1{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:35:24.381Z","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:35:24.385Z","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}4{"parentUuid":null,"isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":"Begin"},"uuid":"655bd6de-1171-4c07-b121-803e8b68fd57","timestamp":"2026-10-30T05:35:24.388Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","timestamp":"2026-10-30T05:35:24.397Z","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/RT0016\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"}],"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":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"21a7428e-347f-4ed4-aeb5-65352472fe87","timestamp":"2026-10-30T05:35:24.397Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"bc739a4f2b8c017572aa0b68d37b2621bbd8ef6cb0ed0b83600a0ee4c3fd44cf"}8{"parentUuid":"655bd6de-1171-4c07-b121-803e8b68fd57","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"1d6d2861-70d7-4d33-9b7a-df2423dc2346","timestamp":"2026-10-30T05:35:24.392Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"1d6d2861-70d7-4d33-9b7a-df2423dc2346","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"8fefda56-816e-4060-8ac6-0baa6920984e","timestamp":"2026-10-30T05:35:24.392Z","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/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"8fefda56-816e-4060-8ac6-0baa6920984e","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":"746138f4-4177-4e55-927b-1d3eaf13f211","timestamp":"2026-10-30T05:35:24.392Z","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/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}12{"parentUuid":"746138f4-4177-4e55-927b-1d3eaf13f211","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvJ2wi2ysX5UxYZBkz","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":2209,"cache_read_input_tokens":1504,"output_tokens":125,"output_tokens_details":{"thinking_tokens":19},"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":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":409,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsvHibF16Lw16C1tmu8","requestRef":"21a7428e-347f-4ed4-aeb5-65352472fe87","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"10c88708-b79c-49cb-973f-3c6bfb652eef","timestamp":"2026-10-30T05:35:27.728Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"10c88708-b79c-49cb-973f-3c6bfb652eef","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvJ2wi2ysX5UxYZBkz","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016YbHEokVXiLoHqm8hgi8qK","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 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":2209,"cache_read_input_tokens":1504,"output_tokens":125,"output_tokens_details":{"thinking_tokens":19},"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":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsvHibF16Lw16C1tmu8","requestRef":"21a7428e-347f-4ed4-aeb5-65352472fe87","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3e3a6095-812b-45b0-b1fa-2ef72a808f1e","timestamp":"2026-10-30T05:35:28.381Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"3e3a6095-812b-45b0-b1fa-2ef72a808f1e","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016YbHEokVXiLoHqm8hgi8qK","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 01:35 ..\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\ndata:\nfirst_release.csv\nREADME.md\nRSAFS_current.csv\nUMCSENT.csv\nvintages\n\ndata/vintages:\nPAYEMS_vintage_2025-10-31.csv\nPAYEMS_vintage_2025-11-30.csv\nPAYEMS_vintage_2025-12-31.csv\nPAYEMS_vintage_2026-01-31.csv\nPAYEMS_vintage_2026-02-28.csv\nPAYEMS_vintage_2026-03-31.csv\nPAYEMS_vintage_2026-04-30.csv\nPAYEMS_vintage_2026-05-31.csv\nPAYEMS_vintage_2026-06-30.csv\nPAYEMS_vintage_2026-07-31.csv\nRSAFS_vintage_2025-10-31.csv\nRSAFS_vintage_2025-11-30.csv\nRSAFS_vintage_2025-12-31.csv\nRSAFS_vintage_2026-01-31.csv\nRSAFS_vintage_2026-02-28.csv\nRSAFS_vintage_2026-03-31.csv\nRSAFS_vintage_2026-04-30.csv\nRSAFS_vintage_2026-05-31.csv\nRSAFS_vintage_2026-06-30.csv\nRSAFS_vintage_2026-07-31.csv","is_error":false}]},"uuid":"0ac804a8-b168-4f5a-8c52-23e76bff8925","timestamp":"2026-10-30T05:35:28.470Z","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 01:35 ..\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\ndata:\nfirst_release.csv\nREADME.md\nRSAFS_current.csv\nUMCSENT.csv\nvintages\n\ndata/vintages:\nPAYEMS_vintage_2025-10-31.csv\nPAYEMS_vintage_2025-11-30.csv\nPAYEMS_vintage_2025-12-31.csv\nPAYEMS_vintage_2026-01-31.csv\nPAYEMS_vintage_2026-02-28.csv\nPAYEMS_vintage_2026-03-31.csv\nPAYEMS_vintage_2026-04-30.csv\nPAYEMS_vintage_2026-05-31.csv\nPAYEMS_vintage_2026-06-30.csv\nPAYEMS_vintage_2026-07-31.csv\nRSAFS_vintage_2025-10-31.csv\nRSAFS_vintage_2025-11-30.csv\nRSAFS_vintage_2025-12-31.csv\nRSAFS_vintage_2026-01-31.csv\nRSAFS_vintage_2026-02-28.csv\nRSAFS_vintage_2026-03-31.csv\nRSAFS_vintage_2026-04-30.csv\nRSAFS_vintage_2026-05-31.csv\nRSAFS_vintage_2026-06-30.csv\nRSAFS_vintage_2026-07-31.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3e3a6095-812b-45b0-b1fa-2ef72a808f1e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"0af54e53ed93bb764ef75489bcb2c66828e2e89e10153c7e950911059cfccf3b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016YbHEokVXiLoHqm8hgi8qK","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"d3aeb2b0-f39f-4127-b0c5-0b9189e69f71","timestamp":"2026-10-30T05:35:28.474Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"21a7428e-347f-4ed4-aeb5-65352472fe87","keep":2,"tail":["0af54e53ed93bb764ef75489bcb2c66828e2e89e10153c7e950911059cfccf3b","82c36baf0c7f6d724cb5a06b0d0d631ca03a81084b4d1a7a3bdb824712ed4cc0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"bc14618ca1245fa8ffefa16d6c33e268c6b2994102867c4baf65c707f2c2edec"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"0ac804a8-b168-4f5a-8c52-23e76bff8925","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}18{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}19{"parentUuid":"0ac804a8-b168-4f5a-8c52-23e76bff8925","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvSvyuAjpkcE44ozYz","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":4875,"cache_read_input_tokens":3713,"output_tokens":305,"output_tokens_details":{"thinking_tokens":82},"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":4875},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":606,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsvSecahZTfydAL7wpg","requestRef":"d3aeb2b0-f39f-4127-b0c5-0b9189e69f71","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a1d5c8ca-f99e-4bec-b2a4-78b7c08f6faa","timestamp":"2026-10-30T05:35:30.425Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"a1d5c8ca-f99e-4bec-b2a4-78b7c08f6faa","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvSvyuAjpkcE44ozYz","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HV1PvEX7VyDTXDYTW33D8x","name":"Bash","input":{"command":"cat data/README.md; cat data/first_release.csv; cd data/vintages; for f in *; do echo \"$f $(wc -l <$f) $(head -1 $f) $(tail -2 $f|tr '\\n' ' ')\"; done; cd ..; tail -3 RSAFS_current.csv UMCSENT.csv; grep -c ',$' UMCSENT.csv; shasum -a 256 *.csv vintages/*","description":"Inspect data files and provenance"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4875,"cache_read_input_tokens":3713,"output_tokens":305,"output_tokens_details":{"thinking_tokens":82},"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":4875},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsvSecahZTfydAL7wpg","requestRef":"d3aeb2b0-f39f-4127-b0c5-0b9189e69f71","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4610fb8c-6d5a-49a4-93ef-467a9e853141","timestamp":"2026-10-30T05:35:32.179Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}21{"parentUuid":"4610fb8c-6d5a-49a4-93ef-467a9e853141","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HV1PvEX7VyDTXDYTW33D8x","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.\ntarget_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\nPAYEMS_vintage_2025-10-31.csv 1041 observation_date,PAYEMS_20251031 2025-07-01,159518 2025-08-01,159540 \nPAYEMS_vintage_2025-11-30.csv 1042 observation_date,PAYEMS_20251130 2025-08-01,159507 2025-09-01,159626 \nPAYEMS_vintage_2025-12-31.csv 1044 observation_date,PAYEMS_20251231 2025-10-01,159488 2025-11-01,159552 \nPAYEMS_vintage_2026-01-31.csv 1045 observation_date,PAYEMS_20260131 2025-11-01,159476 2025-12-01,159526 \nPAYEMS_vintage_2026-02-28.csv 1046 observation_date,PAYEMS_20260228 2025-12-01,158497 2026-01-01,158627 \nPAYEMS_vintage_2026-03-31.csv 1047 observation_date,PAYEMS_20260331 2026-01-01,158558 2026-02-01,158466 \nPAYEMS_vintage_2026-04-30.csv 1048 observation_date,PAYEMS_20260430 2026-02-01,158459 2026-03-01,158637 \nPAYEMS_vintage_2026-05-31.csv 1049 observation_date,PAYEMS_20260531 2026-03-01,158621 2026-04-01,158736 \nPAYEMS_vintage_2026-06-30.csv 1050 observation_date,PAYEMS_20260630 2026-04-01,158829 2026-05-01,159001 \nPAYEMS_vintage_2026-07-31.csv 1051 observation_date,PAYEMS_20260731 2026-05-01,158927 2026-06-01,158984 \nRSAFS_vintage_2025-10-31.csv 405 observation_date,RSAFS_20251031 2025-07-01,727414 2025-08-01,732010 \nRSAFS_vintage_2025-11-30.csv 406 observation_date,RSAFS_20251130 2025-08-01,732059 2025-09-01,733258 \nRSAFS_vintage_2025-12-31.csv 407 observation_date,RSAFS_20251231 2025-09-01,732444 2025-10-01,732633 \nRSAFS_vintage_2026-01-31.csv 408 observation_date,RSAFS_20260131 2025-10-01,731412 2025-11-01,735904 \nRSAFS_vintage_2026-02-28.csv 409 observation_date,RSAFS_20260228 2025-11-01,735085 2025-12-01,734967 \nRSAFS_vintage_2026-03-31.csv 410 observation_date,RSAFS_20260331 2025-12-01,734685 2026-01-01,733537 \nRSAFS_vintage_2026-04-30.csv 412 observation_date,RSAFS_20260430 2026-02-01,739772 2026-03-01,752063 \nRSAFS_vintage_2026-05-31.csv 413 observation_date,RSAFS_20260531 2026-03-01,753370 2026-04-01,757085 \nRSAFS_vintage_2026-06-30.csv 414 observation_date,RSAFS_20260630 2026-04-01,757036 2026-05-01,763705 \nRSAFS_vintage_2026-07-31.csv 415 observation_date,RSAFS_20260731 2026-05-01,766876 2026-06-01,768553 \n==> RSAFS_current.csv <==\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n\n==> UMCSENT.csv <==\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n210\n1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 first_release.csv\n627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f RSAFS_current.csv\n3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 UMCSENT.csv\nd4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 vintages/PAYEMS_vintage_2025-10-31.csv\na05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 vintages/PAYEMS_vintage_2025-11-30.csv\n829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 vintages/PAYEMS_vintage_2025-12-31.csv\n8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 vintages/PAYEMS_vintage_2026-01-31.csv\n4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 vintages/PAYEMS_vintage_2026-02-28.csv\n919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e vintages/PAYEMS_vintage_2026-03-31.csv\n06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a vintages/PAYEMS_vintage_2026-04-30.csv\ne2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d vintages/PAYEMS_vintage_2026-05-31.csv\n19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a vintages/PAYEMS_vintage_2026-06-30.csv\n3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 vintages/PAYEMS_vintage_2026-07-31.csv\n3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 vintages/RSAFS_vintage_2025-10-31.csv\n4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 vintages/RSAFS_vintage_2025-11-30.csv\n436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd vintages/RSAFS_vintage_2025-12-31.csv\nb92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e vintages/RSAFS_vintage_2026-01-31.csv\n2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 vintages/RSAFS_vintage_2026-02-28.csv\n0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f vintages/RSAFS_vintage_2026-03-31.csv\n02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f vintages/RSAFS_vintage_2026-04-30.csv\n8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b vintages/RSAFS_vintage_2026-05-31.csv\n2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 vintages/RSAFS_vintage_2026-06-30.csv\n52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 vintages/RSAFS_vintage_2026-07-31.csv","is_error":false}]},"uuid":"37eb99ee-ac0b-47fe-b0de-dac302dd57d2","timestamp":"2026-10-30T05:35:32.315Z","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.\ntarget_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\nPAYEMS_vintage_2025-10-31.csv 1041 observation_date,PAYEMS_20251031 2025-07-01,159518 2025-08-01,159540 \nPAYEMS_vintage_2025-11-30.csv 1042 observation_date,PAYEMS_20251130 2025-08-01,159507 2025-09-01,159626 \nPAYEMS_vintage_2025-12-31.csv 1044 observation_date,PAYEMS_20251231 2025-10-01,159488 2025-11-01,159552 \nPAYEMS_vintage_2026-01-31.csv 1045 observation_date,PAYEMS_20260131 2025-11-01,159476 2025-12-01,159526 \nPAYEMS_vintage_2026-02-28.csv 1046 observation_date,PAYEMS_20260228 2025-12-01,158497 2026-01-01,158627 \nPAYEMS_vintage_2026-03-31.csv 1047 observation_date,PAYEMS_20260331 2026-01-01,158558 2026-02-01,158466 \nPAYEMS_vintage_2026-04-30.csv 1048 observation_date,PAYEMS_20260430 2026-02-01,158459 2026-03-01,158637 \nPAYEMS_vintage_2026-05-31.csv 1049 observation_date,PAYEMS_20260531 2026-03-01,158621 2026-04-01,158736 \nPAYEMS_vintage_2026-06-30.csv 1050 observation_date,PAYEMS_20260630 2026-04-01,158829 2026-05-01,159001 \nPAYEMS_vintage_2026-07-31.csv 1051 observation_date,PAYEMS_20260731 2026-05-01,158927 2026-06-01,158984 \nRSAFS_vintage_2025-10-31.csv 405 observation_date,RSAFS_20251031 2025-07-01,727414 2025-08-01,732010 \nRSAFS_vintage_2025-11-30.csv 406 observation_date,RSAFS_20251130 2025-08-01,732059 2025-09-01,733258 \nRSAFS_vintage_2025-12-31.csv 407 observation_date,RSAFS_20251231 2025-09-01,732444 2025-10-01,732633 \nRSAFS_vintage_2026-01-31.csv 408 observation_date,RSAFS_20260131 2025-10-01,731412 2025-11-01,735904 \nRSAFS_vintage_2026-02-28.csv 409 observation_date,RSAFS_20260228 2025-11-01,735085 2025-12-01,734967 \nRSAFS_vintage_2026-03-31.csv 410 observation_date,RSAFS_20260331 2025-12-01,734685 2026-01-01,733537 \nRSAFS_vintage_2026-04-30.csv 412 observation_date,RSAFS_20260430 2026-02-01,739772 2026-03-01,752063 \nRSAFS_vintage_2026-05-31.csv 413 observation_date,RSAFS_20260531 2026-03-01,753370 2026-04-01,757085 \nRSAFS_vintage_2026-06-30.csv 414 observation_date,RSAFS_20260630 2026-04-01,757036 2026-05-01,763705 \nRSAFS_vintage_2026-07-31.csv 415 observation_date,RSAFS_20260731 2026-05-01,766876 2026-06-01,768553 \n==> RSAFS_current.csv <==\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n\n==> UMCSENT.csv <==\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n210\n1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 first_release.csv\n627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f RSAFS_current.csv\n3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 UMCSENT.csv\nd4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 vintages/PAYEMS_vintage_2025-10-31.csv\na05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 vintages/PAYEMS_vintage_2025-11-30.csv\n829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 vintages/PAYEMS_vintage_2025-12-31.csv\n8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 vintages/PAYEMS_vintage_2026-01-31.csv\n4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 vintages/PAYEMS_vintage_2026-02-28.csv\n919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e vintages/PAYEMS_vintage_2026-03-31.csv\n06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a vintages/PAYEMS_vintage_2026-04-30.csv\ne2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d vintages/PAYEMS_vintage_2026-05-31.csv\n19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a vintages/PAYEMS_vintage_2026-06-30.csv\n3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 vintages/PAYEMS_vintage_2026-07-31.csv\n3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 vintages/RSAFS_vintage_2025-10-31.csv\n4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 vintages/RSAFS_vintage_2025-11-30.csv\n436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd vintages/RSAFS_vintage_2025-12-31.csv\nb92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e vintages/RSAFS_vintage_2026-01-31.csv\n2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 vintages/RSAFS_vintage_2026-02-28.csv\n0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f vintages/RSAFS_vintage_2026-03-31.csv\n02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f vintages/RSAFS_vintage_2026-04-30.csv\n8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b vintages/RSAFS_vintage_2026-05-31.csv\n2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 vintages/RSAFS_vintage_2026-06-30.csv\n52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 vintages/RSAFS_vintage_2026-07-31.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4610fb8c-6d5a-49a4-93ef-467a9e853141","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016/data","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}22{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"8e8f837680478117ea0118581a128d04f85ac6ce86f09896b8a267c03ff0c0b7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01HV1PvEX7VyDTXDYTW33D8x","name":"Bash","input":{"command":"cat data/README.md; cat data/first_release.csv; cd data/vintages; for f in *; do echo \"$f $(wc -l <$f) $(head -1 $f) $(tail -2 $f|tr '\\n' ' ')\"; done; cd ..; tail -3 RSAFS_current.csv UMCSENT.csv; grep -c ',$' UMCSENT.csv; shasum -a 256 *.csv vintages/*","description":"Inspect data files and provenance"}}]}}23{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"5242b628-7d72-481b-aa41-e2686c8e91b1","timestamp":"2026-10-30T05:35:32.318Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"d3aeb2b0-f39f-4127-b0c5-0b9189e69f71","keep":4,"tail":["8e8f837680478117ea0118581a128d04f85ac6ce86f09896b8a267c03ff0c0b7","594a27efc2e7faf8d8241a319d20b1b62ee33566283df86e59566379d4071989"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1d6ed15717419aa9338135e720d6b810eceb271f573768618d80b9ff252911b4"}24{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"37eb99ee-ac0b-47fe-b0de-dac302dd57d2","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}25{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}26{"parentUuid":"37eb99ee-ac0b-47fe-b0de-dac302dd57d2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvjMwVN4K6HtKgQ4WB","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":8664,"cache_read_input_tokens":8588,"output_tokens":1895,"output_tokens_details":{"thinking_tokens":1519},"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":8664},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":15394,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsvj5pahc2ZUxt8165b","requestRef":"5242b628-7d72-481b-aa41-e2686c8e91b1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b1d4e2fc-9f92-46fa-9fbd-1ceebbe6d3d7","timestamp":"2026-10-30T05:35:49.250Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016/data","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"b1d4e2fc-9f92-46fa-9fbd-1ceebbe6d3d7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsvjMwVN4K6HtKgQ4WB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01K3MefuyoqaHYAgyPEBMkVA","name":"Bash","input":{"command":"mkdir -p out/state && cd data && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('vintages/*.csv'))+['RSAFS_current.csv','UMCSENT.csv','first_release.csv']:\n d=pd.read_csv(f); c=d.columns[0]\n print(f,d.shape,d[c].min(),d[c].max(),'na',int(d.iloc[:,1:].isna().sum().sum()),'dup',int(d[c].duplicated().sum()))\nu=pd.read_csv('UMCSENT.csv');u=u.dropna();print('UMC first nonmissing monthly run', u.observation_date.iloc[0]); \nd=pd.to_datetime(u.observation_date);print(d[d>='1978-01-01'].diff().dt.days.max())\n\"","description":"Audit schema, ranges, missing values"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":8664,"cache_read_input_tokens":8588,"output_tokens":1895,"output_tokens_details":{"thinking_tokens":1519},"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":8664},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsvj5pahc2ZUxt8165b","requestRef":"5242b628-7d72-481b-aa41-e2686c8e91b1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8e207066-a51d-4c69-af88-ad08128bfd3f","timestamp":"2026-10-30T05:35:52.240Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016/data","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}28{"parentUuid":"8e207066-a51d-4c69-af88-ad08128bfd3f","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n(eval):cd:1: no such file or directory: data","is_error":true,"tool_use_id":"toolu_01K3MefuyoqaHYAgyPEBMkVA"}]},"uuid":"c78c0407-1492-4310-b0c3-5478f562c58b","timestamp":"2026-10-30T05:35:52.280Z","toolUseResult":"Error: Exit code 1\n(eval):cd:1: no such file or directory: data","sandboxed":false,"sourceToolAssistantUUID":"8e207066-a51d-4c69-af88-ad08128bfd3f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016/data","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}29{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"42829d551bff4260b9709b79b0a29b0b96b88fcb8a5b6566d15b5e1206512a26","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01K3MefuyoqaHYAgyPEBMkVA","name":"Bash","input":{"command":"mkdir -p out/state && cd data && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('vintages/*.csv'))+['RSAFS_current.csv','UMCSENT.csv','first_release.csv']:\n d=pd.read_csv(f); c=d.columns[0]\n print(f,d.shape,d[c].min(),d[c].max(),'na',int(d.iloc[:,1:].isna().sum().sum()),'dup',int(d[c].duplicated().sum()))\nu=pd.read_csv('UMCSENT.csv');u=u.dropna();print('UMC first nonmissing monthly run', u.observation_date.iloc[0]); \nd=pd.to_datetime(u.observation_date);print(d[d>='1978-01-01'].diff().dt.days.max())\n\"","description":"Audit schema, ranges, missing values"}}]}}30{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"4768f81c-0c3a-456c-b26b-f37b127d2b7a","timestamp":"2026-10-30T05:35:52.282Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"5242b628-7d72-481b-aa41-e2686c8e91b1","keep":6,"tail":["42829d551bff4260b9709b79b0a29b0b96b88fcb8a5b6566d15b5e1206512a26","9d3924653dea1559f8a83b19bbeff022638deb681103f08f5a84b3b79d85d87b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"aa755752c2dfb27238bac45c41bf9036a5064fee6f4890216fc93ed4ff14d1bd"}31{"parentUuid":"c78c0407-1492-4310-b0c3-5478f562c58b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsxCj1dqKhuGj1ErbYg","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":1930,"cache_read_input_tokens":17252,"output_tokens":425,"output_tokens_details":{"thinking_tokens":45},"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":1930},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":369,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsxCT95knWbesJUx7RG","requestRef":"4768f81c-0c3a-456c-b26b-f37b127d2b7a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9e0a5e02-4a00-48c7-83a5-df25fb7f66dc","timestamp":"2026-10-30T05:35:54.127Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016/data","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"9e0a5e02-4a00-48c7-83a5-df25fb7f66dc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsxCj1dqKhuGj1ErbYg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MDQRStGHjVnoVFdg47DFpm","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016 && mkdir -p out/state && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('data/vintages/*.csv'))+['data/RSAFS_current.csv','data/UMCSENT.csv','data/first_release.csv']:\n d=pd.read_csv(f); c=d.columns[0]\n print(f,d.shape,d[c].min(),d[c].max(),'na',int(d.iloc[:,1:].isna().sum().sum()),'dup',int(d[c].duplicated().sum()))\nu=pd.read_csv('data/UMCSENT.csv');u=u.dropna();\nd=pd.to_datetime(u.observation_date);print(d[d>='1978-01-01'].diff().dt.days.max())\n\"","description":"Audit schema, ranges, missing values"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1930,"cache_read_input_tokens":17252,"output_tokens":425,"output_tokens_details":{"thinking_tokens":45},"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":1930},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsxCT95knWbesJUx7RG","requestRef":"4768f81c-0c3a-456c-b26b-f37b127d2b7a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2e473d83-448f-47bc-8af0-ad59b33ef8e0","timestamp":"2026-10-30T05:35:56.345Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016/data","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}33{"parentUuid":"2e473d83-448f-47bc-8af0-ad59b33ef8e0","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MDQRStGHjVnoVFdg47DFpm","type":"tool_result","content":"data/vintages/PAYEMS_vintage_2025-10-31.csv (1040, 2) 1939-01-01 2025-08-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2025-11-30.csv (1041, 2) 1939-01-01 2025-09-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2025-12-31.csv (1043, 2) 1939-01-01 2025-11-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-01-31.csv (1044, 2) 1939-01-01 2025-12-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-02-28.csv (1045, 2) 1939-01-01 2026-01-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-03-31.csv (1046, 2) 1939-01-01 2026-02-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-04-30.csv (1047, 2) 1939-01-01 2026-03-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-05-31.csv (1048, 2) 1939-01-01 2026-04-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-06-30.csv (1049, 2) 1939-01-01 2026-05-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-07-31.csv (1050, 2) 1939-01-01 