giIDICJgUmCMcMfgz6K92ZmmLCiyH8+/2HQ2UHQg55oja7uWF0EuJT0iwJe/wh/GMUZ4brXdQ5+mU7jAJgxxhhjTIOsXLkS0dGyLquTJycfIOmK08++4p13qJgeXK8ITAxTLn0kJ9GToG3Rthl6vYYNG6JVq1ai/NTWrVsxduxYlCpVCtmtZt6a4pYYBb4uNVzwMfgjKttXTrCM5pE4xCGfhaybuLwl+P7++7jreVfMa+TUiFt+mU7jADiLBZ8/L/63bNIkq1+KMcYYY1ouICBA0erYoEED1KyZNAjSFdTaue6irPXXxswQPWs6Z8vrLlq0CKdOnUJsbKwoi3T48GFoChp73KF4h2SX1c5bGwvqLhCBsKOZY4Jl4TGyLuSMMR4DnKUinj+Hx8hfxS3ixQutP9569+6N/v3TXvSd1qXHMMYYYyxtNmzYgODgYDGt662/l15549nnIDE9sE5hmBun3G7z1v8tZt2YJRJEZVb58uUV5ztHjhzB9evXoQ2cLJ1Ey/eISiMU2avlCa/CYsJQJU8V1LGvg4seF1PMDs2YLuAkWFnIe/16xbSP0jRjjDHGWGIRERFYtWqVmK5QoQJatGih0zupXH5rDG1QFI5WJuhXO2kyK+WW4qX3luLgm4P46chPCIqSBc2ZQaWQTExkY28nTpyYpfV6s0ribM8bftyAaRWnoalz02SzQzOmKzgAzsLW35Dz/yruB587nyNagRljjDGWNXbs2AFPT08xPWnSJJGUSZflsTSGS8tSuDq5EazNUs5UHBEbAX09WYtnq8KtYGVklenXdnJywujRo8X0zZs3RUuwNge/8mzP1IV63g/zUiyRxJgu4AA4G1p/s6MVmJI2/Prrr+jWrRusrKzEF/eePXvw33//oXbt2rC0tESNGjXw6tUrxVVm6lpVuHBh5MqVC/Xq1cPt27cTPOfSpUvh7OwMGxsbDBo0CFFRUUnGKQ0bNgwFCxaEra2tSBrh6uqaZe+RMcYYy6lovKm89BH9rnbt2lXdm6Qxvlf2yNTAFOubrMfGJhsxvNJwlb2ui4sLcufOLaZpLHBMTAy0xYWPF1IsdZS4RBKty5gu4SRY6fB1wQJEvnj53fWkoaGiBTgxagV+36kzJGYJ09anxLhUSdhOmpTm7aOSCceOHcPu3buxZs0a/PzzzyIwpvv58uVDjx49MGrUKJw5c0Z057l06RLOnTsnglxav0mTJnjx4oUInnft2iUKwp84cULUxNu2bRtGjBiBXr16ideirkAdOnQQz/vw4UOYm5tjxowZaNOmDR4/fgxDQ64pxxhjjKUVJVp6+1aW8GncuHE6/Tv6OSAcFiYGsDJJ3z6ok7+OSreDGgCmTZsmPg9qQKCs0L/88gu0gbzOcWPnxsnW+VUEwR+bJVsTmbGcjAPgdKDgN+yuLIV8RkU8e5bmddM72qRTp06oX7++mKbkDWPGjBFJqAoVko2b6dmzp2jJlUql4kucAuNixYqJZePHj8dff/2FnTt3iiueFPAOHDgQP/zwg1g+ZMiQBLXwKOilpBB+fn6wsLAQ8yhgXr16tWhJrlu3bjq3njHGGNNNdFF58eLFYpp6VNEFbF0289gz3HL1xaC6RTC6SfEU14uVxiqSPWVVRY7hw4eLcxs3NzfMnDlTNATIz3s03fcCWwqCOfhluogD4HQwLl0qw62/ykzKlk1TKzC1AKdH3rx5FdPUIpvcPMos6ePjg/DwcBQtWjTB4ykY/vhRVkPOw8MD7dq1S7CcukvLvXnzRnQFotbixNzd3dO13Ywxxpguu3jxIu7duyemR44cqfgN10Uvvwbh3HNPRUtwapbcXYKvoV8xvtp4OFs5p1qRgxQ+fAgmpUuna3uMjY0xb9480aBA47NXrFgherwxxrSXVgbADx48wKxZs3Dt2jUxlrVIkSKihZK692Ylx6lTv7uO+8iRwHcCYMN8eeG0Zs13n4taamlMkKrZ2dmJzIbv3r1DuXLlFPPpPnV3JhTY0tVOZXRfvr6joyOMjIzg7e2t0920GGOMscySt/6ampqKAFiXbbj0Tvwv0QOGNUx4oV6Za4Ar9r7ai9i4WJEEa1PTb73UUqvIkZbzr8RoCNny5ctF7zfKjzJ06FDY29tD24T8ewFRVGKrfcIGDsZ0jdYlwTp79qxI6uTl5YXp06eLcgE07pRaLDUt83NK1J0RWiKRiO7NdAWTklZRcqvff/9djD2Sj/Ht168f/vzzT9y6dUu09G7ZskWM7ZWjLs4UDFMSLPosiL+/Pw4ePIiwsDC1vTfGGGNMm1BQRec2hIYp0UVqXeXmE4p/Hn8W020q5EMhu5Rbwq2MrdCmSBuR/Xlc1XFZWpGDzpuWLFkipkNCQkSJJG1D++LrmDEInT4dkS+/n8+GsZxMqwLgoKAg9O3bF61bt8aNGzcwduxYDB48GIsWLVJ8MamT365daV7XPx3rZgXKNNmsWTM0atRIXMWkwJUSYhUoUEAsp0CYSjB06dJF/BhTIExJr+T09fXF+mZmZqhZs6bIMl2xYkWRxEPXyzYwxhhjaSU/f6HfVUq2pMs2Xn4HaXwClOGNUm79JXamdphXdx5OdTyFkrlLprkih/e6jFXkoEShdN5EKCcKDQXTJsr7wm9j8q3ljOkKvTgtquy9ceNG0eL4/PlzlC5dGqGhoaK7EF2Zy4hnz56JVsynT5+ibNmyivnyUj7UtTo9wh89wudp09K0br7582FasWKaukDTj2JG3yPLWVRxTGT0+GaaKTo6Gr6+viJxDg9H0E18DGgv+j4uXry4+G6nC8+UiFJV/E+fEXk/8rZvpxXfDTTet8HSi4iOjUOT0g7Y0q9aknXipFJIg4IQGxgouwUExP+vNB0/P/rrV0SlFKQaG0PfxAR6RkbQMzaOvxlBYpjoPi03+nbf2z8Am7dvQ6RUilIVKqD/4MGQ0DKxDq1rJLsvn2dk+O2+sXH88xkBBgbZ2lhArb/vO3ZKMC8j46FZzhWt4ecSKcVsOjEG+Pz586LG7adPn9C+fXu8fv1aJIro06eP6MJL41rVybRSJRQ9flyt28AYY4wx7UAJlSj4JdTrStXdXUlkqZIwLF8emiRJIBsYiDP/PkXL1x9hER2GHrDGp4n7EBsYIAtuAwMgpf+DgvDVOg4OAUCmwsfISMRGRmbopHm4bXwX9S9f4TlnbsZeXyJJEBCnJwhPfF8RdKcShHstW55kEzI6HpqxnECrAmB55mHKTkwlAhYuXChq2VIN24CAAFHWJyU0TpUSNimT19ujqx50k6MfI7oyJ/9RUid5A70mbAvTDJk9JujxdFM+5pn2ou9E6hVA/zPdxMeAdqJzEsq1QZo3by56tqnqe9lr7TrFtO+GDTBetQpZFsgGh8gC1PhAVgSq9H+QvDU2ULYsSHlZEP0YJXiuWvE34SUQlMzrhZgAU/vrI78vMOBsLIrIkkUrSCwtIbG2FkFgdHxvp5RYtGgBibkZ4qKiEBcZBWlUpPhf3FdMRyIuKhpxkZHx68n+zzSpFHHh4YgNTz3LdVai8dAh//0H41Lfr3DCcr4YDT+XUPU5q1YFwJR4gBIsUfY9qslGOnbsKJI40XgMSkpAXYmSs379esyePTvZZYGBgaLZX46ejzIcZ0UG5vSgIEW+DTyulqnqmKDnoGNc+Zhn2ot+rKibI32uBgZa9ZXOVISPAe1EuTioJCGhShaq+k6OefMGoRcuKO6HXbgIz1u3YVC8WKqBbFxoKOKCguJvwYgLDhKBqnw6LjAIUvquoXlK/ycOZFVBz9wcelZW8TdL6FlaQWJlhX1OrggxfY5XTkDwiN6wtK0lW8fSCnoWFtAzkNUEDpk2nfqXp/oakaGhsHCZnO5to+/a+bNmYceWLTDW08Pa339HvVq1ZIExBcl0oi6C6Pj7UYnuJ14eLV+P/o9OdD/lx6vC19VrYDFX+xJ6Md37HQkMDFTp82neO0wFjfeVp6NX1rNnTxEA37x5M8UAmAqZU0KnxC3A1JXa2tpa9HlXDrQpuKBxlppAEw9Epr3HBB3bdIFH+Zhn2v2jRZ9p7ty5+btCR/ExoH3oPGP79u1imsoPUjULVV3o/pJMt9zIpUth2ORHWetrYJBsvGxQ/LS8RTYLepqJFlkrK+hbW0NiYwN9ayvoW32bptZafRsbSKysxX09+t/KEpIUxiD+GhUMs2db8dr/NTo2mpjsPot88QL+1659d9uir16Fhbd3hlpAp8+Zg//t2wffgADM2bAB9wcNytbvX9ETLDoaUnnLtLx1mlqto79NR7m+g8/iJVmyD1jOEqPh5xIUq6mS5r3DVOTLl08MgnZwcEgwX16LjcrwpITWSalmGw32Vh7wLU8upO7EU/Ku2JqwLUwzqOKYoMfTTROTHLCMoYt19IPFn6nu4mNAu+zYsUNxzuLi4iIuSqpq7K9y669c1OvX8Hv9OlOBLAWxihsFsDbWIoA1oABWeb61bJk+tcyq+EQ6t2FuTKwxEdI4KSR6yf8Geu/bl+bnC963DxZz0z+Ol85Dp0yZgsmTJ+PFixfYtWuXGJqXreiYMU+5TBRx3//9fRGweTOPBWYa/zui6m3SqgC4atWqovQOJcEqWfJbyvvPn2U14/LkyaPGrWOMMcYY+/5YNkp+RUqUKCHymqhKcmV/lEksLOKD1KSB7LcAlqZpfnwga2kJvSw6IQ6LisEH3zCUzmuVrselFPySXJ07i6ocaWHTuTMy6tdffxU5aDw8PDBjxgzRO5FKQ2qKxDWQUyKvjcwZoZku0aoAuGvXrqLm79atW9G4cWPF/C1btogrFg0bNlTr9jHGGGOMpYYSdrq7u4vpiRMnqmy4VVoCnoJ//6VRgc6u2x8x78QL/FjKHsu6VEQu86Qt4THSGBx3PY7WRVrDUGKoMRU5aFjevHnz0L9/f9EQs2rVKtEqrCn8du1K87r+u3YhbwZawhnTVlrVr7Zy5coYOHCg6GrSrVs3kdiKgmL6MaEfEeoizRhjjDGmiWjs5pIlsjGZjo6OooxjdrX+ykvfaIrImFj8cVWWqOq9byisTJMPbg+9OYTp16ej07FOcAt0gybp3bs3yseXmKIGGh8fH2gKagk3KlY04a1oUUgKFRT/K8/PTEs4Y9pIq1qAycaNG+Hs7Ixt27bh8OHDKFiwoKgBPCa+3p26nXE7g8bOjVO8ShktjcaFjxfQvFDzbN82xhhjjKnPyZMnRS4TQuctxsbGOtvd9cB9D3gGyWrxDm9YDPoSvWQvGBx7d0xMR8ZEwtHcEZqEWu8XL16MVq1aISgoSLQIr1y5EpoguZZw6n5P2cYpCaYmjvNkLLtoVQswoT/YmTNnws3NTZRyodrAmhT8Trg8AS5XXESgmxjNo2W0Dq3LGGOMMd1BwRKxsrISJR3V1d1V3WJipdh4+Z2Yzm9jinaVku/BRwkb/2z+J8ZXHY9JNSbBxMAEmqZFixZo1KiRmKaeia7fKb/EGFM/rQuANRm1/DYr2AxnP5xNEgTLg19aRuvQupqA6inXrFlTJG5wcnJS9+YwxhhjORKVarx69aqYpuBXlWU9LJs0pWhRTFPCKtHFVYO7ux57/BnufrIayEMbFIGhfsqno0b6Ruhfrj9+dP4RmoiCdHm3dmphnTZtmro3iTGW07pAazLq9ryo/iLgCkSgS/+L+1TmQCn4pXlpSeSQlaj1nMou0LjpSZMm4eXLl9iwYYNat4kxxhjL6a2/9Nur6p5rwefPUX9hMe20fh0s6tXT2O6uUmkc1l+Stf7msTRGl2oFoO2qVauG7t27Y8+ePSIvzbhx48Q8xphm4hbgLAqC5S3BEy9PFLfsCH7XrVuHcuXKia5V8uQa8oQMs2bNQt26dTF9+nQR9FaqVEnM79y5Mzp16oT8+fNnyTYxxhhjuo5qxR49elRM9+3bF3nz5lXZc9P438CDh8S0RYMGIvjVZGeefcVbrxAxPbheYZgYJs2CfffrXax9uBZh0WHQFvPnz1dcaKD6wDR+mTGmmTgATqcjb49gwOkB4pYYBbo0f8ezHSLQpe46/378V9xsjG3gE+6DdwGyq55yW/7bIh5Dj80sCnoPHTqEgIAA3L59G69fvxZ16uRu3bolvpxpfMq9e/cy/XqMMcYY+76lS5cqustS1QpVoSDr64IFstZfAwPYT56s0R8Hba+89dfGzBC9ahZMsk6sNBaL7yzGpieb0O14N1EGSRsUKVIEw4YNE9MXLlzAmTOc64UxTcUBcDp9DvmMe573xC2xJ95PxPz3ge+TLAuIDMADrwcIjgpOMJ/WpcfQYzOLWnJLlCgBiUQismO7uLjg7NmziuUODg6iBdjExESjirUzxhhjOZWHhwd27twppjt06CB+p1Ul+MwZhN+7L6Zz9+oF4yKFocnoAgDV+6WkV4PrFYG5cdKReH4RftCXyFqF2xRpAwOJ9ozWo/G/lpaWilbg2NhYdW8SYywZ2vOtoiHyWeRDNYfkx3VUyFNBLHe2chZjfqnll1qBKei98/UOchnngqmBaYLHFLYuLJ7PztQu09tGrb/Lli3D27dvERERAalUitDQUMUXMAXF9OPDGGOMseyxatUqMR6XUM4NVZFGRMBriaxlWT9XLtiNGA5tUNLREqu6V06xi3AeszzY3Xo3Tr0/pbGJr1KSJ08e0fjw22+/4cmTJ/jf//4nurwzxjQLtwCnU/ti7bGtxTZxS2xpg6XY3GwzXvu9Voz5pXkbm24U0/6R/tj2dFuC7NCDyg8Sz0XrZfYKc5cuXUSX548fP4p6dH///bdYJv+RoZZhxhhjjGUPGpK0adMmMd2gQQNRdUFV/LZvR/Tnz2I6z+hR0LeygjZJ7YK8RE+C1kVaa2TZo++hBGeUa0XeIkwNEowxzcIRkQolLnUkT3iVODFWSnWCMyMkJES0+NrZ2YkuzlQfeeHChd99XExMjPhyll+dpmm6cfIGxhhjLHOoukJwcLCiS6yqRHt6wWfzH2LauEQJjSht9D1X33iL+r8pkcalvEyb0BCz2bNni2l3d3esWbNG3ZvEGEuEA2AVuvDxQorZnhMHwbSuKpUqVUoEvNTVhsaf9OvXD7179/7u4+bNmwdTU1MMGTIEnz59EtN0+/Dhg0q3jzHGGNMldDGZuj+TChUqoEWLFip7bu8VKxAXJsuQ7DB1CvQMNHtE22P3APTZegeNl1/GPTe/ZNeZfGUyZt+cDd9wX2i7/v37o3Tp0mJ6wYIF8PNL/j0zxtSDA2AVal6oOZY1WJZiqSN5EEzr0LqqRuNOvnz5Iq4237hxA6NGjRItuQYGBqIM0rVr15I8hubTOolvhQoVUvn2McYYY7pix44d8PT0VIz9VVUOjvAnTxAYX1LJosmPMK9VC5pu3cW34v/PAeHIa5MwFwq59/UeTrudxoHXB7D64WpoOzrvWrRokaIbfFp65DHGsg8HwCpGgW1qdX5pWVYEv4wxxhjTDJR8kpJSyhNQduvWTSXPSxeoPecvENN6hoZwUGFSrazy2jMYZ5/LLgR0rJIf+ZMJgG1NbVEnfx2Y6JtgWEVZKSFt17ZtW9SLr8m8evVq7lnHmAbhAJgxxhhjTIWoKgNVZCDjx48XLYKqEHT8OMIfPxbTufv1hZGzMzTd+vjWX4keMKxhsWTXoYoYG5tsxKF2h+Bo7oicgFr8lyxZIqajoqJEGUrGmGbgAJgxxhhjTEWolXbx4sVi2tbWFgMHDlTJ80rDwuC1bLmY1rezg+3QodB0H3xDceyxLFN1q/J5UdjOPNX1C1gWQE5Sq1YtdOrUSUxTLejH8RcvGGPqxQFwCjgLMsup+NhmjLGsc/HiRdy/f19MU2lCc/PUg7608t2yFTHxY4rtx46BvoUFNN3Gy+8gjS/3O6JR0tbfLyFfkNNREix9fX3x26vKTOCMsYzjADi5nSKRiPE7HCiwnIjKZakqGQtjjLGE5K2/VFFhxIgRKtk9VO/Xd+tWMW1SpgysO3TQ+N3+JTAcB+57iOkmpe1ROm/COsWfQj6hzeE2GHNxDDyCZevlRCVKlMAvv/wips+cOYPz58+re5MY03kcACfD2NhYBMBeXl4cBLMcJTQ0VNR+NjIyUvemMMZYjvPw4UOcPXtWTA8aNAh2dnYqeV7q+hwXGfmt7JFE80/ftl93Q3SsrPl3eDKtv2sfrkWUNAr/fvwXPuE+yMlmzJgBi/gWe8oITheiGWPqo9mF49TEwcEBkZGRom5bYGCg6LqijhYzeUkiem1usWOZPSbocZSIg3o45MmTh3coY4ypmDzpEZ03jBs3TiXPGfbgAYJOnhTTli1bwKxaNWiDkY2LwcbMCC++BKGKc64ky8dUGQOJngQx0hhUsq+EnH5eOWHCBFF6ki6S7NmzBz179lT3ZjGmszT/EqIaUIDg7OwMGxsb0VKmruBTHrBwV2ymimOCjmMzMzPkzZuXW4AZY0zFXF1dsW/fPjHdvXt3FCpUKNPPGSeVfit7ZGwMhwkToC0sTQwxrGFRrO5ROdnlDuYOmF93PhbUlb2/nI6ygVMgTH777TfR0MIYUw9uAU4lCKZAQZ2io6Ph6+srskgaGqZcW5jpDj4mGGNMMy1fvlzRtZW6uapC4JGjiHj2TEznHjgAhvnzI6fRl+hDF1AXaGoBHjZsGNzc3LBhwwaMGTNG3ZvFmE7iFmDGGGOMsUygnCF//vmnmG7ZsiUqVKiQ6f0ZGxIKr99XiGkDe3vYDRqkFZ/R9bc+8AqKSHZZWHQYzn84r7M9237++WeRFIvMnTsXAQEB6t4kxnQSB8CMMcYYY5mwdu1aRETIgj5Vlbrx3bwZsd6y5FD248dBoqJySlkpLCoGI3c9QN0lF7H5yrsky7c924axl8ai/+n+8Ivwg66h3nwLFy4U05RnRp4xnDGWvTgAZowxxhjLoJCQEBEAkxo1aqB+/fqZ3pdR7u7w275dTJtUrACrtm214vPZfccd/mHRiIqRIp+NaYJl0bHROPr2qJgOjwmHjbENdFGHDh1Qu3ZtMb1y5Up4eOTcElCMaSoOgBljjDHGMmjLli3w9/dXtP6qInGm15KliIuKEtOOU6dqRdmjyJhYRatvETtztCyXMI+Kob4hDvx0AP3K9MPkGpNFBmhdRMeHPFs49RqYOXOmujeJMZ2jm98+jDHGGGMqSEy4YoVsnC6N7WzXrl2m92no7TsIPndOTFv91BamFStqxed08P4neAbJMhsPbVgU+pKkFwKsjKwwofoEVHWoCl1Wt25dxbGyfft2PH36VN2bxJhO4QCYMcYYYywDdu/eDXd3dzE9ceJEUf83M+JiY+EZP0ZUz9QU9uPHa8XnEhMrxcbLstbf/Dam6FA552WrVjUaC0wVRyhzuIuLi7o3hzGdwgEwY4wxxlg6UeAi78pKZRP79OmT6X0YcOAgIl++FNO2gwfBML5urKY7/uQLPvqFielfGhSBof6300vK+rz75W7ESGPUuIWap3Tp0iIrNDlx4gQuX76s7k1iTGdwAMwYY4wxlk4nT57Es/gavVTP1djYOFP7MDY4GN6rVolpg3x5YTtwoFZ8JlJpHNZdfCum7SyM0bVaAcUySna16M4iLLi9AEPPDVXjVmomqgtsamqq6EGgq+WhGMtuHAAzxhhjjKWTvPXXysoKv/zyS6b3n8/6DYj1k5UGcpgwARITE634TK699cEbrxAxPaheYZgYfusG/in4EwwkBmK6VZFWattGTZUvXz6Mj+/mfvfuXezfv1/dm8SYTuAAmDHGGGMsHW7evImrV6+K6WHDhsHa2jpT+y/KzQ1+O3eKadOqVWHZsqXWfB71itth+4DqaFzKHr1rFUywrFiuYjja/ihm1Z6FdkUznyAsJ6KWXzs7OzE9depURMVn/2aMZR0OgBljjDHG0mHx4sXifyMjI4wePTrT+85z8RJKKU01cuAwZYpKSillF9rWhiXt8Wf/6rAwlrX2KjPWN0anEp2gL8lcgrCcinoQzJgxQ0y/e/cOmzdvVvcmMZbjcQDMGGOMMZZGL168wNGjR8V03759RQKszAi5fh0hFy+KaesOHWBarqzWfxY8ljV9qAt90aJFxfScOXMQFBSUJZ8LY0yGA2DGGGOMsTRaunSpouWTuq9mRlxMDLwWLZKdkJmZwX7sGK35HJ59DsQtV98kwS7dH3JuCNY9WoewaFlmaJY66kkwf/58Me3t7Y1ly5bxLmMsC3EAzBhjjDGWBh4eHtgZP1a3Q4cOKFGiRKb2m//evYh8I8ugbDtsKAzy5NGaz2HJ6VfovvkWem+9LTJBy51xO4NbX25h4+ON2PFsh1q3UZt06dIF1atXF9PLly/Hly9f1L1JjOVYHAAzxhhjjKXBypUrEU1jdQFMnjw5U/ssNiAAPqvXiGnDAgWQu18/rfkM/vMIxOXX3mK6iJ0FJJJvY5YdzR1ROndp5DbJjT5lMl8bWVdIJBJFZvGwsDBRIokxljU4AGaMMcYY+w5/f39s2rRJTDds2BA1atTI1D7zXrsOsYGBYtp+0kRIjIy05jOQ1/01kOjhlwZFEiyrZF8Je9rswY4WO2BhZKGmLdROdFy1aiUrF7V161a8fPlS3ZvEWI7EATBjjDHG2Hds3LgRISEhKmn9jXz7Fv67d4tps5o1Ydmkidbs/zeewTj97KuYbl85P5xymSVZR6InQSHrQmrYOu23aNEiMb48NjYWU6ZMUffmMJYjcQDMGGOMMZaKiIgIrFq1SkxXqFABzZs3z/D+oiRRnosWA7Gx1O8VDlO1q+zR+kvvxP+0ycMayjIXE+8wWZdoljnly5dH//79xfSRI0dw/fp13qWMqRgHwIwxxhhjqdixYwc8PT3F9KRJkzIVsIZcvozQa9fEtE2XLjApWVJr9v1H3zAce/xZTLcqnxdF88i6OD/zfYZmB5ph3q158I/wV/NWaj8qhWRiYiKmKdM4l5ViTLU4AGaMMcYYSwF1RZWXpSlYsCC6deuW4X0VFxUFL2r9pRMwS0vkGT1Kq/b7hsvvEBuf8XlEw2KK+SvurUBMXAwOvjmIoCiuYZtZTk5OGD16tJi+efOmaAlmjKkOB8CMMcYYYyk4dOgQ3r6VJX0aP348DAwMMryv/HbtQpSbm5i2Gz4cBrlza81+D46IxtFHn8T0j6XsUSaflWKZSw0X1M5bGz1L9URBq4Jq3Mqcw8XFBbnjjw8aCxwTE6PuTWIsx+AAmDHGGGMsGdT1dPFiWYutra0tBg4cmOH9FOPnB59168W0UaFCyN2rp1btc0sTQ5wdWx99axfEiMbfWn9J8VzFsanpJoypOkZt25fT2NjY4LfffhPTr169ElmhGWOqwQEwY4wxxlgyLly4gPv374vpX3/9Febm5hneT96rV0MaHCym7V0mQ0+Lyh7JUcbnOe3KoYpzriTLaFy0ocRQLduVU40YMQKFCsmyac+cOVORhZwxljkcADPGGGOMJWPJkiXifzMzM4wcOTLD+yji1SsE7Nsvps3r1oVFgwZav799wn1w7+s9dW9GjmZsbIx58+aJaUrCtmLFCnVvEmM5AgfAjDHGGGOJPHz4EGfPnhXTgwYNEl2gM1z2aMFCQCoF9PXhQK2/WlT2KCgiGjtuuCE8KjbB/LUP12LAmQEYd2kcImMj1bZ9OV2PHj1QuXJlMb106VJ4eXmpe5MY03ocADPGGGOMpdD6q6+vj7Fjx2Z4/wSfP4+w27fFdK4ePWBcLOH4WU33980PmHnsGeouviDKIBEqdXTy/UkxHRUbBWN9YzVvZc4lkUgU49CpCzSVSGKMZQ4HwIwxxhhjSlxdXbFv3z4x3b17d8U4zPSSUtmjJUvFtL61NfKMHKFV+zksKgZbr70X03ksjVEgt6mYzmWSC8faH8NPRX/C+Grj1byVOV/Tpk3RrFkzMb1p0ya8efNG3ZvEmFbjAJgxxhhjTMny5cshpS7LACZNmpThfeO3Ywei3d3FtN2vv0Lfxkar9vPuO+7wC40S0yMaFUvQddvR3BHz685HYevCatxC3UGtwLT/qRzS1KlT1b05jGk1DoAZY4wxxuLRGMs///xTTLds2RIVKlTI0L6J8faG74aNYtqoWFHk6t5Nq/ZxZEws/rjiKqYL25mjVfm86t4knVapUiX06tVLTB84cAC347vVM8bSjwNgxhhjjLF4a9asQUREhJiePHlyhveL18qVkIbJxsw6uEyBnoGBVu3jQw8+4WuQbD8Ma1AU+hI9HH5zGOc+nBOJvVj2mzt3Loziy2dRzwT+HBjLGA6AGWOMMcbikwytW7dO7IuaNWuifv36Gdov4c+eIfDQYTFt0bAhLOrW0ar9GxMrxYZL78R0PmsTtK+cH77hvlh8d7HI+jzr5ix1b6JOorHo8nJcV65cwfHjx9W9SYxpJQ6AGWOMMcYAbNmyBf7+/orW34yUK1KUPaJWUkND2E/O+BhidTn+5As++slar39pUBRGBhK4BrrCUGIo5jVxbqLmLdRdv/32G2zix5K7uLiIMcGMsfThAJgxxhhjOi86OhorVqwQ+6FEiRJo165dhvZJ8OnTCL9/X0zn7t0bxoW1L0nUwQce4n87C2N0q15ATFd3rI7jHY5jeq3pqOdUT81bqLty586NKVOmiOnnz59jx44d6t4kxrQOB8CMMcYY03m7d++Ge3zG5okTJ4r6q+kljYiA59L4ske5c8Nu+DCt3K9b+lXDwo7lMalFSZgY6ivmWxtbo2vJrmrdNgb8+uuvcHJyErtixowZCIsfa84YSxsOgBljjDGm06jk0ZIlS8R03rx50adPnww9j9+2bYj5/EVM5xk9GvqWltBGxgb66FHDGV2rFeBESxrI1NRUJMQinz9/xqpVq9S9SYxpFQ6AGWOMMabTTp48iWfPnonpMWPGwNjYON3PEe3pCZ/Nf4hp41KlYNO5E7RddGw0+p7qi32v9iFGymNNNQldpClfvryYXrRoEXx8fNS9SYxpDQ6AGWOMMabTFi9eLP63srLCL7/8kqHn8Fq+HHHh4WLaYcoU6Ol/6zqsLSjz83ufUMX93S9345H3I8y9NRf/vPtHrdvGEtLX11cct0FBQZg3bx7vIsbSiANgxhhjjOmsGzdu4Nq1a2J62LBhsLa2TvdzhD96hKBjsgDRsmlTmNesAW1z180Pi0+/xI/LL+HIw09iXgHLAshvkR+FrAqhTdE26t5ElkiLFi3QqFEjMb1+/Xq4urryPmIsDTgAZowxxpjOko/9NTIywujRo9P9+DipFF8XLhTTelT2aNJEaKN1F9+K/w30JfihqK2YbuTcCEfbH8WaxmsUJZCY5qAyXfLjl7KYT5s2Td2bxJhW4ACYMcYYYzrpxYsXOHr0qJju16+fSICVXkHHjyPi8RMxnbt/fxgVkJUN0iZPPwXi0itvMd2tWgHYW5kolhnrG6OQdSE1bh1LTbVq1dC9e3dFJvN79+7xDmPsOzgAZowxxphOWhpfsoha0iZMmJDux0vDwuC1XFY7WD+PHWwzOH5YU1p/9SV6GFyvMPwi/NS9SSwd5s+fD0NDWQv95MmTOXM3Y9/BATBjjDHGdI6Hhwd27twppjt06IASJUqk+zl8t2xBjKenmLYfMxb6FubQNm+9gnH62Vcx3b5SfriF30eLgy2w4dEGhMfIknoxzVakSBExfp1cuHABZ86cUfcmMabRtCoAvnTpkrhKm9zt1q1b6t48xhhjjGmJlStXinGT8laz9Ir+9Am+W/8U0yZly8K6Q3too/UX3yEujlrBgV8aFsKye8tE4PvX8784ANYiNP7XMr7uNB3PsbGx6t4kxjSWAbTQqFGjUL169QTzihUrprbtYYwxxpj28Pf3x6ZNm8R0w4YNUaNGjYyVPYqMFNMOv02FnkSr2hQEd78wHH38WUy3KpcXJeytMb3WdCy5uwRtirRBbpPc6t5ElkZ58uQRgS8Fwk+ePBG9G2hcO2MshwTA9erVQ+fOndW9GYwxxhjTQhs2bEBISEiGW3/D7t9H0MlTYtqqVSuYVakCbXTuuSdipXFienijouL/6o7Vsaf1HkghVfPWsfQaO3asKIf0+fNnTJ8+Hd26dYOJybeEZowxGe27XBkvODgYMTEx6t4MxhhjjGmR8PBwrFq1SkxXrFgRzZs3T3fZI88F8WWPTExgP2E8tNXAuoVxZEQdTGhWAmXzfat/rC/R57JHWsjMzAyzZ88W0+7u7lizZo26N4kxjaSVAfCAAQNgZWUlrmpRAXBO+c4YY4yxtPjrr7/g5eUlpidNmiTyiKRH4OEjiHj2TEzbDhwIw3z5tHrHVypgg5+qGeOtvywTNNNu/fv3R+nSpcX0ggUL4OfHGb0Z0+ou0FSkvlOnTmjVqhXs7Ozw/PlzLFu2THSJvnHjBipXrpziY+nHzttbVuNO7u1b2Zc9JcGQJ8LQJNTCTUkMuKWb8THB+HuC8TGQefSbSucNpGDBgiL7c3p+/6UhIfBaEV/2yN4eVv36auT5Q3rPIRbcWoBbX2+ha/GumFB1QrovCjDNMm/ePHG+HBAQIEokLVq0SMzn80qWkhgNjzlU/T2rVQHwDz/8IG5yP/30kxgLXKFCBUyZMgWnT59O8bE0JkLeLSSxwMBA+Pr6QtPQQUhdvePi4mBgoFUfFcsifEwwPiYYHwMZ988//ygufg8ePFj8/qdH2KbNiI0/XzAePAj+4eHUp1rrfi+OPfWBtYkB6hW1hnvoR9z8clOM+Q0KC+IWwxygdu3aqFmzJm7fvo21a9eie/fuKFCgAJ9DMK09vwxM53f192jeO0wnyv7crl07HDp0SFy50NfXT3a94cOHo0uXLgnm0Y9g+/btYW1tDVtbW2jiwUhXYXPnzq2RByPLfnxMMD4mGB8DGUMndhs3bhTT9Js/YsQImJunvW5vtLs7/A8cENPGFSogb7duGt1SmtLvRXBEDNZee4ygiBi0q5gXyzpXwW7r3djwZAPGVB8DW1PNOx9i6SfvIRkVFSXGvG/bto3PIZjWnl9aW3/LUaAKmvcOM4CuatEfeGhoqBgbnBx7e3txS46hoaG4aSIK6OlA1NTtY9mPjwnGxwTjYyD9/v33Xzx48EBM//rrr7CxsUnX4z1//5364YnpvNN+E8OytPH3Ys/1DyL4Ja0r5BPLyuQpgzU/csKknKRu3bqiG/TBgwexa9cujBkzRnSJ/vDhg+j+36BBAz63ZFpzfqnqbcoRAbCrq6tIiGVhYQFtNWjHXXzwDUtytVreqq18lbmgrRm29EtYB5kxxhhjKVu8eLEiU+7IkSPTtatCb91G8LnzYtq63U8wrVBBK3d1eFQstl59L6ZLOliiSWkHdW8Sy0KUBOvw4cOQSqWoU6eOaCySc3R0FL0jXVxcNDLgYSwraVUATEmsqNC3ssePH+PYsWNo2bIlJFpYhF6Ogt83XrKahIwxxhhTHWr5PXfunJgeNGhQuoY9xcXGwnNhfNkjMzPkGTdOaz+aPXc/wjdUFgRVKf8Mj7wtUMVBO2sYs+8rXLgwnJyc8PHjxwTBL/H09MSMGTPEOGEKkjkIZrpEqwJgKuhtamoqEmFRd2bKAr1582ZxNVee4Y4xxhhjTNnSpUvF/9Sjalw6A9iA/QcQ+eqVmLYbMhiGDtrZahoVI8XmK65iuoB9CE5/3ozjn9bj18q/YkiFIerePJYF6NyYgt/kUC9DcuLECdE7Ytq0afwZMJ2RJU2mV65cSVJySJmPj49YJ70oYRU9dsWKFaLbxt69e9GxY0dRB1he84wxxhhjTHmY1L59+8R0jx49xPjHtIoNCoL3qlVimur95u7fX2t37KEHHvgSGCGmG1WIgr5EH3rQQ938ddW9aSyLysasW7fuu4naaDmtp6nlvBjTmgC4UaNGiq5GKSWioHXSa9SoUaKrBpUsoj/Uz58/4++//xaZoHMCA8sn9HObyhqx8eswxhhjLC2WL18uxkCSSZMmpWun+azfgFh/fzFtP2kiJCYmWrnTY2Kl2HD5nZjOZ22CaQ174Z/2/2Bm7ZkoY1tG3ZvHssD169dFN2d5S29KaPnXr1/F+ozpiiwJgL/3xxYZGZliuSJdFWH0AKZOu2CSf08KQXCsWEbr0LqMMcYYS52Xlxf+/PNPMU25QsqXL5/mXRb5/j38du4U06bVqsKyeXOt3d0vvwbDKyhSTA+pXwRGBhLktciLTiU6qXvTWBbx8/PL0vUZ02YqGwNMYwzc3NwU91++fJlsN2dKwb5p06Z0dUHSBcZRFREdVB6GVv+J+xGfutNopQTBLy2jdYyjK6p1WxljjDFtsGbNGkREyLr9Tp48OV2P9Vq8hIpjUh9ROE6dqtE1f7+nXH5rXHdpjP/d+oDuNZzVvTksG1A916xcnzFtprIAmApsz549W/xA0G3+/PnillzrMLX+UhDMvtGDfnzQi0RBMBIEvzRPz55bzxljjLHUhISEiLGNpGbNmqhfv36ad1jI1WsIuXRJTFt36giTMtrfTdjQMBK3ImehzOeBaOzcWKsDevZ9VPbIwcFB9IJIrWcmHQe0Hq3PmK5QWQDctWtXlCtXTvyR0TSN161Xr16SPzJzc3NUqlRJ/LGxxBIHwbIxS4ZWzxTBL60TI029izljjDGm6/744w/4x4/fpdbftAZ8cdHR8IyvLCExN4f9mDHICTY/2Ywn3k8w5tIYbG66GbXz1Vb3JrEsRGWNRowYIUodpYbO22k9LoPEdInKAmDKwizPxEytwXSlleqPsYwGwVIR+JKYkGIJukR/9AvDPTc/VCvE3VUYY4wxOUqQScl8qNVrwYIFYl7JkiXRrl27NO8k/z17EfVOljDKbthQGNjZafwOHrTjLj74hiUJbEIiohEVGwcbcyNEmoSLOsYWkvyolbeW2raVZR8XFxeRPJZKHdEFIOWWYPn91q1bp3t4AGPaLkvqAPfr1y8rnlZn6Zu/g8TEA9II2bjpWGkcevxxC6u6V0ar8nnVvXmMMcaY2gNfqnlKXZ4p862yUqVKITY2FhLJ9/N+xvj7w3vtWjFt6OyMXH37QhtQ8PvGKyTF5X5hVOKmMiApCVt72VA1lvNRq+7hw4dFnV/626Bsz3LUE5Nafin45dZfpmuyJAAmL168EC3BVH+PuiAlHn9AX75UDonJFLQ1E//HIRaBFtsRYfwM+jF5EKvvDT29OOTOdxM2IaUQFC6Fd3AkLIwNUD6/Ne8+xhhj0PXgt3379jh58mSygd3Ro0fRoUMHEQh870TfZ+06SAMDxbTD5EmQGBkhR5GawUBqoe6tYNmIjvlp06aJQPfy5cv48OGDSETboEEDDnyZzsqSAJhq8w4YMED8YVHXo1y5cqW7VJKu2dKvOqKl0XC54oKzHx6iWcFmmFt7Lq6/u46DHgdx/ct1VCxxAovqL8I9Nx9IpQYokFsWNDPGGGO6ilp+KfhN7dyCuoBSKxgFAimJfPMG/nuoFCFgVrsWLBo3hjYxsHyCmOCyShUkiBSQRAFSql8cCwNLGlr1gxq3kqkLnZNT0Ovr6wtbW1sOfplOy5IAeNasWahcuTJOnToFOy0YO6MJvgW/Z0XwS4EulQMun7s86hStg+k3p4tluAKYGZrhU8gnFHSYAydLJ/H4fXfdUdTeAlULJr3YwBhjjOXU1l/q2pl4fGNitJzWS6m7Jz3Wc9FiIDYWkEjg4DJFq7oJRxg9gKntrgQJM4mhzT0Y5TmDKO8mYjiVodVTRARTMNxA3ZvMGGNq8/0BMRnw+fNnDBw4kIPfdLjw8UKC4NdQ8u0HmqZpHi2jdY68PYK7X+9iyd0lYvmNdz6Ycvg/dN98E3vufFT9B8oYY4xpIEp4RWN+v9erjJbT+EdaPzlU8ig0fplNt64wKVkC2sQ4qqIIfqmCBJVOFFfQJZEwynMWEoNQGDucFMEvrUPrMsaYLsuSFuAKFSqIIJilXfNCzcX/VJtPOfhNHAQ3eN8Aj7we4dT7U5hSY4pY9sk/HHSdOjo2Di6H/sN/nwIxs21ZGBlkyfUNxhhjTCNQd8708PPzSzIvLioKXtT6S60CVlbIM2oUtI1ekjKKQMSnboj82gYmeQ9CTz9a0TqsZ6/cRZoxxnRPlgTAK1asQJcuXdCyZUv88AOPNUlvEJwSCoJ/KvqTuA2vNBx2prLu5V2qFUBBW3MMPbAXfr4F8L/bH/HqazDW964Ce0vq6sQYY4zlHNSiS4k0Z86cma7H5c6dtHyg3/92IerDBzGdZ8RwGCSTt0Q7JA6CpWJaOfhNOD6YMcZ0U5YEwJRowtraGvXq1UOZMmXg7OwMff2EX7o0toYyM7KMkQe/ckGSB4i2Xw+H3OXh5foT7n0AflpzHRv7VEWlAja8mxljjOUIFy9eFIHv1atX0/wYOuegsi916tRJMD/Gzw8+69eLaaPChZGrZ09oN31EfO4sgl9DK0p4BUQHleXglzHGsjoAfvLkifixocA3JCQEz58/T7KONiWX0IYr4RsfbxTTBmYf0KaiI/55EIqvQRHouvEm5nUoh67VCqh7MxljjLEMoxIuFPjS/3Lm5uaoUqXKd4Nh+p2kmqeJE2B5r1oNaXCwmHZwmQy975RJ0nT6pm4wyb8L0ihbdW8KY4zpVgDs5uaWFU/LUkAXE7Y234qFdxaiXv56aFW4Aao5fcCc488RFSvF3fd+HAAzxhjTSteuXROB74ULFxTzzMzMREA7ceJE2NjYiDq/VOoocTZo+f3WrVuLDNDKIl6+RMD+/WLavF49WDTQvszInkEROPvcU0zr6YfA1Hkr9CTRkBgGITq4FBCnH98SvIdbgRljLCsDYJb9rI2tsajeIsX9fj8UQklHSyy+sh+Nqmr3FW3GGGO658aNGyLwPX/+vGKeqakphg8fjkmTJsHe3l4x//Dhw2L4FZU6omzPctTtmQLlxOWPRNmjBQsBqRTQ1xetv9rma2AEevxxC+99QlE0jzmK2uaBb6wjYiTuMIh2hn3kUMTGxiLEeCdg9RCWxgawDumPgrZm6t50xhjLmQEwfenu379fjNXx8vLCnDlzUL58eQQGBorEFTQOh36YWNYp6iiFl/HfmHw1CE98esGlhgvComLEj2XZfNa86xljjGmc27dvi8D3zJkzinkmJiYYOnSoCGQdHR2TPIaC22nTponlVOqIsj1Twis610iu7m/wuXMIu3NHTOfq1RPGRYtCm3wOCBfB7wffMHG/RmFrROXeibMf3FE3f12sbrxaVEKiLNlWuTZi+s3pooxi/RJ5REUJxhjTZVkSAAcEBKBFixa4c+cOLCwsEBoail9//VUso/ujRo1C3759sWDBgqx4eRbPLehbV/RqDtXEFe+JB57g3HNPLOxQHp2qOvG+YowxphHu3r0rAt9Tp04p5hkbG+OXX36Bi4sL8ubN+93noGC3YcOGqa4jjYyE15KlYlrfxgZ5RoyANvHwDxPBr0ewB0zyn0QHp7FoWMkLE66cRbOCzUSAS1UjomOjE5RRxBWIILjZx2bfrTrBGGM5WZYUiqUfqmfPnomrt66urgnG41A26M6dO+PkyZNZ8dJMSXXH6jjS7ggmVZ+EJgWbiPrAp59+RVSMFOP3P8Lsf54hOlZWJoExxhhTh/v376Nt27aoUaOGIvg1MjISXZffvXuHVatWpSn4TSu/HX8h2sNDTNuN+hX61trTI8rdLwzdNlHw6w6zQuvE+F4/iz/xY8EfsazBMkXwm5g8CKZ1OPhljOm6LAmAjxw5Ilp8mzZtmmy25xIlSnCirGySxywP+pTpI6YrONng759rIJdVKMwKr8Rfj86iz9bb8A2JzK7NYYwxxoSHDx+iXbt2qFatGo4fP65owR02bBjevn2LtWvXIn/+/CrdW9FeXvDdKKuaYFy8OHJ17ao1n8YH31B033wLnwLCERedGwVMy4j5pXKXgh70RGCbXPArR8s4+GWMsSzqAk3jfAsXLpzi8ujoaMTExPD+V4PaRWxRvuIZPPTxhJnzn7jjaoWf1oZjU5+qKJdfe66CM8YY005UKnHWrFkicZWcgYEBBg4ciKlTp6JgwYJZ9treK1dBGiYbN+swxQV6BtqRC9QrOEIEv18CI8T9XxoUw6gf1+Lml5uihxdjjDE1twAXLVoUDx48SHH52bNnUaaM7Moly35ti7eAqYEp8krqQxrpKK4md9pwA4cfyrqEMcYYY6r29OlTMQSqYsWKiuCXhkUNGjQIb968waZNm7I0+A1/+gyB8a9r0bgxzH/4AdrCyDASzoXovCoOIxoVhUuLUjA3MufglzHGNCUAph+zP//8E3v37lWM/6Wu0JGRkfjtt99w+vRpkdSCZT/6HLqU6IJDPx3Cga4LMa11aUj0gMgYKSYfvo53Pv78sTDGGFOZ58+fo1u3bqhQoQIOHjyoCHwHDBiA169f448//kChQoWydI/Lyh4toAnqZw2HSROhLdyD3NHnVG88j/oLvZp9xIRmJZMdXsYYYyxtsqTvz+jRo0USrB49eogC9aRnz54iHT91fabg9+eff86Kl2Zp5GQpywA9qJ4VSjlaYcTue3AqfRijr/6NeXXmoZJ9Jd6XjDHGMuzly5eiBOKePXsUF8MlEgn69OkjShYVK1Ys2/Zu8KlTCI/vmZa7Tx8YZXHArQpuPqFwtDaBiYEJwmPCxbxwyVt1bxZjjGm9LAmA6cokXdHt168fDhw4ILo2SaVS0TW6a9euqF+/fla8LMugusXtMLVLBObdeSbuH3c9LgLgiOhYmBjq835ljDGWZtSqS4Hv7t27xW+/PPClC+HTp08XiTCzkzQ8HJ7Llolp/dy5YTdsKDTdy69B6PXHbZR3shY5Oqiu7yX3SxhacSi3/jLGWCZlafaHunXrihvTfJ1LtkVYrD+OvTuGcVXH4a1XiKgzSF2k21VSbRZOxhhjOQ9lbp47dy527typCHzpgjj1BqPAt1SpUmrZLt8//0TM5y9iOs+Y0dC3tIQme+Lhh747DyMg1BGXXnnj3xdeaFW+DMrYcu4UxhjT2DHA79+/xz///JPiclrm5uaWFS/NMkhfoo8B5QZgf9v9MJKYYNjO+/AOjsToPfcx4OAqhEdxqSTGGGNJubq6ivG8FOD+9ddfIvilwJfG/VLiq//9739qC36jv36F75atYtq4dGnYdOoETXbLzR29jv+MGId1kBh/wm+tSqNVedXVQGaMMZZFAfCECROwevXqFJevW7cOLi4uvP81kIHEAAb6EkxvUwbWpoYwsr2CeyFbUH9XB7z0/qDuzWOMMaYh6EI2Jb2kLs3bt29HbGysmE+ZnqnUEY39VXfFB6/lKxAXLhs/6zh1CvT0NXdYzxOPAAzecwRxJu+gJ4lG+XJ3MLh+EXVvFmOM5ThZEgDfvHkTTZs2TXH5jz/+iKtXr2bFS+coIf9eQNTVa2p57fol8uDwiFqwyP1S3A+NisCgbS/w4kuQWraHMcaYZvjw4QOGDBmC4sWLY+vWrYrAt2PHjnj8+DH279+PcuXKqW37gs+fF7fwR48QFN8bzbJ5c5hVrw5N9cg9AL223EZwQBFEerVCCYs62NNhjbo3izHGcqQsGQPs7+8Py1TG2FhYWIiM0CxlEc+f4+uYMWI6slRJGJYvn+27q4idFS702I+eB+bi5ecC8IiIRcf1N7C0SwW0qZAv27eHMcaY+ri7u2PBggUi6I2OjlbMb9euHWbNmoVKlSppxG+nx8hfxbRR8eLifz0jI9hP1MyyR5Qd+8b7Txi64xmCI2PEvOn1hqJPrYKc7IoxxrSpBdjZ2RnXr19PcTm1/jo5ycrwsOR5r1+vmPbbuEltu8nGzBQn+szHhIZNQWUHw6NjMXLXQ4w6uQzbnm5DrFR25Z8xxljO5OHhgREjRoiyRRs3blQEv23btsX9+/dx5MgRjQh+E/92Rr15I/7PPWAAjJw0L5ljdGw0Zt+cjVl3hyMkOlTMW9ChPPrWLsTBL2OMaVsATBkfqfwBjQOWZ4Ik1E1q1apV2Lt3ryiHwFK+gh1y/l/F/dB//0XEixdq212UzGR4w2L4s391WJkYwNHOB1d8dmLF/RWYe2uu2raLMcZY1vn8+TNGjRolShiuX78eUVFRYn6rVq1w584dHDt2DFWqVNHY306inysX7IYMhiba93ofDr45iK8R79Gg1i0s7lQePWs6q3uzGGMsx8uSLtBTpkzBtWvXMGbMGMyfPx8lS5YU81+9egVvb280bNgQv/32W1a8dI6gfAVbzmf9ejitUe94oEYl7XFsZF089XmKjS+c8Cn4E7qX6q7WbWKMMaZaX79+xaJFi7Bp0yZEREQo5rdo0UJ0da5Zs6bW/HYa5MsHibk5NE1MrBTdSnbDVY+rCIwMxNLGE5HHLI+6N4sxxnRClgTAxsbGOHv2LHbs2IFDhw7h3bt3Yn6NGjXQqVMn9O3bFxJJljQ+a73krmCT4HPnRSuwSenSUKdCduYoZFcTPxbbjweeD1AqdymsOv8GxR0sRKmGkKgQWBhZqHUbGWOMpZ+npyeWLFkiWnuVA19Kajl79mzUrl1b6347I58904jfTmXX3/pgxtGn2D6gBpY1WCaqL5gYmKh7sxhjTGeoPAAODw8XrbuNGjUSdQHpxjJ3BVvu82QXFD50EHoGWXLdIl1MDUxRJ38dnHjyBb+ffy3mda0Tg6vBizG26hh0KdGFxzAxxpgWoJ5ZFPhSiUL6DVeu2ECBb506daDpvH5fmeIyTehBRcmudjzbgQef3XDmSk1ExkjRZ+ttnBlbH8YGmluaiTHGciKVN8OampqKblN0JZmp5gq2XOTr13jXug3CHjzQmF1rZqwPSxMKyGNx4stKhEQHY9GdRfAI8VD3pjHGGEuFj48PXFxcULhwYSxbtkwR/NIwpcuXL+P8+fMaH/xSYOmzaTNCUymtKO9BpU6bn2zG8vvLcfHLQUgtbkFfooeJzUtx8MsYY2qQJf2Qq1atiqdPn2bFU+ts669c9IcP+NCzFz67TEGMBpSSko8LLmZvjQjPnyCNtoZhUCtEhNmoe9MYY4wlg8oQTp06VQS+ixcvRmioLANx/fr1cfHiRXGjaU1Hv4GfRo2G9++/f3ddagVWJ1vURlyMhfiNRGQBrO1RGa0r5FXrNjHGmK7KkgB45cqV2LNnD7Zs2YKYGFldO5a51t/EAo8cwbuWreC3axfiYtVbiqiwnTmOjKiDHwvWQ6jrWHi610T7dddx+ulXsfyF7wt4h3mrdRsZY0zX+fv7Y/r06SLwXbhwIUJCQsR8auWl1t5Lly6J1l9tEHTqFFzbtEXwuXNpWl+drcDnnntiyj4PhH0cgKiPv2Jt5zZoWZ6DX8YYU5csGUzav39/keTql19+ESUU8ufPL7pGJy6t8/jx46x4ea1EgWxaGeTNi5gvXyANCoLnnLkIPHAQjjNnwLRiRaiLhbEBNvauirUXrbHi3GuERsVi6M77GNbICRdDJiMkOgTTa01H80LN1baNjDGmiwICAvD777+Li9NBQUGK+ZTUisb4NmnSRGtyNsT4+eHrnLkIPn063Y/137ULeedmT+m+fz/+C0OJIcICSuDX3Q8QHRsHIxTA+l5V0KSMQ7ZsA2OMsWwMgHPnzg1bW1tF+SP2fbk6d0b4o0cJZ8ZRqYQYGOgbAErnJvnmzxcnAZ7z5iP60yfReuzWvQdsOndGnnFjYZArl1p2uUSih1E/FkeZvFYYu/cRgiNj8C7sOj6FfBLLfcJ91LJdjDGmiwIDA7Fq1SqsWLFCTMtRRQYKfJs3b641gS8JOnsWX2fNRqyfn6LGb+5+fRF4/HiaHk+/kdmBkl0tu7cM5gbmiP00EtGxuWCkL8GmPlXRqJR9tmwDY4yxbA6AqRsVSx/TSpVQNNGPeHR0tBirRRcTDA0NkzzGvHZt+G7eDN8/tiAuOhoB+/eL7mB5xo+DTadO0FNTqSm6un1kZB38dcMNM9q2wgX34jj9/jR6lOqhlu1hjDFdQq28q1evFoEvdXuWq1atmgh8W7ZsqVWBb4y/v7jgG3TihGKeZdOmcJw1Ewa2trAbOhSaJL9FfvF/HOIwoZUDVv4jwcKO5dGwJAe/jDGmCdRfT4dlmMTEBHlGjYL1Tz/h67z5CL12DbEBAfg6fQYCDhyA44wZMC1bVi17uGgeC8xuV05MNy3YVNx8QyLxxCNQXAEPigrCuofrMLzScFgbW6tlGxljLCcJDg4WVRgoo7NffCspqVy5sgh827Rpo1WBLwn+9198mTkLsT6yHkT61tZwmDEdVq1aaex7aVKwCabVnIbKDpVRIlcJtCsZCxNDLnXEGGOaQpKVV6AXLVokuljRj++dO3fEfPpRpqvSb9++zaqX1jlGhQqhwB+bkX/1KjE+mEQ8fgK3Ll3FWKlYpTFf6hIdK8XIXQ8xYPtdrDz/GotvL8aul7vQ/mh7fAn5ou7NY4wxrUXJrNauXYsSJUqI7M7y4LdixYo4cuQI7t+/j7Zt22pswJic2MBAfJ48GR4jRiqCX4vGjVHk+D+wbt1ao96LcqLHQw888O8LT3Qr1U0Ev4SDX8YY04EA2MPDQwS9M2bMENNPnjxRZJuk8cF0hXqNmovS5zR0MmDVrBmKnjgO28GDAAMDQCoVST8oW3TAkSOiXqK6vPYMxhOPADG98vwLXHX9KKZL5ioJR3NHxXpn3M4gWhqd4vPQMlqHMcZ0HZUvotZeCnznz58vhsyQ8uXL4+DBg3jw4AHatWunUcFiWgRfuiQyPAcePSbuS6yskG/JYjitWwuDPHmgSc66nUXfU30x6sIo7LrzFuP3P8awnQ9w8ZWXujeNMcZYdgbAEydOFF2xHj16hMuXLycJvNq3by9KLjDVk5iZwX78eBQ5egRmNWuKebG+vvjiMgUfevdBxKvXatntZfNZi1JJVDKJet5/fNENlsG9MbDkJMXJGQW2Ey5PgMsVl2SDYJpHy2gdDoIZY7oqLCxM9KQqUqSI+L31iW8hLVOmDPbv3y9+ezt27CiqMWgT6q30ecpUeAwdhhhvWYuqRYMGKPLPP2KojyYG8je/3EREbASe+T7HjLPHQKc7hvp6ojICY4wxzZQlv45nz54V5Y/oxzi5Hyz60XZ3d8+Kl2bxjIsWhfP2bci3fJniinn4/ft437EjPBcuQmx8i3x2Ku5gKYLgRiVpe/Tw2aMcft76BhdeeorljZ0bw9HMEWc/nMXEyxMTBMHy4JeWNSvYTKzLGGO6JDw8XGR1Llq0KMaPHw8vL1krY6lSpbBx40bR4tu5c2etC3xJyNWrcG37EwIPHxb3JRYWyLtgAZw2boChg+Ymj5paYyqKWdRE6Md+iAkpKQLfv36ugeqFcqt70xhjjKVAklU/0nlS6aZErcMs69HFBxorVeTUSeTu1w/Q1wdiY+G3YwdcW7ZC4IkT2d4t2trUEFv6VcfIRsXEfSqV9POOe1jz7xv8++ECvoZ9VdRQlLcEJw5+F9VfJOorMsaYLoiIiBDDhijwHTNmDL5+lX1PUqnBXbt24eHDh6KrszYGvnQx9sv06XAfPAQxnrKLoeZ164qxvjYdO2hcq69vuC+kcVLF/d13PuHh3Q6IDS0Jy/jgt2pBDn4ZY0yTZcmvJbX8XrlyJcXllJSDxgiz7KFvYQGHKS4ofOggTKtWFfOoe9nn8RPwccBARL57l60fhb5EDxOal8TG3lVgZqQvuoxtvuIKe6OiqOZQDdZG1mjg1EDREkw3Dn4ZY7omMjIS69evR7FixUSvqi9fZAkDixcvjr///hvPnj1Djx49oE8XN7VQ6I0botU3YP8BcV9ibg7HuXNEUkdDx2+5ITTFU5+n6PJPF6x+sFrc33b9PWYcfSamrUwMsHNQTVRxzqXmrWSMMfY9WTJIha5Q9+vXDxUqVECXLl3EPKlUKjI/UymGmzdvigQdLGVUA5jGT3/48AEFCxZEgwYNkq0FnB4mJUui4M6/EXj0KLyWLhNjg8Nu3YJr+w6w7d8PdsOGiTHE2aVFubwobGeBoTvvY3qb0lh//iPcffvCUOKNl1/sYGwRIFqCiVFUKTx+0BqtHtwQ9wvamomWZMYYy2mioqLw559/YsGCBQmGC1ELMCWX7NmzJwwo0aGWig0JhdfSpQjYu1cxz/yH2sg7bx4M8+WDJqLeUnNuzoF3uDe2Pt0Kg8jyWPZPhKJn086fa6K8E5f0Y4wxbZAlv6C9e/cWgdu0adPw22+/iXktWrQQPyDURYt+1CkRFks+8KXyUevWrYNnfHcw4ujoiOHDh8PFxSVTgTB1J7Np3x6WjRvDe+Uq+O/ZQy8K3z+2IPD4CdFSbNm0abZ1OyvpaIkzY+rDyECChSdf4q1XGJ0K0YgwmBjGwNBYtl6k4Ut8jD2GKN8fs7J6F2OMqfX7f/v27Zg3bx4+fpRlyieFCxfG9OnT0adPH60OfEnorVv4MvU3RH/+LO7rmZnBYdIk2HTrqnHdnZXRti1vsBy9T/XG0IpD0aZQfVx4dAeuPqEi+C2Xn4NfxhjTFln2S0qBL/1YHzp0CG/evBEtwHT1mjJTUhIslvzJD10YOHnyZJITAQqG6cr/7du3cfjw4Uy3ButbWcFxxnRYd+qIr3PmiLrBMV++4NOo0WL8leO030R94exAwW9CsTDJvweGVs8QHVwaBuavoSeJhZHdJUQH1EBcLJ9oMMZy1nf/X3/9JQJfNzc3xXzq/UOBb9++fTP9na9u0tBQeC1fIUrzyVGlgrzz58HIyQmaiMb6SvS+/T4VsCqAkx1PwtyQLtIC2wfWgGdghEjwyBhjTHtkaVNaUFCQ6MpFLb8U0FEQTOUbWPKo5ZeCX5I4OZX8/okTJ7B48WKV7ULTsmVRaPduMe5K31oWWIZeuybGZXmvXg1phKyLV/aRB7//ITqoPCI8eiPM7RdIY41FEGzseFyswxhj2i4mJka0+FIW50GDBimCX2dnZ2zatAmvX7/Gzz//rPXBb9jdu2KojTz41TM1hcP0aXDe9qfGBr9fQr6g54meuP3ltmLejbc+MDP4NkzIysSQg1/GGNNCkqxK3NG/f39UrFhRdNndvHmzuNE0zaOr2RQYs4QtANTt+XtdwGg5rUfrq4qeRIJcXbqgyOlTsIkfsx0XHQ2f9Rvg2roNgi9czJaPKi5x8PupO7VVQxrpjNDXv4l5tIzWoXXvfb2HoKigbNk2xhhTZeBLLb6lS5fGgAED4OrqKuY7OTlhw4YNIvAdMmQIjIyMtHqnS8PD8XXBAnzo0xfR8WOZzapVE3Xqc/fqJX57NFFUbBT6n+6PZ77PMO7SOHwO+YyV51+j55bbWHb2VbZXT2CMMaZaWfLrM3nyZPHjPmzYMLx48UKUcKCgmKaHDh2KnTt3YtKkSVnx0lrr+vXropvz935YaTmVwKD1Vc0gVy7knTsHhfbugXGZ0mJe9KdP8Bg+HO7DhiPKwwNZKdLocZLg9xsjMU8eBIcZX8PICyPR+VhnPPB8kKXbxRhjqhAbG4v//e9/KFu2rEgUSYkhSb58+bB27Vpxn34jjY3jkx9osbAHD+Davj38//pb3NczMYHD1Klw/msHjJydocmM9I0wqsooMd2mSBvsuh6AleffiPv773nAP0x1F6AZY4zlkDHAFODS+F/6QVdGNQup9ZK6RtM6K1euzIqX10p+fn5Zun56mFasiML794sEWZQoSxocjJCLF0XJCruhvyD3zz9DkgUtEyZRVRDuEYGY4LKJgl85fREExwSVh3luH4RGh4pbSHSIyreFMcZUGfju27cPc+bMwcuXLxMkN5w6dSoGDx4MExOTHLHDadiM96rV8Nu+na7YinmmlSsj38IF2ZZXQhVaF2kNZ0tnnLpviLWXZKUCHa1MsHtILeQ21+6WecYY03VZ0gJM3XNr1aqV4vIffvhBdAFj3+TOnTtL108vPX190UWt6OlTsI7P2B0XGSlObFzbtkXI1WtZ8roxwRVSCH7l9MU6FuFtMbXmVPQv2x/1nepnybYwxlhmUN4LCnypJCCVLpIHvw4ODvj9999F1+dff/01xwS/4Y8e4X2HjvDbtk0Ev3rGxrCfPFmU39Pk4JcupM69ORd+EX4Jelsdv2eA9fHBb15rE+wZUguF7WQJsBhjjGmvLAmAmzdvjjNnzqS4/PTp02jWrFlWvLTWqlOnjjgpSksZCDs7O7F+djCwtUW+RQvFCYxxiRJiXvSHj3AfPBgeo0Yj+ssXqIMe9NCjVA+MrzY+wXz3YHcceH2Ax2gxxtQa+B44cEDkvOjWrRueP38u5ufJkwfLly8Xge+YMWNgamqaIz4laWQkvJYtg1vPXoh6/17MM6lYAYUPH4LtgP7igqqmCowMRO+TvbHv9T6MvTgW0bHR4vdj/okX2HRZNjY7v40p9g6pjUIc/DLGWI6QJQHw3Llz8f79e1Hy6N9//xU1gel2/vx5dOjQQUzTOtSNV/mmyyjL54gRI9IUuIWGhuLOnTvITpS4pPDBA7B3mQyJuewKePDZs3jXug18t2xBnAYkNYuRxmDK1SmYfXM2xlwcI+4zxlh2oe9vKlNXuXJldOnSBU+fPlVctFyyZIn4XRw3bhzMzL5lEtZ24f/9h/cdO8F3y1aK/KFnaAj7CeNRaNcuGGtByUMrIyuUzF1STJsZmiEyNhJzjj/HlmuyQN4pl6lo+XW2zTmfGWOM6bosGQNMmS3Jf//9h6NHjyZYJg/wypQpk+w4KV1GWbKpzi+VOqKWYOVgWPl+eHg4fvzxR5ForGvXrtm2fXRiY9u/P6xatoLXkiUIOnECcWFh8Fq2HAGHj8Bx+nSY16qZbdtD+2PpmVdoWS4vyjtZi7IVX0JlLdKO5o4wkGRZmWvGGEvwXXTs2DHMmjULjx49SjBUZeLEiRg5ciQsLCxy1B6TRkXBZ916cQEU8b/dJuXKiR5DxsWKQVvQb+vsH2ajnG050auI6v5SDyPinNsMuwbXhFMuDn4ZYywnyZIIYcaMGWnqysuStgJT6wHV+aVkYZTtWY66R1MLMf0/fPhwkVWbutZR3Ug6wcrO/W3oYI/8y5fBpktnfJ0zF1Guroh69w4fKThu3Rr2kyfB0N4+3c9bMB1X2Gndrdfei/FZf15/j9+7VkLL8gVw6KdD+OPJHxhZeWS6X58xxtIb+NIFSwp879+/r5ifK1cuTJgwQYzvtbS0zHE7NfzpM3yZMgWRb2SZkWFoiDwjRsB20M/QM9DsC4+x0licfH9SZHeW/24a6xujd5neinWmtymN3OaG6FjFCflsckY3dcYYY9/oxWlxQbv58+dj2rRpoqSEvKtZejx79gzlypUTj6Xn0CSUSOzy5cuiu3jBggXRoEEDESAT6kreqVMnkU2bUNmMNWvWwEANJx7U9dl3xw5RMzguPFzMoy7SeUb9ilxU5zELt2nHDTfM/ucZpPFH8MTmJTG8YdEkFwOipdGYfWM2+pbtixK5ZOOYtRUdF76+vrC1tVUcD0y38TGR/ehn89SpUyLwvXv3rmK+jY2N6OI8evRoWFlZ5bhjgL7vfTZuhM+mzd9afcuUQd6FC2FSUvO/W0OiQjDpyiRc/XQVIyqNwNCKQ8V8qTQOUbFSmBhq7ljljODvBsbHBMsp3xfPVByzaWYV+jTw8PDAggULYB4/HjWnoYOPgt7WrVsnCH5JkyZNcO3aNRQoUEDc37hxI9q1a4eQkOwvB6RnZAS7wYNR9MRxWMYnNpOGhsJz4SIxLixMqVVE1fr9UAh/9q8OC2NZkE3docfve4zImIRd6Tc/2Yyj746i+/HuuPv128kqY4ylN/ClBI+1a9cW383y4Nfa2loEwzTGd/r06dka/GaXiJcv8b5rN3GxUwS/BgawG/WrqBuv7uD3jNsZcaEzJbSM1qG8EG5BbmLeuQ/nxHjfWGkcJh18gv7b7iA8SreHYTHGmK7Q2gCYupdRqaVq1apBF5UvXx63bt1CpUqVxP2TJ0+ifv36+Pz5s1q2xzBfPjitXoUCf2yGYUFnMS/y9Wt86NUbn12mIMbXN0tet2FJexwa/gMK5JZ1Uzv08BN6/nEbPiGRinX09fTFuK6CVgVR3q58lmwHYyxnB77nzp0T2fdbtGghcjUQ6t5MAS8FvjNnzhQtwDlNXHQ0vNetw/vOXRAZX8bJuFQpFN6/D3mGDxe5IdSJAtsJlyfA5YpLskEwzaNltM7tr7extvFaUeP3r5Z/wUDPCBP3P8aB+x645eqHeSdk2boZY4zlbFoZAF+5ckWUmFi5ciV0Wb58+cS+aNWqlbj/8OFD1KxZUyQfUxeLevVQ5Ngx0TJANSBJ4JEjeNeyFfx27UJcFiQ6K+FgiSPD66BawVzi/v0P/mi/7jpefQ0W96mb244WO7C4/mKYGHyrt6nFvf8ZY9mAviMuXLggLi5S6b6bN2+K+ZTQ6rfffhM5GObMmSPG/OZEEa9e4323bvBZsxaIiQH09WE3fDgK79sLk/hkl+rW2LkxmhVshrMfziYJgml61IVRYhmtQ+sWsSmCRfUWwVhiinH7HomLpqSUoyXGNtX8btyMMcZ0MACmTNGUWGTQoEGiFVTXUQsEZdqmccDyruF169YV44TVRWJsLFoGipw4DouGDcU8aVAQPOfMhVuXrgh//Fjlr2lrYYz/Da6JjlXyi/se/uG48c5HsbySfaUk43/XPVqHWTdmISw6TOXbwxjTbpSDoWHDhiLjPg05ITTkhrL1U4vvvHnzRJbnnCguJgY+GzfhfefOiHz+QswzLl4chfbtFfkdaOiLpjCUGGJR/UVJguDwmHC0P9Ie1z5dQw3HGmIdWpfExEoxZu8jHH0k6zFVOq8Vdg2uBTsL2UVbxhhjOZtmp2tMBo13ldcUTg8vLy94e3snmPf27VvFwG+6aZqYmBgR8NP/37Nq1So4Oztj6tSpIjlWy5YtsWHDBvTr1w/qoufgAMc1qxF66RK8Fy1CzKfPiHj+HG7de8CqY0fYjhkNfRV2GaSrOYval0ERWzN4BISjV/X8KX6uj7wf4Y///oA0Tgq/cD8sr78c2iA9xwTTDXxMqBYFu9Sqe+nSJcU8qts7bNgwkeAqT548Yp4m/Wao8higjP6ev01D5LNnshkSCXL9PBC5hw4Vga8mvW9lc2vPFS32FARHX4xGcHQwPgZ/FMvoO14aI0W0XjSiY6UYt/8/nH7mKZaVyWuJ7f2rwNJIT2PfW0bxdwPjY4LllO+LaBV/P2tVAEzZyajEEo25kp+EpNX69esxe/bsZJcFBgaK59Y0dBAGBweLH/W0ZHgeMGCAyN42atQoUSZp8ODBeP78ebaXSUqifHlYbN2KiP/tQsSePXQUI+jgQQSfOwfTIUNg1Kol9CSq64zQuawV4uIs4efnp5jnFxYNK2MDGOjHl72INEY5m3J4EfgCPZx7aOTnr4pjguV8fEyoxp07d7Bs2TJcvXpVMc/ExAT9+/cXJejs7OzEPE38rlDFMRAXE4vIffsQvm2b+I4mkoIFYT7FBShVCn7BsiElmmxsibEIiwjDRY+L4n4xy2LiIufsirPh7+cvgt9pJ9/j8rsAsbyUvRlWtisCaXgwfGVFDHIU/m5gfEywnPJ9ERgYqNLn07x3mAoqeURdzqgLdHpR7dwuXbokaQFu3769yOBJgaMmHowUuNJ7TuvBSEFwyZIlRZkkOlH7/fff4enpiU2bNsE4fkyu2kyaiKhuXeG9YCHCb9xAXFAQwpYtQ+zZM8jz22+inEZiIf9eEP9b/Ng4wy8bGhmDcXvuIreZIVZ3rwhrU0PYwhZb823FK/9XKGOb8HVDo0NhbqiZ2cUzckywnI2PicyhhFbU4ktJrpQD319++QXjx4+Ho6MjcvoxEOX6Hp7TpyHySXz+CIkENv37I/fwYWJIi6a77HEZR94dQWHrwjBS6p5dwLoA5tWeB1NDWZLEBx8DcP297CSqgpMVtvWtCitTzSv3oSr83cD4mGA55fvC2tpapc+nee8wBW/evMHmzZtF4ivlTMcRERGiWZySkVDpiZTGZNnb24tbcqjEkCbWvCL6+vriQEzP9lHZJErWQt2g3717h127dol9dujQIbUnazEsVgxmW7cg+Ow5eC5ciJivX8VJl0ePnsjVvTvyULfo+BIi1F3665gxYrrw4UMZTrqy4dxbvIxPiNX1jzvY2q86CtuZwxCGqOhYMcG6Dzwf4NcLv2JqzakiU2hOOSZYzsbHRMZafClz8+nTpxXz6CIhBb40zjdv3rzI6ccAJSX02/EXvFeuFDV+iVHhwsi3cAFM4ysMaLpBO+7iQfRaRBu+w2WP64BeDIwjZd/r1BL8486RsA7pDz3oo6CtGdb0qIxt192wpX81WJnk/O9Q/m5gfEywnPB9YajibdKaJFifPn2CVCoV3XsLFy6suNHV+9evX4tpuorPZIoXLy6CYKpXSWg8G5XwoAsF6kZXmKyaNxO1g20H/SzqSUIqhf+uXSJbdMCRI6ILhvf69YrH+ChNp9foJsXRoqysFcfVO1RkiL75Lmk3xqjYKEy9NhVBUUGYcX0GvoZ+zfBrMsayH10Mpe86uthH/yc3Zuj+/fto06aNyJgvD36p1XDkyJHigiHlU9C24DcjIt+/x4fefeC1ZIks+KUr/wMGiIuNmhr8hkSF4MDrA3jt/1ox74NvGIK8KyJOKhHBb3RQGfi4dhW36KDyiDB+CA/DLXjjFSjWbVk+L/YMqaUTwS9jjDEtD4DLlSuHw4cPJ7mVLVtWJH+i6Z9//lndm6lRaJz0v//+i86dO4v7L168ECd9d+/ehSaQmJvDfsIEFDlyGGY1aoh5sb6++OIyBe87dkLI+X8V6wafO4+IF7JspOllZmSA9b2qYESjouJ+YHg0+my9jb13ZQlS5Iz0jeBSwwW5TXJjXLVxcDTX/K6PjDFZ4Dt37lwUKFAAjRo1EkNA6H/6baD5tJzKxP3000+idvyJEycUV5QpuRUNh1mzZg3y55dlkc/J4qRS+P31F9536Ijwhw/FPKrdXvB/O+EweRIkJt9KxWkSGprS5EATzL45G3tf7lXMj0MsDCxeQU8ilQW8n3pRO4a4RXzqLuYZWv0Hk/x7xLpEIlFjTgzGGGNqpzVdoCkBCY3XTUxeCzi5ZQwwNTXF3r17RZe+pUuXimzYVNpj9+7d4mRQExgXKwbnHdsRdPwEPJcsRqy3DyKTCXapFdhpzZoMvQad8ExsXgpF81jA5eB/iIqVYvLB//DWKwQuLUtDP/6EqGGBhjjS7ghsjBNmp3YPcoejhaOijAZjTDNQcEvf/ydPnkyS7I/yH1DixHXr1olpOeriRRdMKWs+Bcm6IurjR3yeOhXh9+7LZujpIVef3rAfOxYSU9k4WU3hGeqJPGZ5INGTXaenvAxVHariiscVPPB6IHoJ0ecdafQYhpbP4oPf7vHBr5wsCCYUBEcGUwm+jOeTYIwxljNoTQswyziJRIIlS5aIk0CaDgsLEyeM1OKhKehExrptGxQ9dQpWbZIfe5uZVmC5jlWcRL3g3OayRCl/XH2PKYeeJFgnl0muBCfS1CX657M/o+/JvvgQ9CFTr88YU61FixaJ4JdQUKRMfl8e/FLgSzXkKacEldTTleBXtPru/B9c27VXBL+GBQqg4F874Dh1qkYFvx+DPmLo+aFodrAZ7ny9k2DZkApDsKHJBhxoe0DxHW0SVQXhHj2TCX4TBsG0Dq3LGGOMaX0ATOO8nj59qu7N0AqUCfvo0aOipiWdGNJ46rFjx4q6X5pC38IC0oiIFJdnZiywXPVCuXF0RB2UcLCAkYEE3WukfhK8/el2fAn9gqe+T3Hj841Mvz5jTHWtv3RhLy1l3qg3DP1W/PHHHyhUqJDOfARRHh742H8APOfNQ1y4rNZPrl69UOToEZhVrw5NY21sjbtf7oryRYffHE6wrGKeiqibvy70JQkD3ZjgCikEv3L68eswxhhjWtQFmqkGJX+5cuWK+P/r16+iC/mHDx+wc+dOERirG2V+Vh77m1wrcPjz5zBNpmRSehTIbYaDw37Afx6BqOKcembsoRWHIjI2Eu8D36N7SVl3OsaY+l2/fj1B1+bUhIeH48uXL6JMnC6gi5wBe/fCc8lSxIWFiXmG+fMj7/z5MK9VU92bh8DIQJx8fxIXPl7A+h/Xw1DfUBEAdyjeQUx3LN5RzVvJGGMsJ+IAWAdVrVpVZM9u1aoVnj17JhKINW7cGMeOHUuxVFR2Uc78nJJPv45C0dOnoJfJlOiWJob4oZhdgnkXX3khOCIGP1XMlyA51sTqExEjldVIUz6Be+H3ArXy1srUdjDGMsbPzy9L19dW0Z8+4cv06Qi9cVMxz6Z7N9hPmAh9C82ocU5jeRfcXqCY/rHgj4pl02pNU+OWMcYYy+m0vgs0yxga+3bt2jUR+BIKiGvVqoVXr15pbOuv8smdW5++iA0JUenrv/oajF93PcSo3Q/x+7nXScYTGki+XS+iZfNuzcPgs4Ox+M5iREuTllthjGWtlOq+q2p9bUPfS/779sH1p3aK4Ncgb14U2LoFeWfNUlvw6xHsIVp6lTUp2AQWhhbIb5EfUVJZDeK08g+NSvL9zBhjjKUVB8A6zMbGBqdOnUK/fv3E/ffv34u6wdRFWh38du1K87oRjx7hQ6/eiP6qulq9/mFRkFfHWPXvG/y6+yEiopMfH+0R4oHLHpfF9MfgjzDQ484UjGW3UqVKiVJG30M9NxwdHUUt9JxK6uWFL8OG4euMmZCGhop5Nl06o8g/x2Chxve99uFatDzUElOuTkFYtKwrNjE1MMXu1rtxsuNJtCzcMk3P5eYTiulHnqL2on9x7a1PFm41Y4yxnIwDYB1nZGSEbdu2Yfbs2eK+v78/mjZtKsokZbdcnTvDqFjR1G9FikASP1Y58tUruHXtlunM0HK1itji8Ig6KGQre/7jT76g2+Zb8ApOmpSrgGUBkYm0gVMDzP5hdpqS8DDGVIcyOdevX18kwvoeai0cMWJEmoJlbUPvLejwEQQOGIiw67IkfQYODijwx2bknTtXJBbMzm1RDnJJWduy4v+wmDDc/PKtSzYpZF1IUeYoNQ8++mPo3/fRaPkl/H3rAyKipdh8xVXFW88YY0xXcLMVE8Eb1cqkzKhUGzMqKgo9e/aEm5ubqB+cXcGdaaVKKHr8+HfXi4uJgeeCBfDftRsxXl6iJTj/yt9hUb9+preB6gQfHl4HQ3fex+33fnjsHoD2a69jS7/qKJPPKsG6zlbOWPvj2oTbFheH7c+2o02RNqKGJWNM9a5evSpKucnH9ObNm1ckuKLvKuWusfL7rVu3xuTJk3PcRxHt6YkvM2Yg9PK3XjvWHTrAYYoL9K0Sfl9ltT0v92Dvq70oalMUyxosU8yv61QXg8oPEq28JXKVSPPzSaVxOP/CUwS69z74J1jWsGQeDKlXREwXjL9gmRbpWZcxxljOxQEwU+jbty+cnJzQsWNHBAYGYurUqXB1dcX69es1quVEz8AADtOnw7CAM7yWLIE0LAzuw4bDccYM5OrWNdPPn8vcCH//XFN0tdt7zx2fAyPQeeMNrOpeGU3LOKT62H9c/8GK+yuw7ek2rG68GpXsK2V6exhj3/zvf//DwIEDxYU68ttvv2H69OlYunSpKIlE2e3lHBwcRMsvBb+a9B2mklbfY8fwdf4CSIOCxDw9W1s4zpkNmx+/JZPKTk+8n+BtwFtRKz0gIgA2JjZivqHEEKOrjE7Xcz1yD8C4vY/g6iPryi2eR18P7Srlx+B6RVDS0VIxny5OMsYYY+nBATBLgJJiUWkRyhD98eNHbNmyBe7u7ti3bx+ssrlFITXUsmM7oD8M8+XD50mTEBcZia8zZyLawx15xo6FniRzvfupPvCiTuVRzN4CC069QFhULLZdf48mpe1TbRGnk0BC3fqomzRjTHVB39y5czFz5kxx38DAAJs3b8aAAQPE/WnTpolAl76/qGWYEl7RmN+cFPiSGG9vfJk5CyEXviWVsmzbBpIhQ2CeDfWNqRzckbdHUNWhKuo7fet1Q6WLnvg8Qfti7SHJ5PdvPmsTuPvLulJbmhigV82CGFCnEBysTDK9/YwxxhgHwCyJsmXLiqzQVCv4/v37OHPmDOrVq4cTJ06IFmJNYtW8GQwd7OE+fARi/fzg+8cWRHl4IN+iRZAYG2fquSnQHVy/CArZmYus0Ot6Vvlud3Aq31HFvoqoZWlrapup12eMyURGRmLw4MH4+++/FQn8Dh48qMhiL0fBbsOGDXPkbhOtvidOwnPuXMQGBop5+nZ2yDt7Fkzq14evr2+Wb0N0bDR6n+yNoKggvPJ/lSAAruZQDf+0/yfdQ2YosdWOm24Y17SEKE1H7K1MMKR+EeQyM0L3Gs6wMOZTFcYYY6rDSbBYsihj6qVLl0QQTJ48eSLKJD1+/Fjj9hiNHS60ZzeM4ls/gk+dxscBAxHjn3DcWEZRt+fjv9YVXaOVx6cFhieffKdVkVaokz9h1tV/3v2DLf9tQaw0+azSjLHkUWtus2bNFMFv4cKFcePGjSTBb04W4+ODT6NG4fOECYrg16p1a5Hh2TKLujxTwP3Q6yFCo5W7IRuiVeFWYjoiJiJB+TcKfNMT/Conttp23Q1777onWD6xeSkMqleEg1/GGGMqxwEwS5GFhQWOHDkixtCRT58+oW7duqJFWNMYOTuLINi0WlVxP/zBA7h1744oNzeVPL9EXh8p3tKzr/DT2mt46/X9WsTuQe6iZvCqB6sw+WrOS8TDWFZ5+/ZtgtJsNH3r1i2ULl1aZ3Z60KlTcG3TFsHnzov7+rlzI//qVci/fBkMcuXKsrq9Px35CX1P9cUZt4Tf9wPKDcCx9sewvcV2Mb43PejC4dlnX9F5ww10XH8Dp599hTxnWVq+SxljjDFV4ACYpUpfXx9r1qzB8uXLxdX9kJAQkVH1jz/+0Lg9p29jA+c//xQtIyT6w0e4de+BsAcPVPo6N9/5YsOld/jgG4YO66/j6hvvVNen8h/2ZvZimsbHMca+j8byUq+T169fi/tdu3bFv//+C3t72d9SThfj5wePMWPxaew4xAYEiHmWLVqgyPF/YNWsmUpfSxonTXDf0dxR0fJ79O3RBMvyWeRDYevC6Xp+qqf+v9sf0GTFZQz5+74iqzMltupc1QlnxtTHok4VMv0+GGOMsbTgAJh9FwW+48aNw/79+2FiYoLY2FgMGTJEZImWShOeOKmbxMgI+ZYuge3QX8R9OnH82H+AaEVRlVpFcmNMk+JiOjgiBv233RW1KVNSMndJ7G2zF0vrL0Xd/HUTLFMu2cIYk6E65NTFWT6udcqUKWKeqampTuyioDNnZa2+p08rLu7l/30FnFb+DoPcuVXa0rvk7hI03d8UfhGyklLEQGKAIRWGYGK1iVjRcEWmX+fsc0/8dvipIqszJbYa2qAork1ujGVdKibI6swYY4xlNQ6AWZp16tQJFy5cgJ2dnbi/cOFC9O7dWySo0SSUAdp+zBg4zp1DTdiIi4oSrSi+W7aoJOCkCwJjmpTAmh6VYWwgQaw0TpRMmnXsGWJik78gYGZohhaFWySY9zHoIzr90wkPPFXbQs2YtqK/z3nz5ok65FTmiDI9b926FQsWLMh0ZmFtQHkLPo2fgE+jR4ukfsSyaRNZq2/Llip/Pc8wT/z9/G94hXvh+LuENdi7l+qOvmX7ZiiZn1dwRIL7Lcs5iszOdJvWujRuTvkRLi1LcVZnxhhjapHzzyiYSsnH4BUvLmsBpVaZpk2bikQ1miZXly4osGkTJObm4r7XsuX4Ons24mJiVPL8bSvmw54htWBnIcs2vf2GG37ecQ9BEcknx1IWI43BlKtT8Mb/DQaeGQj34IQJYBjTNRTwUkkjqulLrK2tcfr0aVHzVxcE//svXNv+hKATJ8R9ibU18i1bhvyrV8Mg/qJjZro43/5yWyTiU0YZ6wtZFUJNx5ooZJ35EkoPP/pj2M77qL3wAl57BivmG+pL8Pegmrg8qREntmKMMaZ2HACzdCtatChu3rwpamySq1ev4ocffoCrq6vG7U2LunVQcNf/YODoKO4H7NkL9+HDERvyLbNpZlR2zoWjI+ugdF5ZjeTLr73Raf0NhEelnu2Z6gRTtmgjiRF6lOrBNYOZTqMLaM2bN8eOHTvE/UKFColMzz9mUYZjTUJZnT9PngyPESMR6+Mj5lk0aiQyPFu3aZ3uskLJWf9oPQadHYTVD1bjU8gnxXx67n1t92FL8y0JShqlN7HVueee6LLxBjqsv4FTT7+KXjF/XEn4e1A0j4UIhBljjDF1418jliG2trY4f/48unXrJu6/evVKJKyh1mFNY1KyJArt3Qvj+MyxoVeu4kOfPoj29FTJ8+e3McWBobXRpLSDuN+8rCNMjfS/GwD3Kt1LnHyOqTomwbKQqBAeG8x0xrt378QFNCq7RmrWrCm+R8qUKYOcLvjiRTHWN/DoMXFfYmWFfIsXwWn9OhhmMNlXZGykyDyvrGnBpoqxvU99niZYZmqQsXHVlNhq1+2PIrHV4L/u4a7bt8RWnao44ed66UuUxRhjjGUXDoBZhlFCrF27dmHyZFlpH29vbzRq1AiHDx/WuL1q6GCPgn//DfMGslaOyBcv4NatOyJevVLJ85sbG2BTn6pY0bUixjUtkebHFbUpCmN9WRdqQnU1h5wbgvGXxyMgIkCUIFGutZkYLUtcpoQxbUGtvHThjC6gkS5duuDixYtwcJBdTMqpYoOC8HnKVHgMG44Yb1kWefpuEq2+7dpluNV383+b0WhfoyTl1igR38J6C3Gx60U0L9Q809tPpYzqLLqAqYf/+5bYytgAvzQogquTGmN514oo5SjrFcMYY4xpGg6AWeYOIIkEixYtwsaNG0XJpIiICJEs6/fff9e4Vkx9C3MUWLcONt1lrdYxX7/iQ89eCLl6TTXPL9FDxypOCWoG+4ZEYuPld6KbYFrseLYD//n8h3MfzmH2zdmYcHkCXK64JBsE0zxaRutwEMy0zZ49e0SmZ5/4br8uLi5iXk7P9Bxy9aoY6xsYf6FQYmGBvPPno8DGjTDMZOBPuQWCo4LFdwjlF1DWpkgbWBtbQxWccpnBNzRKTMsTW92Y0hhTWpaGo7WJSl6DMcYYyyoGWfbMTKf88ssvcHZ2FrU6qVYwlU16//69CIQpMNYUegYGcJw5E0YFCsBr6TJIQ0PhPnQoHGfNFEmzVCkyJhZDd94XXQMffQzAim4VYWaU+p9cp+Kd8J/3f3APcce8uvMguS7B2Q9ngSvAovqLEgS/069PF8uaFWyGxs6NVbrtjGUVujBGWZ2nTZsm7lOm5w0bNmDQoEE5eqfHBgfDc/FiBB44qJhnXrcu8s6dA8O8edO1/659uobDbw+jsn1l9CnTR7Hsp6I/4YX/C3Qo3gEFrQqqZLspsdXBBx6Y1bYsDOLH8JbJZ4X+PxRCZWcbtCqfl8f2MsYY0yocADOVadmypUiI1bp1a3z+/Blr1qzBhw8fRDdp8/hMzJqAuhfa/vwzDPPnx+dJk0WZpK/TZyDa4xPyjB4lyiipgn9otKKV5PSzr/DYFIYtfaun2kKSyyQXVjZaiaCoIJgbmsuC3isQgW7ov6FYUX+FaOWZdmMazn08J4JfWsdQYqiSbWYsqzM908Wy7du3i/tWVlY4ePAgmjRpkqN3fMj16/gybTpivnwR9ykzvb3LZNh07pyh7s5L7y3F+8D3eBvwFr1L91bMd7JwwsamGzO9vdRj5d+XXiKR1R03WYb/WkVs0aZCPsU6s34qm+nXYYwxxtSBu0AzlapUqZJIYFO+fHlx/9ixY2jYsCG+fv2qcXvaqsX/2bsL8KbOLg7g/7rSFtpCaYHiznB3hg2GM2z4sCEbDgPGYMDGGDpkQz5kOAzbhru7DXf3KnX/nvOWhLa00NK0Sdv/73lCcyXJzc1NuOe+73tOQ+RauhQmDg5q2nP+fDwdNhyRodFBa3JJoLvp66qolj+6hMnlJ6/RdM4R/PfY572PkxNiTVdFCWwlwM1jnwdHnx5Fxx0dMfHiRAa/lOZ4e3ujYcOG2uDX3d1djQFOz8GvZJt/9sM4PPqqhzb4ta5cCXn/3qJ6nHwo+A0MC8SW21veydzcIn8LWJpYooRTCQSFB+lse+MmttIEv5LY6oFnoM5eh4iISJ8YAJPO5cyZU7UES31gcebMGZXo5tq1awa3t63LlEbutWtg7h7dXVBqcD7s3h3h3tEZTZPL3toMS7qVR8dKudT0S78QtJl/HNsvRZ8MJ4ZnkCce+j5U92/53MLRl0dRO0dtFRg/8XuCcy/O4UXAC4Mbc02kISXSJNOzJLgSFSpUwMmTJ1GsWPptRQw4cQL3mjaFz9q1atrI2loNtci1eLHqffIhHkEeqLO+DsYcHYONtzbGWvZFwS9UQqtJ1SbB2sw62dvqHRCK3/beQrVfEk5s1a92/mS/DhERkSFgAEwpwt7eHlu3bkX37t3VtHSFjnkCbEgk+HVfsxpWZcqo6aAzZ/GgfQeEPowOOpNLal9OaFYc45oUheTHCg6LxNcrz2HOvluJClpdbFwwv/58WJu+e6IrJ8ZddnRBw40NERkVGWvZ2utrsePeDjx4/UAn74PoY0jNcLkAdv36dTUtSfLSc6ZnySvw/McJeNi1G8KePlXzrCtUiG71bdcuwVZf7+DYF92crJyQ1z6vui9jfmOyNbdVN11Ze+YRpu++CQ9/JrYiIqL0jwEwpRgzMzMsWrQIEydOVNM+Pj5o0KABVqxYYXB73TRzZuRashh2jT5T06H376sySYHnz+vk+eWkt2vVPPhf1/KwtYgeej//0F08fx38wcdKwqt1N9YhMDxQtfxWzVoV+x/vVxmgH/lF1/t0tXGFifHbZGMRkRGYfHoyhh0ahg233ibdERdfXcRPJ39SGad9Q3x18v6I4rNu3TpVGk1KpInhw4eredbWyW+1NESBp0/jbvMW8F61Sk0bWVkh25gxyLV0Ccxz5Ij3MXd97mLAvgGqfNF1r+iLBBr9SvXDb7V/w4pGuv3NfOITu9t0+wq5YGNugqLZ7TCrXSkcHF4bParnRSZL5hYgIqL0h0mwKEVJ4Dd69Gjkzp0b3bp1Q1hYGDp16qQyREsW2I+td5kSjC0s4Dp1KszccsBz4UJEeHurVhzXKVNg16C+Tl6jdqGs2Ni3Cnr9eQY/NiuO7PbvL/miKXWkyfY8ofIEeHl6YfqN6WpeNbdqmF17NqIQuyX5VdArlSxLuNnE7m7536v/sPr6am1plJjGHRsHnxAfVMpeCe0Kt9PJe6aMR3o2SHm0UaNGqWnJBC+Znnv27In0KDIoCC9nzID3n8u186zKloXrT5O0wysSYmlqiYOPDqrv8ObbmzGywkjtsqpuVXW3jTESW1147INjI+vAyTa6Brm9lRm2flMd7o7WBvWbTERElBIYAFOq+PLLL5EjRw40b95ctQSPHTtWBcHz589XLcWGQjJAZx0yGGY5cuD5jz8iKiQETwYORNiwYcjSratOTg4LZsuE3YNrvlM6JDA0PFaZpLjBr8oIHQGYGptiYpWJaltkmXSNjlkiSdNt+nj74yp5jqOVY6xlIREh6jFywp3FMkusZdLV8kXgC1iZWsUKgK94XEHfvX3hZuuG7yp8hxLO0UnOhLQiy/rmJuZIKVLnWEo9JZTtWvbVvof70CB3gxTbBkocucjVp08fLF68WJvp+a+//tLmBEhvAs+dw9PvvkPYg+ghE0aWlsg6aCAyd+oUK6O8f6g/dtzfgRPPTuDXGr9qf0tcbV3xaa5PVeK7xnka63z7JLHVpvNPsPDwXdx9FT22V/x57D4G1y+knc7tZDiZ+omIiFISA2BKNTVr1lRZXxs1aoT79+9jyZIlePTokTo5ljHDhiRz2zYwc82OJ98ORGRgIF5OmYKwx4+QbdQoVUs4ueIGv2fue6HX8rOY9kVJ1C6cVc2TgC5m8CvBX1hEWKzs0JoSSfUf1n8n+JMxgoWyvD3B1ehRoge+Kv4V/ML8YgX0Moa4YOaCKpiVrNMxSV1ir2AvdZMAPKaJJyaqALWkc0ksb7Q81vOdfXFWBc3ZrLPF6qKdFPLcQw8OTbDkU8wLBSKjBcH+e/ch1M8PaN5M35uiLm7JGN99+/apaakNLrkAihcvjvQmMjgYr2bOgteyZdLkreZZlS6N7D9NgkWe2N8fzXh9KV8k2hduj7LZymqXzag9Q+fbJ4mtVpx4gGXH72vH9moSW3WolAvtK0Yn5iMiIspoGABTqipSpIgqk9SkSROcPn0ae/bsQbVq1dRJspwsGxLb6tXhvmolHvXug/AXL+C9ajXCnjyF2/Rpqo6nrviHhKPPirPwCgjFV8tOY0zjouhWNbc2kEuo5VMTBMcX/H6IBL525nax5hkbGWNe3Xnxru9i7YKWBVqqrNNumWJ3qZZWZmlNtjCJ7k6p8SrwFbrvjE6CNqriKHXSr3HZ4zLuv76v6pZ+4vyJeu2EyPuX4FcFuIcQKwiO20ou62YkwVev4vnAgep+SOFCMHtTfkwfpEeH1ADXZHsvX768KoPm4uKC9CbowgU8HfmdyhUgjMzN4TxwILJ06QwjExM8D3iuks9VzF5R+5jP832OGWdnqF4XciEpJf15/D5+2nZNJdzTcLW3RPdqedC2fE6O7SUiogyNATClOsn+euDAAXTo0AFbtmzB5cuXVZbYf//9F2XeZGI2FJaFC6sySRIEh9y4Af+DB3G/Uyfk/P0PmGWLbqlNLkmKJVmiB627oE5Yf/z3Ku688se4psU+GNhKIJgaLZ6lspZSt/h0LtYZd3zuILtN9ljzY9YulVbgmLbd24blV5fD3NgcpzuejrVs1rlZyGSeCeWylVPBcdzWbk0QLOJ2EU+oi3R69Wre2wsWXn/Mh+3cOXrZDrmo1bRpU22yqxYtWqhkd+kt2VVkSAg8Zs+G5+IlMqhWzbP85BO4Tv4ZFnmjMzZPPzMdS68sVVmcd7Xepe0xIYHvysYrUShzoY/uDZFYOTJbaYNfSWzVq0ZeNP4k+zs9T4iIiDIiBsCkF3JivGHDBgwePBi//fYbnj17hho1aqgMsdJFWjOW8OjRo/Dy8kKWLFlQtWpVvYwXNnNxgfvKFXgycBACjhxByNVruN+uHXL+8QcsCxXUyWt8ViI7cmS2Ro8/T+PF6xCsPPkQ2y49Q2Ybc5jE6KYsyYUiIiJUUqGY3Zclec2iLuWhDw1zN4x3foHMBTC/3nwVCBd1LBpr2VP/p9rxjzFbf6VFd/Hlxar7dM8SPVUALCSwbVGgBc6/PK8C3qB9QWrM8d6HezNs8Cutv/579mqnA/buRfC1a7AsUiRVt0OGMEhiu+Dg6IzmQ4cOxS+//ALjGONf04OgS5eiW33v3FHTRmZmcPpmAOw6d4S5xdtkdrntc6seEZKIToYAxGwFjvs90EViq33XX+LgjRfoV/ntBblaBbOqzM6NS2RH1fyOTGxFREQUAwNg0hsJ4mbNmoW8efNi0KBBCAgIUF2jJSCWoHfu3Ll48eKFdn3pStm3b1+MHDky1QNhE1tb5Px9nqrv6bN+PcKfPcMDSez12yzYVKmik9cokcMeW/pVQ88/z+DSE194B4apW1olrbhVXOPfNz9V+wnPAp4hMCww1nyvIC/YmNnAL9RPBccx3fa+rYIKcfjJYfVXkgdlxOA3buuvhse8ecgxe3aqvL5cjJkyZYr6Pmq+z/Kd7d27N9KTyNBQeMyZC89Fi962+hYvjmPf1sAWn9345PwLjKk0Rru+9Mi44XUDzfI3Q5EsKXMxIr7EVtXdrVHbMTrhnbGxEX5uqb/u8ERERIaMATDp3bfffgt3d3fVJTooKAj9+/dX8+NmXJZgWLJHnzx5Eps2bUr1IFhafFx+HA+zXDnxatp0RPr742Gv3sg+fhwcWrXSyWu42FtiXe/KGLzuArZffo70ytrMGvkc8r0zP5tNNhxrfwyvQ1/D1Cj2z5Mk58pnn0/VPg6NfJvUJyOK2/qr4bd7D17v3o1MdeqosagpRXpnyMUoqfMtMmXKhPXr16s63+lJ0OUrePbddwi5dSt6hpkZnPv1g2OPr/DLgf645nUNj/0fY2i5oaqckZALON9V/C5FtiehxFYyjOKJb0iKvCYREVF6wwCYDIKUR9q/fz/q1KmDwMBAbQtTTJppSZglXSyljnBqk6DcqWdPmLu54emIkYgKC8Oz0WMQ+vgxnL/5RiddDa3MTTC3QxmUnbg7TbcAJ0fcBF2iZcGWOPX8FO743lEtv0K6QPfd01dlux5YZuA7GaozUuuvxpMB38DI2lqNX7csWjT6VqyoGqMqF3F0ken5iy++UAnshCSvk/H7JfSYgEvXoqTV948/4DF/AV5kisCB6saoEJkLdYbPhGWh6MzqLfK3wH3f+6qlV1NzO6U89AzE/47cxbozjxEUFvFOYquWpbIjNMA3RbeBiIgovcgYZ4uUJkgCLBkbrAmAEyJBpnS1HDFihN5qCNs1agTTbNnwuG8/RPj6wvP3PxD2+AmyT5oIY/Pk18OVLoxOthYZNgCOK96ayAAG7R+Eg48Pqtqqt7xv4fe6v783o3R6bv2NKSowEEHnzqmbhmQqtihU6G1QXLQoLAoWgLFF7Ozd7yPlyyTT89WrV9V0uXLlVKbn7NljJ0BLy2Qc9dPvRiHk+nUEmQODe5oizBQIyf0JGr0JfkXdXHVRz71eqhxvEvwuO/5AOx03sZW0yHu+LfFLRERE78EAmAyGJLzy8PD44HrSEvz8+XO1fq1ataAv1mXLqgzR0g067OFDvP7nH4Q/f44cc2bDxMDqGqe34Fcz5ndE+REq0ZB/mD88gzwRERWRrgNgaZl8PGjQB9czy5EDJo5ZEHL9BqJCQrSPDb50Sd20TE1hkT9/rKDYsnAhGMeTvfnUqVNqjP7Lly+1vTYk07ONDkuC6Xus75H/TUTm3zfBNDS6RdchTyHUzJoVe7yO43nQS/Xbo+nlkVKZnCWx1UOvQOR2ertfpZV3+YkHqFbAGb1r5EWVfExsRURE9LEYAJPBkMRXSdGuXTvValygQAEULFhQ/ZWbdMmUhDypwTx3buRes1q1BEtt0MDTp3G/XXvkXDAf5jlzIrVI2aRmc44gr7MtCmSzRd9a+ZFe7Hu4L8FSRzntcmJnq53osauHGo8p66ZGWSh9CH30CI/69kPYg4cfXDfs8WPkmP0bLAoUQMjdu6rVWHOTLOaRml4W4eGqpVNuvhs3Rs8zMoJ53ryxguJdt26iQ8+e2kzPQ4YMUcMQUut7ltKuXdiHoYeH4aFdKIbnikC5eyZw6t0LTn36oH/gI/SNilRZzVOSJLba/CaxlU9gGI6OrANLs+j96+5og8Mj6sDN4W22aSIiIvo4DIDJYEipo6SQpFjbt29Xt5jMzc2RL1++WEGx5r6rq6vOS4KYZsmCXEuXqBIpfjt2IPTePdxv205ljbYqWRKpITIKuPjYV93yONnECoBfvg5WNYZlfl4nW+R1jv7rltkKJsa63RcpQRPQ1slVJ95sz3YWdqq+aszgV7JLb723Fa0LtE4XJWBeb9+OZ9+PVYnXEst71SpknzABlgULqhuaN1fzoyIjEfrgQaygOFiCYt83Y0ijolSpH7lJrwZRGMDm7K64FhKCAg0boGbzFoiS9ZP4nU0JO+/vTPDY0PQgiHthRNOSGxUerrI7By+Yi1d9JMeAEQ5WsUXryUtgVbyYWjef+bvJ2nSd2GrlyQdYeuwBPPzfJrKSLM9SykiDwS8REZFuMAAmgyF1frNly6a6WMZNgBWXdLusX78+7ty5g1u3bqns0RqhoaG4du2ausX3uPz588cKijV/nZycPjpYMra0hNv0aXjp5gqv/y1GhJcXHnTuAtepv8KuXj2kNHsrMxRztVMlUfI5x+6SevulP47e9lS3mMxNjZHb0VoFw3mcbTCwbgFYmBpmi96HWnUl+NGsIzWERx0ZpRJknX52GhOqTYCFSeLHuRqSyKAgvPjpZ1V6S8PY3h6mTo6qpVaJAsIjwmFqYirxm5ZD69bxPqeRsTEs8uRRN/vGjaOfIioKYU+eIvjqlbdB8eUr6jjWyGVurm44egyPjh5T80yzZ3/TSlzkzd9iMM3qnGoXHST4HXpwaIK1oGN2nxfFHIth/c312P9oP5YX/gleY8Yj+PJlSP7mJqeMYVemHNr2nQQrB7cU3/YPJbb6/JP0M66aiIjIkDAAJoMhCa369eunSh19iNQe1WSBjoyMxNOnT3Hz5k0VDMtNc18CZEkQoyG1hi9evKhucdnb278TFGtuDg4OH9wmCSyyDRsG8xw58HzCRDX28sk33yJsxHBk6dIlRYOCrJkssKpnJXU/QpqDY5DJEm72uPvKHwGhb0+0Q8MjcfOFv7rZmJtgeINCsZZ1WHhCjUPUtBjLX3dHa4MNkjU8gjxw3eu6uh9fOaW0QkrvPBk8GCG3bqtpGVee/eefVImjmFQCJE9PODo6fnRSODk2zXO4qZtd/frw9fVFj9atceHUKRS1tEDlrNnQsUoVmD95ompga8h9f7ntfZuUy8TJKUZAHB0Um7npvueFkJZfCX5VgHsIsYLguGPHZd1Djw5h8eXFavnase1R/XL0WF/zfPkw9JufYPXJJ0gNP2+7pro6x/yqxk1sRURERCkjbZ4ZUrolga3U+ZVSR6qLYoyWYM20ZKGVDNAaxsbGyJEjh7pJGaWYwsPD8fDhw1hBseavZLSV4FlDTvpPnz6tbnE5OzvH26VaWpPjJgHK3L49zFxd8XjQYJWN9+XkX1SG6GzfjUzR2qwacbs1VyvghGoFqql998ovBHdeBeCuhz/uqb8BKjB2sDaPFaA89ArAmQfe6haTPLV0ndYExAPqFEAWm+RnvX6fHstO44Hn+zODa0iAvqhLeaxuvBozzs7AkHJDUixZUUqRz0lafKXlN+rNmFurcmXhNnUqzFxcUvz1Hzx4oL5jV65cUdP+hUvim3/+0WZ6DvfyUl2mY3ahliRwGhEeHgg4dFjdYrZaxw6Ki8Lc3V1dNEoOCXZVRvBDiBUEyz7ss6cPTj8/Hat1uGJYDtiHmCD7y3Bk8o+UHw84du8GpwEDkpQNO7lkTK8m+K1RkImtiIiIUhMDYDIo0oK1adMmlWBHSh1JtmcN6R4tLcRJKX9kamqKvHnzqluDBrG70UpX6bt3777Taix/Hz9+HGvdV69eqZtkno7Lzc3tnVZjue+2eDFeDBiA8Fev4L1iBcKePIHbtKnxZthNKJgTcjIv2bElSZh0dY353rJkzqK6bmvWfR8JcLPaWapb5XyO72SejSkkPBLlc2fGPY8AePiHvl0vCnjkFaRuB2++wpD6b1uNhbQaZ7YxRz7VcmwbPe7Y2QaZLD++XJUEv7deJn7sq8hsmRk/Vv3xnfkXXl5AqaylYKgi/PzwbOxY+G3fET1D6k737Qunr/vAyDTlf67l4o9kepbx9aJZs2ZYuXJlrIs8MubdtlpVddNu9+vXCL52PVZQHHr3rhpPLGR8ceDxE+qmId8DizhBsapVnMT3GTcIDln/DLfDnuFJhAeMYYxRFUfBNMoYnouX4NXMmZhhHArb4OgEdtlX/gTr0qWR0omt7nsGYuRnMpI6Wssybrj6zBdfVnRHkezv1rwmIiKilGMU9aHBlumYtHAUL14cly9fRrFi0QlPDIkuujamZfL+JeCUwE8SZMkY4dTaD1KLWLpPx201lpsmOPgQaZku6+6On21s4fqmG3ZIjhyw/fln5C5dSgWwidkHUm5m27Zt720Rl4sGKbVvfAPDoluMVWtxgPorWadl3OLBYbXfrhcUhpLjo8daxuWcyUIFwzI++eua+ZErEQG7Rr3pBxMdABfIaovdg2vGu0zGfv54/Ed0KNwBw8oPg6mxYV3/C/rvPzwZPERlcBamWbPC9ddfYVOxQqr8TmzcuBEdO3bUjqcfNGgQfv3114/O9BwZEIDgGzdjZ6C+fVtlnk6IkYUFLArHqVVcoECiamtLl+fB//TGAZ+3PThMYIJpxUcj39RNCDp//s2LGKkhCc4Dv1Vj91OCT2AoVpx4m9hKek7IdyVnlsQf90mR0f+voPjxuCAeE5Refi+u6DhmM6wzQKIY5Auorzq/1tbWKFGihLrF9fr163eCYrkvNx8fH+160r369L17aGZsjJmubqhqYwOLx49xv107NHn+DJE5csQ75li6ckvwLCZPnqyCXxH3WpVmWrqLS4u5Zky0rtlbm6F0rszqFt/ra/iHhKN6AScVJD/1DdI0/inS9Vpup+55oVeN2Fl1e/15BpFRUW9ai22R18lGJeVytrXQ2bjR4PBgzL84X5s4qUeJHnC2doYhkKzMXkuW4uWMGdrg0KZmDbj+/LNqbU3x14+KwrRp0zB8+HB1X4692bNno2/fvsl6XmMbG1iXKa1uGpEhIQi5eSt2UHzjhqpRrLYlJATBF/9TNy0zM1gUeFur2EqC4kKFYGwVXRIoNCIU51+eR5lsZVQGdrw5TPMG2GCKTUdEffUTgt50JTdzzwXXn35SNbxTwiMvSWx1D2tPP4qV2MrFzlItS6kAmIiIiBKPATBREtnZ2aFs2bLqFpMED3L1LL4u1UNu3cLQsDC0dnCAm5kZlrq64dvHj/HvzZvvPL+lpaUaWyy3Xbvib1GNSYJE6S6elK7huhA3OJUyLcu/qqjt+nnfMyDGOOPocccSBOTIbBWr6/WhW68QHPZ2LLZGJgtT1X36+evo4CU5LE0tsfyz5Rh6aCiGlRtmMMFvuKenKp8VcPjNeFkzM2QdMhhZOndO9vjYRL1+eDj69++P+fOjLw7Y2tpi7dq1aNSoUYq8noyztSpRXN00osLComsVX4lRlunaNURpMrvL8qvX1M0XG948kTEs8uXF4zJumJr3Oh7AG+VsiuBUZg9UuBF9LJ0qFICp137HN6GR6j+6zJ06IeuggYkegpAUFx/5YMHhu9h+6VmsxFbSvbk3E1sREREZFAbARDoMCGU8rtwqV678TnD87NkzPJn1G2y3bIGdiQkW5cyF342N8L+7dxES8rb+Z3BwsOriIbfEkOeWsdLSXVxfLeZxWZqZoLCLnbq9T2BYBGoUcFZB8gPPAIRFvI0e/ELCVV1jXclumx0rPlvxTuDuFeyFLJapX8824PhxPBk+HBGvPNS0Wa5ccJs2LVZwmJKkJ0ObNm2wc+dONS09D/7991+UTKXa1RpGZmawLFRI3dCyhZoXFRGB0Pv3tTWKNYFxpJ9f9IMiI1V2bP/Xt3E/twmijI1wKuAKKl2LxDd/RwfAvzUFThQxhrGVNaY0nAX7ilVS7D3M3X8bu66+HRohia16Vc+Lqvkd00UdaiIiovSEATBRKpCTYFdXV7j+Mhm+1arh2ahRMAkLQ//IKIydMgVBTZvi9u3bsVqNz58/r4LmxJKx0mmNrYUpFnQup+6HR0TiiU+QtsX4noe/+ivdpsPjJOn6WHGDkdvet9Fpeyd0KdYFvT/pnSrBSlR4OF7NmQPP+Qu0SaLsGjWCy4/jYWJri9QgmdFl7LjmIkvp0qVV8CvHqCGQbOkW+fKpm32TJm9rFT9+jOArV7StxbmvX4Gb52s8djZCxevRwa/pm84EmkD4WJFg/Bi0AZMjy79TJ/hjSO+GZ77Bqsu+Ru+aebHv+ks0LeWKntXzMrEVERGRAWMATJTK7Jt8DjOXbHjUf4DKjus173fYP3mCTydMQN26dbXrHThwALVrv00y9SGSKCwtMzUxVuVh5Fa70MclwUoKCahGHRkF/zB/zL0wF1Vcq+AT55StAxv29CmeDB2GoHPn1LSRpSVcvh8D+5YtU62l8MyZMyrTsybDutxftWqV6v5syILCg/Dbs5VoWKYhSjVsqObtvLcTjw8NRdVndui3xUsb/Aq5L0GwWbZs2IVdqP+wPhrkjp0J/mMTW2W2NsPOgTVg/KbkWFn3LDj+3acq2RsREREZtpQfZEZE77AuXx65V6+GWc6catp3y9942LMXInzfdvmVrNdS+ulDgZEsd3FxUetT4sl++6naT8iZKSf6l+qf4sGv3549uNuipTb4tShYEHk2/AWHVq1SLfjdvHkzatSooQ1+v/32W5VB3NCDX8nw3H5re6y8thJjj41FSET0kIEGeRrg53wD0e/P2MGvhsz7euEz/Jx/0EcHvzJufdzfV1D5532YuuumyuosF2Rk7HpMDH6JiIjSBgbARHpikTcPcq9ZDcuS0YFX4MmTuN/hS4Q+fqKmJaGV1D3+UKUyWd69e3eDTFtv6PJnzo91n69Dr096xZofEfk2g29ySebj5xMm4vGbFn/h0L4dcq9bq7r4pgY5RqZPn46WLVuqMkeaTM8zZ8786DJHqUm6LjfJF90V2sHCAa9DXmuXlVxzPt7gV0OWlVrzpgRSEhNb9Vt1DjV/3Y+lx+5rszpLYqsZbUuian6nj3krREREpGcMgIn0yNTREe7LliFTvXpqOvTOHdxv2xZBly6p6ZEjR6qxmuJ9rYQ7duyAt7c3MrqXfiEqs3RS2Jrbxtq3UjKp646uWHdjXbK3J+TuPdxv2w7eK1eqaeNMmeA2axay//BDitWgjS/Ts1xIGTJkiAqEbWxs8Pfff6vsz4bsdejbIFd0LdZVtdgvbbhUm8VbxgH779n7wefy271HZZZOrD7Lz6LZ3KPY+t/brM5S4mvFVxWx7ZtqaFE6B8xM+N8nERFRWsT/wYn0TAIht1kzkaVbNzUd4emJB506w2/vXtWqK11UJ0yYoLpDxyTTmmLg586dQ/369dNlEOzuaI0CWW0TvOV2tIaZSXQA6xsUhpl73i0tlRSTTk7ChVcXMOHEBGy/t/2jn8dn02bca90aIdevq2mrkiWRZ9Mm2DWoj9QimZ5ljO/vv/+upt3c3HDkyBHtRRVD5Bvii9FHRqPNP20QGBaonW9qbKpagY2N3v635bVqVaKf1zsJ6xbIFt0l3NTYCC1Lu2H7t9VVia9qBZyY1ZmIiCiNYxIsIgMgNV+zjRgOsxxueDHpJ0QFB6sus9m++w5ZOnfCmDFjVJ3fk7/9hlevXiFT3bqoWbOmeuyXX36J9evXq+RGEgRL7eDMmTMjvVjUpfwH13nuG4wvF51QZZQ6VHRP1uu1KtAKhx8fRm773Kib621SssSK8A/Aiwk/qnHdGo49e8L5mwGq5E9qefTokQp0L73pTVCqVCmV6VmCYEO28/5O/H0net/NuzAPQ8sPTXDdzK1bI+jChUQ9r0Pr1vEmtlp58qG63692fu38zpVzIzQ8El2r5kZ2+7d1q4mIiCjtYwBMZECyfPklzFxd8WTwEEQFBeHFTz8h9PEjZBsxAhG3bsFx4SI4Asgp670Jpla+6V4bMwjevXs3HBwckFG42FtiTa/KCAmPUPeTo1TWUljz+RqYm5jDzCRpAat0yX0yaDBCHzxQ0yaOjnD95RfYVkuZBGVhYWE4ePAgHjx4AHd3d3VRRI6Ls2fPqpZfTRktCYTXrFlj8MmuROuCrfHv3X9hY2aDjkU7vnfdARfD8KDOsEQ9r/uFUCwq+Tax1f+O3MO6M48QGBoBG3MTdKzkDnsrM21Cq+8aFUn+myEiIiKDwwCYyMBkql0b7suX49HXfRDxygPefy5X5XMQ8TbTj9cf82E7d466LwFP3CC4Xr16GS4Iji8L7/7rL1ElvyMsTJOW6MnFxuWdeVIqqWDmgqjnHj1eOyYZW+u9fAVe/vorosLC1DybKlVU3WdT5+jxqroOfCdPnoy5c+fixYsXb7fbxUWVzpJsz5LsSnzzzTcqAZYhJruS/bbrwS5Udq0MO3M7NU+6OM/9dC5szWKPzY7PA8/AJJXI+u+xD+Yfuovtl96O7RW5HG1ULwJNAExERETpFwNgIgNkVbwY8qxdi0e9eyPk1u13Ev0E7N2rkvpYFikSKwiWgOKvv/7KsEFwTNK6N/yv/1CzoDPmdyoLS7OPDwClRfKPi3+o+99X+h5tCrXRLgv39sazUaPhv39/9AwTEzh/+y0ce3yluranRPDbvHlzbNu27Z0AUcobrV69Wt2XZZLlWQJgQyTje0ceHon9j/ajZYGWGF9lvHZZJvNMOn+9x95BaDrnaKx5ktiqV428qJafY3uJiIgyCibBIjJQ0hXafdUqWFeuFO9yj3nzYq9vZoZVq1ah9Zuxjpog2MfHBxmNZILecPaxun/w5it0W3IagaHhH/189ub2qkXS3sJetVZqBJ45g3stWmqDX/WZrVgOp149UyT4FdLyK8GveF+JLBkbbqjBr7AytVIZt8WBRwfgE5yyx6mmjJEmsdW2b6ITW1Uv4MzEVkRERBkIA2AiA2aSKROyDhyYYGmXoCtXYs1jEBzN2NgIS7qVR5V8MmIaOH7XE53/dwp+wdHdk5Oqeo7qWNl4JWbVnoWcmXIiKiICr+bNw4POXRD+/LlaJ1P9+sizaSOsS5dGSpHWX+n2/KGuwbJ8z549an1DJds4rso4NMvXDJuabYKDZcr2VDA2AnrXyIvDI2pjettSKOoa3eWaiIiIMhYGwEQGzmPhwgSXPfiyI17NnRs9RvgNBsHRrM1NsbhredUFWpx54I2O/zsF38CPCwrz2udF2WxlEfbiJR526w6P32bjcs4oXMlnBpdxP6hSVib29khJR48eVWN+39fyK2S5dIeW9Q1BZFSkqqs87ti4WPNdbV0xsdpEZLHMkuLbkMfJRiW2YlZnIiKijI0BMJEBk6zCccf/xiTlkjxmz8HtT+viYfev8HrbNkSGhDAIfkPG/S7oXBZ1i0TXUL74yAftF56AV0DoR30e/gcP4l7z5gg8dQrPMwPTW5lhYhsj7C5tnCrdaL28vFJ0/ZQy/+J8VVd5w60N2Psw4eM5JRmnwudDREREho8BMJEBk262iRIVhYBjx1T5pFs1auL5hImqbBLHBENlgP69Yxk0LpFd7aqrz16j3YLjSQqCo0JD8WLyL3jUuw8ivL3VPM8mlRFqZYoIRKrxwakhS5YsKbp+SpY2kizPkl1byhsRERER6UuaCoCvXLmCL774Annz5oW1tTWcnJxQo0YN/PPPP/reNKJUb/2NKdNnn8H4TffbSF9feK9ciXstW+FR27aY93kTdGrePEMnxjIzMcasdqXQorSbtjtsJsvEJcEPffgQ9zt8Ca+lS9W0sY0NXKdORetRi7G04VIMKjsIjfI2QmooVKgQzM3NP7ietEZLSaSqVVOm/vCHPA94HqubtrO1sypttKnpJlTKHn9St48REv62NBgRERFRuguAHzx4AD8/P3Tp0gWzZs3C999/r+Y3bdoUCxYs0PfmEemU16pViV7XxNYGBQ4dhNv0abCRoOdNd8+Qq9fg8fPPGHXnLtZUqIjK1tY4e+YM6tevn+GCYFMTY0z9oiTGNy2G2e3LqKD4Q3y3blVZnoMvX1bTlsWKIc/GDbD/vLGaLuFcAt2Ld4/1GM8gT1zzvKbz7T916hQqVqyI0NAPt1xL8NmvXz/VFT41hUeGY/HlxWi8sTG23tsaa1mprKVga26r0zJXj7wCdfZ8RERElDEYRX0om4qBi4iIQNmyZREcHIzr168nuUW5ePHiuHz5MooVKwZDIxlcPT094ejomOonsqR/QRcu4OmYMbFnRgHhEeEwNTEFYgxpdJ00CVYlS2qnw548gc/mzfDduEndj+lpWBg2+fribm53rNqzJ8PWCdYIj4iEh38oXOwttfMiAwPx/Kef4PvXBu28LF26IOuQwTB6TwtsWEQYeuzqgaueVzGh6gQ0zNMw2dsnP9ELFy7EgAEDtMGvq6srnj59qlp6Y/6Ea6YbN26MTZs2pfrvhm+IL5pubgqvYC9ktsiMna13qnJHuvbUJwi1px5IUgtwgay22D24JtIj/l9BPC6IvxWUnv8fuaLjmC1xfQANmImJCXLmzInTp0/re1OIdMqqVCnk+/ffj/qBMnNzg3O/fnD6+muVsMnnrw3w27VLjWV1NTNDPycnwD8Ae6pWQ9Wx3yNbs2YwtnwbAGYUEZFRGPbXfzh2xwMre1RC/qy2CL5xE08GD0bonTtqHRMHB2Sf/DMy1ar1wec78+IMLry6oLIeH35yONkBcFBQkGrJXbJkiZo2NTXFtGnT0KdPH0yZMkWVRJJszxrZsmVT648YMUIv/4FJneQxlcbgt3O/qQsAKRH8ClcHK0xoXhxjNl2CcyZLWJubfPAx7o7WKbItRERElLakyRbggIAAdWLo6+uLv//+G8OGDUPbtm2xcuXKJD0PW4ApI12hi/D1VVmivf/agJA49YONMmWCQ5PPYd+yFSyLFU2VjMaGYOeV5+i9/Ky672RjhhVZnwLzZiIqJETNsy5fHq5Tf4VZtugs0olx7Mkx/Hn1T8yqMwsWJhYfvW337t1Dq1atcP78eTUtY3rXr1+PatWqxToeDh48qIaHuLu7o2bNmqka+EpL91P/p6jrXvedlnAzE91uh3dAKDLbxG599w0Kg72V4V2pTm2GfuWe9IPHBfGYoPTye3GFLcDAkCFDMH/+fLVDjI2N0bJlS8yZM+e9O+7ly5d49epVrHm3b9/WfuhyMzTh4eGqi7f8JUr2MWFtDdvWrdUt4MoV/NW3L4q98oCDiQmi/PzgvWq1upkXKgS7Fs2RqXFj1fqZntUp6IiBn+bHwu2X0OvUn4h6+l/0AmNjZOnTB5l79ZRuJkn6fSiftby6IRIIi4x+nLQIewR5IKt11kQ9x44dO1SuA+83Gacl6JULfNmzZ39nWyTRVZEiRbQZn1Prt2zF9RWYdX4WLE0sUci+kMrwHJPmvSdXZGQU5h++hwWH72NdrwqqK7OGtWnqvV9Dxv8riMcF8beC0vP/I2E6/r8+TXaBHjhwIFq3bq3GwK1bt059YB9KDDNv3jyMHz8+3mXSkixXPQyNHISS9Esa6aXrI5HOjgkXFzRYuxb9+/RByKHDaGlvj6q2tiorXuiNG/CY/As8pk2HWdUqsGjUCKZly8LI5MPdTNOi1sZPUP34LFh7e6hpTyt7RA77DpnrVISXjhKFLb+9HJsebMLokqNR1qlsgutFRkZixowZqpuzpnNOr169MGbMGHVFNr7fKX39TjjBCRFREQiOCMbhu4dRx7WOzl/DLzgcP+66j8N3fdX0oLUXsLR94QzTQyGx+H8F8bgg/lZQev5/xNc3+jwgQ3eBjkuT0fbkyZMJnhgl1ALcvHlz1cXQEJNgycHo5eWlWnYM8WCktH9MyBW1jh07qoRJLqam6FukKNo4OSHy6dNY65lmy4ZMzZrBrnlzmOXMgfQgKjISPkuWwnP2bMmmp+adcCmK6WXaIjKTHRZ1KoNy7pmT/Tp3fe/ii61fIApRyG2XG+sarYOp8bufnXyu3bp1w/bt29W0jY2Nym4vpd8M4XdC/quI+/v6vyv/Q3XX6iiYuaDOX+/Gcz/0W30RD95kes6VxQpz25dCYZdMOn+ttI7/VxCPC+JvBaXn/0euXLmC0qVLMwlWTNIa3Lt3b9y8eVPVyYxP1qxZ1S0+0rJiiP3dNUm+5EA01O2jtH1MyHOsXbsW7du3x4YNGzD20n/4t1w5/D13LiJ27cTrnbsQFRyM8Bcv4L1ggbpZV6wIh1Ytkal+/TSbOCvcwwPPRoxEwNGj0TPMzJBt2FBYFqoJ/82XERUSge7LzuF/XcqhSn6nZL1WIadCmFx9MqacnoJZtWfByuLdxFByEU7G+8q4X/WYQoWwceNGFC1a1CB+J848P4OfT/2MGbVmIJddLu38PqX6pMjrbT7/BCM3/ofgsOgsz3WLZMW0NqU43vc9+H8F8bigxOBvBaXFY0PX25Sm6gAnRBJipUTzOFFGID8qq1evVgGYOHXmDJqO+g7W332HAocPwWXcOFh+8ol2/cCTJ/F0+Ajcql4Dz8aNQ9ClS7FK8Rg6/6NHcbd5C23wa+aeC7lXr0aWzp3RvqI7prYuCWMjICgsArdf+evkNRvlbYTtrbYjr0Ped8bJLl26FFWqVNEGv5LTQGr+Jjb4TWmP/B7hq11f4ab3Tfxw7Ac1njmlhIZH4octlzFw7QUV/EqD87AGhbCgUzkGv0RERJTxAmDpxhxfF84///wTVlZWBnPCSJTmg+BTp9CgQQP4RUQgc7u2yLNuLfL8vUXVwjXJHN0tONLPDz5r1uL+F21wr1lzeC1bhnAvLxiqqLAwvJw2HY969ESER/R4X7smTZBnw0ZYFX87BKJV2RyY1a40Rjcqgs6Vc+vs9eOWBDr5+CQqL6yMvj/2VXXMJaGflDb666+/YGdnB0ORM1NOtCnYRiW7qp2zdope7Ji++yaWHX+g7me2NsOybhXQr3Z+GMsVCSIiIqKMNga4RYsWeP36NWrUqAE3NzdV/1Iyo16/fl0ljRk8eHCSno9lkCitSek09fL8mu7QokKFCti5cyccYmSDllrCfgcOwGfDBgQcPiKZm94+gZkZMtWuDYfWrWBTtarBJM4Ke/IET4YMRdCFC2rayMoKLmPHwr55s0QnVAqLiISZiW6uGV6+cxntd7UHrIGIwAh4TvbEmqVrULt2bb0fE69DX+N1yGvkyPR2rHdgWKDKYh2z+3NK8AkMxeezjyCLjTnmfVkGOTKzdm96KF9B+sHjgnhMUHr5vbii4zJIaaoFWGr9SivJ77//jq+//hrTp09Hjhw5sGXLliQHv0SUcEuwdMON2RIsSeY0jMzNYVe/PnLNn4/8+/fBedAg1Y1YCQuD365deNSrN27X+RQvZ8xE6IPoFj19kXHMd1u01Aa/FoUKIc+Gv+DQonmig18P/xA0mX0Em84/Tvb27NmzB7Ur1cbTjU8RFREF61PWOHv07EcFv7p28NFBtNjcAsMODkN45NtSCNZm1ikS/Mr114jIt9dgHazNsbJHRazrXZnBLxEREaWINBUAt2vXDrt371Ytv3KlQrKVyXTTpk31vWlE6SoIXrNmzXuDYO262bLBqXcv5NuxA+7L/4R98+aqdVVI4izP+fNxp0FDPOjUGT6bNyMyMDqjb2qIDA7Gs/Hj8eTbbxH5+rWal7lDB+RetxYWeWOPxf1QkNbrzzO4/twPg9ddxLrTjz5ueyIj8fPPP6t96eHhAa89XqhwtQKOzT+mLuQZgrMvz+Jl0Etc9ryMXfd3pehr+YeEo+/Kc5i8/Vqs+e6ONrA0M4yeA0RERJT+pKkAmIgMLwgW0pJqXb48XCf/HJ0468fxsCpZUrs88PRpPBv5XXTirLE/IOjixRQdSxpy5w7ut20Hn9Vr1LSxnR3cZv8Gl7Hfw