2026-06-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2025-10-31.csv (404, 2) 1992-01-01 2025-08-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2025-11-30.csv (405, 2) 1992-01-01 2025-09-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2025-12-31.csv (406, 2) 1992-01-01 2025-10-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-01-31.csv (407, 2) 1992-01-01 2025-11-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-02-28.csv (408, 2) 1992-01-01 2025-12-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-03-31.csv (409, 2) 1992-01-01 2026-01-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-04-30.csv (411, 2) 1992-01-01 2026-03-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-05-31.csv (412, 2) 1992-01-01 2026-04-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-06-30.csv (413, 2) 1992-01-01 2026-05-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-07-31.csv (414, 2) 1992-01-01 2026-06-01 na 0 dup 0\ndata/RSAFS_current.csv (417, 2) 1992-01-01 2026-09-01 na 0 dup 0\ndata/UMCSENT.csv (887, 2) 1952-11-01 2026-09-01 na 210 dup 0\ndata/first_release.csv (28, 5) 2024-06-01 2026-09-01 na 0 dup 0\n31.0","is_error":false}]},"uuid":"6ce21cf4-7713-4df9-8424-ce575270d8ba","timestamp":"2026-10-30T05:35:56.578Z","toolUseResult":{"stdout":"data/vintages/PAYEMS_vintage_2025-10-31.csv (1040, 2) 1939-01-01 2025-08-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2025-11-30.csv (1041, 2) 1939-01-01 2025-09-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2025-12-31.csv (1043, 2) 1939-01-01 2025-11-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-01-31.csv (1044, 2) 1939-01-01 2025-12-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-02-28.csv (1045, 2) 1939-01-01 2026-01-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-03-31.csv (1046, 2) 1939-01-01 2026-02-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-04-30.csv (1047, 2) 1939-01-01 2026-03-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-05-31.csv (1048, 2) 1939-01-01 2026-04-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-06-30.csv (1049, 2) 1939-01-01 2026-05-01 na 0 dup 0\ndata/vintages/PAYEMS_vintage_2026-07-31.csv (1050, 2) 1939-01-01 2026-06-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2025-10-31.csv (404, 2) 1992-01-01 2025-08-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2025-11-30.csv (405, 2) 1992-01-01 2025-09-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2025-12-31.csv (406, 2) 1992-01-01 2025-10-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-01-31.csv (407, 2) 1992-01-01 2025-11-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-02-28.csv (408, 2) 1992-01-01 2025-12-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-03-31.csv (409, 2) 1992-01-01 2026-01-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-04-30.csv (411, 2) 1992-01-01 2026-03-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-05-31.csv (412, 2) 1992-01-01 2026-04-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-06-30.csv (413, 2) 1992-01-01 2026-05-01 na 0 dup 0\ndata/vintages/RSAFS_vintage_2026-07-31.csv (414, 2) 1992-01-01 2026-06-01 na 0 dup 0\ndata/RSAFS_current.csv (417, 2) 1992-01-01 2026-09-01 na 0 dup 0\ndata/UMCSENT.csv (887, 2) 1952-11-01 2026-09-01 na 210 dup 0\ndata/first_release.csv (28, 5) 2024-06-01 2026-09-01 na 0 dup 0\n31.0","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2e473d83-448f-47bc-8af0-ad59b33ef8e0","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}34{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"ea201a9d764d3e26142dae3b32d588a319066aa73656491916c10bdb7241d41c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01MDQRStGHjVnoVFdg47DFpm","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016 && mkdir -p out/state && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('data/vintages/*.csv'))+['data/RSAFS_current.csv','data/UMCSENT.csv','data/first_release.csv']:\n d=pd.read_csv(f); c=d.columns[0]\n print(f,d.shape,d[c].min(),d[c].max(),'na',int(d.iloc[:,1:].isna().sum().sum()),'dup',int(d[c].duplicated().sum()))\nu=pd.read_csv('data/UMCSENT.csv');u=u.dropna();\nd=pd.to_datetime(u.observation_date);print(d[d>='1978-01-01'].diff().dt.days.max())\n\"","description":"Audit schema, ranges, missing values"}}]}}35{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"2744948d-64eb-4417-a136-d4955263cd83","timestamp":"2026-10-30T05:35:56.580Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"4768f81c-0c3a-456c-b26b-f37b127d2b7a","keep":8,"tail":["ea201a9d764d3e26142dae3b32d588a319066aa73656491916c10bdb7241d41c","4eb963f85dd2d5357bfc091427ffbde44e425a2605cc26209c53c983ad1b25e8"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"99c1023b89359a0fc9c092e678db4b29bbbae4c545bedaa12b8b7802f84531b4"}36{"parentUuid":"6ce21cf4-7713-4df9-8424-ce575270d8ba","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsxX7YwWYyasvETQjZX","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":1674,"cache_read_input_tokens":19182,"output_tokens":615,"output_tokens_details":{"thinking_tokens":183},"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":1674},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1586,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsxWqBJj689gENspFKf","requestRef":"2744948d-64eb-4417-a136-d4955263cd83","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"80903606-dab1-4ad7-95f5-272e9a65ab45","timestamp":"2026-10-30T05:35:59.723Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"80903606-dab1-4ad7-95f5-272e9a65ab45","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsxX7YwWYyasvETQjZX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UGG7GWB2Ev3HB4TS17N1Xp","name":"Bash","input":{"command":"grep -h '2025-1[01]-01' data/vintages/PAYEMS_vintage_2025-12-31.csv data/vintages/PAYEMS_vintage_2026-07-31.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nfr=pd.read_csv('data/first_release.csv')\nprint('yoy recompute maxdiff',(100*np.log(fr.level_first_release/fr.level_prev_year_same_vintage)-fr.yoy_first_release).abs().max())\nfor _,r in fr.iterrows():\n f='data/vintages/RSAFS_vintage_%s.csv'%r.first_release_vintage\n try: v=pd.read_csv(f,index_col=0).iloc[:,0]\n except FileNotFoundError: continue\n print(r.target_month,r.first_release_vintage,v.get(r.target_month)==r.level_first_release)\n\"","description":"Check PAYEMS gap and first-release consistency"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1674,"cache_read_input_tokens":19182,"output_tokens":615,"output_tokens_details":{"thinking_tokens":183},"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":1674},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsxWqBJj689gENspFKf","requestRef":"2744948d-64eb-4417-a136-d4955263cd83","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8c43af7f-cd8d-4685-91bf-a05844c0c741","timestamp":"2026-10-30T05:36:02.780Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}38{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"8c43af7f-cd8d-4685-91bf-a05844c0c741","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}39{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}40{"parentUuid":"8c43af7f-cd8d-4685-91bf-a05844c0c741","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UGG7GWB2Ev3HB4TS17N1Xp","type":"tool_result","content":"2025-10-01,159488\n2025-11-01,159552\n2025-10-01,158408\n2025-11-01,158449\nyoy recompute maxdiff 4.656392009749766e-07\n2025-09-01 2025-11-30 True\n2025-10-01 2025-12-31 True\n2025-11-01 2026-01-31 True\n2025-12-01 2026-02-28 True\n2026-01-01 2026-03-31 True\n2026-02-01 2026-04-30 True\n2026-03-01 2026-04-30 True\n2026-04-01 2026-05-31 True\n2026-05-01 2026-06-30 True\n2026-06-01 2026-07-31 True","is_error":false}]},"uuid":"3f8cc047-028b-4515-b442-be44565c0d23","timestamp":"2026-10-30T05:36:02.976Z","toolUseResult":{"stdout":"2025-10-01,159488\n2025-11-01,159552\n2025-10-01,158408\n2025-11-01,158449\nyoy recompute maxdiff 4.656392009749766e-07\n2025-09-01 2025-11-30 True\n2025-10-01 2025-12-31 True\n2025-11-01 2026-01-31 True\n2025-12-01 2026-02-28 True\n2026-01-01 2026-03-31 True\n2026-02-01 2026-04-30 True\n2026-03-01 2026-04-30 True\n2026-04-01 2026-05-31 True\n2026-05-01 2026-06-30 True\n2026-06-01 2026-07-31 True","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8c43af7f-cd8d-4685-91bf-a05844c0c741","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}41{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"6da3cc50738ea9bd4aa35127f40df7428b542b0d5f821964880619966f4fe6d8","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01UGG7GWB2Ev3HB4TS17N1Xp","name":"Bash","input":{"command":"grep -h '2025-1[01]-01' data/vintages/PAYEMS_vintage_2025-12-31.csv data/vintages/PAYEMS_vintage_2026-07-31.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nfr=pd.read_csv('data/first_release.csv')\nprint('yoy recompute maxdiff',(100*np.log(fr.level_first_release/fr.level_prev_year_same_vintage)-fr.yoy_first_release).abs().max())\nfor _,r in fr.iterrows():\n f='data/vintages/RSAFS_vintage_%s.csv'%r.first_release_vintage\n try: v=pd.read_csv(f,index_col=0).iloc[:,0]\n except FileNotFoundError: continue\n print(r.target_month,r.first_release_vintage,v.get(r.target_month)==r.level_first_release)\n\"","description":"Check PAYEMS gap and first-release consistency"}}]}}42{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"2210d543-00c3-49e1-a4ac-2e2e01d0644f","timestamp":"2026-10-30T05:36:02.978Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"2744948d-64eb-4417-a136-d4955263cd83","keep":10,"tail":["6da3cc50738ea9bd4aa35127f40df7428b542b0d5f821964880619966f4fe6d8","973a7d180e55b7c15a2a2486251f8aa8c690a810a25d4edaeabb98eb61b8794b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4a3b84e251fbac3c46b24ebd569d619bdff97e6c8c18cc99aa0a965f74cf6e98"}43{"parentUuid":"3f8cc047-028b-4515-b442-be44565c0d23","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsxzTr6DW9RhscC4ohM","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":813,"cache_read_input_tokens":20856,"output_tokens":1350,"output_tokens_details":{"thinking_tokens":55},"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":813},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":359,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsxzBjSRNGZS99qzhmr","requestRef":"2210d543-00c3-49e1-a4ac-2e2e01d0644f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f45a65bb-4c80-41af-8d1d-361d90bbe84c","timestamp":"2026-10-30T05:36:04.621Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}44{"parentUuid":"f45a65bb-4c80-41af-8d1d-361d90bbe84c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsxzTr6DW9RhscC4ohM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LyPKrWZPtHRNDQp7zTr3gU","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract (P0) — T1-forecast\n\n**Question.** In real time (only data published at each of 10 month-end origins, 2025-10-31 … 2026-07-31), how accurately can US retail & food services sales YoY growth g_m = 100·ln(L_m/L_{m-12}) be forecast h = 1 and h = 3 months beyond the last published month last(V), and does my own model beat the naive (no-change) forecast when errors are measured against the first-release YoY of the target month?\n\n**Estimands** (h ∈ {1,3}, n = 10 origins each):\n(a) RMSE and MAE of naive, seasonal naive, AR(1) and my model vs `yoy_first_release`;\n(b) 1 − RMSE_model/RMSE_naive;\n(c) DM statistic (d_t = e²_naive − e²_model), Bartlett/Newey–West LRV with lag h−1, no HLN correction, two-sided normal p-value;\n(d) mean over the 10 h=1 target months of |g^current_T − yoy_first_release_T|.\nMeaningful under: the forecast-error loss differential is covariance-stationary (DM), first release is the agreed \"truth\"; with n = 10 inference is very weak (DM asymptotics unreliable).\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (keys listed in TASK.md: task_id, model_name, model_description, n_origins, first_origin, last_origin, rmse/mae_{naive,snaive,ar1,model}_h{1,3}, rel_improvement_rmse_h{1,3}, dm_stat/pvalue_h{1,3}, conclusion_code_h{1,3}, mean_abs_revision_h1_targets, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md, out/analysis.py, out/claims.json; plus protocol files in out/state/ and out/exclusions.csv.\n\n**Information rules.** At origin V: only RSAFS vintage V, PAYEMS vintage V, UMCSENT months ≤ month(V). Target = last(V)+h where last(V) = last month in RSAFS vintage V (publication delays exist). RSAFS_current.csv only for (d). first_release.csv only as actuals (never as forecast input).\n\n**Invalidating conditions.** Missing target in first_release.csv; vintage lacking needed history; any use of current data / future vintages in forecasts; model tuned on the evaluation origins' outcomes (avoided: model pre-specified before evaluation); negative LRV estimate in DM (would make statistic undefined → null).\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > out/state/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":813,"cache_read_input_tokens":20856,"output_tokens":1350,"output_tokens_details":{"thinking_tokens":55},"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":813},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsxzBjSRNGZS99qzhmr","requestRef":"2210d543-00c3-49e1-a4ac-2e2e01d0644f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5f83cfa0-f3e5-4c6f-8c2b-14e1f80170ca","timestamp":"2026-10-30T05:36:14.865Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"5f83cfa0-f3e5-4c6f-8c2b-14e1f80170ca","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LyPKrWZPtHRNDQp7zTr3gU","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"6497a545-0cfb-4572-8388-79af6923bd27","timestamp":"2026-10-30T05:36:14.929Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5f83cfa0-f3e5-4c6f-8c2b-14e1f80170ca","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}46{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"adbcb53735fd5b7444beea8c858b875aa158ab3913b5503530feb4ea06f61192","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LyPKrWZPtHRNDQp7zTr3gU","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract (P0) — T1-forecast\n\n**Question.** In real time (only data published at each of 10 month-end origins, 2025-10-31 … 2026-07-31), how accurately can US retail & food services sales YoY growth g_m = 100·ln(L_m/L_{m-12}) be forecast h = 1 and h = 3 months beyond the last published month last(V), and does my own model beat the naive (no-change) forecast when errors are measured against the first-release YoY of the target month?\n\n**Estimands** (h ∈ {1,3}, n = 10 origins each):\n(a) RMSE and MAE of naive, seasonal naive, AR(1) and my model vs `yoy_first_release`;\n(b) 1 − RMSE_model/RMSE_naive;\n(c) DM statistic (d_t = e²_naive − e²_model), Bartlett/Newey–West LRV with lag h−1, no HLN correction, two-sided normal p-value;\n(d) mean over the 10 h=1 target months of |g^current_T − yoy_first_release_T|.\nMeaningful under: the forecast-error loss differential is covariance-stationary (DM), first release is the agreed \"truth\"; with n = 10 inference is very weak (DM asymptotics unreliable).\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (keys listed in TASK.md: task_id, model_name, model_description, n_origins, first_origin, last_origin, rmse/mae_{naive,snaive,ar1,model}_h{1,3}, rel_improvement_rmse_h{1,3}, dm_stat/pvalue_h{1,3}, conclusion_code_h{1,3}, mean_abs_revision_h1_targets, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/table1.csv (model,horizon,rmse,mae,n), out/figure1.png, out/report.md, out/analysis.py, out/claims.json; plus protocol files in out/state/ and out/exclusions.csv.\n\n**Information rules.** At origin V: only RSAFS vintage V, PAYEMS vintage V, UMCSENT months ≤ month(V). Target = last(V)+h where last(V) = last month in RSAFS vintage V (publication delays exist). RSAFS_current.csv only for (d). first_release.csv only as actuals (never as forecast input).\n\n**Invalidating conditions.** Missing target in first_release.csv; vintage lacking needed history; any use of current data / future vintages in forecasts; model tuned on the evaluation origins' outcomes (avoided: model pre-specified before evaluation); negative LRV estimate in DM (would make statistic undefined → null).\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > out/state/log.md","description":"Write contract, phase ledger, log"}}]}}47{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"6a8fd4e0-5244-49a9-b2eb-1bf46c40d7d9","timestamp":"2026-10-30T05:36:14.932Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"2210d543-00c3-49e1-a4ac-2e2e01d0644f","keep":12,"tail":["adbcb53735fd5b7444beea8c858b875aa158ab3913b5503530feb4ea06f61192","56ce949291be53054cab1f8f5e8262c5e251700df961a33c3aee001c0d2a3a0a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4818e32ac720355d8d6a56600c8719eb94aa4d184611e1dc1490bf3478cdea2c"}48{"parentUuid":"6497a545-0cfb-4572-8388-79af6923bd27","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsysa8ufpmgjYKZPedy","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":1336,"cache_read_input_tokens":21669,"output_tokens":688,"output_tokens_details":{"thinking_tokens":241},"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":1336},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2192,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsysHXegtcNDxiKAP4u","requestRef":"6a8fd4e0-5244-49a9-b2eb-1bf46c40d7d9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"40fa7310-e756-4749-8161-791a2ec8e81a","timestamp":"2026-10-30T05:36:18.475Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"40fa7310-e756-4749-8161-791a2ec8e81a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsysa8ufpmgjYKZPedy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WeS4d4QrufRv9jZr9BQHQQ","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np,glob\nfs=sorted(glob.glob('data/vintages/RSAFS*'))\nvs={f[-14:-4]:pd.read_csv(f,index_col=0).iloc[:,0] for f in fs}\ncur=pd.read_csv('data/RSAFS_current.csv',index_col=0).iloc[:,0]\nks=list(vs)\nfor a,b in zip(ks,ks[1:]):\n c=vs[a].index.intersection(vs[b].index); d=(vs[b][c]/vs[a][c]-1).abs()\n print(a,b,'n changed',(d>0).sum(),'max rel', d.max().round(4), 'first changed',d[d>0].index.min())\nc=vs[ks[-1]].index; d=(cur[c]/vs[ks[-1]][c]-1).abs(); print('current vs last vintage changed',(d>0).sum(),d.max(),d[d>0].index.min())\nprint(cur['2026-05-01':], )\n\"","description":"Quantify revisions across RSAFS vintages"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1336,"cache_read_input_tokens":21669,"output_tokens":688,"output_tokens_details":{"thinking_tokens":241},"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":1336},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsysHXegtcNDxiKAP4u","requestRef":"6a8fd4e0-5244-49a9-b2eb-1bf46c40d7d9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8295e22d-fcdb-437d-8d18-ff3c11230fb1","timestamp":"2026-10-30T05:36:21.895Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}50{"parentUuid":"8295e22d-fcdb-437d-8d18-ff3c11230fb1","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WeS4d4QrufRv9jZr9BQHQQ","type":"tool_result","content":"2025-10-31 2025-11-30 n changed 4 max rel 0.0004 first changed 2024-08-01\n2025-11-30 2025-12-31 n changed 4 max rel 0.0011 first changed 2024-09-01\n2025-12-31 2026-01-31 n changed 4 max rel 0.0017 first changed 2024-10-01\n2026-01-31 2026-02-28 n changed 4 max rel 0.0011 first changed 2024-11-01\n2026-02-28 2026-03-31 n changed 4 max rel 0.0005 first changed 2024-12-01\n2026-03-31 2026-04-30 n changed 5 max rel 0.0013 first changed 2025-01-01\n2026-04-30 2026-05-31 n changed 4 max rel 0.002 first changed 2025-03-01\n2026-05-31 2026-06-30 n changed 4 max rel 0.0021 first changed 2025-04-01\n2026-06-30 2026-07-31 n changed 4 max rel 0.0042 first changed 2025-05-01\ncurrent vs last vintage changed 138 0.04639237632277804 2015-01-01\nobservation_date\n2026-05-01 731415\n2026-06-01 732898\n2026-07-01 729915\n2026-08-01 739322\n2026-09-01 745021\nName: RSAFS, dtype: int64","is_error":false}]},"uuid":"62751e6b-b9a9-4063-8b07-3fa2c6e32cb4","timestamp":"2026-10-30T05:36:22.119Z","toolUseResult":{"stdout":"2025-10-31 2025-11-30 n changed 4 max rel 0.0004 first changed 2024-08-01\n2025-11-30 2025-12-31 n changed 4 max rel 0.0011 first changed 2024-09-01\n2025-12-31 2026-01-31 n changed 4 max rel 0.0017 first changed 2024-10-01\n2026-01-31 2026-02-28 n changed 4 max rel 0.0011 first changed 2024-11-01\n2026-02-28 2026-03-31 n changed 4 max rel 0.0005 first changed 2024-12-01\n2026-03-31 2026-04-30 n changed 5 max rel 0.0013 first changed 2025-01-01\n2026-04-30 2026-05-31 n changed 4 max rel 0.002 first changed 2025-03-01\n2026-05-31 2026-06-30 n changed 4 max rel 0.0021 first changed 2025-04-01\n2026-06-30 2026-07-31 n changed 4 max rel 0.0042 first changed 2025-05-01\ncurrent vs last vintage changed 138 0.04639237632277804 2015-01-01\nobservation_date\n2026-05-01 731415\n2026-06-01 732898\n2026-07-01 729915\n2026-08-01 739322\n2026-09-01 745021\nName: RSAFS, dtype: int64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8295e22d-fcdb-437d-8d18-ff3c11230fb1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}51{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"154263cec71c0fa4b046887662fc79007305795d19aca517f70b0149f404104d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WeS4d4QrufRv9jZr9BQHQQ","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np,glob\nfs=sorted(glob.glob('data/vintages/RSAFS*'))\nvs={f[-14:-4]:pd.read_csv(f,index_col=0).iloc[:,0] for f in fs}\ncur=pd.read_csv('data/RSAFS_current.csv',index_col=0).iloc[:,0]\nks=list(vs)\nfor a,b in zip(ks,ks[1:]):\n c=vs[a].index.intersection(vs[b].index); d=(vs[b][c]/vs[a][c]-1).abs()\n print(a,b,'n changed',(d>0).sum(),'max rel', d.max().round(4), 'first changed',d[d>0].index.min())\nc=vs[ks[-1]].index; d=(cur[c]/vs[ks[-1]][c]-1).abs(); print('current vs last vintage changed',(d>0).sum(),d.max(),d[d>0].index.min())\nprint(cur['2026-05-01':], )\n\"","description":"Quantify revisions across RSAFS vintages"}}]}}52{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"1f6abd5b-386f-4a13-9c51-6a329d175aeb","timestamp":"2026-10-30T05:36:22.121Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"6a8fd4e0-5244-49a9-b2eb-1bf46c40d7d9","keep":14,"tail":["154263cec71c0fa4b046887662fc79007305795d19aca517f70b0149f404104d","0263731f22996cc9dc468f103ae9b17fff51e5781129378d161ff119978cde7f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3166a0268ed46cbe71421a59104b485d0eb3371cffdc26fd9d6a2d7027a833f3"}53{"parentUuid":"62751e6b-b9a9-4063-8b07-3fa2c6e32cb4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXszQJ5WyRTAHUNMV3qz","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS1gsKEAgTGAI4AUIIdGhpbmtpbmcSDJyi2JzjgDBumIvA6RoMs+ElX3F0KdD2oBgBIjD17UiTeglN6EXC1pSJZnnUt9IGiNghJ/nZT26zgSRUC3Weubol53RjhVtS7MPpNIcq8wqJwaFvAYAcJ+pAfVtK/7wS61ghTMK6nkqn3fiGE3uHlfnhXLsyZL9ZCtpv46NEowwc9zK66hcnT6kM92lcDrtwUbNz5C6iXWioYCUwudu9NAW7GuTnC3NJ8BAwdQebWY+/X0oUNhOOldTSZtxDBS1k5n4u9tSiayG+/D98A5ij9ldrWw7v1S9ezgjn91PYRDXITtUSoIPvro7fZEWMGVWBxxYWTubQ1d5MzwQX5C+00CbQ0y3XNTDOaflVmulyYG6pER92p+6Ntd9U4w7YOyMSzL4bHZcnDZ78uZjhZ2VAnakQbSl5TAyRaf7BRWmBhVpbDMQiSOZhefrnpBk8NUWTlWuz7LSpFcB6EIIqC5lRKplTEDXtjs5Rr/Yfj+TRWWnHUrNI9RLjSGPW69W4A7owL6Mq321iiVeCFPclhEJlC1+j1L/u1ZZkLU/N7EdAbfjxBfJqPOtcyydQcZVdFNZsFj/I3cr9nMvBUVoh1uuBS09kjvfZ+Q++FFAr9sMajKiz0VYsTpIkngPFCG29zqbT3kbRhNxBchxnXgtrp32iIpPIbjRM4w2qBVSfd4dwGnfSwqIicQj6biPTJbSGkuJrDPGDFbyv9VEoGTfCKksvCegICF9NsmtfTNLVIvifANx2ZvsTaMwfPtGj1z8oI2moi5vnOXwt+ot/XdNVWkg5o7yKCUSD5qsB1RHIdly7XElhmC07eZLhcmScBXKadE3pqZw72OsOY2i+bJfswsF8JZgYVl/kPgSLyu9etDM6aLNB0xbHdJ3zVgKIMAipAUE/rEN9tlPeQBRXeM9QCfZZ29C4Wrlkicy5Xt6ZDNEPBrK8Gy66vlSC8IpwlhG4eB2UrYHi4YuyWaQ6yvVDlwsNURfZ0N6kfCj/ffe6gbiJ0wyYqLKd7Cj25+vAQhst6J/McB5+n4bxWHmfJD02WQbqvYWnd0yuFsCUlsC880yzErpcAUcMEYzq6lNf2SFN3sXwDh+Z3740dOxytnut/1KpjdPU3zvivX2Bwu+v4ai//nN712nf978XgrPLVd0EKC481reYsY0KiO7zk4xM9iJKcccwFGsCfB4ABVycm8hRQsVaYo9Jq8liuwUMLFgDe+j8q5e1Hk8f9TDDn6fuHAY61Y8zg/XNbFyemHV+MWN8jdrjqf+z/gUdsE2NyGO1rFvEQ8Buv5c0laXL2DzT/e/Qtzm8VHNIBzVMLfaqXWYgEXGQvZnUNn/PMAdASrWOgBG0+V4gf2OXkmhPpUyFqA6rlGBBY6n6H7h/LVNFCUiRmCHUu25JQt9eo/QTIStnne2Q42sPBZYYGTaVjeMJ4b5y0qGyIpf4qvSXLmgEhegZXB0075jpeCNjUH1HfWKqaD5TtnetwyY4Kmzd9FiDMNqaBfkDfrrfIanSVKz+XRlPVgLufHhLln6f66irQhUYfNGv2Im8XLfb7nrQg0XPafZkGEgv0izqBJTAyC7cbJDOalqkiyrCEGlU/nS88GUcYqfMdaQL4/ThX/CiwSLY72Eb4N3BETXcNsUMOsEiOABRRbalywbwW2w8z0EV/t/f1gUMyWZ+H86aKTocQv1ptneexmiIPsApuZYdusoLcVvLnweR20Cb5nFKiXqbX+hhmMxfvAdYJwzWU4nmPPfrw8aS86LIiIRM2BLdSxuVzK2mLcndyn5s+mxMOoxukZEtfYXe05wsfG+r0cBrdpEa+Gwtwu3+SH/ysom+Kn/hZsLZhyKQp7Cxl6GpmwCYz6E2zfLZxgajgfFkC0lrOCY5oxxgTpbf8tFj8jZ6qhUpsJKy/3q5dx3tLFuyUVWBe+nD+WLAoqJg/Eq6FmTn+6jLI9aRGQiSeYgJK3C7NSkgT2bnlcYuf/EYAQ=="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1150,"cache_read_input_tokens":23005,"output_tokens":2061,"output_tokens_details":{"thinking_tokens":310},"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":1150},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2917,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXszQ3DD1ayNwGZW3sLr","requestRef":"1f6abd5b-386f-4a13-9c51-6a329d175aeb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bc30e87c-a74a-4820-bcab-ce389c49a045","timestamp":"2026-10-30T05:36:26.371Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"bc30e87c-a74a-4820-bcab-ce389c49a045","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXszQJ5WyRTAHUNMV3qz","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018nhKU7yA5r5TUkjzKLDi4u","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\nAll SHA-256 hashes computed with `shasum -a 256` match `data/README.md` exactly (23 files). Row counts (data rows after header) match README.\n\n| file | rows | cols | range | missing | dup dates |\n|---|---|---|---|---|---|\n| PAYEMS vintages 2025-10-31 … 2026-07-31 | 1040,1041,1043,1044,1045,1046,1047,1048,1049,1050 | 2 | 1939-01 → 2025-08 … 2026-06 | 0 | 0 |\n| RSAFS vintages 2025-10-31 … 2026-07-31 | 404,405,406,407,408,409,411,412,413,414 | 2 | 1992-01 → last(V) | 0 | 0 |\n| RSAFS_current.csv | 417 | 2 | 1992-01 → 2026-09 | 0 | 0 |\n| UMCSENT.csv | 887 | 2 | 1952-11 → 2026-09 | 210 empty (pre-1978 non-survey months; monthly without gaps from 1978) | 0 |\n| first_release.csv | 28 | 5 | 2024-06 → 2026-09 | 0 | 0 |\n\nUnits: RSAFS millions USD SA; PAYEMS thousands SA; UMCSENT index 1966Q1=100; yoy in percent (log ×100).\n\n## last(V) per origin (RSAFS vintage)\n2025-10-31→2025-08 (2-month lag, shutdown delay); 2025-11-30→2025-09; 2025-12-31→2025-10; 2026-01-31→2025-11; 2026-02-28→2025-12; 2026-03-31→2026-01 (2-month lag); 2026-04-30→2026-03 (two months added at once); 2026-05-31→2026-04; 2026-06-30→2026-05; 2026-07-31→2026-06.\nConsequently h=1 targets: 2025-09,10,11,12, 2026-01,02,04,05,06,07 (2026-03 is never an h=1 target); h=3 targets: 2025-11,12, 2026-01,02,03,04,06,07,08,09. All 20 targets exist in first_release.csv.\n\n## Anomalies\n- PAYEMS vintage 2025-12-31 adds two months at once (2025-10 and 2025-11) — delayed BLS publication; PAYEMS vintage 2026-02-28 shows a level shift of ~ −1,000k vs prior vintage (annual benchmark revision). PAYEMS is not used by my model, so no handling needed beyond documentation.\n- first_release.csv: yoy recomputes from its levels to < 5e-7; levels match the shipped vintages for the 10 target months whose first-release vintage is shipped. 2026-02 and 2026-03 share first-release vintage 2026-04-30.\n- RSAFS revisions between consecutive shipped vintages are small (≤0.42% in level, 4–5 months changed). Current vintage vs vintage 2026-07-31: 138 months changed back to 2015-01, max 4.6% level revision (annual benchmark revision lowering 2025–2026 levels) — relevant for estimand (d) only.\n- RSAFS_current.csv contains information after all origins → used only for (d). first_release.csv is used only as actuals.\n\n## Availability violations\nNone in the forecasting inputs as used: each forecast reads only the RSAFS vintage dated V (my model uses no other predictor). UMCSENT not used by any forecast.\nEOF\ncat > out/exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep (origin,horizon,model) forecast pairs whose target month exists in first_release.csv,80,80,0,all 20 target months (10 origins x 2 horizons) have a first-release actual\n2,keep pairs with a non-missing forecast,80,80,0,all vintages have complete history from 1992-01; no missing levels\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 of 23 files match README\",\"row counts match README\",\"missing/duplicates checked\",\"last(V) and targets enumerated; all targets in first_release\",\"first_release yoy recomputed (max diff 4.7e-7) and levels match shipped vintages\",\"availability: RSAFS_current and first_release isolated from forecasts\"],\"notes\":\"see data_audit.md\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P1 passed: audit + exclusions (none removed). Decision: model pre-specified as base-effect drift model using only RSAFS vintage V (no tuning on evaluation origins).\" >> out/state/log.md","description":"Write audit, exclusions, 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":1150,"cache_read_input_tokens":23005,"output_tokens":2061,"output_tokens_details":{"thinking_tokens":310},"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":1150},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXszQ3DD1ayNwGZW3sLr","requestRef":"1f6abd5b-386f-4a13-9c51-6a329d175aeb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ed3d21d1-fbe0-4328-8b46-dc9fc90c630c","timestamp":"2026-10-30T05:36:41.208Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}55{"parentUuid":"ed3d21d1-fbe0-4328-8b46-dc9fc90c630c","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018nhKU7yA5r5TUkjzKLDi4u","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"e4baaf96-a6fe-4e42-ba72-54ea47db72bd","timestamp":"2026-10-30T05:36:41.283Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ed3d21d1-fbe0-4328-8b46-dc9fc90c630c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}56{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"9d5cd56a7c8a6909746877f48508f0ddbe0fade59ef8a0ee8b6fc6f5cbea7369","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS1gsKEAgTGAI4AUIIdGhpbmtpbmcSDJyi2JzjgDBumIvA6RoMs+ElX3F0KdD2oBgBIjD17UiTeglN6EXC1pSJZnnUt9IGiNghJ/nZT26zgSRUC3Weubol53RjhVtS7MPpNIcq8wqJwaFvAYAcJ+pAfVtK/7wS61ghTMK6nkqn3fiGE3uHlfnhXLsyZL9ZCtpv46NEowwc9zK66hcnT6kM92lcDrtwUbNz5C6iXWioYCUwudu9NAW7GuTnC3NJ8BAwdQebWY+/X0oUNhOOldTSZtxDBS1k5n4u9tSiayG+/D98A5ij9ldrWw7v1S9ezgjn91PYRDXITtUSoIPvro7fZEWMGVWBxxYWTubQ1d5MzwQX5C+00CbQ0y3XNTDOaflVmulyYG6pER92p+6Ntd9U4w7YOyMSzL4bHZcnDZ78uZjhZ2VAnakQbSl5TAyRaf7BRWmBhVpbDMQiSOZhefrnpBk8NUWTlWuz7LSpFcB6EIIqC5lRKplTEDXtjs5Rr/Yfj+TRWWnHUrNI9RLjSGPW69W4A7owL6Mq321iiVeCFPclhEJlC1+j1L/u1ZZkLU/N7EdAbfjxBfJqPOtcyydQcZVdFNZsFj/I3cr9nMvBUVoh1uuBS09kjvfZ+Q++FFAr9sMajKiz0VYsTpIkngPFCG29zqbT3kbRhNxBchxnXgtrp32iIpPIbjRM4w2qBVSfd4dwGnfSwqIicQj6biPTJbSGkuJrDPGDFbyv9VEoGTfCKksvCegICF9NsmtfTNLVIvifANx2ZvsTaMwfPtGj1z8oI2moi5vnOXwt+ot/XdNVWkg5o7yKCUSD5qsB1RHIdly7XElhmC07eZLhcmScBXKadE3pqZw72OsOY2i+bJfswsF8JZgYVl/kPgSLyu9etDM6aLNB0xbHdJ3zVgKIMAipAUE/rEN9tlPeQBRXeM9QCfZZ29C4Wrlkicy5Xt6ZDNEPBrK8Gy66vlSC8IpwlhG4eB2UrYHi4YuyWaQ6yvVDlwsNURfZ0N6kfCj/ffe6gbiJ0wyYqLKd7Cj25+vAQhst6J/McB5+n4bxWHmfJD02WQbqvYWnd0yuFsCUlsC880yzErpcAUcMEYzq6lNf2SFN3sXwDh+Z3740dOxytnut/1KpjdPU3zvivX2Bwu+v4ai//nN712nf978XgrPLVd0EKC481reYsY0KiO7zk4xM9iJKcccwFGsCfB4ABVycm8hRQsVaYo9Jq8liuwUMLFgDe+j8q5e1Hk8f9TDDn6fuHAY61Y8zg/XNbFyemHV+MWN8jdrjqf+z/gUdsE2NyGO1rFvEQ8Buv5c0laXL2DzT/e/Qtzm8VHNIBzVMLfaqXWYgEXGQvZnUNn/PMAdASrWOgBG0+V4gf2OXkmhPpUyFqA6rlGBBY6n6H7h/LVNFCUiRmCHUu25JQt9eo/QTIStnne2Q42sPBZYYGTaVjeMJ4b5y0qGyIpf4qvSXLmgEhegZXB0075jpeCNjUH1HfWKqaD5TtnetwyY4Kmzd9FiDMNqaBfkDfrrfIanSVKz+XRlPVgLufHhLln6f66irQhUYfNGv2Im8XLfb7nrQg0XPafZkGEgv0izqBJTAyC7cbJDOalqkiyrCEGlU/nS88GUcYqfMdaQL4/ThX/CiwSLY72Eb4N3BETXcNsUMOsEiOABRRbalywbwW2w8z0EV/t/f1gUMyWZ+H86aKTocQv1ptneexmiIPsApuZYdusoLcVvLnweR20Cb5nFKiXqbX+hhmMxfvAdYJwzWU4nmPPfrw8aS86LIiIRM2BLdSxuVzK2mLcndyn5s+mxMOoxukZEtfYXe05wsfG+r0cBrdpEa+Gwtwu3+SH/ysom+Kn/hZsLZhyKQp7Cxl6GpmwCYz6E2zfLZxgajgfFkC0lrOCY5oxxgTpbf8tFj8jZ6qhUpsJKy/3q5dx3tLFuyUVWBe+nD+WLAoqJg/Eq6FmTn+6jLI9aRGQiSeYgJK3C7NSkgT2bnlcYuf/EYAQ=="},{"type":"tool_use","id":"toolu_018nhKU7yA5r5TUkjzKLDi4u","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\nAll SHA-256 hashes computed with `shasum -a 256` match `data/README.md` exactly (23 files). Row counts (data rows after header) match README.\n\n| file | rows | cols | range | missing | dup dates |\n|---|---|---|---|---|---|\n| PAYEMS vintages 2025-10-31 … 2026-07-31 | 1040,1041,1043,1044,1045,1046,1047,1048,1049,1050 | 2 | 1939-01 → 2025-08 … 2026-06 | 0 | 0 |\n| RSAFS vintages 2025-10-31 … 2026-07-31 | 404,405,406,407,408,409,411,412,413,414 | 2 | 1992-01 → last(V) | 0 | 0 |\n| RSAFS_current.csv | 417 | 2 | 1992-01 → 2026-09 | 0 | 0 |\n| UMCSENT.csv | 887 | 2 | 1952-11 → 2026-09 | 210 empty (pre-1978 non-survey months; monthly without gaps from 1978) | 0 |\n| first_release.csv | 28 | 5 | 2024-06 → 2026-09 | 0 | 0 |\n\nUnits: RSAFS millions USD SA; PAYEMS thousands SA; UMCSENT index 1966Q1=100; yoy in percent (log ×100).\n\n## last(V) per origin (RSAFS vintage)\n2025-10-31→2025-08 (2-month lag, shutdown delay); 2025-11-30→2025-09; 2025-12-31→2025-10; 2026-01-31→2025-11; 2026-02-28→2025-12; 2026-03-31→2026-01 (2-month lag); 2026-04-30→2026-03 (two months added at once); 2026-05-31→2026-04; 2026-06-30→2026-05; 2026-07-31→2026-06.\nConsequently h=1 targets: 2025-09,10,11,12, 2026-01,02,04,05,06,07 (2026-03 is never an h=1 target); h=3 targets: 2025-11,12, 2026-01,02,03,04,06,07,08,09. All 20 targets exist in first_release.csv.\n\n## Anomalies\n- PAYEMS vintage 2025-12-31 adds two months at once (2025-10 and 2025-11) — delayed BLS publication; PAYEMS vintage 2026-02-28 shows a level shift of ~ −1,000k vs prior vintage (annual benchmark revision). PAYEMS is not used by my model, so no handling needed beyond documentation.\n- first_release.csv: yoy recomputes from its levels to < 5e-7; levels match the shipped vintages for the 10 target months whose first-release vintage is shipped. 2026-02 and 2026-03 share first-release vintage 2026-04-30.\n- RSAFS revisions between consecutive shipped vintages are small (≤0.42% in level, 4–5 months changed). Current vintage vs vintage 2026-07-31: 138 months changed back to 2015-01, max 4.6% level revision (annual benchmark revision lowering 2025–2026 levels) — relevant for estimand (d) only.\n- RSAFS_current.csv contains information after all origins → used only for (d). first_release.csv is used only as actuals.\n\n## Availability violations\nNone in the forecasting inputs as used: each forecast reads only the RSAFS vintage dated V (my model uses no other predictor). UMCSENT not used by any forecast.\nEOF\ncat > out/exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep (origin,horizon,model) forecast pairs whose target month exists in first_release.csv,80,80,0,all 20 target months (10 origins x 2 horizons) have a first-release actual\n2,keep pairs with a non-missing forecast,80,80,0,all vintages have complete history from 1992-01; no missing levels\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 of 23 files match README\",\"row counts match README\",\"missing/duplicates checked\",\"last(V) and targets enumerated; all targets in first_release\",\"first_release yoy recomputed (max diff 4.7e-7) and levels match shipped vintages\",\"availability: RSAFS_current and first_release isolated from forecasts\"],\"notes\":\"see data_audit.md\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P1 passed: audit + exclusions (none removed). Decision: model pre-specified as base-effect drift model using only RSAFS vintage V (no tuning on evaluation origins).\" >> out/state/log.md","description":"Write audit, exclusions, update ledger"}}]}}57{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"38bc409c-837a-4664-b40c-1a3a4b84ae4c","timestamp":"2026-10-30T05:36:41.285Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"1f6abd5b-386f-4a13-9c51-6a329d175aeb","keep":16,"tail":["9d5cd56a7c8a6909746877f48508f0ddbe0fade59ef8a0ee8b6fc6f5cbea7369","1ec2041d25bcfb56c78058595bcbfab5b82251c21196ee84c86476ade2678374"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8dadc5ce2887cf766d96846b7ef5d3d84f64dc441baa839f9d9954956d82afb8"}58{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e4baaf96-a6fe-4e42-ba72-54ea47db72bd","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}59{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}60{"parentUuid":"e4baaf96-a6fe-4e42-ba72-54ea47db72bd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1pEH9vjUmrL51NDJR","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":2076,"cache_read_input_tokens":24155,"output_tokens":5724,"output_tokens_details":{"thinking_tokens":380},"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":2076},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2937,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt1oxAH8jRj2jj2dSJp","requestRef":"38bc409c-837a-4664-b40c-1a3a4b84ae4c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"654e1cc1-82b2-4280-8506-e96495c72622","timestamp":"2026-10-30T05:36:45.643Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"654e1cc1-82b2-4280-8506-e96495c72622","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1pEH9vjUmrL51NDJR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KDmmDVn9r22EhcHCSzx8hb","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\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\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import norm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nSEED = 20261030\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\"]\nn_input_rows = {}\n\n\ndef read_series(rel):\n df = pd.read_csv(os.path.join(DATA, rel))\n n_input_rows[rel] = int(len(df))\n s = df.set_index(pd.to_datetime(df.iloc[:, 0])).iloc[:, 1].astype(float)\n s.index = s.index.to_period(\"M\")\n return s\n\n\ndef yoy(level):\n return (100 * np.log(level / level.shift(12))).dropna()\n\n\ndef fc_naive(L, g, last, h):\n return g[last]\n\n\ndef fc_snaive(L, g, last, h):\n return g[last + h - 12]\n\n\ndef fc_ar1(L, g, last, h):\n gg = g[(g.index >= pd.Period(\"1993-01\", \"M\")) & (g.index <= last)]\n y = gg.values[1:] # m from 1993-02 to last(V)\n x = gg.values[:-1] # m-1\n assert gg.index[1] == pd.Period(\"1993-02\", \"M\")\n X = np.column_stack([np.ones_like(x), x])\n a, b = np.linalg.lstsq(X, y, rcond=None)[0]\n f = g[last]\n for _ in range(h):\n f = a + b * f\n return f\n\n\ndef fc_model(L, g, last, h):\n \"\"\"Base-effect drift model: future monthly log changes = mean of the last 12 monthly\n log changes in vintage V (= g_last/12); the base-period levels L_{T-12} are taken\n from vintage V (they are already published).\"\"\"\n drift = g[last] / 12.0 # percent per month\n lnL_T = 100 * np.log(L[last]) + h * drift\n return lnL_T - 100 * np.log(L[last + h - 12])\n\n\nFUNCS = {\"naive\": fc_naive, \"snaive\": fc_snaive, \"ar1\": fc_ar1, \"model\": fc_model}\n\n# ---------------- actuals ----------------\nfr_df = pd.read_csv(os.path.join(DATA, \"first_release.csv\"))\nn_input_rows[\"first_release.csv\"] = int(len(fr_df))\nfr = pd.Series(fr_df.yoy_first_release.values,\n index=pd.PeriodIndex(pd.to_datetime(fr_df.target_month), freq=\"M\"))\n\n# ---------------- forecasts ----------------\nrows, lasts = [], {}\nfor V in ORIGINS:\n L = read_series(f\"vintages/RSAFS_vintage_{V}.csv\") # only the vintage dated V\n read_series(f\"vintages/PAYEMS_vintage_{V}.csv\") # audited (row count) but not used by any model\n g = yoy(L)\n last = L.index.max()\n assert last.to_timestamp() < pd.Timestamp(V) # information rule sanity check\n lasts[V] = str(last)\n for h in HORIZONS:\n T = last + h\n for m in MODELS:\n rows.append(dict(origin_date=V, target_date=T.to_timestamp().strftime(\"%Y-%m-%d\"),\n horizon=h, forecast=round(float(FUNCS[m](L, g, last, h)), 6),\n actual_first_release=float(fr[T]), model=m, vintage_used=V))\nfc = pd.DataFrame(rows)\nfc.to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False)\nfc[\"err\"] = fc.actual_first_release - fc.forecast\n\n# ---------------- accuracy ----------------\nres = {}\ntab = []\nfor m in MODELS:\n for h in HORIZONS:\n e = fc[(fc.model == m) & (fc.horizon == h)].err.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=round(rmse, 6), mae=round(mae, 6), n=len(e)))\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n\ndef nw_lrv(d, lag):\n d = np.asarray(d, float); n = len(d); dc = d - d.mean()\n v = np.sum(dc * dc) / n\n for k in range(1, lag + 1):\n v += 2 * (1 - k / (lag + 1)) * np.sum(dc[k:] * dc[:-k]) / n\n return v\n\n\nrng = np.random.default_rng(SEED)\nB = 10000\nextra = {}\nfor h in HORIZONS:\n sub = fc[fc.horizon == h]\n en = sub[sub.model == \"naive\"].sort_values(\"origin_date\").err.values\n em = sub[sub.model == \"model\"].sort_values(\"origin_date\").err.values\n d = en ** 2 - em ** 2\n n = len(d)\n lrv = nw_lrv(d, h - 1)\n if lrv > 0:\n dm = float(d.mean() / np.sqrt(lrv / n)); p = float(2 * (1 - norm.cdf(abs(dm))))\n else:\n dm, p = None, None\n res[f\"rel_improvement_rmse_h{h}\"] = 1 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = dm, p\n better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n sig = \"significant\" if (p is not None and p < 0.05) else \"not_significant\"\n res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n extra[f\"dm_lrv_h{h}\"] = float(lrv)\n extra[f\"dm_mean_loss_diff_h{h}\"] = float(d.mean())\n # circular block bootstrap of RMSE_model - RMSE_naive (block length h; iid at h=1)\n bl = h\n nb = int(np.ceil(n / bl))\n diffs = np.empty(B)\n for b in range(B):\n starts = rng.integers(0, n, nb)\n idx = np.concatenate([(s + np.arange(bl)) % n for s in starts])[:n]\n diffs[b] = np.sqrt(np.mean(em[idx] ** 2)) - np.sqrt(np.mean(en[idx] ** 2))\n extra[f\"boot_rmse_diff_model_minus_naive_h{h}\"] = float(np.sqrt(np.mean(em ** 2)) - np.sqrt(np.mean(en ** 2)))\n extra[f\"boot_ci95_lo_h{h}\"] = float(np.percentile(diffs, 2.5))\n extra[f\"boot_ci95_hi_h{h}\"] = float(np.percentile(diffs, 97.5))\n extra[f\"boot_share_model_better_h{h}\"] = float(np.mean(diffs < 0))\n\n# ---------------- revision analysis (d) ----------------\ncur = read_series(\"RSAFS_current.csv\") # used ONLY here\ngcur = yoy(cur)\nh1 = fc[(fc.horizon == 1) & (fc.model == \"naive\")]\nT1 = pd.PeriodIndex(pd.to_datetime(h1.target_date), freq=\"M\")\nrev = gcur[T1].values - fr[T1].values\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(np.abs(rev)))\nextra[\"mean_revision_h1_targets_current_minus_first\"] = float(np.mean(rev))\nextra[\"revisions_h1_targets\"] = {str(t): round(float(r), 6) for t, r in zip(T1, rev)}\n\nucs = pd.read_csv(os.path.join(DATA, \"UMCSENT.csv\")) # read only for the row count; not used\nn_input_rows[\"UMCSENT.csv\"] = int(len(ucs))\n\n# ---------------- figure ----------------\nfig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\nfor ax, h in zip(axes, HORIZONS):\n sub = fc[fc.horizon == h].copy(); sub[\"t\"] = pd.to_datetime(sub.target_date)\n a = sub[sub.model == \"naive\"].sort_values(\"t\")\n ax.plot(a.t, a.actual_first_release, \"k-o\", label=\"first-release actual\")\n for m, sty, lab in [(\"naive\", \"C0--s\", \"naive\"), (\"model\", \"C3-^\", \"base-effect drift model\"),\n (\"ar1\", \"C2:\", \"AR(1)\")]:\n s = sub[sub.model == m].sort_values(\"t\")\n ax.plot(s.t, s.forecast, sty, label=lab)\n ax.set_title(f\"h = {h}: target month = last(V) + {h}\")\n ax.set_xlabel(\"target month\"); ax.grid(alpha=.3); ax.tick_params(axis=\"x\", rotation=45)\naxes[0].set_ylabel(\"YoY growth, % (100·log ratio)\")\naxes[0].legend(fontsize=8)\nfig.suptitle(\"US retail & food services sales: real-time forecasts vs first release (10 origins)\")\nfig.tight_layout(); fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130); plt.close(fig)\n\n# ---------------- results.json ----------------\nissues = [\n {\"issue\": \"Irregular RSAFS publication timing: vintages 2025-10-31 and 2026-03-31 end two months before the origin; vintage 2026-04-30 adds two months (2026-02, 2026-03) at once.\",\n \"handling\": \"Targets defined as last(V)+h from the vintage itself, per task rule; 2026-03 is never an h=1 target, h=1 target of 2025-10-31 is 2025-09.\"},\n {\"issue\": \"PAYEMS vintage 2025-12-31 adds 2025-10 and 2025-11 at once (delayed release) and vintage 2026-02-28 contains a benchmark level shift (~-1 million).\",\n \"handling\": \"Documented; PAYEMS is not used by any forecast.\"},\n {\"issue\": \"UMCSENT has 210 empty fields (pre-1978 non-survey months).\",\n \"handling\": \"Documented; UMCSENT is not used by any forecast.\"},\n {\"issue\": \"Large annual benchmark revision of RSAFS between the last origin vintage and the current vintage (138 months changed back to 2015, up to 4.6% in level).\",\n \"handling\": \"Affects only estimand (d), which by design uses the current vintage; forecasts use vintage V only and are evaluated against first release.\"},\n {\"issue\": \"first_release.csv dates first release at month-end granularity; 2026-02 and 2026-03 share the first-release vintage 2026-04-30.\",\n \"handling\": \"Used as given; yoy recomputed from levels (max abs diff < 5e-7) and levels verified against the shipped vintages.\"},\n]\nout = {\n \"task_id\": \"T1-forecast\",\n \"model_name\": \"base-effect drift (BED)\",\n \"model_description\": (\"Univariate real-time model using only the RSAFS vintage dated V. The h-step-ahead log level is \"\n \"100*ln L_{last(V)} + h*mu, where the monthly drift mu = mean of the last 12 monthly log changes in vintage V \"\n \"(= g_{last(V)}/12); the forecast of YoY growth for T = last(V)+h is that log level minus 100*ln L_{T-12}, with L_{T-12} \"\n \"taken from vintage V (already published). It therefore keeps the recent trend but accounts for the known base \"\n \"effects (the monthly changes that drop out of the 12-month window). No parameters are estimated (estimation window: \"\n \"the 13 most recent levels of vintage V); PAYEMS and UMCSENT are not used. Specified before looking at evaluation errors; no tuning on the 10 origins.\"),\n \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1],\n}\nfor m in MODELS:\n for h in HORIZONS:\n out[f\"rmse_{m}_h{h}\"] = res[f\"rmse_{m}_h{h}\"]; out[f\"mae_{m}_h{h}\"] = res[f\"mae_{m}_h{h}\"]\nfor k in [\"rel_improvement_rmse_h1\", \"rel_improvement_rmse_h3\", \"dm_stat_h1\", \"dm_pvalue_h1\",\n \"dm_stat_h3\", \"dm_pvalue_h3\", \"conclusion_code_h1\", \"conclusion_code_h3\", \"mean_abs_revision_h1_targets\"]:\n out[k] = res[k]\nout.update({\n \"feasibility\": \"complete\", \"feasibility_reason\": None, \"data_issues\": issues,\n \"n_input_rows\": dict(sorted(n_input_rows.items())),\n \"n_analysed\": int(len(fc[fc.model == \"model\"])), \"random_seed\": SEED,\n \"last_month_by_origin\": lasts,\n})\nout.update(extra)\n\n\ndef rnd(o):\n if isinstance(o, float): return round(o, 6)\n if isinstance(o, dict): return {k: rnd(v) for k, v in o.items()}\n if isinstance(o, list): return [rnd(v) for v in o]\n return o\n\n\nout = rnd(out)\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(out, f, indent=1)\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n print(f\"h={h}: rel_impr={out[f'rel_improvement_rmse_h{h}']}, DM={out[f'dm_stat_h{h}']}, p={out[f'dm_pvalue_h{h}']}, {out[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets =\", out[\"mean_abs_revision_h1_targets\"])\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":2076,"cache_read_input_tokens":24155,"output_tokens":5724,"output_tokens_details":{"thinking_tokens":380},"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":2076},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt1oxAH8jRj2jj2dSJp","requestRef":"38bc409c-837a-4664-b40c-1a3a4b84ae4c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0e7aa96d-6c77-4b03-8251-9d6315dd095f","timestamp":"2026-10-30T05:37:25.757Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"0e7aa96d-6c77-4b03-8251-9d6315dd095f","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KDmmDVn9r22EhcHCSzx8hb","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 0.952689 10\n model 1 0.550298 0.486332 10\n model 3 1.142220 0.933977 10\nh=1: rel_impr=0.447977, DM=2.428978, p=0.015141, model_better_significant\nh=3: rel_impr=0.195643, DM=1.546577, p=0.121965, model_better_not_significant\nmean_abs_revision_h1_targets = 0.54822","is_error":false}]},"uuid":"9ba04c86-c149-4a49-8265-dfb2179e69cd","timestamp":"2026-10-30T05:37:26.735Z","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 0.952689 10\n model 1 0.550298 0.486332 10\n model 3 1.142220 0.933977 10\nh=1: rel_impr=0.447977, DM=2.428978, p=0.015141, model_better_significant\nh=3: rel_impr=0.195643, DM=1.546577, p=0.121965, model_better_not_significant\nmean_abs_revision_h1_targets = 0.54822","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"0e7aa96d-6c77-4b03-8251-9d6315dd095f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}63{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"8bf239649bc8c9d49bca599b44fd44dbfc89a5b94c76d09bbdc3cce3580cc9d7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KDmmDVn9r22EhcHCSzx8hb","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\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\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import norm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nSEED = 20261030\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\"]\nn_input_rows = {}\n\n\ndef read_series(rel):\n df = pd.read_csv(os.path.join(DATA, rel))\n n_input_rows[rel] = int(len(df))\n s = df.set_index(pd.to_datetime(df.iloc[:, 0])).iloc[:, 1].astype(float)\n s.index = s.index.to_period(\"M\")\n return s\n\n\ndef yoy(level):\n return (100 * np.log(level / level.shift(12))).dropna()\n\n\ndef fc_naive(L, g, last, h):\n return g[last]\n\n\ndef fc_snaive(L, g, last, h):\n return g[last + h - 12]\n\n\ndef fc_ar1(L, g, last, h):\n gg = g[(g.index >= pd.Period(\"1993-01\", \"M\")) & (g.index <= last)]\n y = gg.values[1:] # m from 1993-02 to last(V)\n x = gg.values[:-1] # m-1\n assert gg.index[1] == pd.Period(\"1993-02\", \"M\")\n X = np.column_stack([np.ones_like(x), x])\n a, b = np.linalg.lstsq(X, y, rcond=None)[0]\n f = g[last]\n for _ in range(h):\n f = a + b * f\n return f\n\n\ndef fc_model(L, g, last, h):\n \"\"\"Base-effect drift model: future monthly log changes = mean of the last 12 monthly\n log changes in vintage V (= g_last/12); the base-period levels L_{T-12} are taken\n from vintage V (they are already published).\"\"\"\n drift = g[last] / 12.0 # percent per month\n lnL_T = 100 * np.log(L[last]) + h * drift\n return lnL_T - 100 * np.log(L[last + h - 12])\n\n\nFUNCS = {\"naive\": fc_naive, \"snaive\": fc_snaive, \"ar1\": fc_ar1, \"model\": fc_model}\n\n# ---------------- actuals ----------------\nfr_df = pd.read_csv(os.path.join(DATA, \"first_release.csv\"))\nn_input_rows[\"first_release.csv\"] = int(len(fr_df))\nfr = pd.Series(fr_df.yoy_first_release.values,\n index=pd.PeriodIndex(pd.to_datetime(fr_df.target_month), freq=\"M\"))\n\n# ---------------- forecasts ----------------\nrows, lasts = [], {}\nfor V in ORIGINS:\n L = read_series(f\"vintages/RSAFS_vintage_{V}.csv\") # only the vintage dated V\n read_series(f\"vintages/PAYEMS_vintage_{V}.csv\") # audited (row count) but not used by any model\n g = yoy(L)\n last = L.index.max()\n assert last.to_timestamp() < pd.Timestamp(V) # information rule sanity check\n lasts[V] = str(last)\n for h in HORIZONS:\n T = last + h\n for m in MODELS:\n rows.append(dict(origin_date=V, target_date=T.to_timestamp().strftime(\"%Y-%m-%d\"),\n horizon=h, forecast=round(float(FUNCS[m](L, g, last, h)), 6),\n actual_first_release=float(fr[T]), model=m, vintage_used=V))\nfc = pd.DataFrame(rows)\nfc.to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False)\nfc[\"err\"] = fc.actual_first_release - fc.forecast\n\n# ---------------- accuracy ----------------\nres = {}\ntab = []\nfor m in MODELS:\n for h in HORIZONS:\n e = fc[(fc.model == m) & (fc.horizon == h)].err.