9jCIknPJe9tRMPCsDE3gWzy8A3/Yfnx+0l6DknQJ/ty1KhRKhCWnAWSu2Dx1MUwNzd/u16IL/rv7Y/7vkl7fl3pW7IvPnH6BOOrjMdneT5Lsde5/dIPzeYcwfbLz7Hw8D3svPI8xV6LiIiIKCYGwESkkyBYw8TWFpnbtEHutWuQ999/kKV7d5g4OqplkQEB8Fm3TgWnd5s0geeSpQj39NTZJyBBtc+GjbjX+guE3Lih5lmVLo28mzbCrl69j37einkdsbxHRWSyjK6N9/2WK1h0+G6iHnvp0iWUK1dODdUQ+fLlw4kTJ9CpU6dY60mXY+l6fPDxQXTY2iHFg2AZ0zv19FSERYRp51maWmJFoxVoWaBloruHJ9XW/56h2ZyjuPMqQE3XLOiMCrmzpMhrEREREcXFAJiIkhwEJ7bkmEX+/Mg2fBgKHNiPHHNmw1bGub5JjBV6+w5e/vILbtWshccDBqjEWlHhb8edvo/fnj3qFlOEvz+eDhuOZ6NHI0pKoxkZwbFPb9U128zNLdmfcplcmbGqRyU4WEcnh5i49Rrm7r/93sesWrUKlSpVwu3b0es1adIEZ86cwScxykppGBsZo4RzCXW/kmulFE04JSWNWmxpgWVXl2HhpYWxlqVU4BseEYlJW6+i36pzCAiNUPO+/bQAFnctj8w2b1vBiYiIiFJSdHMGEdEHgmAZg79x40YVBNevXx+7du2Cvb19ovabkWSHrltX3cJevITv31vgu2EjQu/fB8LD4bd7j7qZOjurccT2LVvAIk+eeJ8r+OpVPO4/QN3Ps2kjLIsUQdCly3gyZAjCHj5U802cneA2ZQpsKlfW6edaIoc9VveshI6LTsIzIBS/7ryBkLAIDKpXMFbgGBoaiqFDh2L27NnR79/ICBMmTMB3332nEvnFRwLgAaUHoKRzSZTLVk5Np5Q89nmQzTobfEJ8cP/1fdVynlKBr3jpF4wBq87j5L3oMll2lqaY2a4U6hTOlmKvSURERBQftgAT0Ue1BEsQnNiW4FjPlS0rnHr2RN7t2+C+cgXsW7aEkXV0uZvwV6/guXAh7n7WCPc7doTPxk2q23RMr+bNe3t/7jxVf/h+hw7a4NemWjXk3bRJ58GvRpHsdljbuxKyZooeS7z46H089Q3WLn/69KnK6KwJfrNkyYIdO3Zg9OjRCQa/MdXIUUNlXdaQ4HTBfwvwIuDFR2+zPEdY5NuuzmbGZphQdQKm1ZyGKTWmpGjwK8mums4+qg1+Zf/9O6A6g18iIiLSCwbARJTqQbA2cVbZsnD9aRIKHDqE7JMmqvG6GkFnzuLZqFHRibO+/x6B588j6MoV+O/Zq13Hf88evPh5siq/BFNTZB02FDkXzIepk1OKfqr5s2bC2t6Vkc/ZBku6lYebQ3Tm64MHD6JMmTI4duyYmpaxv+fOnVP76WP9efVPzD4/G+23tsd1r+tJfvxT/6fovbs3fjv3W6z5RRyLoH7uj9+uxLK1MEWb8jnV/VZlcmDj11WQy5H1fYmIiEg/GAATUZKD4BYtWugkCNYwsbWBQ6tWyL16FfJu2wrHHl/B5E0QK6WTfNb/hQftO6hySvFul5sbcq9cAcevvoJRIlpZdSGPkw12DaqJ8rmzqBbWadOm4dNPP8WLF9EttT179sThw4fh7u7+0a8hz/vIL7rskomxCZytnLHz/s5YrblxyTJZR+OHYz/g+LPjKpD+79V/0AcZ67uwczlM/eITWJmzxBERERHpDwNgIkpyELx27VqdB8EaUqM369ChKLB/H3LMmwvbTz/VJs6KSqCOcPZfJscqu5RaTIyN4OfnhzZt2qgxv6YuheD82QAsWLgICxYsgKWlZbKeX1rJR1ccjTEVx+C32r/hzIszGHpwKEYeGhlvECzzZJmsowmCR1YYCXNjc7TI3wK57XMjpd195Y9O/zuJV34hsfZTvaLZUrSrNREREVFiMAAmIoMLgrWJs+rUQc65c1QWafP8+RNc13vZMujDtWvXUKFCBfz1118wz5YPLm3Hw/qTBrhoXRphEZE6eQ0JGtsWbqu6LNfJVQf13etj14Nd6LmrJzyDPGMFvyMOjVDLZB1ZV+RzyId/W/yLcVXGwc7cDilp15XnqsTR4Vse6L/qnMr8TERERGRIGAATkcEGwRqSHCv0TSmh+EgG6eBr15CaJOiV4Pf69ehxudXLFkdB1+h6x//+9wz9Vp5DSHh0uR9dkeRVk2tMRqXslXD2xVk02thIlTSSGsKDDg7C7ge71XqtCrRS62pkt82OlBQRGYUpO66j1/Kz8AuJLmVVxj1zir4mERER0cdgAExEBh8Ex8z8nBCPRKyjC+Hh4aq78xdffAF/f381b+zYsdj59was+7oqPskRXRpq19UX6LP8LILDdB8E58oUXSM4MDwQk89MxsSLE3Hs2TGYGEV3FZf6vqnF0z8EXRafwrwDd9R0JgtTzO9UFiMaFoapCf+LISIiIsPCsxMiMuggWOr+xsz8rM9WYElwVbduXZXwSjg4OOCff/7B+PHjYWJiAgdrc6zoURFl37R+7r/xCj2WnUFgaHSrqK6MrjQavUv2RsHMBXHh1QUcfXkUtXPUxpCyQ9ClaBfMrD0TqeHCIx80mX0ER257qOmC2WyxpX9VNCjmkiqvT0RERJRUDICJKEWC4AYNGugkCPZatSrR63onYd2kktJGUuJISh2JkiVL4syZM/j8889jrWdnaYY/u1dApbxZ1LQEh12XnFb1cHXF2MgYvT/pjZyZossLabQr0g5Dyw+FlWl0WaaUtO3SM7T547i2BnLTkq7Y3K8q8jrbpvhrExEREX0sBsBElCJB8MmTJ3USBGdu3Rrm+fMl6ubQurXOP00pRTRnzhzUrFkTT58+VfM6d+6sAuJ8+fLF+xgbC1Ms6VoB1QtEl3I6dc8LE/65qrNt0mR73vtwr2r5rZq1KvY/3p9gduiUUMzVDhZmxjA1NsIPTYpiVrtSsDY3TZXXJiIiIvpYPFshIp3XCW7Xrh02bdqkDYJ37twJe/vosbFJZVWqFPL9+69ePqWAgAD07t0bK1eu1L6/3377Tc37UEkfqXcrtW8lGdZDr0AMb1hIp8GvJtvzhMoT4OXphek3pqt5OASVKCtmEqyU4O5og9ntS6tgX2ohExEREaUFDICJSKfMzc11HgTrw61bt9CyZUtcvnxZTefIkUNlfq5YsWKin8PSzAS/dywLv+AwONpa6Dz4lUAXEYCpsSkmVpmogvKUCoL3X3+JF6+D0a5CdAIuUatQVp09PxEREVFqYBdoIkqxIFjX3aFTy5YtW1CuXDlt8FunTh2cO3cuScGvhrmp8TvB77rTj/DydfTY2aTY93BfrOA3ZoCrKZGkqRMs6+pCZGQUZuy+iW5LT2PM5ss4+8BLJ89LREREpA8MgIkoRaTFIDgiIgKjR49G8+bN8fr1azVv5MiRqvXa2dlZJ6+x9Og9DN/wH9rMP46nPkFJemyD3A0wtebUBFt3NUGwrCPrJpdPYCi6LzuNWXtvaYN5T//QZD8vERERkb4wACaiFJOWgmAPDw80bNgQP/30k5q2s7NTXbh//vlnmJqa6iyh1p1XAer+fc9AFQQ/8gpM0nNIYPu+rs2yTBfB7+Unvvh89hEcuPFKTed1tsGWflVRnyWOiIiIKA1jAExEyOhBsJRtkhJHe/bsUdPFihXD6dOnVUuwLskY3R+bFUO3qrnV9GPvIBUE3/OIDooNxbozj9Dq92Nq+8RnxV1U8FsgWyZ9bxoRERFRsjAAJiK9BMHS2qrvIFhaZBcsWIDq1avj0aNHal779u3V9hUsWDBFXlOC4LGfF0WfmtEllJ75Bqsg+NYLP+hbeEQkvtt4CcP/+g8h4ZEwNgJGNSqMeV+WQSbLlM0qTURERJQaGAATUaoGwZpW1RMnTug1CA4KCsJXX32lShqFhoaqbs6zZs1SJY9sbGxS9LUlCB7RsBAG1i2gpl/5haDtghO4+jR63LG+mBgbISQsQt13sjXHih4V0atGvg+WfCIiIiJKKxgAE1GqBsFr167VexB87949VK1aFUuWLFHT2bNnx4EDB/DNN9+kWrAnrzOwbkFtfWCvgFC0X3gCDzz11x1atmlSixJoUy4H/hlQDVXyOeltW4iIiIhSAgNgIspQQfD27dtRtmxZnD9/Xk3XqFFDlTiSgFgf+tbKj+8/L6ru1ymcFTkyW6faa0uJo5UnHyAoNLrVV1iZm2BK65LIbm+VattBRERElFoYABNRhgiCIyMjMX78eDRu3Bje3t5q3uDBg1XiKxcXF+jTV9XyYFn3Cvi19SeqG3Jq8A0KQ6/lZzB602WM2nRJjYcmIiIiSu8YABNRug+Cvby80KRJE4wbN04FejLGV1572rRpMDMzjORONQs6w9Tk7U9yaHgkLj7ySZHXuv78NZrNOYI9116q6XMPveEdGJYir0VERERkSBgAE1G6DoKlq3O5cuWwbds2NV2oUCFV9qhNmzYwVGERkRiw+hy++OM49l57odPn3nz+CZrPParqEIu6RbLi7/7VkMXGXKevQ0RERGSIGAATkUEGwa9fJz8j8tKlS1GlShWV9Eq0atVKBb9Fi0aPuTVU/z32xd5rLxEaEYk+K85ix+VnyX5OaVH+YctlDFx7AcFhkZBcX8MaFMKCTuVgb2UYreBEREREKY0BMBEZZBDcoEGDjw6CQ0JC0KdPH3Tr1g3BwcEwNjbGr7/+ivXr18POzg6Grqx7ZvzRsSzMTYwRFhGFfqvOY8uFJx/9fM99g9FuwXEsO/5ATWe2NsOybhXQr3Z+GKfSmGMiIiIiQ8AAmIgMKghu1qxZsoLghw8fonr16pg/f76azpo1q0p0NXTo0DRVz7Zu0WxY1KUcLEyNEREZpVpu15959FHP9dQ3CJeeRHcr/ySHvSpxVKOgs463mIiIiMjwMQAmIoMKgtetW/fRQbAEulLi6PTp02q6cuXKqsRR7dq1kRZJkLq0WwVYm5tAkjQP++s/rDr5MMnPUyZXZlVqqX2FXFjXu3KqlloiIiIiMiSm+t4AIqL4gmBJUrVlyxZtELxz507VfTksLAxHjx5VmZ2zZMmi6veampril19+wejRo1W5I9G/f3+V5VmeLy2rnM8Rf3avgK5LTsM/JFyVLJqx+yYcrKPH7UpW64iICJiYmGhbuCOjolRSq/V9qmifp1Ml9zTVAk5ERESUEhgAE1GaCILr1aunbosWLcKLF28zI0sXZwmEr1+/rqatrKywYMECdOzYEelFudxZsLJHRbSYdxSRUcAr/xB1e597HgG47xGA3E42aprBLxERERG7QBNRGukOLdmbJ02ahJcvo2vXasi0JvjNmzevCpbTU/CrUTKnQ5K6LkugvOz4/RTdJiIiIqK0hmOAichgaYLgwoULa+dJl9+EtG/fHp988gnSK0mIlVjSBXpMY8Mu90RERESU2hgAE5FBk667Mt43Mev973//U2OECXC0MYcJSxwRERERxcIAmIgMmiS8itvtOT7SMvz8+XO1PhERERFRfBgAE5FBS0zrb3LWJyIiIqKMgwEwERk0yfCckusTERERUcbBAJiIDJrU+c2WLdsHy/jIchcXF7U+EREREVF8GAATkUEzMzNDv3793pv9WchyWU/WJyIiIiKKDwNgIjJ4I0eOROPGjdX9uC3BmmlZPmLECL1sHxERERGlDab63gAiog+RVt1Nmzbhl19+wdy5c1W2Zw3pHi0tvxL8pvfWX3dH63hbviMiImBiYhLr4kB86xIRERFldAyAiShNkOB2zJgxKtCVUkeS7VkSXsmY3/Qe+Gos6lL+nXlS99jT0xOOjo4ZZj8QERERfSwGwESUpkiQV6tWLX1vBhERERGlQRwDTERERERERBkCA2AiIiIiIiLKEBgAExERERERUYbAAJiIiIiIiIgyBAbARERERERElCEwACYiIiIiIqIMgQEwERERERERZQgZug5wSEiI+nv79m0YorCwMPj6+sLe3l7VPiXiMUH8nSAeA8RzCOJ5JWWkmOP2m1hNE7slV4YOgB89eqT+Nm/eXN+bQkRERERERO+J3cqUKYPkMoqKiopCBuXj44ODBw8iZ86csLCwgCFe7ZDgfPPmzcifP7++N4cMAI8J4jFBPAaI/18QzyEoI51fhoSEqOC3Zs2acHBwSPbzZegWYNmBzZo1g6GTA7FYsWL63gwyIDwmiMcE8Rgg/n9BPIegjHJ+WUYHLb8aTIJFREREREREGQIDYCIiIiIiIsoQGAATERERERFRhsAA2IA5Ozvjhx9+UH+JeEwQfyeIxwDxHIJ4XkmMOZInQ2eBJiIiIiIiooyDLcBERERERESUITAAJiIiIiIiogyBATARERERERFlCAyAiYiIiIiIKENgAExEREREREQZAgNgIiIiIiIiyhAYABMREREREVGGwACYiIiIiIiIMgQGwERERERERJQhMAAmIiIiIiKiDIEBMBEREREREWUIDICJiIiIiIgoQ2AATERERERERBkCA2AiIiIiIiLKEBgAExERERERUYbAAJiIiIiIiIgyBAbARERERERElCEwACaiJLt//z6MjIzQtWtX7j2iNGDcuHHqO3vgwAGdPWdoaCgKFCiARo0aIaVMnz4dZmZmuH79us6eM3fu3OpGpGu1atVS3zMiMmwMgIkoXVu8eDGaN2+O/Pnzw87ODjY2NihSpAh69uyJGzdu6Ox15IRaTnw0N2NjY9jb26NSpUqYOXMmwsLC4n1cREQEFi5ciJo1ayJLlizqZD9r1qz45JNP0KNHD/z999/vfd2VK1dqX3PXrl0JrieBT8zti+8mFzY0goODMXXqVFSsWFG9D3Nzc2TPnh1ly5ZF//79cfDgwQ/uk5YtW6rnlSAmIadPn1bvOU+ePHj9+vUHnzM8PFxtkzzvpk2bElxPlsk6sq48Jr1bunSper/yN7X89ttvuH37NiZOnBhrvnyOffv2RY4cOeDo6IgmTZrgzp078T7HokWL1Od//vz5eJd//fXXcHZ2xtChQ5EepMfgOyUurhgquegb97eSiNIeU31vABFRSlqxYgWePXumAiEXFxcVmF65cgVLlizBn3/+ic2bN+Ozzz7T2et9++23cHBwUIHtw4cPsXHjRgwaNAh79+7FP//8E2tdWefzzz/Hjh071GMaN26sggZpWZNtXLVqlWr5atq0aYKvt2DBAnVCFhUVpe7Xr1//vdvn7u6eYMu9bIPw9/dXAfm5c+fUPmvVqpX6K/MvXryoXsfHx0et8z4S2J84cQKjRo1CvXr1UKJEiVjLAwMD0bFjR0RGRmL58uXqAsWHmJqaqs+0dOnS6iKGXGCQwDym58+fo1evXupih1wgkMeQbgUEBGDSpEnqcy1TpkysZXJ8yYUb+Wytra1VUP7pp5/i6tWralrjyZMnKrAdMWKE+jzjY2VlhYEDB6p1jh07hipVqvCjJCKi5IkiIkqie/fuRcnPR5cuXQx+3wUFBcU7f9euXeo9FClSRCev4+7urp5P9k1Mt27dirKxsVHLDhw4EGvZ8uXL1fySJUtG+fj4vPOcAQEBUfv27UvwNa9fv64eX7du3aiyZctGmZmZRT1//jzedffv36/WrVmz5gffy4QJE9S69evXjwoJCXlnuZeXV9TRo0ejEmPHjh1RRkZGUSVKlIgKDg6OtaxPnz7qdUaNGhWVVPPnz1ePbdCgQVRkZGSsZZ999platmDBgqiMYsmSJeo9y9/4/PDDD2q5HAe6IPtWnm/lypWx5svxJ/PHjx+vnbd06VI1b+3atbHW/fzzz6OKFi0a7zEW05MnT6KMjY2jvvzyS519V+WmD/p87ZSi62PLkMn/efH9zmvI7ytPrYkMH7tAE1GySFewdu3awcnJCZaWlihXrhz+/fdfg9mrsk3xkZYrafGULpwpSbpea1pKpbtvTNKipWkxk27GcUlrWe3atd/bwiq6deumnkO6WeuiC6xmu6T7qXR9jitz5syJbolr0KCB6jJ96dIlfPfdd9r527Ztwx9//KG6VEsXSuHr66vWKVSokPrc5HXk8Xv27HnneaWFV1rGd+7cidmzZ2vnz5s3D9u3b0ezZs1UC3Fi3bx5U7V0y2tKy7G8v61btybYtVjTlVW6+w4ePFjdl668mvcipNW/YcOGqmu7hYUFChYsiJEjR6r3GVP79u3Va9y6dSvW/C5duqj50noak5+fn3qtGjVqaMcdyjEg5G9C3do1/vrrL1SoUEEdX7Jt8v2V1tik+N///qeODRleENODBw/UX3l+Dc19zTIhrfhyDMgQhfiOsZhcXV3Ve5XtTkw3+cSSz0GOTTc3N3W8FS1aVHXrlt4UGtIDQ/bj+76H0rNBPg/pafKhIQiyD+QW8zOK2SNDeqRIy7kcK3Icyk2+I7Jd0lMioS65d+/eVd8DGTohreZyTHzssS0eP36s9k3evHnVsStd2eX7Fvc3TI778ePHq/uyj2K+rw/R7BP5zpw5c0Z9V+R3ULZTtvfRo0dqPXlvcoxKV3h5b/I60hMlPvIZ9OvXT22XHFfyGBmKcfbs2XfWjfn+9+/fr/ZZpkyZVE8U6Y1z7dq1WOvLusuWLVP3ZciG5n3G16Vdhl389NNPaoy87L+cOXOqXgzSu4eI9I/9wojoo8mJnJzcyklSp06d4OXlhbVr16rgQ4KW95006tuRI0dUN9643Tc1J5VyoiPdpHWZ6EtOkmOSk0rNCWpSyYmUbKOcMLZo0QJBQUEYMmSIGlM5fPjwZCViSc52xWfKlCkqGJSx0HJiWbJkSXTv3l0FYNJFWfaLfBZVq1ZV3WTLly+vur16eHhg3bp1qlv377//jt69e8d6XnmvEnzIiWXdunVVV+dhw4YhW7Zs2osDiSFBjgQF3t7eavskiJCTbtmv70vwJJ9BnTp11HEv2ygnznJiLObPn68uIEjA8cUXX6hx3XLC/8svv6iu8EePHtV2OZcAd82aNWofyQmzhkxrLkjImGzNxRwZfy0n2JrAWI5Rea4tW7ao716pUqW0z6F5jZgXCKR7sgQzcmHm5MmT6jsrAcWFCxfUyXpiAkcJWORzitmlWeTKlUv9lYBDAhoh62q634sXL16oz1eGBsjQhMSQY0P236FDh9SwgeSSz06OGTnuJLiS6Q0bNqghDJIbYO7cuWq9woULq98xCZDk+yCBaUzy2Vy+fFkFbHG74sckQdIPP/ygvgNC3r9GzM9LLpDIMA3ZLxKYy77et2+f2i4JPmWoQHxk+eHDh9XxK8esiYnJRx/bMvRBjmc5ruUClASQ8l2U4LxatWpqfL3msfI+ZL4ck3LB5mPGN8v7ku+FHI9y0UoulsnQEdmvckzLa8rn0LlzZ/V/jiyTC5jyPmxtbbXPc+/ePbXu06dP1fdSLixJEL1+/XoV8MvnG9+xIxds5XVkKEyfPn3Ub5BcnJHtkvtycVfI5yfvVb4rmqEu8X3HRIcOHdTnIc8pvwvyfPI7+PLlS/X/ChHpmb6boIko7XaBltu4cePe6fIq86UbamJJt03pRpfYW0LdPN9n/fr16rHDhw+Pat68eZS5uXlUlixZoo4dO5ZgN7ekvE5CXaClm7K1tbVadubMmVjLzp07p7otSxfhjh07Rm3YsCHq/v37iXq91atXq+fs1auXdl6rVq3UvD179iTYBVq2M759GrP74j///KPWlX309ddfR/37779RT58+jUqO8+fPq+dzc3PTdlGeN2+edrm8D837idml+ebNm1F2dnbqsfF1O9y6dat6XKlSpaLKly+v7m/bti1J21anTp13tkfI82iO87jHgubz/vTTT6P8/f1jLZPPULY3U6ZMUdeuXYu1TPanPK5nz57aeXfu3FHzWrdu/U739nr16r3zmQ4cOFDNO3ToUJK7QMs2/ffff7GWtW/fPt4uygnZvn27Wr9///7xLm/WrJk6rrt166berxz/uXLl0u4nOU4LFCgQFRgYGJVYmzdvVq85bNiwqOTSfHZVq1aN1S3f09MzKm/evGrZwYMHY/12yLwhQ4Yk+FshQyp00QX69u3b78yLiIiI6ty5s3qdEydOxPv6rq6uUXfv3k32sR0WFhaVL1++KAsLi3eGbEhXdHkdFxeXWPvtY7tAa36T5LZixYpYy7p3767mZ86cOWrixImxlv34449q2cyZM2PNlyEbMj/u+jJcw8TERP3e+/n5vfOdkWVxfzNHjhyplv3yyy8f1QW6TJky6njSkGNf9qt05X/27Fmi9xERpQwGwET00QGwnMiFh4e/s1xOdh0dHRP9fJqThsTeEjOONa62bdvGeg45AT99+nS860qwJ4FLfONyP3RS/e2336oTwjFjxqiTVs3436FDh8b7OAk65IQy5rbJiZoE6X///XeCr6c5sY0ZwGsC1zZt2rz3ZDO+m2xzTLNmzYqyt7ePtY5sZ4cOHWIFB0khJ5Oa52rcuLF2vowBlSDJ1tY21kmjhuzLuONK4wsq5da3b98kbdPDhw/V4/Lnz68CjbhkfPX7AuALFy688xg5AZdl3333XbzjpyUItbS0jBVE5M6dW31nNMH/3Llz1XMcP35cnaDHfC4ZTy3HVWhoaJID4NGjR7+zTMaZJxTgvW/89aRJk+JdLt8buZCRPXt2FcA0atRIXcjQBJNywUeCd3n/EkTLOhIwy/f6ypUr8T6nBH7ymvI9Ti7NZxfzAkLc/di1a9dYQaG8F/l8Yn5m3t7eUVZWViqwiTsOXddjgM+ePRvvd0ATkMUNBj/22NZcaEjo90peR5bLhSddBcDVqlV7Z5n8xsgy+V7E/T9GLjDF/YwePXqk5sn/PTG/FxpygVGWL1u27J3POr6x5XIxQZbJxZqPCYB37979zrKxY8eqZfI7TUT6xTHARPTRpOuepqtdTDLeSbrcJZZ0bXxzQS5Rt48ptyFdTOWx0qVQup9KV1XpVhnf+Dfpyihd7uIbl/shs2bNUmPipDSMZJmWbLkyxu3XX3+Nd/02bdqobNEylvX7779XXfRkrJ90tZNuqtKtMOaYRCHjlqVLpoyVrVy5sna+dDmVbM3yWOmyGB/pZhjfPo05dlV88803qiuhPJd0qZYuhzL2VDJTy3OMHTs2yftGMv7K9omY+0O6nEpGaOkaLWNS45LujCKhUjnTpk3T3pfSTUkh3X6F7EfpehqXdKlMiHRJli6l8XUhjbndMcn4Rsl4LF2aY9a2lXU9PT212yPdXuU4lCzXMgZU0x361atXqmuobFfcLvWJIWP04/u+isR+Z2U7Ne8lPvK9kS7gcvxIN1rpfipdu+W+jCuVEknVq1dXXdclo7gce9ItW55XjmHZN3FpjouEjuukku7y8Y1j14ydjXmsybrSNVe2T7rRakh3ZBl6IOPRdVX7VV5DukHLcSXdezXjTOUYEAmN1Y455jo5x/bx48fVX+lqLJ9L3NupU6fU8rjjY5MjvmNSxn0n9H+MdA3XjFPW0HxeclzF971432+ILr4TqfGcRKQ7HANMRB8tvrFP6ofF1DTehC2GQMZjyYmvjMOUkxQZpyljAaX8kC7IODQZBycn8XICKmPKJCDWjJOOj5ywyZg7TQkjKY8kJ9oyTlaCaBmvFzPZkIxvlaA17vhk2e9ffvmlCgglsE9u7VQZ3yljSuUmZJykvLaMf5swYYIaGxhz/OKHyEm4ZoypJLPR0CSFSmgMpWa+jNeMT8znink/MTSvLeOG45PQfCHjeuMLfD7m/ch4XkkIJYGuXAiQCxyacZayTMYPasaDymcfNzFWcr6zmjJRctwlhmYfxxeovo9cVJHHTp48WV0YknHd8p2Q+ULGS0uyK7nIIsd+TBJoxnzt5JJxnfFdvNNcoImbqEyCXCn7JIG9jO8UErxLoiVNArLkkuNBxlXLb4gEtDLmVQJ/+XxkmVxcCwkJifexmu1O7rGtubgh42bfR0qi6Up8Fxo1x+T7lsWsrZ6c3xBdfCdS4zmJSHcYABOR3kmwFl+22oRIgJnc5FRy4ipBhCRckVq1rVu3hi5J66C03klGYmlNlkBbXk/TsvE+cmIuLcOybdKSLEGPJgCOmelZMibHzKwckwSqyQ2A49tnkmFV9pdk8ZXtSkoAnBDNSa7U742PJrvux7TIf4im9rAkZopPQvNFQq1+Md9PsWLFEvV+NC1UkjxOk1hLE+TK9M8//6yCYk1LcHyty6lFAv+YwVJiSCuwJDzbvXu3atn877//1AWVmEnoNK2cUgM7Ls1raV47uaQlWQKRuEGw5hiMe6xJq6P0yJAEUNJyL5+PtMS3bdtWZRrWBUnqJsGvJFuK2yNDWmYlAE7Ksfgxx7bmfUtSqPfVHzc0+vwNIaK0hwEwEemdBHSSRTSxpAuuLrIza7oTaq7MpwRpeRg1apTq1igntknJTiwlOUTMLtByYiqZRKX7c0LdczUZa2Wfakow6VJ825Uc8l6ktVmyq0oLTdzWE3k/Ir6M3cmlCeAlwJBeC3G7ikq28KSSLs6SqVa66sdtqZX3Jz0D5AJJkSJFYrXgSRkeyRy7Y8cONU/zWOmqLy3nEvzKRQdNN+qYNIFcarQuabp9x+zC/T7SOicZvL/66ivV2yKmmC2a72tR1ryWLi64CMmiLRmcpctsTJrhFXH3r5Cu2xIASyuwphtr3MzkHyKfU0KlcDQl2SSjdFxJ+X1MzrEtF+2EHIeJDYBT89hLiObzkvckn23c33Rd/YYYwnslouTjGGAi0ruUGgMsrUZSKiM+UvpCTmalNSpukCitBXLCHbcb5McaMGCA6m4ogX7MWq+rV69WLWLxdReXlgxNsKyp96rpdil+/PFH1WIU300C7pjrJpXU58ozjfoAANxGSURBVJVW3vjIftF0j4y5XcltWZau2zLGWMZBx3Tnzh1VA1W6iSfUhTw5pGyPjPuU4EMCm5gkEI2vBvGHSB1X2V6pyxq3zrS8P6llK+vELTkkrboyFlpa+mTMrGbMoHT7lXGcUhJK9odsb9xgRlO6SsaTpzRp1ZZWz4SOkbikPFfcsdr58uVTn3vMmuEyLEHz/HFpXituaTXpOZJQLdYPkd4TMQNwadWVHhcivm7NckFCyiBJ+TH5LOTCTVJLvcnnJOO4NV26Y9K8h7i/bzJuVXoApMaxLcMd5LORMlBSuic+ElDLcRrzPaXWsZcQGcIieQrkeNCUmtKQUl/SrV4uHMlwkuQwhPdKRMnHFmAiSrekBqR0q5SxvnKyKt0YNS1wckItQYoEjHGT+ciJsS7rAEvrprQAS91TSR4lga/mxEyCHWn9k9ZcTQ1Z6QYpXUblJFlOSDXds2W+nLTK+MWYY4Ljkm6ZUp9TxhFLEBZfYqn3kZNj6bItJ+TS+iiBmAQKErxLsi7phi3jNmW8oq7IuFBpdZozZ46qvymBhaYOsATGMl+zf3RNTvblfUoLn5z0a2qlyv6T/S+t7vElEUqI7Dc5CZfu4tLiJN3ZJWCUVjwJHqRLvNQ9jS/AkvcpLfwyvjruMk1gFN/4XwmQ5TiT15ULP5oxoXLxRdfdPiXglEBCLrBId+X4AlYNOV7/97//qeA25nbIeF/ZPzNmzFCJr/Lnz6++b3KsacbYasgFInke+Q4XL178nWUf04tDembIMS3PJy2dckz/9ddf6uKXHAfxXdyR9y1j+gcPHqwdF5xU8tnJ8S3vWV5DLoLImO8mTZqoMb+SHE6+u9JiKRdB5DsnFwnkeJB6zSl9bMtvovRekPq/UjdY8iVIS7IcW/J7Ktsuj5f9pKkBLd9VeQ753ZRu4Zrf0zFjxiA1yYU7ea9SC3zXrl3qd19TB1i2T44vTe+VjyWfn3xGkhRNWurl+aTHiiR3I6I0RM9ZqIkoDZdBkpIQ7ysFoW9SckbKvkiZDSnhI6VWpNxO4cKFo3r37h119erVeB+nyzrAGkFBQaqGppSAuXjxorZMyZw5c1TJo4IFC6ryOLKNsq1SK3f58uWxypeMGjVKvcagQYM+uD1SZ1bWnT59eqySI4kpIXXjxo2oqVOnRjVs2FCVeJF9JnVtc+bMGdWiRYtklfF4336SsjJSp1nKtsjrSRkmKdWyc+fODz6vpgzSx5KyV/Le5DXl/VaqVEnVP/7111/V827atCnJ5Wxku6WOr4ODg3o/si+ljq28z/jIfKkTKq+3bt26WMuk3JXmPSZ03Ep9XtluTemtmPv5faVqPvR9jo+Uf5LHyOeVEKm5KmVs4iszI6SkkJQNc3JyUnVna9euHW8ZJNmP8lozZsx4Z5mmbE985Z0SovnspFyTlM2S76V8PvK7IOW/3lfSSH5T5DOSMlYeHh5RSSX1YPv06aPqYUt5q7j7Xd5/kyZNopydndVxKPVkFy5cmOBn9KGyPB9zbIsXL15EjRgxIqpYsWKq1JMcU/K9lLJA8rskpaFiknklS5ZU+yWx30XNb1LcEmyJOSYT+i17/Pix2r9SDkl+S6V0ldSlPnXq1Dvrfqh0WEKvMW3aNHWsyDGjKQeYmP/7PvR6RJR6jOQffQfhREREhki6Zkv3Sen6LS2Q9Ja0EkoyK2kR1FV25vhIS5u0nkv377it2dIaK917pWyP9IxIadIKLy2e0oVdyiClZTy2iSij4hhgIiLK0KQbbXzZYyXplHQ7leRUDH7fJTWXZTzrvHnzUuyzkfGvMlZfsiLH15VbAmPpjpoawa+QclQirXR55bFNRPQujgEmIqIMTbLyythTadmT8bkynlTGtkqCMknUJOMo6V0lSpRQtYtljHZKkQsTUnNaxt7G5+zZsyn+0Ug5MhmHK68lZc0+//xzVKxYEWkBj20ionexCzQREWVoUtJEEg9JiaHHjx+rDLfSoihJiiR5WXwlcSjjkOztkhVa6upKt29p8U6tFufk4rFNRPQuBsBERERERESUIXAMMBEREREREWUIDICJiIiIiIgoQ2AATERERERERBkCA2AiIiIiIiLKEDJ0GSQfHx9VQ1DKX1hYWOh7c4iIiIiIiCiGkJAQPHr0CDVr1oSDgwOSK0MHwBL8Nm/eXN+bQURERERERO+xefNmNGvWDMmVoQNgafnV7Mz8+fPD0ISFhcHX1xf29vYwMzPT9+aQAeAxQTwmiMcA8f8L4jkEZaTzy9u3b6tGS03sllwZOgDWdHuW4LdYsWIwxIPR09MTjo6OBnkwUurjMUE8JojHAPH/C+I5BGXE80sLHQ1ZZRIsIiIiIiIiyhAYABMREREREVGGwACYiIiIiIiIMgQGwERERERERJQhMAAmIiIiIiKiDIEBMBEREREREWUIDICJiIiIiIgoQ8jQdYCJiIiIiCh967HsNB54BiZqXXdHayzqUj7Ft4n0hwEwERERERGlWxL83nrpr+/NIAPBLtBERERERESUITAAJiIiIiIiogyBATARERERERFlCAyAiYiIiIiIAERxL6R7TIJFREREREQE4M5LfzSYcQj5stogv7Mt8mW1RT5nW+R1toG1OUOn9ICfIhERERER0ZsW4Bsv/NQtLjcHK5R1z4zf2pfWzouKioKRkRH3XRrCAJiIiIiIiAiAg7UZSud0wO1X/njsHYSoGH2in/gEwdXBMtZ+uvrsNTouOqlaifO/aS2Wv3KTgNnYmMGxoWEATEREREREBMDZ1gJLulVQ+yIoNAL3PAJUMCxdo+VvoWyZYu2n2y/94R0YhjMPvNUtJgtTY+R1tkXBbLaY2bYUW4oNBANgIiIiIiKiOKzMTVDU1U7dEiKtvG3L5VTBsQTDvkFh2mUh4ZG49uw1AkLCYwW/r/xC0Or3Y29ajG20LcbSeuxgbc7PIYUxACYiIiKidCksLAxHjx6Fl5cXsmTJgqpVq8LMzEzfm0WpzN3RGv4h4XjmG6ymHW3MkcXGPMF1k6Jc7izqphkP7BkQqgLhO28C4juvApDdLna3aVn20CtQ3fZdj/18TrbmqtVYAuIxjYvoPPFWj2Wn8cAzMNY82e6IiAiYmJjECtRlXyzqUh7pDQNgIiIiIkp3ge/kyZMxd+5cvHjxQjvfxcUFffv2xciRIxkIZyALO5fD57OPqADY3soMB4bVQiZL3V8IkeDRydZC3SrldUxwPSszE3xW3EUFwtLFOizi7UBjD/9QePh74dJjX0xsVlw7PzwiEq3/OI7cjtaxxhq7O9rA3DTxlW0feAbi1kt/ZGQMgImIiIgoXQW/zZs3x7Zt294ZcynB8NixY3Hy5Els2rSJQXAGEREZhRal3fDidQg6V3ZPkeA3KUrmdMDvHctqA1tpCZaW4pgtxxIkx0ygJetceOSjbjGZGBvBPYu1ttW4V428CbZuJ6Ty08vq73HXtwF3esYAmIiIiIjSDWn5leBX07UzJs301q1b8csvv2DMmDF62UZKXaYmxuhRPS86VnJHZJxjwhC2TYJXudUrmi3B9UIjIlE1v6MKjiWQjxnc3/UIULc9117g61r5Yj2u36pzqsu3psU4PDL2+8/n8wRjTy2NXrfWINx1cEN6xwCYiIiIiNJN6690e5aW37jBb0yyXNYbMWIEW4EzEEszE6RVhV3ssLJHJXXfLzjsnRZj+StZq6WLt4ast/W/Z+993g43dse6P7FiV6R3DICJiIiIKF2QhFcxx/wmRILj58+fq/Vr1aqVKttGqU8+ZxlT65zJIl3tfunCXSqng7rFJK3BMfkEhqGEm70KjgNDI955nnw+T1DlWXT3Z1H12WXk9XmS7luBEz9imoiIiIjIgEm255Rcn9KW43c8UXXyPozedAke/m+7DadXMh44ppxZrPHPgGq4Mr4Bjo2sgz+7V1B1juNr/X3fvPSGATARERERpQtS6igl16e0ZdbeW2rs7MZzTxA7NMxYpMu/q4MVahR0hoO1Wbytv3FbgdMzBsBERERElC5InV9Hx4TLz8QMCKQkkqxP6dPJu544eS+6hb9jpVxwjNHySUDHazsT3A3pvRWYATARERERpQvXrl1DcHBwosaG9uvXjwmw0rHZ+26rvxamxuhZI6++N8dwREWhzc29qPTiaoKrpPdWYAbARERERJTmnT59WiW0CggI0M6LWwdYo1q1aioDNKVPZx9448htD3W/fYVcyJrJUt+bZBCCLl7EoC1T0O3q9g+um55bgZkFmoiIiIjStCNHjqBRo0bw8/NT01OmTEFISIgqdSTZnuMyNTVVN0qfZu+7pf6amxijT83YdXEzorBnz/By+gy8/ucf5EnkY6QV+E74K6RH/OYTERERUZq1e/duNGvWDEFBQarF9/fff0fv3r3VMmnllVJHku1ZEl6tX78e8+bNw4EDB7Bt2zY0btxY35tPOnbxkQ8O3IgO3NqWzwkX+4zb+hsZGAjPRf+D5+LFiNIMDTAyUt2gE+Mbv4sAWiO9YQBMRERERGnS33//jS+++AKhoaEwNjbG0qVL0alTJ+1yMzOzWHV+ixcvjpUrV8LX1xfDhg1DgwYN2BKcTlt/zUyM0KdWxmz9jYqMVK29L6dNR/jLl9r5mRo0gF2jRng1+7c4DwDCI8JhamKKmOmyHVqnv+BXMAAmIiIiojRnzZo16NixIyIiIlSgu3r1arRq1eq9j3FycsLo0aMxfPhwlTBr0aJF6NOnT6ptM6W8blXz4HVwOPI528DNwSrD7fLAc+fx4uefEXzpknaeRdEicPnuO1iXL6+m7RrUj/WYsLAweHp6qgzq8l1K7xgAExEREVGasnjxYvTo0UNlc7awsMDGjRvVGODEGDBggBob/ODBA/zwww/o0KED7OzsUnybKXVUze+kbiHhERlql4c9eYKX06bh9ba3Ca5MnJ2QddBg2DdvBiNj5j7W4J4gIiIiojRjzpw5+Oqrr1Twa2Njg+3btyc6+BWWlpaYPHmyuv/y5Uv88ssvKbi1pC8WpiYZYudHBgTg5cyZuPNZI23wa2RuDsc+vZF/xw44tGzB4DcOBsBERERElCZIsCotuMLe3l4lwKpdu3aSn6dt27aoUKGCuj99+nQ8evRI59tKqev689fqokhGGufrs2EjbjdsCM8/5iMqNFTNt2v0GfJt34asAwfC2MZG35tpkBgAExEREZFBk8Dm+++/x8iRI7Vjeffv34/KlSt/1PNJtuhp06ap+8HBwWpcMKVdt1/64bNZh9Hq92O4/MQX6V3g6dO43/oLPBs9GhGvousdW5YoAfdVK+E2fTrM3Nz0vYkGjQEwERERERl08DtkyBBMnDhRTWfPnh0HDx5E6dKlk/W81apVQ8uWLdX95cuX49y5czrZXkp9c/bdVpV9zj/ygaVZ+u36HProER5/8y0edOqM4KtX1TzTbNngOuUX5F67BtZlyuh7E9MEBsBEREREZJAkw7PU9J0xY4aazpUrFw4dOoSiRYvqrEu1qWl0TlgJsjNSF9r04p5HAP6++FTd//wTV+TPaov0JsLfXyW4utuoMfx27VLzjCwt4dSvn+rubN+0Kcf5JgEDYCIiIiIyOOHh4ejSpQsWLlyopvPnz4/Dhw+rv7oiz9WvXz91/8CBA/j333919tyUOubuv43IN9ct+tfW3bFhCKIiIuC9fj3uNGgIz4WLEBUWpubbNWmiAl/nAf1hbG2t781McxgAExEREZFBCQkJQZs2bbBy5Uo1XaxYMdXyKy3AuiZjix0cHNT9YcOGqZqolDY89AzEpvNP1P3PirugkEsmpBcBJ07iXqvWeP79WER4eqp5ViVLqq7Obr9OgVn27PrexDSLATARERERGYygoCA0b94cmzZtUtNly5ZVY35l7G9KcHR0xJgxY9T9GzduaFucyfDNO3AbEW+af/vXSR+tv6EPHuBR//542LUrQq5fV/NMs2eH69SpcF+zWgXBlDwMgImIiIjIIPj5+amavjt27FDTVapUwd69e1WQmpL69++PPHnyqPs//PADfH3TfybhtO6xdyD+OvtY3a9bJBuKudojLYt4/RovfpmCO583gf+evWqekZUVnL/9Bvm2bYX9541V9nJKPgbARERERKR33t7eqFevnhqLKz799FPs2rVL1ftNaRYWFpg8ebK67+Hhob1Phmv+wbsIf9P6+82nabf1Nyo8HN5r1qhxvl5LlgBvuuDbN2+OfDt2wOnrr2FsZaXvzUxXGAATERERkV69fPkStWvXxsmTJ9V048aNVUIqGxubVNuGL774ApUqVVL3Jev0w4cPU+21Ken61c6PrlVyq7G/n+SIHsOd1vgfPYp7LVrg+bjxiPD2VvOsypZF7vXr4Tr5Z5hly6rvTUyXovO+ExERERHpwZMnT1C3bl1cfzPeUQLRFStWwNzcPFW3Q7qXTps2DVWrVlVJuEaNGqW2gwyTi70lxjUtliZLV4XcvYeXU6bA/01vB2Hm6oqsw4chU4MG7OqcwtgCTERERER6cf/+fdSoUUMb/ErZo1WrVqV68KshY45bt26t7ksG6jNnzuhlOyjx0tK42AhfX7z4+WfcbdpUG/xKGSPnwYORd/s22DVsmKbeT1rFAJiIiIiIUt3NmzdRvXp13L17V0337dsXixcvhqmpfjsoyvhfMzMzdX/IkCFpsoUxPTtx1xOBoeFIS6R+r9eKlbhTvwG8lv0pRa4lcod961bIt3MHnHr1hLGFhb43M8NgAExEREREqerSpUuq5ffx48fa+rtz5syBsbH+T03z5cunskILqT38999/63uT6A0P/xB0W3Ia1X7Zj38uPk0T+8X/8GHcbd4CLyZOVC3Awrp8eeTZ8BdcJ06EqbOzXrcvLCxMlRnbunWr+psR6mDr/1eGiIiIiDIM6VZcq1YtvHjxQk2PHz8ev/zyi0F1/ZS6wJkzZ1b3hw8fniGCgrRg0eF7CAqLgFdAKBxt9NNNPrFCbt/Gw5698KhnL4TeuaPmmeXMCbfZvyHXn8tgWbSoXrcvLCwMEyZMQM6cOVX29R49eqi/uXLlUvPT8zHPAJiIiIiIUsWRI0dQp04deHl5qempU6di7NixBhX8iixZsuD777/XdtWeP3++vjcpw/MOCMWfx++r/VDOPTMq50vZ2tAfK9zbG88nTMTdZs0RcPiwmmdsY4Osw4Yi79Z/YVevnt6P97CwMDRv3lx99yQDe0xyYUrmt2jRIt0GwQyAiYiIiCjF7d69G/Xr14efn5+a/v3339UYW0MlY5Lz5s2r7o8bNw6+b7qvkn4sPnoPgaER6v43nxbQexAZV1RoKLyWLVP1fL1XrgQiIgBjYzi0bYt8u3bC8auvYKyn5G7xjXPftm2buh93jLtmWrpES8+M9IgBMBERERGlqH/++Qeff/45goKC1DjfZcuWoU+fPga91y0sLLQBgKenJ3766Sd9b1KG5RsYhqVHo1t/S+V0QPUCTjAUEjD67d+Pu02b4cXPkxH5+rWab125EvJs2ojs48fB1NFwWqvDwsIwd+7cD15AkOWyXnpsBWYATEREREQpZu3atWjZsiVCQ0NVdmWZ7ty5c5rY461atVKlkcSsWbNU2SZKfUuO3YNfSHTm528NqPU3+OZNPPqqBx5/3Rehb44Nc3d35Jg3F7kWL4ZloUIwNEePHlXdnD+U3VyWP3/+XK2f3jAAJiIiIqIUsWTJEnTo0AHh4eGqRXXz5s3aOrtpgQRa06ZNU/dDQkIwatQofW9ShuMXHIbFR+6p+yXc7FGrkH6zJotwLy88GzcO95q3QMCxY2qecaZMyDpyBPL+8zcy1aljMEF6XF5vxt+n1PppQZoMgM+dO4emTZuqBAXW1tYoXrw4fvvtN31vFhERERG9IWWNunfvjsjISNjY2Kgxh40aNUpz+6dSpUpo06aNur969WqcOnVK35uUoaw78xivg6NbfwfUya/XwDIyNBSe/1us6vn6rFkLREYCJibI3KFD9Djfrl1hZCDjfBOSJUuWFF0/LdBvpfGPsGvXLjRp0gSlS5dW2flsbW1x584dbR05IiIiItIvGTs7cuRIdd/e3l4Fv5quxGmRJA2S1mvpxi2Ju6Q+sKG28KU3nSu7I5OlKfZee4F6RbPpZRukO7D/3r14MeVXhD18qJ1vU7Uqso0cAYsCBZBWVKlSRV2QCggIeO96cnxny5YNVatWRXqTpgLg169fqzEjjRs3xl9//WUQxdKJiIiI6G2gICVUJk6cqKYdHR1V40WZMmXS9C7KkycPBgwYoLpDSyknCYalTAylPDMTY7Qpl1Pd9CH4+nWV3Crw5EntPPO8eZFtxHDY1KiRpi6EyPfzu++++2Dwq1m3X79+atx+epOmIshVq1apQduTJk1Swa98eNKthoiIiIj0S06YpXVUE/y6uLjg4MGDaT741Rg9erS2O+jw4cNVazClX+EeHnj2/fe416KlNvg1trdHttGjkXfLZtjWrJmmgt+IiAj06tUL06dPV9OWlpbqb9z3oJmWBscRI0YgPUpTAfCePXtgZ2eHJ0+eoFChQqr7s0x//fXXCA4O1vfmEREREWVI0iAhZY1mzJihpnPlyoXDhw+jWLFiSC8yZ86sWrfF7du38ccff+h7k9K1gzdf4c4r/xR7fr89e9QtrsiQEHgsXKjq+fqs/0uu7ACmpsjcqRPy79yBLJ06wiiNtYrKxZovv/wSixYtUtMFChTA5cuXMWHCBNXNOSaZlvmbNm1Kl62/wijqQzmwDUjJkiXVD4746quvUKtWLRw4cACzZ89Gu3btVGKChLx8+RKvXr2KNU+eq3nz5jh//rxB/kBLxkTJvCZXG01N01RvdUohPCaIxwTxGCBD+/9CXqtHjx6qp57Inz8/duzYoYLg9EYCiVKlSqlzSNm3169fh4ODA9KCtHQOERwWgTrTD8MjIBS9quXB0Pq6HWMbcu0aHrVpq+7nXL8OFoULqx4MAbt3w2P6DIQ/eaJd17pGDTgNGQLzvHmQFkntbYmTtm/frqZLlCihxuRrAl+p8ysXqx4+fKi+s9WrVze4wPfKlSsq/5ME7bqI2Qz76I/D398fgYGB6gqjJuuzpq7c/Pnz8eOPP6orGvGZN28exo8fH+8yX19fVeDcEH+o/Pz81BfS0H+oKHXwmCAeE8RjgAzp/wspDdS3b191Qi2kh57U+ZUkO4Z4bqULktxLAn4JJn/44Qdtq7ChS0vnEOsvvMQr/+gu5i7WUTo/lvx/m629//y32bDs+CWC5s5D+H//aecb53aHdd++MKtQAX4yIw0ez/J5d+nSBcePH1fTMhxh5cqV6vOPuU8lqJTgN1OmTCrnkqGRWE2XDPvoj8PKykr9bd++faz5Ul9OAmD5cBMKgOXH+Ysvvoi3BViyE0qSBkP8oZJ++GnhSh2lDh4TxGOCeAyQofx/IS1LXbt2xc6dO9W0tNBs3boVTk5O6fpD6tSpk6pvfPToUfzvf//DwIEDVZIsQ5dWziFCwiOx4txldT9XFiu0q5wfpibGOm399T5yRDsddviwumkYOzjAsX8/2LVqBSMD3k8fIgGuxEhnzpxR07Vr11ZJhDNlypTmjg2J1XTJ8N7he7i6uqom8Lh91bNmzar+ent7J/hYWUezXlzSzG9oTf0aJiYm6kA01O2j1MdjgnhMEI8B0vf/F9Ky1KxZMzUUTVNaRVqBdX2iaqgkG7TUB5ZeiNICvGbNGqQFaeEcYu3ZB3jxOkTd71+7AKwsLXT6/M8XLIh/gZkZsnz5JZz6fg0TOzukZc+ePUO9evVU3CSkhOy6deu0ia/S2rGh621KU0mwypYtq/5KEqyYnj59qv46OzvrZbuIiIiIMgppcKhfv742+K1Tp45qBc4owa+oWLGiGlcppMv3iRMn9L1J6UJoeCR+P3BH3XdzsEKLMm46ff7gq1fhv2dvvMtyzJyhavqm9eD3/v37ahyvJviVVuANGza8N/jNaNJUANymTRv1V7qbxCQZzeSKhSTFIiIiIqKUIQlFJeDVBHxSKkW6PUtljozm559/hrm5ubov5Z/SUF5Zg7Xp/GM88QlS9/vVzq9qAOvSi1+nJrjMd/NmpHWSlK1atWq4cyf6IoLkTVq+fLlBturqU5oKgGVsSffu3VWWwbZt26rEVhIUS/bnYcOGqS7SRERERKR70uOuZs2auHDhgpqW3CobN27MsC1LuXPnxrfffqvuHzt2TO0L+njhEZGYuz86cHO1t0Srsrpt/fVZvx6Bb5JBxcdv9x4EX7uGtOrcuXOq5VfTU1ZqVUusZGycpsK9VJHm9ojUXBs3bhxOnjypkg5ICSOpOffTTz/pe9OIiIiI0iVNt8prbwIEySwrDRKaFtCMatSoUdpEqiNGjFBjgunjHL/riYdegep+n1r5YGFqorNd6fv333g29ocPrucxbx7SoiNHjqgkVx4eHmp60qRJmDx5skpsRekgAJYmfEk5Lz/E8iNz69YtFQgTERERke7dvHlTBb93795V019//TUWL15skNliU5vUAJbzUiHdTqXFjT5O9QLO+Kd/NbQumwNtyuXUyW6Ubumv5szF0+EjZOKD66fFVmAZfy9j8jXli2bPnq0uzDD4TUcBMBERERGljkuXLqFGjRp4/Pixmh46dCjmzp3LbpUx9O7dW1uG88cff3xvVRJ6vxI57DH1i5KwNEt+629kaCiejhgBjzlzkvQ471WrkFZIt3vJ8CwlyaSr87Jly9C/f399b5bBYwBMRERERO+Q+qGSYPTFixdqWoagTZkyhS1LcUg3cNkvQoLfiRMn8mjSswgfHzzq/hVe//2PmjbJmhWnqjnDuEBemOfPF+9Nlp2u5QKH1q2RFkiwK+Pww8LC1DEoNX47d+6s781KE9h3hYiIiIjeGVPYqFEjVe9X/Prrr6r1l+InNZGlm/jhw4dVF9R+/fohb9683F2JcPjWK7wOCsdnxV1gbJz8MauhDx/iUa/eCL1/X01blSqFa2NaY+rZcajvXh6Ta0yGmXHsrMhhkWEYeWgkdj3YhWz2z9EAJQ36s5szZw4GDBig7ltZWWHz5s2qGzQlDluAiYiIiEhrz549aNCggTb4lXGtDH7fT8ZbTps2Td2XFrmRI0fyiEqEyMgoTNp6Df1WnUP7hSeSXUoq8Nx53G/bThv8ZvqsIXItW4q6RZuivnt9FeBKoCsBb3zBr6xTJ1cdg/3sZP9IgitN8GtnZ4fdu3cz+E0iBsBEREREpPzzzz+qtm9gYKB2TKEkvaIPK1++PDp06KDur1+/HsffU3KHou2+9gLXn0dfaKlR0DlZ3etfb9uGh127IuLNGGzHXr3gNm0ajC0sVIuvtPzGDYLjBr/xtQ4bUvArmcbHjBmjpp2cnHDgwAFUrVpV35uW5rALNBERERFh7dq16NixI8LDw1WG59WrV6N1GhkPaSikLOeGDRsQEhKCwYMHq/rAzMabcED3295b6r69lRk6V3b/6OfxnL8Ar2bOjJ5haors4354ZyyvJgjGIaiAN+JghJq/9+Fegw9+IyIiVLf6+fPnq2k3NzfVU6Nw4cL63rQ0iS3ARERERBnckiVLVOulBL8WFhZqTCGD36Rzd3fXluc8ceKESkxE8dt3/SWuPI0u3dO9ah5kskx68BkVFoZnY8Zog19jW1vkWjA/wURWmiC4uFNxFfjKLWemnLGCX48gD/xz5x8ce3IMr0Ojt0+fpEu9JLfSBL/58uVTY/QZ/H48BsBEREREGZiUNerevTsiIyNhY2ODbdu2qW7Q9HG+++471T1VyFhgaQ2meFp/991W9zNZmKJr1dxJ3kURr1/jYa9e8N2wUU2buboi9+pVsKlS5YOPtTe3196PjIqMtey613WMOjIKvff0xm3v6G3UmHthLvrs7oNfT//6zvuRdX2CfZI9jjmm4OBgtGrVCqvelGYqXry4SrSWO3fS91dMO+/vjDUOOi5ZJuukVwyAiYiIiDIoKd+jqRsqCXV27dqFOnUMNwlQWmBvb69KRom7d++qCwwU26FbHrj4yEfd71Y1t+oCnRShj5/gfocOCDx+Qk1bliiB3GvXwOJNPeaEaMb8Hn16FNXcqiGrVVY88X8SKzGWZ5Cndn0nq+gLGRqXXl1Sjz374mys+dJS3OLvFqi+tjr+vPpnrGUnn53ErHOzsOLqCoREJP5iiCShk0zsMi5fM8Zcxvxmz54dybHz/k4MPTj0nWRgcfeRrJNeg2AGwEREREQZjLRSjR07ViXVEY6Ojti/fz+qJKL1jD6sV69eKFSokLo/YcIEeHl5cbfFM/bXxtwE3avlSdK+CfrvP9xv2xaht++o6Uz16sL9z2UwdXZ+7+PiJrz6rc5v2NF6xzuJsernro9/mv+DJQ2WwMXGJdZz5LbPjWKOxVAgc+xA2zP4bdDsaOUYa9np56ex6NIiTDk9BcZGsUOvln+3RP2/6qsAOabbz26jdu/aOPn4JIwtjVGzZk3s3btXfU+Tq06uOukiI3ZyMAkWERERUQYLQIYMGYIZM2aoaRcXF5VQp1ixYvretHTDzMxMta5LfWAfHx8VBGv2d0b32DsIN95kfu5cJTccrM0T/djXu3bh6fARiAoOVtNZunVD1qFDYGRi8t7HhUaEounmpqq1N27Cq5iJseSvTEugK7e4RlaIv7yVtBRPqTFFjR8u4VQi1jJp9TUxMoG9hf07Sbae+j9FQFgAAsMCtfOeP3+OFn1aAC2BvA3ywmWvC/6e/7eq9yt+v/g7rnteR/7M+TGgdHQ5JM33Wt6fBOBWptHrxscsTjIw+Tuh8gSER4ZjzLEx2P1wt8EnBUsuBsBEREREGYSM85WyRgsWLFDTuXLlUi1L+fPn1/empTtNmjRRLXcHDx5U3aAliy/3M5AzizWOjKiNJUfvJzrzswR3XkuW4uWvv8oEYGwMl+/HIHP79ol6/Ogjo1VwKOrkrBMrsIsbENZ/WB8NcjdI0mdtZ26Hz/J8Fu+yIeWGYFDZQfALjQ76Y449blOwjQqaSzqXVPMePHiAunXrwiO7B3Igh5q3cNZCbfArzr04hxPPTqjHxQyAfUJ88NnG6G34rsJ36FAkuiSXphVaum1LoN4sXzOYmcR+z2ERYQgNDcXRl0fTffArGAATERERZQCS4blbt25YsWKFmpZgTFp+JXMx6Z6UP5o2bRrKlSunMvlKQixmhY4mrb6D6hVM1H6MCg/H84kT4bNmrZo2traG28wZsK1RI9GfRcM8DbHv4T5ktc6KajmqvbNcWyf4I4LfxJCuz9ICHHfe4HKDtdM3btxAvXr18OjRIxg/NkaJMiXw9ZCv4WbnFutxbrZuyO+Q/50W6phjlzNbZo617PjT41h4aaF6zRb5W8R6z8fXHMf+x/vVvNo5aqf74FcwACYiIiJK56R1p3379ti4MTpjbtGiRVXwm9yEOvR+ZcuWVbWV5aKD1Ac+evQoqlatyt2WSBH+/ngyaDACDh9W06bZsiHn/D9gmcT6t5/m+hSrP1+t7YocHwn6UiL4TYwLFy6gfv36ePXqlZoe1G8Qfv3113hrSI+rEp1gLS5p3f2xyo9qPHKRLEViLdO0PmexzAIT49jdxQPCA5DRMAkWERERUToWFBSE5s2ba4Pf0qVLq265DH5Tx6RJk2Bpaanuy9hrXZbJSUvOPfTG1J034B0Qmqj1w549w4MvO2qDX4uiRZB73dokB78aBTMXRD6HfDA0x48fR61atbTB748//phg8Ps+DpYOaFGgBXqU6PFO6/DoSqNxpuMZrG+yPlbCqxGHRqiu2M5WziiZuaRqCU4oO3R6wgCYiIiIKJ3SlFLZvn27mpYsz/v27dPWqaWUJ+OsBw0apO6fPHkS69aty5C7fdaeW5iz/zbqTDuAoNCI964bdOUK7rdpi5AbN9S0ba1ayL18OcyyZUvUa0kAN/nUZLwIeAFDJr0wpNuzr6+vmp45cya+//77JAe/iWFhYqEt6xT2Jtvz7gfRCa/+bfYvJpebjHq56sWbHTq9YQBMRERElA7JSbUEv1I7VEh93507d8LBwUHfm5bhyPhf5zdleuR+SEji68GmB1Lz9+DN6BbOzz9xhZV5wlmb/fbtx4NOnRH+pkU0c8eOyDF3DoxtbBL9er+c+gUrr61E+63tcdfnLgzRli1b0LhxYwQEBMDY2BiLFy/Gt99+m+KvGxan1JFmzK+psSkmVpmYYImk9IQBMBEREVE6I90pW7durVochZxo//vvv7C1tdX3pmVIdnZ2GD9+vLp///59zJ49GxnJ7H3RdX/NTIzQp1bC3ZC9lq/A4/79ERUYKFnEkG3UKLiMGf3BMkcxSZfeiKjoFmZna2e42rrC0MiY8FatWqmx+VIya82aNSpBXWrY93DfO8HvO8nA3gTBsm56xCRYREREROnI06dP8emnn+L69etqWgLhlStXwtw88fVWSfd69uyJ3377TX0uEydOVAGPo6Njut/Vl5/4Ys+1l+p+67I54ebwbo3aqIgIvJj8C7yXL1fTRlZWcJs2FZnq1Eny60mm47GVxqK4Y3FUdasKS9Po8deGYt68eaoklpDyRjI2v2HDhqn2+g3eJPqqkyt2OajUyohtCNgCTERERJROSOti9erVtcGvZCBevXo1g18DYGpqqpIbabqnS7KjjNT6a2JshL7xtP5GBgTgcf8B2uDX1NkZ7suXf1TwqyFjaFsVbAUXGxcYksmTJ2uD30yZMqkhCakZ/Go0yN3gvaWO9JkROzUwACYiIiJKB27evIkaNWrg7t3oMY+dO3fGokWLVOBFhkG6oteuXVvbEnjrVnRwmF5df/4aO69EJ6JqWdoNObNYx1oe9uKlGu/rvz+6Dq1FwYIq07NV8WJJep3AsEAsu7IMEZHvT66lL5L5+7vvvlM3IS3/+/fvVxerKPUxACYiIiJK4y5fvqyC30ePHqlpyTosrU2SXIcMh7RMTps2Tf0NDw/HiBEjkJ7N3ndb/TU2AvrVzh9rWfCNG7jfti2Cr15V0zbVqsF91UqYJbE2tYz5HXVkFKaemYoB+waoYNiQREZGon///ur7KFxdXXHo0CFVI5r0g7+KRERERGnY2bNnUbNmTbx4Ed3SNm7cOHWynRKlVCj5pA5zp06d1P1Nmzbh8Js6t+lNcFgE7rz0V/eblXJDbqe3WZz9Dx/Ggw5fIvz5czXt0LYtcv7xO0w+Ikmbb4gv7vve1wbD5iaGM9ZdLnJ06dJFtfaLPHnyqM+7aNGi+t60DI0BMBEREVEadeTIEVXeyMvLS03LGNMffviBwa+BmzRpEiwto5MzDRkyRLUSpjeWZibY9k11/NGxDAbUedv6671mLR71+VqN/ZVMz1mHDYPLuB9g9JFd9TNbZsaKRivQvnB7/FLjF1XOxxBIqasvvvhCZXwWEvRK8Js3b159b1qGxwCYiIiIKA3as2cPGjRogNevX6tpaWUaOnSovjeLEiFHjhwq8BWnT5/G2rVr0+V+MzY2QsPi2ZHX2RZRkZF4MeVXPB83DoiIgJGFBdxmzoTjV92TfcHG1twWoyqOgr2FPQyB1Pb9/PPPsXnzZjUt3Z0PHjwINzc3fW8asQWYiIiIKO35559/1Al2YGCgGue7dOlSfP311/reLEoCGf+bNWtWdV+SIwUHB6fb/RcZFIQn3w6E1+LFatrE0RHufy6DXYP6H/V8nkGeOPXsFAyRj48P6tWrpy5QCUl0tW/fPjg5Oel70+gNtgATERERpSHr1q1Dy5YtVRdLyfC8Zs0aNc6Q0hYpg6MphfTgwQNVIzg9eOgZiB7LTuP8Q281He7hgQddusJv9241bZ4vH3KvXQurkiU/6vnDIsIw6MAg9NrdCyuvrVQZlg3Fy5cvUatWLRw/flxNS4mjHTt2wM7OTt+bRjEwACYiIiJKI6Slt3379iq5joWFhUqiJOMMKW366quvtAmRZFywh4cH0rp5B25jz7WXaDHvGO6evoT7bdoi+L//1DLrSpWQe/UqmOf4+K7AV72u4qrnVURERai/hkIysEtr78WLF9W0fC+3bNkCa+vYpZ9I/xgAExEREaUBMsa3W7duKmGSjY0Ntm7dqrpBU9olLfiSuEzIWO7x48cjLXvsHYgN5x6r+92tPBDW9yuEPX2qpu1btkSuBfNhkszW0JLOJbG04VLUzVUXYyuPNYiEb1LPuVq1aqoWt+jevTtWr14Nc3PDyUhNbzEAJiIiIjJwU6ZMQb9+/dR96U65a9cufPrpp/reLNKBzz77TPtZ/vHHH7hx40aa3a9/HLyDsIgo1H9wCq3X/YpIPz8133ngQGSfNBFGOgoIizsVx4zaM2BhYgF9u3Tpkmr5ffjwoZoeOHAgFi5cCBMTE31vGiWAATARERGRgZLxjWPHjlUJk4SjoyP279+PKlWq6HvTSEekBXPq1Knqr3Rt13zWac1z32CsP/UQXa5ux6Dz62AkmZ7NzeE6bSqc+vROVkvtY7/HKvGVoTl58mSsGtxSgmz69OkqMR0ZLn46RERERAYa/EpZowkTJqhpFxcXHDhwAGXKlNH3ppGOlSpVSpvITMaNSsmctGbBnmsYdHIF2t3cq6ZNHByQa+kS2DdunKzn9Q/1R7+9/dB+a3tc97oOQyEXoqTl3ts7OtnXtGnTMG7cOIPokk3vxwCYiIiIyMDIOF8payStSSJnzpw4dOgQihcvru9NoxQyceJEWFlZqftSI1iOgbTi+cOnKD59FGo+uaCmzXPnRu61a2Ctg4s1W+5swV3fu3gW8Ay7H0RnkjaEMmTSdV3q/UrAK12eBw8erO/NokRiAExERERkQKQbbNeuXTF//nw1nS9fPhw+fBgFChTQ96ZRCnJzc1Mt/uLs2bMqiVJaEHL3Hh61/xJFPO+r6fDipeAumZ7d3XXy/B0Kd8CQskNQO2dt9C3ZF/omn0uLFi20ZchkukePHvreLEoCBsBEREREBiI0NBTt2rXD8uXL1bSUyJHg111HwQQZtuHDhyNbtmzq/qhRoxAUFARDFnj6NO63bw9bz+dq+mKRyii2ahlMM2fW2WtIC2vX4l0xs/ZMmBjrN7HUggUL8OWXXyIiIgKWlpbYvHkz2rZtq9dtoqRjAExERERkACTYad68OTZs2KCmS5curcaCZs+eXd+bRqnE1tZWO+ZbsgrPmjXLYPe9799/40H3rxDp66umTbr1RMl5M2Csg0zPzwOeIzIqdhdwYyP9hi1Srqp3795qbL58Tjt27EDjZI5vJv1gAExERESkZ35+fmjUqBG2b9+upitXrox9+/bByclJ35tGqUxqPRcrVkzd/+mnn/Dq1SuD+gwkAHw1Zy6eDh8BhIUBZmZw/WUyCo4YjCLZ7ZP9/B5BHvhy25cYenAoAsMCYQjvd8yYMap1XmTJkgV79+5V2Z8pbWIATERERKRHPj4+qF+/vsrwLGrXrq3q/Do4OPBzyYBkXKmURdJcGJHMwoYiMjQUz0aOhMecOWra2N4Ouf63CPbNmunsNX49/SteBr5UCa/2PNwDfZJEZN9++y0mTZqkzcQuvTIqVKig1+2i5GEATERERKQn0ronAe+JEyfUtLQCb926VXWxpIyrQYMGqFevnrovydCuX9d/+Z8IHx88+qoHfLf8raZNcuTAT58Nxd9wQWi47jJWj6o4CpWyV0KL/C3QJG8T6DMZ3VdffYXZs2er6dy5c+PIkSPMxJ4OMAAmIiIi0oOnT5+iVq1auHAhunRMq1atsGnTJm0pHMq4JPGTtALLX0m4pOl+qy+hDx/ifrv2KumVsCpVCrv7/YSDwdb4buMlHL3jobPXsrewx+91f8f3lb7XW01dyfAsyeiWLl2qpgsXLqyS0UlGdkr7GAATERERpbIHDx6gRo0auHr1qpru3Lkz1qxZA3MdJBCi9OGTTz5R44E1dWf379+vl+0IPHce99u2Q+j96DJHmT5riCzzF2L+RS81XdzNDrUKOifvNeKM9TU1NoWZiRn0QWr7Nm3aNFYyOqnBnSNHDr1sD+keA2AiIiKiVHTz5k1Ur14dd+7cUdN9+vTBkiVL1NhPopgkI7S1tbW6LzWCZUxqanq9bRsedu2KCG9vNe3Yqxfcpk3D8nPP8To4XM37pk6BZLXU3vO9h882foZNtzZB33x9fVX3cxmDL6pWraqS0Tk7Jy/AJ8PCAJiIiIgolVy+fFm1/D569EhNDxkyBPPmzYOxMU/J6F2urq4YNmyYun/u3DmsXLky1TIfe8xfgCeDhyAqNFQycyH7xAnIOngQAsMisejwXbVekex2qFc0um7xx5BSR0MODoFXsBfGHhuL616pM9Y5LCxMJZ3buHGj+ivTmvH4R48eVetIYrqdO3cyGV06xF9bIiIiolRw9uxZVTrlxYsXavqHH35QtUX1Nc6R0gYJgDW1oEeNGqXqRaekqLAwPPv+e7yaMUNNG9vaIteC+XBo3VpNrzjxAN6BYer+gDr5k3X8Sm3fMRXHIItlFvT+pDcKZymMlCSBrrSq58yZUwW7Mu5e/rq5uaFo0aI4f/68Wq9ly5b4+++/YWNjk6LbQ/rBAJiIiIgohUmrUp06deDlFT1ucsqUKaq8DYNf+hAJwiRoE48fP8aMN4FpSoh4/RoPe/WC71/R41/NXF2Re/Uq2FSpoqaDQiOw4FB062+BrLZoWMwl2a9ZJlsZbGi6AX1L9UVKB7/NmzfH2LFj8fLly1jLpPXXwyM6kVenTp2wdu1aWFhYpOj2kP4wACYiIiJKQXv37lXdKV+/fq2m586dq+3WSpQYXbt2RYkSJdT9n3/+WduLQJdCHz/B/Q4dEHg8uiSXZYkSyL12DSwKFNCus/LkA3gGhKr7Az4tAGNjo4/u+hyTk5WTag1OSZMnT8a2bdu0XbwTUqBAAY7HT+cYABMRERGlkH///ReNGzdGYGCgGucrZVX69k3Zli5Kf0xMTFRZJOHv7696D+hS0H//4X67dgi9HZ2YLVO9unD/cxlM4yR/srEwhaONOfI626Bxiehu2Ul18dVFtP6nNe76RrckpwZp/ZULTx/qcSHLZUy+rE/pFwNgIiIiohSwbt06tGjRQtUUlQzPUuaoS5cu3Nf0UaQXgWQoFgsXLtSW0Equ17t24UHnLoh40wU4S/fucJs1C8bx1KNuXyEXjoyog/kdy8LkI1p/JdnVwP0Dccv7Frps7wL/UH+k1hAEaTV/X8uvkOXPnz/XJsKi9IkBMBEREZGOSUtv+/btER4ersYSbtq0CV988QX3MyWLtAJLT4KIiAgMHz48SY/137sPoYePxAr2PBcvwZNvByIqOFiameEy7gdkGz4MRu/JSm5lboIC2TJ91PY7WDjgi4LR34P+pfrD1twWqUGTdT2xNGP1KX1iwTkiIiIiHZIulP369VP3pYarZJP99NNPuY8p2YoXL47u3btj0aJF2Lp1qxpfnphjK/jqVTwfOFDdDylcCKZFiuD5xInwWbNWzTO2tobbrJmwrV493seHRUTCzCT57WYyzleSXdXKWQtFHYsiJUk35h07dmDFihXqAlRSZMmSJcW2i/SPATARERGRjkhZI03LnJ2dnUq6U7VqVe5f0pkff/wRq1evRkBAAIYOHYozZ86oMcLv82rePO19zzlz4RUZiYDDh9W0qYsLcv7xOywLF04w+G0w8xCq5nNCn1r54ObwbtfopEqp4FdatU+dOoXly5erTM6azM6JJWOAs2XLxu9sOscu0EREREQ6OPGWur6a4FdakPbt28cTadI5qQmsOc4uXLigWjg/1Prrv2evdjrw4EFt8GtRtAhyr12bYPArNp17gruvArD8xAMcvPEqydt76PEhjDkyBiERIUgpd+7cURcGChUqhEqVKqmEV5rgV3phfPnll6q8UWK+x9J7w8zMLMW2lfSPLcBEREREySAnzVLWaNq0aWpaWpD27NmjuqsSpYQhQ4Zg/vz5ePr0KUaPHq3Gl0ug96HW35hsa9WC27SpMLaxSfB1wiMiMWf/bXU/u70lWpV1S9J23vW5i+GHhiMgLADPA59jYb2FOqt97enpqRLNSWvv8ePHYy2TcdJ169ZFx44dVSI6W1tb1SVaxvZK13HZhpgJsTTTkrF9xIgROtk+MlxsASYiIiL6SJGRkaqskSb4zZkzJw4fPszgl1KUjY0NJk6cqO4/efIE06dPf2edqPBw+GzcFKv1Nyan/v3fG/yKLRee4qFXoLr/da18sDB9f1fruOwt7FEwc0F1v12hdskOfoODg/HXX3+hWbNmqiVcvnsxg99SpUqp76Ikvdq5c6dq9ZXgV0irrowFnjBhgrpIFZNMy3xZztbf9I8twEREREQfQTI8S0IiaYES+fLlU0mJ3N3duT8pxXXu3BkzZ87Ef//9h8mTJ+Orr75C5td+CDxxHAHHTyDw9GlEBgQk+HjP+X8gx+zZCS6PiIzC3Detv1kzWaBNuZxJ3kZHK0f8r/7/cOzpMdTMWRMfe5FJLipJV+/169fD19c31nK56CRdnOX2oV4XEtyOGTNGtfJKqSNpEZbhCjJOn4FvxsEAmIiIiCiJQkND0aFDB2zYsEFNFy1aVHV7llYpotQgia9mfvcd5vXpg0rWNnhavwF8wsIS/Xi/3XsQfO0aLIsUiXf5v/89xV2P6AC6d818sDRLWuuvhpmJ2UcFv1LnWILelStX4uHDh7GWSYI56fYtXZxr1KihujwnaZvMzFCrVq0kbxOlDwyAiYiIiJIgKCgIrVu3VhmeRenSpVV3S2dnZ+5HSlHhHh4IOHESASeOI/D4Cbg8eYIfXd5cdIkR/EpmZxgZIfzZs/c+n8e8efG2AkdGRmH2vujWXydbc3SokCvR27jl9haYm5jjszyfIameP3+uMlxL4Hvu3LlYy0xNTfHZZ5+pbs2ff/45rKySn42aMiYGwERERESJ5O/vj6ZNm2L//v1qunLlyioQdnBw4D4knYvw80Pg6TPagDfk1q141/OJiMDJwAD45cmD4cuXIzIwEPdbtf7oVuDtl5/j9kt/db9n9bywMk9c6+/5l+cx7vg4hEeG46n/U3xV4qsPPkbKOW3evFkNJdi9e7fq8hyTZHWWlt62bdvCyckpUdtB9D4MgImIiIgSwcfHB40aNdIm3alduzb+/vtvbZIdouSKDAlB0PnzagyvBL3Bl68AERHvrGdkZQXrcuVgU6kSbCpXwrczZ2LBwoXA06eodPs2ih08mOjX9F61CtknTIg1L5udBcq5Z8adV/7oWCnxY9ql1JGVqRWCwoNQOmvp946flzJhEvRK4ikJgmOS8fQS9Motf/78iX59onQXAB84cED9ZxMf+c9IrhARERER6dqrV6/QoEEDnD9/Xk1LICzZaNkNk5IjKiICwVeuaAPeoHPnERUST71cU1NYlSypDXitPvkERubm2sXjf/wRq1avVj0Uhg4diqNLliDowoU4LyZljcJhamIKxEjG7ND63ZbicrmzYH2fynj+Ohg2FokPFyplr4TVjVfjmtc1lMlWJvbLR0WpusUS9Eo3Z+nuHJMko2rXrp0KeuWcXlflkojSdACs8c0336B8+fKx5vHqEBEREaUEqbVar149lZRHtGrVCqtWrYJ5jACEKDEkCAy9ffvNON4TCDx1CpF+fu+uaGQEiyKFYVOpsgp4rcuUeW/JIhcXF5XZ+Pvvv1dZoddfvIhu//4bax2pgyu1cx0dHROV8VgC0Oz2SR9n627nrm4aksBKvi8S+Gq+QxoWFhZo0qSJGtfbsGFDfqcoVaTJALh69eoq+QQRERFRSnrw4AE+/fRT3LlzR03LifrixYtVQh6ixAh78kQFu6qV9+QJRLzyiHc9c3d3WFeupIJe64oVYJo5c5J28ODBg/HHH3+ousBS6qdNmzaqXnBS+AaFwc7SNEmtrxtubkCF7BWQM9PbMklSqkh6SEgyK+nBGZdkYJaWXrmYxPHzlNrS7K+3n5+f6nbE/4CIiIgoJdy6dUsFv48ePVLTffr0wdy5c5NccoUylnAvLwSePPmmW/MJhMUp4aNh6uysDXilldcsmSW0rK2tMWnSJHTt2lX1Wpg2bRrGjh2bpNbpzotPwczYCIPrFUSV/B9OOLXv4T6V9Mrewh7Tqk3Di3MvVNArY+ND4nTlllJhcgFJyoflypX4rNJEupYmA+Bu3bqpMQ5S/0xag3/99VeUK1dO35tFRERE6cTly5dRt25dvHjxQtu6NnXqVI5LpHdE+Acg8MxpBL7p1hxy/Xq8e8nYzg42FSvAWsbxVqoE87x5dX48SYA5c+ZMNdZ2ypQp6NmzZ6JrUx+65YGLj3zU/eN3PRMVAF/1jO7S7B/oj2YNmuHF1ejvi0a2bNlUwCvbVapUKX5/yCCkqQBYxtpIVwlJPCFp0GUcgfxnJEHwsWPHVB2+hLx8+VIlsIjp9u3b2jERcjM0kiEvIiJC/SXiMUH8nSAeA6lD6o82btxYjZcUo0ePVi1paen/Y55DpJyo0FAEX/xPtfIGnTyJ4MuXZYe/s56RpSUsS5eGdcWKsKpUERaFC8PI5G05oZQ6nn755ReVsE0yK0tXaOkW/aHzSmn9nbXnprpvY26CThVzvPfcWM6hJZGV3DyyeiAiMAJ+V/20LdHNmzfHl19+qZLXanprpqXvT0YTbuAxh67jNKMoOeLTMPkCfvLJJ6hRowZ27NiR4Hrjxo3D+PHj410mYxMKFSoEQyMHoXT1zpQpE7t6E48J4u8E8RhIBadOnVJjE+X/XyFJhfr27Zvmjj6eQ7wVeviI+mtevdpHZ2qOuH0b4efOIezcOYT/dwmIL1OzsTFMihSBWZkyMJVbsaKxMjWnJmlx3bNnj+quL3+LFCny3mPizKPX6L8husZwp3LZ0K9ajneeUy4I/fPPP2ps79mzZ2Mtk9eRc3FpqPrss8+SPPaY9CvcwGOOGzduqHHj0jOnWLFiyX4+w3uHSSTZn5s1a4aNGzeqKxfSLTo+8p/XF1988U7wLFeo7O3tVUY8QzwYpWuMpIU3xIORUh+PCeIxQTwGUo7UJW3fvj0CAwPV9G+//abG/aZF/P8iWsi1a3j0/ffqfpb161Qr7IdI21DYvfvaFt6g06cR+fp1vOuaFywIq4oVVdIqq7JlYWwgNaFl/G+ZMmXUufHkyZPx77//vveYWL7lrvprZWaMfp8WhqOthZoOCgrC1q1bsXLlSuzcuVM9h115O0BOtyOgujVLS68k3EpsV2syPOEGHnNIrKZLhvcOP0LOnDkRGhqqunrY2dnFu07WrFnVLT6SCj4x6eD1QQJ6ORANdfso9fGYIB4TxGNA9yRAkAoTkrhHWrMk03OXLl3S9MHG/y+A5wsWaPeHz4IFyDF7drz7Kuz5c5W0KvDEcVWiKPzN2O+4zHLm1Nbila7NpgbYgCKkd6SM/5Xuz7t27VI3KTkkWc3d3d1Rs2ZN7bnlybueOHnPW93vWMkdWe2tcejQIZXMav369XgdI/jPXCsz3Lq6wTHQET9X/hmVS1XW23ukjPN7YabjbUoXAfDdu3dhaWkJWwO56kakCz2WncYDz+hWiJhXpTU9HWImznB3tMaiLrFrYxMRUeLISb4k6pFWEDkBlNYuadGitC346lX479mrnfbbvQfB167BskgRRPj4IODkKQScOI7A4ycQev9+vM9h4uQEm4oVowPeSpVhnsMNaYUM/ZMgVhLHSo/HmOM7pW6w9I4cOXIkZu+LzoljbmKEV4fXIPfXS7WZz2O2wLX+ojVefvoS90LuAVmAPAXypPp7IspwAbAksXJ2do417+LFiyrVuow3YFkCSk8k+L310l/fm0FElK4tW7YM3bt3R2RkpGohk/GNn3/+ub43i3Tg1bx578x7PHAQTGxsVCCMeNLgSBdm6woVVCuvtSSuKlAgzWYuzpw5M1xdXXHz5s13khtJdnNJ7Lbz7C08LtxWzfM4uQWz9r5tMZeLQZJ4VsYTy3dCGpuCw4Mx4cQEfFHwC7jYuKT6eyLKcAFw27ZtVe3fKlWqqO7MkgV6wYIFKtucjG8gIiIiSqx58+ahX79+6r6cS2zZskWVPqL01/qrEfbgAWLmk5UkVVZlymi7NVsWKwYjAxwD+THk3FiC3/hocuCe2LsNdgE2sC1eG69PblDzKleurBLBSS8IqboSk6WpJSZVm5QKW0+UctLUN1y6b0i3pOnTp6vxCNIa3LJlS/zwww8qGRYRERFRYvz6668YPny4ui/5QyTRT7VqH5clmNJG62/MeryZ27VTAa9V6dIwtrREeiNlY+bOnatar99X8CXC3xPee/5A5ocH8f3QASrwzZcvn3Z5ZFQkLnlcQknnkqm05UQpL00FwN988426EREREX0MCQakNOKPP/6opiXrqSQIKlu2LHdoOm/91ZCMznafNVRjgdOro0ePqm7OibXoj7mqZm9cv1/8HfMvzkf/0v3Rs0TPNNsdnCgm41hTREREROk4+B02bJg2+M2WLRsOHjzI4DcDtf5qeCRinbTMy8vrvctNbDLDyDS61JHw9o7OAh2TR5AHll9djihE4Z87/yAwPHZiTqK0KkUCYEmdLgmrEuLh4aHWISIiIkoNkuRKst5KfVRNCcXDhw+jePHi/AAyUOtv3IzQ6ZX0bHifzPX6wK3PImQq1yzB9Z2snLDisxUokqUIfqvzG2zMbFJse4nSfAAsXSh2796d4PK9e/fG282CiIiISNckA27Xrl1VTVQhYxwl+C1QoAB3djrjtWpVotf1TsK6aU3VqlVVD4f4uiybObnDplBV1QpsnjWPKokk68cnf+b8WPv5WuSxZ8kjSj9SZAzw+wbbCykyL3VMiUg3nr8ORmBoOKzN09SwfiIinSf+kbGP0v1TWrTkpF7OSb788ktV3kgUKVIEe/bsUeVhKP3JVLcufDdtBiIiACMjmOXMCSNzs3jXdWjdGunV16suwKXbHBi/evnOMtNM0Zmd5bth4VYU+UpNg5lZ9D4KiwiDd4g3slpn1a7Pcb+U3ujsbPnhw4e4H6OI+PXr1+Pt5uzj44P58+fD3d1dVy9NlOH5BYej5bxj+KNjWeR2YhclIsp4ga+UfJGstzET/0gLmGR4vnXrlpouVaqUSnglVSQo/YmKjIT3n8ujg18ArpN/hn2z6C6+Gc0Dz0D4RFnB3Cnh820JbM2yuMI8i402IJ50chIOPDqAmbVnolTWUqm4xURpMABesmQJxo8fr75Mcps0aZK6xSVfLmn9lSCYiD7wBc30H8L9ikm6igTWiIBppisI9/sE15/74ds157G5X1VerSWiDBX8SpnEbdu2vfPbJ8GwJiCuUKECdu7cCQcHBz1tKaU0ryVLEXDsmLpv17RJhg1+k0rzvTnz4gw23IquBTzz3EwsabCE5xOULuksAJZi2ZJIQgJcuS/liqpXr/7OF8zGxkZdgZWrskSUMFvHK7DCKliGlIa9f1cYwUR9vyIiIqKHEBhFwtd2KYItzsPW1wKvPYri1y9K8j8rIspQpOVXgt8PDcFq0KABg990LOjSJbycMUPdN8uVCy5jx+p7k9Kc8i7l8X2l7/G/S//DlBpTeD5B6ZbOAmAZUyM3TWtwjRo1kCcPB8wTfax1nXpi5KE72PVgF2oUdMbkGpOlwReenp6wy2yH749/j10PzqO+e31MrjEA3v4RyGpnGes5gkIjYGXO8fZElH5bf6Xbs1xgf1/wK8sXLlyI77//XjvWkdKPCP8APBkyVLKdAab/b+8uoJvIujiA/9vU3V2gxd2Lu7u7y7I4i7OLs7jDh7O4u7u7u2vd3S3Jd94LDQ0tUKBp7P7OCR1rMkymydx5792rA+dFCyEwMVH0bqmkjoU7olWBVtAXfCmRRIi6kUsW6F69elHwS8hv0tXW5UEvC3BZEDzh6gSkidKQLkrHpJuT+DJJ8DuXb/t18HvggT8aLLmC5wEx9F4QQtQSS3jFujj/KPkmWx8cHMy3J+onZOYMpPn68mm7kSNgWLKkondJdWilQgyRzCIKfom6k1vK2FevXvGW4I8fP/Li2l9/ObG7sawcEiHkx0EwroIHvCw7Y2pqKm6E3pAJfr/mE5GAvw89Q0q6CO1W38SsNiXRvrwLHWpCiFph2Z7luT1RfjFHjyLmyFE+bVy1Cqz69lX0LqkQEQyddyFKXwuxqeVhpmem6B0iRHVbgLdt24aSJUtixYoVeP/+PS8+zwLgzA+2jBCS8yC4nls9XPK/xINfVxNXjCo/Ktvgl3GzMsLohoWgrQUeBI/Z9wT/8IBYkhmTEELUASt1JM/tiXJL9fVF8LTpfFpgZQXHuXOhpS2XS1u1pGt5Ezqmr5Cq9xIrHq5Q9O4QototwNOmTUPZsmVx6tQp2NhIao0RQnKPX7wftr7cioleE7Ndz3pY/FHTEyWczTFs5yNEJKRixx1fvAiMxeru5eBobkhvByFE5bE6vyyo/VHLLvtMZMk32fZEPYhTU/m4X1FiIp93mjMbunZfateSH1eSSIspBx3zx9DXTcPwcsPpkBGNIZfbZIGBgejbty8Fv4TkAjbul43/veB7ARXsK8Bc15wv94/z5+syJKQlZPndqp42ODasOkq7Ssp+PPaLRvPl13HzQzi9N4QQlXf58mXExcX9cDvW82zIkCGUAEuNhC1fjuRnz/i0Va+eMKlVS9G7pFRitO/D0GUnDJx385KJWQlh4HgIOob+ME6qB1M9UwXsJSFqFACXKlWKB8GEkNwJfjMSXq2ssxK7a+9GNadquBpwVZoYi13c9TzVEwPODsD94Psyz+FkYYi9Ayujq5cbn2etwT3+u8uDYUIIUVUHDx5E8+bNeSboDF/XAc6Yb9asGcaPH5/n+0jkI/7GDURs+I9P6xctCtvRo+lQZ3LlbRjCggsiLbYkdM2efRUEsyGIQr6MrWPbGKZ60fEjGkUuAfDixYvx33//4ebnYuSEkN8PfjMSXulo62BxzcUy2aEv+13G26i3uB10G49CH2V5Ln0dAWa3KYn57UtBT0cb9YvaobSLpCWZEEJUDUuy2aFDB54UkJU12rVrF2bOnMm7OWfG5tnyQ4cOUeuvmkiPiEDghAl8WsvQEM6LFkFbT0/Ru6U0zr4IxoAt9yGGAMkBnSFILMMDXVuP/fCwFcDCcz0sC6ySBMYpZeGS1h/5rKn1l2gWuYwBnjdvHszNzVGjRg0UK1YMbm5uEAgEWe7KHjlyRB4vT4hauOh7MUvwy7JAZ5cdupJjJXQv2h1nvM+gU5FOMs/zPuo93MzcoCfQQ8cKrijuZMaTZGVuKWEtyF+3nBBCiDJasmQJRo0axaeNjIx4S3CjRo34PGvlZaWO2JhgNjaYjfmlur/qQywSIXDiRAjDJMN4HCb9A32P/IreLaVx/GkgRu5+jHSRGLoCLazoUgn1ijWR3ky3sgqBMEHSQ7O4dXFsa/rfN5NpEqLO5BIAP336lF9Ms8A3Pj4eL1++zLINXWwT8n2N8kku6Oq61c32C0paJ9i3oXRbnhla8GVbFjAPPD8QEAMjy49EC88WKO4k2/LLMkP333If3bzc0LiEI70thBClxG7UTZkyBf/++y+ft7CwwIkTJ1C1alXpNizYrV27tgL3kshT1LZtSLh6jU+bNW0C87Zt6YB/duCBP8bufwKRmPX60saaHuVRp7AkKRi7VhBeEfJcIoy5njn+a0TBL9FccgmAvb295fG0hGicjMD2W1gQnHmbzMEvc9r7NEITQ/l0uig92+f49/grXHsXzh9/1vLEmIaFoCOgMhKEEOXBSicOHz4cK1eulHZtPnv2LM85QjRD8suXCF24iE/rOjvDYdo0akz57PCjAIze94RPG+oK8F+vCqhawAbhSeGw0JckwcyshHUJ3iuMEE1FV7mEqLHG+RpjZrWZ8HL0QjOPZjLrLvleQkB8AGoWsoWpvuRe2JorH9Br011ExKcoaI8JIUQWS3LVs2dPafDr7u6Oa9euUfCrQUQJCQgYNRpilvBMIIDTwgUQmJkpereURoV8lnC2MISJvg629quECvnNsOHZBjQ72Ax7Xu+RVpKo41IH1eyq4UbQDWkSTUI0kdwCYKFQiN27d2PgwIFo06YNnn1OVR8TE8PH64SEhMjrpQkhmVqEWxdojQ0NN8jc7Y1LjcPf1//mX44+wmM4Oqw6CttLkmDceB+BFiuu4wlliSaEKFhSUhLatWuHHTt28PmiRYvyMb4FCxZU9K6RPBQ8ezZSP/cutB02DEZly9Lxz8TF0gg7+nvxR8V8VhBDjP1v9yMxPRGLHiz6kk+k+lxMKj0JDdwaSJNoUhBMNJFcAuDo6GieeKJr1648M+PRo0cRFhbG15mYmPBuTMuWLZPHSxNCcuCq/1XEp8VDKBaioEVB5LcxxqEhVdGytBNfHxiTjA5rbmHXXV86noQQhYiNjUWTJk1w7NgxPl+hQgVcvXoVzs7O9I5okNiTJxFz4CCfNqpUCdYD+kPTsfHwzwNiZJblszFGaVdJd2d9gT7+KvcXjHWNeYD7dSWJf6v+K1NJgoJgomnkEgBPmDABL168wJkzZ/Dx40f+h5qBZYNu3749Tp48KY+XJoTkAOsOvaf5HvQs1hM1XWryZUZ6OljWuQyaVn8DPdM3SBUKMfHgM8w++YqOKSEkT7Gb5nXr1sWVK1f4PEtsdeHCBdjY2NA7oUFS/f0RNGUqnxaYm8NpwXxofVVVRNOwa2r2vdzif9dx5HEAopOj8e/tf7H2ydos2yakJcgEv1mSaH4OglnVCUI0iVySYB0+fBjDhg1DgwYNEBERkWV9oUKFsHnzZnm8NCEkh4pZF+OPzEISQ3Arahv0XdJhFFcbsQGNUauQLR1TQkie8ff359cPr1+/5vMtW7bEnj17YGBgQO+CBmHjfQNHj4EoPp7PO86ZDd2v6jxrGpFIjKlHX2DbbR8+v/DsGxwJ3ol7IXdgIDBAS8+WcDSRVHNolL8RoPVzlSQI0RRyCYDZON/8+fN/N6FFenr2GWkJIYrzJvIN7zrFMkYva9Eb0VEOqFaAWlwIIXnj3bt3qF+/Pnx9JcMvevTogY0bN0JHRy6XK0SJha1ciaQnkszGlt26wbRuXWgyoUiMiQefYu99fz7vZmWEnQO8EJJqjt6n76CsXdks1R5+tpIEIZpCLt8onp6eePjw4TfXs9IFxYrJtjwRQhSvlmstnG1/Flf8rqCWe3nA/cu6f67/A+10O1gKa+OvuqWo/AQhJFc9efIEDRs2RGiopHQb60m2dOlSaGtTwQpNk3D7DiLWruPT+oUKwW7cWGiydKGIlzk6+vIJdC0+wVW3Dnb2rwwHcwO4oDx2NduF4tbF6XuZEEUGwP3798f48eP5mJ169erxZVpaWkhJScGMGTNw+vRprFsn+WAjhCgXMz0ztPBskaVl+OiHo3w6NfIlXgcMwMKOpWFmkLVbFSGE/CyW2blZs2a8BxkzZcoUTKM6rxopPSoKgePGscGu0DIwgPPiRdDW14emSk0XYfiuR7jgfwzGHoehBRHm1u/Ig98MJWxKKHQfCVE1cgmAR4wYwZNgdenSBRYWkox0LCM0Gw/Muj6z0kj9+vWTx0sTQuSAJdJwN/GET9wnpEZWx9mQELT+3w2s6VEe+W0MeLklQgj5FeymeNu2bXnJI2bJkiUYOXIkHUwNTfAU9M8kpH/uBWA/cSL0CxSApkpOE2Lwjoe4+DoU2vquPPjV0gLexj5CJRRX9O4RorLkEgCz1t7169ejV69e2L9/Px/TIxKJeNfojh07omZNSdZZQohqKGdfDsfaHsKDoBdYdTaJfxl/DE9A65XX4V7yPxS3y4f+JfujiFURRe8qIUSF7N27F927d+e5QVhX5//++w+9e/dW9G4RBYnauRPxFyUZiU0bNoRFxw4a+158iP4AV5Mv+XTK2BdB83JjUdm5fJYEloSQnyPXrBLVq1fnD0KI6mM3tio4lcCGnmKsuPgeSy+8RYrOG/gnvoG/9xvkN/OgAJgQkmPsRjnrEcZa/fT09LB79260adOGjqCGSn7zBqHz5vNpHUdHOM6coZFjWkMSQjD/3nxenmhjo41Y1a0cll14hyF1CsBEv5qid48QtSCXzBKfPn2SFq7PDlvn7e0tj5cmhMiZtrYWRtQviI29K8JI2wZpMWUhFhrg4t2CiEpIlW4XEB8AkVhE7wchJIv58+fjjz/+4MGvsbExTp48ScGvBhMlJSFg1GiIU1PZlwycF8zndX81UVxKKq76X+XTyx8uh4GuAOMbF4GJPmVCJyS3yOWvacyYMYiNjUWLFrKJdDKsXLmSjw1md3sJIaqpTmE7nBjUFn9ud8fL96FIdzKEkb6Ar0sTpaHv6b7Q19HHiHIjUM9NkgyPEKLZWMD7999/Y+7cuXze0tISp06dgpeXl6J3jShQyNx5SP3wgU/bDB4MowoVNOpvgmGt3RHxKRi2zRuuts1QwDURoyqMUvTuEaKW5NICfOvWLV7E/ltYZuhr167J46UJIXnIzdoIBwZVRS+vwljdvTz0dSQB8BnvMwhMCMSnmE+ISIqg94QQAqFQiEGDBkmDX0dHR1y9epWCXw0Xe+Ysovfs4dOGFcrD5s+B0BTPwp6h+6nuuOB7AaGxyei07jZeBcXi4dMKqGg8DA7GDoreRULUklxagKOiomBqavrN9SYmJjwjNCFE9RnqCTC9lWwJhtoutVHbpi+ChbfQqkArmXV3g+6ikGUhWBhIMsQTQtRfamoqevbsiT2fAx0PDw+cO3eO/ySaKy0wEEGTJ/NpbXNzOM+fDy0dzejqm5yejCEXhiAqJQpz785HmrcIPhFpfF3bci78QQhRoRZgNzc3XtPvW1jrr4sL/WEToq523ArBsWuFEP9pKEJjhDLllEZeHomGBxpi56udCt1HQkjeSExMROvWraXBb4kSJXD9+nUKfjWcOD0dAWPHQRQby+dZ0itdJydoCgMdAwwpMwQ62rqICi0Gn8gEvryrlxsWti8NgbbmJQAjRKUDYFb/d9euXVi+fDkvf5S5+9OyZcv4lyCrC0wIUT8ikRhX3obx6VdBcWi+4jouvZHUdDzrfRZxqXFISk+CvZG9gveUECJv0dHRaNSoER/ny7CxvleuXOHdn4lmC1+zFkkPHvBpi06dYNawIdR5nO95n/M4/em0zPKylo2gEzgOEX4NALEe+lTLh1mtS/Bkk4QQ+ZFLP5OJEyfyu7uskP2sWbNQuHBhvvzNmzcICwtD7dq18c8//8jjpQkhCsa+uLf0rYR5p15jw/VPiElKQ9/N9zCyXiEMrdOKj2k6+ekk6rjVkfm9fW/3oYhlEZS0LamwfSeE5J7Q0FAe/D5+/JjP169fH4cOHeLDoIhmS7x/H+GrVvFpvQKesJ8wHups0o1JOPrhKCz0LVDFqQrM9c3xOjgW3TfcQ3i8ZMjg4NqeGNuosEaWfiJELVqA9fX1cfbsWV7QvlKlSggPD+cPNr1x40acP3+eb0MIUU+6Am1Mal4MK7qUhZGeACzJ5ZLzb/HHtgcoZlkBM6vNhLbWl4+fsMQwzLkzB11PdsWKRyuyPB9LqsUyS38LW8e2IYQoB19fX9SoUUMa/LZt2xbHjx+n4JdAGB3Nuz5DJIKWnh6cFy2GtqGhWh+Zmi41+U8xxPgQLcl2fedjJMLjJaUDRzUoRMEvIarcApyUlMRbd+vUqYM+ffrwByFEM7Uo7YTCDqb4c9sDfAxPwIXXoWj5v+tY0708ijqaSbd7FPqIXxgwNZxryDwHC2zHXBmDhu4NMbfmXOhq62YJfidcnYCzPmf5fKN8jfLk/0YIyd7r1695JQh/f38+37t3b6xfvx46GpLciHy/K3DQ5ClIDwri83bjx8GgcCG1OmTsO+l1xGuZ3kzs+2t8xfFo4dmCt/4yvarm4z2kDHS18UdNTwXuMSGaJ9dbgA0NDbF27VqEhITk9lMTQlRQIXtTHB5aDQ2LScb8+kQk4nlAjMw2DfM1xKm2pzCh0gSUsSsjs+5ByAMUsy7GA1wW6GZuCc4c/LILjLpudfPof0UIyc7Dhw95y29G8PvXX3/x3mAU/BImeu8+xJ07x6dN6taFpZrlg2HfV+2OtkO/s/0QnBAsXc66NXcv1h1mel9u/DLD6xWk4JcQdekCXb58eTx//lweT00IUUFmBrq81Xdc48LoUdkdHSq4ZtmGjQ3uVrSbzDLWVWzX6114GfESbqZuMkHw18Fvdq3DhJC8w2r6shwfbMgTM3PmTCxatAja2nK51CAqJuXdO4TMns2ndezt4TjrX7Ub7yoUCfEp5hNP9Ljt5TaZdVffhqHd6puITpR0eyaEKI5c+iMtXboUTZs25aUOWNcnuvNLCGHJsQbXLsC7wGX2KTyBjxO2NzPIcpBCEkPgaOzI76Qvq7MMq5+s5gGv8IqktNIF3wsU/BKiBE6cOIH27dsjOTmZz69YsQJDhw5V9G4RJSFKTkbA6DEQp6Sw5lA4zZ8PHUtLqLo0YRp0BV9uvFZyrIQ2BdrA08ITXYt8ad0+/zIEg3c8RKpQhD6b7+HAn1Up0zMh6hYAs6CX3fEdOHAghg8fDmdnZ941OjN21+/JkyfyeHlCiBLLfMc/LjkN/bbcQ1xyOlZ2LYdK+a1ktq3qVBUn2p7A49DHKGBZgLfysuCXBb4MaxUeW3EstfwSokCs7GHPnj2Rnp4OgUCAzZs3o3v37vSeEKnQ+QuQ8vYtn7Ye+AeMvSqpfEvvgXcHsObJGqxrsI5/P2WYUW2GzLYnngZhxO5HSBeJoSvQwh81PCj4JUTB5NIvycrKipc+qlmzJq/55+LiAmtra5kH24YQotmOPgnEx7AEhMWloOv629h4/VOWFmLWrbmiQ8Vsf983zhc7X+3Mo70lhHxt9erV6NatGw9+WXUHVuaIgl+SWdzFi4jaKfmcNixTBrZDhqj8AfKO9casO7MQlhSGBfcXZPneynDwoT+G7XrIg189HW2s7VEeTUpSDWxC1LIF+PLly/J4WkKImunm5Q5tLS1MPfKCdw2bcfwlHvtFY267kjDSk/14yhjzy1p/K9pXxLvod4hOican2E98Xcb433RROnS0KdssIfLELvjnzJnDqz4wrLbvsWPH+BhgQqSf2yEhCJr4N5/WNjGB08KF0NJV/VwNrItz+4LtcS3gGtoUbJPtNrvu+uLvQ894GUCW6XlDz4qoXtAmz/eVEJIVZaYghChUl0pu2PdnFTiZG0hbhdusvMnHBmf4OuHV2oZrcbHjRV4y6bLfZWliLNYtrePxjph5ayYC4wMV+L8iRL2D33HjxkmDX9ar69KlSxT8EtnzRChE4NhxEMZIsv47zpgOPRdnlTtKiWmJWP5wOS/Xl9nI8iNxtPVRNM7XOEsyr003PmHiQUnwa6wnwNa+XhT8EqIJAXBsbCzmzp2LRo0aoWzZsrh79y5fHhkZicWLF+P9+/fyemlCiIop7WqBY8Oqo1oBaz7/JiQOLVdcx7mXId/M9swey+ou48syskOf+HgC76LeYe/bvdJxwoSQ3CMUCjFgwAAsXLiQz7McH9euXUOFChXoMBMZEevXI/HztZ95+3Ywa9pU5Y4Q+/5pf6w91j9bj7l350IkFknXmeqZwkAnm+SNsclYcOYNnzYz0MH2/l5Z8lsQQhRLLv0EWf2/WrVqwc/PDwULFsTr168RHx/P17Gxv6xOsI+PD5YtWyaPlyeEqCBrE31s6VMJi869xerLHxCXko7px17gf3de4aP2WRiklMWTh83Q9OFNmd8ToxkMTMJ4EPzKxww1XWriRfgLtC/UPstdfCNdozz+XxGiPlJSUvj43v379/P5AgUK4Ny5c8iXL5+id40omcRHjxC24n98Wi9/fjj8LekGrWrYjdam+Zti7dO10IY2IpMjYWP4/W7MrKLBhl4VMGbvE6zvVQHFnczzbH8JIQoMgMeOHYu4uDg8fvwYdnZ2/JFZ69atcfz4cXm8NCFEhekItDG+cRGUdrHApMPPeO3gv/YIkJTUFXFxxRGGpOx/MbQ9dEyLIs2wKlb2qoXo5GgY6nzJPM9qMjY/1ByVHStjYOmBcDdzz7v/FMlTcefP85+m9evTkc9FCQkJaNu2Lc6ePcvnS5UqhTNnzsDBwYGOM5EhjI1F4OgxrLsAH+/rvGghtI1U4+ZjSEIIT2xVwqaEdFnfEn2RzzwfD4S1tXLWcbKqpw0uja0NfR2BHPeWEKJUXaDZFyQrf1SsWLFsi5x7eHjw1mFCCMlO4xIOuDauLko4S+6cp8eVAvC9CwnB520kLAwsZNbue7OPX9Qc+3iMtw4T9ZT88iX8hw7jj+RXrxS9O2ojKioKDRo0kAa/VatWxZUrVyj4JdmODw+eNg1pgZIcDHZjx8CgWDGVOFI7Xu1Ai8MtMPbKWKQKU6XLWc+h5h7Nvxn8ikRizDn1Co98o2SWU/BLiIYFwElJSbC1tf3metY6TAgh32Ool3t3zqs4VUGjfI3gYe7Bf2bGurQR9RC2apV0OjzTNPl1wcHBfEjTrVu3+DzL68ECYQsL2ZtMhDAxBw8i9uQpPm1SqxYse/RQyIE5432Gj9/9FraObfM11lvIP94fV/yv5Oh1hCIxz/S89spH9Np4Fy8CJQm/CCEaGACzlt+rV69+c/3hw4d5YixCCMkLBS0LYmGthdjdfDcE2l8C64ikCDQ+0BgjL43Eh+gP9GaoeOtv/Pkvic/izp2nVuDf5O3tjerVq+PZs2d8vkOHDjh69CiMjY1/96mJGkr5+BHB/87i0wJbGzjOmZ1tL0B5Y4HtmCtjpNUBvpaRWJFtkzkI7li4I0+q+F/D/9DAvcEPXyddKMKYfU+w+56kR6ONiT6sjPVy+X9DCFGZAHjkyJHYvXs35s2bh5jP6e9FIhHP/NyjRw9+J/mvv/6Sx0sTQsg3ZR4XzGx9uZXf8WcZo1kwTNSj9TcDtQL/upcvX6JatWr48EFyY6h///7YtWsX9PToAp9kJUpNRcDoMRAnJQFaWnCeNw86VorJfFzXra5MdYDMQTCbHnV5FF+nJ9BDJYdKMgmvFtVehEqOX5Z9S2q6CMN3P8KhRwF8vpC9CXYPrAxHc9nvGEKIBiXBYlkiWZbnSZMmSesENm7cmI8N0dbWxuzZs3kiLEIIUaR2BdvxLtCsZnBFh4oy6/zi/OBq6qqwfSO/3vr7dSuwQdGidDh/wr1799CkSRNERERIE1uyG9qKaM0jqiFs0SKkfB53b92/H4yrVlXYvrBAlpXLw1XwQJf95PMAD4hZ7XiGjfP979l/GFNxzE89f3KaEEN3PsT5V6F8vriTGbb186LWX0I0PQBmWODLWnsPHjyId+/e8RZgT09PnkWSJcEihBBFczNzw8xqMyEUCWUu7r1jvNHqSCueNXpshbEoYFlAoftJssduqiY/f4GAESO+eYhYK7DLihV0CHPo0qVLaNmypbR04Zw5czBhwgQ6fuSb4i5fRuSWrXzaoFQp2A4frvCj9XUQnHY5jSexYr19WOtwaGIoTPRM0LZQ25963qRUIf7Ydh/X3oXz+TKuFtjStxLMDXXl9D8hhKhUAMzExsYiNTWVX6Swi0sWBCcmJsrzJQkh5KdlHhfMbHi2ASKxCDcDZWsOE+UgjI9H7PHjiNq7Fykvv5/tmVqBc+7IkSPo1KkTr/fLvrNXrVqFP//887ffL6K+0kJDETRRUuNX29gYzgsX8NJHyuBlxEs8CXvCpy/5XeI/67nV44Exa/011v35sewzjr+QBr+V8lthY++KMNGX66U0IUQO5PJXy748Bw4ciG3btkm7PTMsAJ44cSK6deuGDRs20FgiQohSGlp2KC99EZcal6X190XECxSzyr7EG5F3a+9zRO/di5gTJyH+iZup1Ar8Y+z7uk+fPhAKhdDR0eHznTt3/q33jKg3sUiEoAkTIIySlP9xmDYVem5ueb4f4UnhuB98HwlpCWhXqJ10uZOxE0ISQ7L9nV8Jfpm/6hfCrQ8RcLUywroeFXK1WgEhRMUD4PHjx2Pr1q0YPHgwhg0bxrs+s4tFlgRr+fLlWL16NaysrLB06VJ5vDwhhPwWB2MH/O31Nw+6MnsU+gg9T/VEObtymFJlCjwtPOlIy5kwLu5za+8+6RjDDAIbGwjDJa0x30OtwN+3YsUKDP/cbdXAwAAHDhxA06ZNf+t9I+ovcuNGJNyUlMcyb9UK5i1aKGQ/Zt2ehfO+52FtYI22BdtKb06yevAuJi68rBEbzsKCXtYFmo0DZq3ArJv0z7IzM8DegVVgZqgLA10KfglRVXIJgLdv387H//7vf/+TWV64cGGsXLmSd41m21AATAj5EXdro5/alpWmGLnnMbpXdkdlD+vfOsBft/JufLaR/3we/hymeqa/9dzkB629z57xLs6xrLWXZZbNIBDApHZtWHbsgNizZxFz4GCODmXUzp1wnDmTDvtXx3nmzJmYOnUqnzczM8Px48dRo0YNOk7ku5KePkXo0mV8WtfdDfaTJ8v1iMWkxPChKXeC7mBgqYGo515Puo5lbWYBMGsBDkoIgpOJk7TUEQt+2ZjfzEmwMifG+lEQHBqXjOvvwtG2nItMEEwIUW1yCYDT0tJQuXLlb66vWrUqjh07Jo+XJoSomQ29ZLMz/8i0oy9w/GkQTj8PxvRWxdHNyz3X9mVa1Wm8dBJjZ2QnXc7GC7MLM9bKQF2jf6+1N+bYMUSz1t7Xr2XW6Tg5wrJDB5i3bQtde3u+TGBujqQnkjF+MkQipHr78J9aBgbQdXGGRfv2v7Fn6ocNSRo9erT0RrStrS3OnDmDsmXLKnrXiAqMwWclj5CeDujqwnnRYghMcq82dHJ6Mj7EfEBx6+LSZfoCfex4tYMHtreCbskEwKxmb0GLgihlW4qXNsoIflmgmxH8ZgS62WWH/lYQHBSThG7r7+BjeAKS00To6pX33bsJISoUADdq1Ih/kQ4aNCjb9adPn0bDhg1/+3VmzZrFSy0VL14cz58//+3nI4SovhLO5tATaCNVKMI/h57jdVAcprQoBl3B75c9tza0xl/ls9Ywv+R7CSMvj0RRq6L8gsrDnDLd/1Rr79OniNqzF7GnTmVt7a3DWns7wrhaNWgJZLscGpYpA8/jx7N93pD5C3gXTXFyMpzmzIVhyRI/81artfT0dAwYMACbN2/m866urjh37hzvpUXIjwTPmIE0Pz8+bTdyJAxLfAlUf9fWF1ux9OFSaEELN7ve5IEvY6BjgHL25ZCUloT85vllfsfG0IY/Mlz0vZht8JtdduiGvg3RKF+jLPvhF5mIrhtuwy9S8nn0LCAm1/6PhBA1DYBZl6qOHTvykkdDhgxBgQKSJDKsHBLrAs1qBO/ZsweRkZEyv8fGBeeUv78/rydsbJx7dx0JIaqvfXkXeNga44+tDxAen4Jtt33wPjQeq7qVg6Wxnlxec/ur7fxnYEIg7I0krZPk+4SxsV9ae9+8kVmn6+QEi44dYN6GtfZ+aWn/GVY9uiNy61beShW5aROcFy+it4S1riUno0uXLjh8+DA/HoUKFeLBr5sCkhcR1RNz5Ahij0p68LGbUlZ9ev/STS+WTJD1miloWRA1XWrK5F9gLbjMk9AnvHtzhrX112bJ2J+djIC2rlvdbFt3M4LgbwW/H8Pi0W3DHQTFJPP53lXzYUrzYj/9/ySEaFgAXLRoUf7z2bNnvKxCZhlJZYoVy/phwrJP5tSYMWN4N2v2O+E5SIJCiDqIv3ARqXFxQOtWit4VpVbOzRLHhlXDgK338TwgFrc+RqDlyuvY0LMiCjvk/tjdZXWXYeernTDRNZHJLpoiTMFlv8uo71Y/RxduGtHa++QJT2gVe/Ikb52VEghgWrcOLFhrb9WqWVp7f5auoyPMmjRB7LFjiD1zBrb+o6Dn4gxNFhcXhzZt2uDChQt8nnV3Zj2y7Ox+7SYD0Syp3t4Inj6DTwusreE0dw60Plf5+J6MUpiZDbkwBJHJkbz7cuYAuKJDRXQu3Blejl4oai25lszwM5+h2QW2XwfB2W3zNiQOXdff4TdPmYG1PDChcREa2kKImpFLADxlyhS5flhcvXoV+/fvx6NHj3iWaUI0QfLLlwgeOZJPpxQpDN2SJRW9S0rN0dwQ+wZWxdj9T/iYYNaVre2qG1jWuSzqF8vdVlozPTP8WTprvdTD7w7j3zv/Ip9ZPqyqvwqupq7Q2Nbeo6y1dy9S3r6VWafr7AwLPra3DXRzORCz7tObB8AQChG1bSvsJ06EpoqIiOCZne/evcvnWaIrlovD3Nxc0btGVIA4NZWP+xV9Lj/Ggl8dW9vv/s6L8Bf47/l/vETRwVYHpd2U2fVhJYdKOO19GsEJwTK/Y2lgiX8q/wNFeB4Qg54b7yIyIZXPj6xfECPqFaTglxA1JJcAeNq0aZAX1uLLgt7+/fujJAUARIOErVolnY5csxYmK2WzrJOsWI3GFV3KooiDKRaefYvENCFkCxvJD2v1OPhekqGYdeljXfs0Cfv/Jz1+jGg2tvf06Wxae+tKWnurVc1RK9KvMChWDEZVKiPx1m1E79sPmyFDIDAzg6YJDAzkeTdevHjB51kgvG/fPhgZ5TzDOtFsocuWIfnz+WPVuzdMvsoU7h/nj9jUWBSzLibTA+aczzk+fS/4HprkbyJdN6TMEJ5PgWVsVgas23PX9bcRm5zO58c3LoJBtanMHSHqSi4BsDytWbOGjyE+f/78T/1eaGgowsLCZJaxusQZWavZQxkTlbCAn/0kmo3VP40/L+m2yCRcuID4Z8+gX6SIQvdLVQyskQ+eNkbwjUxE7YJWefb3vr7eehx4dwC2RraAEEgTpklLelzyv4Rm+Zv9Ui1KZf6cEMbEIu74ccTu34/Uz5+xGXScnWHWvh3MWrWSth6ls6EvPzH85WeZ9+jBA2DWchWxaxcs+/aFuvneOfDhwwce8H769InPd+rUCRs3boSurq5Sfu+R3JNbnw2JN28i8j9JCTj9okVhOWyozLkz7NIw3Ai6gTK2ZbCxgWQ7poh5ETgbO/NszpZ6ljK/42wkGY6gLOego6kuqnla49SLEExuVgQ9K7spzb7lJmX7viDKI13Jz43c/nvUUbUuXKx79eTJk3nJhp+xatUqTJ8+Pdt1MTEx/LmVDTsJ2Zgt1pKio6NSbxXJZfHLV2RZFrx8BUxmSsZjkR8raydAWTtTmb/1d2GJMDfUgZ2JfJJjMU3sJK0emV9387vN2PFxB9Y+WYulXkthY/Alg6kqfk6w1xY+f46U48eReukykCrpQsgJBNCtVg36LZpDp3x5iLW1wfOp5tFnrrhoUWjnc4fI2weR27ZD2LQptHR/76aDsvnWOfD69Wse8LIbwEzPnj158sjY2FgF7i3JK7nx2SCKjETshIlI0gMeF9bDux4uaBP0Am4mX5Km2enaSeuj+4f4w1DHULpuU7VN0i7Eynidldk/dZ3RsKApquQzVvp9VeXvC6Kc0pX83GCxWm5Svv/hd7CSRyxT9K+M+x08eDA6dOiQpQW4devWfAyUtbU1lPFkZF8c7P+sjCcjybvW36jr17MsT7t2DSZhYdQK/ItCYpMx5uhziMRirOpaBmVcLZAXeM3giDt82sbIBoWcCv3WGDNFfk5IWnuPfW7t/SCzTsfFBebt2sG0dSvo2Px6gJ8b9Pr2Q+iUKRCHh0Pv7l2YtWwJdZLdOXDnzh1eiSEqKorPjx8/HjNmzKDxjBrkdz4bWG8VHS0Bgv6ZBHFUFKKsgCXNRUDUJRRJKo+y7l/qRbcq0gru1u6oYF8BTpZO0NaSz5CG3PbYLxrFncxkSuQ1t1PsZ5W80XUlUdVzwzyX81Uo3//wG1gJpXXr1mHp0qV8PFPmkg6sWdzb2xtmZmbfLKXEslx+K9Ml6wrGHspIIBDwE1FZ94/IX/C6dd9cF7V6DVxXraS34RecfumHkDhJps9uG+9jbtuSaFvOJU+O5Z4We3D4/WG4mblBT+9L63NAfADPGt2uYDte91IZPyf42N6HD3lCq9jTZyBOkRxDTkcHpvXq8RJGxlWqyG1s77ew74IbN27wEnvsu6BatWr8mFi2boWIFcshDAtHzNZtsGrbVm0CwYz/Mxsa5O7ujlq1auHKlSv85m5CQgLfZsGCBbxyAtE8P/vZcPDdQex9sxeJ6YnYFNUWiTdu8OWFqzSFndFjPnwjNj1W5vnKO5bnD2XRf8s9+ERIknV9S3xKOi9zZG+qj5sT60GgrR6fBzlB15VEFc+N3N4nlQmAAwICIBKJMHz4cP74Wv78+TFixAgeIBOiTpmfM4/9/Vr8xYtIuHMHxl5eebpf6qB/DQ/o6wow/egLpKaLMGrvE7wJjsO4xkXkfjGkJ9BDx8Idsyzf8GwD9r/dj/+e/YdDrQ7BXF95MvQKo6MRc/QoovbuzdLaq+vqyoNeizZtFNLay4LAuXPn8jrzISEh0uUODg6898+ECRNg1a07wpYu5TWHE27ehEm1alBl3/o/W1hY8G5sbCyXtrY21q5dy5NGEpIZS1D1NOwp7Izs4G7mLl0ekRTBa/Qyr9YtAusbp+viAsdp07BeFAZnE2foC/SV+mCy4PddaHyOtg2NS8HLwFiUdFGez1pCiPypTABcokQJHDp0KNtu0ezLftmyZfD0pIx9RH0zP3+L35+D4HH4EPTcv1zEkJzpUdkdnrbGGLzjIaIT07D26ke8CYnD8i5lYWaQt3dAWabox6GP+TTLpPqt4PeM9xnUdav7zeRZ7Hku+l78YR3MHLf2PnjAg9441tqbeWwva+2tXx+WHTvAqHLlPG/tzRwIstbOkydPZmnVZYEhyxvBugPv37wZ4WvXQpyUhMiNm1Q6AP7e/zk6Opr/ZMt37NiBzp07K2gvibJKTEtE7b21kZSehP4l+2NEuRHSdZUdK+OC93kUuuELrbRo/nfuvGghBKam8EDu11BXNCcLQwp+CdFAKhMA29jY8C/8r2W0+Ga3jhB1bv3NwC7oP7VrD9d162BU7su4LJIzVT1tcHRIdQzYep8Hv5ffhKHNyhvY0Ksi8tsY59lhZAHtvhb7cOrTKRSwKCCz7lXEK9wIvMFba/65/g8aujfE3JpzswTBLPidcHUCzvqc5fO/GgSnR0Uhlrf27kPqh69ae93ceNBr3rq1wsf2MqwVlAWCGQF7ZhnzJ06cwMI1a9C/XTtEbd+OhBs3kPzmDQwKF4Yq+t7/OQNbnlHpgGgm3zhfnPh0Ah9efsDi2osh0Bbw5Ua6Rshvnh8vI17iTpAkH0GGkrYlsfiWJ2KOPOXztqOGw7B0aagrIz3JMSGEaBaVCYAJ0TSRO3fmeFtRfDx8e/eG07y5MGvypdYiyRk3ayMcGFwVI3c/xvlXIfgQloDx+59iz8DKeTpWVEdbBy08W2RZvvrJalzyuwQrfSvUc6snCXCvggfBmYPfyTcm83UsQGatxD/d2nv/Pg9648581dqrqwvT+vVg2bEjjLy8FNbam11LKOsCzN6jbwWCGRYvXozS8+fDU0sLWmIxHk6bDv82rfnQGlV6sEQlZ89KbnB8Dzsm7Niw5FfKOJ6L5C52/rNxu8a6X27aPQx9iPVv1/Pp11GveTmiDANKDoBQLERFh4oyzxNz/ARiPve2YzW0rfv3o7eKEKJ2VD4Avnz5sqJ3gRC5sGzfHkmPJV1ipcSsbmo6dAQ6wOe4TBQbh/SICB6wBPw1Cqn+/rDu319tkvzkFRN9HazrUR6Lzr3Brrt+WNSxtFIcQ9ZdkSXHYuq41cE/lf/50sp7FZhZZSbSRemYdHMSzvme+2br8Pdae2OOHEE0a+39+FFmna47a+3tKGntVcJM+Sz5U+bxr9/DsiG3HDAAS5yc0MjUDCYPH2LY/n0IVdKah7kREAUHB/NjVLt2bUXvDpGjqTen8uR5NV1qYma1mdLllewr8Z+sFm9kUqTM79R3r5/leVL9/BA8bRqfFlhYwGnuPKW52UUIIblJ5QNgQtSVYZky8Dx+PEuLF6tPyMp2ZW7VYUl9/IeP4C3BYYsWI83PHw5TJkNLCVPZKzNtbS2MbVQE/ap7wMpYT7bOrUgMnUzlMvIK667IukZf8r2EwlaFeWDLW36vggfBbyLfwEHfAXfC7+Q4+OWtRffu8aCXt/ZmLjCvqwuzBvVhwVp7K1VS6gtglu35Z22KjOQBsK6WFrpZWGJJeFiu7xe7ccISUMnjwWr4sozP8jxGRDkFxgfibvBdNHBvINPSG5oYisjkSNwLviezvZOJE7bX3I5iLsV+2AuAfQYEjBnDv0MYxzmzoWuffeUMZcYSGqaLvt8bhBBC6OqYEDVgXLUq3HfugN/AP5EeFMRL1KQFBsJ56RIITEwUvXsqJ3Pwy2y77YOjjwOxpkd52JjkfQZUVleznns96TwLcOfUmIPbQbfhE+fDH3Vc6kiDX/84f+x7uw9WBlZ8HLCDsYO0tTf68GHEsNbeT59kXoMlUWNBr3mb1tD5Rjk5ZfOtsnffwjIiV6pUCaJp06H9+jX6u7piwNkzEBgb51qAyoJfefYcYL2e6tSpI7djRJTTzcCbGHhuIJ9mf9estTcDG+5gqGMILwcvCEVC6Vhfxt7QPkfPH7bif0h+Ihn3a9mjB0x/4hxTBmFxKdh5xxc77vjwEkeEEPI9FAAToiYMChVCvj274f/nIJ5AK+H6dfh06w7XtWug6yAJgMjPe+AThenHXvIW4JYrrmN9rwoo7qT4khlxqXEQC4XSeVHcl7IfH2M+YuPzjXy6tG1pmD735TdF4s6exYpGQjxqqYX8IdqYdEAAswYNeOBrUKkCDr4/CKv4RyiqV5S3Hik7Dw8PWHpZIup+FPDlUMgSAOblzGHoZ4g+ffrwlrC4YUPhP2QotBITYf/sGax69oSqYLWN7e3tERoa+t1xzywIZ9ux7YnquBFwg4/314IWH+6QoZRNKQi0BHzc7oOQBzIBcIdCHfjjVyXcvo2I9ZKxwvpFisBuzGioiqf+0dh8wxvHnwYhVShS9O4QQlSE8vZtI4T8NF07O7hv2wqTz3fvWc1T746dkPzqFR3NX1TcyQytykiCwcCYZLRffQsnnwUp9HiyhFez78xGnDABhf3E/HEl5h4fG8zWJaQlQEdL0goUP3gsfHv1QuyJE7ybY7QJEGekhbR8Tih45TKcFy+CcWUvHlDPuDUDIy+N5GWUMjv64Sg6H++MIReG8DHJmT0Le8a7YUcnS8rv5JVHjx6h1h+14DzIGa4DXXmgm4UAfJ3rEFe0HNNS2g2U/X1klA2L3LwFYhUaB8z+D0OGDPlh0i+2nm1HCbCUV3xqfJa/p9Pep7HnzR7+N8f+ljOY6JlgetXp2N1sN4aXHZ5r+8B6hQSOHcdOGGgZGPCSR9r6yl3nN00owtEngWi76gZa/u8GDj4KkAa/7PPa3ky5958QongUABOiZrSNjeHyvxWw7NaNz6eHhvKW4PgrVxS9ayrJQFeARR1K45+mRaGtBSSlCXnd4CXn3kKkgLFmmUsdVX4lwtSdQv5g02zZ2MN/oNiKs9i5QIiNS9Jh+cKf/54WG9vbrBkaV+6FjoU6omH5TjJdndkYwgysi2VmPrE+eBHxAtcDrkNfIHtxOe7qOLQ/1h6z786WWf4x+iPGXBnDA3X2+5mxYJkF6T8K4r7l4MGDqF69OrzPeyPmbgzMK5nzQFdLRytL8MvWGfkZYcnQJdJVbFyzVZ/ekuMZGMhbxlXJhAkT0KxZMz79dXfrjHm2nmWAJsonLDEM3U50Q/Xd1Xld78wqOVTiwxiK2xTPclOpVYFWfHnmLs6/g/39BU38G+lhknHw9v/8DX1PTyh78Ft30WUM3/UID30lx0egrYVmpRyx/88qOD6sep7XcCeEqB7qAk2IGtISCGA/6R/oubkiZO48iBIT4TdoMBwmT4Jlly6K3j2Vw4KKATU9UMDeBMN3PkJcSjqWXXiHN8FxPFu0sb5Onge/1SNtMfhoEHQ+9/obflTE3/cLhe4jQU+E4UIRTNIAvfz5JWN7W7eCjqUlenzjud3M3HCu/TkeCDsZy3Z/djFxQTWnajzb9NcX3xmBs7WBbJZovzg/6cV9Cw/Z0k4sWGb1jj3NPXG49WHpcjZ+ccWjFTwA93L04km/vr5gZzVw//77bz7PxtyOLDgSfq5+OI/zMDAwwLtl7/i6jODXNdEV+8fuh5G+kcxzmbdqhbBlyyGMikLExk0wbdJEKbJ+5wRr1T106BDmzZvHSx2xbM8ZWLdn1vJL5Y8UL1WYiidhT/jNoE5FOkmXs/P7U8wn3p2ZJbVqU7CNdB1LcMUeBjoGct+/qO07EP+5koZp48awaN8eyojdaGQJChldgTYq5rOCX2QALI100dXLDd0ru8PR3FC6vbu17N/69/zMtoQQ9UEBMCFqil3MW/XqBR0nJ97FTZycjODpM5Dq58/HeClzdl9lVaewHQ4NqYr+W+7DOyIRp18Ew3t1AvYMrAJzQ/m3OrCuySz4rW9ZGX3nXZcGvwybHnYoDeKW2rhdVBt1jcqhZeNhMKpYMUeBHatBzJJlZSTMyoxdoGe+SM8ckK6st5IHwc6mzlnWu5u58/IrVoayLcoZJVlYt87MolOi8d/z//j0hEoTZALgLc+2YOntpYgXx0PbQJtnwd29ezeaNm2Ks5/OIjw5HI9LPUbXnV15tvRX6a/QwK0B5tWal21WbG1DQ1h27YrwlSuR/Pw5r4HMjpWqYEHwpEmTeKB75coVnhna3d0dtWrVom7PSoLV797wbAMfz9s4f2OY60tyB7CbSO0KtePTmcfyMnkR+DLJr18jdP58Pq3r5ATHGdOV6gYQa+k98yKYj+9tVNyB34DM8EdND1T2sEbL0k68h87XNvRSnb9jQohiUABMiJpjSY50t27hLcDCiAhEbtyINH9/OM2fB22DvLnYUicF7ExxZEh1DNn5ENffh6OYkxnMDPLmo5RldGYKLTyC5GzyvbAgeOwrT3zo0RtNerWV+/6wC+YKDhWyXVfLtRZ/ZKdb0W6o5lwNFvoWMstjUmKgo6WDdHE6rA2/tCizhE8r/luB9LLp0LfXh5ujG44dPYYSJUrw9YseLEJgQiAcjBzwNFGSybaeW71vBr8ZLLt24cl/WA1t1gqsSgFw5kCYBb3ZlUcj8icSi7Dt5TbeklvVqSo/tzNUtK/IA2AxxHgR/gJVnatK142uoLhEU6xHUMCo0ZLyZ9racFq4AAIzMyiDiPgU7L7nh223fBAcm8yXsZ99q+fnXZ2ZIg5m/EEIIb+KAmBCNIBhqVI8QzQrk5T64QMf8+gbEgKXVSuhYy3bdZX8mLmRLjb3qYjNN71597u8bDmp5mcEv/OXvrle+OYd6mgXhTKr45Z9iRUPCw886PGAJ+TSE0hKUT1//hwtWrRAhGUETKNNYe9kj4u3L8LOzk7aCp3RDTvjdzK3NLOxxux5s8POffPWrXmG7PhLl5Dy8SP0PbLflhB2rrGuy/nN80v/5lmJsr1v9sI3zhdpwjSZALisfVksqLWAB8KZb+goWsicuUj9+JFP2wwdAqNy5RS9S3gRGMNbe488CeS1fDNYGOmiRWknpKQLYaRHl6yEkNxBfSAJ0RB6Li7It3MHjLy8+HzSkyfw7twFKR9l68GSnNERaKN/DQ+ZLnhJqUKsufIB6XIoxyEWiRC5Ywf8/hz0w23DV62CqmIBBesqyuqanjx5ElWrVoW3tzfiHsWhnqgebk29JQ1+MxxqdQiVHSvzIIS1/LLHBd8L6H6qO9oebYuVj1fylrrsWPWWJMNiIjdtlvv/j6imq/5XUWdvHbQ60oqfZ5lVcqwER2NHPo4+M3YON87XWKmC39jTpxG9bx+fNqpQATYDJbWFFSUkNhkd19xCs+XXse+BvzT4LeJginntSuL2xHoY37gIBb+EkFxFATAhGkRgbg639et4AiAmzc8P3l26IPHePUXvmlq0Do3Z/wRzT71Gr013EZ2YmmvPnfLuHXy6dkPIzH+BTLV/vyXu3HmVLn3FjuWSJUt4y29cXBxfNmfOHGzZsgX6X5VoYd2llzxYgttBt9HQvSFvcWMPlrQrOCGYJxp6HfGaB9bZ0ffID5O6dfl0zJEjSI+IyIP/IclNLNla5pJBX2Prvs62/C3snGEliE58PCGz3N7IHhHJknODdXfOjI1XP9PuDCZVngRllhYQgKDJU6TfBazrM0ucp0jWxnrwi5KUgmI9nBsXd8DuPyrj1Iga6FTRLdsxvoQQ8rsoACZEw2jp6cFx7hzYDBvK50UxMfDt2w8xx44petdUWmxSOj6FJfDpG+8j0HrlDbwPlQRvv0qUmoqw5cvxsW07JD1+/FO/G7VzJ1RRamoqBg4ciFGjRkEkEsHIyIiXPWKlf77uap45KzYLfufWnMvH/LLHinoreCZpRgTRdwMk688lkdhY4KgdqnncNBULbFm5rYwa2F/LOEfYNjkJgsdfHY9/rv8jTcaWoaBlQZ7N/G+vv/nNlcxYaTBlSiCVHVbrOmDsOIg+31BynPUvdB2yJryTp1dBsZhw4Cn/mbknzaDanhhYywNXx9XBmh7leYIrZT+ehBDVRgEwIRqIXVzYDhkCp3lzWRYdngyFZYoOX736l2uzajo2Lnj/oCpoWlJyUcmyRLdeeRMXX4f80vMl3r+PT61aI3zVauBzshqzpk2h5+EBvQKeXx6entDO585/Zl6urCVNvicyMhKNGjXC+vXr+byzszOuX7+ONm2yZqDOnBU7c/CbgU2vrr+ar2PdV9m2DDu/J12fxFv4Ms51wwoVYFCypPTGgSgpKQ/+tyQ31HWry99jdh58HQR/fYOEbZvRyjvnzhy0OdIGD0MeyjxfRQdJIrSg+CA+fjwD60Ewu8ZsdCnSBU4msmXCVAH7HEl6KPm/WnTpDNP69fPkdYUiMU4/D0bndbfQZNk1nuBqy01vmW16VsmHiU2KwsWSShIRQvIGZRQgRIOxrtA6Do7wHzYMothYXhc11dcPjtOn8ZZi8nNYkpb/dSmHFfbvseT8W8SnpKPflvt8DNvAmh45atUQxsYidOEinpgpg37RonCcMQOGJSVZjzNjJX/UIQPwmzdv0Lx5c7x//57PV6hQAUeOHIGTk9MPs2KzwCa7bM9sGQuMG/o2lG57xucMjnw4wh/hSeHoVbwXf1+s+/ZBwF+jIIyORszhw1QvW0VkvMe4Ch7osp98nnVN/hz8VnGsInODhJX82vla0tJ/J/gOytl/SQLFyn2x0kTFrIvx7dRB0r37CF+zhk/rFywA+/Hj5f6abAjInnt+2HrLBwHRX24osY/AhFQhv/lErbyEEEVRj093QsgvM/aqhHy7dsLvj4F8jFjMoUNICwqCy/JlSlMaQ5Voa2thRP2CKOxggr/2PEFSmpCPC34bHIfZbUt+d0xb7NmzfJxvelgYn9fS14ftsKG8nrOWCge3P3L+/Hl06NAB0dHRfL5jx47YtGkT7/78IxmB7bewoCfzNmzeysCKX4C38pSMhWdMWbkwZ2f+NxC5eQssOnZU+PhI8mtBsPCKZJw8S4TGavC+iXzDy2tlsDG0QRGrIryWtLOJbP1qNv/1MlXGhriETJwIiET888Rp0SK5lr/zi0zEqssfcOiRP5LTviSeMzXQQeeKruhROR/crKmllxCiWBQAE0Kg7+kpKZM0eAiSnz5F4u3b8O7aFW5r1/KggPy8xiUc4WZljAFb7/MWkGNPA9G7Wj6UcpGtfcukhYQgeOZMxJ+/IF1mVKUyHKdPh56bbGZZdbNmzRoMHToUws/JvaZOncof8modYhmiK9hX4OVsLAy+vBdigTaiejaByZwNSPXx4WWR8qqbKPl9LNCdWmUqT3rGAl+mkGUhvI16i8iUSHyM+QhPC0/p9rub7YZAW71vcLCbPIkLFiI9RDIMw37iBBgUKiTX12S9Xnbd/ZIlu4CdCXpXzYc2ZZ1hrE+XnIQQ5UBjgAkhnI6NDdy3bIZpA8lFf+r7D/jUqTOSnj2nI/SLijmZ4cjQaqiUzwqzWpfMEvyy0kZRu3bhY7Pm0uCXZWd1nD0bbhs3qnXwm56ejuHDh2PQoEE8+GXZnXft2oVp06bJvWskK7NUxq6MzLKD7w6iH7Zgc1MDJOsCERs3yXUfSO5g5a12vNqB5oeaY92zdTLrrA2s0b1od6ystzLLuF11D36Z2H37kHb9Op82qV8PFp065erzxySm8fG8aZnKvhV1NENVT2vUL2qH7f28cO6vmrxWOgW/hBBlQrfjCCFS2oaGcF66FKELFiJy82YIw8Ph07MnnBcthOnnUjHk59iY6GPXH5UhYDU+Mgl68hIp82ZJE9MwZs2awf7vidCxVp66ofIQExODTp064cwZSVZee3t7Pt7X63ON6ryWKkzF/x79D2KIcb+EPjqdT+bvC8u8bVhGNlAmyoUlpzrncw4B8QHY8XIHL4vFWvkZ1hJsqmeKKk5Vsh0jrs6S375F+PwFfFrH3h5O//6bazeW3oXEYfNNbxx8GMCHeFib6KF5qS83GLb0rQRdAbWvEEKUF31CEUJksHGP9hPGw37yJJ55WJyUBP8hQxG5dRsdqV+UOfhlpY3ezFuM8C4dpcGvjpMjXNeu4Tca1D34/fjxI6pUqSINfkuXLo27d+8qLPhl9AR62NhoI8rZlcPEihNgKJYESxGbNitsn0j2PkZ/hH+cv8yyHkV7wFDHkAe/9d3qS2tBfys7tLoTJScjcPRoiFNS+Ge4/Zw5EFhkHXrxs9mcz78MQfcNd9BgyVXsuOPLg1/mwqtQmW0p+CWEKDtqASaEZMuqWzfoOjkhYPQYiBMTETJ7NlL9/XgGUUoO9GsSHz5E0OTJEH34yD98hdDC44oN0WLZdJhYmav9mXjt2jVe0ohlrWZatWqF7du3w8TERNG7Bg8LD2xuvJm3kgU2v8uTwcWdO4ftt1ZBYGmJjoU6akS3WWUlFAnx1+W/cMnvElp6tsSs6rP4chbYnvx0EknpSVnKYWWXHVoTWoJD5s1DyjtJNnWDHt1hWLHCLz9XTFIa9t2XZHP2jUyUWVe3iB0f31u9gM1v7zMhhOQlagEmhHyTaZ06cN+2FTq2tnw+aus2+A8fAVGi7IUQ+T5hXByCpk+HT9duSP3wkS8LsHLGqFrDMMm5AdpvfgyfiC81R9XR5s2bUa9ePWnwO27cOBw8eFApgt8MGV1ErXr35j9DTUVY9nodZt+Zjck3Jit47zQbu/mQUZbo9KfTiEmJyVEtaF4G63NLcEYtaHUWd/48onft5tMGZcvCoEfP33o+Fvz+e+KVNPg10ddBn2r5cGlMbWzsXRE1C9nyzPeEEKJKKAAmhHyXYfHiyLd3D/QLFuTz8RcuwKdnL2mpHvLjC1KW5CrjopSXNho1ChXPHIVLFUnLzLvQeLRaeQM334er3eFkCa5YsNunTx9es5jVKmYljubNmwdtbeX8CjIoXAjG1asjxhgwjRNK68OSvJGYloidr3bicehjmeV9ivdBh0IdsL/lfp7IjGElrhbWWvjN1t2MIJht86OSWaqOla8L/GcSn9Y2NYX93DnQ0sl5rwWRSIyXgbEyyzpUcIWhrgAeNsaY3rI4bv9dD1NbFEd+G+Nc339CCMkrynn1QQhRKrqOjnDfuQPGVavy+eTnz+HdqTNS3r1T9K4prbSQUPgPGw7/ocOQHioZI2fk5QWPI4dh88cAmJsaYX3PChhYy4Ovi05MQ4+Nd7H1ljcvX6IO4uPj0bZtWyxYIEnGY21tjQsXLqD35xZWZWbdtw8KBgKL1qdjakpjVHSoKLP+63GoJHekCdPQ4nALzLk7B2ufrpVZV9K2JKZUmYL85vlllrPA9ntdm7+uBa2OxEIhAseO43V/GceZM/gQlpyIS07DphufUHfRZbReeQNhcSnSdeaGujg6tBrOj6qFXlXz8RZgQghRdRQAE0JyRGBqyhM1WXRoz+fTAgPh3bUbEm7doiP4dWmj3XvwsXlzPoaUf9Cy0kaz/oXb5k3Qy5fvyzHV1sLEJkWxpFNp6Olo80QzU468wMYb3ip/TH19fVG9enUcPXqUzxcrVownu6pRowZUgVGVKtAvUgQGaUCprbd58rIM76Le8SBt4rWJiEyOVOh+qhtdgS7quNbh0z6xPkhIU++hAbklfO1aJN6/z6ctOnSAWePGP/ydj2HxmHb0BSrPvoDpx17COyIRqUIRdmeq48sUtDelbs6EELVCATAhJMe0dHXhMGMGbP/6i8+L4uLgO+APRB88REcRQMrHj7xsVPC0afzYMGZNm8DzxHFYtGv3zTIkbcq6YO/AKrAz1YezhSFal8lZy42yun37NipVqoQnT57w+caNG+PmzZvw8JC0dqsC9l5Z95G0VLNyYLHHjknXLby/EOmidJ58KTghWIF7qbpYL4eHIQ8x7OIwnPY+LbOuV/FeWFx7MY61PgZjXepqm5PkeuErV/FpPU9PXkrte92cL78JRe9Nd1F30RVezighVdLN393aCFOaF0Oval9u0hFCiDqiviyEkJ8ODGwG/gFdF2cETZgIcVoagv7+G6l+vrAdPjzXak2qEnFqKsI3bEDE6jX8eDA6jo5wmDoFprVr5+g5yrha4Niw6jzrqrWJPlTVrl27+HjfFFaCBcDw4cOxaNEi6Oio3teNWZMmCF28BOkhIYjYtAnmbdvy83t61emYdWcWXE1dUcy6mKJ3UyWlilIx8tJIRKVEITQxFI3cG0k/O9hxZQ/yY8LYWASMGcMG2/MblKyUGqvn/i0TDz7Dnvt+MstqFLThia1qF7Kjll5CiEagFmBCyC8xb9aMd+kVmEuS0bDgL3DceJmuopog8dEjfGrXDuHLV0iCXy0tWPboAY9jx3Ic/GawNzNAIXtTmWUrL73H6efK38ooEokwdepUdO3alQe/AoEAq1evxrJly1Qy+GW09PRg1bMHn059/wEJ167xaQdjByyvsxyjyo+S2f5p2FOsfbKWj2MlWRNbJacnS+f1BfroUqQL9LT1+E2EFOGXcack563oQVOmIj0wiM/bjRsHgyJFZLZJTRfJzDcu4cB/GukJ0KOyO86Pqolt/bxQt4g9Bb+EEI2hmlclhBClYFS+PPLt2Q3fgQOR5uPLu4mmBwXB5X8rILCwgDoTxscjbPESRO3axa5E+TL9QoV48hnD0qVz5TWOPQnEgjNv+PToBoUwtG4BpWxhT0xM5K2+e/fu5fMWFhbYt28f6tevD1Vn0bEjwlethighAREbN8GkZk2+nL0POlpfvkJZPdppt6bx8cEXfC9gZ7Od0rI9mowFvRuebcDuN7sxqPQgdCvaTbquW7Fu6FC4A2wMqY7sr4jevx9xpyXdx01q14Zl927SwPjau3BsvP4RoTGJODzky/GtVcgWs9qUQPNSTjzBFSGEaCJqASaE/BaW1Cnf7t0wLFuWz7NELN5duiLVT7abnTqJu3iRlzaK2rmTB7+spdB25EjkP7A/14JfxlhfIM26uujcWwzd9QhJn8frKYvAwEDUrl1bGvwWLFiQjwFWh+A3I/mbRXtJ4rfE27eR9OJFttuFJ4ZLs3fXcatDwW+mDMynPp3idXu3vdzGx05nMNMzo+D3F6V8+ICQ2XP4NKvT7jhnNhJThdh2yxv1F19Bz413cfltOF6GJOKxvyQzNMNq9nbzcqfglxCi0ej2NCHk9z9ILC15d+jACRMQd+o0Uj994mWSXFethGGZMmpzhNNCQxEyazbizpyRLjOqWBEOM6ZDP79saZbcwLolHhpcFf233odPRCJOPA3C+ZchcLIwhI62pCWYBV2s1i7rcpy5dZgltNnQS7Z0T257+PAhWrZsiYCAAD5fp04d7N+/H1ZWVlAnrBt05PbtfJxl5KbNcF4oKeuUmaOJI/Y234v97/ajXcF2MutYpmhLfUulbL3PTexcfBT6CO5m7rA2tObLBNoC9CzWE4ffH0bvEr2hBfU+BnlBlJKCgNFjIE5K4kMuBJNnYM6NIOy9dxdxKV9uMBjqaqNxEStYG+spdH8JIUTZUABMCMkV2vr6cF60CGEuLohYvwHCyEj49OoNp/nzYdaoocqXNmLdDUMXLJRmd9Y2M4Pd2DGS7M7a8utMw0qQHB5cDUN2PsTNDxFISRfhU7jiS8McPHgQPXr04N2fmQEDBmDlypXQ1VW/bpW6zs68rEzsiROIPXUKdqNH8drYWbYT6PJxrV93Ae5+sjuvXfuP1z9wMlHtDN/fEpsai0HnB/Fx0ANKDsDwcsOl69oXao+OhTuq/Q2AvBK6cBFSXr/m04+qt8Q/lxIgFn+SrnexNESvKvnQpowD0hNjYW1lpMC9JYQQ5UNdoAkhuYYFgnajR/MWUQgEELOWipEjEfHfRmn3UFWT8vETfHv2QvCUqdLg17RxY17ayLJDB7kGvxksjfWwpW8lWCjBmD32Ps6ZMwft2rXjwa+2tjaWLFmCtWvXqmXwm8GqTx/JBGsF3rotx7+36fkm+MX54ar/VVzyuwR1ZaprCnz+E2etvZm7OrNWYAp+c0fcpUuI2iY5/wxKl8L7Zl0yUhCgqqc11vUojytj62BATQ/q5kwIId9ALcCEkFxn2bEjdB2dePDLkgeFLliAVH8/OPzzD7RUJCMwK20UsXEjT4DEphkdBwc4TJkC07p18nx/dAXasDXVR3SS4jIMs+zOrKV32+cLcFNTU+zevRtNmzaFujMsURxGlSoh8e5dRO/dC5vBg/j44B/pXKQz/OP98TH6IzoX7gx1wLp07369G03yN+Et2wwLcP8o9QeehD1B16JdaQx0LvOLTMS+M49Qb9EEsA7N2iYmvMdNTwNLJIm00LtqfhR2+PH5SAghhAJgQoicmNSoDvedO+A38E+kBwcjetdupAUGwnnRYghMjJX6uCc9eYKgSZOR8u6dZAErbdS1K2z/GgmBiQk0UWhoKNq0aYObN2/y+Xz58uHYsWMoUaIENIVV3z48AGY3daL37oN1v74//B1LA0vMqj6Ld4VmLaEZ4lLjsOXFFvQt0RdGuqrTRTUqOQqNDzRGUnoSr987reo06bparrX4g+Reb4tbHyOw+YY3Lr4Mwszr66AXH8vXOUybBj0XF+QDMKdtKTrkhBDyE6gLNCFEbgwKF+ZlkvSLFuXzCVeuwqdHD6SFhCjlURfGJyD431nw7txFGvzqFyzAA3mHyZNUKvj1jUzk44YXnHmNfff9cM87EuHxv1Zr9fnz5/Dy8pIGv9WqVcOdO3c0KvhlWAkkPU9PPh25bZuk7nMOGegYyMwve7gMa5+uResjrRGcoPx1njMH9F6OXnz6U8wniMSydWbJ72OZ3nfd9UXjpdfQdf0dnH0ZgjZvL6NM+Hu+XqdZC5g3b0aHmhBCfpFq9EUkhKgsXXt7uG/bhoDRo3gAnPLqFbw7doLrurU8QFamsXXBM2byOsaMlq4urAf9CZv+/XmZI1XDkmWxrNGZlXe3xIFBVaXzwTHJuPYuDPlsjJHP2hg2JnpZxmqePHkSnTt3Rtzn8c8s8dX69euhr68PTcPGe1v36c17B7BeDbGnT8O8RYuffp40YRqvF8y4mbrB3sgeykYoEvIxy5tfbMboCqNR1k5S5owZWmYoz+xcwb4Cje3NRclpQiw5/xa77/ohJtNQh5Ixvuj9WlLvV8/dHflnTM3NlyWEEI1DATAhRO5Yl2fXlSsRPGsW7wqdHhICn67d4Lx0Ke8qrUjp4eF8v1j5pgyGFcrDccYM6Ht4QFUZ6QlgbaKHgKgkiD4nyWFBbmb3fSIxdv9T6TyrOczKJ7GA2N3KCO8e3sD21YuR/Dn4Zcmvxo8fr9FBj1mLFghdshTCiAhEbNwEs+bNf/p4sGzRmxpvwv63+3lraubfT0xL5K3F2lqK7aAVlRKFcVfHIU2Uhs3PN6Ns3S8BcGEr5blxpU70dbRx4VWoNPh1NDdA7zI2qLNwCYQiEaCrC6fFi6BtrNxDSAghRNlRAEwIyRMs+RVLIKXn6saTYrFxlH5//smXWXbqqJDxdTEHDyJk/gKIYmL4Mm1TU9iNGQOLDu3zJLuzPDlbGOLcqFpITRfBLyoR3uEJsPqqHiirLZxZfEo6XgTG8oeEA6yajUL0tuHYvn07HwMclZCK9dc+SluN89kYwdZEX2OCYlbuy6p7N4QtW857MyTevg3jKlV+/nm0tHlpoK9NvzUdQQlBmFJ5CgpYFkBeju010zOTjlO2MbRBS8+WOOtzlu8H+3vRlPc4r1p7jzwOQBEHM5R2teDL2PHtXTUfjj4ORO9q+dCgqB1Cx49H7Oc626z8lmHx4grec0IIUX0UABOiItLS0nDlyhX4+PjA3d0dtWrVUrmyM+wCz7pvH15XNXDcOF4mKXjqVKT5+8H2r7/yLOhM9fZG0NRpSLxzR7rMtGFD2E/6B7p2dlAnejra8LQ14Y+vDajhgcYlHOATkYBP4Yn859ugaNx/7YM0PVNoaQsgSIzE9evXUbaspAXwfVg8Vl3+IPM8xnoCuFsbIz9rOf7cgtymrDPPXC1P/bfcyxLEfwvbrw29KubK61p07ozwtesgTk5GxKZNvxQAZ+dW4C2c/HSST696sgqLay9GXgS+Kx+vxJH3RzCnxhzUd68vXTes7DCMqzhOpZJ0KbvA6CRsu+3Dx/hGJ6ahSQkHrO5eXrq+m5cbuld259PRhw7z2tOMcY0asOrZU2H7TQgh6oQCYEJUIPCdO3cuVq5ciZBMyaMcHBwwePBgTJgwQeUCYbNGDaFrbwe/wUMgjIxExPoNSPX3h9PcubyFTV5Y0iLWbTV85covpY3s7OAwdQpM69WDpvk6OH7z5g2aj+mDD+/fA9o6KFOtHlasXImyJSWJn5iQ2GRoa0HarZpJSBXiZVAsf2R05WxfzkW6Pl0owog9j3m36txsOWbB77vQeOQ1HUtLWLRti6idO5Fw9RqS376FQaFCv/28pW1Lo3vR7jjy4QgPPPOCvkAfpz6dQrIwmY/3zRwAWxta58k+qDvWen7POwqbb37CmRchEGb643nqH8Nbgw10JS3vGX8PKZ8+IXjmTD4tsLGB05zZKt8rhRBClAUFwIQoefDbunVrnojo60CBBcNTpkzh2XgPHTqkckGwYZkyPEO03x8DkfrpEx+D6xscApdVK3mAkduSnj5F0OQpSHnzRrrMoktn2I0alaN6rsqAtWJmd3EtFAohEAhkzpHstv2e8+fPo0OHDoiOjubzHdu3xaZNm2BkJPs8zUs5oWExB96tOnPL8afwBB6Q+kcl8gBXm0XJnwVEJ2VJyJW55ZgFw+x3WIu05VfdtJWVVa+eiNq1i70BiNy8BU6zZ/32c7KW1vGVxuPP0n/CXN9c5j3e/mo7Wni0gIWBpLvsrya2uuJ/BVWdqkqzUrPX7FS4E95EvUHv4r2pq3MuYoHt0SeBvIxRxs2hDBXcLXk350bFHbL0lBClpiJw9BiIEyW9G9iNQR0bm9zcNUII0WgUABOixFjLLwt+My6CM8uYP3HiBObNm4dJkyZB1ei5uiLfrp3wHzoMiffvI+nRI3h37gy3tWuhl49VuPx9bKxx6LJliNq2nQcr/HU9PeE4cwaMypWDKsmuCy+7SRIREQFra+tfvgmyevVqDBs2jAfSzNSpU/njW62z3+tWzcYcRydKWtczsKQ+blZGPDj+XsvxwJpfWpqZHv/dgamBzucWY+Uac8yy8ZrWr4+4c+cQc+wYbEeOyLXu85mDX+aMzxnMvzcf65+ux7K6y3j93bpudaGrnf37zRJXXfS9iEb5GkmX+cX5YdD5QfCJ9cHkypNlxh8PLTtU4Um31BErOzbhwFPpOa8n0EaL0k58nG9JF9n3OLOwJUuR/PIln7bq1xcm1avl1S4TQohGoACYECXFAhvW7Zld6H8d/GbG1rPtWHZeVWsFZgQWFnDd+B+C/pmE2GPHkObjC+9OnXlLsFH5L2PjfkX8lSsImj4d6YGZShsNHAjrPwZAWwVLG+W29PR0jBo1CitWrODzrLTR5s2bedmjX8WCYzsz2Zq3pVwscHVcHR4csyCYtRSzFmPvCPaQJOhKTE2HudGX85fNX3sXnu1rZLQcB8UkQ5Gs+vbhATDS0hC1Yyfs/hopl9e5EXBDOs1q7069ORUN3Rtibs25WYJgFvxOuDqBJ69iMoJgR2NHXn6JOfTukEwATMHv72Of0Q98olDMyQxGepJLKxdLI95b4qFvFHpUdkcXLzfYmHx/iEf8tWuI3LSJTxuUKAG7ESNyYe8IIYRkRgEwIUrqxo0bMmN+v3fhFRwczLevXbs2VBELRp3mz4OeqwvCV62GMCYGvr37wHHOHJg3b/bTz5ceEYGQWbMR+7n1nDEsV463+up7yrYyaqqYmBh06tQJZ86c4fP29vY4cuQIvLy85PaaLDj2sDXhjzpfrcs8LpKJT05HzUK2PDj+VsuxohmVLQvDsmV5z4Wo3bthw26syKFEzYyqM1DNqRrP0FzbtTYPiHmAexWYWX0mdKErDX4n35jM17H6wuXsvvRw0NHW4S290SnRaFuwba7voyZ3cz7+NIiP730eEIvZbUqiq5ebdP2/bUrAzECXn/s/kh4WhsAJE/m0tpERnBcuUMka5IQQouwoACZESUVGRsp1e2XDWrJthw+HrosrgqZM4QmrAseMQVpAAG+xzUmXV0lpo0MImT//S2kjExPYjRkNi44dKYnMZx8+fECLFi3w6tUrPl+6dGkcPXoUbm5fLtzzmiDTmGGGtSJv7VuJT3/dcuzzueX45odwpAm/3TsiL1j16Y2AR4/4+RZ98BCsenTP9ddg537j/I2l86zllwW/LNC9GXgTy2otg5OWEybdnIRzvuf4Nr5xvjjw7gAfT5yhhWeLXN83TcWSwW2/7YOdd3wRkfCly/+OOz4yAfCPWnwziEUiHvyy+tIMS8yXW8NACCGEyKIAmBAlZWVlJdftlZVF2zbQdXSA//AREMXFIWzJEqT6+cKRjUn93MU77vx5/pONwcyQ6uODoGnTkHjrtnSZaYP6sJ80Cbr29gr4nyinq1evom3btnzcMNOqVSte49fEJOt4XmXxrZbjBouvKCQLdGYse7iumxvSfH0RuWULLLt2gZZAktFXXli357EVx+Ki30XEp8Vj8KXBKG9dHjdDb/Ku0b6xvngd9ZqP+yW5h91ge+QXzZNanXwWhPRM3RJsTfXR3ctdJvj9GSyRWsINSVd3s5YtYN6qVa7tNyGEEFkUABOipKpVq8a7pYaGhv5wDDDbjm2vLlhd1Xw7d8B34EA+fjdm/wH+03nZUqT5+fGkWUz+QwehX6AAIjZvRvj/VvK6woyOrS3sJ0+CWcOGCv6fKBeW1XngwIF8fDkzbtw4zJkzB9pUXuWXsWDXqncvhMyYiTR/f8SdOw+zxl+ST8mLlYEV+pfsj7VP1iJFmMKD3zoudXjr8IvwFzDWNUZBy4Jy3w9NcuZFMP7c/lBmWRlXC/Splg9NSjjmqJtzdpKePUfokiV8WtfVFQ5TpuTK/hJCCMkepX0kREmxhFZDhgz5bvDLsPU9evRQyQRY36NfsCDy79nDE8EwCTdvwqdrN4QuWizdJmTOXHzq0BFhixZLg1+LTp3gceI4Bb+ZsOzOLNjt27cvD37ZucKCYZY9XFOCX3l2lLZo04Ync2MiNm784d9sbtAT6OGPUn/wscFfK2NXhoLfXMCyl2dWu7AdLI10oSvQQusyTjg0uCoOD6mGVmWcfzn4FcYnIGDMaJ5IDTo6cF60EAIl7o1BCCHqQDOufAhRURMmTECzZpIkUN8bA3vgwAH4+vpC3bCWXPetW2BSty6fT3n3TtpNkEm8excpr1/zaT0PD7hv3wbH6dMgMDNT2D4rm/j4eN7lecGCBXyelUu6cOECevfuDU0SFJOEdKFILs+tbWjIa0ozyU+fIumhbCuhPGRke74eeJ23/Fazq4ZL/pf4MraO/LrHftEYufsRKs46z8ebZzDQFWBFl3K4Mb4ulnYui7Juv1+vPGTmTJ75nrEbOQKGpUrRW0cIIXJGATAhSoy11B06dAgzZ87k3Zwzc3BwkGbs/fjxI2rVqgVvb2+oG5YN1WXFclj27JH9BlpasBk8GPkPH4JRhQp5vXtKjd0UqV69Ok9wxRQrVgx3795FjRo1oA7crY1Q0M7kmw9PW2MY6Eq+5hJShDxpkbxYdesmHaMesVFSxkZeMpc64uWQqs/FpNKT0MCtAV9GQfDPY4nWjjwOQOuVN/jj8ONAvmzrLdlzpnpBmyxlvn4Vqx8dc+QInzauWgVWffvmyvMSQgj5PhoDTIgKBMGTJk3idX6vXLkCHx8fuLu784BXR0eH13FdunQpD35r1qyJS5cuwVPNSv2wcZYWrVsjauu2rCvFYp7siur6yrp9+zZat24tLaXVuHFj7N69G+bm5lAXG3pV/OE2sclp6Lr+NgrYmqB7ZXe57YuOjQ3MW7dC9L79iL94ESmfPkE/f375B78sI7RQUubo36r/8p4iGSWSsqsTTGSFxaXwTM7b7/jwaen7qa2FpiUd0aK0k1wOWaqvL4KnTefTAisrOM6dS1nqCSEkj1AATIgKBcIs6GXZe1k31owxv4sXL4aenh7mz58PPz8/HgRfvHgRhQsXhjoJW7Xqm+vCV62Cy4oV0DRsPO/XN0XYebFr1y706dMHKZ/HRQ8fPhyLFi3iN0w0DavBunNAZRjr6WQptZTbrHr35gEwuynDMkI7TpuW669x0feiTPDLAtw0oaTLM5vOXCKpoW9DNMon/4RcitR/yz1eHiunPQYy3zTZdtsHM4+9RGqmrvHWxnro5uWGbpXdYZ9LLb1fE6emImD0GIgSJN2rnebMhq6dnVxeixBCSFaadzVEiJphLT5z587lgc+sWbMQGBiI2rVr83GerMurOkh++RLx5y98cz3LvJv86hUMihaFpgS+7D1fuXKltIU3o1t8kSJFcPnyZT4vEAjwv//9D3/++aUWrCZiQXBmbCzwuZchaFLSMVdfR9/TEya1ayP+8mXEHDrM61rr5HJ5soyAtq5b3WxbdzOCYE0IfhkW/P5qKaxijmbS4LeEsxn6VM2PZqUc+VhfeQpbsQLJz57xaatePWFSq5ZcX48QQogsGgNMiJoEwf/++y+mT5d0qQsODuZB8LPPF1nq3PqbuRVYU4Jf1rV5ypQpvERWZux9zwh+WVfn06dPa3zw+zU2rnPozkcYtOMhVl1+n+vvj1WfPvwny0oetXMX5IEFtt/r2szWaULw+7P8o5IgylS7t5ybBQbV9sT+P6vg2NDqaFfeRe7BL8tmH7HhPz6tX7QobEePluvrEUIIyYoCYELUCAuKZs+ezafDwsJQp04dPH78GOrc+vt1K7C6Yy2/J0+e5NPfK7fDsjzXr18/D/dMNYTFp+ChbxSfnn/6DbbczN3EcUaVKsKgeHE+HbVzJ0TJybn6/OTXJaUJcfVdmMyNw/GNi6BCPqvvZtnPLemRkQgYP553kdcyNITzokWUu4AQQhSAAmBC1MzEiROxcOFCPs3GC9etWxf379+HqorcuTPH27KAQ91bf1m35x9drLP1e/bs4dsTWc4WhtjR34vXc2WmHn2Bvff8cu0wsWNv1VfSCiyMjETMEUkGbqJ4+jrach8H/i3sZlXgxIkQhoXzeYdJ/0DfI/eTpBFCCPkxCoAJUUOjR4/GsmXL+HRUVBTq1avHswKrIsv27aFXwDNHD4v27aHObty4wcf8fq/ll2HrWXdotj3JqqC9Kbb184KpgSQNxviDT3H0SWCuHSqzRo2g4yQZXxy5aRPEIvnUHyY/x83KCDUK2irksEVt24aEK1f5tFnTJjBv21Yh+0EIIYSSYBGitljmX5YYa/DgwYiNjUXDhg1x6tQpVKtWDarEsEwZeB4/rujdUAqRkZFy3V6TlHA2x+Y+ldDjvztITBVi1J7HMNQVoEEx2Xrbv0JLRwdWPXsidO48pHp786RYpnXr5sp+E9UcxhG6QNIrR9fZGQ7TpuVJl2tCCCHZoxZgQtTYoEGDsGHDBn6xFRcXh0aNGvGyOUQ1Wf1kRuGf3V7TlHe3xIZeFXjX2HSRGEN2PMS1TGNEf4dF+w7QNjXl05EbN+XKcxLVI0pM5CWPxGw4gkAAp4ULIDAzU/RuEUKIRlOpAPjFixfo0KEDPDw8YGRkBBsbG17z9NixY4reNUKUVr9+/bB582Zoa2sjISEBTZo04SWSiOoJCAjIUcsR24aVRFK11n5FqOppgzXdy0NXoMVL4niHS2qz/i6BiTEsO3Xk04n37yPp6dNceV4im9H7+4MBFC949mykfvrEp22HDYVR2bKK3iVCCNF4KhUA+/j48FasXr168fGNkydP5stbtmyJdevWKXr3CFFaPXv2xLZt23gQnJSUhObNm/MSOUQ1pKSkYNiwYejevfsPx/8ybJshQ4bwLvDkx+oUscPyzmUxv10p9KiSL9cOmWWPHoCOZJxxxCZqBc5N/lGJ6LD2FsLjUqCsYk+eRMz+A3zaqFIlWA8YoOhdIoQQompjgJs2bcofmQ0dOhTly5fH4sWL8ccffyhs3whRdl27duUBUZcuXZCcnIxWrVrhwIEDPBgmyn3jj/V8uXfvHp+3sLBAwYIF+Txr6c0cEGfMN2vWDONZuRWSY01KSpJW5SZde3uYN2vKM0HHnTmLVH9/6Lm40Lvymy69DsVfex8jOlF5s5yn+gcgaMpUPi0wN4fTgvnQEsi3xjAhhBA1bAHOjkAggKurK6KjoxW9K4QoPRZI7du3jwfCqampaNu2LQ4fPqzo3SLfcOLECZQtW1Ya/FaqVInXdWbZnWfOnAl7e9mETWyeLT906BC1/v6mkNhkdFl3Gx/D4n/reaz6SEoiQSRC5Natv7tbGi1dKML806/RZ/M9afDrYmmIAnYmKJiDh7u1UZ7spzg9HYFjxkAULzl3HOfM5jdDCCGEKAeVagHOwMYxsm6cMTExOHr0KM9s26lTJ0XvFiEqoU2bNjh48CDatWvHg2AWFO/cuZP/JMohPT0dU6ZMwZw5c6TLWBdoVt9ZT0+Pz0+aNIm38rKkZqyV2N3dHbVq1aLANxfEp6Sj49pb8IlIRLcNd7B3YBW4Wv1a8GRQpAiMq1ZFws2biN5/ALZDhvAWQfJzQuOSMXzXI9z+KMlsbqwnwNx2pdCitJPSHcqwlSuR9Pgxn7bs2pUygBNCiJLRUdUap2vXruXTbEwja8X63//+993fCQ0NRViYbHbP9+/f859paWn8oYwXwUKhkP8kJDfPCZYNmgXB7du3592hO3fuzG8qse7RRLFY/d4ePXpIs3WbmJhgzZo16NhRklDp688qluiqaNGi0ozPyvhZpmr0tYFWpRyx/NIHBMUko+v629jZvyIczAx+6fnMe/XkAbA4MRERO3fBsn+/XN1fdf+uuPMpEn/tfYqw+FQ+X8jOBCs6l4aHrbHSne+J9+4hYo3k+kSvYEFY/jVSYfuo7ucF+Xl0ThBVPTfScvlzVCUD4JEjR/IL98DAQOzdu5e/Yawl63tWrVqF6dOnZ7uOtSRHRERA2bCTkCX9YmP6dD4nUiGaLTfPCTZ2fuvWrTxBFguC+/Tpw4cSZARaJO/dvHmTl65iN+yYIkWKYP369ShQoMA3P6Poc0I+upQyR0SsPXY8CIFfVBK6b7iLNR0KwdLo5xOLiQsVgsDDA8KPHxG5fTuEzZtBKxcTlKnzORAcm4rem5/zMlVM06JWGFfXHQbayYiISIYyEcXEIHbceJaFDtDXh8E/fyMqIYF1W1PI/qjzeUF+DZ0TRFXPjZiYmFx9Pi1xTlKKKrmGDRvyC/c7d+58s0TIt1qAW7dujUePHqF48eJQxpMxMjKSt+wo48lI1OOcuHr1Kk+IxYYWsL8f1trIgmGSd0QiERYsWICpU6fyaYa1Aq9YsYKXfPse+pyQH/b1OO34K+y868/nizqYYlvfCjA3/PngNfbIEYROklQusPt3Jsxatcq1/VT3c2D5xfdYe80bU5sVQYfyzjkqBaaIcyV4xEgkXLrE522nTIF5h/YK3Sd1Py/Iz6NzgqjqufHixQueE+X58+e5ErMp3//wF7DW4IEDB+Lt27coXLhwttvY2dnxR3ZYQiBlLRfCknyxE1FZ94+o/jlRr149nDlzhtcHZnf/2N8SC8L+/PPPXHl+8n3sC4e1wrOEV4y+vj5WrlyJvn375vhCnz4n5Off1qWQkg4ceOiPV8Fx6L/tEbb394KJ/s99fVq1bInI5SuQHhqKmC1bYdWuXa4Gcup0DiSnCWGg+yVj8sgGRdC6nCs8bU2grCJ37pQGv6YNG8K6S2elCNTV6bwguYPOCaKK50Zu75PKZ4Fm2NhFeTSPE6Ip2DjSs2fPwvxzch7WDXf58uWK3i21x7I7lytXThr8enp64vbt2+jXr59SXDwTlmdCC/PalUSzz2WSHvtFY+TuRz99aLT09GDZozufTnn3DgnXb9DhzaYVdestb9RbdIUnvcog0NZS6uA3+c1bhM6dx6d1HB3hOHMG/f0SQogSU6kAOGNc3NeDotk4RkNDQxQrVkwh+0WIOqhcuTLOnz8PS0tLPj9ixAgsWrRI0bulthf6LHEfu/HAMjgzLJnfgwcPUKZMGUXvHvmKjkAbSzqVQd0idrz787C6BX/pGFl27Aitz13aIzdtpOP8Vebt4bsfY8qRFwiITsLovU9kalwrK1FSEgJGj4KY5SHR1obzgvmU5ZsQQpScSnWBZl0zY2NjUbNmTTg7O/NsqTt27MDr16/5hTrLlkoI+XUVKlTAxYsXUb9+fZ50acyYMTzB3MSJE+mw5hLWzXzAgAHYs2cPn2fdjebPn8+T+1Grr/LS09HGqm7leHD2q62RrPyRRft2iNq6DQk3byH59WteJknTvQmOw6AdD/AxTJIsytHcACPrF1SJv4eQefOQ+v4Dn7YZPBhGFSooepcIIYSoUwswq/XLyh6tXr2ad9FcvHgxXFxccOTIEYwaNUrRu0eIWmAtkJcuXYKtrS2f//vvvzFjxgxF75ZaYMkbKlasKA1+2ecXK3f0119/qcTFvqZj41K/Dn7fh8ZB9DlDcU5Y9ezFWwqZyE2boOkOPPBHq5XXpcFvjYI2OD6sOsq7S8p6KbPYs2cRvVvyt2xYoTxs/hyo6F0ihBCibgEwq1V67tw53vLLuj6z5DFsvmXLloreNULUSsmSJXH58mU4ODjweZadePLkySrRJVFZbdmyBZUqVcKbN2+k2etZBvqqVasqetfIL7r+LhwtVtzAP4ef5/hvQ8/FGWaNG/HpmBMnkRYcrJHHnyW6mnjwKUbve4LkNBHY/Z+/6hfC5j6VYG2iD2WXFhiIoM9ZvbXNzOA8fz60lDBzKiGEEBUPgAkheYeNqWetk2y4AfPvv/9iwoQJFAT/QpI+1uW5d+/efJq19LKa5CdPnoSNjY083jqSB1ir77zTr5GUJsSuu77498SrHP9tWGWUGWNlJ7ZtgyaadPg5dt3149PWxnrY2rcSRtQvyBNeKTuxUIiAceMgio3l844zZ0LXyUnRu0UIISSHKAAmhHxToUKFeBDs6urK59lYVTbcgFqCc4bVGmctvBs2bODzrFs5y7Y9ZcoUXm6AqHZ26P96VUA+a0lSq/+uf8KSc29z9LuGJUtKx4pG79kLYXw8NM3wugVhaqCDCu6WODG8BmoUlAy5UAXha9Yg6f4DPm3RqRPMGjVU9C4RQgj5CRQAE0K+i5XmYUFwvnz5+PzSpUsxbNgwXiuYfNvBgwdRvnx5PH78mM+zjM+syzNLMEbUg52ZAXYMqAxnC0M+v/zie6y+LEmI9CNWffvyn6L4eETv3w91lyYUydw4c7M2wt6BVbDrj8pwMDeAqkh88ADhK1fxab0CnrCfMF7Ru0QIIeQnUQBMCPmh/Pnz8yCYBcPMypUreSI6CoKzYvkJWCt5u3bteNZ6hmXTZonFMrqTE/XBgt8d/b1gayoZt8q6RbNatj9iUrsW9PLn59ORW7dCnJYGdRUUk4TO625j0w3Z41LU0Qy6AtW5DBHGxCBgzFjW/53XdXZetBjahpKbH4QQQlSH6nzzEEIUys3NjQfBrFs0s27dOvTr1w9CoZDemc/8/f1Ru3ZtLFmyhM+bm5vj0KFDWLBgAXR1dek4qal8NsY8CLY0krzHrJbt3vuS8a3foqWtDavevfl0emAQYs+chTq69i4MzZZfxwOfKMw++QrP/GOgiljrddDkKUgPCuLzduPHwaCw5LOQEEKIaqEAmBCSY6wFkwXBLEEWs3nzZvTq1Qvp6ekafxTZ2N6yZcvi5s2b/Fiw6YcPH6J169Yaf2w0QSF7U2zr5wVTfUkmYNYKnC78/jAB81YtIbCSlPuJ3LhRrcbWC0ViPia658a7iExI5cs6VHBFQftfq6GsaNH79iHurOQmhUndurDs2lXRu0QIIeQXUQBMCPkprDQS687LSiUxO3bsQPfu3XnXX03EWsBZmajGjRsjPDycLxs4cCAPhD08PBS9eyQPlXA2x+a+FVGtgDV29KsMnR9079U2MIBlN0kglfzyJRLv3oM6CI9PQa+Nd7HswjuwmN5QV4AlnUpjTtuSvJayqkl5/x4hs+fwaR17ezjO+pfqdhNCiAqjAJgQ8tPs7Oxw8eJFlClThs/v2bMHXbp0QWqqpKVHU4SGhvLAd8aMGbz1zsjICNu2bcOaNWtgYKA6iX1I7invboXt/bxg/rk79I+wlkQtfX1pK7Cqu+8diWbLr+H6e8nNIE9bYxwZWg1tyrpAFYlSUhAwajTEyclgxYqd5s+HjqWloneLEELIb6AAmBDyS1gN2wsXLqDC53IuBw4cQIcOHZCSkqIRR/T69eu8m/P58+f5fJEiRXDv3j3eGk40G6v1nNn6qx9x91NkttuyYMq8jaSbfPyVK7y1UVW9CY5Dp3W3ERIr+QxoWdoJR4dW593DVVXo/AVIeSspb2U98A8Ye1VS9C4RQgj5TRQAE0J+mZWVFQ8AK1euzOePHj2KNm3aIJm1lqgp1tK7aNEinuwqMDCQL+vatSsPfjPGRhOSgY2DnXXyFfpuvoen/tHZHhirXr146yITsXmzyh68QvYmaFXGCXoCbcxsXQLLOpeB8ecx0aoo7uJFRO3YwacNy5SB7ZAhit4lQgghuYACYELIb2GZjs+cOYPq1avz+VOnTqFly5ZITExUuyMbHR2Ntm3b8rJGbOyvnp4eVq9eje3bt8PERDWT+xD5crMy4j/jU9J5QqjXwZLSWJnp588Pk3p1+XTskaNIDwtTqWRXmVu+/21dAgcHV0WPyu4qPU42LSQEQX//w6e1TUzgtHAhtCiTOyGEqAUKgAkhv83MzIwHvqxVlDl37hyaN2+OhIQEtTm6LKNz+fLlcfjwYT6fL18+3LhxA3/++adKX+gT+WpX3oUHhUx0Yhq6b7iLj2HxWbaz7tuX/2T1gCN37lSJnhA77/ii9cobSEz9kgXeSE+HJwNTZWKhEIHjxkMYLWmxd5wxHXouVMObEELUBQXAhJBcwVpAT5w4gfr16/N5lim6SZMmiIuLU+kjzC70Wc3jqlWr4uPHj3wZa+FmAXHG+GdCvqd7ZXf807SoNENytw134Bcp20PCsGxZGJYuzaejd+6CSIl7ULCAd9TeJ/j70DM8C4jhdY/VScT6DUi8c4dPm7drC7OmTRW9S4QQQnIRBcCEkFzDsiCzccAsMzJz7do1NGrUCDExMSp5lFkLds+ePXlZI5bcSyAQYP78+bwV2JIywZKfMKCmB0bWL8ing2KSeRAcEvtlrDzrRWDVpw+fFsbEIPrQIaU8vu9D43ir76FHAXzezlQfHcqrZobn7CQ+eoSwFSv4tF7+/HD4R9INmhBCiPqgAJgQkqsMDQ15gNiiRQs+f+vWLTRo0ABRUVEqdaRfvXqFSpUq8fG9jKOjIy/9NHbsWOryTH7JiHoFMbCmpDa0b2QiD4JjEr/UzzZtUB+6LpJgMnLLVt4VV5kceRyAlv+7gbchki7cVT2tcWJ4DXh5WEMdCOPiEDhmLCvuzcf7Oi9aCG0jyRhuQggh6oMCYEJIrtPX18f+/ft5RmiGZUiuV68eIiIiVOJo79q1CxUrVsTLly/5fN26dfHo0SPUrFlT0btGVBhr5Z3QpAi6V3bj85XyW8HU4EuWZC2BAFa9e/PpNF9fxF24AGWQki7EpMPPMGL3YySmSoLyYXULYFs/L9iaSmoYqzo21CF46lSkBXxu2R47BgaU1Z0QQtQSBcCEELlgGZL37NnDawMzLIBkgWSYEme4Zd2cBw8ezMsaZSTwmjRpEs6ePQt7e3tF7x5RkyB4RssSWN6lLGa1LgFtbdkEahZt20DbXJJEKnLjJiiDEbseY/ttXz5taaSLzX0qYnTDwhB8te+qLObgIcSePMWnjWvVhGWPHoreJUIIIXJCATAhRG50dXWxc+dOHlAyT58+5Zmig4ODle6of/r0iZdyYmWNMmocnzx5EjNnzuRjfwnJLSzobVnaSaYrPWtlTU4T8i63lp0782VJjx8j8eEjhR/4gbU8oCvQQlk3C97luXZhO6iTlI+fEPzvv3xaYGsDp9mzaZgDIYSoMQqACSFypaOjg61bt6JXr158nnUrZkFwYGCg0hz5Y8eOoVy5crh//z6f9/Ly4i3WLIs1IfLGAt8/tj7An9sfIDVdBMtuXaU1ZyM3bVJId+DMyrpZYns/L+z5owqcLAyhTkSpqQgYMxripCTWPA/nefOgY60eY5oJIYRkjwJgQojcsRbUjRs3on///nz+zZs3qFWrFvz8/BR69NPT0zF+/Hhe1ij6c83PESNG4OrVq3Bzk4zTJETelp5/hytvw3D5TRhG7H4ELWsbmLWUJJGLO38eqT4+efYmhMYmo/O62zjzQraXBkt0paejfpcMYYsWI+XlKz5t3b8fjKtWVfQuEUIIkTP1+zYjhCglbW1trF27FoMGDeLz79+/50Gwt7e3QvaHtUCzMcmsrBFjamqKffv2YenSpXz8MiF5hSWUKu9uyadPPQ/GuP1PYdlT0mMCYjEit2zJk/24+SEcTZdfx51PkRiz7wl8I5S3FnFuiL9yRXpsDUqVgu3w4YreJUIIIXmAAmBCSJ4GwStXruStrBnjblkQ/PHjxzx9F1g5o7Jly/I6xUypUqV49+f27dvn6X4Qwhjr62Bj74oo4WzG5w8+CsDMlykwrlGDz0cfPIR0OZYRE4nE+N/Fd+i+4Q7C41P4siYlHGBnph4ZnrOTFhqKwIl/82ltY2M4L1wg7XZOCCFEvVEATAjJUyzxz5IlSzBmzBg+7+vry8sLvXv3Tu6vLRKJ8O+///K6xKGhoXxZ3759cfv2bRQqVEjur0/It5gb6mJrXy8UtDPh8zvv+OJUsXp8WpycjOjdu+Vy8KISUtF3yz0sPPsWIjGgr6ON+e1LYX770jDQVc/kb2KRCEETJkIYGcnnHaZNhR4NeSCEEI1BATAhRCFBMOt6/PffkhaYgIAA3hL86pVkLJ48sBrEzZs3x+TJk3kgbGBgwMcl//fffzA0VK/EPkQ1WRnrYUd/L7hbG/H5OcHGiHHx4NOR23dAlCJpnc0tj3yj0Gz5NT72mMlvY4zDQ6qhYwVXqDOWWCzh5k0+bd6qFcxbSMZbE0II0QwUABNCFBYEs9bYadOm8fmgoCCeHfr58+e5/lqshZd1eT51SlLns2DBgrhz5w769OmT669FyO+wMzPgQbCTuQHPSrzWoTJfLoyIQMzRo7l2cB/4RKHj2lsIjEnm801LOuDo0Goo6ijphq2ukp49Q+iSpXxa190N9pMnK3qXCCGE5DEKgAkhCg2Cp06dilmzZvF51i25Tp06ePLkSa6Vc1m+fDnvYp2RcZqN82Xjfdm4X0KUkYulEXYMqMyD4LZ/9YKOgwNfHrlpM+++mxvKuFqggrsVdLS1MLVFMazsWg6mBuo9BlYYn4CA0WNY+ndWpBzOCxdBYGKs6N0ihBCSxygAJoQoHOsKnZGNOTw8nAfBDx48+K3njI2NRadOnXjCrbS0NOjq6mLZsmXYu3cvzMzUu5WLqD7WHfnimNpoUd4NVj178mWpHz8i/urVXKnvK9DWwvIuZbH3zyroUy0/vxml7kJmzkCary+fths5EoYlSyh6lwghhCgABcCEEKUwduxYXoKIiYqKQr169Xg35V/x9OlTVKhQgZc1YlxdXXnG5+HDh2vEhT5RDxlJqCw6doC2iSQ51vv/rf2l59p73w8Dtt6HkGW6+szWVB/l3CTll9RdzJEjiDki6UJuXK0arPr0VvQuEUIIURAKgAkhSoO11rIySUxMTAzP1nzzc7KanNq0aRO8vLykWaWbNGmCR48e8WWEqCIBC36bt+bTBs8f4+qxKzn+3eQ0Icbtf8JrC59/FYpl599C06T6+CB4+gw+LbC2htPcOdDSpssfQgjRVPQNQAhRKoMHD8a6det4S21cXBwaNWqEqzno9pmYmMhLGrFHcnIyrznMkmwdP34c1tbWebLvhMhLZOPWSNeSfGW/Wr4W19+F//B3PoUnoPXKG9h735/P25joobKHZv0tiFNT+bhfUWIin2fBr46traJ3ixBCiALpKPLFCSEkOwMGDOBjdlkwGx8fz1txjx07hrp16/LxvDdu3EBkZCSsrKxQrVo1eHt78+RWrOszY2dnh127dvHtCVEHVSoXx4MadaFz9Tyq+T9BvxWnoOvsDENdAR/bKxQKIRAIpF3841PSERqXIu3yXCmfFVZ0LQt7MwOou7jz5/lP0/r1EbpsGZI/Z5a36t0bJjVqKHjvCCGEKBoFwIQQpdS7d28eBPfs2ZO37jZt2pQntTpz5gxCQkKk21lYWPD1qampfL5GjRrYvXs3nJycFLj3hOS+4iMH4dPV8xCIRWj54TrWG7XM0e8NrOWBsQ0LQ0eg/p2+kl++hP/QYXzafsoURP63kU8bFCsG21F/KXjvCCGEKAP1/zYkhKisbt268ZZc1p05JSUFW7dulQl+mejoaGnwO2bMGFy8eJGCX6KWWBD3xrkIn27scwfGqUnf3V5bC1jfswImNimqEcEvE7ZqlXQ6ZO5c/lPLyAhOixZCW09PgXtGCCFEWWjGNyIhRGV17NiRP3LC3NwcOjrUsYWor4sl6/OfRukpaOJz+7vbulkZoUExe2gK1vobf/7ClwWfb4w5TJ4M/fz5FbdjhBBClAoFwIQQpcbG/F66dOmH27GxjyyDNNueEHX1yrU4fEwlQW2rD9ehI0r/5ra6GtLqmyFs5ZfW3ww69vYwb91KIftDCCFEOVFTCSFEqbGEV193e84OSwQUHBzMt69du3ae7BsheU5LCwcK1MKoR3thkxyDmv5PcNGtvFq/EWKhEMLISKSHhWX/CA1DWmAgn/5aekgIUl6/hkHRogrZd0IIIcqHAmBCiFJj2Z7luT0hquaySzn0fnkKVilxaPf+Mi66luOBsSqWKEqPiMgUyIbKBLXSafY3LRT+8uuEr1oFlxUrcnXfCSGEqC4KgAkhSo2VOpLn9oSomjSBDo56VEfvV6fgERuErq/P4ZO5E245lYAyECUlZWmhza7lVhgV9Vuvo21mxmv6ahsZIfnZs29uF3fuPJJfvaJWYEIIIRwFwIQQpcbq/Nrb2yM0NJR3c/7eGGC2HdueEHV3In8VdH57HgbCNPR4c5YvG1L7L3y0cJbL67G/PVFcXI4CW1F8/K+/kJYWBFZWPLD95sPOFjo2NtA2kNQ09hs6FPh2/MtRKzAhhJAMFAATQpQaqwU8ZMgQTJky5YcX6Gw7tj0h6i5ezwhn3L3Q6uN16bKub87hX6/eP/U8YpGIt8T+KKhlD3FKyq/vsI4OdKytswlm7WQDWysraP3E33CWzM/fQK3AhBBCMlAATAhRehMmTMCdO3dw4sQJ3tKbuSU4Y75Zs2YYP368QveTkLz00LagTABcLeg5PKIDeCuwQCSERXwUkp49+35gGxEBpH87k/SPaOnrf7+l9vO0wNISWtq5n5U6cufOHG8btXMnHGfOzPV9IIQQolooACaEKD3Wqnvo0CHMmzePlzpi2Z4zsG7PrOWXBb/U+kvUnbu1kXS67eOHWdYvvLkaaQJdmCTFQxtieOc8PpShbWLyw6CWj781NeU3oRTFsn17JD1+nKNtLdq3l/v+EEIIUX4UABNCVAILbidNmsQDXVbqiGV7Zgmv2JhfCnyJptjQq6K06++ndU+yrDdMTYYhkr/5+6wlNkeBraEhVIFhmTLwPH5c0btBCCFEhVAATAhRKSzYpTq/RNOFrVr1zXW6zs4wb9UqS1DLxuBq6enl6X4SQgghyoYCYEIIIUSF/CjxU1pAAEwb1KeyP4QQQkg2cj8jBSGEEEIU0vqbuewPIYQQQrKiAJgQQghRET9b9ocQQgghsigAJoQQQlTEz5b9IYQQQogsGgNMCCGEqIhsy/6IgXRhOnQEOkCmikRU9ocQQgjJigJgQgghREVkV/YnLS0NERERsLa2ppJghBBCyA9QF2hCCCGEEEIIIRqBAmBCCCGEEEIIIRqBAmBCCCGEEEIIIRqBAmBCCCGEEEIIIRqBAmBCCCGEEEIIIRqBAmBCCCGEEEIIIRqBAmBCCCGEEEIIIRqBAmBCCCGEEEIIIRpBBxosJSWF/3z//j2UUVpaGmJiYmBubg5dXV1F7w5RAnROEDonCJ0DhL4vCF1DEE26vnz/OVbLiN1+l0YHwH5+fvxn69atFb0rhBBCCCGEEEK+E7uVK1cOv0tLLBaLoaGio6Nx5coVuLq6Ql9fH8p4t4MF54cPH0aBAgUUvTtECdA5QeicIHQOEPq+IHQNQTTp+jIlJYUHv7Vq1YKFhcVvP59GtwCzA9iqVSsoO3YiFi9eXNG7QZQInROEzglC5wCh7wtC1xBEU64vy+VCy28GSoJFCCGEEEIIIUQjUABMCCGEEEIIIUQjUABMCCGEEEIIIUQjUACsxGxtbTF16lT+kxA6Jwh9ThA6BwhdQxC6riQUc/wejc4CTQghhBBCCCFEc1ALMCGEEEIIIYQQjUABMCGEEEIIIYQQjUABMCGEEEIIIYQQjUABMCGEEEIIIYQQjUAB8Dfcu3cPQ4cORfHixWFsbAw3Nzd07NgRb9++zbLtq1ev0LhxY5iYmMDKygo9evRAWFiYzDavX7/GuHHjUKZMGZiamsLR0RHNmjXD/fv3szzftGnToKWlleVhYGCQ4zdWJBJh/vz5yJ8/P/+9UqVKYdeuXdlu+7///Q9FixaFvr4+nJ2dMWrUKCQkJOT4tTSJqp8Xs2bNQsuWLWFvb89/lz1ndt68eYO//voLVatW5c/PtvX29s7x62gSRZ4TGfbs2YMqVarw17ewsODv28WLF3P1s+Lu3bsYPHgwypcvD11dXX5OEM06B9avX49atWrxzw/2fcG279OnD302aPA50bt372y/l4oUKZKj19E0mnJeZHdOZDwaNGiQo9fSNJpybihN3MGyQJOs2rVrJ3ZwcBAPGzZMvH79evHMmTPF9vb2YmNjY/GzZ8+k2/n5+YltbGzEnp6e4mXLlolnzZoltrS0FJcuXVqckpIi3W706NFiCwsLcb9+/cRr164Vz58/n/+OQCAQnzt3Tua1p06dyjJzi1evXi3etm2b9LFz584cv1UTJkzgzzFgwADxunXrxM2aNePzu3btktlu3LhxfHn79u3567H/r46Ojrhhw4Z0WqjhecF+n+1/o0aN+DR7zuxs2rRJrK2tLS5RooS4TJkyfNtPnz7ROaFk50TGeaGlpSXu0KGDeM2aNeIVK1aIBw4cKN66dWuuflaw19HV1RWXL19eXKhQIb4N0axzYNCgQeJevXqJFy5cKP7vv//EkyZN4v9P9n8KCAig00EDzwl2Pujr68t8J7HH0aNH6XzQ4PPi6/OBPUaMGMG3ZftINPfcGKckcQddwXzDjRs3ZE4k5u3bt/yDvlu3bjIXBIaGhmIfHx/pMnZisTeXnXAZ7t+/L46Li5N5vvDwcLGtra24WrVq2QY6YWFhv/Sm+vv78wvVIUOGSJeJRCJxjRo1xC4uLuL09HS+LDAwkJ90PXr0kPl9dtKz16cvMPU6L5iMIJY9x/cC4IiICHFsbCyfXrBgAQXASnpO3Lp1i39hLV68WCzPzwomODhYnJiYyKfZ9hQAa945kB22r2z/58yZ80uvr6405ZxgATC7QCc5oynnRXZYIMZenwVwRDPPjUAlijsoAP5J5cqV448MdnZ2/G7J11gLSb169X74fG3bthVbWVllG+iEhoaKY2Ji+En0M1auXMl//8WLFzLLWUshW37t2jU+f+DAAT5/4sQJme0ygqOuXbv+1OtqMlU4LzL7UQCcGQXAyntOdOrUSezo6CgWCoX8fPj6yy63Piu+RgFwzqjzOZD5goptN378+J96XU2lbudERgDMLnDZ9xL5Nep2XnwtOTmZt0bWrl37p16TqNe5cUCJ4g4aA/xz3cUREhICGxsbPh8QEIDQ0FBUqFAhy7aVKlXCo0ePfvicwcHB0uf7moeHB8zNzXnf/e7du/PXzgn2uqz/Putf//U+ZaxnUlJS+E9DQ0OZ7YyMjPjPBw8e5Oj1NJ2qnBdE/c6JCxcuoGLFili+fDlsbW2l43zY+Jrc/KwgP0+dz4GIiAj+f2FjydgYYKZevXo5ej1Npq7nRGJiIszMzPj3EhuPOGTIEMTHx+fotYj6nheZnTx5EtHR0ejWrRu95Rp8bqQoUdxBAfBP2LFjBz/5OnXqxOeDgoL4T3aSfI0ti4yMlL7Z2bl27Rpu3bolfb4MlpaWfCD82rVrsX//fvTv358PTK9RowZiY2N/uJ9svzKSHH29T0xgYCD/WbhwYf7zxo0bWfaLYf9Xoj7nBVGvcyIqKgrh4eH873fy5MmYMGECPx9Ywothw4bx8yS3PivIz1Pnc4AlLWG/wy6Ybt68yS+aKLGNZp4TbBlLtLNp0yae8IYlWVy1ahVP0JOenp6Do0LU8bzI7v/IEh61b9+e3nANPjcKK1PckWdtzSru1atXYjMzM3GVKlWkfdmvXr3Km+z37NmTZfvJkyfzdVFRUdk+X0hICO8X7+HhkaOuBjt27MjxOKu6deuKixYtmmU569rAnoMlIsjg5eUlNjExEW/cuJGPDz158qTY3d2d9+VnA+WJ+pwXmVEXaNU/J3x9ffnvscfu3btl/s6LFSvGfyc3Pysyoy7Qmn0OXLx4kX9XLFq0SFy2bFka/5sD6n5OZMaS8mSX/IZo5nnBusYbGBiI27RpQ6fAT1DXc8NLSeIOagHOAdZdgKUOZ917WMubQCCQacLP7m5LcnKyzDaZsVTfzZs3R1xcHI4cOcLTmP9I165d4eDggPPnz8vsV+ZHUlKS9DVzuk8HDhxA6dKl0bdvX566vEWLFjztetmyZXO0X5pM1c4Lol7nRMb2rCRR5rvq2tra/O6uv78/fH19c+2zgtA5kKFOnTpo0qQJL12xb98+TJ8+Pcdd5TSRpn0usBJ67PUyfy8RzT0v2HUm24a6P+ecOp8bB5Qk7qAA+AdiYmL4Fz0bu3D69Gk4OTlladrP6JKQGVvGxsKwLh+Zpaamom3btnj69Ck/CUuUKJHjN8vV1ZV3b8j8+pkfrMtCxnJ2Ykqq3sjuE5P5/8C6sl2/fp3XGbt69So/0VkdLz8/PxQqVCjH+6ZpVPG8IOp1TrDfYbX2rK2tpV+OGezs7KRdm3Lrs4LQOZAdT09PfuHCuuoR+lzIuNhln0uZv5eI5n5fsM8GFsixAIz8mLqfG85KEnfo5NkrqSB254LdmWBvEruTWaxYMZn17E1kg8WzKyp99+5d3n/+6yLRPXv25IPN9+7di1q1auV4X9hJ5e3tzS80Mpw7d05mG1Y8m2Gvu2HDBl4oO/M+37lzR7r+awULFuQP5uXLl/ykZQXuifqcF0S9zgl2d5b93r179/gXnJ6ennRdxngb9pq5/VlB6Bz4GmsF+N64M02lqZ8LrJWJjSnMeB2iuecFu5a8dOkSv578OjAjmn1uFFR03JFnna1VDOtv37JlS16v6ut03Zn9+eefvB4X60Of4fz587zPOyvwnNngwYOz1OnKDitz860U4zmp0cVqrH2rHpezs/N3a7Wx/vqseLWRkZFMjTGi+udFZjQGWD3OiSVLlvDtWNH5DElJSXyMDxu7I6/PChoDrHnnQFpamjgyMjLL79+5c4eP2/q6rqOm04Rzgj1nRr34zMaOHctf/+DBgz98LU2jCedFZuzahL3mhQsXfvj8mk7Tzg1Fxx1a7J+8C7dVx8iRI7Fs2TJp3/SvsfIzDGuyZ61vFhYWGDFiBE/9v2DBAri4uPC7KRl3vJYuXcrHxVSpUgWDBw/O8nxt2rThKcQz0oGzfvclS5bk3RJYV4Hdu3fzPvMsc1pGuvDvYVkZ2X788ccfPFPn4cOHceLECd4VhY0bzcD2md1xYndn0tLSsHPnTn4XacuWLejRo8dvHUN1pOrnxbZt2+Dj48PLVsyZM4eP5atbty5fx95vd3d3aRecFStW8Gn23KwbzujRo/n/hz1YNmqi+HOCtbyxv292t5g9p5ubG3+PHz58iGPHjvFuVLn1WcHOG/bczPHjx/md3ZkzZ/J5dt5o8ueFJpwDrDse20/2GcTu+rPXf/bsGc/+yz6Pbt++Lb2bTzTjnMjofdSlSxcUKVKELztz5gwvecOyQLPtWesS0azzIjNWroe17LH/D50L36cp58YIZYk78izUVjG1atWSZkXL7pHZ8+fPxQ0bNuR3L1ih727duomDg4NltmHF4r/3fCwTWob+/fvzOy6mpqb8jkqBAgXE48ePz/ZO6/fuqMyePZtnVtPT0xMXL15cvH379izbbdq0SVy6dGleyJ69HiuizTJ8EvU8L763/5cuXZJux173W9uxc4ooxzmRkdmR/Q4rbK+vr88zLJ4+fTrXPyvY+fGtfWLHQJNpwjmQkpLCM3mWKlWKZyZln0Fs+379+mXZH6IZ5wTLNtu9e3f+XcT2nb0O2479XmpqKp0GGnpeZHj9+jXfh1GjRtG5kAOacm4oS9xBLcCEEEIIIYQQQjQC9U0hhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEKIRKAAmhBBCCCGEEAJN8H8VJXJJqt3A3wAAAABJRU5ErkJggg==","media_type":"image/png"}}]}]},"uuid":"402747bc-0bf6-4210-b6dc-7c84066db296","timestamp":"2026-10-30T05:38:02.719Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":122086,"dimensions":{"originalWidth":960,"originalHeight":840,"displayWidth":960,"displayHeight":840}}},"sourceToolAssistantUUID":"05eab99b-89ec-4f19-8c09-75f9d9144480","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}128{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"6f11c8213c51fa6cfa0eaa99d61e4f2032890daf84044fe5c6da5a4300a0f856","message":{"role":"assistant","content":[{"type":"text","text":"Let me view the figure quickly."