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=round(rmse, 6), mae=round(mae, 6), n=len(e)))\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n\ndef nw_lrv(d, lag):\n d = np.asarray(d, float); n = len(d); dc = d - d.mean()\n v = np.sum(dc * dc) / n\n for k in range(1, lag + 1):\n v += 2 * (1 - k / (lag + 1)) * np.sum(dc[k:] * dc[:-k]) / n\n return v\n\n\nrng = np.random.default_rng(SEED)\nB = 10000\nextra = {}\nfor h in HORIZONS:\n sub = fc[fc.horizon == h]\n en = sub[sub.model == \"naive\"].sort_values(\"origin_date\").err.values\n em = sub[sub.model == \"model\"].sort_values(\"origin_date\").err.values\n d = en ** 2 - em ** 2\n n = len(d)\n lrv = nw_lrv(d, h - 1)\n if lrv > 0:\n dm = float(d.mean() / np.sqrt(lrv / n)); p = float(2 * (1 - norm.cdf(abs(dm))))\n else:\n dm, p = None, None\n res[f\"rel_improvement_rmse_h{h}\"] = 1 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = dm, p\n better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n sig = \"significant\" if (p is not None and p < 0.05) else \"not_significant\"\n res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{sig}\"\n extra[f\"dm_lrv_h{h}\"] = float(lrv)\n extra[f\"dm_mean_loss_diff_h{h}\"] = float(d.mean())\n # circular block bootstrap of RMSE_model - RMSE_naive (block length h; iid at h=1)\n bl = h\n nb = int(np.ceil(n / bl))\n diffs = np.empty(B)\n for b in range(B):\n starts = rng.integers(0, n, nb)\n idx = np.concatenate([(s + np.arange(bl)) % n for s in starts])[:n]\n diffs[b] = np.sqrt(np.mean(em[idx] ** 2)) - np.sqrt(np.mean(en[idx] ** 2))\n extra[f\"boot_rmse_diff_model_minus_naive_h{h}\"] = float(np.sqrt(np.mean(em ** 2)) - np.sqrt(np.mean(en ** 2)))\n extra[f\"boot_ci95_lo_h{h}\"] = float(np.percentile(diffs, 2.5))\n extra[f\"boot_ci95_hi_h{h}\"] = float(np.percentile(diffs, 97.5))\n extra[f\"boot_share_model_better_h{h}\"] = float(np.mean(diffs < 0))\n\n# ---------------- revision analysis (d) ----------------\ncur = read_series(\"RSAFS_current.csv\") # used ONLY here\ngcur = yoy(cur)\nh1 = fc[(fc.horizon == 1) & (fc.model == \"naive\")]\nT1 = pd.PeriodIndex(pd.to_datetime(h1.target_date), freq=\"M\")\nrev = gcur[T1].values - fr[T1].values\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(np.abs(rev)))\nextra[\"mean_revision_h1_targets_current_minus_first\"] = float(np.mean(rev))\nextra[\"revisions_h1_targets\"] = {str(t): round(float(r), 6) for t, r in zip(T1, rev)}\n\nucs = pd.read_csv(os.path.join(DATA, \"UMCSENT.csv\")) # read only for the row count; not used\nn_input_rows[\"UMCSENT.csv\"] = int(len(ucs))\n\n# ---------------- figure ----------------\nfig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\nfor ax, h in zip(axes, HORIZONS):\n sub = fc[fc.horizon == h].copy(); sub[\"t\"] = pd.to_datetime(sub.target_date)\n a = sub[sub.model == \"naive\"].sort_values(\"t\")\n ax.plot(a.t, a.actual_first_release, \"k-o\", label=\"first-release actual\")\n for m, sty, lab in [(\"naive\", \"C0--s\", \"naive\"), (\"model\", \"C3-^\", \"base-effect drift model\"),\n (\"ar1\", \"C2:\", \"AR(1)\")]:\n s = sub[sub.model == m].sort_values(\"t\")\n ax.plot(s.t, s.forecast, sty, label=lab)\n ax.set_title(f\"h = {h}: target month = last(V) + {h}\")\n ax.set_xlabel(\"target month\"); ax.grid(alpha=.3); ax.tick_params(axis=\"x\", rotation=45)\naxes[0].set_ylabel(\"YoY growth, % (100·log ratio)\")\naxes[0].legend(fontsize=8)\nfig.suptitle(\"US retail & food services sales: real-time forecasts vs first release (10 origins)\")\nfig.tight_layout(); fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130); plt.close(fig)\n\n# ---------------- results.json ----------------\nissues = [\n {\"issue\": \"Irregular RSAFS publication timing: vintages 2025-10-31 and 2026-03-31 end two months before the origin; vintage 2026-04-30 adds two months (2026-02, 2026-03) at once.\",\n \"handling\": \"Targets defined as last(V)+h from the vintage itself, per task rule; 2026-03 is never an h=1 target, h=1 target of 2025-10-31 is 2025-09.\"},\n {\"issue\": \"PAYEMS vintage 2025-12-31 adds 2025-10 and 2025-11 at once (delayed release) and vintage 2026-02-28 contains a benchmark level shift (~-1 million).\",\n \"handling\": \"Documented; PAYEMS is not used by any forecast.\"},\n {\"issue\": \"UMCSENT has 210 empty fields (pre-1978 non-survey months).\",\n \"handling\": \"Documented; UMCSENT is not used by any forecast.\"},\n {\"issue\": \"Large annual benchmark revision of RSAFS between the last origin vintage and the current vintage (138 months changed back to 2015, up to 4.6% in level).\",\n \"handling\": \"Affects only estimand (d), which by design uses the current vintage; forecasts use vintage V only and are evaluated against first release.\"},\n {\"issue\": \"first_release.csv dates first release at month-end granularity; 2026-02 and 2026-03 share the first-release vintage 2026-04-30.\",\n \"handling\": \"Used as given; yoy recomputed from levels (max abs diff < 5e-7) and levels verified against the shipped vintages.\"},\n]\nout = {\n \"task_id\": \"T1-forecast\",\n \"model_name\": \"base-effect drift (BED)\",\n \"model_description\": (\"Univariate real-time model using only the RSAFS vintage dated V. The h-step-ahead log level is \"\n \"100*ln L_{last(V)} + h*mu, where the monthly drift mu = mean of the last 12 monthly log changes in vintage V \"\n \"(= g_{last(V)}/12); the forecast of YoY growth for T = last(V)+h is that log level minus 100*ln L_{T-12}, with L_{T-12} \"\n \"taken from vintage V (already published). It therefore keeps the recent trend but accounts for the known base \"\n \"effects (the monthly changes that drop out of the 12-month window). No parameters are estimated (estimation window: \"\n \"the 13 most recent levels of vintage V); PAYEMS and UMCSENT are not used. Specified before looking at evaluation errors; no tuning on the 10 origins.\"),\n \"n_origins\": len(ORIGINS), \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1],\n}\nfor m in MODELS:\n for h in HORIZONS:\n out[f\"rmse_{m}_h{h}\"] = res[f\"rmse_{m}_h{h}\"]; out[f\"mae_{m}_h{h}\"] = res[f\"mae_{m}_h{h}\"]\nfor k in [\"rel_improvement_rmse_h1\", \"rel_improvement_rmse_h3\", \"dm_stat_h1\", \"dm_pvalue_h1\",\n \"dm_stat_h3\", \"dm_pvalue_h3\", \"conclusion_code_h1\", \"conclusion_code_h3\", \"mean_abs_revision_h1_targets\"]:\n out[k] = res[k]\nout.update({\n \"feasibility\": \"complete\", \"feasibility_reason\": None, \"data_issues\": issues,\n \"n_input_rows\": dict(sorted(n_input_rows.items())),\n \"n_analysed\": int(len(fc[fc.model == \"model\"])), \"random_seed\": SEED,\n \"last_month_by_origin\": lasts,\n})\nout.update(extra)\n\n\ndef rnd(o):\n if isinstance(o, float): return round(o, 6)\n if isinstance(o, dict): return {k: rnd(v) for k, v in o.items()}\n if isinstance(o, list): return [rnd(v) for v in o]\n return o\n\n\nout = rnd(out)\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(out, f, indent=1)\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n print(f\"h={h}: rel_impr={out[f'rel_improvement_rmse_h{h}']}, DM={out[f'dm_stat_h{h}']}, p={out[f'dm_pvalue_h{h}']}, {out[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets =\", out[\"mean_abs_revision_h1_targets\"])\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"}}]}}64{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"d7591f40-b497-4631-b2e6-aa9884ce6782","timestamp":"2026-10-30T05:37:26.737Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"38bc409c-837a-4664-b40c-1a3a4b84ae4c","keep":18,"tail":["8bf239649bc8c9d49bca599b44fd44dbfc89a5b94c76d09bbdc3cce3580cc9d7","de1a7c6d4b3b57c8361c668733e244bfb424825351c7b00a41d750ae5811b94b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d5e072cdc5428b3c0a1b5dbc91b5294c44504f9506cc43b89256534e952de1d3"}65{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"9ba04c86-c149-4a49-8265-dfb2179e69cd","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}66{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}67{"parentUuid":"9ba04c86-c149-4a49-8265-dfb2179e69cd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5AZyG4ax3mLixBgHz","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":5985,"cache_read_input_tokens":26231,"output_tokens":235,"output_tokens_details":{"thinking_tokens":66},"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":5985},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":516,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt5AGNWxFhTt4BQPdgq","requestRef":"d7591f40-b497-4631-b2e6-aa9884ce6782","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2b99b0ec-bc18-416e-b91d-58701d257a32","timestamp":"2026-10-30T05:37:28.752Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}68{"parentUuid":"2b99b0ec-bc18-416e-b91d-58701d257a32","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5AZyG4ax3mLixBgHz","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01E9Bc752X1aF8bwNHjddsNg","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; cat out/results.json | sed -n '/dm_lrv/,$p'; grep -E 'model$' out/forecasts.csv | head -30; wc -l out/forecasts.csv","description":"Inspect extra results and forecasts"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5985,"cache_read_input_tokens":26231,"output_tokens":235,"output_tokens_details":{"thinking_tokens":66},"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":5985},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt5AGNWxFhTt4BQPdgq","requestRef":"d7591f40-b497-4631-b2e6-aa9884ce6782","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1962df64-2eb2-4ee6-a683-f098d2b4084c","timestamp":"2026-10-30T05:37:29.994Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}69{"parentUuid":"1962df64-2eb2-4ee6-a683-f098d2b4084c","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01E9Bc752X1aF8bwNHjddsNg","type":"tool_result","content":" \"dm_lrv_h1\": 0.809137,\n \"dm_mean_loss_diff_h1\": 0.690931,\n \"boot_rmse_diff_model_minus_naive_h1\": -0.446577,\n \"boot_ci95_lo_h1\": -0.696991,\n \"boot_ci95_hi_h1\": -0.208832,\n \"boot_share_model_better_h1\": 0.9998,\n \"dm_lrv_h3\": 2.118518,\n \"dm_mean_loss_diff_h3\": 0.711849,\n \"boot_rmse_diff_model_minus_naive_h3\": -0.277821,\n \"boot_ci95_lo_h3\": -0.688736,\n \"boot_ci95_hi_h3\": 0.080764,\n \"boot_share_model_better_h3\": 0.934,\n \"mean_revision_h1_targets_current_minus_first\": -0.54822,\n \"revisions_h1_targets\": {\n \"2025-09\": -0.550217,\n \"2025-10\": -0.664176,\n \"2025-11\": -0.43892,\n \"2025-12\": -0.328627,\n \"2026-01\": -0.975676,\n \"2026-02\": -0.409956,\n \"2026-04\": -0.748173,\n \"2026-05\": -0.16534,\n \"2026-06\": -0.744089,\n \"2026-07\": -0.457025\n }\n} 81 out/forecasts.csv","is_error":false}]},"uuid":"e0e76a33-a7b3-4a29-84ae-ea51739ee716","timestamp":"2026-10-30T05:37:30.047Z","toolUseResult":{"stdout":" \"dm_lrv_h1\": 0.809137,\n \"dm_mean_loss_diff_h1\": 0.690931,\n \"boot_rmse_diff_model_minus_naive_h1\": -0.446577,\n \"boot_ci95_lo_h1\": -0.696991,\n \"boot_ci95_hi_h1\": -0.208832,\n \"boot_share_model_better_h1\": 0.9998,\n \"dm_lrv_h3\": 2.118518,\n \"dm_mean_loss_diff_h3\": 0.711849,\n \"boot_rmse_diff_model_minus_naive_h3\": -0.277821,\n \"boot_ci95_lo_h3\": -0.688736,\n \"boot_ci95_hi_h3\": 0.080764,\n \"boot_share_model_better_h3\": 0.934,\n \"mean_revision_h1_targets_current_minus_first\": -0.54822,\n \"revisions_h1_targets\": {\n \"2025-09\": -0.550217,\n \"2025-10\": -0.664176,\n \"2025-11\": -0.43892,\n \"2025-12\": -0.328627,\n \"2026-01\": -0.975676,\n \"2026-02\": -0.409956,\n \"2026-04\": -0.748173,\n \"2026-05\": -0.16534,\n \"2026-06\": -0.744089,\n \"2026-07\": -0.457025\n }\n} 81 out/forecasts.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1962df64-2eb2-4ee6-a683-f098d2b4084c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}70{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"d693250b137d4045e6d51ed5cb5bcb9a266c0181cff54f699c1a8561d2abd7a9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSzAcKEAgTGAI4AUIIdGhpbmtpbmcSDEE58CCy3MZVqlZJ0RoM4Oo4/V9eLNuMwTViIjDp009d8Go1o1TJKERbJGa7/AV6Fxk9x7blIQOW8vScSVSQtfi9sFErB/svjwIRHIsq6QYrIO+5IB7jvPmmuOBJCZCMjU2pBa7Pdd5JuLqj2+RlkrbazpwFT8GnHpfuYQBi7+dkcRtz6Y/UYVdz0nX1mdkKaSr0zBiP/BCxahmwYpwKLdusQjQ9KDRlwoxBRaoCGRsXxE9HM9/uDGPmwATr+280em2es2ap3gXJho4YwO67GgS2aPA8xHn87Io/c45+PntZ7c6znEfAoD+PjLjin3vAVKRgPdZ78XpXh0RJouNXT09Kpiq7Kl7g8X+OqQKQ32pGCEejGeNZjaQDfxmow+NReM8D7/6EzRMNSmyxokLJgRnY3+BJN9ILsyUQSLc1Rf3/IsG3WjmJqaNf7wNHsI9QW4qD6FST/X79mPDmid3lzsVTJxtvYPyMh57snsmWByZcZhng4FR2Fz4O5yRUGY2a2nTKGzSq/tlU+O3PAoOXz6kieEhhK0/oPsGz9L9hYkGerqb1EynHEYTYdpGWB7pvdMb/p1yT/LsVNYjHTq7dvuKe868dmacsCosgOIYwV4ygVrhQ10zJxCFC/MG857cvAYzwp/7kzg7IX2RzxusnCbiTcdIcV2l20/Ij+e+C2Je7ByRKREZJqyEb5r/DeipnSbrunpjCwyVUz4kVajL/5rhJ4oJyIrr4V48sXBnjKIbiOwpDXewSShqqN1h/IWUudwFDH3uNl2TdchFdgJWG2W871nLx4bsANd5d+bShro+/lHTgugsiSOpoqGaEtCB4wflWUJoOHqY928HGRFzAcnK9Y+5tQyR+fXWlwQBVUoPFNV3wCOrijuMplM6W/cl95+XshtjnJmAnLyNFJ9n/6t6gkykRhyXOcqDi9wK0m+wojFzqS7epMtBSCGJW9XAEzqCH3g4gQjM3Of2ZmRH8U7wWiiukD53+32m5ACj6AGs+9886TDUQxFuiMCjVD4w0TQq3ivQnZeOgo8NKet6XCfR1HQ8WVphVQ0kc+AvWlUbnfjCByMYDPoYPsCZGTxf6dEnJRkwxX1QTIhJ/cQGDC8+E4ZXC8AbjNWKHDjnwmJMWVUxyURllFjni2gCMQyXAsztq/HpLdxgRJRdGnN8IraFFJM0arWM8kafmzNZVBrdLH6l6u2qnqOC34Pl6zbsYoEbqE2Nlo71AY+fR9VPTzqAWU0nW/Uw1LqG1v9EEBWtXiFT83qtbYmcYAQ=="},{"type":"tool_use","id":"toolu_01E9Bc752X1aF8bwNHjddsNg","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; cat out/results.json | sed -n '/dm_lrv/,$p'; grep -E 'model$' out/forecasts.csv | head -30; wc -l out/forecasts.csv","description":"Inspect extra results and forecasts"}}]}}71{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"072e34fb-e504-47af-b6ab-fb025293e4e3","timestamp":"2026-10-30T05:37:30.051Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"d7591f40-b497-4631-b2e6-aa9884ce6782","keep":20,"tail":["d693250b137d4045e6d51ed5cb5bcb9a266c0181cff54f699c1a8561d2abd7a9","8290392b66426cda3650c1c0171d2d812c5e99dfcdeec80a65da4c63061ab335"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8f33c048b625af75c883c9c81cc29d0a7baf8d2bf164ed1a9a0ce12b3054dbd6"}72{"parentUuid":"e0e76a33-a7b3-4a29-84ae-ea51739ee716","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5QmzjLNnBYqqDPyoK","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":712,"cache_read_input_tokens":32216,"output_tokens":2358,"output_tokens_details":{"thinking_tokens":85},"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":712},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":575,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt5QUPMb9dAbmrK4pQC","requestRef":"072e34fb-e504-47af-b6ab-fb025293e4e3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"01a67c8f-8522-4fb0-9368-2c2e52335883","timestamp":"2026-10-30T05:37:31.993Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}73{"parentUuid":"01a67c8f-8522-4fb0-9368-2c2e52335883","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt5QmzjLNnBYqqDPyoK","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01T2xztu8M9TaeRvA2qrCmmi","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv > /tmp/h1; mkdir -p /tmp/bk && mv out/results.json out/forecasts.csv out/table1.csv out/figure1.png /tmp/bk/; ~/wp29/venv/bin/python out/analysis.py >/dev/null; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv | diff - /tmp/h1 && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd,numpy as np,json,statsmodels.api as sm\nfrom scipy.stats import norm\nr=json.load(open('out/results.json')); f=pd.read_csv('out/forecasts.csv')\nok=lambda c,m: print(('PASS ' if c else 'FAIL ')+m)\nok(len(f)==80 and f.groupby(['origin_date','horizon','model']).size().max()==1,'80 unique rows')\nok((f.origin_date==f.vintage_used).all(),'vintage_used == origin')\nok((pd.to_datetime(f.target_date)<pd.to_datetime(f.origin_date)+pd.DateOffset(months=4)).all(),'targets within 3 months of origin')\n# info: target - h is last month which < origin\nf['lastm']=pd.to_datetime(f.target_date)-f.horizon.apply(lambda h: pd.DateOffset(months=h))\nok((f.lastm<pd.to_datetime(f.origin_date)).all(),'last(V) precedes origin')\nfr=pd.read_csv('data/first_release.csv').set_index('target_month').yoy_first_release\nok(np.allclose(f.actual_first_release,f.target_date.map(fr)),'actuals match first_release')\n# naive equals last g in vintage; AR1 via statsmodels\nfor V in f.origin_date.unique():\n L=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv',index_col=0).iloc[:,0]; L.index=pd.to_datetime(L.index)\n g=100*np.log(L/L.shift(12)); g=g.dropna()\n y=g['1993-02-01':]; x=g.shift(1)['1993-02-01':]\n b=sm.OLS(y.values,sm.add_constant(x.values)).fit().params\n fc=g.iloc[-1]\n for h in (1,2,3):\n fc=b[0]+b[1]*fc\n if h in (1,3):\n v=f[(f.origin_date==V)&(f.horizon==h)&(f.model=='ar1')].forecast.iloc[0]; assert abs(v-fc)<1e-5,(V,h)\n for h in (1,3):\n assert abs(f[(f.origin_date==V)&(f.horizon==h)&(f.model=='naive')].forecast.iloc[0]-g.iloc[-1])<1e-5\n T=L.index[-1]+pd.DateOffset(months=h)\n assert abs(f[(f.origin_date==V)&(f.horizon==h)&(f.model=='snaive')].forecast.iloc[0]-g[T-pd.DateOffset(months=12)])<1e-5\nok(True,'AR(1) matches statsmodels OLS; naive & snaive recomputed')\nfor h in (1,3):\n s=f[f.horizon==h].pivot(index='origin_date',columns='model',values='forecast')\n a=f[f.horizon==h].groupby('origin_date').actual_first_release.first()\n e={m:a-s[m] for m in s}\n for m in s: \n ok(abs(np.sqrt((e[m]**2).mean())-r[f'rmse_{m}_h{h}'])<1e-6 and abs(e[m].abs().mean()-r[f'mae_{m}_h{h}'])<1e-6,f'rmse/mae {m} h{h}')\n ok(r[f'rmse_{m}_h{h}']>=r[f'mae_{m}_h{h}'],f'rmse>=mae {m} h{h}')\n d=(e['naive']**2-e['model']**2).values; n=10; dc=d-d.mean()\n g0=dc@dc/n; lrv=g0+(2*(2/3)*(dc[1:]@dc[:-1])/n+2*(1/3)*(dc[2:]@dc[:-2])/n if h==3 else 0)\n dm=d.mean()/np.sqrt(lrv/n)\n ok(abs(dm-r[f'dm_stat_h{h}'])<1e-5 and abs(2*norm.sf(abs(dm))-r[f'dm_pvalue_h{h}'])<1e-5,f'DM h{h} independent recompute (lrv>0: {lrv>0})')\n ok(abs(1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']-r[f'rel_improvement_rmse_h{h}'])<1e-6,f'rel impr h{h}')\n ok(r[f'boot_ci95_lo_h{h}']<=r[f'boot_rmse_diff_model_minus_naive_h{h}']<=r[f'boot_ci95_hi_h{h}'],f'boot CI contains estimate h{h}')\nc=pd.read_csv('data/RSAFS_current.csv',index_col=0).RSAFS; c.index=pd.to_datetime(c.index); gc=100*np.log(c/c.shift(12))\nT=f[(f.horizon==1)&(f.model=='naive')].target_date\nok(abs(np.mean([abs(gc[pd.Timestamp(t)]-fr[t]) for t in T])-r['mean_abs_revision_h1_targets'])<1e-6,'estimand (d) recomputed')\nok(r['n_analysed']==20 and 80-0==80,'n_analysed=20; exclusions sum 80-0=80')\nimport subprocess\nok(all(int(subprocess.check_output(['wc','-l','data/'+k]).split()[0])-1==v for k,v in r['n_input_rows'].items()) and len(r['n_input_rows'])==23,'n_input_rows match wc -l minus header (23 files)')\nEOF","description":"Clean rerun and 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":712,"cache_read_input_tokens":32216,"output_tokens":2358,"output_tokens_details":{"thinking_tokens":85},"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":712},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt5QUPMb9dAbmrK4pQC","requestRef":"072e34fb-e504-47af-b6ab-fb025293e4e3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2b1f7593-0f6f-4ecc-86a9-8957b34d9af7","timestamp":"2026-10-30T05:37:48.852Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}74{"parentUuid":"2b1f7593-0f6f-4ecc-86a9-8957b34d9af7","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01T2xztu8M9TaeRvA2qrCmmi","type":"tool_result","content":"IDENTICAL\n<stdin>:9: PerformanceWarning: Adding/subtracting object-dtype array to DatetimeArray not vectorized.\nPASS 80 unique rows\nPASS vintage_used == origin\nPASS targets within 3 months of origin\nPASS last(V) precedes origin\nPASS actuals match first_release\nPASS AR(1) matches statsmodels OLS; naive & snaive recomputed\nPASS rmse/mae ar1 h1\nPASS rmse>=mae ar1 h1\nPASS rmse/mae model h1\nPASS rmse>=mae model h1\nPASS rmse/mae naive h1\nPASS rmse>=mae naive h1\nPASS rmse/mae snaive h1\nPASS rmse>=mae snaive h1\nPASS DM h1 independent recompute (lrv>0: True)\nPASS rel impr h1\nPASS boot CI contains estimate h1\nPASS rmse/mae ar1 h3\nPASS rmse>=mae ar1 h3\nPASS rmse/mae model h3\nPASS rmse>=mae model h3\nPASS rmse/mae naive h3\nPASS rmse>=mae naive h3\nPASS rmse/mae snaive h3\nPASS rmse>=mae snaive h3\nPASS DM h3 independent recompute (lrv>0: True)\nPASS rel impr h3\nPASS boot CI contains estimate h3\nPASS estimand (d) recomputed\nPASS n_analysed=20; exclusions sum 80-0=80\nPASS n_input_rows match wc -l minus header (23 files)","is_error":false}]},"uuid":"9664478c-40c5-4aee-95d6-4ee8d56968fe","timestamp":"2026-10-30T05:37:50.604Z","toolUseResult":{"stdout":"IDENTICAL\n<stdin>:9: PerformanceWarning: Adding/subtracting object-dtype array to DatetimeArray not vectorized.\nPASS 80 unique rows\nPASS vintage_used == origin\nPASS targets within 3 months of origin\nPASS last(V) precedes origin\nPASS actuals match first_release\nPASS AR(1) matches statsmodels OLS; naive & snaive recomputed\nPASS rmse/mae ar1 h1\nPASS rmse>=mae ar1 h1\nPASS rmse/mae model h1\nPASS rmse>=mae model h1\nPASS rmse/mae naive h1\nPASS rmse>=mae naive h1\nPASS rmse/mae snaive h1\nPASS rmse>=mae snaive h1\nPASS DM h1 independent recompute (lrv>0: True)\nPASS rel impr h1\nPASS boot CI contains estimate h1\nPASS rmse/mae ar1 h3\nPASS rmse>=mae ar1 h3\nPASS rmse/mae model h3\nPASS rmse>=mae model h3\nPASS rmse/mae naive h3\nPASS rmse>=mae naive h3\nPASS rmse/mae snaive h3\nPASS rmse>=mae snaive h3\nPASS DM h3 independent recompute (lrv>0: True)\nPASS rel impr h3\nPASS boot CI contains estimate h3\nPASS estimand (d) recomputed\nPASS n_analysed=20; exclusions sum 80-0=80\nPASS n_input_rows match wc -l minus header (23 files)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2b1f7593-0f6f-4ecc-86a9-8957b34d9af7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}75{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"ed5535203add18ed466f9f2c0332edf08a725d77385772763c5dbb98d4ad4108","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01T2xztu8M9TaeRvA2qrCmmi","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv > /tmp/h1; mkdir -p /tmp/bk && mv out/results.json out/forecasts.csv out/table1.csv out/figure1.png /tmp/bk/; ~/wp29/venv/bin/python out/analysis.py >/dev/null; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv | diff - /tmp/h1 && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd,numpy as np,json,statsmodels.api as sm\nfrom scipy.stats import norm\nr=json.load(open('out/results.json')); f=pd.read_csv('out/forecasts.csv')\nok=lambda c,m: print(('PASS ' if c else 'FAIL ')+m)\nok(len(f)==80 and f.groupby(['origin_date','horizon','model']).size().max()==1,'80 unique rows')\nok((f.origin_date==f.vintage_used).all(),'vintage_used == origin')\nok((pd.to_datetime(f.target_date)<pd.to_datetime(f.origin_date)+pd.DateOffset(months=4)).all(),'targets within 3 months of origin')\n# info: target - h is last month which < origin\nf['lastm']=pd.to_datetime(f.target_date)-f.horizon.apply(lambda h: pd.DateOffset(months=h))\nok((f.lastm<pd.to_datetime(f.origin_date)).all(),'last(V) precedes origin')\nfr=pd.read_csv('data/first_release.csv').set_index('target_month').yoy_first_release\nok(np.allclose(f.actual_first_release,f.target_date.map(fr)),'actuals match first_release')\n# naive equals last g in vintage; AR1 via statsmodels\nfor V in f.origin_date.unique():\n L=pd.read_csv(f'data/vintages/RSAFS_vintage_{V}.csv',index_col=0).iloc[:,0]; L.index=pd.to_datetime(L.index)\n g=100*np.log(L/L.shift(12)); g=g.dropna()\n y=g['1993-02-01':]; x=g.shift(1)['1993-02-01':]\n b=sm.OLS(y.values,sm.add_constant(x.values)).fit().params\n fc=g.iloc[-1]\n for h in (1,2,3):\n fc=b[0]+b[1]*fc\n if h in (1,3):\n v=f[(f.origin_date==V)&(f.horizon==h)&(f.model=='ar1')].forecast.iloc[0]; assert abs(v-fc)<1e-5,(V,h)\n for h in (1,3):\n assert abs(f[(f.origin_date==V)&(f.horizon==h)&(f.model=='naive')].forecast.iloc[0]-g.iloc[-1])<1e-5\n T=L.index[-1]+pd.DateOffset(months=h)\n assert abs(f[(f.origin_date==V)&(f.horizon==h)&(f.model=='snaive')].forecast.iloc[0]-g[T-pd.DateOffset(months=12)])<1e-5\nok(True,'AR(1) matches statsmodels OLS; naive & snaive recomputed')\nfor h in (1,3):\n s=f[f.horizon==h].pivot(index='origin_date',columns='model',values='forecast')\n a=f[f.horizon==h].groupby('origin_date').actual_first_release.first()\n e={m:a-s[m] for m in s}\n for m in s: \n ok(abs(np.sqrt((e[m]**2).mean())-r[f'rmse_{m}_h{h}'])<1e-6 and abs(e[m].abs().mean()-r[f'mae_{m}_h{h}'])<1e-6,f'rmse/mae {m} h{h}')\n ok(r[f'rmse_{m}_h{h}']>=r[f'mae_{m}_h{h}'],f'rmse>=mae {m} h{h}')\n d=(e['naive']**2-e['model']**2).values; n=10; dc=d-d.mean()\n g0=dc@dc/n; lrv=g0+(2*(2/3)*(dc[1:]@dc[:-1])/n+2*(1/3)*(dc[2:]@dc[:-2])/n if h==3 else 0)\n dm=d.mean()/np.sqrt(lrv/n)\n ok(abs(dm-r[f'dm_stat_h{h}'])<1e-5 and abs(2*norm.sf(abs(dm))-r[f'dm_pvalue_h{h}'])<1e-5,f'DM h{h} independent recompute (lrv>0: {lrv>0})')\n ok(abs(1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']-r[f'rel_improvement_rmse_h{h}'])<1e-6,f'rel impr h{h}')\n ok(r[f'boot_ci95_lo_h{h}']<=r[f'boot_rmse_diff_model_minus_naive_h{h}']<=r[f'boot_ci95_hi_h{h}'],f'boot CI contains estimate h{h}')\nc=pd.read_csv('data/RSAFS_current.csv',index_col=0).RSAFS; c.index=pd.to_datetime(c.index); gc=100*np.log(c/c.shift(12))\nT=f[(f.horizon==1)&(f.model=='naive')].target_date\nok(abs(np.mean([abs(gc[pd.Timestamp(t)]-fr[t]) for