},{"type":"tool_use","id":"toolu_01P3YWfN8DQb67hL9QQU5pm5","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0015/out/figure1.png"}}]}}129{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"37a4c4d7-7acb-4eca-bb21-694a742c53cf","timestamp":"2026-10-30T05:38:02.731Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"7a44e11d-ab64-4324-9d3c-b622866ed1be","keep":42,"tail":["6f11c8213c51fa6cfa0eaa99d61e4f2032890daf84044fe5c6da5a4300a0f856","cd5f4cc011bcfaf8ecdf54acb66c3f610210a3bdd050240e7130f4182dd726d4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",43,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b4ec0807c29ce625007ffda9d7543a217d7444e2b890a9c7fe5d3c27c43cbea9"}130{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"402747bc-0bf6-4210-b6dc-7c84066db296","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}131{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}132{"parentUuid":"402747bc-0bf6-4210-b6dc-7c84066db296","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7q1a56YYpwWKoJfxq","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1161,"cache_read_input_tokens":55190,"output_tokens":979,"output_tokens_details":{"thinking_tokens":37},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1161},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":429,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt7pixtpjwD84fxWxp1","requestRef":"37a4c4d7-7acb-4eca-bb21-694a742c53cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c023475c-721c-41cb-85b2-57a945f4d281","timestamp":"2026-10-30T05:38:03.972Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}133{"parentUuid":"c023475c-721c-41cb-85b2-57a945f4d281","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7q1a56YYpwWKoJfxq","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PBsqaPTiUPkt6ArQH8EWf1","name":"Bash","input":{"command":"{ echo \"# Verification checks (P4) — 2026-10-30\"; echo; echo \"## Independent recomputation (script /tmp/verify.py, statsmodels OLS/HAC used as independent implementation)\"; ~/wp29/venv/bin/python /tmp/verify.py; cat <<'EOF'\n\nNote on the FAIL above: the check \"vintage_used <= origin_date < target_date\" fails for the 40 h=1 rows. This is not an information leak: by TASK.md, the target is last(V)+h with target_date written as YYYY-MM-01, and because RSAFS is published with a 1-2 month lag, every h=1 target month starts on or before the month-end origin date (e.g. origin 2025-10-31, last(V)=2025-08, h=1 target 2025-09-01). The substantive real-time condition was checked instead (below) and passes.\n\n## Real-time availability\n- [PASS] vintage_used == origin_date for all 80 rows (only the vintage dated V feeds origin V).\n- [PASS] 0 of 80 target months are present in the vintage used (no target value was published at the origin).\n- [PASS] analysis.py asserts that no vintage contains a month after its origin date.\n- [PASS] RSAFS_current.csv is read only after all forecasts are produced, in the revision block (code inspection).\n- [PASS] UMCSENT / PAYEMS not used in any forecast (code inspection; read only for row counts).\n\n## Reproducibility\n- [PASS] Deleted results.json, forecasts.csv, table1.csv, figure1.png, aux_diagnostics.json; re-ran analysis.py; results.json byte-identical (cmp), forecasts.csv and table1.csv SHA-256 identical.\n\n## Internal consistency\n- [PASS] RMSE >= MAE > 0 for every model/horizon; DM long-run variances positive (h1 0.809, h3 2.119; aux_diagnostics.json).\n- [PASS] exclusions: 20 − 0 = 20 = n_analysed.\n- [PASS] magnitudes: model RMSEs (0.55, 1.14) are below but of the same order as the naive baseline (1.00, 1.42); h=3 RMSE > h=1 RMSE for naive and model, as expected.\n\n## Gate\n- Gate run at end of P4: all checks ok except report/claims (not yet written, P5) and forecasts_chronology (spec conflict above, cannot be fixed without misdating targets in violation of TASK.md).\nEOF\n} > out/state/checks.md; grep -c PASS out/state/checks.md","description":"Write checks.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1161,"cache_read_input_tokens":55190,"output_tokens":979,"output_tokens_details":{"thinking_tokens":37},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1161},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt7pixtpjwD84fxWxp1","requestRef":"37a4c4d7-7acb-4eca-bb21-694a742c53cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d240e902-6b22-4db0-b133-9e059cf77d42","timestamp":"2026-10-30T05:38:11.962Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}134{"parentUuid":"d240e902-6b22-4db0-b133-9e059cf77d42","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PBsqaPTiUPkt6ArQH8EWf1","type":"tool_result","content":"33","is_error":false}]},"uuid":"244c7a3d-4648-4d03-bf81-9b9c839e69dc","timestamp":"2026-10-30T05:38:12.682Z","toolUseResult":{"stdout":"33","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d240e902-6b22-4db0-b133-9e059cf77d42","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}135{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"62b255dc058f54aa7c37c94e8d0ff8596cd1f7b89b6fdb5f3f32f8ef392d71a4","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01PBsqaPTiUPkt6ArQH8EWf1","name":"Bash","input":{"command":"{ echo \"# Verification checks (P4) — 2026-10-30\"; echo; echo \"## Independent recomputation (script /tmp/verify.py, statsmodels OLS/HAC used as independent implementation)\"; ~/wp29/venv/bin/python /tmp/verify.py; cat <<'EOF'\n\nNote on the FAIL above: the check \"vintage_used <= origin_date < target_date\" fails for the 40 h=1 rows. This is not an information leak: by TASK.md, the target is last(V)+h with target_date written as YYYY-MM-01, and because RSAFS is published with a 1-2 month lag, every h=1 target month starts on or before the month-end origin date (e.g. origin 2025-10-31, last(V)=2025-08, h=1 target 2025-09-01). The substantive real-time condition was checked instead (below) and passes.\n\n## Real-time availability\n- [PASS] vintage_used == origin_date for all 80 rows (only the vintage dated V feeds origin V).\n- [PASS] 0 of 80 target months are present in the vintage used (no target value was published at the origin).\n- [PASS] analysis.py asserts that no vintage contains a month after its origin date.\n- [PASS] RSAFS_current.csv is read only after all forecasts are produced, in the revision block (code inspection).\n- [PASS] UMCSENT / PAYEMS not used in any forecast (code inspection; read only for row counts).\n\n## Reproducibility\n- [PASS] Deleted results.json, forecasts.csv, table1.csv, figure1.png, aux_diagnostics.json; re-ran analysis.py; results.json byte-identical (cmp), forecasts.csv and table1.csv SHA-256 identical.\n\n## Internal consistency\n- [PASS] RMSE >= MAE > 0 for every model/horizon; DM long-run variances positive (h1 0.809, h3 2.119; aux_diagnostics.json).\n- [PASS] exclusions: 20 − 0 = 20 = n_analysed.\n- [PASS] magnitudes: model RMSEs (0.55, 1.14) are below but of the same order as the naive baseline (1.00, 1.42); h=3 RMSE > h=1 RMSE for naive and model, as expected.\n\n## Gate\n- Gate run at end of P4: all checks ok except report/claims (not yet written, P5) and forecasts_chronology (spec conflict above, cannot be fixed without misdating targets in violation of TASK.md).\nEOF\n} > out/state/checks.md; grep -c PASS out/state/checks.md","description":"Write checks.md"}}]}}136{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"1aba162b-0726-4d1b-9a95-b714b17ce72e","timestamp":"2026-10-30T05:38:12.684Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"37a4c4d7-7acb-4eca-bb21-694a742c53cf","keep":44,"tail":["62b255dc058f54aa7c37c94e8d0ff8596cd1f7b89b6fdb5f3f32f8ef392d71a4","f3d2916595c422cefc357854743e6e47938ec575229593d2c1efedff66e45a7b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",45,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7224e246a4d44d4d3ec967a42df102714023d28f960eb1388f04f7d26389a210"}137{"parentUuid":"244c7a3d-4648-4d03-bf81-9b9c839e69dc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8ZaAoa2JM8dtFZ8FR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016674dHd3qmj5ZpsnH4vTyQ","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|receipt|passed\"; ls out/state/gate_receipts/","description":"Run gate at end of P4"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":985,"cache_read_input_tokens":56351,"output_tokens":145,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":985},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt8ZGp7ZCSJfwqE8qko","requestRef":"1aba162b-0726-4d1b-9a95-b714b17ce72e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4884f949-a0c5-450e-b4d9-ccf198f0f232","timestamp":"2026-10-30T05:38:14.908Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}138{"parentUuid":"4884f949-a0c5-450e-b4d9-ccf198f0f232","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016674dHd3qmj5ZpsnH4vTyQ","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (11 of 65 checks failed)\n  [FAIL] file:out/report.md: missing or empty\n  [FAIL] file:out/claims.json: missing or empty\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P2', 'P3', 'P4', 'P5']\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053815.696144Z.json\n20261030T053732.391378Z.json\n20261030T053815.696144Z.json","is_error":false}]},"uuid":"67c2a039-8798-4be3-bd8c-b57c633ed30d","timestamp":"2026-10-30T05:38:15.704Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (11 of 65 checks failed)\n  [FAIL] file:out/report.md: missing or empty\n  [FAIL] file:out/claims.json: missing or empty\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P2', 'P3', 'P4', 'P5']\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053815.696144Z.json\n20261030T053732.391378Z.json\n20261030T053815.696144Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4884f949-a0c5-450e-b4d9-ccf198f0f232","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}139{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"4157c2511eb19e369cda77f9983f0a1d336982bb239b8f9fe3e29673a24a515b","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_016674dHd3qmj5ZpsnH4vTyQ","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|receipt|passed\"; ls out/state/gate_receipts/","description":"Run gate at end of P4"}}]}}140{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"e296245d-368e-44a3-9855-4ff76ecdb064","timestamp":"2026-10-30T05:38:15.706Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"1aba162b-0726-4d1b-9a95-b714b17ce72e","keep":46,"tail":["4157c2511eb19e369cda77f9983f0a1d336982bb239b8f9fe3e29673a24a515b","3abdf310db774836d3cf04cfa4b7bd4299e93fa5930acd47bc1a7bdc1556fe18"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",47,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a7b132b9a8b81cbcfa2d77f4b24dbdf20892a37a2e6d0b2deee4e72317a8d971"}141{"parentUuid":"67c2a039-8798-4be3-bd8c-b57c633ed30d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8nPM9Tiaj3mZ7PeC5","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TZpbAczaYutY34sM1Uxufe","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, seasonal naive, AR(1) computed from vintage V only with the same first-release evaluation rule; stored as rmse_/mae_{naive,snaive,ar1}_h{1,3}\",\"naive and AR(1) independently recomputed for origin 2026-04-30 (statsmodels) - PASS\"],\"notes\":\"baseline RMSE naive h1=0.997, h3=1.420\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"out/analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png\",\"no randomness (random_seed null)\",\"model pre-specified (RW with drift, 12-month drift window) before computing errors\"],\"notes\":\"\"}\np['P4']={\"status\":\"blocked\",\"checks\":[\"clean-state rerun: results.json byte-identical, forecasts/table1 hashes identical - PASS\",\"independent recomputation of RMSE/MAE, DM (statsmodels HAC), rel. improvement, conclusion codes, revision - all PASS (checks.md)\",\"real-time: vintage_used==origin_date, 0 targets already published in vintage - PASS\",\"gate receipt out/state/gate_receipts/20261030T053815.696144Z.json: passed=false; failures = report/claims not yet written (P5) and forecasts_chronology (40 h=1 rows target_date<=origin_date)\"],\"notes\":\"Blocked only by gate rule origin_date<target_date, which contradicts TASK.md's target definition last(V)+h with YYYY-MM-01 dates under 1-2 month publication lags. Not fixable without misdating targets. All substantive P4 checks pass.\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2,P3 passed. P4: all verification checks pass; gate forecasts_chronology fails by construction (h=1 target months precede month-end origins due to publication lag); decided NOT to alter target_date (TASK.md authoritative); P4 marked blocked with explanation.\" >> out/state/log.md","description":"Update phase ledger and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":527,"cache_read_input_tokens":57336,"output_tokens":832,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":527},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt8nAx91urZswfCPgKu","requestRef":"e296245d-368e-44a3-9855-4ff76ecdb064","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2ac6815e-c543-4a4f-8583-8158d08e2657","timestamp":"2026-10-30T05:38:23.588Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}142{"parentUuid":"2ac6815e-c543-4a4f-8583-8158d08e2657","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TZpbAczaYutY34sM1Uxufe","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"d8340dcd-0458-4322-a124-26228dc730d1","timestamp":"2026-10-30T05:38:23.615Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2ac6815e-c543-4a4f-8583-8158d08e2657","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}143{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"b97c5a16a351777405dc704f9b10a5793f958edfbed3261afc907c04c6fab434","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01TZpbAczaYutY34sM1Uxufe","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, seasonal naive, AR(1) computed from vintage V only with the same first-release evaluation rule; stored as rmse_/mae_{naive,snaive,ar1}_h{1,3}\",\"naive and AR(1) independently recomputed for origin 2026-04-30 (statsmodels) - PASS\"],\"notes\":\"baseline RMSE naive h1=0.997, h3=1.420\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"out/analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png\",\"no randomness (random_seed null)\",\"model pre-specified (RW with drift, 12-month drift window) before computing errors\"],\"notes\":\"\"}\np['P4']={\"status\":\"blocked\",\"checks\":[\"clean-state rerun: results.json byte-identical, forecasts/table1 hashes identical - PASS\",\"independent recomputation of RMSE/MAE, DM (statsmodels HAC), rel. improvement, conclusion codes, revision - all PASS (checks.md)\",\"real-time: vintage_used==origin_date, 0 targets already published in vintage - PASS\",\"gate receipt out/state/gate_receipts/20261030T053815.696144Z.json: passed=false; failures = report/claims not yet written (P5) and forecasts_chronology (40 h=1 rows target_date<=origin_date)\"],\"notes\":\"Blocked only by gate rule origin_date<target_date, which contradicts TASK.md's target definition last(V)+h with YYYY-MM-01 dates under 1-2 month publication lags. Not fixable without misdating targets. All substantive P4 checks pass.\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2,P3 passed. P4: all verification checks pass; gate forecasts_chronology fails by construction (h=1 target months precede month-end origins due to publication lag); decided NOT to alter target_date (TASK.md authoritative); P4 marked blocked with explanation.\" >> out/state/log.md","description":"Update phase ledger and log"}}]}}144{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"1e19afae-933d-4bf5-b89d-0e7bb728f0d1","timestamp":"2026-10-30T05:38:23.617Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"e296245d-368e-44a3-9855-4ff76ecdb064","keep":48,"tail":["b97c5a16a351777405dc704f9b10a5793f958edfbed3261afc907c04c6fab434","0534f214ec3367fcd6b46ec374fc0ae556f111cef162116dec6f113be0dcf664"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",49,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"25ebbae4bf20a89e99e2b811e60aecc1da8f5e445ac83081248cadb92dd5f23f"}145{"parentUuid":"d8340dcd-0458-4322-a124-26228dc730d1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt9NGYoCsgKqc1rrUAn","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":847,"cache_read_input_tokens":57863,"output_tokens":249,"output_tokens_details":{"thinking_tokens":27},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":847},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":438,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt9MzvLQ49nY7nf4XT1","requestRef":"1e19afae-933d-4bf5-b89d-0e7bb728f0d1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"867affcf-da62-421d-a823-445f8aa072f2","timestamp":"2026-10-30T05:38:24.978Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}146{"parentUuid":"867affcf-da62-421d-a823-445f8aa072f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt9NGYoCsgKqc1rrUAn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01StZq1gchxiLE9FPjA5hdAH","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n  if isinstance(v,float): print(k, round(v,4))\n\"; ~/wp29/venv/bin/python -c \"\nimport json;a=json.load(open('out/state/aux_diagnostics.json'));print([ (x['target'],x['abs_rev']) for x in a['revision_by_target']])\"","description":"Print rounded results for report"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":847,"cache_read_input_tokens":57863,"output_tokens":249,"output_tokens_details":{"thinking_tokens":27},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":847},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt9MzvLQ49nY7nf4XT1","requestRef":"1e19afae-933d-4bf5-b89d-0e7bb728f0d1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1235397d-d591-476c-ad37-64504bbfb344","timestamp":"2026-10-30T05:38:26.153Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}147{"parentUuid":"1235397d-d591-476c-ad37-64504bbfb344","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01StZq1gchxiLE9FPjA5hdAH","type":"tool_result","content":"rmse_naive_h1 0.9969\nmae_naive_h1 0.8487\nrmse_naive_h3 1.42\nmae_naive_h3 1.2004\nrmse_snaive_h1 1.6745\nmae_snaive_h1 1.3067\nrmse_snaive_h3 1.3161\nmae_snaive_h3 1.0659\nrmse_ar1_h1 0.9405\nmae_ar1_h1 0.7977\nrmse_ar1_h3 1.1871\nmae_ar1_h3 0.9527\nrmse_model_h1 0.5503\nmae_model_h1 0.4863\nrmse_model_h3 1.1422\nmae_model_h3 0.934\nrel_improvement_rmse_h1 0.448\ndm_stat_h1 2.429\ndm_pvalue_h1 0.0151\nrel_improvement_rmse_h3 0.1956\ndm_stat_h3 1.5466\ndm_pvalue_h3 0.122\nmean_abs_revision_h1_targets 0.5482\n[('2025-09', 0.550217), ('2025-10', 0.664176), ('2025-11', 0.43892), ('2025-12', 0.328627), ('2026-01', 0.975676), ('2026-02', 0.409956), ('2026-04', 0.748173), ('2026-05', 0.16534), ('2026-06', 0.744089), ('2026-07', 0.457025)]","is_error":false}]},"uuid":"9eb33558-fe1c-4e75-9b9a-c72adb7a15d6","timestamp":"2026-10-30T05:38:26.197Z","toolUseResult":{"stdout":"rmse_naive_h1 0.9969\nmae_naive_h1 0.8487\nrmse_naive_h3 1.42\nmae_naive_h3 1.2004\nrmse_snaive_h1 1.6745\nmae_snaive_h1 1.3067\nrmse_snaive_h3 1.3161\nmae_snaive_h3 1.0659\nrmse_ar1_h1 0.9405\nmae_ar1_h1 0.7977\nrmse_ar1_h3 1.1871\nmae_ar1_h3 0.9527\nrmse_model_h1 0.5503\nmae_model_h1 0.4863\nrmse_model_h3 1.1422\nmae_model_h3 0.934\nrel_improvement_rmse_h1 0.448\ndm_stat_h1 2.429\ndm_pvalue_h1 0.0151\nrel_improvement_rmse_h3 0.1956\ndm_stat_h3 1.5466\ndm_pvalue_h3 0.122\nmean_abs_revision_h1_targets 0.5482\n[('2025-09', 0.550217), ('2025-10', 0.664176), ('2025-11', 0.43892), ('2025-12', 0.328627), ('2026-01', 0.975676), ('2026-02', 0.409956), ('2026-04', 0.748173), ('2026-05', 0.16534), ('2026-06', 0.744089), ('2026-07', 0.457025)]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1235397d-d591-476c-ad37-64504bbfb344","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}148{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"730569146f7ecd180ec792208afa520bc929fafabfd597f139ecad9c29ada61b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01StZq1gchxiLE9FPjA5hdAH","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n  if isinstance(v,float): print(k, round(v,4))\n\"; ~/wp29/venv/bin/python -c \"\nimport json;a=json.load(open('out/state/aux_diagnostics.json'));print([ (x['target'],x['abs_rev']) for x in a['revision_by_target']])\"","description":"Print rounded results for report"}}]}}149{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"28d8acab-78c8-44ef-869a-df20016bbd48","timestamp":"2026-10-30T05:38:26.199Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"1e19afae-933d-4bf5-b89d-0e7bb728f0d1","keep":50,"tail":["730569146f7ecd180ec792208afa520bc929fafabfd597f139ecad9c29ada61b","b7cd58fba340fa33bc1d9afaef5db89c56363e74bf87fd929526bff196a8efba"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",51,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f6b551a939c1c9540a90f011d0210588cbfe2fa7daf4219ae9d1ae9e82762075"}150{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"9eb33558-fe1c-4e75-9b9a-c72adb7a15d6","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}151{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}152{"parentUuid":"9eb33558-fe1c-4e75-9b9a-c72adb7a15d6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt9ZL3yf7YzU63vH7F3","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":734,"cache_read_input_tokens":58710,"output_tokens":4573,"output_tokens_details":{"thinking_tokens":197},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":734},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1869,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt9Z4gTE9YDdufWbPvY","requestRef":"28d8acab-78c8-44ef-869a-df20016bbd48","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6fdaa17e-ce21-45d2-b98e-a0580e469cbe","timestamp":"2026-10-30T05:38:29.103Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}153{"parentUuid":"6fdaa17e-ce21-45d2-b98e-a0580e469cbe","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt9ZL3yf7YzU63vH7F3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019Ky9szuyb68BRjEum9SJaD","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from data vintages (T1-forecast)\n\n## Question\nCould the year-over-year growth of US retail and food services sales (RSAFS, g_m = 100·ln(L_m/L_{m−12}), percent) have been forecast in real time at 10 month-end origins (`first_origin` = 2025-10-31 to `last_origin` = 2026-07-31, `n_origins` = 10), h = 1 and h = 3 months beyond the last published month last(V)? And does a model of my own design beat the no-change (naive) forecast when errors are measured against the first-release YoY value of each target month?\n\n## Data and exclusions\n- Inputs (row counts in `n_input_rows`): 10 RSAFS ALFRED vintages and 10 PAYEMS vintages (one per origin), UMCSENT (current), RSAFS current vintage, and `first_release.csv` (28 target months, 2024-06 to 2026-09). All 23 SHA-256 hashes match `data/README.md` (`out/state/data_audit.md`).\n- **Real-time design.** The forecast at origin V uses only the RSAFS vintage dated V (`vintage_used` = `origin_date` in all 80 rows of `out/forecasts.csv`). The target is last(V)+h. Publication delays: for the first six origins (2025-10-31 to 2026-03-31) last(V) is two months before the origin month (e.g. V = 2025-10-31 ends at 2025-08, so its h=1 target is 2025-09 and its h=3 target is 2025-11). From 2026-04-30 on it is one month before (the 2026-04-30 vintage added 2026-02 and 2026-03 at once). Targets therefore run from 2025-09 to 2026-07 (h=1) and from 2025-11 to 2026-09 (h=3). All 20 targets are in `first_release.csv`, and none of them is in the vintage used for its forecast.\n- **Actuals.** `yoy_first_release` is used as given. Because of the irregular calendar, 2025-09 first appears in the 2025-11-30 vintage, and 2026-02 and 2026-03 both first appear in 2026-04-30. Their \"first release\" is defined at month-end granularity (see `data_issues`).\n- **Revisions.** For 2025–2026, the current RSAFS file has levels about 4.7–4.9% below those in the 2026-07-31 vintage. YoY growth is always computed within one vintage, so levels are never mixed across vintages. `RSAFS_current.csv` is used only for the revision estimand (d).\n- **Exclusions** (`out/exclusions.csv`): 20 candidate model forecast–actual pairs, 0 removed, `n_analysed` = 20 (10 per horizon). UMCSENT has 210 empty values, all before 1978. It is not used, and neither is PAYEMS.\n\n## Method\n- **Baselines** (from vintage V only): naive, where the forecast is g_{last(V)} for both horizons; seasonal naive, where the forecast is g_{T−12}; and AR(1), fitted by OLS of g_m on a constant and g_{m−1} for 1993-02 ≤ m ≤ last(V), then iterated h steps.\n- **My model** (`model_name` = rw_drift_base_effect; full text in `model_description`) treats the log level as a random walk with drift. The drift is the mean monthly log change over the last 12 published months: d = (x_l − x_{l−12})/12. The forecast is g_{l+h} = 100·(x_l + h·d − x_{l+h−12}). Unlike the naive forecast, it accounts for the monthly changes that leave the 12-month window (\"base effects\"), all of which are already published at the origin. It uses only the RSAFS vintage dated V. I fixed the specification before computing any forecast error, and nothing was tuned on the evaluation targets.\n- **Evaluation:** RMSE and MAE against `yoy_first_release`. The Diebold–Mariano statistic for the model against naive uses d_t = e²_naive − e²_model and a Bartlett (Newey–West) long-run variance with truncation lag h−1, with no HLN factor and a two-sided normal p-value, as specified in TASK.md.\n- **Revision (d):** the mean over the 10 h=1 targets of |g^current_T − yoy_first_release_T|.\n- `out/analysis.py` regenerates everything deterministically (`random_seed` = null, since no randomness is used).\n\n## Results\nTable 1 (`out/table1.csv`; percentage points; n = 10 per cell):\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 (`rmse_naive_h1`) | 0.849 (`mae_naive_h1`) | 1.420 (`rmse_naive_h3`) | 1.200 (`mae_naive_h3`) |\n| seasonal naive | 1.675 (`rmse_snaive_h1`) | 1.307 (`mae_snaive_h1`) | 1.316 (`rmse_snaive_h3`) | 1.066 (`mae_snaive_h3`) |\n| AR(1) | 0.941 (`rmse_ar1_h1`) | 0.798 (`mae_ar1_h1`) | 1.187 (`rmse_ar1_h3`) | 0.953 (`mae_ar1_h3`) |\n| model | 0.550 (`rmse_model_h1`) | 0.486 (`mae_model_h1`) | 1.142 (`rmse_model_h3`) | 0.934 (`mae_model_h3`) |\n\n- At h=1 the model has the lowest RMSE and MAE of the four methods. Its RMSE is 44.8% below the naive RMSE (`rel_improvement_rmse_h1` = 0.448). DM = 2.43 (`dm_stat_h1`), p = 0.015 (`dm_pvalue_h1`), so `conclusion_code_h1` = model_better_significant.\n- At h=3 the model again has the lowest RMSE and MAE. Its RMSE is 19.6% below naive (`rel_improvement_rmse_h3` = 0.196). DM = 1.55 (`dm_stat_h3`), p = 0.12 (`dm_pvalue_h3`), so `conclusion_code_h3` = model_better_not_significant.\n- Among the baselines, AR(1) is slightly better than naive at both horizons. Seasonal naive is the worst at h=1 but beats naive at h=3.\n- Revision: the mean absolute gap between first-release and current-vintage YoY growth for the h=1 targets is 0.548 pp (`mean_abs_revision_h1_targets`). That is about the same size as the model's h=1 RMSE.\n- `out/figure1.png` shows the first-release actuals with the naive, AR(1) and model forecasts for each horizon.\n\n## Uncertainty\n- With only n = 10 origins, the DM statistic is compared with a normal distribution far outside its asymptotic regime. Its p-values should be read as rough indications.\n- **h=1:** the model's squared error is below the naive one at 8 of 10 origins (aux file `out/state/aux_diagnostics.json`, `n_origins_model_sq_error_below_naive`). However, a single origin (2026-05-31) contributes a loss differential of 3.11, about 45% of the total (`loss_diff_by_origin`).\n- **HLN sensitivity:** applying the Harvey–Leybourne–Newbold factor and t(9) critical values gives a p-value of 0.047 at h=1 and 0.28 at h=3 (`sensitivity_dm_hln_pvalue_t_nminus1`). These are not the required estimand and are reported only as a sensitivity check. The h=1 significance is therefore borderline once small-sample corrections are applied.\n- **h=3:** the forecasts overlap, so errors are serially correlated. With lag-2 Bartlett weights, a long-run variance estimated from 10 points is very imprecise. The h=3 improvement is not distinguishable from zero.\n- No bootstrap was run. A resampling interval built from 10 dependent observations would add little reliability.\n\n## Limitations and open issues\n- **Small sample.** Ten origins in a single 2025–2026 episode, which includes a large jump in YoY growth in spring 2026, cannot establish that the model would generally beat the naive forecast. The h=1 result depends heavily on a few origins.\n- **What the model exploits.** Its advantage is mechanical. It uses the base effects already visible in the vintage, so it is a sensible real-time benchmark rather than a behavioural model. PAYEMS and UMCSENT were deliberately not used, so their value as predictors was not evaluated.\n- **First-release actuals.** These include values that are not advance estimates (2026-02) and are themselves revised later, by a mean of 0.548 pp (`mean_abs_revision_h1_targets`). Rankings evaluated against the current vintage could differ; this was not evaluated.\n- **Gate conflict (open issue).** The executable gate requires origin_date < target_date in `out/forecasts.csv`. Under TASK.md's own definitions (target = last(V)+h, target_date = YYYY-MM-01, month-end origins, and 1–2 month publication lags), every h=1 target month starts on or before its origin date. For example, origin 2025-10-31 has its h=1 target at 2025-09-01. The 40 h=1 rows therefore fail this gate check by construction. Satisfying it would mean misdating the targets, so I did not change them. Instead I verified the substantive information rule: each forecast uses only vintage V, and no target value is present in that vintage (`out/state/checks.md`). As a result, phases P4/P5 are recorded as \"blocked\" by this check only. All other gate checks were run and recorded.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect random-walk-with-drift model has lower RMSE than the naive forecast (0.550 vs 0.997 pp; 44.8% improvement), and the DM test as specified rejects equal accuracy at 5% (DM=2.43, p=0.015).\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"n=10; one origin contributes ~45% of the loss differential; HLN-corrected p=0.047 (sensitivity, aux file).\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the model has lower RMSE than naive (1.142 vs 1.420 pp; 19.6% improvement) but the difference is not significant (DM=1.55, p=0.12).\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\"],\"status\":\"supported\",\"caveat\":\"Overlapping multi-step errors; long-run variance from 10 points is imprecise.\"},\n {\"id\":\"C3\",\"text\":\"Among baselines, AR(1) is slightly better than naive at both horizons and seasonal naive is worst at h=1 but beats naive at h=3.\",\"results_keys\":[\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\",\"rmse_snaive_h1\",\"rmse_snaive_h3\"],\"status\":\"supported\",\"caveat\":\"No significance tests among baselines.\"},\n {\"id\":\"C4\",\"text\":\"First-release YoY growth of the h=1 target months differs from the current-vintage growth by 0.548 pp on average, about the size of the model's h=1 RMSE.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"rmse_model_h1\"],\"status\":\"supported\",\"caveat\":\"Current vintage includes a large level revision; rankings against current data not evaluated.\"},\n {\"id\":\"C5\",\"text\":\"All forecasts are strictly real-time: each uses only the RSAFS vintage dated at its origin, and no target month is present in that vintage.\",\"results_keys\":[\"n_analysed\",\"first_origin\",\"last_origin\"],\"status\":\"supported\",\"caveat\":\"Gate check origin_date<target_date fails for h=1 rows by construction of the TASK target definition (publication lags), documented in report.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'));print('ok')\"","description":"Write report and claims"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":734,"cache_read_input_tokens":58710,"output_tokens":4573,"output_tokens_details":{"thinking_tokens":197},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":734},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt9Z4gTE9YDdufWbPvY","requestRef":"28d8acab-78c8-44ef-869a-df20016bbd48","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"adcf907f-a388-4e70-b913-f3bf7eac4bf1","timestamp":"2026-10-30T05:39:05.121Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}154{"parentUuid":"adcf907f-a388-4e70-b913-f3bf7eac4bf1","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019Ky9szuyb68BRjEum9SJaD","type":"tool_result","content":"ok","is_error":false}]},"uuid":"ef9d167d-cbfa-4a02-b1ae-3b371dd97001","timestamp":"2026-10-30T05:39:05.171Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"adcf907f-a388-4e70-b913-f3bf7eac4bf1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}155{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"8aeeec11e200b132c5a0f6c0de453b4c753777b86e667fc176f57d414412b6f3","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019Ky9szuyb68BRjEum9SJaD","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from data vintages (T1-forecast)\n\n## Question\nCould the year-over-year growth of US retail and food services sales (RSAFS, g_m = 100·ln(L_m/L_{m−12}), percent) have been forecast in real time at 10 month-end origins (`first_origin` = 2025-10-31 to `last_origin` = 2026-07-31, `n_origins` = 10), h = 1 and h = 3 months beyond the last published month last(V)? And does a model of my own design beat the no-change (naive) forecast when errors are measured against the first-release YoY value of each target month?\n\n## Data and exclusions\n- Inputs (row counts in `n_input_rows`): 10 RSAFS ALFRED vintages and 10 PAYEMS vintages (one per origin), UMCSENT (current), RSAFS current vintage, and `first_release.csv` (28 target months, 2024-06 to 2026-09). All 23 SHA-256 hashes match `data/README.md` (`out/state/data_audit.md`).\n- **Real-time design.** The forecast at origin V uses only the RSAFS vintage dated V (`vintage_used` = `origin_date` in all 80 rows of `out/forecasts.csv`). The target is last(V)+h. Publication delays: for the first six origins (2025-10-31 to 2026-03-31) last(V) is two months before the origin month (e.g. V = 2025-10-31 ends at 2025-08, so its h=1 target is 2025-09 and its h=3 target is 2025-11). From 2026-04-30 on it is one month before (the 2026-04-30 vintage added 2026-02 and 2026-03 at once). Targets therefore run from 2025-09 to 2026-07 (h=1) and from 2025-11 to 2026-09 (h=3). All 20 targets are in `first_release.csv`, and none of them is in the vintage used for its forecast.\n- **Actuals.** `yoy_first_release` is used as given. Because of the irregular calendar, 2025-09 first appears in the 2025-11-30 vintage, and 2026-02 and 2026-03 both first appear in 2026-04-30. Their \"first release\" is defined at month-end granularity (see `data_issues`).\n- **Revisions.** For 2025–2026, the current RSAFS file has levels about 4.7–4.9% below those in the 2026-07-31 vintage. YoY growth is always computed within one vintage, so levels are never mixed across vintages. `RSAFS_current.csv` is used only for the revision estimand (d).\n- **Exclusions** (`out/exclusions.csv`): 20 candidate model forecast–actual pairs, 0 removed, `n_analysed` = 20 (10 per horizon). UMCSENT has 210 empty values, all before 1978. It is not used, and neither is PAYEMS.\n\n## Method\n- **Baselines** (from vintage V only): naive, where the forecast is g_{last(V)} for both horizons; seasonal naive, where the forecast is g_{T−12}; and AR(1), fitted by OLS of g_m on a constant and g_{m−1} for 1993-02 ≤ m ≤ last(V), then iterated h steps.\n- **My model** (`model_name` = rw_drift_base_effect; full text in `model_description`) treats the log level as a random walk with drift. The drift is the mean monthly log change over the last 12 published months: d = (x_l − x_{l−12})/12. The forecast is g_{l+h} = 100·(x_l + h·d − x_{l+h−12}). Unlike the naive forecast, it accounts for the monthly changes that leave the 12-month window (\"base effects\"), all of which are already published at the origin. It uses only the RSAFS vintage dated V. I fixed the specification before computing any forecast error, and nothing was tuned on the evaluation targets.\n- **Evaluation:** RMSE and MAE against `yoy_first_release`. The Diebold–Mariano statistic for the model against naive uses d_t = e²_naive − e²_model and a Bartlett (Newey–West) long-run variance with truncation lag h−1, with no HLN factor and a two-sided normal p-value, as specified in TASK.md.\n- **Revision (d):** the mean over the 10 h=1 targets of |g^current_T − yoy_first_release_T|.\n- `out/analysis.py` regenerates everything deterministically (`random_seed` = null, since no randomness is used).\n\n## Results\nTable 1 (`out/table1.csv`; percentage points; n = 10 per cell):\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 (`rmse_naive_h1`) | 0.849 (`mae_naive_h1`) | 1.420 (`rmse_naive_h3`) | 1.200 (`mae_naive_h3`) |\n| seasonal naive | 1.675 (`rmse_snaive_h1`) | 1.307 (`mae_snaive_h1`) | 1.316 (`rmse_snaive_h3`) | 1.066 (`mae_snaive_h3`) |\n| AR(1) | 0.941 (`rmse_ar1_h1`) | 0.798 (`mae_ar1_h1`) | 1.187 (`rmse_ar1_h3`) | 0.953 (`mae_ar1_h3`) |\n| model | 0.550 (`rmse_model_h1`) | 0.486 (`mae_model_h1`) | 1.142 (`rmse_model_h3`) | 0.934 (`mae_model_h3`) |\n\n- At h=1 the model has the lowest RMSE and MAE of the four methods. Its RMSE is 44.8% below the naive RMSE (`rel_improvement_rmse_h1` = 0.448). DM = 2.43 (`dm_stat_h1`), p = 0.015 (`dm_pvalue_h1`), so `conclusion_code_h1` = model_better_significant.\n- At h=3 the model again has the lowest RMSE and MAE. Its RMSE is 19.6% below naive (`rel_improvement_rmse_h3` = 0.196). DM = 1.55 (`dm_stat_h3`), p = 0.12 (`dm_pvalue_h3`), so `conclusion_code_h3` = model_better_not_significant.\n- Among the baselines, AR(1) is slightly better than naive at both horizons. Seasonal naive is the worst at h=1 but beats naive at h=3.\n- Revision: the mean absolute gap between first-release and current-vintage YoY growth for the h=1 targets is 0.548 pp (`mean_abs_revision_h1_targets`). That is about the same size as the model's h=1 RMSE.\n- `out/figure1.png` shows the first-release actuals with the naive, AR(1) and model forecasts for each horizon.\n\n## Uncertainty\n- With only n = 10 origins, the DM statistic is compared with a normal distribution far outside its asymptotic regime. Its p-values should be read as rough indications.\n- **h=1:** the model's squared error is below the naive one at 8 of 10 origins (aux file `out/state/aux_diagnostics.json`, `n_origins_model_sq_error_below_naive`). However, a single origin (2026-05-31) contributes a loss differential of 3.11, about 45% of the total (`loss_diff_by_origin`).\n- **HLN sensitivity:** applying the Harvey–Leybourne–Newbold factor and t(9) critical values gives a p-value of 0.047 at h=1 and 0.28 at h=3 (`sensitivity_dm_hln_pvalue_t_nminus1`). These are not the required estimand and are reported only as a sensitivity check. The h=1 significance is therefore borderline once small-sample corrections are applied.\n- **h=3:** the forecasts overlap, so errors are serially correlated. With lag-2 Bartlett weights, a long-run variance estimated from 10 points is very imprecise. The h=3 improvement is not distinguishable from zero.\n- No bootstrap was run. A resampling interval built from 10 dependent observations would add little reliability.\n\n## Limitations and open issues\n- **Small sample.** Ten origins in a single 2025–2026 episode, which includes a large jump in YoY growth in spring 2026, cannot establish that the model would generally beat the naive forecast. The h=1 result depends heavily on a few origins.\n- **What the model exploits.** Its advantage is mechanical. It uses the base effects already visible in the vintage, so it is a sensible real-time benchmark rather than a behavioural model. PAYEMS and UMCSENT were deliberately not used, so their value as predictors was not evaluated.\n- **First-release actuals.** These include values that are not advance estimates (2026-02) and are themselves revised later, by a mean of 0.548 pp (`mean_abs_revision_h1_targets`). Rankings evaluated against the current vintage could differ; this was not evaluated.\n- **Gate conflict (open issue).** The executable gate requires origin_date < target_date in `out/forecasts.csv`. Under TASK.md's own definitions (target = last(V)+h, target_date = YYYY-MM-01, month-end origins, and 1–2 month publication lags), every h=1 target month starts on or before its origin date. For example, origin 2025-10-31 has its h=1 target at 2025-09-01. The 40 h=1 rows therefore fail this gate check by construction. Satisfying it would mean misdating the targets, so I did not change them. Instead I verified the substantive information rule: each forecast uses only vintage V, and no target value is present in that vintage (`out/state/checks.md`). As a result, phases P4/P5 are recorded as \"blocked\" by this check only. All other gate checks were run and recorded.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect random-walk-with-drift model has lower RMSE than the naive forecast (0.550 vs 0.997 pp; 44.8% improvement), and the DM test as specified rejects equal accuracy at 5% (DM=2.43, p=0.015).\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"n=10; one origin contributes ~45% of the loss differential; HLN-corrected p=0.047 (sensitivity, aux file).\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the model has lower RMSE than naive (1.142 vs 1.420 pp; 19.6% improvement) but the difference is not significant (DM=1.55, p=0.12).\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\"],\"status\":\"supported\",\"caveat\":\"Overlapping multi-step errors; long-run variance from 10 points is imprecise.\"},\n {\"id\":\"C3\",\"text\":\"Among baselines, AR(1) is slightly better than naive at both horizons and seasonal naive is worst at h=1 but beats naive at h=3.\",\"results_keys\":[\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\",\"rmse_snaive_h1\",\"rmse_snaive_h3\"],\"status\":\"supported\",\"caveat\":\"No significance tests among baselines.\"},\n {\"id\":\"C4\",\"text\":\"First-release YoY growth of the h=1 target months differs from the current-vintage growth by 0.548 pp on average, about the size of the model's h=1 RMSE.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"rmse_model_h1\"],\"status\":\"supported\",\"caveat\":\"Current vintage includes a large level revision; rankings against current data not evaluated.\"},\n {\"id\":\"C5\",\"text\":\"All forecasts are strictly real-time: each uses only the RSAFS vintage dated at its origin, and no target month is present in that vintage.\",\"results_keys\":[\"n_analysed\",\"first_origin\",\"last_origin\"],\"status\":\"supported\",\"caveat\":\"Gate check origin_date<target_date fails for h=1 rows by construction of the TASK target definition (publication lags), documented in report.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'));print('ok')\"","description":"Write report and claims"}}]}}156{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"95f06335-39a8-4f83-9c2e-549c2358eaee","timestamp":"2026-10-30T05:39:05.173Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"28d8acab-78c8-44ef-869a-df20016bbd48","keep":52,"tail":["8aeeec11e200b132c5a0f6c0de453b4c753777b86e667fc176f57d414412b6f3","43084fa1f8bee3c73424bbab45b7c7a7824304f5a6d73c2a3503e1a558301fa4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",53,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1e79d5d7fe280f1fc0f02e5712a14353fdc9c8372b8f30df78c7a55a2729add8"}157{"parentUuid":"ef9d167d-cbfa-4a02-b1ae-3b371dd97001","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCRw9aVAp2GQ4xxhDF","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4580,"cache_read_input_tokens":59444,"output_tokens":168,"output_tokens_details":{"thinking_tokens":35},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4580},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":431,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtCRfmZXgApxJEJ32dm","requestRef":"95f06335-39a8-4f83-9c2e-549c2358eaee","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1f0c8228-9914-438f-b88e-69118879194d","timestamp":"2026-10-30T05:39:06.475Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}158{"parentUuid":"1f0c8228-9914-438f-b88e-69118879194d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCRw9aVAp2GQ4xxhDF","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019HC6eaCh1t5x17PpvKRC3e","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|receipt|GATE\"","description":"Run gate at end of P5"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4580,"cache_read_input_tokens":59444,"output_tokens":168,"output_tokens_details":{"thinking_tokens":35},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4580},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtCRfmZXgApxJEJ32dm","requestRef":"95f06335-39a8-4f83-9c2e-549c2358eaee","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2ceb3eef-2c15-4b98-9f91-ef7da121fb1a","timestamp":"2026-10-30T05:39:06.907Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}159{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2ceb3eef-2c15-4b98-9f91-ef7da121fb1a","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}160{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}161{"parentUuid":"2ceb3eef-2c15-4b98-9f91-ef7da121fb1a","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019HC6eaCh1t5x17PpvKRC3e","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (2 of 65 checks failed)\n  [FAIL] phase_ledger: phases not terminal: ['P5']\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053907.685901Z.json","is_error":false}]},"uuid":"a1770c0e-b8ca-45ac-8bd8-f21c27c68e8c","timestamp":"2026-10-30T05:39:07.691Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (2 of 65 checks failed)\n  [FAIL] phase_ledger: phases not terminal: ['P5']\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053907.685901Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2ceb3eef-2c15-4b98-9f91-ef7da121fb1a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}162{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"3d4139e3c8f8885ada26e072eeebb45d5ce9a2a8e1f7995b315bfd2e3dc3afcd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019HC6eaCh1t5x17PpvKRC3e","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|receipt|GATE\"","description":"Run gate at end of P5"}}]}}163{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"bf3070b7-5e3e-4318-8a8d-9de620111727","timestamp":"2026-10-30T05:39:07.693Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"95f06335-39a8-4f83-9c2e-549c2358eaee","keep":54,"tail":["3d4139e3c8f8885ada26e072eeebb45d5ce9a2a8e1f7995b315bfd2e3dc3afcd","351fe310403f2e835a05729dd88939e875e8db868b6957c006e3289d13548609"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",55,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1e7b145be0db9155eea9d13716bbf0aeae6987313085c317e469501e3180a3e2"}164{"parentUuid":"a1770c0e-b8ca-45ac-8bd8-f21c27c68e8c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCciHLBUgNp6XqwuKA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XbGKKzZjhQdRiHV3VYmZJd","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"blocked\",\"checks\":[\"report.md written with 6 required sections; every number cites a results.json key or the aux diagnostics file\",\"claims.json: 5 claims, all results_keys exist in results.json (gate claims check ok)\",\"gate receipt 20261030T053907.685901Z.json: passed=false; only failures = forecasts_chronology (spec conflict) and P5 not yet terminal; final receipt recorded below after status update\"],\"notes\":\"All deliverables complete. Blocked solely because dependency P4 is blocked by the gate chronology rule, which conflicts with TASK.md's target definition (see report, Limitations).\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|receipt|GATE\"","description":"Set P5 status and re-run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":326,"cache_read_input_tokens":64024,"output_tokens":427,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":326},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtCcSAi3KVpiawqVT1K","requestRef":"bf3070b7-5e3e-4318-8a8d-9de620111727","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"af50d031-75ae-4298-a08a-a83c04270bdb","timestamp":"2026-10-30T05:39:11.369Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}165{"parentUuid":"af50d031-75ae-4298-a08a-a83c04270bdb","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XbGKKzZjhQdRiHV3VYmZJd","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053912.178034Z.json","is_error":false}]},"uuid":"9b763a41-eca7-409a-8b88-415aa4a2e464","timestamp":"2026-10-30T05:39:12.183Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0015/out/state/gate_receipts/20261030T053912.178034Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"af50d031-75ae-4298-a08a-a83c04270bdb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}166{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"30e617f6f8d262e3452db03b61b388962c1ba4b1c8b3ffc5cea4d981503747fd","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01XbGKKzZjhQdRiHV3VYmZJd","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"blocked\",\"checks\":[\"report.md written with 6 required sections; every number cites a results.json key or the aux diagnostics file\",\"claims.json: 5 claims, all results_keys exist in results.json (gate claims check ok)\",\"gate receipt 20261030T053907.685901Z.json: passed=false; only failures = forecasts_chronology (spec conflict) and P5 not yet terminal; final receipt recorded below after status update\"],\"notes\":\"All deliverables complete. Blocked solely because dependency P4 is blocked by the gate chronology rule, which conflicts with TASK.md's target definition (see report, Limitations).\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|receipt|GATE\"","description":"Set P5 status and re-run gate"}}]}}167{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"38a1befd-782a-4864-950b-e87e8b539979","timestamp":"2026-10-30T05:39:12.189Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"bf3070b7-5e3e-4318-8a8d-9de620111727","keep":56,"tail":["30e617f6f8d262e3452db03b61b388962c1ba4b1c8b3ffc5cea4d981503747fd","3a1df94429a5ef66c1ee88ce96cb8662758ef7fd48059ac6de262db452179ee4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",57,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0de0cfad72c47890c0456d247fe9a28b3a821c38cd9803e686e0e3503ac65c81"}168{"parentUuid":"9b763a41-eca7-409a-8b88-415aa4a2e464","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCwuCx8JgFa6GenMyB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CkYC5gh9gZcoWYeCXFhfAW","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']['checks'].append(\"final gate receipt out/state/gate_receipts/20261030T053912.178034Z.json: passed=false, 64/65 ok; sole failure forecasts_chronology (40 h=1 rows) - irreconcilable with TASK.md target dating, not altered\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P5: report/claims written; final gate 64/65 ok, sole failure forecasts_chronology (spec conflict, documented). P4/P5 status blocked for that reason only.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|GATE\"","description":"Record final receipt and confirm gate state"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":558,"cache_read_input_tokens":64350,"output_tokens":387,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":558},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtCweKbRTFCA2zPpTT8","requestRef":"38a1befd-782a-4864-950b-e87e8b539979","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aca5d027-daa9-4208-b490-f9b1e986354c","timestamp":"2026-10-30T05:39:15.429Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}169{"parentUuid":"aca5d027-daa9-4208-b490-f9b1e986354c","isSidechain":false,"promptId":"10c01b7a-abe6-463b-a18c-e94d873846a1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CkYC5gh9gZcoWYeCXFhfAW","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80","is_error":false}]},"uuid":"501387d0-5153-47e8-bce4-391c24c841da","timestamp":"2026-10-30T05:39:16.238Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 65 checks failed)\n  [FAIL] forecasts_chronology: 40 rows with target_date <= origin_date out of 80","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"aca5d027-daa9-4208-b490-f9b1e986354c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}170{"type":"api-request-blob","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","hash":"741b6fb42b15c5e79ce04946fac01ffbdf35bdee13306f4e13ada28ff5f5619e","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01CkYC5gh9gZcoWYeCXFhfAW","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']['checks'].append(\"final gate receipt out/state/gate_receipts/20261030T053912.178034Z.json: passed=false, 64/65 ok; sole failure forecasts_chronology (40 h=1 rows) - irreconcilable with TASK.md target dating, not altered\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P5: report/claims written; final gate 64/65 ok, sole failure forecasts_chronology (spec conflict, documented). P4/P5 status blocked for that reason only.