t in T])-r['mean_abs_revision_h1_targets'])<1e-6,'estimand (d) recomputed')\nok(r['n_analysed']==20 and 80-0==80,'n_analysed=20; exclusions sum 80-0=80')\nimport subprocess\nok(all(int(subprocess.check_output(['wc','-l','data/'+k]).split()[0])-1==v for k,v in r['n_input_rows'].items()) and len(r['n_input_rows'])==23,'n_input_rows match wc -l minus header (23 files)')\nEOF","description":"Clean rerun and independent verification checks"}}]}}76{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"99cdd963-589f-4a67-9d3a-7e4d418e2327","timestamp":"2026-10-30T05:37:50.606Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"072e34fb-e504-47af-b6ab-fb025293e4e3","keep":22,"tail":["ed5535203add18ed466f9f2c0332edf08a725d77385772763c5dbb98d4ad4108","f9f36ad721defc81c2ad95587165a9d482fa160ed7dab0b436c66d1a0d5f968b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3e6db1d7678461784d5232fff08c27cb8e3aad30f6146315cb2c38401d4e0289"}77{"parentUuid":"9664478c-40c5-4aee-95d6-4ee8d56968fe","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6vctfm7XH1p7KGstE","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":2904,"cache_read_input_tokens":32928,"output_tokens":698,"output_tokens_details":{"thinking_tokens":157},"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":2904},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1192,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt6vLmnmQKM6VMweSvr","requestRef":"99cdd963-589f-4a67-9d3a-7e4d418e2327","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"13da1e3d-c007-40bc-95c0-dd282615fde8","timestamp":"2026-10-30T05:37:53.301Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"13da1e3d-c007-40bc-95c0-dd282615fde8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6vctfm7XH1p7KGstE","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LifnZf5xa3e2YX6UBo6ryQ","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; ~/wp29/venv/bin/python - <<'EOF'\ns=open('out/analysis.py').read()\ns=s.replace(\"from scipy.stats import norm\",\"from scipy.stats import norm, t as student_t\")\ns=s.replace(\"\"\" extra[f\"dm_lrv_h{h}\"] = float(lrv)\"\"\",\"\"\" extra[f\"dm_lrv_h{h}\"] = float(lrv)\n if dm is not None: # sensitivity only (not the required statistic): HLN small-sample correction, t(n-1)\n hln = np.sqrt((n + 1 - 2 * h + h * (h - 1) / n) / n)\n extra[f\"sens_dm_hln_stat_h{h}\"] = float(dm * hln)\n extra[f\"sens_dm_hln_pvalue_t_h{h}\"] = float(2 * student_t.sf(abs(dm * hln), n - 1))\"\"\")\nopen('out/analysis.py','w').write(s)\nEOF\nrm out/results.json out/forecasts.csv out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py | tail -3; grep sens out/results.json; shasum -a 256 out/forecasts.csv out/table1.csv; cat /tmp/h1","description":"Add HLN sensitivity 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":2904,"cache_read_input_tokens":32928,"output_tokens":698,"output_tokens_details":{"thinking_tokens":157},"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":2904},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt6vLmnmQKM6VMweSvr","requestRef":"99cdd963-589f-4a67-9d3a-7e4d418e2327","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f2206c89-2a89-4d8f-aec0-263a3e2d11de","timestamp":"2026-10-30T05:37:56.901Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}79{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f2206c89-2a89-4d8f-aec0-263a3e2d11de","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}80{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}81{"parentUuid":"f2206c89-2a89-4d8f-aec0-263a3e2d11de","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LifnZf5xa3e2YX6UBo6ryQ","type":"tool_result","content":"h=1: rel_impr=0.447977, DM=2.428978, p=0.015141, model_better_significant\nh=3: rel_impr=0.195643, DM=1.546577, p=0.121965, model_better_not_significant\nmean_abs_revision_h1_targets = 0.54822\n \"sens_dm_hln_stat_h1\": 2.304331,\n \"sens_dm_hln_pvalue_t_h1\": 0.046667,\n \"sens_dm_hln_stat_h3\": 1.157352,\n \"sens_dm_hln_pvalue_t_h3\": 0.27692,\nceaed71dee17e8e28e8dfb673af024b1c92a68aa556a0e663190b13c405560af out/forecasts.csv\n8b06ea5904ed2b34e8cc3acb72fc336b04618f8b7d37f2b4fc85679a14106734 out/table1.csv\n107e579ab0f10354fa01d4e476f2c25d71534d0aab6d4d80da1f80afc9ad1acb out/results.json\nceaed71dee17e8e28e8dfb673af024b1c92a68aa556a0e663190b13c405560af out/forecasts.csv\n8b06ea5904ed2b34e8cc3acb72fc336b04618f8b7d37f2b4fc85679a14106734 out/table1.csv","is_error":false}]},"uuid":"54199bb7-ac80-47bf-b774-aeedc9266def","timestamp":"2026-10-30T05:37:57.943Z","toolUseResult":{"stdout":"h=1: rel_impr=0.447977, DM=2.428978, p=0.015141, model_better_significant\nh=3: rel_impr=0.195643, DM=1.546577, p=0.121965, model_better_not_significant\nmean_abs_revision_h1_targets = 0.54822\n \"sens_dm_hln_stat_h1\": 2.304331,\n \"sens_dm_hln_pvalue_t_h1\": 0.046667,\n \"sens_dm_hln_stat_h3\": 1.157352,\n \"sens_dm_hln_pvalue_t_h3\": 0.27692,\nceaed71dee17e8e28e8dfb673af024b1c92a68aa556a0e663190b13c405560af out/forecasts.csv\n8b06ea5904ed2b34e8cc3acb72fc336b04618f8b7d37f2b4fc85679a14106734 out/table1.csv\n107e579ab0f10354fa01d4e476f2c25d71534d0aab6d4d80da1f80afc9ad1acb out/results.json\nceaed71dee17e8e28e8dfb673af024b1c92a68aa556a0e663190b13c405560af out/forecasts.csv\n8b06ea5904ed2b34e8cc3acb72fc336b04618f8b7d37f2b4fc85679a14106734 out/table1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f2206c89-2a89-4d8f-aec0-263a3e2d11de","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}82{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"9e95e37134c4732eea7bdb32995b58e0b28ece444f3c6489723211035523a6ab","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LifnZf5xa3e2YX6UBo6ryQ","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; ~/wp29/venv/bin/python - <<'EOF'\ns=open('out/analysis.py').read()\ns=s.replace(\"from scipy.stats import norm\",\"from scipy.stats import norm, t as student_t\")\ns=s.replace(\"\"\" extra[f\"dm_lrv_h{h}\"] = float(lrv)\"\"\",\"\"\" extra[f\"dm_lrv_h{h}\"] = float(lrv)\n if dm is not None: # sensitivity only (not the required statistic): HLN small-sample correction, t(n-1)\n hln = np.sqrt((n + 1 - 2 * h + h * (h - 1) / n) / n)\n extra[f\"sens_dm_hln_stat_h{h}\"] = float(dm * hln)\n extra[f\"sens_dm_hln_pvalue_t_h{h}\"] = float(2 * student_t.sf(abs(dm * hln), n - 1))\"\"\")\nopen('out/analysis.py','w').write(s)\nEOF\nrm out/results.json out/forecasts.csv out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py | tail -3; grep sens out/results.json; shasum -a 256 out/forecasts.csv out/table1.csv; cat /tmp/h1","description":"Add HLN sensitivity and rerun"}}]}}83{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"83448b1a-80fe-46d2-8994-e99e012d05e6","timestamp":"2026-10-30T05:37:57.945Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"99cdd963-589f-4a67-9d3a-7e4d418e2327","keep":24,"tail":["9e95e37134c4732eea7bdb32995b58e0b28ece444f3c6489723211035523a6ab","a48d3a3269c70bf4dcb5592f3d6824b42f90427d647b0b56d8514ae8a98c72b4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"90cd9035af528ae195ec38d8bb30211e9a218ad229f2232ce89e14baa90393aa"}84{"parentUuid":"54199bb7-ac80-47bf-b774-aeedc9266def","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7TzGrqi5p1BJAXcBM","type":"message","role":"assistant","content":[{"type":"text","text":"Results.json changed (new keys only); rerun once more to confirm determinism of the final version, and view the figure."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1162,"cache_read_input_tokens":35832,"output_tokens":370,"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":1162},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt7TjALph8dgn7DWi1X","requestRef":"83448b1a-80fe-46d2-8994-e99e012d05e6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c550ebf3-cd2c-4699-a632-11cb66993d8a","timestamp":"2026-10-30T05:37:59.482Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}85{"parentUuid":"c550ebf3-cd2c-4699-a632-11cb66993d8a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7TzGrqi5p1BJAXcBM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01B1QyAo2KBTbFAj5V1trvjP","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv > /tmp/h2; rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py >/dev/null; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv | diff - /tmp/h2 && echo IDENTICAL; ls out","description":"Second clean rerun determinism check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1162,"cache_read_input_tokens":35832,"output_tokens":370,"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":1162},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt7TjALph8dgn7DWi1X","requestRef":"83448b1a-80fe-46d2-8994-e99e012d05e6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b8101b88-14a6-4bdc-a6d0-0be42ec008c9","timestamp":"2026-10-30T05:38:01.180Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"b8101b88-14a6-4bdc-a6d0-0be42ec008c9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7TzGrqi5p1BJAXcBM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0147Y92euW4sgQBFji6Wedc4","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0016/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":1162,"cache_read_input_tokens":35832,"output_tokens":370,"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":1162},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXt7TjALph8dgn7DWi1X","requestRef":"83448b1a-80fe-46d2-8994-e99e012d05e6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4b06514b-e7d1-476d-8b22-d18eb170494b","timestamp":"2026-10-30T05:38:01.561Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}87{"type":"tools-used","tools":["Bash","Read"],"sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}88{"parentUuid":"b8101b88-14a6-4bdc-a6d0-0be42ec008c9","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01B1QyAo2KBTbFAj5V1trvjP","type":"tool_result","content":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nforecasts.csv\nresults.json\nstate\ntable1.csv","is_error":false}]},"uuid":"5ef59bc7-a79d-4963-9353-7a0fc5208e3c","timestamp":"2026-10-30T05:38:02.208Z","toolUseResult":{"stdout":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nforecasts.csv\nresults.json\nstate\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b8101b88-14a6-4bdc-a6d0-0be42ec008c9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}89{"parentUuid":"4b06514b-e7d1-476d-8b22-d18eb170494b","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0147Y92euW4sgQBFji6Wedc4","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"4ca4dfee-69f7-44fb-b28a-ffe19485f1ed","timestamp":"2026-10-30T05:38:02.212Z","toolUseResult":{"type":"image","file":{"base64":"iVBORw0KGgoAAAANSUhEUgAABhgAAAJJCAYAAABYjz3AAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAT/gAAE/4BB5Q5hAABAABJREFUeJzsnQd0FFUbhj/SSUINvffeRKQ3KdKlg3TpiFQRFRARFVEUkKogvQiCNBGkCQLCD9JFOtJ7DxBC6v7nvWGWzWY32U12s7vZ9zlnktmpd+7cmbn3q6l0Op1OCCGEEEIIIYQQQgghhBBCrMDDmo0JIYQQQgghhBBCCCGEEEKoYCCEEEIIIYQQQgghhBBCSKKgBwMhhBBCCCGEEEIIIYQQQqyGCgZCCCGEEEIIIYQQQgghhFgNFQyEEEIIIYQQQgghhBBCCLEaKhgIIYQQQgghhBBCCCGEEGI1VDAQQgghhBBCCCGEEEIIIcRqqGAghBBCCCGEEEIIIYQQQojVUMFACCGEEEIIIYQQQgghhBCroYKBEEIIIYQQQgghhBBCCCFWQwUDIYQQQgghhBBCCCGEEEKshgoGQghxQi5duiSpUqVSU3z8+eefapt8+fLFWafT6WTZsmXSsGFDyZo1q3h7e0vGjBmlWLFi0qZNG/nuu+/k7t27klIxV3+W1Ks5Tpw4oeouU6ZM4ufnJ/nz55eWLVuqek4Kz549k/fee0/dR9wnlO/tt98WZ2LBggVOWS57Pn+mnivCerIV2vu7du3aNm9WSXnPOQMXL16Utm3bSpYsWcTT01NdC95BhGhs375datWqJWnTptW3d7y77flcuQK4blw/6sGdCQsLk4IFC0qZMmUkOjo61rpdu3bJF198Ic2bN5ccOXLo28/Tp08TPC7aWPfu3SVnzpzi6+ur+gmDBg2S+/fvi7OAfpot35mObFNVq1ZVdR0SEpLs5yaEEGIdVDAQQkgKJDIyUlq1aiUdO3aULVu2SJ48eaRFixZSr149SZ06taxdu1aGDh0q+/fvd3RRXWYwfOTIEalUqZKsWrVKKWxQn6jXDRs2yIgRI5J07JEjR8rkyZMlIiJCWrduLd26dZPq1avbrOyEkJTDp59+qt6Z+J8SgTAQ78FffvlFsmfPLh06dFDvxEKFCjm6aE6PuyiCr169qoTDu3fvlgoVKkjXrl1VGwkMDEzWcri6Ii8lM2XKFLlw4YJ8/vnn4uERW+QBhcDo0aPl119/lZs3b1p8zGPHjkm5cuXUc5Y5c2ZlYOLj4yPTpk2T8uXLy40bN+xwJe4N7h/qdcKECY4uCiGEkATwSmgDQgghrseMGTOUEgFWP5s2bZJSpUrFWg/PheXLlytBeUrl1KlTNj3ehx9+qCyohg8fLl9//bVeqKDVZVJYvXq1+g9hSYECBWxSXpJ48Nyg/cCbhBBXxNbvv+QEFsJQ6MIyGP+NhYOEbN26VVmbd+nSRRYtWhSrQipWrKjav7+/PyvKTQkODpZx48Yp7wUoooypX7++UmJCOfXqq69a1BeOiopSyk4cG8rdMWPG6BWivXr1kvnz56v/GzduFEczfvx4+eijj5SC1hbgGYOnLYxqkpu6desqL4Zvv/1W3n33XeXVRgghxDmhgoEQQlIgK1euVP8xADJWLgBYXg0cOFBSMggFZUv27t2r/g8ePDiWxaIt6vLatWvqP5ULzgEUC7ZuP4QkJ67cfrX3Yd68ealcIFZ/M6FYcOX2T5LOwoUL5fHjxyqUkSm++eYbq4+5fv16pbgqXry4fPLJJ/rlUIBOnz5dGfX8/vvvcvz4cSldurQ4EigWbKVcAI5QLBgCj6w+ffrI3Llzk+wxTAghxH7QJIgQQlIgd+7cUf9taeljGNP18OHDKkQQjo/BFQZWGrDoh+VUyZIl1UA/TZo0UrlyZZkzZ47KC2Ec537nzp3q9+uvv64PN2AYMglhgxYvXizt27eXIkWKqBAImMqWLSufffaZ2bistg5doFmzw+XeVsBCF2XU6sXw+lE/Gk+ePJGxY8eqQatWp6+99ppMnTpV1Y8pYFWHe1WjRg1Jnz69yhlRtGhR5YFx7949s2VasWKFCgWF8wQFBUmzZs3U/U4MsPiD5RvCPWGwi3jF2bJlU8cfNWqUPH/+PM4+ly9fVlZqCIeCMqPsaBual4e5OkR9oew4V7p06dQyxETGOQMCAlQdmovTnCFDBhXn/fr16xblYMDzhbBWsI5EW8T9gECrX79+8u+//8bZ3tJnQuPRo0cqPjTaOMqGsGa5c+eWN954Q2bPni2WEhoaqkI3oK1AEYb6RLzpmjVrypdffhlrW9TPrFmz5M0331Rxq3FOxDaHNTBCTSDsmrU46rotDSGD+4h7BuEJnu8hQ4botwsPD1dCI1hOas8PBEsIq2GqLeFYyGuDsqLdYHtcA+ra2MI6KeDYeBcA/Dd8ZxiGTLIkBw3uwyuvvKLuDdoFFKVaDPIHDx6oMCKoG1xLiRIl4o3nbW19mUJ77hBXH+DboJXX+FlEjgYInLAczzjeVQ0aNJDffvstwVB827ZtU/cJOYmw7OjRo4l+/2jXDq9BvGtxz7X8PLCQNrZmRljCYcOGKatpfD9RdrTxzp07m3x3WPMc4xo1gSoErIZtwzBkEkLC4DuA5xLPON5hUObA0hthqRIC7wK8x3Hc//77z+x2aDPYZt++ffpl58+fl759+6pvEd7LOD/eN/i+//HHHxY/v5r1uOEzoF2juRwMhsvRzuGViPuMe4D+jAbaHerCsG2hrt555x399Wrl0DCsa0v7HbbuU1kC+gVLliyROnXqqPaP64OSBoYTt2/fjrN9Yr8LeKYQohP1i33wXKD/hms21Z+wxfvDkB9++EF901EGW4FwSgBt1fge476gjsC6deusOi6+HXgnoH60d4723TB1fy1pN/HlYIAHBs6HZx7nw/2H0B4eCuZCllqy/H//+5/K+Ybyoz7QFzP3TFv7HmjXrp1qq2iL1rZ5QgghyYiOEEKI03Hx4kX0oNUUHzt27FDb5M2bN9byunXrquWNGjXSPX/+3CZl6tatmzpmz549dT4+ProiRYro3nrrLV29evV0v/32m9rm6NGjumzZsunL1Lx5c139+vV1adKkUcs6duyoP97du3fVMbNmzarWNWjQQP3WplOnTqntrl69qtZnzJhRV61aNV379u3VMdOlS6eWv/rqq7pnz57FKa+5+rOkXk3Ro0cPtV+pUqV0jx8/1tmCYcOG6esVk+H1o37A7du3dSVKlFDrM2XKpGvdurXuzTff1AUGBqpltWvX1oWGhsY6bnR0tK5du3Zqva+vr65hw4bqd86cOdWy3Llz686dOxenPF988YVa7+HhoatVq5a6v4UKFVLH6Nevn76MltKlSxe1j7+/v+6NN97QdejQQbVNnB/Lb968GWv7rVu36ttK0aJFda1atVLl8PPzU8tGjBgR5xxoZ1j3zjvvqP9VqlRR50G7ePToka5ly5Zq+bx580yWccWKFWo9ymf8/Bk/V+DgwYO6LFmyqPX4jzbepk0bXfny5VW9jRkzJtb21jwT4OnTp7pixYqpddgP9xptvnr16rr06dOrerGEqKgo1TZwHOzXpEkTVS9YhnLjnhqye/du/Tm1e1+nTh193Tdt2lS1K0Piq6fkuG7tucF70FLmz5+v9mncuLEuT548usyZM6t2hnai3buHDx+qdqS9d1BulD9HjhxqWcmSJXX379+PddzFixerdTgm2jjqr0aNGjpPT0+1vH///mbf36hva94ZZcuWVfvhv+E7Y82aNXHqxlyd4TjauwHXhuvEcrzP7927pytcuLB6X+C9UbNmTV2qVKnU+oULF8Y5ZmLqyxTaNwHfAuyHb4N2bSivxp49e3Rp06ZV26CcqGu0a62uP/roozjHRh1jXd++fdW1lCtXTj0PaF/Hjh1L9PsH1/Xaa6/p33O4dpQH36qAgIA49xZtw8vLS907tHG0O3xLsX/q1Kl1O3fuTPRzPH78eHVebFuwYMFYbePHH39U29y4cUP/zc2fP7+uRYsWurZt26r7h/Kj7i1h6NCh6hiffPKJyfV///23Wo9r00A9a98tfNPwLUMdo/68vb3VvUkIvKdwPaaeAe0azT1X2vKKFSuq9zXaULNmzdT7Wzv33Llz9d/AqlWrqnuJd4X2DV62bFmscpj6dlv6jbR1n8q4rRu/F8PDw9X+WIf7gDaE+i9QoIBahuf9v//+S/J3YfPmzaqNa/0zvEPQ1vHMoV7RTu3x/tA4e/as2q9MmTIW76PdxydPnpjdBuXHNuvXrze5furUqWo96tRSzpw5o7/OXLlyqbrCOxnPtXZ/jevXknajbYPvnSHBwcGqXrS6Rllxb9CeKleurNq8qbZjrk1py99//311z3G/8d1GPxnLscz4nZbY94DWRo4cOWJx/RJCCEleqGAghJAUqGBYuXKlfn8MDPv06aMErOjYQ2CRGAwH02PHjo0z6AkJCdHly5dPrZ80aVKs81y7dk0N6LEOA3hLBi4aEOZjQBcRERFrOYTHGPhjX+MBqz0UDLgnmpDt9ddfN6nUSCzxlQmDL00AbqjYgKAIA2+s++CDD2LtM23aNJOKBCibMGDVhCyGHDp0SA3+MbD9448/9MtxHwcNGhRLkGIJly5d0gtc79y5E2c9hIRoMxrXr19XAjQMMDUhjgaUTZoiwbBsQFuO/SDYMGbt2rV6RYwpICDB+iVLliQoOEf9a8KA9957TxcWFhZr/ZUrV5QCIinPxIIFC/SCG+M2j/tnPFg3x59//qkX8EB4b0hkZGSceoQib/v27XGe61u3bunLaXxfzNVTcl13UhQMmpLBuG4ABK6acAcCGQ0o8rT3IJRnhpw8eVIJVY05f/68egawz//+978kKxgAFCHYz1iZZc37D98FCLcM7wuULZpADwIrw/b9ww8/6IXStqiv+IivXnBMCOKwfuTIkbHaK94pmuBq48aNJr8zpoRuSXn/aO8PfBOM33N4X2zbti3Wst9//10pjY2BcBzHgZLN8JqsfY619m3uPf3pp5/qFbLGQLi6d+9enSVA8I3jQDht/M4AAwYMUOuhtNZ4++231bKvvvoqzvYQIOMbZItnICEFg1afmhLfEO29ZfysAnxLL1y4YJP+hCP6VMOHD1fLIYg2VO7juHiWsA5K0aR+FzSF2PLly00+ZydOnLDr+2P27NlqH/R7balgyJAhg9oGbd8Uq1ev1rctS6lQoYL+eTV8354+fVrf15g5c6ZV7cZwG+N33cCBA9VyKBLQhza8n5oSLTEKBvSNDdsByqS9A/BuNCSx7wFNqTl58mST6wkhhDgeKhgIISQFKhgABiWalb/hhEESLIQuX75sVZm0AUvx4sVNKilmzJih1nft2tXk/hg0YP0rr7xilYLBEks1DNLsqWCAIAIDMtSnNqiGwN9W3iHmygQhPQZuEHqhTZi7/xCqGXoxQAhoLDQ3tBbU2gWsEzW6d+9uVvCE69QGu5YqGDQLVlgiWoIm/DBnEbtq1Sq1Hha/hmiCP3NWb7DahOcH6tG4zUMgCAs7WO8ZKjvMCc4h5MFyWHBaQmKeiQkTJthkEK15ZgwePFiXVLZs2aKOBUtfQ8zVU3JdN6zMMe3fv9/ifTQBLCw/Tb0D//33X71lvKnnG+0EFuBoN5Za1WoCL1h5OouCQbP2NmTIkCFqHSy74cVgLMwOCgpS6/Fesmd9xVcv8KDAOtx3U98hrW7gKWDqO2POQj8x75/Dhw/rLYHxXk0qmvUw6jSxz3FCCgZ40mC9obdLYtEsoXft2mXRO1czCLCFBXJSFQymFAgAXhxQNFmKLRQMydGnwvMMrwP0/4yfbYDza14hmkdPYr8LmqDakmfCHu8PrY1b8y2xRMGAfhi2MeX9aVgfhl478QGlufb+MOUVqz3L8Eaypt2YUzCgLtG+sdyUEB9K2cQqGOC1YKrfrH1r8U5I6ntA+45a40VLCCEkeWEOBkIISaEgXvDVq1dVHNcePXqoePGI0frw4UMVxxRxzv/++2+rj4s4sziOMUhuB9q2bWtyP8T6RqznY8eOmYy9nxAHDhyQCRMmqPjYiDONGLOI1w7Onj0r9gIxhlu2bKliZyPJ344dO1T84S1btqgY24gdbAiuHzFpN2/enORz7969W8WbRTxeU/kAEP8Wsb4RT/rQoUP65JeIT+7j4yNvvfVWnH0QH7dVq1ZqXst/YTjfqVOnOPsg9q25+2oO5CTA/d6wYYN8/fXXqi3GR0LtB3UADON5G2IYQ9sQxNbv0KGDqkfk8jBk2bJl6v7inIgZnBCbNm1S//E8WUJinokKFSqo/2jrP/30k4qXnBhwbMSgnjdvnopHreVliQ/UEdoBnqv+/fvrnzPsb81zllzXffr0aTXhebQWlMFU4krtHuM9h3ZvDNoJyop2c/DgwVjrkA8F14748MjtoNWfFtfenu8pa0EOAmMQAxsgPwDizhuCtqS9g27cuGGT+koMu3btUv+Rs8DUd0h7Nvfs2aNywFj6nkjM+0e7drxP8V61FDyLSFaKOOi9evVSbQTTrVu34rSTxDzH8aE9Z4i5jpjyiLueWLp166b+G+cYQV0izw9yVxg+Y9q58W5BnHXjb2dykTVrVpXDwBQoI3LB4H7g/ZQc8d6To0+FGPnYBrkXjJ9tgPMjZr6pb6y13wXtPuMZRVx+U8+hPd8f2jNi6jqdCe1dhv4l8moYg/pD/wV5P7T8UJa0G3Ogj4jnvXDhwlK+fPk46xs1aqRyZSQG7GtMpkyZVJ4PPOeGeb8S+x7Q7mdS34GEEELshxcrlxBCnA9LkwQaJgc2BQYtXbp0URNA0lsIVZE4TxtEnzx50qqyITGcKbTkx0gKnBAoR86cOS06H4TnEJRDUG2Ox48fi71Aff3111+qrpDEE0C5UK9ePVUmJKVbuXKleHnFfFJPnDihhPuJEXoaow0qoUQwBxL0QaGgbav9h2AHgilz+xhuazhvLrGxueXmQNtDgkEI0JCgEhOSmUKIgQSaUM5odWbYfpDIOj6Q8NKadqkJwpAkFQoGJJfW0ARjXbt2teiarly5ov4jMaElJOaZgFAOwj8I2qHsgQAByS6R+BZtTRN0JgSSayIJ5/vvv6+UjZiwDG0Ydd+4ceNY7w0INyF8hSItqc+ZI6/bVu+xiRMnqsnStghFB9p1fEoES+oPx/nqq6/iLMe9MSccTwy5cuWKswzCSnPrDNcjMXpS68te70SUHe9fCFPRtpD81Jr7bs37x9r3AZg5c6ZSLMQnEDZsJ9Y+xwmBdyGEzXj3ob3iHQxjAyirIdAsV66cxcfCc4pEyfj+4f2KhLHxvVc/+OADZdQAoTK+nxAoQ5kFoTe2heAzOYjvW/H9998rhRGSZGOCwBXKCCQQRxkTK4B1dJ9KO9aqVasSbC+GbTwx3wW8v/AeQ/8IE94b6A/hnqP9IUG5Pd8f6NsCU0L7pIDrgIFOSEiI2b6qNedN6F2GZxP9OE3BYHx/42vH8Z0vvv1wPlyjtaBvZwrUxYMHD2J9MxL7HkAiaMP7SwghxPmggoEQQpwQQ2tqDGYCAgJMbqcNdDTBjyUWQAMGDFBCGFhNnTp1Ss6dO2fVwD516tQml2tWarCqSmgQbspSzRwQTGOQWrJkSWUJD+snWEXBsguWT9YcKzFs3LgxjsVvunTpZOvWrWpwtHbtWmUhv3z5cjl+/LiqUwhE7SGIcDUgAKtbt666f6gveGRAYYMJgjz8Rl0atp+OHTuqe2st5tolwOAV7QfKHwhKKlWqpO4TLPqgOLFUeG2NIC8pz8SXX34pffr0UR4z27dvVwouCCYxYQAOwZclwNsH9+C3335TloKo7/nz56sJ9wUDfE3JA0UQ6gaCy7FjxyqPJ9wbrIfQHEJUS615HX3dtniPQSAGBUd8GApq2rRpo+oJwjgIXVFfEIhAyQeFJASUltQfBHqmrhPt1JYKhvgsX62xik1sfTmKhO67Ne8fa98H8MLD9xfP1KRJk6Rp06bqW6yVCefGu9G4nVjzHCcE7i3aF9oojgePvL1796p3IQS8MD747LPPLPYEwHcR38h169ap7x6Efzgu+iwosyFYBqt8WKLjmwCreFjL4/zjx49Xwv3evXuLvYnvW1GiRAn1HUc9o15R1/BGRLlRL3iW8T1JjvLYsk+lHQvX99prr8W7Lb6VGon5LmTPnl15LuD9jXqDpT7qEe/0zz//XCmkmjRpYrf3h+ZNZGvDE5wfwnd4Y0IpZwy8R60ppz3bcWLfW9a8+xO7X2LfA5pXozXeYoQQQpIXKhgIIcQJgQAdSga4M8N6CYM6U5w/fz5ei1NzQChhaBVmC8tBWDCdOXNGBg0aFOv4SUULLwIBfqlSpUxevz3RrKXgom8IBjkQmuNaUUZ4iaAuIZz69NNPbXJuzWJNs/IzhbZO21b7D+taDN5NeTEY76PNY/nly5dNWkJeunQpUdeAeoKlqxZ6CR4zsGLE4BKWjhhQau0H9xNCHC1Uiy2BgBpCNVjXQsFgaGVrqaAQ1n1QTECworn52+uZgEB54MCBaoIAB20NnjwoNwSREFhbQrZs2ZSQCBOAsAgKMQjQEKalb9++SlGJAT/aCoT7mtInsc+ZM1x3YtEsMSE4hTDMEmCtC+UVBK54Fxg/c9bUHyzJkyMsiyPry57vRAj5oHiGNT2+o5aSmPePFv7H0tBXsB7HvcVzMXTo0Djr42snljzH1gBBMyZYE+PbhnarhR3Ec4YQd5aAdzkUDHg+oWD4+eeflbUy5s0ZPuDdqb0/4ckxe/ZsGTJkiKqXdu3axXn/JDf4hjds2FBNWkgW1BMUM1AQQXieHNiyT6U9pwiNA89CS0jKdwECZyjuNeU9hP341uObD+GxFmbNHu8PvIcBLOdtCUJSHT16VCnjoBw0RgtTaakXUELvMjyXmpeUpR6/8aF5jmjHNAX6f8mFte8B7X4ae6URQghxHpiDgRBCnBAM6LRwPLCQN8eaNWv0QilDEhJQwWtBwxYDF6ANxjWFgKUgnIUpAb7xoMKUCzasPe2NptSA4MQYWBVu27ZNWbOhLJiHcsFS4UxCoA1A+A0LQFMCflh+ITwSBDmaVSWUTXC5h5ANShlTVmBau0H4GQ1NEID498bgWNbeV3NAqKUJ1/75558ktx9L0WK24z5iMLt06VKrwiMZerEgHrol2Oqa0AZwbljJG9ebtUC5ogkpteOgTURHR6twBqaEe9Y+Z8543daWHc8I6sQStHcULHdNKfRMPYdJIaF3ZnKSmPpKCtp7Cs+vqfPBqh9Uq1bNYqv+xLZZ7X2wevVqi3KGxPctg5LqyJEjSXqOE9s2UE9Q4qFu0XeABb+lwLoeSmRY9t++fdvqsHNQBEGgiLBPeC87U54SDQg04V1l6h2kebvY41m05TcRCgqUFV4ZWiifhLDldwHeXKhDtM+bN2/qwx3Z4/2hCfitDf9pSVsH6EMY97FhDIScJgChx6x5l6GP/+TJkzjr8Y5DXh8oPG3RT0cfEV4PUFohb4cx8NSxtVLGUix5D2j3E4oeQgghzgkVDIQQ4qS899576v8333yjrBQNwUAMlmAQPGNw37Nnz1jrEbMXIRhMJUODhZLmfgwhha3cuRHaBMJtJJBG2QxjrhoOECCMMUQbOMEy3BSasB5hUgyBMD+hmL22AMlaMfiBKzesqo3d7mHlZ1iHsG7EoNAW4LgIZQXhBcphKBiAMAfl0ZLlafGvgSbAR0x7eMAYKgpggQmvDIQk0JI6amE4IICHNSxidBu2NYSpMpVkMD4gLFuxYkWcWOMYmGthpwwTgCLGOAQZUNCgDMaJIbEfQozAoj2x1nsIaYVY1cOHD1dhDiCEtMZbAgI9CJHxPMIbwjg5IY6pWTEm9pmAoAWhJYwFGBD2YDkwlZzYGISjgPWpseALZdbqUDsOLD7xHkG7MBYaLVmyRK+MsZTkum68GzAlJll9fEIYCJLgkQCvGzxnxmDZjz/+qP8NDzA8O//++68KBaKBa4FQzXCZLUjonZmcJKa+kgIS3uL6ISRDMm3D9gKrfu2boH0/LSUx7x9YgyPUC94pUIIZJjIFEBoafru1bxmE8IbvcuyHxLmmhNTWPMeWtA2c25QiA54fmtDRkveLBr47sDZG+WCBjjAnUKAgp4ox+IYbGjdoQKGBfgmeIWu9MW0JhMSTJ0+Ocx8Bwj6Zqht7PouJ7VOZ84BB/g5cG/oUpqzm8f7HubS2ltjvAp5BLVyQIWivaLdQNmhhbuzx/tAMboyTVScV9KsRxgn32tDbAn0k9MUQPgnJjs15HJtSMOD6IdSHcN2w34jnRMsXhZwttgChifCeAcZ9WYwV8A5MDhL7HtDup7FBFSGEECdCRwghxGn57LPPID1R0yuvvKJ76623dK1bt9blzZtXLQsMDNRt2rQpzn5ly5ZV6z09PXVlypRR+7Rr105XtWpVtQzrcubMqTt16pTFZenWrZvab/78+Wa3OXr0qC5Xrlxqu8yZM+vq1q2r69Spk65Jkya6PHnyqOXt27ePtc+6devUcl9fX12zZs10PXv2VNPp06fV+p9//jlWHXTo0EFXpUoV9fujjz7SrzPG2uXxsXbtWl1AQIDaL0OGDOq6tHJ4eXnpPDw8dMOHD9dVqFBBbYO6joyMtPj48ZXp9u3buuLFi+vrtE2bNrrmzZvr0qRJo5bVrl1bFxoaGmufqKgoXdu2bdV6Pz8/XaNGjVS9a/cG/8+dOxfnXGPHjlXrcT04Lq6xcOHC6t707dtXrUM7sIQ1a9ao7VFvNWvWVMdq2bKlLnfu3Gp51qxZdRcuXIi1z9atW3Xp06fXl7FBgwa6jh07qv/YHss//PDDWPtoz8LFixcTLNPSpUv1dY1p9uzZJrfDsbAexzZm//79ukyZMumvAdeEe1K+fHlVb2PGjEnSMzF48GC1LEuWLLqGDRuqbRs3bqxLmzatWl6tWjVdeHh4gtc6efJktT3qE+dEPb755puqDFhepEgR3cOHD/XbT5gwQV8vOAful/Ye0Z4z4/qIr56S47q18u7YsUNnKXh/JdSOUS/Vq1dX2/n7+6v3ptZ+S5YsqUuVKpW694b0799f/87FteJdjWcHv99//321rlatWrH2QblNLU+ImzdvqnJh3xo1aujefvtt9c7Eu9S4bqx51yRUNyinqfpOTH3FR0L18tdff+nbRdGiRdW56tSpo/+2ob1aWvakvn/u3r2rnn3t2rEt7j3qA+8+w2t48OCB/plAO2/VqpX65uFdjuto0aJFnG+stc/x8+fPddmyZVPrXn31VV3Xrl1V25g3b55aj28H1uE93LRpU/Wc1a9fX30ntG+XtezZsyfWe3XkyJEmt9PeJ4UKFVLXimtB/eAbiuX4hloK3rPYx/h9G1/7SahdoR61Zxj3FHWBd1S5cuXUcpTT8BkDQ4cO1b/jsK3Wf3Fkn8pcWw8LC1NtDuu8vb11FStWVNeofb+0+2DYn0jMdyFdunTqmcezj74n9qlcubJahu1nzJhh1/cHQJ8J3+Nbt26ZXP/jjz/qKlWqpJ+0a3zttdf0y9D/NubIkSP6dw/aBeoe73ntmbp27ZpV5Txz5owuR44c+v1xPPTX0OfCMtRDdHS01e3G3DaPHj3SlSpVSq0LCgpS9wfvBFwT2gPuE9bhmbakTSX0XjXVP0vMewDl9vHxUcczrg9CCCHOAxUMhBDi5OzatUsNOjD4QAcbA7BixYrpBg4cGEdAq3H+/Hk1iMMArUSJEko4gc47BhQYyH311Ve64OBgq8phyaBGE6J8/vnnStgOwQkGShgIQ8j85ZdfqrIZM3PmTDXoSJ06tUmh4bZt25QgDdcBpQoGf4sWLVLrkkPBADBAghAUdQ9hDMoKoRAEiydPntQL/rRBP4R+lg6EEirT48ePlSAFg22cG4IrCI++++47JTQwBZQMECpBKID7gLaDAd2wYcN0d+7cMXuuZcuWqUE2rg/1jcHugQMHLBLMGoK6wP2GwA2DQpQbyhnc59GjRyvFiSmuX7+u++CDD3SlS5dW14ly5M+fXwnBcL1Yn1gFw7Nnz/TCAZQHg1ZTxCc4Bzdu3FD1iPuP46B+0S7QFk6cOJGkZwICDFw/lFfZs2dX9w0CQ9zHWbNmKQGiJUCB9MknnyhFEQRUOCcEVCjDN998Y/L5X758ubr3KCOERNh3w4YNZusjoXqy93XbS8EAIiIi1LYQ6OG9ifcnhFx47t577704Ahg8b3jnQqGLdzT2gRBw7969iRZ4xsf27dvV/dGEecbC1uRUMCSmvuLDknr577//dL169VLtCcJSvFvwjjAWAFtS9qS8fwAEslAEQECHdo53Qr58+ZSS9/fff4/zXuzRo4d6ZvA8YLshQ4YoIaupb2xinmMIpdH2MmbMqISshvd0586dukGDBqn9oeTAc4bj4r7h3W+NYtwQTciKSTMOMGb9+vW6Pn36qG8A2giuBfUARcfGjRutOp89FAxow+iLQOgOxQ3uJdoA3vO4Z8ePHzf5TUH7RhtBO7Smf2GvPlVCbX316tWqzvF8osxQmOO91a9fP5MGK9Z+FxYvXqwUW1rfE89QwYIFVT/W3HvAlu8PMGXKFFW2iRMnxtt+4pvMvQfR78Y67TuFe4H+OJSNiQF9ISiq0D/D8VDP6KcvWLDAZB8yKQoGgHcNzofnXhPaQwn+9OlTdZ+wHxQf9lIwJOY9gD4AjoP2TgghxHlJhT+O9qIghBBCCCGEEEIISQoIrYdwVpisySniziA8EUJGIpQSwj0hVJGzULVqVZVgG7nImOSZEEKcF+f5chBCCCGEEEIIIYQkEiSlRg4D5MVBfh/ykoMHD8bJdYQcW0jMjtwznTt3dirlAvLYILcZcmdRuUAIIc4NPRgIIYQQQgghhBCSIkBS7BIlSoi/v79KYO5MQnNHkilTJvHx8ZFSpUpJUFCQSsh9+PBhleQcSayRqF1Lwu0s3gvwrjh79qzyriCEEOK8UMFACCGEEEIIIYQQkoKZMGGCrF+/Xs6dOycPHjxQyobChQtLy5YtZciQIZI2bVpHF5EQQoiLQgUDIYQQQgghhBBCCCGEEEKshr6ChBBCCCGEEEIIIYQQQgixGioYCCGEEEIIIYQQQgghhBBiNVQwEEIIIYQQQgghhBBCCCHEaqhgIIQQQgghhBBCCCGEEEKI1VDBQAghhBBCCCGEEEIIIYQQq6GCgRBCCCGEEEIIIYQQQgghVkMFAyGEEEIIIYQQQgghhBBCrIYKBkIIIYQQQgghhBBCCCGEWA0VDIQQQgghhBBCCCGEEEIIoYKBEEIIIYQQQgghhBBCCCH2hx4MhBBCCCGEEEIIIYQQQgixGioYCCGEEEIIIYQQQgghhBBiNVQwEEIIIYQQQgghhBBCCCHEaqhgIIQQQgghhBBCCCGEEEKI1VDBQAghhBBCCCGEEEIIIYQQq6GCgRBCCCGEEEIIIYQQQgghVkMFAyGEEEIIIYQQQgghhBBCrIYKBkIIIYQQQgghhBBCCCGEWA0VDIQQQgghhBBCCCGEEEIIsRoqGAghhBBCCCGEEEIIIYQQYjVUMBBCCCGEEEIIIYQQQgghxGqoYCCEEEIIIYQQQgghhBBCiNVQwUAIIYQQQgghhBBCCCGEEKuhgoEQQgghhBBCCCGEEEIIIVZDBQMhhBBCCCGEEEIIIYQQQqyGCgZCCCGEEEIIIYQQQgghhFgNFQyEEEIIIYQQQgghhBBCCLEaKhgIIYQQQgghhBBCCCGEEGI1VDAQQgghhBBCCCGEEEIIIcRqqGAghBBCCCGEEEIIIYQQQggVDIQQQgghhBBCCCGEEEIIsT/0YCCEEEIIIYQQQgghhBBCiNVQwUBICiRVqlRqciVCQkJk6dKlMmTIEKlWrZoEBASoa2jTpo2ji0ZSMK74rHz66aeqzPjvzFSvXl2yZs2qnm3QuXNnVe6BAwdatH+FChXU9tOnT1e/t2zZon5/99134qzs2rVLvvjiC2nevLnkyJFD376ePn3q6KIRQghxQlyxH3Ly5EkZNGiQ6q/nzJlT/Pz8VL+9dOnS8tFHH8m9e/ccXUSSwrh06ZJ6TvLlyyeuxNtvv63KvWDBAnFWwsLCpGDBglKmTBmJjo7W9+FR7okTJya4f2RkpGTPnl1t/9tvv6lls2fPVr/Xrl0rzsjjx49l1KhR0qBBA8mfP78EBgaKr6+vmsc9O378uKOLSIhLQgUDIcQpOHfunBJATpkyRfbu3SvPnj0Td+/wuevA1d0E8SmxPa1YsUL27NkjI0eOVEIH7ZkDy5Ytk/Dw8Hj3P3HihBw6dEh8fHykY8eOatkbb7whNWrUkM8++0wePHggzggELqNHj5Zff/1Vbt686ejiEEIIITYH/fRp06bJ5cuXpWjRotKyZUupWbOm+u59/fXXStFw9uxZm52vdu3aqu/x559/SkrFVQXotsJdxmXO2J4w9r5w4YJ8/vnn4uHhEavPvnDhwgT337x5s9y6dUuyZcsmDRs2VMu6d+8uBQoUkOHDhyfY53cEd+7ckS+//FL279+vlKSNGjVSE64f11y+fHlZtWqVo4tJiMtBBQMhxClIkyaN9OjRQ2bOnKk+9j/88IOji0QISQRRUVEyYsQIyZw5s/Tr10+/vE6dOpI7d265f/++bNiwId5jaAOaZs2aScaMGfXLIbx/+PChGhQ4I/Xr11cKkI0bN8rt27cdXRxCCCHE5tSrV0/OnDkj165dk+3btyvDgd9//12uXLkiHTp0UMJGS70VCSGOIzg4WMaNG6e8F+B9q9GuXTvx9/dXlvxHjhyxqM/eqVMn8fLyUvPe3t7Km+n8+fPKm8HZgDIE8gaMSf766y9ZuXKl8rZAeeEpDa+MXr16SWhoqKOLSohLQQUDIcQpgGvm3Llz5Z133pGKFSsqN0VCiOsB5QEsoeB5YPgcwyqoW7duCVpEQUGxZMmSWBZUGnXr1lVKCrwrbOXlBOsuW1kMfvPNN0oJAiuoLFmy2OSYhBBCiDOBb2aRIkXiLIdAcsKECWoeigct3AohxDlBfxzhguBxYEjatGmlVatW+m3MAaMfeO2a6rO3b99eUqdOrQ91agvglQGPpqSCkEiQN3h6esY5/uDBg5Vc4tGjR3LgwIEkn4sQd4IKBkJSOIsXL1axzNHphyUwchr8999/4s6g86B1ltCh0sK+GLvmwjUSnaUSJUpIunTpVCepWLFi8v7775uNL4tBF44D11SEiUEMS+yLZeioaMDaCx0b3JegoCBp0aKFHDt2TJ0f2xp30jT+/fdftS5PnjxKeIt9mzRpEsdtXDuO4TUbTta6K//zzz+qjDgfOp0Q9B48eFC/7fz58+XVV19V4XAgWO3bt6+yijEFBpw4JsLdpE+fXsXuhYs93GhN1SuuTetQIk7omDFjpFChQur6c+XKpfJ2aHH+De/D2LFj1Tz+G167uZBJrv6swN0XVjcIJYTrR71myJBBhS1YtGiR2f127typrJawj9amSpYsqZR92vVb054076MuXbrEOZfWrmHhb+4Z2rp1qwqzYOhqbaikgIUUnqXly5dbVT+EEEKIM+Pq/RCgWTAjxGFSQ3RqYV7QTwGvv/56rL6H1veNiIhQdQeBJhQfEB5iKlu2rPIqNO4jamjH0el08v3336t+LPZD39SwzwoBKcI+YRyA3FII6YqyJRSKE6Ei27Ztq3IyoT7Qr4Fl+NGjR2Nth/0R+x0g7JThNVpqAGEYRgr1BS8TjD/QD0T/HaFotetBXH3083A9CA/z4Ycfmg1jg+XoW6JdwtscbRPW7ginYyq/lOE4BuMACGthGIL+JYS26JPDOjwx4zLDe4Iy4RrQ18U9gRc8+sGuAu4zvHFr1aqlxjKon0yZMqmcAFoeA1OsW7dOectq+2DMVa5cOXnvvffk7t27Vrcn9NkhZNfCkZrqs//000/qGTPFzz//rMZmeHZKlSoVax3GixhfwNsJCkdXfI/R4JEQK9ERQlIceLQxjRgxQuft7a2rW7eurnXr1rqcOXOq5dmzZ9fdu3dP58zMnz9flRXljo8dO3bor9dSunXrpitYsKDap1q1auq3Nu3evVu/naenpy5NmjS6SpUq6dq2batr1KiRLkuWLGq/fPny6e7cuRPn2Hnz5lXr33nnHfW/SpUqug4dOuheffVV3aNHj9Q2n376qVrn4eGhq1Wrlu6tt97SFSlSROfn56fr37+/WoeyGLN48WJ1P7G+bNmyujZt2uiqVq2qypkqVSrd999/r98W14FjaHVjeI2mjm2unrAvypQ6dWp1zvbt2+tKliyplgcGBupOnTqlGzp0qM7X11fXoEEDXYsWLXQZM2ZU6+vUqRPnmNHR0bp27dqp9dinYcOG6rfWNnPnzq07d+6cyXuMukR9pU+fXte8eXNd48aN1f3BujfeeCPWPsOGDVPl1erK8NrXrFnj0s/KmDFjVNnw37h9YHmePHnUdaBd1ahRQ7UP7T4aM3fuXH1bRFvCPqjXEiVKqOXLli2zqj2FhISoesQ9wr02RfXq1dUxpkyZYnI9yoD1uIem2Lx5s1qPNmAL8MxisgdafT158sQuxyeEEOLauGI/xBzh4eG63r17m+2/a317S7+5d+/eVX2MrFmzqv3QzzTse6APCq5evarWo/+Jfj36qvXr19elS5dOLUcf/NmzZ2brHn12Ly8v3euvv676IOgPabz99ttqGx8fH3V+HDtXrly6oKAgfb/IuD8GvvrqK9U3R/+qYsWKahyBcmjH+vXXX/Xbol+K+sK6gICAWNdori9kDPrH2H/IkCGq34c+M85ZoEABtTxbtmxq3ILzoP/erFkzXZMmTdT5sL579+5xjok6Qz8S69HffvPNN9X+uHYsK126tLpHpu4x+mjFixdX9w7jlXr16ql+P9ahjVg7Lrt48aK+7XTs2FHn7++v+qs4T6ZMmdS6UqVK6Z4/f65zJrQ2gnox5PPPP1fLCxcurMYwGAuhnWhtcsKECXGONXr0aLUO7wm0VYwv0SYLFSqklv/vf/+zqj2dPXtWbVOmTBmTZUc/HmMKbLNu3TqT21SuXFmtnzZtmsn1s2bNUusHDx6sswU4Ftq6PdHaMJ7z0NBQu56LkJQGFQyEpEC0zknmzJl1x48f1y+HkAvCcqwbO3asxcfTOnXWTsadKWdRMMTX4TNkxYoVcQYk6Gj07NlT7du3b1+zCgZ0/iAINebvv/9Wgw0I7Hfu3KlfHhUVpRs+fHgsAa4hR44cUcfEYGnbtm2x1qFDCYEu1p8+fTrWusTUjYahQNlQGIwOZ+fOndVyKBswaDlz5ox+PQZ6Wmf/zz//jHVMdEBNKRIwIMCAAevQwTZ3jzFgevDggX7d+fPn9QNIw/qMTxDv6s+Kues6efKkal/GoI60AYI2+NCAoszUcoD7c+HCBava05YtW0wqfAyZM2eO2qZ8+fJx1kEJB0Ub1hveD+NtMGjPkCGDem6SChUMhBBCHIUr9kM0bty4oRdcNm3aVPUHcSyU++bNm0lWMBgLz9EfNMXjx49169ev10VERMTpL0AIjX3Hjx8fZz/t2tGfOHz4cJz1q1at0t+bEydO6JeHhYUp4a62v3F/7LffflPL0fc6dOhQrHVQLECZgb7r/fv39csNBeiJQasjjDEMDWnQv4YwWuuzQ+hveG/++ecfNX5AvwplMATCaM1Q5/bt2/rlwcHB+mNCMG7qHmNq2bJlLAHtvn379EZRxudKaFxm2K4hlL9y5Yp+HcqWP39+tW7hwoUW15nh+MKayVw7NIW560J/Hf12Yw4cOKDaBtqI4TWiHtE/hnLI2BALHD16NNY9sqQ9zZ49W23Tp08fs9t8/PHHaptWrVrFWYexn6YwM2zLhhw7dkzfhpxVwTBo0CB1nyBzKFasmDoH3mV79+616XkIcQdifH8IISkSuAUbuivC7RfhfeCuu2PHDvnkk08sOg7202KnWwPC2NgbuOoivI49QD0ZA1fcadOmKVdehFAyl4warroIVWMMkljDtbd3794qdI1h6Bck2ULoJCTNMwZutHBPnTx5sgpPZEjlypVV3Pdhw4bJrFmzZNKkSWJLqlWrJoMGDdL/host2hHi5J84cUJ+/PHHWLF44bYL93G4L8NVG+6/GlrZxo8fH6t9wAV1xowZKn7/33//rRJuIbyUIaijOXPmKHdvDbhb41zYF23asE7d7VkpXry4yeWoo48//lj69Omj2izaiwbcyREKwHBZUsqkuf2bKwtAeAC0p8OHD6uQX4b1jrBiz58/N+lqrQGX/+zZs8uNGzdUQklb5U8ghBBCHIUr9kMQAsc4PjvCGKGvhnBApr7f6LMjLI8tQeiepk2bmjwf+qIIy4j+D5LOmuKDDz6QV155Jc5y9PfBiBEjVLhUDYQ7mjp1qoo9byr8khaiE+F9ypcvH2tds2bNVAhKHBv9aMP+tS1Akm2ERDLsXyNMEdoQ+uwIQ2l4bxD6CaFWkeAWoZW0PhWS22pjHPSxDfNKIfQNEvcibOwvv/yi+mII3Wp8TzAmwbhJo1KlSir0Jfr6hueyFtQ9wi5poGz9+/dXoVZxnV27drXoOKiHxDwrptq2tbz22msmlyMU1bvvvqvGfWhfmAdPnjxR/WOE/TL1rGK5PfrsCJP0xRdfqLBNDx48UKHbNLRnH23acLkh2rGRLBo51oxzHjgDCPN0+/Zt/W+0S4T+rVKlikPLRYgrQgUDISkYJBo1RhPGQzhnKYgJaSoGpjOAPAanT5+22/FPnTolmzdvVjFwMYjQEtZhcIEY8khuZSjw1jDs3Buya9cu9R9xYo3x9vZW8XYxGDIE50QZ0CnTEm4ZownW9+3bJ7bGlKIEQmtL1hu2MyhOLl68qOrurbfeirMPBN24PnTqMPAwVjBg8GI4wEtKm06pzwqUUNu2bVPtAJ1lxEWFwQ9yGoCzZ8/GGcigTWIAMXToUBVXNykxk7X4t8jjYA4MOlu3bq3iJWNwgsTIxoMVczlINHB83Becz9IB6ldffWXyXaHlgjB1TgyezQkkCCGEEFvhiv0QfCNfRESQ69evK6OSUaNGKaE14rYj/rohLVu2VJO9QEJWCJgRd/7Zs2f6spnq/yTUZ0eegP/9739m++yoZ8TCh2DeuE+BcmC9uWS06LNDwYC+mq0VDPH1yTHOgALI3HrDdnbo0CE17sE6GBoZAyE3rgP1vXv3bpUfyxAYimTOnNlkm4aCIbF9dlwD8kuYOq7xNVjSfh3ZZ4cS5/fff1c57dButDwYWr4MwzaLusQ4CPn6oBDr1auXyUTrtu6z4/4jZx7uMYzgNIUHxqboxyfUZ8f9Qr8fCpL79+/HUlTFR3z5DtGXN3VOjBtRL9Zy69Yt9R/nQ/1CmYvnZOTIkcr4jxBiOVQwEJKCMbTu0MBHHkDwSMyDgQUSFc+bNy/eanr8+LFJBUPevHlNbo8BWHzrTS1HhwznAYaJ50yhJfiyJfBIMGUhZ8l6w3amXTs6yOYsWAoUKBBr24Tas63adEp4VtDhxmA+vkG01o40kNQQSh0I9jGhLcObAUnmYAFmqm3Hh5bIXKs7c2BggIHJ0qVLleAf7eH8+fMqISIUUKaSzRkC6znD81nCpk2b9IkiTWFshQngfUMFAyGEEHvjyv0QGCZo3quwzIY3AJL1wjjH2n5EYkCyYRiuQHBtaf8nob43hI2od/RJ4DVp6X4wpNH2h+etM/XZYXlvqv8dX59dSxZsrs8OBUNy9tlxDVoCXlseN7lBfxcevfEpRIzbLDxe0M5hmIMJya2rVq0qjRs3Vv1mePXbq88OBQP6yZqCAff96tWr6n7AKyWhPjsUDDifpQoGeMZAUWgKGFCZ6rODxCgYNKAURJQA1CneY/AigcLO0BOfEBI/VDAQkoJJqGNrKegkw5LAWvCRN7ZCdxXgRQDlAty4EZYIbpLoFGGgAXLkyKGswjXLKGNSp04d7/HNWYmbumdwKQU4N1yfE+ocJXc7slU7S2o53P1ZgfcLlAuwxPvwww+VNRc69RhMbtmyRSkNjNsrPELgtvzHH38oATwGEPCWgUUVwjVgP1ihWYqmAItvIA9gGYSBOQYPOAcsNxctWpSgq7VhWAbD81kCLCtNoXlAXLp0yeJjEUIIIbYkJfRDAPoeMFTQLNvffPNNsTcwBIByoWTJkvL1118r70z0I2A9DatwhAmKj/j67PF5dcbXZ8f50Z9JyII+OdtRcvXX7XkuWx4XhjkwcklMe0vKvYNnCIx74EGAkLkImQVPASh6cH0IPwUjN+M+OzwJ4N2AfjomPF9r1qxRE/rs+G3OgC0pfXaEaRs4cKDyzIFnP8IeaQJ+eK6YUvgktc9urk+O5xECf3N9eluA9wGUP2PGjJF169ZRwUCIFVDBQAixyDLInKVAfMA12FUVDLCcAIg/ahzXFR1DzZ3SWqCYgHUT4pVi3pIOFZQGiGGK8DeIZ5rQQMlZ0WLu4trNxeG8cOFCrG1dDUc9KxgkIbYurJnQdo3rFt4B5sAAHNZHmgUSBjxwv8Z1DBgwQB8iwBJwfoA4rfGBAQLi3mJAhPPg3Ja4Wmtox7fUEooQQghxB5yhz66FxrGHhX58ffbly5fHyd8UX/8nPhA2BoY9sIiHxbSpuPum+uya5T6syZ01vKwlaP1wrV9uClfvs2Msl5hnBf3UpCgYoAhAXxsGPFAmGBNfm0W7Mgw1BkOdfv36KSMhKD4QxsjWfXZ4OMCICYZAqC/kdVu9erVFfXaMXfFOguLEHkZw9iK532GEpBSST41NCHFZYOGrxTG1ZrJEUOgoNE8EhEIyhdbZMuXiiwGMOc+FhID1iZZQylQnDEnojIFlCOKNQihvHOs1ISA8ju86kxO4bcPVGtZkqENTFi6wwgG2cEdN6B6npGdFa69w4zeluDFV3+aA0B5uweCff/6xqj2VK1dO/T958mSC54GCAYoGWAdhwkDdEldruFjDewjWgdZYahFCCCEpHUf32dHH27t3b6ITR9u6z26NwNW4vwNPDHN9dpwTCZONgbAdSg7kHdu/f79T91njA8LvgIAApURAOB9jEP4KgnIIjrWxTVJwxPVDqZaYZ8Vcbg1Lia+94vnRhPeWgH7w6NGj4/TZLalPa/rs2vsBYZrwPMDYDm3EWKFnjHZs5HhLTg+apKJ5SNjqHUaIu+A6TzkhhJjg77//VlYk1lqSaNY2cPU0hXY8xKg3VCYcPXpURowYkeh70b9/fyVUhcWKYYcd50AHEdb9pkDCKSgasL8pJQOUD3BHN07ynNB1JjdIJAxQhxicGHaoYS0P4TESd9vCis7Zrt2eFC5cWHXc//33XzXgM2xXUBYYLtNAAkSE/zKVRO23337T58uwpk4RtxSDGjyXCSnhELsXg9Lnz58rF3FLXa0xYMexkVwwKQmpCSGEEGI9U6ZMMRl3H1bZEERCuI5+tHFfDkYkWI445/bos8+cOTPW8m3btsnEiRMlsaBfCtCPgqeooUHQ4MGDlWW2KeCdCRDW1FTuJ/R5169fH+uYsJhG/wneEg8fPhRHgzAxCNOj1YOhJTfi6WMdhNewbDfuKyYGd+qza+11+/btcubMmVjtasiQIbHGRxrwVJg7d66qe0v67Ja0J01RYjx2NLctlJd47rXcZJYoJbVjJ1UpY2ugeMSY3hh4LE2YMEFWrlypIgYgrwwhxHIYIokQ4jTA3ROWyUDryEJorlkQaYOH8uXLxxKSGnbOLAXJcDEAQK4FCGVhXQ9hZY8ePZSQFJ0nuJsiJBGsGGDlgYHTrl27VFxGWGeZSz4VH5UqVVKupZ9//rkSkMJSH1bbhw8fVhbccHNFWCbN8kQDyabgat2zZ09VT4jViQ4qYuyj83jkyBHVgYRCxLC+sC2EyBjM1alTR5/Ibc6cOeIIkBwMwm503GD1glj8uAYoWzAgxX1A4l9bgJwDcCWGJRDqGnUG637EA06OmMDJCQYSaDt4PlCn6Mhj2aFDh5T1GeIxf/vtt3EGuO+9954MHz5cypYtq6x08AzgeUKnG4J+xDI2JKH2hPrGOuRwwLkRBzk+MDjBM6UpOSwZrGBABhKKbewIUA+mni3UlWa51aRJE721GSGEEOJqoB+A/gNyHhQpUkT1F9CHQ182NDRUCYtNhWuEpyr6GDAssAb0PdAHRn8FXgNaeET8Rs4H9Kvbt28vI0eOVP1L9I/Rp0aIR/TnExNnX4s936VLFxXCEeMA9K/SpUunxgBQLmjrjPvsKC/6TzCmQX8M+a5QTwh3CgEt+uzYH30lTdgMjwn0D6CEQZLsatWqKSE/wsoktvxJ5YsvvlBx99FvRx8R149yYlyEfhv68TNmzLDJuRIal6UkMI5FYuaNGzeq/jf6zehPo13BuwH5DqZNmxZrH4zxkCcF4yi0Dwj7oeCB1wLyr2H/sWPH6re3pD3hniKfAkKsYiyphUwyBe5F165d1T3CvUebR2JpV+2zI4cFyg8PEHhXIAwUQmYhLx1kEHhW58+fr8aOhBAr0BFCUhx4tM093hcvXlTr8ubNq3M2UCat7OamHTt2xNoHv+O73vhYuXKlrlKlSrrAwED9MebPn69ff+jQIV3Dhg11mTNn1vn7++vKlCmjmzx5si4qKkpfVtSnqWswXm7MkiVLdK+++qrOz89PlyFDBl3Tpk11hw8f1n3++edq/xEjRpjc7+zZs7r+/fvrihQpokudOrUuICBAV6hQIV2zZs10s2fP1t2/fz/W9s+ePdO99957uvz58+u8vb2tqqtu3brFqRND4jsW9sE6HMMY1N+8efN01apV06VJk0bn4+OjrmHYsGG6O3fuxNleu8e1atWy+lzbt2/X1a5dW5cuXTpdqlSp1HZjxoxx6WcF5Te+Dq1eZ8yYodop2mtQUJCuSZMmur1795qsw4iICN3MmTN17dq1U+0J9wLtqWjRoroePXrojh8/HufclrSndevWqWUDBw5M8FqePHmizont8TwkBK4xV65cuvTp0+tCQkJ0tgD311b3WLs38U2m2ikhhBD3xBX7IejDdu7cWVesWDH1Pfby8tJlzJhRV716dd3XX3+tCw4Ojre/lpjrQX+lbNmyqu9rakywbds2XY0aNVR50K9H/37RokXx1rElfWL0O6ZMmaIrWbKkztfXV40J3nrrLd1///2n69mzp9p/1qxZJvfFOALf/Hz58ql906ZNq/pYbdu2VXX49OnTWNvfu3dPHRP9HNSpNXWF/p2pcZIl7chcvxKEhYXpJk2apCtfvrzqr2HcgroYO3as6sNZ0ydP6FzxjcsSuoaExgqOwtxY6vnz52rMV7x4cVWnWbJkUf3xkydPmqzDx48fq/vw5ptv6goUKKDuBdpTiRIldEOGDDE57rSkPaFtY/nEiRMTvJYLFy7ox1KtW7dOcHu8B3BtaPO2wlb3ePfu3boBAwaodo26R/1gHIR3zNChQ9XzTQixnlT4Y41CghBCiP2oX7++cumGBRbcjglxNRCuC5Z6jx8/lqtXryorIFuxZcsW5ZkybNiwOB4ZhBBCCCHJAazHS5curcIcwco/IY9NQpwReBUhtBImWO/bEoQDRigteGNo4cYIISkb5mAghJBkBu7hEL4aD1TgsgrlAtxX4dZKiCuCkAjjx49XLtQI2WVrd/0MGTKoMAiEEEIIIfYEQlfjkE4IA4WcYlAuIEwUlQvEVUHIr1GjRqmwVAinZCuQTwJhwhCGqU+fPjY7LiHEuaEHAyGEJDOIhz99+nQVgzN37twqYRcGMIhfi5iWiFvrbLEqCbEWJHc8d+6cygEREBBgM+8FxH5GEjxCCCGEEHsCb2LEa0cc+xw5csj9+/fl2LFjKk47cojBMAh50ghxVZDYGHlCkEcNbVvLGWYL7wUoLVq0aGGTchJCnB8qGAghJJnZuXOnSor2999/KytvWHkgsRYSPkP5gIRfhBBCCCGEEMexdu1amTt3rhw9elQpFxBdGkms69WrJx988IEUKFCAt4cQQgihgoEQQgghhBBCCCGEEEIIIYmBORgIIYQQQgghhBBCCCGEEGI1VDAQQgghhBBCCCGEEEIIIcRqqGAghBBCCCGEEEIIIYQQQojVUMFACCGEEEIIIYQQQgghhBCr8bJ+l5TNjRs35LfffpMCBQpIQECAo4tDCCGEEEKIUxASEiIXLlyQpk2bSo4cORxaFvbZCSGEEEIIcY5+OxUMRkC50LdvX7tXPCGEEEIIIa7IrFmzpE+fPg4tA/vshBBCCCGEOEe/nQoGI+C5oN2A0qVLiyOIiIiQx48fS9q0acXb21vcDXe/fg3WA+uAbcG9nwl3u974cPe6cPfr12A9OL4Ojh8/rgxxtP6yI2Gf3fE4uj06C6wH96wHd7tec7h7Pbj79Rvi7nXh7tevwXpwnnpI7n47FQxGaGGRoFyoUqWKOILw8HB58OCBZMyYUXx8fMTdcPfr12A9sA7YFtz7mXC3640Pd68Ld79+DdaD89SBM4QRZZ/d8ThLe3Q0rAf3rAd3u15zuHs9uPv1G+LudeHu16/BenC+ekiufjuTPBNCCCGEEEIIIYQQQgghxGqoYCCEEEIIIYQQQgghhBBCiNVQwUAIIYQQQgghhBBCCCGEEKuhgoEQQgghhBBCCCGEEEIIIVbDJM9WEhkZKbdu3ZKwsDCJjo4We4DjIuN4cHCweHi4nw7I3a/fnesB1+nr6yvZsmUTLy++ngghhBBCCCGEEEIIcWYowbNSuXDlyhWlXEiVKpUShuK/rcExvb297XJsV8Ddr99d60Gn0ymFSnh4uJry5Mnj6CIRQgghhBBCCCGEEELigQoGK9A8F9KmTSs5cuSwm+AXlutRUVHi6enpNpbrhrj79btzPUDJcOPGDXn8+LF63rJkyeLoIhFCCCGEEEIIIYQQQszgHlJLG6F5LthTuUCIO2P4fOF5I4QQQgghhBBCCCGEOC/0YLDSotxeYZEIITFo4cfsleOEEEJchYcPH8qCBQtk3bp1cv/+fQkKCpIWLVpIt27dJEOGDJKSafjdLrkfEh57oU6n74uJQV8sKMBHNg2pmfyFJIQQQgghxE1hf50YQgWDlVC5QIj94XNGCHF35s2bJwMGDJDQ0NBYy3fu3CkjR46U6dOnS48ePSSlAuXC3Sf0ZCOEEEIIIcQZYX+dGMIQSQ60Spw8ebK8/vrrUr58efX/u+++U8vtzahRoyRbtmxKiItzfvrpp5IvXz5xFVBWlJmwPgkhJKUqF3r27BlHuaCB5ViP7QghhBBCCCGEEEdCBYMDgEAgZ86c8t5778mff/4pR44cUf+HDh2qlttTYLB//3758ssvZcaMGXLz5k3p06ePvP/++3LgwIEkH7t27dry9ttv26Sc5CVI8owQGYQQQlI+MDSA54IlDBw4MFkMEwghhBBCCCGEEHNQweCEVom9e/e2m0D53Llz6n+rVq2UF4O/v78EBgZK5syZ490vIiJC7AliKkdGRtr1HIQQQoizs3DhQrN9BGOePXsmixYtsnuZCCGEEEIIIYQQc1DB4KRWiYMHD7a5VSK8C7p06aLmtWTVly5dihMiCcoNrEOc51dffVV8fHxUgsnHjx9L9+7dlWLC19dXcufOrbwwtGNjewhGsC+m+JQk2jl/+eUXKVGihDrH0aNHlSJj7NixUqRIEaX8wLrvv/9edDqd2WNhHxwvf/784ufnZ3KfqVOnyiuvvCJp0qSRLFmyyJtvvinnz5+PdZw5c+ZI8eLF1TEyZswoNWvWlGvXrunXHzp0SBo0aKCOAYVMy5Yt5eLFi/HW+bJly6RKlSqSPn16lZCzTp066jiGQLGCay5YsKCqV3ixwCoVFC5cWP1HvWv1insGjxdt3hDjerfkugkhhDgP+N5aw9q1a8Xdwfc+JIxGCoQQQgghhDgjUdE6iYyKdnQxiB1hkmcntUrEdosXL5YhQ4bY7PxTpkxRwmYcE+GRQHyeC1AefP3111KgQAEJCAiQjz/+WA4fPqyEH9mzZ1fC9xMnTuiPffbsWaV0wDxIly5dvOW5ffu2ykMxd+5cyZQpkxKAw3sD50AIp6JFiyphPMI4QSHSt29fk8fR9pk1a5YSyCPck/E+8JCYMGGCEuI/ePBARo8eLU2bNpXjx4+Lt7e3Ok+/fv2Uh0mtWrXkyZMnsm/fPv05Tp48qZYPGzZMXZ+mFKhXr578+++/kjp1apNle/78uUrGCcUF7uk333yjlBSoKygxADxafv/9d5k4caJUrVpV7t69K//73//Uur179yqFA3JltG/fXn/PjBUL5kjougkhhDgXwcHBVm0PhXPJkiWlVKlSsSZ8uxFizx0ICYuSkmM2S+6MqaVYtrRSLFsaKZotjZrPF+QvXp60pyGEEEIIIcRRPAgJlxJjNkuhzIGqn14kK/rrgep/zvSplbEscW2oYLABEDJfvnw5we2uX79u1XEhmIagPT7y5s0r27Zts+h4EPhrQn94ISQEhOGwuNfANUJBUalSJfU7T548SiCuHRteCBC0W3JsTfiO0A4QfgN4A+D3P//8o5QLEIxg3enTp2XatGkmFQzaPhDyw3MBwJPBeB9DRQ2ELlD2ZM2aVSkjcA1XrlxRSpQWLVpI2rRp1XYQ0GhASN+4cWOlVNBYsmSJ8krYsGGDtGnTxuQ1wvPAkPnz56t9Nm3aJB07dlTeBCj/zz//LO3atVPb4JorV66slAOaAgj1a2m9GpLQdRNCCHEuElLOmwJKcEwrVqzQL9M8+oyVDzAESGkd+MjoGGuoqw9C1bT15G39Oh8vDymcJWYg83bVfFImV3oHlpQQQgghhBD3JDwyWk7efKwmQwJ9vaRw1kBpVCqb9KkZIx8krgcVDDYAgnd7hJ2Bxbsjw9loigSN/v37S+vWreXgwYNSt25dadiwobLGh6eAOZBQGpMGvAw6deqk5uG1oCkXAI6LMAcQrhsCbwFzIZK0fSpWrBjvPrt27ZKvvvpKeVzAkl9bB08ACNrr16+vBPAI2/TGG28oxQryVKCMAAJ55K9AvgpjJYmW18IUUJZ89tlnysPi3r17SmmAmNmaBwKWA5zfHiR03YQQQpyL5s2bK68ESylUqJA8evRIfWOMv0/4xmjfGQ2EzDP2dsAEL0JXBUqE6oUyyulbT+Rm8PM4A5kTNx6rqUW5nLHW7b9wXzaduKU8HuDtAAuq1D7u4fVBCCGEEEJIcuHn7SElc6STs7eeyBOj0KZPwyLlyJVHUjJHjLGvxvOIKOmx4IDqo2seD4WzppG0fozG4YxQwWAD4EVgCfBgsDREEoA3AMLj2OLciQEW/YZAmQBL/82bNyvhR+fOnaV06dLKg8LLy3RTQtghzTIfwHre3PEhfAc4NtbBgyE+5YXhPhCka54HxqDMjRo1UiGGRowYobwCoqKilEAlPDxcbQPFAZQVe/bsUdfzww8/yAcffKDmK1SooM4DjwOEiTJGC3VkDBQJUBxAUYP8DvBAgJcHFCjaeROLVi+GShTjRNyWXDchhBDnolu3bsqD0ZL+AnIVQQGOPD937txR3nzGE0L+GYLfCMOnheLTwDcC3wdDjwfM49jOjr+Pl8zvHmNoEPwsQk7feixnbj9RCofTNx/LmVtPJCQ8SoplTxNrvz3/3Zf5e16GHIRjR76gACmaNY3aNibUUlrJk9FfPD1SltcHIYQQQgghyUUaP29Z9U5VJcOCQRD66lA2qP+3n8i5209VH9yQ/+4+lb3/3VeTITnS+UkR9NNfKB6KZ08rJYyUEyT5oYLBBlgaoghx9IcOHWrxcWH5b8scDLYAwvQOHTqoCeF/kMAY8fwROgnCcwiwjbc3J4A3BgmlNcF4s2bNLFIwGO6D8EamgPAFwn7kToDlJkBCamNwPiR2xoRQSAgtgTwYUDBggjcCvBwSKpPGqVOnlMBn3LhxShGjeQ7cv//y5Vi+fHn1f+vWrbEUMYYgV4JxvWqWpjdu3FAhoYCxlaql100IIcR5QBi96dOnq/w8CYFQgJoCAN8FeN8ZhjZEB/7q1auxFA7waEM4JXg4GIL8Pzt27FCTIbly5Yrj7YC8QlBuOCPp/L2lUoEgNWlER+vk+qNQyRzoG2vbM7diu2dDZ3/xXoia4NmgMbReERlcr3AsayoklQ4yOh4hhBBCCCHEPAjVmiN9ajW9XjRLrCTQEUZJoK8/DFVGPlhnyI3g52r688xd9RueDxsG1Yi1za6zdyV7Oj/JlylAvJmPLVmggsFJrRLhvdC1a1dxJkaNGqUE+rBohJB96dKlSsCgeVEg3BG8DxAyCAISCLV9fX2tCvPQo0cPeeedd1S4h+rVq6u6guAcSalRd+b2Qa6Fx48fq7A/ISEhsfYpUqSIeokhiTLuwZkzZ+IcC4mrL1y4oJQLsOJE0mcIZbS8DtgeYZgQ3glKIi3RMvZ79913VXJpYxBuCTGwISiCNwSUAfhvmBAa5ccxBwwYoLwKoLBBKCMkdx44cKC+XqHEQkgq1CcUNtgP9Q5FyNSpU1VoDHgpGGLJdRNCCHE+8F0bP3682TCJ+PZCuYDt4gPfAORLwoQ8QhpQWuObZ+ztgO+EsUL72rVrakLuIMPj4ttk6OmA//juwNjAFgQFxBwnNDxKuU2D1N6e4u+dKkbRb5BHQtvWHB4eqSR3xrgKkSlvvSLn7zxVHg7weoDHA+bvPAmLtR3csQ3Zd+G+vD3/gGRO4xvj5aA8HmKSSxfKEih+3gyzRAghhBBCUjbog8NA535ImPqvLRNdtNX9dSgSPD1i96HfKJlNTn7WQBn/oI8OT4czt56q/1cePNNvZ+z5AIVEn8UH5XlEtHh7ppKCmWOSSSMnW9EX/5FYGmMEYjuoYHBSq0RYnTtbWAIIyz/55BMlWIe1f9myZeX333/Xeyh8+OGHKrkylBAIwYCExm+//bZV55g9e7Z8++238vXXX6vwSgh7BMEF8j/Etw+E6PD4gMDEeB94D3z//fdqPfIRQAgCwQwUGIb3Zv369WoblB1JMCGw79Onj1oPa00I/REiCaGioPiAVefrr7+u9jVFUFCQ/PTTT/LRRx/JggULlDAGAqPBgwfH2g71hDwNODaUELBCNUwaPXnyZHn//ffV/mFhYSqxNZQXSAyNa4T3CJJiIyG44TVZct2EEEKcD4Ts05QL8JyDggCKZOQFgrceDBDMfXssAd9wKMYxtWzZUr8c35izZ8/GUTzgu2MYkg/zKB+mtWvX6pcjXCK+R8YeD/C0wzmtYdOQmhIZFS21vvlTKRg8RCdB+2dI8M1L6vuKeoDyPCn1AEVAqZzp1GTIg5DwmDBLLxQOxuuhiAB3n4Spafe5l/kvME7JnylA5XR4o2RWaW6U98EaGn63S+6HGIU01OlU2EZTgzbUGSGEEEJIcvLw4UMl74DxJaI12KqfRpwf9D2X7LssH6/9V/1+u2o+GdmwsDKahZzQFoZHvl6eql+NyRB4EytDodtPJFf6l0a84OqDZ0q5ACKidDFhU9F/P/ZyG38fT6Vo+KVf1SSHQmWfPYZUOnPZc90UxCSGFTyEybAmN0RL5mvKWt0a5s2bpyzWTXkywCoRygW8jC0JEZQSwcAZFpTuev0a7lwP2rMGLw1bfpxcFXi3sB7crx7c7Xrjw93qAjmO4CUIVq1aJU2bNnXo9cMzEGH/jBUPyC1lCfDcg0egodIBhgBQ1MMbwhzrj92QgcuOqPmn/26X+xsmxTkuDDcS8uSwNZtP3JK1R64r5cPF+yF6iy1j+tQsICMbF9f/Dg6NkK9+P/0iqXRMYmmEdDLHa+O2KQWGJcCb4sCoeuLIfnJy4wxlcbd3kzHufv0arAf3rAd3u15zuHs9uPv1xyfbclQ/zVG4Y1uAp0C9STuVhwFk9H++/7pkS+Pl8HqAsdCGf268yPPwVBkOPX4eO7E0yBfkL38Ofz3Wsr6LD8rDZxEx+R1e9NmLZEnjcn12R/SV6cHgAPCChcXgwoUL5ddff1XhgOCt0Lx5c2WVmC5dujghCgghhBCS8oEnGzzUALzV0DdwdJ8gICBAn4/I2GINOR2MFQ+GuYYABp0IPYjJEHgcGns7YEIYQnBg9x/y/NpN8ctVUh4fWBOnXDiu5hWanIPXBiWzqUmVITxKzt1BMukXSaVfeD7A88DYXRvLl/19JdYyxIZV7trZ0kjxbGnVf7hx+3i5l2EBIYQQQlxPuRBfdA5H9dNI8vHoWbgKQwoFQ6NS2SVPkL9StDiajAE+0qVKPv1v2NUjBCr66oaJpeF1bAi2+/viA6VgwH9DsqXVEkvHhFtqVDq7BPqaEanrdFL3asy454/cr8byOk7JUMHgIOAqhgTOppI4w3KdEEIIIe4Hwt1FRsZY2AwaNEh5sTlawRBfXwZh9wxD76Fjfvv2bZOKh6dPn8baH7mTYFGDyRCECkSoJSzHtXtnyisR9y6bLQdyFsFwwxFu+Kl9PKVMrvRqMgRWTH7eHvEmlQY3g5+rSUtSByrmzygr+jrWO4AQQgghxBwwMoHngiU4sp9G7EtQoK8s6lFRTt187NTGMfCYzprWT021isQYMpkiJDxKsqTxkyfPIyXSKLH0rcfP1YTk0aBOsSxmFQzl7p2X9w8vV/P3UqeTY5mTFgXHVaCCgRBCCCHECXj27JnMmjVLzQcGBrqktRc68NmyZVNT3bp1Yykerly5EkfpgNBLyP1gyJ07d9SkEZ9yQau3RYsWxclx5Ejg/mxMh4p5pErBTHGSShsmqQOFs8ROKk0IIYQQ4kwgGoepsEiu0k8jtqV49tj5EVwVKAw2D60p4ZHRcun+y8TSyvPhRWJphEbNFOirlCsm0emk0+kt+p+YP5apkFt4MVDBQAghhBDiBCxZskQfXggu5QiZmFKA4gF5dTA1adJEvxzeGhcuXDCpeLAGJBZ09oGrl6eHFMoSqKYmZbLrlyOJNQYtWlLpaoUyObSchBBCCCEJ9btSWj+NEA14YyAMEiZDnoXHJJZGjgdzlLt3Xkrdv6j/Xfr+RSl777xbeDFQwUAIIYQQ4mBg4f/dd9/phfFwJ3cHvLy8pEiRImpq1aqVWjZ9+zmZOekrObVpkUhU3IRspkA+K1e2liqfJ4OaCCGEEEKcneDgYKu2d+V+GonL1QfPZNup29KuQm4JMJeHIAXi7+MVJyxqfN4L7ubF4LxBsgghhBBC3IStW7fqrfaR2LlgwYLijtx58lym/nFenpVqJdk6TbB4v/Tp4+nsE0IIIYQQm2Gtly37aSmLuX9dlLHrT0qV8X/I0atUHpnzXjD2YkjpUMFACCGEEOJgJk+erJ8fMmSIuCuL9l6W8KhoNf/s9F8W7welDCGEEEIIsT81a9a0anv201IOj56Fy88HrurDfxbLFjuMkNsSHS39j602u1p5NiCBQwqGCgZCCCGEEAcCz4VNmzap+XLlylk9aEspIK7p4n0xCZ0DfDwl8sxOi/bz9/eXbt262bl0hBBCCCHk5s2bsnjxYosrgv20lMXS/VckNCJKzXetklf8vD3F3cny+K5M3TlVcj+9a3Ybd/BioIKBEEIIIcSBTJkyRT8/dOhQlYPBHVl58JoEh0ao+Q4V88i0SZaFSJo2bRpd7wkhhBBC7Mzdu3elXr16cvFi3DAw5mA/LeUQFhklC/ZeUvO+Xh7SpXJecWeiw8Pl7owZ8uWv46Rw8LUEt0/pXgzuk42DEEIIIcTJuH//vixatEjNZ82aVdq3by/uSFS0Tub8dUHNe3qkku7V80vO9CXU7wEDBkhoaKjJ/QIDA6Vt27aSEgkK8Im7UKeT6Oho8fDwiJUozuS2hBBCCCE24sGDB1K/fn05efKk+l2mTBnp1auXfPjhh2b7aWPHjpUePXrwHqQQ1h29IXefhKn51q/mkqBAX3FXQvbtk1ufjpXwS5fE0l546fsXpVKw5co5V4MKhmSk4Xe75H5IuEXbBvl7y8bBNcQZWbBggXTv3l10KVjzRgghhCQHP/74o35Q9u6774qvr3t21DefuCVXH8TUQ9My2SVn+tRqHoPSli1bysKFC2XdunVy7949yZQpkxKy79q1S54+fSpTp06VUaNGSUpj05C4obLCw8PVAD9jxozi40OlAiGEEELsT3BwsDRs2FCOHTumfhcvXly2bt0qWbJkkc6dO8fqp0VGRsrp06fVdkePHuXtSSFA/vfjrhhjINi49KyeX9yRyHv35PaECfL41/UvF8LwJzomh1xCfBR2QlIqVDAkI1AuaNq+BHFi4T2sK/FxIYQQQkjiiYiIkOnTp6t5KBb69u3rtgOWWS8GLKB3jQKx1mfIkEElvu7fv79euI7/BQoUUMqZb7/9Viln0qdP74DSE0IIIYSkXGDM0bhxYzlw4ID6XbBgQdm2bZtSLpjqp6VNm1bKly8vZ86ckTVr1sjhw4fVb+La/Hn2rpy781TN1yueVQpmDhR3QhcdLY9WrJQ7kyZJ9OPH+uWBdepI2iaN5fZXXxntIAZexy8XZ+jYUVIqVDAQq0mdOrWaCCGEEJJ4fvnlF7l+/bqah/WXNlBzNw5ceijHrj5S89UKBUmpnOkS3CdbtmwqdNI333wjjx49kkmTJslnn32WDKUlhBBCCHEPYMjx5ptvyt69e9XvvHnzyvbt2yVHjhxm9/Hy8pJPP/1UOnTooH5/8skn8ttvvyVbmYl90LwXQJ+asY2BUjrPT5+WW2M+ldAXHjzAK3t2yfbxKElTt676na5JE3F3r2MmeXYz3n77baldu7YKyYCPA7TL+GDcvn1brUeynjZt2kjOnDmVEgGubwg9YBgOCSGStASU0GYj/jFc4gzBgwRrzOXLl8dK7lOsWDHx8/OTwoULy+eff66sNwkhhBB3A9/VyZMn638PHjxY3JVonU5KZE9r0nshPj744APVBwGoS7jlE0IIIYSQpBMWFqbCVO7YsUP9howIyoU8efIkuG+7du2kVKlSan7Dhg2yb98+3hIXJjQ8SiKjYmSC5XKnlwp5M4g7EB0SIre/niAXW7d5qVzw9JSMPXpIwd/W65ULJAYqGNyQI0eOqA8DXvSbNm1ScfTef/99vcIACgisO3HihBq8f/TRR/oElMZgYN+6des466FYgIKiRYsW6jc02AhhMH78eDl16pRSWkDJAW02IYQQ4m7873//07ua161bV0qXLi3uSuUCQbJhUHVZ0beK1CqS2eL9kIth6NCh+v4LvBkIIYQQQkjSgCEoQmNv3rxZ/c6aNav88ccfKjylJSAsDBI8a4wePZq3xIVJ7eMpK/pVkTX9q8ropsX1BscpmSfbtsl/TZrKg/nzRaKi1LLU5cpJ/tWrJOsHw8UjIMDRRXQ6GCLJRszfc1EW7r0U7zYPnlqYfwHbhoTL6xN36kN1ZU3rJz/3rRJrm73/3ZOqBTNZXVZvb2+ZP3++8iQAffr00ceAhoDDUMiBDwgEIEuXLpVu3bqZPB6W16tXT65evSq5c+dWy6BwwAcJ53j27JlMmDBBhYJA7D6QP39++eKLL1TM5C+//NItXlCEEEKIhqH3giYkd2fQD6iYP6PV+7333nvKQxJhkvAfdYnwSYQQQgghxHqQpBmhO5G0GQQFBamcC0WLFrXqOPB+eOWVV5SBK/bftWuX1KxZk7fEhXklT8r3XIi4fl1ufTFOnr7w3AEeadNKlmHDJH3bNpIKORWISVgzNuLRswi5dP9ZvNMLjyKLwLaXDfa99jA0zjbPI2K0aNaCD4OmXACIn6eFSEKMvVGjRiklAz4k8FCYM2eOXLpkXnny+uuvK8XC4sWL1e+zZ8/K/v37VTgmAE8IHLdt27bqeNqEZJawOLx161airoMQQghxRS5fviyrV69W80WKFJFGjRo5ukguCxI7a16Y6GvAU5IQQgghhFgPktL26NFDVqxYoX6nS5dOtmzZog93ZK3xCMJiG3oxGIbeJsSZ0EVEyP05c+S/ps1iKRfSNX9TCv6+UTK0b0flQgJQwWAj0vt7S74g/3gnTyuM9LFtXoN9c2WIm1TZz9szUWWFB4Pxi1970Q8fPlzmzZsnI0aMUC5wR48ele7du6sEJebA/l26dNHnYYD3AgQmVapU0X+ktLBJOJ42HT9+XM6dOyeZM1seDoEQQghxdeA1qH0bkXsBbuTuyM8Hrsivx25IZFRMXVhLVHSU7Ly6U1p0byGZssR4dP7www/Ko5IQQgghhFgOZELvvPOO3nAURqEIqV2+fPlEVyMiWFSqVEnNw4MBMibiOjx+HqH664k1bnYVnh0+LBdbtZY7304UXWiMcbdP/vySZ8ECyfH11+IVFOToIroEDJFkI7pXy6+m+Hht3Da5+8SyMEkZA3xkx7Ba8QodEhMeKSF27twpHTt2VJMGPBISomvXrjJu3DgVU3rJkiUq7JJGyZIllcfEf//9J82aNbN5mQkhhBBXAZ57yEGkWd/j++muyeK++v20PHwWIdOzBsqmwTXFw8O8JcaT8CfirYttIHEz5KYM2D5AzdcYW0PWvLNGGUSgPwJFw+HbhyVHYA7J4p9FPFK5pxKHEEIIIcQS5cKQIUNk9uzZ6jfyaSIvZ+XKlZNUeZoXwxtvvKF+f/zxxyr3GENkuwY//31Vxm08Jd9sPiNTO7xiFxmkI4l8+FDuTpokj1b+ol+WysdHgvr1laBevcTDx8eh5XM1ONoisShWrJisX79e9u3bJ6dPn1YeDYcPH06wljSPhf79+yvLQXg0aEDzPXLkSOUSh/jIZ86cUWGTfv75Z3V8QgghxF1YsGCBBAcHq3ko4/GNdEd+OXRVKRdA9UKZ41UugM/+95l03NRR/r77t97r8vLjy/r1DSo20OdemDt3rpw+f1re3vS21P+lvgzaPijO8c49PCcPnz+kqz4hhBBC3Br0qxDBYurUqeq3r6+v/PrrrzbLl4B8ndqxEEp748aNNjkusS8RUdEyb89FNf84NFIKZQ5MUW3+0Zq1cqFxk1jKhYCqVaXA+l8lc//+VC4kAioYSCy+++47KVSokPoI1KhRQ1kCIhGzJSDZM0If1alTR5/sWQPKBRwbg/6yZctK9erVZdKkSZIvXz7eAUIIIW4BwiJNmTJFzXt6elr8fU1pREXrZM5fMQMWT49U0r1a/H2BE/dOyKZLm+Tco3My/dR0idRFquV50+aV4RWGS7si7eS1nK+pHFJacsJPJ38qOolRRORKkyvOMXtt6SU1f64pXX+P60Fy4+kNeRbxzCbXSgghhBDizHz22Wfy9ddf68Npr1q1SsmDbIVxLoZPPvmEBh4uwIZ/bsrN4Odqvnm5HJIl7cs8rq5M2H//yZWu3eTmiBES9fChWuaZOZPknDRRcs+dIz558zq6iC4LQyQlI0EBlrvXBPnHDgNgS8tJY5CMWUvInDNnTpMa5S+//NLk9oYgaTMmc/Ts2VNNhBBCiDsCV/Pz58+r+datW0uePHnEHdl68pZcvh8jwG9cOrvkzugf7/apvVJLtZzVZM/1PdK9cHfx9vDWKw66lnypICjZu6RMmDBBeVKuWb5GxrQeIyE+IfJq1ldjHS84LFgePH+g5jOljuvqPXjHYDn94LQUSl9I1jRfE2sdvB4CvQPF29M+/TRCCCGEkOQC/aZPP/1Ub/yCvJlNmjSx+XngwQClxbZt21SEjLVr10rLli1tfh5iOwv/2bsu6H/3rlnA5as2+vlzuffDD3J/7jyRiBgvakmVSjJ07CiZhwwWzzRpHF1El4cKhmRk05CaFls4RkWl7CQqhBBCiLsBTz6NoUOHirsOWGYZDlhqxJ+/ChRIX0B+qPeDHLh+QHJ65DS7HVz64TGJ0FPhD8Ll+I/HZdmyZSbL0Lt0bxViyVj5gHVa6CUoNowZvWe0/HX9L8kZmFPWNl8bS9EArwc/Lz/meyCEEEKI04OQSB9++KHey2DRokXSqlUru50PXgxQMGheDM2bN4835yhxHHv/uy8nbz5W87WLZpYiWV1b+P5092659dnnEnH1qn6Zb4nikn3sWEldurRDy5aS4NNMCCGEEGJnjh07Jtu3b1fzlSpVSnLSPFfl0OWHcuTKIzVfuUBGKZMrvcX7ls1cNkHhPTwsCxSIsbJCrqfjx4/H2Sa9X3oZVH6QTKw9UToW7xhrXXh0uLQt0lZq5aolr2V7Lc6+UD5E6aLkedTzOF4M3x78ViourSitfm0l90LvxVoXGR3JcACEEEIIcQqQzHnw4MH63whl3bFj7D6RrUHfV/OO+Pfff2XFihV2PR9JPIbeC31quK73QsTtO3Jt6FC52ruPXrngERAgWUeOlPwrVlC5YGOoYCCEEEIIsTNa7gV39l6IM2Cxg7s1YgePGTNG742gzVuKr6evDH9tuEyvO12Gvhr3PlXNUVUqZa8Ux/MBXHl8RcKiwuTCowuSzjddrHVzj8+VasurSccNHdV6Q7Sk1YQQQggh9gaeCv369dP/njFjhnTv3j3Z8j1oIDQT8mYR5+LMrSey8+xdNV8ie1qpUjBIXA1dVJQ8WLxELjRuLE9+36RfnqZhQymwcYNk7NpFUnkxoI+toYKBEEIIIcSO3L59W5YuXarmc+XKZVf3c2fmwt2nsvXUbTVfOEug1C6Sxey2EVERMvCPgbLr2i6rBfCdOnWSYsWKqfk1a9bIoUOHxFaMqDRC5rwxRybUnBBnXfGg4lIuczkpmamkPk+EoefDk/AncvzecQnwDoi1bu35tVJ3RV3pvqm7HLt7zGZlJYQQQggxBN6dUCZofauJEydK//79k62Sypcvr8+9cObMGfnpp594g5yMH3fHNgZC+CxXIvT4v3KpXXu5PW6cRIeEqGXeuXJJ7lk/SK7vJot31qyOLmKKhQoGQgghhBA78sMPP0h4eLiaHzBggLKyd0fuPQ2X/JlihOu9axQQDw/zA5YVZ1fIn9f+lHf/eFdm/zPbqvMgSeHYsWP1vxHnNzkYVmGYLG68WJY2jlEmGZI9MLsUy1hMgvyCJIt/ljjKhzuhd+Tg7YOSSmLXyb6b+6Tx6sbSb1s/2Xtjr92vgRBCCCEpk3Xr1ikjDOT8BF988YW89957yV4O9NE0oTXmI7SEu8ThREXrlEEQyJ7OT5qUyS6uQtSTJ3Lr8y/kUrt28vzEiZiF3t4S1LevFFj/qwTWquXoIqZ4qGAghBBCCLETz58/l5kzZ6p5f39/6d27t9vWdcX8GWXb0Foy7+0K0vyVHPFue+JezMDAy8NLGhdobPW52rRpI2XKlFHzGzdulL17HSucH/jKQFnZbKXsaLcjjiVYoE+g5EubT11r3rR5Y627GHxRrj65Knuu71FJpAkhhBBCrGXTpk3Srl07iYqKUr8//vhjGTVqlEMqsnTp0tK+fXs1f+HCBVmwYIFDykHi4umRSla9U1V+6l1JPn2zpHh7Or/IGN44j3//XS40biIP4TH+wjvHv0IFKbBmtWQZOkQ8Uqd2dDHdAudvLYQQQgghLsry5cvlzp07ar5bt26SMWNGcWfgtVCnWFbx9fKMd7sva3wpc9+YK+9XeF9yp8mdiPN4xIrzO3r0aHEGTLmZ9yrdS9a3XC8HOh2Ik7sBZA+IsR4zVj4QQgghhCTE9u3bVVgizZt22LBhsfpIjgD5F9BXA59//rmEhYU5tDwkdl+1asFM0qBkNqevlvArV1QC5+tD35PIuzF5IzzTp5fs48dLnsWLxLdQIUcX0a2ggoEQQgghxE4WNd99953+9+DBg1nPVlAxe0XpVLxTouvszTfflAoVKugH1zt27HDq+ocHgzEdinWQLW22KOVDgXS2T4pNCCGEkJTLnj17pFmzZsqjFrz77rvyzTffODyuftGiRaVz585q/urVqzJnzhyHloe4FtHh4XLv++/lQrM3JeSvv/TL07VpLQV+3yjpW7ZwWBt/+PChTJ48Wd544w2pX7+++o/xIJandKhgIIQQQgixA3/++accOxaTtLdx48ZqMOWObDt5W7aevC3R0dYla04qGFjAKs7Qi8HahNHOgp+Xn3h6xO/1QQghhBCiceDAAWnUqJE8exYTYrFnz54ydepUhysXDHNkIW8WGDdunISGhjq6SG5LZFS0bDx+UyKiYvJzODMh+/+Wiy1ayt0pU0X3wvPFt3Ahybt0ieT44gvxypDBYWWbN2+e5MyZU+U22blzp/z777/q/9ChQ9VyrE/JUMHgQDDIfbR2rZqSa8D79ttvS+3atcXVQbzAbNmyqY+jZh06ffp0yZ07t3K1GzJkiKOLKJcuXVLlg4ApIfLly6fcBDUiIyOlV69ekj17dvXRXbt2rTgriJlobSclMfsQQoirYei9gI6luyaLG7fxlPRedFAaTtklYZExsX9NcfXxVdl1bZdN+0QNGjSQatWq6a34Nm/ebLNjE0IIIYQ4IzBwQR/oyZMn6nfHjh1l1qxZ+rBEzkDBggWlR48eav7mzZvy/fffO7pIbsvmE7el/9LDUmvCDtlxJia0q7MRef++3PjwI7nSrZuEX7iglqXy85Ms7w+T/KtXi/+rrzq0fPPmzVNKPHOKMizH+pSsZIjri21jzp49KydOnFDxhyFQzJw5s5QqVUoKFy4s7s6zffvk5kcj1Lx3tmwSULmyo4vkEuzfv1++/PJL+eWXX5TQIG3atHLjxg0VemLSpEkqeVFgYKBNzgVlDIT/9k48BOuC1AaJZ1atWiVLliyRLVu2SJEiRSQoKEg9P/Pnz1dKIkIIIc7N+fPnZf369Wq+ZMmSUrduXXFHtp26LRfvhaj5wlnTxJt7YcqRKbL50mapkLWCfF3za8ninyXJ58e384svvpDXX39d78WAATeV3IQQQghJiZw8eVLq1aunD8nSunVrWbhwod5bwJlAsmmUDfkhvvrqK+nTp4/NZDnEMmDYM3vXf2r+RvBzyRzo61RVp4uOlke//CJ3Jk6S6OBg/fLAWrUk6+jR4pMrpzgaPGsDBgywaNuBAweqnCgZHOhpYS/sor48deqUEvbCBaR48eLSpk0beeedd6Rfv35qvlixYpIjRw5lZY5t3fUhvjt9hv733enTXdZtP7k5d+6c+t+qVSvlxeDv7y8XLlyQ6OhoFW8ZVv9p0qQRV0BLtATFm+GHFNeI64ACBdfo6+tcL3lCCCHxAxd07buO/o67CrR/3BVjYQT61DCfQ+Bi8EWlXAC3n92WDL6263TDWKBOnTpq/uDBg/Lrr7/a7NiEEEIIIc4C5Agwarl375763bRpU/npp5/Ey8vutsWJIk+ePNK7d281f/fuXRWVgiQvBy49lGPXYgT3VQsGSamc6ZzmFjw/c1Yud+ostz4Zo1cueGXNKjmnTZVcP3zvFMoFACVZqIUhvhCybNGiRZISsamC4b///lMKBHgozJ07V8qUKSNjxoxRlbdx40bZsGGDmkestbJly6pELti2bdu2SkDsbt4LoYcO6X+HHjwkz/bvT7bzT5s2TYUTgtU84vIhsY7GxYsX1X2EggjroSQyFJSAa9euKU14pkyZxM/PTwoUKKCSBWlERESokD/58+dX60uUKKFc3ixRoixfvlxee+01pTjImzevCisREhJj/Qjr/S5duqh5uPdBYINlNWrUUMtQDsOwRFu3blVCelwHlFrYFh8uQ37++Wd59dVXVTnhKYD6gAYS2yJeGl4WOCam+DwZVqxYIYUKFVLHqVq1qvzzzz9xtsExkPAFCY3Sp0+v6tA4RBIEIbCwvHLlivj4+ChLA6wH3bt315cFIZhMgeNg+9WrV6t437h2WDDcunVL/vrrL5XwMiAgQJURHkaG4DlFXUChkSVLFqUYfPr0qX49lDgoG9ZBIdK+fXuTyWoOHTqkLESh6IHyBBpatCtCCHEHHj16pHd/xXeyU6fEJyp2ZQ5dfigHL8d8Iyrmzyhlc6c3u23+dPllXoN5UjpTaRn0yiDx9vSOtR79hye/rpewzZsTZZBhnIsB3zNCCCGEkJQC5ANQLmDcD5BgduXKlUqm4MyMHDlSyVDAhAkTJNjASp3Ynx93v5TF9q5p3hgoOYl+9kxuf/ONXGzVSkKPHIlZ6OkpGd9+Wwps2CBp69d3KuOtdevW2XV7V8GmakwIkUuXLq2EsLAuhxAzPiA0RpibKVOmqH21zPbu5r1g6MXgX6mS3c9/+PBh9QJH6AZo2fr376/u199//60eUgiUIeSGuxrCD0HI/u6770q6dOmkW7du6hjYB5q3bdu2KUE5PmaIm6cBLTTOgzh/CIeFEEBwd4NSoG/fvmbLhrYDhcLEiROV0gDHhKsRPpLLli1TbeWVV15R1qDa+SBAh+cChPW4BihOMmbMKNu3b5fmzZvL119/rY6LD9Xw4cOlRYsWStCuhRxCuaD0Wrx4scp9sGPHDomKilLnggAex8M8QB2Y4siRI9KhQwcZNmyYiquGsGDw4jHFZ599ps4HRQDOYwwUAwgBBcXH3r17lYLB29tbCfURzxtCfQDBvTkQkuyHH35QdYZrwj4IHQVwLbgOKFBQ1t27d6vlUIigHuGytXTpUnVPUTcQlOE4mmIK9waWBdWrV1e5IcaOHRvHJbNWrVqqLnAunB/bQMmBJDeGoaAIISQlAiMLTTEO7013fe9Z6r2g8Vq212Rp46VmDTPufPyxmg8tUEB8XxgWWAqU6ki0DUX68ePHVf9T+y4SQgghhLgyMACFt6ZmOFqzZk01VtcE984MDEFh2AhDTBgvQuYBQ2Vif/67+1SFMwWFswRK7SLmZUzJxZPt2+XWF19I5I2X8kW/MmUk+9hPxa94cXFGrFWKPXr0SFIiNlUwQDsKAaWlQAEBgTUmV9bgXO7eXSJu3LB4++jQ5xJ1J27iFHgxnKtVWzwMPwIJKOW8c+SQvPPnW1VeCHwhQIa1PoBgHYohCNbxUcI8Jg14BUBBgH00BcPly5eVVXq5cuXUb83CHsBSHZ4qECZDcQTgyXD69GkloI5PwQChO2Ilw0sBgnUoJyDMhsAa+8ISVBPyI3SQBhQKmtBdWw5BPpQTEJhrwBsBXhGwsIclPz5cUIbAmlEDnjca0PZDMGR4LlNA6I7jQeMO4DmAvBCG59Zo1qxZvMk+cS3wDsD147z4ryVjwrUnVBYAZR3ugbYtrhGJsaGAgXcIQGZ7eFJgW3Q84IGC+4kPO0AoM9Q5FDLjxo3Te6ngmrRkTB988IE6JnJGaKAOIMQxVDwgnwRizMGLCd4xhBCSUsE3Fu9OAOUwFPLuyKV7IbL5ZIwFXcHMAVKnmGX5FExZIxkbZjz8/gdJV7261ZZL6BdAwQCg6IdxhbOGDCCEEEIIsQQYY8JzQYsYULlyZfntt99URAhX4aOPPlLGqTBiRV5NyBw0GQ+xH3P/uiiaYzC8FxzpFQCZ6q1xX8rTP/7QL/NIk0ayDHtP0rdtK6mcMIeIhjlDZHPASDslYtMQSdYoF4yBpXliePDggbz//vv60DQQMCORn2aVnVwPQsTlKxZPppQLGlgXceXKyymh41mh2NCA8FtTLgCEqcIDAYUAgFcDhNFQMmA7CLsRzsowJA88CGBlX7FiRfnwww9l165d+nWIbwxhANZhX23C9lr+BMwbroPyAqGLoLjA/YQwGt4TWIeQRUDb11KgFEFoJ8PzaAoPHAtW/tDww3UwqcBqH9aRhsDC3xSVksFLBfkbDBUR+A00hZC2DPcJ9QDgdaGFmtKAYkdb9/jxY7l+/XqC14l6h7WEYb2jHUGRYe09JIQQVwPvP3zLwFtvvaV//7r1gKVGAfHwMD1guRd6L8GQR8ZhJZ8fPpyosJIIAQjjCHDmzBkVk9iVSGqYKEIIIYSkLJBrAZECtNDH5cuXl99//91lclJqIFrDoEGD1DzkDjDgJPbl/tMwWXXomprPnMZXmpfL4ZAq10VEyP158+W/ps1iKRfSNm0qBTdukAxvveXUyoXEyLObJ1L+7ey4tNkWBvAI5YOQPgj1UqRIEeWaglAvEIQmF/AiSKr3giGeWbK89GKwwIPB1iCMECzS8VKHQB4CYliub94ck3xRywXQsGFD2bRpk/J8gBIAlu5QFGhxjaF0gJLAFAgZYRiaIGvWrEpbDb799lvlSWFouQ+QE8IaUA4oKxAKyBicz9IkLLYmodBhtgBWs4ZommjD5doyW8ehxvE6duyoQmwZQysEQkhKB27dhsp4d+RBSLisPBTjop8p0EdavGL6+x0eFS6dN3aWbAHZZOirQ6Vs5rJWh5W01tIK3nVQAuG4mEd4Q+NvprOS1DBRhBBCCEk5IJzQG2+8oYwBNcPRLVu2uKx1NGQ3M2bMkCdPnqhQy+hHxxcWmiSNxfsuS1hkjCzo7ar5xNcr+YX4z44ckVufjpWwM2f0y3zy5pVsYz6RACPDVmcGEVssBZ5FWmSYlIbdFQyIQYyQKWvWrNEnckaoFbilQ5CdFGErwrsgFAEUCo60ELQ0RBEGs5c7d5HQBBQMPrlzS47585TbvqGA3VbAag+eH5qwFx8kKGZKliypfiPnAgTEmDSMkwED1DkUDZgQEgeDdIQzgoUgQJJiKB1MgXMbC5uhZUe+A5wLsf+NFQzWgpBF8MqAd4spcL5cuXKpRNCaRaMxCJFkKk+CMVDEIF+CIXv27BFbAgGIJWVJLLj/yE1hCNqCtg7KIih5cJ2GGlfj60S945nEc26P9ksIIc4KPLi0dyJi38KKzB25fD9EggJ85fqjUOlWJZ/4eZsesKw4s0KuP72upiWH50iRXP0k6tGjmOlhzP/np07F8l4wDCt54c3m4pUpSDx8fCWVn5+k8vURD19fSYXfvr7i4fdyXluXx9dPPmnQQLbv3i1hN2/Jqi+/lBZwu8b+Pr7i4evzYnvs6+M0CeRsFSaKEEIIIa4PrPxh8IlckFqUCuTHNIxU4Wqg7AgljZCWkCMilyaMT4l92PvfffU/tbendKqUJ1mrOSo4WO5MnCSPVqzQL0vl7S1BfftKUO9eqs/uKsCw2lB2mhAIpeuqSkCHKhggxEbIlVOnTinNI5LzAgiQ8dJAzgaEMkqMVTNuIoShCIEDQXdERISanDnOnLGLvzmwTejff0saO2nsoLiAcmb8+PHKih8JnCEEgdeAFnsfCaDbtm2rGj6SVSJhM8IWaSC3AZQK+JAh9A0SEyM5D7bHdojRj1wL+PAhpA4+EDgGEjOPHDnSbNkQ6x/74hhQQvn6+qrcDYgh+OOPP1p1nWhj0Ogj2TK8GCAgP3/+vGp3yDMABQNyMCChENoQcgPA+h4eGQhrgXwPBQsWlD///FOF9kGZsA/KZAw+hMhtgNiBULigzdvarQ9lQacBHQmUAc+NLQX4UPihHeBacO/gIYTYh6gLKAsAEjfDMwEKFdzXX3/9VZXJENxfhMfq1KmTOhaefYTXQp4VtDXk1SCEkJSIPbwX9GFxQp6K7q23xJlBWaOfPpWS8kQ2N8go+45dlBL3/5EHC/dK5MOHL5QHwRL1Yj6t710pVF7kYhadNBmzTS49iv09SYjwc+fUZC3tMeXKHfNj2XK5uGy52W31ygYoKDRlhZ/vy3lNqeEbV8ER89sv9nZKGQJFhqbEMFRq+MVWcBh8482FiQqoXNnq6yeEEEKI6wLZSpMmTVQuRICx+h9//KGiNLg6kB9AAAvvDHgzQP7gruFG7c3y3pXlz7N35PrDUEnv75NsY4XH69fL7a++lqgHD/TL/atUlmyffCK+VngCOAMwvoVcVIvGUqNGDRUy3lS0FMiq0ba1fKYpEbsqGJBAD8JhWLVDYAmLdAAr7NmzZyvhJZL6QklgLVqSvjx58qikuYgzh+NCeInzQoDubDyMZwBrTPDPP9tNwQAhcoMGDdSDcP/+fRVnH/dDs4KDgARJgRHLDwmOoY2DYNgwVjFeDBCeIIcBtkFeAdwD7Rg4HgTsyLUAzxUI92EFn1CySyR3RkgmaKvh+YI2A8G6OU+I+EAuju3bt6sQCLAkhfIA7QVKB01J0KtXL1V+nAvJpXFuJEXS2g/yS6ANwysDrnrz5883GXIJ61E/yF0B5YWWLDkx5TYH3ASRmBn1ERYWppI4GSbXTipIbg2FARJez5w5U90zKF0QHksDyhrkysCHHi9NhMbC84ZyaRQvXly9aKGIQDvDdvAUwf0wVFIRQkhKAqEZV7ywwoGbbFLyUjlDWBxdVJREPX6s9ySIevQw9vyjRwZKgxceB8HByHKtPwYCIwW/mEwBdfO4f0SuZBbJ+iiRBUXf0o7efbqwMDUB+53FDN7eMRZcPj4S/fSJzcJEEUIIIcQ1wdga0QS0yAOIAAGZh7XhpJ0VGKwiVBLkKjBkhVFsYuSFJGGQH61OMdsqpeIzjAq7cFFujR0bK4+aZ1CQZP3oI0nbtInL9Weh4IPxLxR+oGvXrkpeiOgwCxcuVAa2yJECw2XIBbE+pcvDUunsmCUOwlwIIJEN3hQIg4MY/gilYy0IaYMYurCOhlIBguvw8HAl1EbIn3nz5ilL8viAcPzatZikJhrHjx9XyhCEhoGg2RAIdNHozYXcSQg8SDeGf2DRtlm/Gi+BVaq43ENmC9AkoSyCcsEdr1/DnesBnia4figmYL2AF7GrxMi2B/DOYj24Xz242/W6el1AOQtlNYBiVktUlxTwHrzxdnd5/sL93feVVyTngvlWfxOQPA3C/2hNGfDokUTDk0CbD36pIIhWyoNgiX78GAUQu+DlJZ7p04tHunTimSGDeKZLJx7p06tlnulj5rHu4fQZEm4iRKMhfuXLS/Y5P6KRiC48XK8QUFN4uESreSx/HvM/POb3vZs3ZOL48eKl00nGwDTSt3t38YyOjln/PEy/ndo/3GB//e+X53Ak2X+crZQMycW+ffuUYQoMCapUqZJs57W2z55cuMK7yZ64+/VrsB7csx7c7XrN4e71kJzXD3kXokxAhgZg2Y9oAomVTzlrXSDHKiJlQDiLkNUnT55UihRnx92fBfBs33652aePms/y/feSplpViX7+XB7NnSsP581X/XVFqlSStm1byThooHiaydvqzCA0GYxpoUwA7du3V8oFzajeWdpDcvfb7erBcPv2bX1YJHOW9NDsJAZYkwOErEFIG7x4ADRDcBFDmBYkzogvhAxC/8C63RQI7YMQT4aggSQlDr5vhQqSf8d2iwXLmNxNsGx4/cAdr1/DnesB147nDc8gOhj47a4faYC6YD24Xz242/W6cl3ALVYL4wdPOFiWGfchEkPEoUN65QIIO3JEbm/aJF75C0h0cLDoHmN6/GL+seiCMcUoB2J+v1AUvLCssQsI5ZM2rVIIhPgGSERAoARlzyQe6dKq5amgPEibTlKl0+bTwkfY7Hct+sWEa09IuaCFCrr755/ireW78PKKmRLI8YXIp2FHj8qcxYtF7t8Xr+goFTLRWnTR0SIRkTGKBigewsNe/Nd+h4toiogXv/XzYeEJbgsFR/SF/0RCn5s8/91p0yWwUKFk6yegf+wIrO2zJxfO/m6yN+5+/RqsB/esB3e7XnO4ez0k1/XjPFCqa8oF5CtYvny5CpvsqG+gPesCBsQIeQ2lCqKeGEZVcFZc5Vk4dPWJvJIrUDxs3HfEdT+dNk3/+97MGRLy5LGEfjdFom/c0C/3LFRI/N8bKp4lSkgwPJ+dpP1aCgzaEelDUy40bdpU5QoJfvHbmdpDcvfb7apgQAw4LemMKbAusXHiENYGILGwplwA0A4hLMGiRYtUMmOEazFHz549ldbJlDUUwsMY54ZAg8EAzlArZQ80pxJ3tFwH7n79Gu5cD7hevITxDGLena0AtI8T68H96sHdrteV62LVqlXKQgXAezJv3ry28V5YsjTO8pAPPxJ7kSog4IUXgeZdkF4806UXj/TpxDN9Br13geE2Hi/6Y6Dj3ANy8PIjKZ4tjSzp8aqk8Yt7r648uSJfHhgl/cv0lzKZypgty63fYwbQlqDb+LtkrFfP6uvFgBVhrRB2EKEB4XUCwxVntQQzReQ//0jq8+eTzYsB/WNHYG2fPblw9neTvXH369dgPbhnPbjb9ZrD3eshOa4fRocI04yQ1ADfvM2bN0vp0qUlpdYFcjEg7PatW7eUIgUhk7S8kM6KKzwLx64Gy7urzkq+IH/5sEFhqVssi037rI+OH9f/jj7+r4R88KH+d6rUqSXjgHclXYcOkgrGQC4IlAvIUfroUUxsV8ieESrd1P2OcIL2kNz9drveVeRGQHgkeCogpr/mTYBY+HPmzFFhjDAwSAwInQKyZcsWZ52WBEYb7JsDblbmXK3QAAwVF0Arvy0T65oC9YOGiMne53JG3P36Ndy5HrTrxnOIpOSmnkd3g/XgnvXgbtfrinWBdzVyTQG8t5CfyBZlDPnf/2J5L1gFjCHSptUrAlQYIpPzMf+9XoQpSpWEch+58lApF0Cgn5cEpTXtQfD98e/lwO0D0n1rd5lRd4bUzFXT5HZBnTvL82NHYy/UxdS3+iamir1tYuocA1X0QxHbF274P/zwgxrAOgtQMj0yE2bUEGyTrnr1ZDFGcNQAydo+e3LirO+m5MLdr1+D9eCe9eBu12sOd68He14/+j3oq2h5viAw3LJli8oBmZLrAvsjKgmMPyIjI1WOToSgcXac/VlYsO+q+n/p/jPx9PSyWTkT6rOmqV9fso4cId4unLAbuVmRcwFjBoBE6ytXroy3Dr0c3B6Su99uVwUDXJq2bt2q3JvGjBmj4qgBeBYgUSxixZlzd06IihUrqoGgcTxWoC3LksV22jhCCCGEEGPQz0GH0zBMoy066XenzzC73jNTJknXonmMYsCUAgGhiezsbWnMnN0X9fO9a5iug+eRz+XWs1tqPk+aPFIlh/lYoAGVK0mR3btjLYObPMIAwHLPVh31ESNGqPBWSJoI9+Z3331XJRh0BpDgO/TQoQS3Cz14SOX5CnBQHgJCCCGE2B70BwcMGCALFixQvwMCApQXg7MqF2wNjJSR3wzyPUQoQZ+tSJEiji6Wy3L1wTP5/d+baj5/pgCpVzxrsvRZMw0eLJnf6SeuzLlz56ROnTpy584d9Rtetb/88ovTKpIchV3NohEX7uDBg/LRRx+p+QMHDqgJWbTxcsA8licGDOLhxr5kyRIV10rj5s2bKvkzXjzOkuyGEEIIISmTyZMn6+fhvZAcguWoe/cksHp1CerZU9K3bi1p6tQR//LlxbdAAaV0SG7lwpX7lg1Y/Lz8ZEmjJTK59mQZUWmEeHs43n0cnrADBw5U83B3njRpkjgLD5ctt3zbn5bZtSyEEEIISV7lwrBhw+T7779Xv/38/OS3336TqlWrus1twDV//PHHek8OhLYkiWfuXxclOiYKt/Ssnl88PGzj+aoMo6a+zL1gTMiev/Thv12R//77T15//XUlawZ169aVNWvWqPZJYmP3uCtw4Ro3bpyKVYUkiJj+/fdf+eKLL5IUDwpxrGBpdv36dalcubIaEH711VdqHhZu0wySixBCCCGE2JqTJ0+qGLgA4SBr1Khhd+8FjbvTpztNZ33uXxf0A5ZeNeIfsCCMT7289aR6zuriLHzwwQf63AtQGGmuz44mQ8eO4pk5U+wpUyZJlTGj+m+4HNsSQgghJGUAwbpmxAIr6XXr1knt2rXF3UBus/z586t55GKALJFYz6Nn4bLiYEx4pIwBPtK6fEzIeVvw9M+dEhpPWFfN09YVuXTpkvJcgNwZ1KpVS3799Vd9TmASG9fMrPGCPn36KG8IuE2NHj1axeStUqWKSrJRrVo1RxePEEIIISmYKVOmxPJesEUMfFcLi/MwBAOWmNCUQTYesCQX8KbF/fv888+VVyz6lZgcTXKFiSKEEEKI8wBj3C+//FIfwx2hWN544w1xR9DX+eSTT5SiAYY18GJAfRDrWLr/ijwLj1LzXSrnldQ+tvF2jnz0SG68/75FhlH+lSolS74wW3H16lWlXLhy5Yr6DRkzvIj8/f0dXTT3UDDs2rVL/a9Zs2as3wmhbZ8YWrVqpSZCCCGEkOTi/v37Kh6sFmanffv2DgmL42gFw9L9lyU0ImbA0rVKPvHzjjtg2Xt9r/h7+0u5LOXEWXnvvfeU9yvCJCFpN37jvhJCCCGEJBcTJ05UxrMABrQwnm3WrJlb34DOnTvL+PHj5ezZs7Jq1So5evSolCvnvH1KZyMsMkoW7L2k5n29PKRLlbw2OW7k3btyqUNHiQ4JcRnDKEuBxwKUCxcvxuSYq1SpkmzcuFECAwMdXTT3UTDAZQsaKSTKg6ZR+20OaCCxPioqZmBKCCGEEOIKzJo1S54/f67mkRjYVtbk6Tt2kCfbt4tERqrfHkjY7OOjYs9ioCkG3SpHh8V5HoEBy+V4ByzhUeEy9n9j5UbIDambp658W+tb8fJwPgdaJHYePny4jBo1SvVjMZA19FAhhBBCCLEnM2bMkPdfWINDTrZw4UJp27at21c6vDjGjBkjnTp1UnUBjwaEqSGW8evRG3L3SZiab/1qLskU6Jvkqgu/dl2u9OwhEddivJhdxTDKEm7duqXyLJw/f179rlChgmzatClJIf7dBZuO8ObNm6dehN7e3rF+E0IIIYSkFBCmBoNA4OvrK3379rXZsaMfP9YrF1KXLy95ly6RiIgIpwyLc/FeiGjdvLYVcqmYrsZsvrRZKReAr6evUyoXNAYNGqTPwfDDDz+oQX7u3LkdXSxCCCGEpHDmzp0rAwYM0P+ePXu2stwnMcBTGGGjkNt1/fr1sn//fmVVThLm939vqf/osyO5c1IJ++8/udKjp0Tevh2zwNNTPNOlE/F8keJXJ05pGGUJd+/eVcqFM2fOqN/wlEG+PRgikYSx6Sjv7bffjvc3SXkgaXfRokVl2bJlUr265Qkb69WrJ2+++aYazBNCCCGuBGK/3rgRIzTv0qWLZM6c2SbH1UVEyN1JMQn9QJb333dqQ43i2dPKXx++LuuO3pBK+TOa3KZpgaaS2iu1zDw2Uwa88nLg7IzA7fmjjz5SigUokcaNG6cUDYQQQggh9mLJkiXSu3dv/W+EbOzVqxcr3ABPT08ZO3astGnTRu/FAMEvSZjZXV6VzSduy4kbwVIwc9JC/IQe/1eu9u4tUY8eqd9+ZctInlmzxNNAAO+q+cIQ/hZyypMnT6rfpUqVkq1bt6rrIJbxQsVkHz777LN4s7xD+4htiGMenoCAAPWwaCEeNLTQVpjgjpYnTx6VVEcTphiCJIilS5eOpVzAgLxGjRrKhQjHQOZ1Y7ANEvQg1jEhhBDiKiC8I6zcNQYPHmyzYz9atUrCX3wz09SvJ/7lXxFnx9fLU9pVyC15gwJMrkc/oF7eerKq2SrJncb5vQHeeecdyZ49u96a8MKFC44uEiGEEEJSsNFKt27dVP9Sk68YejKQl7Rs2VKfe2HLli3y119/sXoswMvTQ5qUyS4fNCyWpPoK2f+3XHn7bb1ywb9KZck7b14s5YKr8vDhQ6lfv778888/6nfx4sXljz/+kEyZMjm6aC6FXRUMECBrN8gUUD5AC0mSn/nz5ytFQv78+WXFihVx1rdr105u3rwply9fVkks//77b7XMECgmECLCODREWFiY8k5AHGNzwJ0tV65csmDBAhteFSGEEGJf9u7dKwcPHlTz6IjCusUWIEHa3ekz9K7GmYe+JykJZ/bEMMTf319Gjhyp5iMjI2kIQwghhBC7gFA/HTp0UOFkAGRjyAdFTIOQO4YGyh9//LFeMUPsy5PtO5TngpbQGYZQuWfNEo8A0wZGrkRwcLA0aNBAjhw5on4XKVJEKReyZMni6KK5HHZVMCQEBNSwkCfJC17CiOmHEFbwTECiSmNSp04t2bJlk5w5cypFBJQIe/bskceIDf0CJDp58uSJNGrUKNa+eOnjw5hQTDxooOEOSAghhLgKht4LQ4YMsdlx7y9YIFH37qn59G3aiG+BpMdItRfn7zyVQ5cfxrvN9afXxVVBmAIt98LixYv1cVgJIYQQQmwBLPAR7gfGDAAhGkePHs3KTYCmTZtKxYoV1fzOnTtl+/btrDMznLn1xCYKmOD16+XawIGiCw9Xv9O1aCE5J08WDxcKf2QOyDMbNmwoBw4cUL8LFiyo2pTmzUwcrGCAAPrKlStq0kLxaL8Np6NHj8rSpUtTTPK8paeWSpPVTdR05kHsgehf1//Sr0OyQ+MBuLZu1rG4gv4Wa1uodSN3x1jTGfL3zb8TVVY8MLgv8DLo2LGjHDp0KN5QVteuXVOue4h7h0kDL3S4qCU2rhoUENASMkwSIYQQVwAh/9asWaPmkX8IHVJbEHn/vjyYO0/Np0qdWjK921+cme+2nZXW3+9V053HscMsgkvBl6Tp6qYyePtgufDI9UIMIXE3YvsCWBXCI5cQQgghxBZAjtKiRQsVq14Lt4kExq7i7elIUEeff/65/jeUMvRiiMuNR6HSZOpuaTRlt2w5EZPkOTE8+OknufHBhyJRUep3hq5dJPuX4ySVBYbid0PvyrUn1yQsKkyckZCQEGncuLHs27dP/c6XL5+SlcLImjiJggGWfQi7gwkPP6z7tN+G06uvvirbtm2Tfv36SUogOCxYrjy5oqaI6IhY60IjQ/XrQiJiXIo0IqMj9esehcXNR3D1yVW17s6zO3HWPY+KO6i3BHgsvPXWW2oAjRwMzZo1i5PEEMofJDuEJwOUQLt371b3EnkbNC5evJikhw8hkjBwRxgmQgghxNlB0j3NjR2DQbhq24J7M2ZK9LNnaj6oe3fxdmKX3KsPnsnG4zfV/P2nYRIU6Btnm6lHpkqkLlK2X90uB27FWAS5GoiHXKBAATW/fPlyOX78uKOLRAghhBAX53//+580adJEQkND1W9EioAMjcoFy0GIUi0HKOoTkTVIbBbsvSSR0To5feuJXH8U09asAUqbez/MktuffY4falmmgQMk64gRksrC8c/iU4ul0epGUmFJBTn/8HysdTDKhpE2DLDvhcZ4cCcnz549U94wWh4PyDyhXED+WZJ4bB6fCOF0tAaJUDkIg1OmTJlY2+DlCeF15cqVpWrVqpISSOebTvKkiWmM3h7esdal9kqtXxfgHTtGmZeHl35det+4yVGQEBEKiyz+cYUNfp5+Vpfz9u3bsnbtWhXuSANhkuDJgIRCiD0M4N3w9ddfqw/fwoUL1Yv7iy++iHUsrEtK0hM/v5jyax9XQgghxJldaOfMmaPmM2TIIF27drXJcZHU+eGLXEieQUGSsUcPcWbm/nVRol94W/esUUA8PeJa2zXJ30TOPTwn0bpoaVWklbgi3t7eynNBu89jxoyR1atXO7pYhBBCCHFREDkC3q+wnAYIWT1z5kwqFxLpxfD666/rvRhQr1TSxPD4eYT8tD8mokxaPy9pV8G6qDGQ5d755lt5MC/GuxpkHTlSMnbtYtVxDBUHmVLHlhvuv7lfvjn4jZqfWXem1MhVQ7/u9IPTMvHgRCUDbVqgqVTJUUW/DmOL8Khw8fOyXhZqGKq/efPm8ueff6rfOXLkUMoFGMITJ1Mw1KpVS00AlunwUEgoFn9KoFPxTmoyRfWc1WVDqw0m1+UMzGl2HVjbYq3ZdRWzx8Ses4a5c+dKRESEVKny8iEFUVFRykKvxwvBRpo0aaRQoUJq/ttvv1WKooEDB8qPP/6o3ydz5swq1FJiefDggf44hBBCiDOzYMECfR6iPn36xPLoSwp3Jn+HbMJqPlP/d8Qz0HmTpT16Fi4rDl5V8xn8vaVN+Vwmt6ubt67Uyl1LbobcjGN04UrA+AIhC06fPq1CY0EwAA9cQgghhBBr+Oeff+SNN97Q9yURUQKGK7byhnU3YNhct25dlYwX/bN169apsFNE5Oe/r8rTsJixRefKeSXA13Kxry4qSm59+qk8WvlLzAJPT8k+7gtJn0DdIqLL/ef3pUC6GO9fUCV7FUnjl0YehD5QBtnmlA/GxtRXHl+RfTdjwha9kuWVWOtuh9yWN1a9IWl80kiHYh1k4CsDY63fcWWHOleOwBySLSBbnHKGhYUp2Sai6QDknYVyQZN9kqRh17fZ/Pnz3UK54CogrAMUBB9++KHKgWE4QVhiKtmzBrwX5s2bJwcPHtQvK1++vJw4cSLR5UG4AYRo0kIQEEIIIc4IlPBTpkxR88hF9O6779rkuKHHjsmTzTG5mbzz5pEM7dqJM7N0/xV5Fh4Tg7VLlXyS2udlXiZj4KEJL0xXBvd67Nix+t9MvkgIIYQQa4GhQr169fQGlhBwLlq0KFZ+S2I9hrkYkDtLC2PqzkRERcu8PRfVvLdnKulWNZ/F+0aHh8v1Ye/rlQupvL0l15TvElQuwKtg1F+j5K3f3pLfLvymX96sQDMZU2WMTKkzJY53Sbui7WRG3Rlqfa40sQ2WnoQ/Ec9UMc9G5tSZ4+R10LZJJanihJ8f8ucQ6bapm4zZOyZOOacdmiZ1x9aV/aH7Y46dObNSUCGvHnFSDwZzA3O8VB8+fGjyoa9Zs2ZyFMPt2bx5s0pQiTh/xu4/vXv3ltdee00pG0xRsmRJlQBlxIgRsnXrVrWsUaNGMmzYMJWLwfB4SOKNj+f58zFx1k6ePKkSOUM7iEkDLkk4Bl3ZCCGEODMbNmyQ//77T823bdtWxelMKpr7sUaWoUNVR95ZCYuMUvFcga+Xh3StkjfO9aTE73mbNm1UqE9YHv7++++yd+/eFBPekxBCCCH2Bf1HWNrfvRsjGIX8Y9myZSoUI0kaiMqB+kT/DMarv/zyi7RzcmMde4M8aTeDY3K1Ni+XU7KmtSyUEHLBXRs4SEJehFJP5e8vuWdMlwCjyCem2HBhg+y8tlPNTzs8TWpkexnuyBxQKhgrFjRaF2ktLQq1kIdhD+OEmPf19JXauWvLvWf3JG/a2GORB88fKGWHqZBMiOIy78A8iSwaKUGBQeLxr4dSLpQoUUKt//ivj+X4veOS2T+zfF/3e/H29I7lNREeHa6UHUkJzeQO2F3BgDj+X331ld4VzJwCgtgfeChUqFDBZGwxLIdbkHGyZ0Pg+VCjRg31IOIjWbx4cRX3Dtp3xCY21B4jb4MGkhgBbIN4xlosa+SCgNKDEEIIcWaQfE9jyJAhNjnm0z//lGcvvAL9ypSRNA0aiDOz7ugNufskTM23fjWXZDJK7gyLpa2Xt8rg8oOlYPqCklJA6AJYyCFWq+bFgH4QIYQQQkh8IGR4nTp15MaNG+o35letWiW+vrH7UCTxIO8rFAyavKl169Zu6xkCY5/Zuy7of/euYVmkkKjHj+Vq334SeuSI+u2RLp3kmT1LUpcta9H+jfI3kvOPzsvik4tlYu2JKgdtqCQtz6qnh2ccJQEomrGoTKszzeQ+/l7+8mmVT+VO6B0pkqGIfnlkZKR06txJIhpExHg9hIgKkVS6dGn9NhcfX5QLwRfkVsitWMoFsODEAllyaomaX9diXawwUMgXceDWAaWYqJC1gskyuxN2VTAg3j8s3pGTAfHmRo0aJUOHDlXaWqxDaJz+/fvbswjEAAj04+PcuXPxrq9evbp6aRmCQXerVq2UJwMSd2txqjHFx4wZM5SyAsckhBBCnBV49mlJwCpXrmyT0I+Ib3p30iT97yzvD3Nq6//oaJ38+GLAgmL2qh7bUAHJ1qYfmS43Qm7I7mu7ZVPrTZI1IKukFJo1a6a8PA8cOKDitO7YsUOfWJAQQgghxJjr168ro0xEdwCQe/z666+SOnVqVpYNgaEsci9A1oWoKT/99JN06WJdMuKUwv/+uy8nbsQYdtcqklmKZkuT4D6R9+7JlV69Jez0afXbK3NmyT13jvgVeSmgTwiERR366lCVEwF5D8LDw8URBPoEKu8HY2N2JFNfuWKleG7ylAy5MsjsWbOlXLlysbYL8gtSuSDSeMetszvP7ujnjUM2IVn1twdjPNJ/qPeDZMr5UsFw6sEpCQ8JV2Hh3QW75mD4/vvv1WAcAzHE+Nes2eHRAFdzhOuh94JrU61aNZWf4cKFl5pSS8CHdfr06XYrFyGEEGILtNwLAEYStiB47VoJOxcTRjCwVi0JqFhRnJkrD57JnRfeC/WLZ5UCmWMMCjRg7ePrFWON1yB/gxSlXABQ/hjG+YUXg7HBBSGEEEIIuHPnjsq5oIXXrFixogq3GRAQO9wLsQ2G+bIwj3A47sjPB69a5b0Qcf26XO7UWa9c8M6VS/IuXWKVcsEQU0mVHQnC8/fq1UuWLl2qfvvr/OW3eb9Jy+ot42w7tc5U+aPtH7Km+Zo462rmqintirST+nnrS6B37DHQ3Wcxoc9AZv/YyoerT6+Kn6d7hVSyqwfDqVOnlPAZaJZ5mkIhe/bsSumAgXuPHj3sWQxiZ5C/wVoGDx5sl7IQQgghtuLWrVvKEgog7wI89pJKdGio3J36wrXXw0MyD3tPnJ18mQLkfyPqyMqD16Rc7vRx1udJm0dWv7la1p1fJ5WyJ93DwxmBJy6sD//66y/Zs2ePCvHYsGFDRxeLEEIIIU7E/fv3lXIB1vQAltKbNm2StGnTOrpoKRbkykLuhRUrViilDkJ49+zZU9yNCW3KSPVCmWTn2btSrVBQvNuGXbggV3r0lMhbt9Rvn0IFJc/ceeKdNYtF5/rl7C9SJnOZWKGInE25gNyzWmQVKPcQSishT3RTHuXNCzVXkyk6FO+gxj5IPp0rMHZOiZCIEMngn0HcCbt6MCD2maal1f7jhauRL1++BMPyEEIIIYQ4AuQl0tx8Bw4cKF5eSbfLeLB4iUTevq3m07VskWgroeTG38dLulXNJ2VNKBg092i4JZtL2Obq0IuBEEIIIfHx6NEjZZCAhMMACWS3bNkiGTK4l5DRESDXJ/JmaXkZwsJiPG/dCV8vT2lbIbdM71g+3tCroSdOKM8FTbmAXHB5Fy+2WLmAnAOf7/tcOm7oqIyLnA14GQ8YMEDmzJmjj54CDyJEX7E1OQNzSo1cNaRV4Vbi7+0fa13Lgi3V+MidsKuCIU+ePHLx4kU1j0Q2sP7bvXu3fj1i2bpaPCq6xBPC54wQkvJ5/vy5zJw5U837+/srF9ukEvnwodyfPVvNp/L1lcwDByb5mCT5qF27toqnDA4ePKhiKRNCCCGEPHnyRBo1aiSHDx9WlVG4cGH5448/JHPm2GFTiH0oXry4dOrUSc0j7wVyvpK4PDtwQK50e1uiHj5Uv/0rV5Y88+aJlxVKMHgvROuiJSwqTE3OJq9FSFuE6wd+fn6yfv16lReYuLiCoWbNmkpTpNG2bVuZNWuWComERBvQKDVu3FhcBWhE4WpDJQMh9gPPF54zzQKBEEIcwbJly+Tu3Zi4mt27d7eJ9dn9H36Q6KdP1XzGrl3FO5tzxSo15vbj53LiRrDZ9SvPrpT/HsXEF3YXjHMx4HtFCCGEEPfl2bNn0rJlS9m3b58+UgeUC9mcvJ+X0vjkk09UFBUwbtw4CQ0NFXfgVvBzi7Z7unOnSuisjUUC69aV3LN+EM9A63KDfFn9S+lXtp80KdBE2hZpK84kR/rggw/0+fN8fHxU8m/NOIjYH7tK8BBn/91339U/2Ei4AoXCwoULZfHixVK/fn2V8NlVgBcGGu2NGzeoZCDEDhg+X3jeCCHEEeAdNHnyZP3vQYMGJfmY4deuyYOflql5z3TpJKh30j0i7M3sXRekydS/pPOc/XLt4bNY6y4GX5Rx+8ZJq19byXeHvhN3oUqVKnrjGIRAWLlypaOLRAghhBAHerzCEEWL1JErVy7Zvn27it5BkpdChQopQ2YAmQKMm1M6z8IjpcF3u6TlzD2y7WRMCFZTBP+2Qa6+O0B0L0JHpWveXHJN+U48EiFz8fTwlHfLvSvjq4+PNxRTco/dPv74Y/n222/Vb29vb1m9erU0aNDA0UVzK+waEKpo0aJq0kAeBriTBwcHK81iYGDsDNzODjTQiMX8+PFj5QIHC2t7PFB4ODDh2M7ywCYn7n797loPmueCplzA80bLUEKII9ixY4c+fm6TJk2kiA3yJNz9bopIRISaD3qnn3g6ebK/4NAIWf73FTX/741gyRjgE2v9ijMrJEoXpeZzBOYQdwKxfTdu3Kjmx4wZI61bt7ZJfg5CCCGEuA6QDXXo0EF27dqlfmP8Cs+F/PnzO7pobgu8S5HkOSIiQsaPHy+9e/fW54NNiaw8eE312Y9ceST7LtyXeiWyxtnm4fLlcmvsZxC4qN8ZOneWrCNHSCorIkZocilDnElGhb75l19+qebRJ4cBEMZwJIV4MDx9+lSFQjJl2ZUuXTqXUy5oDRV5JdKkSaM0YvZ6oPDw4oXorqGY3P363bUe8DzhucLzheeMwhpCiKP47ruXFvmI45lUkEzt8W+/qXnvnDklQ8eO4uz8tP+KhITHKBC6Vs6rkjwbMqzCMBlbdaxUzFZRWhZuKe7Eq6++Kq1atVLzZ86ckZ9++snRRSKEEEJIMhIZGSkdO3bUGxxkypRJtm3bZhOjFJJ48ubNq5QK4M6dOzJ9+vQUW51R0TqZ89cFNe/pkUq6V4+r2Lo3+0e59elYvXIhU//+knXUSKuUC3ee3ZEuv3eRk/dPijMCxQKSfAMYsiPMbfPmzR1dLLfEbuZWUCAsX77cLpm6HQmEnnB7s7cm/MGDByoBNuKGuRvufv0arAdCCEl+zp07J7+9UAaULl1a6tSpk+Rj3p04UT+fechg8XDyb1t4ZLTM33NRzft4eUiXKvnibOPl4SWtCrdSkzuCsJ9r1qxRRgCYhwUjlOSEEEIISdlERUWpUDyrVq3SG9BC0VCyZElHF42IyMiRI1WS57CwMJkwYYK88847ktbJPYcTw+YTt+Tqg5hw9E3LZJec6VPr16F/ivHH/Tkvk11nHfGRZOzWzapzREZHyge7PpBjd49J542dZWa9mVI5e2VxFr755hsZNWqUmkeEGYTib9OmjaOL5bbYNQdDiRIl5NKlS/Y8BSGEEEKIzZg6darec2zIkCFJ9lZ8+tceCdn7PzXvW6K4pHUBd91fj92QO09iYrS2Lp9TMqdhThxjSpUqJW+99Zaav3DhgixYsCDZ7xMhhBBCkheE8O3bt68sXbpU/Yb3PSymy5Yty1vhJOTMmVMpFQAMV7WkvykJjFVm7YrxXgC9axR4uS4qSm6N+fSlcsHDQ7KPG2e1cgE8j3wufp5+aj5PmjxSJlMZcSaPcyR1BhivzZ8/Xxn8kBSqYMDN/v777+Xs2bP2PA0hhBBCSJJ59OiR6pyCzJkzK9f3pKCLjpY7Bt4LWYYNs8ol2VEDlh8NBiw9q78csERFR6nkziQGuGPDWkqL/YpEj4QQQghJmaCPNGjQIGUdD/z9/WXdunXyyiuvOLpoxIiPPvpI3R8wceJEefjwYYqqo4OXH8qxq4/UfJUCQVIqZzo1rwsPlxvDh8ujFSvU71Te3pLzu8mSvnXiPI4DfQKV18Lg8oNlYu2J4u8dU6eOZsaMGbHC2M6ZM0e6du3q0DIROyd5Pn36tOTOnVuFGGjatKkULlxY/5BrQNOERCyEEEIIIY4EndOQkBA1D8snP78Yi53EgrwLYadOqfmAatUk0AXCRu46d0/O3H6i5usVzyKFsrzMmbXx4kb5eM/H8mbBN2VAuQGSNSBuIjl3AnGWMZiB98K1a9fkxx9/lIEDBzq6WIQQQgixg3IBBrQQbAL0EdevX69CgsNKnjgXWbNmVX2yr7/+WoKDg2XSpEny+eefS0rB0BioT80YY6Do0FC5NniwhOzarX6n8veXXNOmJnn84ZHKQ3qV7iXOAvrbAwYM0P/+4YcfVP5fksIVDFqiDYA4taaggoEQQgghzpCsb9q0aWoesfQ11+rEEh0WJne0ZNGpUkmW94eJqw1YDN2tw6LCZNqRaRKti5Z159dJ5+Kd3V7BAD755BNZsmSJaj9IMtezZ884xjSEEEIIcW3GjBkj3377rb6fCPkW8nQhbyJxToYPHy4zZ86UJ0+eqHA6gwcPVsm4XZ0Ld5/K1lO31XzhLIFSq0hmiXryRK72e0dCDx1Syz3SppU8s2dJ6nLlrD5+RHSEPIt4Jul8Y7winAkY9SBEmWFoW8PfxLHY1U//4sWLCU6IW0sIIYQQ4kgwULxy5YqaR/zObNmyJel4D5f+JJE3bqr5tM2ail/x4uLs3H0SJkeuxLiQl82dXirmz6hf55nKU/qV7SdZ/LNIkwJNpGjGog4sqfOQP39+6dUrxqrr1q1baiBLCCGEkJTD+PHj9dbvnp6esmLFCmnYsKGji0USICgoSOVTA0+fPlUJn1MCi/ddlhfp4qRXjfwS/fCBXO7aTa9c8MycSfIuXpwo5QKYcmiKtF3fVv65+484EzDogaeClisPoa/oOexGHgx58+a15+EJIYQQQmwCLJs0tMFIYokKDpZ7s2bpY59mHjRYXAEkc947oq4s+/uKFMkaGCvBtZeHl7Qq3Eoa5W+kEr6Rl4waNUrl7ggLC5OvvvpKWVIh6SMhhBBCXL9/OHLkSDWPvEtI7tyiRQtHF4tYyHvvvac8lJFnbfr06ep3Uo2IHM3wBkWlQKYAWXf0hjTJ6iGXO3WW8EuX1DrvnDklz7y54pNIWeyua7tk4cmFar7/H/1lS+stTpF34eeff5Zu3brplQvob+NeEufCuTMNEkIIIYTYmb///lv27t2r5mvVqpXkZH33f/xRooOD1XyGTp3EJ1dOcRXSpfaWfrUKSp1ipvMrpPZKLRn8MiR7uZyZXLlySb9+/dT8/fv3lbs2IYQQQlyb77//PlYi2Xnz5kn79u0dWiZiHenTp5f3339fzYeGhirBtKvj7+MlXarkk6UNssvNbl31ygWfggUl709LE61cAGUzl5XauWqr+Y8rfewUyoXVq1dLp06dJDo6Wv3+7LPP5MMPP3R0sYgJqGAghBBCiFtj6L1gOJBMDBE3b8qDRYvVvEeaNBLUt4+4MpqlEImfjz76SJ974ZtvvpGHD2NCTRFCCCHE9YBnYv/+/WMlkoUFNXE9Bg0apMIlaUqja9euiavz/ORJudy5s0TejAnH6leqlORdsli8s5o2ELIU5F2YWmeqzKo/Sxrmd3wYMCRSh1IvKipK/R49erSaiHNCBQMhhBBC3BYMMlauXKnmCxQoIE2bNk3S8e5OnSa6Fwn/gvr0Fq8Mzm/t/+R5hPx396nJdeP2j5PRe0bLrZBbyV4uVwLu9gMGDFDzwcHBMmnSJEcXiRBCCCGJYNmyZdKzZ89YhihMJOu6IGylZvGOpNzjxo0TVwT9dfDs4EGVcyHqwQP1279iRcmzYL7NxhwIkVo1R1VxNL///ru0adNGIiMj1W/cw7Fjxzq6WCQeqGAghBBCiNsyY8YMfccVFk5I3pdYnp85K8Fr16p5r2zZJGOXLuIK/LT/itSbtFN6Lzool++H6JdfCL4gv5z9RdaeXytvb3pboqJjrIeIaT744AN97gUII+7du8eqIoQQQlwIhGPp0qWL3oMTCZ4HD3aNXFrEPO+++65kfWHdP3fuXLn0IqyQqxAdrZPmM/bI6JGz5VKPXhL9NMYwKPD11yX37FniGRiY6GMfuHVAHjyPUVY4C1u3bpWWLVsqhRBAvgU8i4b54YjzQQUDIYQQQtySZ8+eyawXyZjTpk0rPXr0SNLx7kyaiJhCaj7zoEHi4ecnzk54ZLTM33NJFXvnmbuS2vulguXOszuSKXUmNd+jVA/x9Ei88sUdgPu9FmLr6dOnMmHCBEcXiRBCCCEWsnHjRnnrrbf04Vg++eQTFQKRuD4IYzlixAg1HxERIZ9//rm4EttP35FcR/ZIuzVTJFV4mFqWtlkzyTV1SpLGG1cfX5VB2wdJ2/Vt5fDtw+IM7NixQ958800JC4u5TngIf/vtt1QuuABUMBBCCCHELVm0aJE+Vj5c4TXr88QQsv9vCdm5S837Fiki6Zq/Ka7Ab//ckFuPn6v5Fq/kkCxpXw5SKmevLL+1/E0leWtZuKUDS+k6QMGAhIJg+vTpcusWQ0sRQgghzs62bdukVatWSvgMhg8fLp9++qmji0VsCMJc5cyZU80vXLhQzp075zL1e2jmfPnw4FLx0sUkOs7QsaPk+PorSeXtnaTjTj48WZ5GPFVGRVsvbxVHs3v3bhWu9vnz5/p7NnXqVCoXXAQqGAghhBDidkRHR8uUKVPUvIeHhwwcODDRx9JFR8udb77R/84y7D1JlYRQS8kF3P9n77qg/92rRoE42/h5+Un7Yu3F2yNpAxh3AcoFCCVAaGiocucmhBBCiPMCoaahxTT6hF9//TWFmikMPz8/+fjjj9U8vFRcJZ7/8W+ny5vbFoqHxHhJB73TT7KO/lhSeSRdnDu26lipn7e+lAoqJe+9+p44kr1790rjxo2VhzmAZ/nMmTP5HLoQdlUwIFlifFPBggWlVKlSqhEhVm1IyMu4v4QQQggh9mLz5s1y+vRpNd+iRQvJnz9/oo/1ZNMmef7vv/pEawE1a4orsPvcPTl964maf71oZimSNfEeHOQlyOWRKVNMaKkffvhBrl69yuohhBBCnJD9+/creRSMAkCvXr2UbIqx3lMmEFrny5dPzf/0009y8uRJcWZDoDsTJ4nXnBn6ZQ+6vSNZBg+2WftM45NGJtaaKLPfmC3eno4zJvr777+lUaNGKsQoQB6U2bNnKyMw4jrY9W7lyZNHvLy8VAIVhCCAVRcmzGMZ1qVOnVr27dunkna8+uqrcvfuXXsWiRBCCCFEDR41tLj5iUEXHi53Jr88Vpbh77vMoPTH3S+9F3rXjPFeQCLnqYenyq0QhvZJLIGBgfqYzUhO98UXX9jgbhFCCCHElhw5ckQaNmyoF2p27txZGQZQqJly8fHxkdGjR+sF+M4aBksXFSW3xo6V+z/+qH5HSSpZVKOzVP4w8R7X5sC4BYoGR3H48GFp0KCBPH78WP3u0KGDzJ8/XzxdwBucJKOCAYP3Bw8eKLeWO3fuqIaDCUoExKXFOmRwv3fvnkybNk3FQEMiHUIIIYQQe3HixAnZsmWLmodxQ7Vq1RJ9rIc/r5CIFxbqaRo1lNSlS4srcPLGY+XBAErnTCdVCgSp+Q0XN8iPx3+UJqubyNrzax1cStflnXfekezZs6v5efPmyYULL5U5hBBCCHEs//77r9SvX18ePXqkfrdt25ZCTTeha9euUqhQITW/cuVKOXr0qDgTuogIuTH8A3m0/Gf1OyKVp3z1Wmcp0bOzeHokzYgpNDJUPvvfZ3L3mXMYdh87dizWc9imTRuVI4/KBdfErgqG999/X9q3by/9+vUTb4PkI/Bc6N+/v3qJDxs2TGmI3333XaWp2rBhgz2LRAghhBA3R8u9AIYMGZJoj4Oop0/l3syZMT+8vCTLkCHiKswx8l7Q6uCXs7+o/xHREVI8Y3GHlc/V8ff3l1GjRqn5yMhI+eyzzxxdJEIIIYSIyNmzZ6VevXpy//59VR/Iv7B06VIlpyIpH9xnQ8+FMWPGiLMQHRoqVwcMkMcbN6rfzz195NPKPeRE4QrSpnyuJB//q7+/kpVnV0rb9W3ln7v/iKMNvvAcwvAcNG/eXIWt4nPounjYO55dmTJlzK7HOoRH0qhatarcvn3bnkUihBBCiBsDr8nFixereViYt2vXLtHHuj93rkQ9fKjmM7RvLz5584or8DQsUracjOlv5UyfWhqXyqZfN7v+bJXkrWPxjlI0Y1EHltL1QRzn3Llzq3m0OS3nByGEEEIcAzwK69Spo5c7ITTLihUrYhnEkpTPW2+9JSVKlFDzv/76qxw4cMDRRZKoJ0/kSu/eErJzl/odmTpARlbtI4ezFpUulfNKap+khQx6Ev5EDt8+HHMuXZRk8c8ijgJ94rp166pxGWjSpIn8/PPPfA5dHLsqGHx9feN9UJHIA9tohIWFqbi1hBBCCCH2YNasWfL8+XM1D+9JxGJNDBF37siDBQvVvIe/v2Tq/464CoG+XvLn8NoyuG5hGVS3kHh5vuwO+nn5SfdS3eWjijE5BEjiQR9XC/0ZHR0tY8eOZXUSQgghDuLq1atKqHn9+nX1u3bt2rJ69epYMiniHiAEj6EXg6NDtUc+eCBXur0toQcPqd+eQUGSY8ECadmloeQL8pcuVWISUycF5Fn4uenP0rRAU/my+peSLeClgVFygtD4hkq+N954Q3755Rc+hykAuyoY4GqG5BxfffWVPHv2TL8c8+PHj5eFCxeqbTT27t0rRYoUsWeRCCGEEOKmIOHujBkz1Lyfn5/07ds30ce6N32G6EJD1XxQ717iFRSTw8BVyBToK0PrF5H2r+VxdFFSNN26dZOCBQuq+eXLl8s//zjWHZ0QQghxR27evKmEmpcuXdJHz1i/fr0KaUjck9atW0vZsmXV/KZNm2TPnj0OKUfEzZtyuXMXeX7ypPrtlSO75Fu6RILKlpI+NQvKjvdrS+Y0tlGC+Xv7y/ga46VGrhriSA8iPI8A82vXrlXjMuL62FXB8O2336owSCNHjpT06dNLvnz51IR5xKUtVaqUfPPNN2pbWBOiUcGakBBCCCHE1sAFXuvQdunSRTJlypSo44RduCCPVq1S816ZM0vGbt3ElbkXek9uPo2pF2JbEHLBMLavM8X5JYQQQtyBO3fuKM+F8+fPq98VKlSQjRs3MnqGm4NcsIY5skaPHp3sZQi/dEkudeok4RdicqP5FCgg+X76SXzyvfRYSGyuOKDT6SQqOkqcgcuXL8vrr78u165dU79r1qypwlOlTp3a0UUjrqBgyJgxo8rDMH36dJW8Aw0HE17uWIbwSUEvLP6gXEB82s6dO9uzSIQQQghxQ9DBnjx5cqzkzonlzqRJIlExnfVMAwaoEEmuQERUtFx7+NKjVGP6kenSdE1T+fbAt/I0/KlDypaS6dixoxQrVkzNw0rr0KEY93dCCCGE2BckkK1fv76cOnVK/YYB7ObNmyVdunSseiLNmjWT1157TdXEjh071JRcPD91Si516iyRN2KMfPxKlpS8SxaLLpPtciOsPrdaum/uLrdCbokjgVIByoUrV66o39WqVZMNGzZIQECAQ8tFXEjBABDbuH///7N3F1BRbV0cwP/M0N0CIgJ2d/fTZ3d3dz/1szue3d3d3a3P7u4CFOnuIWb41jkjIyMG6AxT++diee+dAS536ty7z957II8Qszd19nX69Gm+7XfrHhNCCCGEZAVLe3748KGs1mdaY7esin/4ELEXLspmGVm3aqkxD8TJpwGoMf8/DN39CN6hcXybd5Q3jrw/giRJEk55n4JAT+lDQ52s86vqGXKEEEKIromKiuJNnNPKExYqVAjnz5/nE2EJScsO+HaMxiYlKRs7n/jYtRvEYWF83bRsWbht3QJ9W1v02noPvbfewx2vsD/alzfhbzD77mw8Cn6Edifa8SbPquDv78+DC97e3ny9QoUKlEGkpbL1LJJ1CE/rEk4IIYQQkl0Ukb3ABvnB86SlHRnHEf9AT18fmoDt+7qrXhBLUnHsiT/PZmCczZwxvPRwWBpaYkDJAbw2K1FOnV82a5JhE21UVeeXEEII0QWxsbFo2LAh7t+/z9dZP6QLFy7A0VFxs8OJdmBBKDajnmHjM5bhokyx167hU89ekMRIL/ib16iBXBvWQ2hujpf+0bj2LhQXXgXj31PSrJvfZSg0RC6LXHy5XYF2vMmzMkVERPDzLTaRi2UNsf9nzJiBGjVqyMqTlSlThve7sLS0VOq+EC0NMLBoFWtwx/ou5MiRg3/Z2Nige/fu8PPzU/avJ4QQQoiOYzNmWGkahpWqYScSvyPmwgUkPH7Ml01KlYJ57drQFDc/hOFlQDRfrlnAAflzSE8yjPWN0b1od5xqeQot8rZQ8V5qd51fdpKVhrIYCCGEEOVISEhA06ZNcfPmTb6eO3duXLp0CS4uLnTIyXezGL4doykriyH6zBn4DhyEVJGIr1s2bgzXFcsh+NLkeMM1aS8Gpk91zz/qv+Bh5YFdjXZhZJmR6Fe8H5Rp06ZNyJkzJ0aMGIErV67g+fPn/P/JkyfLggusofa5c+f4tWGinZQaYGD1tVgDHdZbwdPTk9egZV9sedu2bShfvjx8fX2VuQuEEEII0XHLly+HRCKdsT9s2DB+sTerUlNSELLoaxaE4//+90eD/uzGshfS9K3mmeF2KyMr6As0IxtDW+r8sosdhBBCCFGcxMREtGjRQlZLnwUVLl68CDc3NzrM5IdYCR/2xbCsl+PHjyv8aEXs3w+/ESOB5GS+bt2hPVzmzYWegQFfD4hK4FnGTE5rE9Qv4vTHv9NE34RPJBIKhFBmcKFXr148sPczPXr0oPJkWk6pAQYW+WNpMidOnOB1j1mggX2x5nasoQdruEMzuAghhBCiLNHR0diwYQNfZhmUXbt2/a2fE3ngIJK+1A41r1MbpqVLQVO8DozGlbchfLmIiyUq5bGDWCJtUk20c4YcIYQQomuSk5PRrl07WYkbVg6JBRdYeSRCfiX9GI3NvE+bnKQIYRs3IXDSZODLz7Tr2xdOkydDL92kpy03fJAikY4Le1X1gL4w65dr/WL9kCyWBjCyA7veO3jw4Ezdd/z48fz+RHspNcDA0l9YM2dW++5bDRo0wIABA3j9LUIIIYQQZdiyZQtivtQ47devH0xNs95jQBIfj5CVK6QrQiEcR4yAJll/VRoYYfpW94QkVYJOpzphwb0FiBRFqnTfdA2rR1u1alW+zEo30DiYEEII+XMpKSno3Lkzjh49ytdZI2fWc4GVxiQkM1gfhvr16/PlJ0+e4ODBg3984Hj/tsVLEDw/XQ+3/42S9nFLlwkdI0rGrjuf+LKlsT7alpP2TsgK1sS599ne6HamGw80ZIetW7f+MnMhTXx8PK9kQ7SXUgMMLDqVL1++H97ObouMpBNbQgghhCieWCzG0qVL+bK+vj4GDRr0Wz8nbMsWiENC+bJ169Yw8sxYYkhdBUaJcOyJ9CTDxcoYDYs544TXCbwIe4GtL7dixu2vs7WI8rGTyZkzZ8rWKYuBEEII+TNspnnPnj2xb98+vm5lZYXz58+jWLFidGhJlkyfPl22PGXKFH4u8btSJRIEzZiBsLVrpRv09OA0fRrsevXKcN+993wRk5jClztVzA1zo6yXLZ1zdw4+x37Gs9BnWPpAev6jbGkBPWXdn2gWpQYYXF1d8d9///3w9qtXr/L7EEIIIYQoGivR6OUl7T3Qpk2b3xpzpISFIXzDRr6sZ2IC+0EDoUm23PRBsliabt2zqgcMhAKewWBpaAk96KFv8b6q3kWdU6NGDdT+0iCclQ2lky1CCCHk92eIs8oYrBQ3Y25uzrMDS5cuTYeUZBnrlcUahDOvXr3Cnj17Mv08jDl2HIlnz/Ll1ORk+I8Zi4hdu6V3MDBAzkULYdO2bYbvTRZLsOm6NNvYQKiH7pXdf+uRY42cC9oWRA7THBhXYRyUHdRjFWseP36cpe+jCebaTakBBnYyv3//fowbNw5RUVFy9ZBZ/S0WYWY18gghhBBCFG3x4q9NmYcPH/5bPyN01WpeIomx69EdBo6O0BRJKRLsv+/Lly2M9dG+vLTBYYt8LXC61WnMqzEPBWwLqHgvddO3vRgUWeeXEEII0QXsQi4b361bt46vm5iY8F6fFStWVPWuES3JYpg2bRovv/Ur8bdvI3jiRMTPnoP46zfwechQRH9pFK1nbIxcq1bCskGD737vqWcB8I8S8eWmJXIih6Xxb+23m6UbdjTcgfV118PG2AbK8PnzZz6G9fT0RL169bIcMLC2tlbKfhEdafJcqVIlzJ07F/b29sidOzf/srOzw5w5c1C5cmVMnDhRmbtACCGEEB306NEjXLlyhS+z8Ub58uWz/DOSfHwQsXcvXxba2sK2Z8aUZnVmqC/AiaFVed+FPtU85dKtWQZDfXdpnVmS/dj4uFGjRnz5+fPnfEIOIYQQQjIfXGATWZctW8bXjYyMeEZg9erV6RCSP1KiRAk+WZp59+6dLDvmZ8/FkBUrZetBY8Yg9kslF4GFBdw2boB5tWo//P6qee0xvE4+2JkZok91jz/adyOhETys/uxnfK95+pEjR/i4lV3PZQ2wP378+Fs/q1mzZgrdN6JDAQbWSJGVSFq7di1vamdmZsa/WKSLRZkvX77Mo8yEEEIIIYq0ZMmSP85eCF6ylHUN5Mv2AwdCaG4GTeNsZYLxDQthaO0f98Qi6lHnNzMz5AghhBAi/QxlE1kZAwMDHDhwAH///TcdGqIQU6dOlTVhZlkMSUlJP81eSHjwQLaeGhsrm5yUe9tWmJYp89PfZWduhOF18uPWuNoo6GSZ6X1kgY29r/ciUZwIZWDBlbFjxyJXrlxo0aIFTp06Jcu4ZQG9Tp064fjx45m+psuuD3fr1k0p+0p0IMCQ1lSxT58+PFXt5cuX/IvVRO7duze/jRBCCCFEkQIDA7F7t7TmqZubGx8UZ1XC06eIOXOGLxu4ucGmrXQmk6YKigvCwvsLESnKWiozUR5WH7ply5Z8+c2bN9i5cycdbkIIIeQX5s2bxy8AM0KhkNfJb9y4MR03ojCFCxdGx44d+TKbrb9p06YfZy8slWbRyDE0hNuO7TAuVChLmcdZsfXFVsy8MxNdTnXBp+hPUASRSMTHo7Vq1UL+/Pl5EC8oKEh2e/HixbF8+XIEBARgx44d/HW3YsWKTP1s9n1UIkm7KT3AQAghhBCSnVavXs3TeZkhQ4ZkeUIDO1kInr9Atu74z3DoGRpCU7D9D4uVn820+slqbHmxBQ0ONcDj4Kw