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -E \"FAIL|GATE\"","description":"Record final receipt and confirm gate state"}}]}}171{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"0fb23879-8413-4e7d-95d3-a57d75af5d62","timestamp":"2026-10-30T05:39:16.240Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"base":"38a1befd-782a-4864-950b-e87e8b539979","keep":58,"tail":["741b6fb42b15c5e79ce04946fac01ffbdf35bdee13306f4e13ada28ff5f5619e","f016ad55e77e23b343dba56a0b6eb390baf4631f337845aefb657435744dffef"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",59,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a1cc966b6e1bd541ab210791745339559f8845c41e96153ea4fd13f02ab59c8b"}172{"parentUuid":"501387d0-5153-47e8-bce4-391c24c841da","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDFGj8EmRRguSbfNc7","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":463,"cache_read_input_tokens":64908,"output_tokens":1049,"output_tokens_details":{"thinking_tokens":27},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":463},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6036,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtDF16hSbh5pTtocmYD","requestRef":"0fb23879-8413-4e7d-95d3-a57d75af5d62","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1523a637-69e7-4281-9c82-e09bde9257a3","timestamp":"2026-10-30T05:39:24.131Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}173{"parentUuid":"1523a637-69e7-4281-9c82-e09bde9257a3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDFGj8EmRRguSbfNc7","type":"message","role":"assistant","content":[{"type":"text","text":"All the required outputs are written, but the gate still fails 1 of its 65 checks, so I have not marked the task complete. The failing check requires every forecast's target date to fall after its origin date. Under the task's own rules that can't hold for the 1-month-ahead forecasts. Retail sales are published 1–2 months late, so the 1-month target is the month after the last published one, and that month starts on or before the month-end origin. For example, the 2025-10-31 vintage ends at 2025-08, so its 1-month target is 2025-09-01. Passing the check would mean misdating those 40 rows, so I left them as the task defines them.\n\nI checked the real rule directly instead: each forecast uses only the vintage dated at its origin, and none of the 20 target months is already in that vintage. Because of the gate failure, phases P4 and P5 are recorded as \"blocked\"; the conflict is explained in the report under \"Limitations and open issues\".\n\n**Results** (10 origins, errors in percentage points, measured against the first published value):\n\n| | RMSE 1 month | RMSE 3 months |\n|---|---|---|\n| naive | 0.997 | 1.420 |\n| seasonal naive | 1.675 | 1.316 |\n| AR(1) | 0.941 | 1.187 |\n| my model | 0.550 | 1.142 |\n\n- **My model:** I treated the log level as a random walk with drift, using the average monthly change over the last 12 months. It also accounts for the published months that drop out of the 12-month comparison. It uses only the retail-sales vintage, not employment or consumer sentiment. I fixed the design before computing any errors.\n- **1 month ahead:** the model's RMSE is 44.8% lower than the naive forecast's, and the Diebold–Mariano test gives 2.43 (p = 0.015), so it beats naive significantly. This is fragile: one origin (2026-05-31) accounts for about 45% of the advantage. With a standard small-sample correction the p-value rises to 0.047, which is borderline.\n- **3 months ahead:** the model is 19.6% better than naive, but not significantly (test statistic 1.55, p = 0.12).\n- **Revisions:** first-release growth differs from today's figures by 0.548 points on average for the 1-month targets. That is about the size of the model's 1-month error, so results scored against current data could rank the methods differently. I did not test that.\n\n**Other limitations:**\n- Ten origins in one 2025–26 episode is too few to say the model generally beats the naive forecast.\n- The model's edge is mechanical: it uses months that are already published.\n- Whether employment or consumer sentiment would help was not tested.\n- I did not run a bootstrap, so there is no random seed.\n\nI re-ran `analysis.py` from scratch and got identical results, and an independent recomputation of all reported figures matched.\n\nEverything is in `out/`. Open `report.md` first; `forecasts.csv`, `table1.csv`, `figure1.png`, `claims.json` and `analysis.py` sit alongside it, and the audit, checks and phase log are in `out/state/`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":463,"cache_read_input_tokens":64908,"output_tokens":1049,"output_tokens_details":{"thinking_tokens":27},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":463},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtDF16hSbh5pTtocmYD","requestRef":"0fb23879-8413-4e7d-95d3-a57d75af5d62","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"24ed1323-0e9e-4a0d-8ce3-fffc6acaed7e","timestamp":"2026-10-30T05:39:27.125Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}174{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"24ed1323-0e9e-4a0d-8ce3-fffc6acaed7e","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}175{"type":"cost-state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","totalCostUSD":1.2566994000000005,"totalAPIDuration":298875,"totalAPIDurationWithoutRetries":298857,"totalToolDuration":9371,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":308409,"startTime":1793338458744,"modelUsage":{"claude-opus-5-5":{"inputTokens":62,"outputTokens":34261,"thinkingTokens":6423,"cacheReadInputTokens":1259482,"cacheCreationInputTokens":63867,"cacheCreationEphemeral5mInputTokens":63867,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.2566994000000005}},"hasUnknownModelCost":false}176{"type":"tools-used","tools":["Bash","Read"],"sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}177{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:39:28.150Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","content":"The"}178{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:39:28.151Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}179{"parentUuid":"24ed1323-0e9e-4a0d-8ce3-fffc6acaed7e","isSidechain":false,"promptId":"7f56eed1-b3a6-4a04-acbe-d1458b09a819","type":"user","message":{"role":"user","content":"The"},"uuid":"eaaf2e30-06f1-436c-9ac9-e744955da334","timestamp":"2026-10-30T05:39:28.153Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":2},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}180{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"8019eeeb-64a4-4f64-8d24-4f0c93c2ed87","timestamp":"2026-10-30T05:39:28.164Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","04878791a4ae5a01edee17954b71c97fd56de0f9109491e66262bbc3c6bb3485","a7d51a14689c736bdc6134253af204c3366f1278290aea513914a90dd76bbb7a","67645ec020e1e6b6bbfd1a2d7ba54e4644fbed933698bc45c466458dd88b9c73","a6ef24966278b81b849f44d54ae9a650d0bc17a9c34b8398fc371569ba8f7f6a","26897bed99aabf52dc29eb67a806b5b73b3bb40973d7695916f0b058c6b6b46e","aa32db0fd1bed6030d6194201b6d54fa681cb875900210deea09062c8ef639f3","e9b597b63d6d61e2a108b0a3b377981481cd48476571fae5bcd7cda014aa2ba1","d8df8fb025e14680b38a82962e087bed4123cf76f9942811826f76fb86b4f5d3","bc753158b9b6d471a9ecba192f61b8f943bc75e484eab039a6621abe3575ba69","6a199b89984bce3fe4100ae24cd5f3550cec54925daa41b8ef883159b2d340e6","5b0b2fe7db51b85d8c7a0f0d389209d3128fcf53fd6ec552859f9cdb01bb192a","4571087a023e3c02e0f3c32c654ff09a213fa4b2ecee853efb7631ab7ec65240","077c1c01064471c735bac30f8fe60723ac6ff0920ac226b6423d50f36a568fc0","48d55cd02e38850f67f6a1d32facfc38a0d4f6df8da2db2ae3ff0d2b9ad4be1a","ac1078a7db89035243fe0eb0e4892aec26402f59a226c5f06db9ce1f0737db54","480fca72b530dc30874131f72df36f35d22e8cdef41dcd9dec219843028dbb12","ab0d9c4f8993aeb5e0b13c227da44486801a79c02e774601087566d8fbe35d53","5461167802ec2d50f13e8460192843c68521194bc802e650976d621662dd096d","c0113cde44db1d304a3d4c7281965f6a279b2763a17344f38837e39045bfbb59","6aa2ff52fe77f94c141ab99042e17185c73af357bf43cac8625ccec961d5c326","4637f6389a203d5a44f1c64d73c274fb85a9acb8d21af68a0838cd4274115c66","043b9ddfc80b4f70c27aa4e9228f269434c4cae8cc44c50bc58d0488ced48d90","ba3bb920f903244977ea055013cf04a820efc2d595df357ec28227d3caf191d5","ae6e5b640c923593d0b1592be721b91a31ee0ec5c0ff1b1386c039d6b34e6d9f","6edb58ddbc8e733c56c798519499a8fdff3562bb7dfaee33e2a091d558fe6fbd","892a090f76805358b372072b7cbd969e6977ca5685d0f599699a4465540a07d9","3125703822d77377bafcb918ac8678aba4883828db57f47a9c2e5a75799eaffd","a6d46299ded031bbfbfbcc7373f6ced8a961aeaf0d40797fc126a763c86cbe85","ae20fce5849ad418ad0aa85f622c3901eb6bdee3f69a501656d5262e996a17f5","0f1def8a9194edbb86639499f3b185dcfcb79f26433fa313b0888b5baa0dc2c6","27aef3ca80d375116ed3293a26a0aa1423efed4861387897e9c9e6c3b0107958","0403386b4a8d3dda157877c6cac499088a58796780926652970e0e58201b3e90","69f9e3a6cb41c352c54edbaa67ed5d540590d4297b1ccc31209742f13993f21e","a78df37466699fa31325c66f582a15b44286d0148f1bba44050c6ae3242b2e09","5abea8ec5bc98bc32f15d247997b395db6a6d6bcaf17115c9bfb4c36c4ad2524","b168e7ed119fea63c1358b3cc8315a81ef5b2f18dc4dfd255c2cff06dc63bfbb","a25195d20ce1d077022587497406bbd37868f109e44a90b7e875a8ed7569c957","23a398b3677b1b03a8e0e67676ead9cfe48d73502ed9da97a7d1aadebdab4832","1ee9d72691e695a84fedeabcdf35f63f588db644fd6ef3da36441a0f8f58b2b9","d4a62c5e59bb5b3b2f582cffdc3c6e64271998151da2f43a651dbe2bf24b6dc5","6f11c8213c51fa6cfa0eaa99d61e4f2032890daf84044fe5c6da5a4300a0f856","cd5f4cc011bcfaf8ecdf54acb66c3f610210a3bdd050240e7130f4182dd726d4","62b255dc058f54aa7c37c94e8d0ff8596cd1f7b89b6fdb5f3f32f8ef392d71a4","f3d2916595c422cefc357854743e6e47938ec575229593d2c1efedff66e45a7b","4157c2511eb19e369cda77f9983f0a1d336982bb239b8f9fe3e29673a24a515b","3abdf310db774836d3cf04cfa4b7bd4299e93fa5930acd47bc1a7bdc1556fe18","b97c5a16a351777405dc704f9b10a5793f958edfbed3261afc907c04c6fab434","0534f214ec3367fcd6b46ec374fc0ae556f111cef162116dec6f113be0dcf664","730569146f7ecd180ec792208afa520bc929fafabfd597f139ecad9c29ada61b","b7cd58fba340fa33bc1d9afaef5db89c56363e74bf87fd929526bff196a8efba","8aeeec11e200b132c5a0f6c0de453b4c753777b86e667fc176f57d414412b6f3","43084fa1f8bee3c73424bbab45b7c7a7824304f5a6d73c2a3503e1a558301fa4","3d4139e3c8f8885ada26e072eeebb45d5ce9a2a8e1f7995b315bfd2e3dc3afcd","351fe310403f2e835a05729dd88939e875e8db868b6957c006e3289d13548609","30e617f6f8d262e3452db03b61b388962c1ba4b1c8b3ffc5cea4d981503747fd","3a1df94429a5ef66c1ee88ce96cb8662758ef7fd48059ac6de262db452179ee4","741b6fb42b15c5e79ce04946fac01ffbdf35bdee13306f4e13ada28ff5f5619e","f016ad55e77e23b343dba56a0b6eb390baf4631f337845aefb657435744dffef","65779aa07872ce2c34515198ed77d969bcfc876bc96498b3c7ebac08f9f56719","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",61,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"dfa7b2bbdd5516fd20907fd38eb38ccd4075399538353d9c52e2020ce6751289"}181{"parentUuid":"eaaf2e30-06f1-436c-9ac9-e744955da334","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtE8Sygsvazh2rtayTc","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1052,"cache_read_input_tokens":65371,"output_tokens":288,"output_tokens_details":{"thinking_tokens":32},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1052},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":230,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtE84uenBXkbvK3cLnM","requestRef":"8019eeeb-64a4-4f64-8d24-4f0c93c2ed87","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cdcf0399-2dc2-4b33-a993-26b7c0989a5f","timestamp":"2026-10-30T05:39:29.098Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}182{"parentUuid":"cdcf0399-2dc2-4b33-a993-26b7c0989a5f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtE8Sygsvazh2rtayTc","type":"message","role":"assistant","content":[{"type":"text","text":"Your message came through as just \"The\", so it looks like it was cut off. What did you want to say or have me do?\n\nWhere things stand:\n- **Outputs:** all the required files are in `out/`, the results reproduce exactly when re-run, and the gate passes 64 of its 65 checks.\n- **Gate failure:** the one failing check wants every target date to fall after its origin date. Under the task's own definitions that can't hold for the 40 one-month-ahead forecasts. Because publication runs 1–2 months late, their target month starts on or before the origin date. The report explains this, and I left those dates as the task defines them.\n- **Possible next steps:** respond to the separate reviewer's issues once they arrive, change part of the analysis, or have the task's date rule or the gate reconciled on your side."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":1052,"cache_read_input_tokens":65371,"output_tokens":288,"output_tokens_details":{"thinking_tokens":32},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1052},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtE84uenBXkbvK3cLnM","requestRef":"8019eeeb-64a4-4f64-8d24-4f0c93c2ed87","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7a05220d-6ed7-4a07-b76c-518cd8a1f7af","timestamp":"2026-10-30T05:39:31.813Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}183{"type":"last-prompt","lastPrompt":"The","leafUuid":"7a05220d-6ed7-4a07-b76c-518cd8a1f7af","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}184{"type":"mode","mode":"normal","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}185{"type":"atis-latch","atis":"","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}186{"type":"cost-state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","totalCostUSD":1.2808096000000004,"totalAPIDuration":302539,"totalAPIDurationWithoutRetries":302520,"totalToolDuration":9371,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":312107,"startTime":1793338458744,"modelUsage":{"claude-opus-5-5":{"inputTokens":66,"outputTokens":34549,"thinkingTokens":6455,"cacheReadInputTokens":1324853,"cacheCreationInputTokens":64919,"cacheCreationEphemeral5mInputTokens":64919,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.2808096000000004}},"hasUnknownModelCost":false}187{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:39:32.813Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","content":"The"}188{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:39:32.814Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}189{"parentUuid":"7a05220d-6ed7-4a07-b76c-518cd8a1f7af","isSidechain":false,"promptId":"5374c4ac-8eef-45ae-b2fa-ec0e88058810","type":"user","message":{"role":"user","content":"The"},"uuid":"332887ef-485c-4d30-944e-1d94a280d653","timestamp":"2026-10-30T05:39:32.817Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":3},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}190{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"8877985c-0a0a-4263-b375-982cc0784c7c","timestamp":"2026-10-30T05:39:32.827Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","04878791a4ae5a01edee17954b71c97fd56de0f9109491e66262bbc3c6bb3485","a7d51a14689c736bdc6134253af204c3366f1278290aea513914a90dd76bbb7a","67645ec020e1e6b6bbfd1a2d7ba54e4644fbed933698bc45c466458dd88b9c73","a6ef24966278b81b849f44d54ae9a650d0bc17a9c34b8398fc371569ba8f7f6a","26897bed99aabf52dc29eb67a806b5b73b3bb40973d7695916f0b058c6b6b46e","aa32db0fd1bed6030d6194201b6d54fa681cb875900210deea09062c8ef639f3","e9b597b63d6d61e2a108b0a3b377981481cd48476571fae5bcd7cda014aa2ba1","d8df8fb025e14680b38a82962e087bed4123cf76f9942811826f76fb86b4f5d3","bc753158b9b6d471a9ecba192f61b8f943bc75e484eab039a6621abe3575ba69","6a199b89984bce3fe4100ae24cd5f3550cec54925daa41b8ef883159b2d340e6","5b0b2fe7db51b85d8c7a0f0d389209d3128fcf53fd6ec552859f9cdb01bb192a","4571087a023e3c02e0f3c32c654ff09a213fa4b2ecee853efb7631ab7ec65240","077c1c01064471c735bac30f8fe60723ac6ff0920ac226b6423d50f36a568fc0","48d55cd02e38850f67f6a1d32facfc38a0d4f6df8da2db2ae3ff0d2b9ad4be1a","ac1078a7db89035243fe0eb0e4892aec26402f59a226c5f06db9ce1f0737db54","480fca72b530dc30874131f72df36f35d22e8cdef41dcd9dec219843028dbb12","ab0d9c4f8993aeb5e0b13c227da44486801a79c02e774601087566d8fbe35d53","5461167802ec2d50f13e8460192843c68521194bc802e650976d621662dd096d","c0113cde44db1d304a3d4c7281965f6a279b2763a17344f38837e39045bfbb59","6aa2ff52fe77f94c141ab99042e17185c73af357bf43cac8625ccec961d5c326","4637f6389a203d5a44f1c64d73c274fb85a9acb8d21af68a0838cd4274115c66","043b9ddfc80b4f70c27aa4e9228f269434c4cae8cc44c50bc58d0488ced48d90","ba3bb920f903244977ea055013cf04a820efc2d595df357ec28227d3caf191d5","ae6e5b640c923593d0b1592be721b91a31ee0ec5c0ff1b1386c039d6b34e6d9f","6edb58ddbc8e733c56c798519499a8fdff3562bb7dfaee33e2a091d558fe6fbd","892a090f76805358b372072b7cbd969e6977ca5685d0f599699a4465540a07d9","3125703822d77377bafcb918ac8678aba4883828db57f47a9c2e5a75799eaffd","a6d46299ded031bbfbfbcc7373f6ced8a961aeaf0d40797fc126a763c86cbe85","ae20fce5849ad418ad0aa85f622c3901eb6bdee3f69a501656d5262e996a17f5","0f1def8a9194edbb86639499f3b185dcfcb79f26433fa313b0888b5baa0dc2c6","27aef3ca80d375116ed3293a26a0aa1423efed4861387897e9c9e6c3b0107958","0403386b4a8d3dda157877c6cac499088a58796780926652970e0e58201b3e90","69f9e3a6cb41c352c54edbaa67ed5d540590d4297b1ccc31209742f13993f21e","a78df37466699fa31325c66f582a15b44286d0148f1bba44050c6ae3242b2e09","5abea8ec5bc98bc32f15d247997b395db6a6d6bcaf17115c9bfb4c36c4ad2524","b168e7ed119fea63c1358b3cc8315a81ef5b2f18dc4dfd255c2cff06dc63bfbb","a25195d20ce1d077022587497406bbd37868f109e44a90b7e875a8ed7569c957","23a398b3677b1b03a8e0e67676ead9cfe48d73502ed9da97a7d1aadebdab4832","1ee9d72691e695a84fedeabcdf35f63f588db644fd6ef3da36441a0f8f58b2b9","d4a62c5e59bb5b3b2f582cffdc3c6e64271998151da2f43a651dbe2bf24b6dc5","6f11c8213c51fa6cfa0eaa99d61e4f2032890daf84044fe5c6da5a4300a0f856","cd5f4cc011bcfaf8ecdf54acb66c3f610210a3bdd050240e7130f4182dd726d4","62b255dc058f54aa7c37c94e8d0ff8596cd1f7b89b6fdb5f3f32f8ef392d71a4","f3d2916595c422cefc357854743e6e47938ec575229593d2c1efedff66e45a7b","4157c2511eb19e369cda77f9983f0a1d336982bb239b8f9fe3e29673a24a515b","3abdf310db774836d3cf04cfa4b7bd4299e93fa5930acd47bc1a7bdc1556fe18","b97c5a16a351777405dc704f9b10a5793f958edfbed3261afc907c04c6fab434","0534f214ec3367fcd6b46ec374fc0ae556f111cef162116dec6f113be0dcf664","730569146f7ecd180ec792208afa520bc929fafabfd597f139ecad9c29ada61b","b7cd58fba340fa33bc1d9afaef5db89c56363e74bf87fd929526bff196a8efba","8aeeec11e200b132c5a0f6c0de453b4c753777b86e667fc176f57d414412b6f3","43084fa1f8bee3c73424bbab45b7c7a7824304f5a6d73c2a3503e1a558301fa4","3d4139e3c8f8885ada26e072eeebb45d5ce9a2a8e1f7995b315bfd2e3dc3afcd","351fe310403f2e835a05729dd88939e875e8db868b6957c006e3289d13548609","30e617f6f8d262e3452db03b61b388962c1ba4b1c8b3ffc5cea4d981503747fd","3a1df94429a5ef66c1ee88ce96cb8662758ef7fd48059ac6de262db452179ee4","741b6fb42b15c5e79ce04946fac01ffbdf35bdee13306f4e13ada28ff5f5619e","f016ad55e77e23b343dba56a0b6eb390baf4631f337845aefb657435744dffef","65779aa07872ce2c34515198ed77d969bcfc876bc96498b3c7ebac08f9f56719","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c","63fd6023d4c71857c7f1bd2968bd19fb65e90e3bacdc8618386bec739b48f6e3","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",63,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8ba0fa358e2dfae71a80ac7b73a3e68f694b13d40f1fcbb2d33a1d4bd33333dd"}191{"parentUuid":"332887ef-485c-4d30-944e-1d94a280d653","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEUS2KMGER5JCSZZTN","type":"message","role":"assistant","content":[{"type":"text","text":"Your message again came through as just \"The\", so it was probably cut off before sending. Could you resend it in full?\n\nThings stand as before:\n- **Deliverables:** all required files are in `out/`, and re-running `out/analysis.py` gives identical results.\n- **Gate:** 64 of 65 checks pass. The one failure is the rule that every target date must fall after its origin date. Under the task's own definitions, the 40 one-month-ahead targets start on or before their origin date, because the data are published 1–2 months late. I left those dates as the task defines them and explained this in `out/report.md`.\n- **Phases:** P0–P3 are passed; P4 and P5 are recorded as blocked only because of that one gate check.\n\nIf you want something specific, such as handling the reviewer's issues, changing the model, or treating the gate conflict differently, tell me and I'll do it."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":293,"cache_read_input_tokens":66423,"output_tokens":281,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":293},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtEU9uJDuyaG4ToJ2Cg","requestRef":"8877985c-0a0a-4263-b375-982cc0784c7c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"58328230-92aa-4ab6-913e-bd923d1bb221","timestamp":"2026-10-30T05:39:36.539Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}192{"type":"last-prompt","lastPrompt":"The","leafUuid":"58328230-92aa-4ab6-913e-bd923d1bb221","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}193{"type":"cost-state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","totalCostUSD":1.3011952000000004,"totalAPIDuration":306264,"totalAPIDurationWithoutRetries":306244,"totalToolDuration":9371,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":315861,"startTime":1793338458744,"modelUsage":{"claude-opus-5-5":{"inputTokens":70,"outputTokens":34830,"thinkingTokens":6455,"cacheReadInputTokens":1391276,"cacheCreationInputTokens":65212,"cacheCreationEphemeral5mInputTokens":65212,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.3011952000000004}},"hasUnknownModelCost":false}194{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:39:37.612Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","content":"The"}195{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:39:37.613Z","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}196{"parentUuid":"58328230-92aa-4ab6-913e-bd923d1bb221","isSidechain":false,"promptId":"848eba36-f632-4fdd-a220-4a2b5ad43853","type":"user","message":{"role":"user","content":"The"},"uuid":"df3d9e94-382b-4623-99d8-ffe81af20ef7","timestamp":"2026-10-30T05:39:37.616Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":4},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}197{"type":"api-request","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","id":"67184245-f31b-412a-9a78-46259f5d9700","timestamp":"2026-10-30T05:39:37.627Z","version":"2.1.314","querySource":"sdk","shapeHash":"5b7d8eaa465e2e5d8a5ebcbb4733e01e36592a4db9c842a1740e646909e0456c","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","04878791a4ae5a01edee17954b71c97fd56de0f9109491e66262bbc3c6bb3485","a7d51a14689c736bdc6134253af204c3366f1278290aea513914a90dd76bbb7a","67645ec020e1e6b6bbfd1a2d7ba54e4644fbed933698bc45c466458dd88b9c73","a6ef24966278b81b849f44d54ae9a650d0bc17a9c34b8398fc371569ba8f7f6a","26897bed99aabf52dc29eb67a806b5b73b3bb40973d7695916f0b058c6b6b46e","aa32db0fd1bed6030d6194201b6d54fa681cb875900210deea09062c8ef639f3","e9b597b63d6d61e2a108b0a3b377981481cd48476571fae5bcd7cda014aa2ba1","d8df8fb025e14680b38a82962e087bed4123cf76f9942811826f76fb86b4f5d3","bc753158b9b6d471a9ecba192f61b8f943bc75e484eab039a6621abe3575ba69","6a199b89984bce3fe4100ae24cd5f3550cec54925daa41b8ef883159b2d340e6","5b0b2fe7db51b85d8c7a0f0d389209d3128fcf53fd6ec552859f9cdb01bb192a","4571087a023e3c02e0f3c32c654ff09a213fa4b2ecee853efb7631ab7ec65240","077c1c01064471c735bac30f8fe60723ac6ff0920ac226b6423d50f36a568fc0","48d55cd02e38850f67f6a1d32facfc38a0d4f6df8da2db2ae3ff0d2b9ad4be1a","ac1078a7db89035243fe0eb0e4892aec26402f59a226c5f06db9ce1f0737db54","480fca72b530dc30874131f72df36f35d22e8cdef41dcd9dec219843028dbb12","ab0d9c4f8993aeb5e0b13c227da44486801a79c02e774601087566d8fbe35d53","5461167802ec2d50f13e8460192843c68521194bc802e650976d621662dd096d","c0113cde44db1d304a3d4c7281965f6a279b2763a17344f38837e39045bfbb59","6aa2ff52fe77f94c141ab99042e17185c73af357bf43cac8625ccec961d5c326","4637f6389a203d5a44f1c64d73c274fb85a9acb8d21af68a0838cd4274115c66","043b9ddfc80b4f70c27aa4e9228f269434c4cae8cc44c50bc58d0488ced48d90","ba3bb920f903244977ea055013cf04a820efc2d595df357ec28227d3caf191d5","ae6e5b640c923593d0b1592be721b91a31ee0ec5c0ff1b1386c039d6b34e6d9f","6edb58ddbc8e733c56c798519499a8fdff3562bb7dfaee33e2a091d558fe6fbd","892a090f76805358b372072b7cbd969e6977ca5685d0f599699a4465540a07d9","3125703822d77377bafcb918ac8678aba4883828db57f47a9c2e5a75799eaffd","a6d46299ded031bbfbfbcc7373f6ced8a961aeaf0d40797fc126a763c86cbe85","ae20fce5849ad418ad0aa85f622c3901eb6bdee3f69a501656d5262e996a17f5","0f1def8a9194edbb86639499f3b185dcfcb79f26433fa313b0888b5baa0dc2c6","27aef3ca80d375116ed3293a26a0aa1423efed4861387897e9c9e6c3b0107958","0403386b4a8d3dda157877c6cac499088a58796780926652970e0e58201b3e90","69f9e3a6cb41c352c54edbaa67ed5d540590d4297b1ccc31209742f13993f21e","a78df37466699fa31325c66f582a15b44286d0148f1bba44050c6ae3242b2e09","5abea8ec5bc98bc32f15d247997b395db6a6d6bcaf17115c9bfb4c36c4ad2524","b168e7ed119fea63c1358b3cc8315a81ef5b2f18dc4dfd255c2cff06dc63bfbb","a25195d20ce1d077022587497406bbd37868f109e44a90b7e875a8ed7569c957","23a398b3677b1b03a8e0e67676ead9cfe48d73502ed9da97a7d1aadebdab4832","1ee9d72691e695a84fedeabcdf35f63f588db644fd6ef3da36441a0f8f58b2b9","d4a62c5e59bb5b3b2f582cffdc3c6e64271998151da2f43a651dbe2bf24b6dc5","6f11c8213c51fa6cfa0eaa99d61e4f2032890daf84044fe5c6da5a4300a0f856","cd5f4cc011bcfaf8ecdf54acb66c3f610210a3bdd050240e7130f4182dd726d4","62b255dc058f54aa7c37c94e8d0ff8596cd1f7b89b6fdb5f3f32f8ef392d71a4","f3d2916595c422cefc357854743e6e47938ec575229593d2c1efedff66e45a7b","4157c2511eb19e369cda77f9983f0a1d336982bb239b8f9fe3e29673a24a515b","3abdf310db774836d3cf04cfa4b7bd4299e93fa5930acd47bc1a7bdc1556fe18","b97c5a16a351777405dc704f9b10a5793f958edfbed3261afc907c04c6fab434","0534f214ec3367fcd6b46ec374fc0ae556f111cef162116dec6f113be0dcf664","730569146f7ecd180ec792208afa520bc929fafabfd597f139ecad9c29ada61b","b7cd58fba340fa33bc1d9afaef5db89c56363e74bf87fd929526bff196a8efba","8aeeec11e200b132c5a0f6c0de453b4c753777b86e667fc176f57d414412b6f3","43084fa1f8bee3c73424bbab45b7c7a7824304f5a6d73c2a3503e1a558301fa4","3d4139e3c8f8885ada26e072eeebb45d5ce9a2a8e1f7995b315bfd2e3dc3afcd","351fe310403f2e835a05729dd88939e875e8db868b6957c006e3289d13548609","30e617f6f8d262e3452db03b61b388962c1ba4b1c8b3ffc5cea4d981503747fd","3a1df94429a5ef66c1ee88ce96cb8662758ef7fd48059ac6de262db452179ee4","741b6fb42b15c5e79ce04946fac01ffbdf35bdee13306f4e13ada28ff5f5619e","f016ad55e77e23b343dba56a0b6eb390baf4631f337845aefb657435744dffef","65779aa07872ce2c34515198ed77d969bcfc876bc96498b3c7ebac08f9f56719","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c","63fd6023d4c71857c7f1bd2968bd19fb65e90e3bacdc8618386bec739b48f6e3","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c","7994e0c14c2953c2e7217c7365da1aaf9fd4857ca8361a7656fccb99b02496a7","b60bfcffe9f186fe98f0a9d3641a90cabaf939999df45aac04e41c0e3a3c294c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",65,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"68a149dfd5618dd4999e8706ea2220edc15ef40778b8028258cf8d75f4c8cee6"}198{"parentUuid":"df3d9e94-382b-4623-99d8-ffe81af20ef7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEs43rcvUA2SygauCK","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":286,"cache_read_input_tokens":66716,"output_tokens":109,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":286},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":575,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtErmSgYESMvZbSqLmr","requestRef":"67184245-f31b-412a-9a78-46259f5d9700","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d96dc60d-4131-4f2e-acc0-c8c788851a33","timestamp":"2026-10-30T05:39:39.561Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}199{"parentUuid":"d96dc60d-4131-4f2e-acc0-c8c788851a33","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEs43rcvUA2SygauCK","type":"message","role":"assistant","content":[{"type":"text","text":"Your message came through as just \"The\" for the third time, so it is probably being cut off before it sends. Could you try typing it again, perhaps as a longer sentence?\n\nNothing has changed since my last reply, and I'm waiting for your instructions before doing anything else."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":286,"cache_read_input_tokens":66716,"output_tokens":109,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":286},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtErmSgYESMvZbSqLmr","requestRef":"67184245-f31b-412a-9a78-46259f5d9700","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7a9f375f-2a70-41de-b227-35eea86d646f","timestamp":"2026-10-30T05:39:40.148Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0015","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","version":"2.1.314","gitBranch":"HEAD"}200{"type":"last-prompt","lastPrompt":"The","leafUuid":"7a9f375f-2a70-41de-b227-35eea86d646f","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27"}201{"type":"cost-state","sessionId":"49c3fd2c-5671-4194-8b1e-242022ed2a27","totalCostUSD":1.3181644000000003,"totalAPIDuration":308798,"totalAPIDurationWithoutRetries":308777,"totalToolDuration":9371,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":318429,"startTime":1793338458744,"modelUsage":{"claude-opus-5-5":{"inputTokens":74,"outputTokens":34939,"thinkingTokens":6479,"cacheReadInputTokens":1457992,"cacheCreationInputTokens":65498,"cacheCreationEphemeral5mInputTokens":65498,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":1.3181644000000003}},"hasUnknownModelCost":false}202