1ZCPKw2bFpZ8hl/a8JYQQQkhGrCTSmDFj+DL7/Ny2bZssWE+IIrHsUhbAYmbOnMkvvqeNs0WvXiF03Xp4N2uOhO81Ok5Kgjg4+Kc/n/2c3xWfHI/NLzbz5XeR7xCZ+GcTiJ4+fYqhQ4fCxcUFnTt35pVo0rDG6X379sXdu3d5U+fBgwfDxuZrj4eePXti48aNP8xkYJkL7HZ2P6LdFJpCwN7cf0fXrl0VuRuEEEII0VFs8M8CDAwry8gyJrMq9soVxN+7x5eNixWDRX3N6lVwyysM3TfdQ4tSOTGgZh44WAGXfS/z20z0TaixsxopWrQo2rdvzzNuvL29sXnzZn4SRwghhBB5rMz2sGHDZOvsomXaLHNCFC1fvny8pA/LXogJCMDR0aNRzdwCcdeuISUk5JffH7JiBUwrVJBNJPnWhCPPEZ2QzHulFXfNWvNjUwNT7G60G6OujEJDj4Yo7lAcWRUTE8OzfzZs2MCDB9/rF8bOo9q2bcuDDD/DggcsY3zr1q28F0poaCjvw9u8eXN+vTd9QIJoL4UGGLp3785fPFmJxLH7U4CBEEIIIYqwa9cuhHwZ9Pfo0SPLqbipYjFCFi6SrTuOGvXDEwN1tf6qF5LEEuy974vGJZzhbu+A4y2OY9OzTbzxGwsyEPXByjzs3buX17WdMWMGHxcbGxurercIIYQQtcEms/bv31+2vnLlSj7OI0QZUiUSiF6+wtg8eVE7d24UNzKG8Nx5RGXhZyTcf4D4O3dgVrFihtuCY0Q4cP8zH6/f94nA9TG1oC/MWoEZF3MXbG2wFfp6mb+sy67V3rlzB+vXr+djz7i4OLnb7ezs+Di0V69eKFKkSJb2hwURWN+7gQMHIjw8HLa2tjDUoAxwomYBBta0mRBCCCFEFdigOa25MwsKsFTfrIo6chSJ797xZfMaNWBWoTw0ydugGFx+Iw2wFHK2RNW89nzZ0tASw8v8XrNrolysxi2bIceyFz5//sxP+lhpL0IIIYSAXwhlwYS0iawLFy7kFzEJUaSUiAjE3biJuGtXEXv9BsRhYXx7KWP5iTlCOzuYVakM0bPnSPL2/q0shm03P/LgAtO9inuWgwtpDAQGmbpfWFgYtm/fzrMVXrx4keH2OnXq8GwFlnHAGjgTovIAQ40aNRT54wghhBBCMu3SpUt49uwZX2ZNx1hqc1ZIRCKELF8uXREI4DByhMYdfZa9kKZvdQ+Ny77QVZMmTeInfikpKZg1axafOcZq1hJCCCG6jJVb6dSpE8/yS6uFP2KE5o3PiPphWcui588Re/UaYq9fg+jpMzZbKeMdBQI8io/H1ZgYPNXXx5k7tyF8+RKfjh3/rSyG+KQUbL/9kS+bGQrRobxbpvb3XuA9nPA6gbHlx2YqG5m9ZtgkcBZUOHToEJKSkuRuZ/0WWOCOlTfy9PTM1D4Qkm0BBkIIIYQQVUnLXmBYim5WhbMLvIGBfNmqeXMY588PTRIcLcKRx3582cnSGAVyxSFSFAlr46yViSLZz8PDg88cW7NmDYKCgnjph//973/0UBBCCNFZZ86c4fXfxWIxX58wYQL/IuR3pYSFIe76dR5UiLtxA+LI7zdH1ndwgFm1ajCvXg1mlSph7ZQpWLt0Kb9t+YoV6Bb08wbO6UXs2i0XYNh//zOiEpL5cvvybrAy+XUWQmhCKMZcHYOQhBA8DXmKLfW3wMrI6rv39ff3x5YtW3iPEi+vrxOPGNa0ulGjRnzM2aBBA+jr0yVhojga/Wz60aw81tQxNjY22/eHEEIIIarx9u1bnDhxgi8XL14ctWrVynJadNi69XxZz8gIDkM1r0TNlps+SBZLZ151r5ILE26MQWBcIHoW7YlexXpBoPd76dcke7CLJqxMUmJiIubOnctrTVtYWNDhJ4QQopNZqaxpbNqsa5a1wPoUEZIVqSkpSHj6FLHXriHu6jWIvlMeiNPXh2nJkjCrXp0HFYwKFJC73jh27FjeZDwhIQELFixA7wMHIHz08JtfJs0aEAgEQLpLlTbpGpGLJanYeF1aVkko0EOPKu6Z+jv8Yv2QIknhy3mt8/LSp+mxDNjTp0/zbIWTJ0/KgnJpWIYCy45lfXNZ5gIhGhtgePPmDQoXLsxfoOyJr0jVqlVD37595bYZGGSuDhkhhBBCtMOyZcvksheyWhoobM1aSGJi+LJt1y4wcHKCJolLTMGOL+nW5kb6sHZ8jvc+7/n645DHFFzQAK6urjyosHTpUl4rl/0/ceJEVe8WIYQQkq1u3LiBJk2aQCQS8XXWb4Fd1KWyjyQzkoODEXftOi97xHoqSKKjv3s/fScnmFerBrNqVXmWgvAnkzqcnJwwePBgzJ8/H5GRkVh55QqmX7smdx8WDPtVc+NzLwLxKTyeLzcq5gxXm8yVwyzhUAL7muzDsofLML7CeNlrgWUosEwFNkElICBA7nvYPrRs2RJ9+vRBzZo1pYEPQjQ9wMAu+OfKlUspHwgsEte5c2eF/1xCCCGEaIaIiAg+sGYcHR3RoUOHLH1/0mc/ROzaxZeFVlaw69MHmmbffV9Ei6STODqUz4WGeVwRlOCLna92YljpYarePZJJbIYca/IcHx/PL6YMGjQINjY2dPwIIYTohHv37vHSLexzkGH14ZcvX07BBfJDqcnJSHj8+EsvhetIfPXq+3c0MIBpmTKyoIJRvnxZel6NHj0aq1ev5tVSWFnWYcOGwc7OLtPfz5qUr03XK61Ptaz1PXAyc8K/1f7lma579uzh2QoXL17McL8iRYrwoAK7TpqV/SNEIwIMLAjg4+OjtJ/PIoXsy9zcXGm/gxBCCCHqiQ2w005EBwwYAGNj4yx9f8jSpfzkhLHr3x9CS/m0Y3UnkaRi8w3pOEufp1t7wNLQhAcWWHkkC0Mqs6Mp2Ay5IUOG8BJJUVFRWLRoEZWEIIQQohOePHmCevXqIeZLRmnHjh15WRqaeU2+lRwYKCt7FHfrFiQ/KJFu4OICs+qsl0J1mFWoAIGZ2W8fTHt7e54lzRqNs+coy2aYM2dOpr//wccIPPaV9nyo6GmLYq7f76GQJj45njdzTguCvHjxgp/zbNu2jWdKfFsmvn379ry3QoUKFSggR1RCo3swMAcOHMCOHTt4jTEHBwe0a9eOv+CtrH7+YiWEEEKI5mOlF9nMtrRUYBZgyArRy5eIPn5cdhJi0+lrnVRNIRDoYVvP8ryma4okFS7WJrLbKLigeVhz51WrVvGTVzZDbujQoXyMSwghhGirly9fok6dOjwrlWGlXbZu3cqb0hKSmpSE+IcPpc2Zr11D4rt33z0oeoaGMC1XjmcosKCCoYeHQi+2s14g7LyDTQJh///zzz/IkSNHpr7XzdYU/Wp4YtedT+hb/efZC6zfwqCLg2BraIt8PvmwbcM23Lp1K8P9ypcvz4MKLLhAfbuITgQY2Mk/m1loamqq0C7l7MXUpk0b5M2bF9HR0Th16hRWrFiBK1eu4ObNm7/MaPD19cXnz5/ltj179oz/n5ycLGsolN3Y72bHjP2vi3T9709Dx4GOAT0XdPs1oWt/7+8eCzbRgH2eM2xwzcrJZOXzO3D+fNmyzZDB4EWGVPT5/yfPBRdLA0xqmB/JYtWNX5RNV14T7ASRBRVmzZrF0/Bnz54tmyGn6mOgqt9LY3b1pOrno7qg46Cbx0HX/l5lHod3797x4EJoaChfZyWSWHCBNcxV9zENPQ+UdyyS/f0Rf/064q/fQMKdO0hNSPju/fRz5YJp1SowrVoVJmXKQGD6ta+Bol+fLFOAZTFMmzaNX+NkYzVW0jIzf7+1sQAja+dBv6q5YWog/OFzm5VSmnR2Eu5H3OfrBx4fwKdbn77+HGtrnt3DyocVK1ZMtl1dXiv0mlCf45Ddv1tpAQZWE4xlFrAaemkfFGlpReXKlUOnTp2yXCP5W3fu3JFb79q1K4oXL44JEybwxnjs/59hzVDYG8P3sIDFt2lH2fkkYCeU7I1FFxtW6/rfn4aOAx0Dei7o9mtC1/7e3z0Wixcvli136dIlS5/dyffvI+HWbb4szJcPSRUqqOyzXxHPhVBRKAbdGoRmuZuhhVsLnlatTXTpNcGeyytXruSNBFm9327duvEZcqo+Bmx8rAo0ZldPqn4+qgs6Drp5HHTt71XWcWAB5ObNmyMwMJCvV69enWfxsZ+pCeh5oLhjkZqYhJSnT5B89y6S79yF5NPXi+pyjIygX6okDMqXh0H5ChC65uSbE9kXawz+pTm4srBrmcuWLePZNqyEV48ePeDs7Jylv/97oQA25jt06BB27tyJj5KPcB3gCqGxEEEHg/jtlStX5r+bBeBMTKRjfE0+b9F2yWpwHLJ73K7wAAOL4jVt2hSXLl3iGQslS5bkHctZPWSRSAQ/Pz/8999/OH36NK8fdvz4cX4/RaaVs6DByZMnfxlg6NWrF6/x920GQ79+/WBpacm7v6vqicjSuNgsTF18Qer635+GjgMdA3ou6PZrQtf+3t85Fnfv3sX9+9LZPTVq1OAnpZmVKpHg84aNsnXHUSNham8PTXsuxCeJYWooLR+w8u5KhCeFY/O7zbA2t0bngp2hTXTpNcHGoCNHjsSkSZP4+JmdwLJgmqqPARsfqwKN2dWTqp+P6oKOg24eB137e5VxHFg1ibZt28Lf35+vV61aFUeOHOGzxDUFPQ+k2EXUyCNHYBwXD5u2bXjZ0kwdP19faZbCjRtIuHsPqT8IDhi4u/MMBdMqlWHMshSy2G9N0WO0UaNG8euNrOHy2rVrecDhd54L7Lhdu3YNmzZt4sEF9vPSfJj8AU7FnTC001A+0SRfvnzQBPSaUJ/jkN3jdoUHGCZPnoyrV6/yFxjrXG5kZJThPuxFw06U2InTlClTeHMURWEPnIuLi1zWxI/kypWLf/3o52T2TVEZWCkpVe+DKun635+GjgMdA3ou6PZrQtf+3qweCzbDO31N1Kwcp6jjx5H0+jVfNqtcGdY1akDT/v73wTFotuIG2pTNhZ5V3OFo5ghjoTEsDS3RoXAHGOpr3/NGl14TLAWfjadDQkL4pJwxY8bwJtCqPAaqOkGiMbv60qXX5M/QcdDN46Brf68ijwPLWGAzsX18fPh6xYoVeclrTawjT88D8EbL4VOm8uORki8vzKtV++6xkiQkIP7ePd5LIfbaVSR//H6Wgp6pKW/KbF69GsyqVYOhqyvUybBhw3jVlODgYB4cGDduHM9i+N5zYfV/H+AdGove1TyRP4eF7PnPyoCxDE1WIiw91tScvTZYb4VGjRppZACTXhPqcRyy+7mj8ADDvn37eN3YwYMH//A+LOgwZMgQ/mHCSikpMsDAZnmxSDj7gNIE9ZdcRVjcNwlSqam83iB7Y0G6hjR2ZoY4MzzzszMJIYQQbcVS6vfv38+X8+TJwwfgmSVJTETI4iVy2QuaaMM1b8QlibHlpg+K5bTCkDJD0DZ/W/jG+GpdeSRdxHqJjR07lk/IYXV127Vrx8fQYWFhsLOz4yUl2Iw2NjOKKB+N2QkhRDHYZFDWc+Ht27d8vXTp0rzChSYGF4h0Fn7Iiq+TfiJWr4FV1ap89ja7LcnbB3HXr/GgAgsupKabpZ+eUb68MKtajQcVeC8FNQ7csSwbFlRgTZ7ZTHU2RmNVW74do5mYW2LDNS9+ze/E0wDMLCvGji0beSUXVp8/Pc+qnuhWtxt69ugJVzULqBCikgADm2VVqFChTN23cOHCmco0+J60F+63WCo5e6E2adIEmoC90YTEfP8NlhBCCCHfx7IXxGKxbBaRUCgtE5QZEbt288ZxjGWTJjAuXFjjDnNwjAiHHvrxZSdLYzQp4cKXc5jl4F9EOwwYMADTp09HVFQUbt+W9gtJc+XKFYwfPx4rVqzgjf6IctGYnRBC/hyrW//333/jxYsXfL1o0aI4d+4cb1xLNFP87dtIePBAti56+BCha9YiJTgIcdeuI/nz5+9+n8DMDGaVK/EMBfOqVWHgIh3Laor+/fvz8uysd8K3/WHTxmg9Z25EWJy0TE3s84toNUPaEDr9DHMWjKjcpTI2hm9EZO5IWDlaZevfQYjaBhjc3d1x5swZXiv1V1gKHLv/75g5cyY/0apVqxbc3Nx48wz28y5fvowKFSrwDAlCCCGEaJ+4uDheajGttmT37t0z/b3i6GiErVnDl/UMDOAwbBg00babH5EklvDlHlXcYagvUPUuESXYvXs3Dy78SEJCgmzMTUEGQggh6ow1HK1fvz4eP37M1wsUKIALFy58d+Io0czshTShS5d+9/5GBQvCvFpVHlQwLVkSemqcpfAru3bt4sGFH0lIEOHwqygY2FkiNVWCgMs7ZbcVLFiQl5Tv0qULzG3MUf9gfb79/MfzaOjREHVy18mWv4EQtQ4w9O3bl6dys2Y9rHZsuXLl5Oo+sfQh1pRxyZIlvIHPggXyEbzMYo2jX758yeuWsWwGNnORNT2ZNWsWr8PM0pMIIYQQon22bdvGZ8AxbHCelZT6sPXrIf5ywdamY0cYuuaEpolPSsH22x/5srn1eyRZfEJ8cjeYGpiqeteIArHn+M9KjqbHJta0aNGCyiURQghR28khrJwluxbEeHp64uLFi8iRg7IutSl74VsCCwuYVakiDSpUrQaDHI7QlTGaSZ6yMLCT9nyNf3sLBomR6Ny9O++tULlyZV5CKs3imovxv6v/Q03XmhRcIBpL4QEGFlRgvRVYuvbBgwd5HwF7e3teM5Y1d2YlkVh/AWbQoEH8/r+jWbNm/IsQQgghuoONIVhTNYaNMTJ7AZZJDghA+Lbt0u+1sIBd/37QRPvvf0ZUQjI7GrByPYN1zz7j0Pt9ONj0IGyNbVW9e0RB2CQalqGQGfHx8TzwxsqFEUIIIeqEfZaxazfXr1/n67ly5cKlS5eQM6fmTfIgv85eSGNUoADcD+yHQAObFCtijGZZvqVsuax5FPYEBMDK6vvlj0rnKI39TfbDzMBM4ftKSHZReD49i8KxE/9nz57xpie1a9eGg4MD757N/mfrrBbZkydPsGzZMrmoHSGEEELIz7AyjG/evOHLbMZ2VkothixfIWssZ9e3D/Q1sDmuWJKKDde9+LK+SSASEcKXi9gVoeCCljl69KhS708IIYQoW1JSElq3bs2zFRhnZ2ceXMidOzcdfC3PXkh88+ant2uyX425DJ3ywditGF8WfX6JRL9XPwwupGGThIyERgrdT0I0OoMhfQNn1ieBEEIIIURRWInFNP/880+mv0/09i2ijhzhy/pOTrDt0kUjH5SzLwLhGy6dMdWoQFlMaNoMq5+sRseCHVW9a0TBftZ74Xt+VgeYEEIIyW6sPHb79u15r0yGTThlgYa8efPSg6EV2Qsrfnk/dh/TChW0bmLxr8ZoluVbyJaj7x1GpJlI7nbfaF9c9r2MLoW7aN2xIbqLOgISQgghRCO8ePEC58+f58tly5bl9UszK2ThIlZfiS87DBkCgYb2alp3VZq9wPSp5glHU0dMqTQF+WzyqXS/iOL9aqbbt6ytrelhIIQQohbEYjG6du2Kw4cP83UbGxs+hitUqJCqd40oLHvh4S/vl3D/AeLv3NGpMZrQ0hGmBarw5eQIfyS8uyM3RksUJ2LklZGYf38+hl4aipikmGzZZ0I0NoPB19cXe/fuxb179+Dn58drw5qamvI6e6zxM2sC7ebmpqxfTwghhBAtw/o7pc9eyOyMn7g7dxF75QpfNsqXD1bNNbeH05xWxbDhmjdCYxNRNGfWLkATzcLqVf/3339Zuj8hhBCiDv2yWCPbPXv28HVLS0ucO3cOJUqUUPWuEQUJ27wl0/eN2LUbZhUr6s4YTZKCmEenYF7sb0TfOwKkSuTGaE9DnuJd5Du+HJoQSmWRiNZQSgbD9OnTkS9fPowePRoHDhzAu3fvEBYWxv9n62w7u33q1KnK+PVaQc9QWlM5PVGSWCX7QgghhKhaaGgodu7cyZddXFx4Pd/MpnAHL1ggW3cYOQJ6QiE0VUEnS7SpKsKKjkVUvStEybp16wYTE5NM3ZdN4mH3J+ohKj4ZsYkpqt4NQgjJdmzcNXjwYGzZIr0AbWZmhtOnT/PMU6I9j7E4IkK2rmdiAqGDPYT29tCzteX/8/UvXzYdO+rUGE0cG46IC2vht7o74p5dyDBGK+dUDtvqb0NB24KYX2M+DIWG2bjnhGhQBsOaNWt44KBly5YYPnw4ypcvD0NDQ7kmP3fu3OE1lGfMmIEcOXJgwIABit4NjSY0fw0T161IDq+CxJD6QKr0YYpJTMHsU68wpn5BCARUp40QQoh2i4iI4CeorJHaq1evkPilQXOvXr3kxhY/E3PmDETPnvFl03LlYF6jBtRZ/SVXERaXJL8xNZXPBhQIBEjVj0Ki07+AxBg2oha4OvB/qtpVomSsnATL2mHP919Zvnw5lUhSI0liCdqsuYVN3cvC2SpzQSJCCNHUMRqbTGpnZ8dnabNJpatXr+b3MTY2xokTJ7JU0pKov6hDh2Rja0MPD3gcPsRLj7JrfeHh4bC1tc30OF1Tddj6DJ7/7EFkJvpl5bS1yDBGK+ZQDPsa76P+C0SrKDzAwE6EWHCBZSp8D3ujqVatGv9i91u5cqVOBxjszOTfeFP1EpDodADQS4Wh3XWYpRZCYnR+xCVKsxfWXvWCT1gcVncqQ0EGQgghWmvTpk18BlxCgrShcXrz58+Hu7s7evbs+dOfkZqUhODFX5tCO/5vlNoP5FlwISRGGkj5HiOnMzDUSwaEyYhJCcvWfSPZL+05/qPXApsVx4ILv3otEMWP2b8N/kFPDyliCaISkiFJBV4FRKPZihvY2bsC8uWwoIeAEKL1Y7QrX8pRpl33OXLkCGrWrKmCPSTKkhwQgKDZc6QrAgFcZv+rsX3N/nS8HisWQt/c9pf3lRgZ8ayPb89B1P2chBCVBxg+fPjA6yJnRqNGjXi6nC47M7x6hm3H3qZi1r1Z+Nvtb8zsNpRvO/0sAP/sewxRsgTFXa0puEAIIUSrT1x/NmtbJBLJbv/ZhdWIffuR/OkTX7aoXx8mxYtD0yWF1ub/65u/gTA24xiCaB/2HG/RogW2bt3KZ4qycmH29vZo3rw5b6DJMh2Iasbs35utGRglQq+t9/DCPxq2ZoZwtqYMBkKI7ozR0vTr1w/16tXLln0i2YNdJA+YNBmS2Fi+btujO0xKlqTDnwkzb8+Ek5kTehXrBYGeUirVE6J9AQaWGvf69etM3ZeVO2D3J/Lqu9eHm4Eb3B3dZdsaFHOGi7UJDj/xwsCaeeiQEUII0dqUezYrLjOGDBnCL7x+7wKrODYWoatWSVf09eH4z3Bog9QUSyQGtkCiXhJMzbU7/Zx8xZ7jrPTowIEDdab8gKZysjLGvn6VMP34Swytkw/mRgo/3SKEELUfo23cuBHTpk2jILgWiTp4EHHXr/NlQ09POAyVToYlPyc2vYd9b/fx5Q9RHzCn2pcMEEK0jMJDZ+xEf9myZVi1ahWf1fM9ycnJvDQSS+lmZZJIRk4mTjA1MJXbFiy5hyvxI3HL/5bc9rdBMXQICSGEaAU2S/t7pWC+Jz4+Htu2bfvubeGbNkEcHs6Xbdq1g2Hu3NAqqXRxmRB1ZWakj7mtiyPnN9kLn8LikSyWqGy/CCFEHcZoRPMk+/sjaM5c+dJIRkaq3i2NkAoxDAQGfLmRRyNV7w4hmhNgmDVrFkqUKMEj2yw7oXr16ujQoQO6d+/O/2frbNYVm3VYvHhxzJw5U9G7oJUC4wIx9eZUhCaEov+F/vCK9OLb99z9hHpLrmLd1Q88ZY0QQgjRZKwEzJ/ePzk4GGGbt/Blgakp7Adqeq+nVEDv+5M2CCGagZVOarP2Jrpvvsv7NBBCiC6O0YiGlkaaOElWGsmuZw+YlCih6t3SGPrxFbGz4U6MLjca1VyrqXp3CFEahefsWlpa4saNG1i/fj127dqFBw8e4PqXNCrGxMQEpUuX5sGGPn36wMBAGskjP2duYI4arjVw3Os42hVoB09rT3iHxmHikeesvxz+PfUaXiFxmNG8KAyEVNONEEKIZgoODs7S/SMjIzNsC125CqlfZtjZ9u4FfQ0vxyg0fwVj50NICqmD5MhybIuqd4kQ8sUJ3xMoklIElVwr/fSYDN/7CEHRifyr5aob2Ny9PNzs5LOVCSFEnUVFRf3xGI1onsj9+xF38yZfNsyTB/ZDhqh6lzROIbtC/IsQbaaUK9EsaMBqxLLAQiyrgRwaik+fPvH/2fq1a9f47RRcyDxzQ3P8W+1fLKm1BCPLjuTbPOzNMLVpEUjjCanYc89XOisqnmZFEUII0SyBgYEYNGgQ78+UFdbW1nLriV5eiDxwgC8LHexh1707NJsERg7nIdCPhbHzEQhMPqt6hwghX4QkhGD169Xoe7EvRv4nHZ//yPRmReFqIy2Z9CEkDs1X3cB9H2kZN0II0QRWVlZ/NEYjmlkaKXjuPOkKlUbKND0hlTEnukfpU9319PR4SSRXV1f+P1snv6+2W20Y6xvL1jtXzI3+jSJh4bYDesJY3Hgfhharb+BjWBwdZkIIIRoxG27ixInIkycP79+U1XJ/zZo1k1sPXrQIEIv5ssOgwbxEkmbTQ1JYDb6UElMIkgQt6yVBiAY77XMaSRJp+bJfzUzMn8MChwdWQSk36QW38LgkdFx/B0cf+2XLvhJCyJ/6dsyl6PsTNS2NFCe9tmTXqxdMihdX9W6pBclPzlcERoEwyzsfhvbn+EQhQnSFSmvpxMTE8MwG8vt8Y3xx8ONywOwFLPIsBwQiXiqp+cobuOtNs6IIIYSoJ5FIhIULF8LT05P3b2LNABl7e/tMZziampqiW7dusvX4hw8Re+EiXzb08IB161bQNBkbwOohJbokRIGNkRjcQEV7RQj5ni4Fu2BW6Vmo5FQJHQt2lLstQhSBl2Ev5bY5WBhhd5+KaFzcma8niSUYtucxllx4S73UCCFqzygLTX2/HaMRzRO5L11ppLysNNJgVe+S2ohJSPn+DXrJMM65E3qCJBg5XIKB1YPs3jVCdDPAsGzZMnh4eKhyFzRebFIsrI2kM6HaFmqK0q5OfDkiPhmdN9zBoYdUSoEQQoj6SElJwebNm5E/f36MGjUK4eHSYLiFhQWmT58Ob29vrFmzJlM/a/ny5bL0ezbLKnj+AtltDiP+gZ6+wltNKR3voySQ9o9ILzmiKiRJjirZJ0LI97HM7PIO5bGi1gqYGshnS21+sRntTrTD8MvDERgXKNtubCDEsvalMOSvvLJtSy68wz97HyMxRZp9RQgh6mbnzp28lGVmpR+jEc2T7OeH4LlzpStCIVxmz4bA0FDVu6U2zI1/cI6RasAzj1MlBkiJ80RyVJns3jVCVEbzzryJHJaOfaDJAWx9uRV9i/WFuKwAow88xbEn/nxW1KXXwWhRKieVpiKEEKJSLABw9OhRjB8/Xq7PgqGhIT9hHTduHBwcHPi2nj178v8HDx6MhC/Nmr+dFcdOXNPux8RevIiER4/4skmpUrCoUweayNzyE0TO6yCMbA6DhLLSjampkEgkEAgE7Iqm7L52ZnSiR4g6CksIw57Xe/jy3YC7GYIPAoEeRtYtAHc7M4w99BTJ4lRceRuC4OhE5LLV9LJuhBBts3v3bnTt2lWWadW8eXOcPXs202M0olnY4+w/cSIkX7KLeWmkYsVUvVtqxdHCCHrpPtPlxuviypAEe0BPYg5zCxMarxOdofAAw9WrVzN9XzZLkSimAfSgktLZBAZCYGn7kvB0MMNxr6OoWDIaQCk6zIQQQlTmypUrGDt2LG7fvi0385edrE6bNg25c2fsK8BOTFu0aIGtW7fywERoaCgvn8ROatn32djYyO6bmpKC4EWLZeuO/xulUYH1Bx8jUCa3Dfxj/RFtvRKQJEHPYS821W+EYg7FkJSUxDM9WC8rFpAhhKg3G2MbTK88HauerEJDj4awNLTMkIHMxu+tyrjyxs9D9zzCio6lKbhACFE7+/btQ+fOnfmFU2bq1KmYMmUKIiIiMjVGI5oncu9exN+SjtmN8uWF/eDMZ65oK5ZhmJQigYWxtIzrmeHV5W5PkaRAkiKh8TrRaQoPMNSsWTPTJ/UsMqpJFwA0BTumTcvpY0fgPsy9J8L9oDtYVHMRBHoCpIgl0GflFwghhBAle/LkCc9MOH36tNz2pk2b8r4LRYsW/en3sxPU4cOHY+DAgT8dsEcePIQkLy++bF6nNkxLl4am2HLDG1OPv8SgWnkwqm4B9CzWE2uerEHd3HVRwLaAqnePEPIb2Ji7vkd9/J37b6SkytdpjkqMQqPDjVDDtQb6F++PCp65cOV/tXjppPQkktSvsyIJIUQFDhw4gI4dO8qCC5MmTeLBhayM0YhmSfrsh+B586UrQiGcZ8/R+dJIrD/aoJ2PEBwjwrae5WFt+vV5HimKxMIHCxGTFIN5Veap7oEjRBsDDKzxT+HChfkH0a9cvHiRp9YRxXsS/AQpkmS+nM8mHz/RuecTzssnre5cGgWd5GdSEUIIIYri5eWFyZMnY9euXXKNS6tWrYo5c+agSpUqCvtdLH07ZMVy6YpQCMcRI6Ap9t77xIMLzMrLH1CnUA4MLDEQea3z8guT7LObEKK5hAIh2L/0tr7YyoMMxz4cg4OJA4aXGZ4huCBKFqPrxrtoWTon2pd3y+a9JoQQ4PDhw+jQoQPEYmlvGFbikmWdEu2VKpEgIH1ppD69YVK0CHSZWJLKeyRdeBXE1wfufIhdfSrKbh98aTCehDzhy//l/g/FTYurbF8J0boAQ7FixXiEe+TIkb+8r0gkogCDkrTI1wIeVh7Y9XoX+hXvh09h8ei3/QHC45LQevUtLO9YCrUKULNIQgghihMUFISZM2di7dq1SE6WBrnTxgazZ89Gw4YNFZ65GL51K8QhoXzZulUrGHl6QhMcfeyHsYcfQGjiD3GCO6Y3K4JSbtKSAvXc66l69wghSuJu5Q4nMyc+27F7ke4ZbmdB2VH7n+CuTzj/8g6Nw5j6BSmbgRCSbVjZo7Zt2yIlRZqBNWbMGD6+o+oTOlAa6Us5U6N8+WA/cCB0GcskHHvwKU48DeDrFsb6GN+wkNx9WKnyvuf78gkDQj35yQKE6BqFBxhKly6NLVu28AsLBgbS+mRENUo6luRfjLVZKoq4WOLau1CIjO6j9y4/TKpbC92reNDDQwgh5I9ER0djwYIFWLRoEeLi4mTb3d3dMWPGDD4DTihU/KA7JSwMYRs28mU9ExONqRF75nkgRhy8ARO3LRAYBaBNzpnoWsld1btFCMkGTfM0RX33+ngT/gbWxtZyt215vgUBcQHI7Vhbtm3tVS/4hMVhSbtSMDGkixeEEOU6fvw42rRpIwsujBo1ik8SoeCCdkv6/BlB8xekK400W6dLI7Fg/9TjL7D/wWe+bmooxPpuJeFiJ83oSVPJpRJmVpmJv9z+ghGMeLkwQnSVwgMMrVu3RmJiIm/04+zs/NP7shrMrq6uit4F8h2WxgbY3L0chh8+hf9i9rNLMZh1zQfeoW0xqXFh6stACCEky9jn/apVq3g/hbCwMNl2BwcHTJw4Ef369eOlE5UldNVqSL4ENGy7d4OBo/pn5l1+E4whux9CaH0PQhNfvu1R/HpIUhtQSSRCdISh0JA3cE8vOika656t45kN1kansLTDdoze/wqJKRKcfRGEdutuYUPXsnC0NFbZfhNCtNupU6f49Zy0LNR//vkH8+bNo+CCLpRGGj8BqWmlkfr20enSSCy4MOfMa2y79ZGvG+kLMLa5EWY/6Qvn985YXWe13GuiWd5m/P+kpCSV7TMhWhlgqFOnDv/KDFYygX2R7MGaO9s634VenDTqqidMwNZbH/ExPB7LO5SChTFlnBBCCPk1Vo93x44dvM/Cp0+fZNvNzc35TLcRI0bAwsJCqYcy6eNHROzdy5eFNjaw69UL6u7mh1D03/4AyeJUIKw68uWKgp6RP5bXXk7BBUJ03IfID9DXk56atcjbAs1KuCO3rTV6b72P0NhEPP0chWYrb2Bjt3Io7EK91AghinXmzBm0aNFCdpF02LBhWLhwIQUXdEDE7t2Iv3uXLxsVKACHAQOgy5Zfeo+1V7z4soFQD6s6l8KKNwPgFeXFv057n0ZDz4aq3k1C1A51D9QxkytNxsCSA1HAsgz0Y2rxbf+9CeF9GT5HSCPWhBBCyI9m9Bw7dgwlSpRA9+7dZcEFVhJx6NCh+PDhA6ZMmaL04AITvGQJ8CV9n9WIFZqbq/WD9jYohl8oZLORmW6VPHCw9TLsbLgTuSxyqXr3CCEqVsqxFM60OoPhpYeje1Fpb4aSuaxxZFBl5HcygKH9RQTEhKPNmpu49FrabJIQQhTh3LlzaN68uSy4MHjwYCxevJiCCzogydcXwQsWSlf09eEy+1/o6XBppA3XvLDo/Fu+LBTo8Ym4tQs6YVLFSXxb1ZxVUdyBGjkT8j0UYNAx+gJ9DCgxAPuab8KB/lXhbCVNs34TFIMhh/chSUxpXYQQQjK6fv06qlWrhmbNmuHFixd8G0sP7tKlC96+fYulS5fCMZtKFCU8e4aY02f4soGbG2zatVX7h+xe2HFULJjAl9uWdcWUJkVgrG8MKyMrVe8aIURNmBqYolexXrA1tpVtc7UxRfMaH2HkcB7meedCZPAS/bc/RGCUSKX7SgjRDhcuXOBjO1b2khkwYACWLVtGwQVdKo2UIB2f2vftC+PChaHLclgaw8AoDALDUCxsUwL1i0rLvpfOURp7Gu3Bqtqr4GpBZd4JUXqAgV1k8PKSphJlxbt379C5c2dF7gr5BYGegKdXHx1UBcVdrWBvGwhv/SXoeLIjT9EmhBBCmGfPnqFx48Y8uHDjxg3ZQWHbHj9+jG3btvFmztmZRRGc1oQOgOM/w9V6ppUkVYL59+Zjzr3Z8NZfhnFNHDG7ZXEIBF9rtxJCyI+IJWIc8zrIl4VCCSSJzpjatAicvkwSIoSQ33Xp0iXeF1MkkgYs+/btixUrVlBwQUdE7NqN+Hv3+LJRwYKw798PuixZkowAvRMwz7MEhYqdQbOSLnK3F7EvQq8NQrIrwPD+/XsUKlSINwZiJRQSvkRCvyc2NhYHDhzg0fIiRYrA29tbkbtCMok1itvTpyJc852BOFWMNxFvcDvgNh0/QgjRcT4+PujatSsvh3Ty5EnZ9sqVK+Pq1as4fvw4ihfP/hThuKtXZXVijYsVg0X9+lBXKWIJD4h8ipaWkgpLCIOLUyBPuSaEkMwQCoR81mSvor3Qq1h37OtdDx0ruMlufxH2AvHJVOaUEJI1V65c4ZNF0q7Z9O7dG6tXr4ZAQEUudEHSp08IXkilkdLTgx4ufLyAlNRkfIp/jrMfz6rs8SEEut7k+datW9i1axdmzJjBa/jp6+vz4EGePHlga2vLT7LDw8N5xsKrV694k8jChQtj+/btaNeunSJ3hWSBqZE+Vv69BGOvjoW5oTk6FuwI/8gErL/mhbENCsJIX0jHkxBCdERwcDBmzZrFTzKTk5Nl29nn+ezZs/nJKCuNpAqpYvHXOrEsSD5qlNrOJPINj0e3zXcxs1lRzK0+F4MuDkLnQp1RO3dtVe8aIUTDWBtbY3iZ4Rm2J6QkYPDFwYhNTEaPIn0wsHQ3lewfIUSzXLt2DQ0bNpQFF3r06IG1a9dScEFXSyP16wfjQoWgi1hPo7veERhTvwAvJz6l8hT0PNMTfYv3RW03GrMTorIAA9OxY0f+dfHiRezfv5/Pcjxy5AgkEmlTQxYRZ1kO/fv3R5s2bVC9enV6xNJhQZiYY8eRGBeL1Pbts+3Y5DTPic31N/MTlbgkMXptvY9XAdF44ReNKS2dUMTRgx4nQgjRYjExMVi4cCH/YlmGadzc3DB9+nReylAoVG3AOebECSS+e8eXzWpUh1mF8lBH/pHx6LD+Nj5HJKD7lnvY2bsCNtXbpLbBEEKIZtr3Zh9CE0L58tpbN1DZoRlvDE0IIT/Cyl02aNAA8fHSzCeWrbp+/XoKLuiQiB07EX///tfSSP36Qhevuy25vRdrzschMd4JMaJkzGhWFEXsiuB8m/OwNLRU9S4SonEUHmBIU7t2bf7FsOBCWFgYP7G2s7OjE+yfiL99G8ETJ/LlBE9PGFWrhuzCIrYWhhZ44R+FgChpNPtB0AO0P7UeTT3aYUrVUTAUqm+da0IIIVnHmvqxWWszZ85ESEiIbDv7vJ44cSJv9mdkZKT6wHtkJKK2bZNu1NOD44iRUEfXPz3CkHMTERnTCYAVirpYorCzJY19CCEKV8etLtbdvIso4R1EB9RAu7W3sLhdSTQs5sxrSSMVMBAa0JEnhMgqTtSvXx9xcXF8nU0e2bRpk8onkJDsk/TxI4IXLZKu6OvDZc5ste5lpgxRiVHod3Y4XkTch9AxF+AzAAZCATu94Ci4QMjvyZYCeyxrwcHBAfb29nSC/YuLKCErVsrWI1av4duyWxEXKxweWAXu9vowzrkX0JPgmM9urL53NNv3hRBCiHKwMoWsRGHBggUxbNgwWXDBzMwMkydPhpeXF4YPH67S4EL6wHv8ggWQBAfzbVbNm8O4QH6om6sf72Hgpd5IMfgEk1ybUTinAbb0LA8zI6XN5yCE6LCcFs44320pKugvRmqKNRJTJBi48yFWXn6Pg28PovHhxjj07pA02EAI0Wl37txBvXr1ZFmqHTp0wJYtWyi4oGOlkfwnTEDql6be9gP6w7hgQega72AxXgRIz3uEJr6oUyoWU5oUpmuVhPwh6uCjRthFlIQHD2TroocPEX/njkr2xcPeDEcG1kIutEKq2AjJ0UWw/Jgpdt+VNqokhBCimVjgmjVtLlWqFE+LZ82cGQMDAwwePBgfPnzAtGnTYGlpqXaBd87QEA5Dh0DdRIuSMfdYJFIS7fi6mSAHNnatAEtjmj1MCFEeU0N9rO9cFf1qeMq2zT/3HAvuroJ/nD+m35qOwNhAeggI0WH37t1D3bp1eTlMhvW/3LZtGwUXdEzEjh1IuC+93mRUuBDs++peaaTXgdHovvk+4vxbQCxyQRmDSVjbpj0FFwhRAAowqInvXkQBELJihUqyGBhrU0Mc6z4UNc1nQxTYEikSYNyhZ5h18iXEklQkihNVsl+EEEJ+z82bN3nvI9ao+dmzZ3wbK1/YqVMnvH79GsuXL0eOHDnUNvDOWNapDQNnZ6iTuMQU9Nh8Dy/8kpDg2x2mcfVxrN1aOFtZqXrXCCE6QCDQw7gGhTC3VTHoC/SgJ0hCbKQ7kKqH+rkbI5dlLlXvIiFERR48eMCDC9HR0Xyd9cHcsWMH9PUpu1KXJPn4IHjRYumKgQFcZs+GnoGBTpRDYoH2pyFP4RUSi84b7iIyPhmSRCdUNZmJDe1aQyigHmmEKAJ9qqjxRRSGRZhZFoNZxYoq2S9DfQGWt6mDIo5emHvmNd+2/po3PsQ+wkfBJsysMhOVXCqpZN8IIYRkzvPnzzFhwgQcO3ZMbjtr8jd79myUKFFCYwLvyf4B/DZ1aJicJE5CeEIM/tn1Dg8+RvBtOS2csL/TdDhbmqh69wghOqZdOTfksjFF/x0PEO3fDkmhtXAz3BpR5ZJhZSq9kMTKJQ2/PBxN8zTF37n/hkCP5psRoq0ePXqEv//+G5GRkXy9VatW2LlzJwUXdEyqWAz/8d+URipQANrOL9YPnU52QpgoDPcDHyH49QCExkpLBtbI74DlHUtDX0ifgYQoCr2a1PgiSpqQ5arLYmDYRZwBNfNgTefSMDYQwNAwAe8k6xEcH4y+5/viVdgrle0bIYSQH/v48SO6d++O4sWLywUXKlasiP/++w+nTp1Sy+DCTwPvjx+rrHxgetFJ0eh/oT8GXxoI/yjpibuTpTF29a4IZysKLhBCVKNyXnscGlgFbramkCQ5ooZnPliafJ1TdvT9UVz9fBWjrozC0odL6WEiREs9efIEderUQUSEdAJE8+bNsXv3bl4Sk+iW8O3bkfDwIV82LlwY9n36QBe4mLkgj3UevhwQG4LghM98uYKHLdZ0LgMjfWpuTogiUYBBjS+ipGG3RR05AlWrX9QZ+/pVwtyWJVHFVZpR0cizEQrZFVL1rhFCCEknNDQU//zzD/Lnz4+tW7fKgtSFChXC4cOHeamkGjVqqO0xEyckwH/M2B/ersrygWmm3pyKe4H38CbiJcqU+Q+V89hhZ58KcLMzVel+EUJIXkdzHBlUhU8Q+rZxZdrEIJa50DxvczpYhGihp0+fonbt2ggPD+frTZs2xd69eym4oIMSvb0RsniJdMXAAM5aXBpJkiqRW2effZMqTkKb/G1wrvUJdCxdDqXcrLGxezmYGFJwgRBFoxJJap69kCZg/AQkBwbBvncvlX4gFHe15l8tMAe1ctVCZZfKSEgS89IQVfPZq2y/CCGEALGxsVi8eDHmz58va+TH5MqVizduZk2dhUL1HlCL3rzF54EDkRIc/MP7qLp8IDOy7Eg8Cn4EI6ERhpTpB4+/PFS2L4QQ8i1bM0OMqV8ww/aGLoPQLE9zPAl9DA8r+fetG343oAc9Xv5UHcrQEUJ+rywmCy6EhYXx9UaNGmHfvn0wNDSkw6mDpZHYdaTURGnvTIdBA2FcID+00ePgx5hxewbGlR+Hsk5lZdvdrdwxudJkvjyjmRUSksUwNaTLoIRofAbD58+fMXfuXAwePBj//vsvvLy8oOt+lb0gk5qK0KVL4d2qNRKePoU6qOdeD2b65hi5/zG6bLqDdVc/4PKnyxh6aSgiRNJUTEIIIcqXlJSEFStWIE+ePJg8ebIsuGBra4uFCxfi7du36NGjh1oHF1IlEoRv3QrvVq2Q7Of3y/urKotBIknF8ovvYAR7rKmzBjsa7shwkY4QQtTRxVdBaLPmFtZeSEabfB3lbkuRpODfO/+i34V+6H6mO+8xQwjRLC9fvsRff/3FM1nTem0dPHgQRkZGqt41ogLh27Yj4dEjvmxcpAjsevfWysfhZdhLdD3dFW8j3mL67en88ytGlIy73tIMnjQscE7BBUK0IMBw9epVXqph5cqVePjwIZ9hWbhwYZw+fRq6LGL3nizdP/HtW/i074Cg2bMhiYuDql15G4JTzwJZ/AOzz93FqMsTcNn3Mloda0VBBkIIUTKJRMKb9RUsWBBDhgxB8JdZ/6amprypMwvkjxgxAsbGxmr9WCQHB8O3T18EzZ4DpKRk6nvSshiyCwugi1JEmH7iJRaef4t2a2/BSpgb9iaUvUcIUX9xiSn434GnkKQCJ58GoP262wiJkc5qTcte+BTziS+z9zVDIc12JkSTvH79mgcXQkJC+Hq9evVw6NAhCi7oqEQvb4QskZZGYhUwnGf/Cz197Zy5X8i2EKrmrMqXc5jmQEhcFHptuY/OG+7g7ItAVe8eIToj2wIMY8eOxciRI/Hp0yde+5llM/z9998YM2YMdJlNx44QOtjLf9nbQ8/Wlv8v22ZrA6OCX9Kc+SzPbfBq0hSx166pdP9rFXTEzOZFIRToQU8YC1GS9EOrolNV2BjbqHTfCCFEW7GZ+yxAX7p0aXTu3Bne3t58u76+PgYOHIj3799j5syZsLKygrqLuXgR3k2bIe7GDemGLJTliNi1G9lxrFc+Xomhl4ei1YGh2HJTmn3pG5EAnzDVB/oJISQzzIz0sb5rGdiZSQMHj30j0XzlDbwJlGa81chVAxvrbkRpx9IYUGJAhrrWL0Jf0IEmRE29efMGtWrVQlBQEF9n11lYzy11n2BClFkaabysNJL9oEEwzq89pZHCRRkzEyZUnIDZ1WZjea3VGLvfC3d9wpEklmDmyZdITBGrbF8J0SUKD2Gy8kesDJKZmZnc9o8fP6Jly5aydZam17BhQx540GVmFSsg/zdBAlbqgjVkYqUt0tdKZBc5og4dRtC8eZBERSHZ35/P+LRs0gQ5xo2Fvq2tCv4CoHPF3MhtZ4qBO4WI8R4GI/tLuBVaBT6F4+BuL/88IIQQ8mdu377Ng/MsMzC99u3bY8aMGcibN69GHGJJfDyC5sxF5L59sm2G7u6w6d4doStXyN85VZqtIRAIAD35IL2yhSaEYs9rabbhp8RbEJoWhSAxL9Z2LoOKnnZK//2EEKIoZXLb4vDAKui59R7eB8fCLzIBrVffxIpOpVEjvwPKO5fnX98663MWo6+O5jNER5UdhTzWeehBIURNvHv3jgcXAgOlM7VZFsORI0dgYmKi6l0jKhK+ZSsSHj/my8ZFi8Kudy+teCySJcnY/nI71jxZg0U1F8myFpic5jnhaOKMATse4to7aYkwe3MjbO1RHkb66lsilhBtovAMBpadUKhQIZw4cUJue/ny5TFlyhQ+yzI5OZmXSWL1osuVK6foXdBaLDJr3aol8pw4DosG9WXbo48fh1fDRog6dkwl9aiZavkccGhAZeSytkFicEN4h6Sg+aobuOMlbS51/uN57HuzT2X7Rwgh2lBXt0WLFqhUqZJccIGlwLPP1N27d2tMcCHh+Qt4t2wlF1ywbtcOHocOwrZ9Ox54T//lfukirA8d5P+n386C9MrmYOqAOrZjkSo2RoJfe0CUF8val+IZfIQQomnc7ExxcEBlVM0rLe8Wk5iCnlvuYfvtj9+9v1gixqrHq/jydb/r1JuBEDXCMlZZcCEgIICv16xZE8ePH+elMoluSvTyQsjSpbLSSC5aVBrpQdADLH6wGAkpCZh5eyb/P41Ykop/9j7GhVfSLB4bUwPs7F0Bng7mKtxjQnSLwgMM9+/f53Wg2UzKdu3ayepBL1u2jAcX2MUPlqrHAgspKSlYvXq1ondB6+k7OMB18WK4rloFfScnvk0cGQn/0WN4RkPS588q2a98OSxwZGAVlM0tLY0UGZ+MzhvvYNPth5hyYwpm3J6B4ZeH8yZyhBBCMsfX1xc9e/ZEsWLF+Iy09IH7S5cu4cyZMyhVqpTGpGyHrlsPn/btkeTjw7cJbWzgunIFnKdNhUANT4i33/LB5ktA7PvREMeUxMI2JdCgmLOqd4sQQn6blYkBNvcohw7l3WQXZiYdeY4ZJ17y5fQEegIMLzMc+W3yo7ZbbRSyKyR3OzWDJkQ1WC0sw9oAAQAASURBVJ8tFlzw8/Pj69WrV+eTPCm4oOOlkcaNR2pSEl+3HzIERvnyQVtUdK6Iv3P/DUOBIVrkbQF9PWngRCJJxdiDT3HiqTTQZmGsj+29KqCAk4WK95gQ3aLwAAMrX/C///0PT58+RUREBG88uXHjRuTKlQtPnjzBtWvXsGfPHj778sWLF8inRW942c3ir1rwPHFcWiLiS83quOvXeW+GsC1b+AdMdrMzN8KO3hXQrKQLX08Wp+JD7FPEpUjrVDubO0NfoB0RdEIIUaawsDBMmzYNRYoUwebNm3mJIKZAgQI4ePAgL5XETiw1RXJAAD5174GQRYtkjZzNqlSBx9EjsKhdG+ribcRbLLq/iGfc7bvvi0lHv9Qdl5ji3xbF0LxUTlXvIiGE/DEDoQD/tiiKiY0KyVrfPPeLyhBgYBnULLCwv8l+TK8yPUNvhuF3h2Pyrcnwi5Ve5CSEKJ+Pjw8fA7K+lkzVqlVx8uTJDGWqiW4J37IFCU+e8GXj4sVh17MHNBUbh7OMhW+NKz8Oh5odQr8S/WAgNOD3m3b8BfY/kL4WTA2F2NKjPIrmVP8+dIRoG6Vd6fX09MS5c+ewbds23tx5x44dWLduHSpXrqysX6mThObmcJo8CZaNGyNg0iQkffiA1IQEBM+Zi+gTJ+E8cwaM05pDZxNjAyGWtCsJT3tziFLEGFOnEVoHl8CmZ5vwT5l/snVfCCFE08TFxWHJkiWYN28eoqOjZdtz5szJAw7dunXjzZw1SfSpUwiYOg2SL3+PnqEhHEeNhE3nztBjfRXUxJ2AOzzTLjY5FsliATafKCC7bUqTwrLZvoQQog1Y8KB3NU+42ZpiyYV3WNO5DAz1v/+ezDIZLA0t5bZd/nwZ76Lf8a/IpEis+XtNNu05IbqL9bZkpZA+ffrE19n1lVOnTsHcnErB6LLEDx8QsnTZ19JI/87S2NJI/rH+vATSNb9rWFJrCQ9ypy9dmt7G697Yekta4s9IX4AN3cqizJeKGoSQ7KX0s/quXbvyutHswkiJEiXw77//8tJIRLFMS5eCx+FDsB88GDAw4NtEz5/Du1VrBC9aDIlIlO0nLMPq5MPoetKLM6UcS2F57eU8nS0qPll2v/98/4NXlFe27hshhKgj1p9o1apVyJMnDyZOnCgLLtjY2PBgA2vi16tXL40KLohjY+E/Ziz8RoyUBRdYqrb7/v2w7dpVrYILjB70IBJLPy+9o19jVedSMDYQYHT9AuhRxUPVu0cIIUpRt4gTTgypChszQ7ntouSfZ0Oz8hSOxtJ+NINLDaZHhxAlY0EFlrnAggxMxYoVcfr0aVhYUCkYXcYqV/iPT1caaegQGGlIX7bv+RTziQcXmNl3Zv+0FB/LLC7oZAEDoR7WdCmDynmk/YUIIdlPKWf2LFWPlUVifRfu3bsHBwcHnsFw+PBhbNiwAaVLl8bdu3eV8at1msDQEA6DB8Hz8CGYpNXjFosRtm4dvJs1R9yd7D/mLNCQ3opL79Fw2TW8DozGp+hPGHN1DNodb4cDbw9k+74RQog6YKWPWOnAQoUKYdCgQQgKkjYnMzEx4T2NXr9+zUsPsnVNEv/oEbybt0DU0aOybTZdu8D9wH4YF8gPdVTeuTxmVJmBlvla8qD4XwWccP6fGhhYU3NP0gghJDMEAvkx+/vgGNSc/x/Ovgj84ffUcK2BzVU3Y3H1xShqX1TutnuB97Dz1U4ki79OLCKE/Nk1FhZcYH0t03pxsT5clpbymUVE94Rv3gzRk6dfSyP10NzSSGm9Fpp4NoG7pTtmV5sNQ6F88Ds9e3Mj7OlbEZu6l0OtAtKANyFESwIMrOEku0gydOhQXsqBRdWnTp3Kb6tXrx6eP3+Ov//+G9WqVcOwYcN4KQiiWCxanXvnDuSYPAmCL3UYkz5+xKdu3XgZJXFUlEoO+YWXQVh4/i38IhPQatVNzL6xFvEp8Xy26OcY1TSmJoQQVWE1Q8+ePYuyZcuiQ4cO+PDhA98uFArRv39/nv03fvx4WFtba9SDlJqSgpAVK/Gxcxckf6kNLLS3R6716+A0fjwERkZQF2KJmD8Oad4Hx6KheyNMqzwNBgJpNmAuW/VrPE0IIcoUGZ+EnlvuIzBahP47HmD9VS+598r02IWf6jmrZ+jNMP/efMy5OwdNjjRBWEIYPWCE/AHWyJkFF1hjZ4aNHdkY0sqK6szrusT377+WRjI0hMvsfzWqNFJsUix2vdqV4TNmXIVxONj0IMo5lcvwPYkp8tl11qaGqJZPvnQSIUQLAgxslmWVKlUQGhrKG1TOnDkTs2bNQkhICL/d1NQUCxcuxM2bN3nD58KFCyt6Fwj7cBEIYNuxIzxPnoB5uiagkfsP4EOjxog+c/aHJwrKUt7TFtXySVPW4pLEOHu1AirZtEdx++IYVHIQPW6EEJ1x584d1K5dG/Xr18ejR49k29u2bYtXr15h9erVcHFxgaZJ8vXlgYXQFSt4Bh3DPoM8jx2FebVqUCfxyfEYdGkQNj3fxNcffIxA0xXXMfrg0wxNTgkhRJdYGBvg78I5+DI7XZh16hXGH36OZLEkU9//Ovw13kW848uu5q6wNbZV6v4Sos0CAgLw119/4f3793ydVYNgvS41bQIKUc6kHv9x45GaLM0Ucxg2FEZ58mjMob7pdxPNjjTD7Luzcdr7tNxtFoYW381cOPTwMxosucYnrRJC1IvCQ5tv375Fv379ZKUcOnfujAkTJvBoOyuVlKZMmTK8fNKiRYsUvQsaKyIiAlu2bMHRo0d5cMbOzg7NmzfnDT1ZDe7fYeDkBNdVKxFz9iwCZ86CODSUf/kNHw7z2rV5g2iDHNITCGWzNDbA5u7lMO34S2y//RGSVCHO3SwJE4OSqPzoCit+LZWaihR9LwhTckNP7+tT1M7MEGeGy8+QIoQQTcLKHbHPxEOHDsltZ5l9s2fP5p+NmogFrFkppKAZMyH5kpmoZ2yMHGPHwrpd2wzl8tQhc6H3ud54FvoMN/xuQJxkjeXHzRGfJMaBB59Rys0anSrkVvVuEkKISggFepjUuDDc7c0w9dgLHnTdffcTDjzwhZWJwdf39NRUXuZPwPrppHufZ2P2oz2PYsWjFehapGuGz4D3Ee+R14ZKzxHyK4GBgTxzgV1jYUqWLInz58//9rUBol3CNm2G6NkzvmxSogRsu3eHJjExMEFwQjBfXvd0Hep71IdA78dzoE89C8Co/U/A5gG1XXMLp4dX49eYCCFamsGQL18+3mshMTGRr+/evZuXe/D09MxwX7adZTwQYNOmTbwR9ogRI3DlyhVeSor9/88///Dt7PbfxQb1lvXrI8/JE7Bq3Uq2PfbiRXg1aoyI3buRKsncjKQ/pS8UYHqzIpjSpDDSSr0mJAMhsYkIiZF+hSX5IjnHGsTbLUdoQuDX7XE/bu5DCCHqXje3T58+KFKkiFxwgaW4X7hwgc9E09TgAiu75z9yJALGjpMFF4wKF4LHoYOwad9O7YILjFAgROv8rfmyrZE9Vp2LQYwoha83Lu6M9uXcVLyHhBCiel0q5uZ1rS2MpBN+ksWpCI1Nko3NQ2KTEBafwv+XbfsyZnezdMO8GvMy9Ga45X8LLY61wPDLw+ET5aOiv4woY6JBzLHjSDyb/Vny2or15GKZC2/evOHrxYsX52NGW1vKCCJA4rt3CF2+XFYayZmVRhIKNerQlHIsxcfjzfI0w+b6m38aXLj0OghDdz/iwQWmfblcFFwgRNsDDHPnzsXVq1f57Ht7e3uMHTuW15BOn71A5LHgQa9evZCQ8P00L7ad3f4nQQZGaGUFl5kz4bZlCwxySy+eSGJjEThtOi9pkfil/reysYtNPap4YEO3srKkhfSMnA9DT5ACoeknGFg/yJZ9IoQQZQgPD8fo0aN58H3Dhg18pieTP39+7N+/H3fv3uWlkjRV3J278GreAtGnvqQ16+nBrncveOzZA6PvTCxQJ6yRc/8i/0Os90BERknHKKwkyOJ2JfnsXUIIIUCN/A44OLCybGLQn2C9GZY8XMKXL366CP9YfzrEWiL+9m0ET5yI+NlzkHD3rqp3R+MFBwfz8SErm8kULVqUBxfYNRZCMpZGGqb24+4XoS8w8/ZM/jmQ3qSKkzCz6kzYGP84K+fG+1D03/EQKV+iCwNq5sHgvygLjhCtDzCwMg/sg5CVPpo0aRJu377Nmz2TH5dFGjx4cKYOz5AhQ/j9/5RZxQrwPHoUdn36sDQSvi3h4UN4N2+BkFWrkJqUPZkCfxXMAWvTjCltIv/WEIuckRLngaTQr/0jCCFEU8THx/OSRyx7b/78+RCJRHw766uwbt06vHjxAq1bt1bL2f2ZwT4nghcuwqfu3ZESEMC36efIAbfNm+E4ahSfSaVufKN95dfD47HjfE6ERUmbOLMeQSs6loKBUOFDI0II0Wj5c1jAxvTP39f1oIfexXrD3dIdFZwqoJJLJYXsH1EtlrEQsmKlbD1i9RrKYvgDrJdlnTp1+FiRYT0rL168SBM2iUzYxk0QPX/Ol01KloRt925qfXR2vNyBjqc6Yu+bvTj6/qjcbT/LWmDu+4Sj99b7SEqRBia6V3bH6HoFNPYcihBtppSzaDc3N/Tt2xfDhg1D+fLllfErtMbWrVt/mLnwvQtW27ZtU8jvFRgbw3HkCHgc2A/jIkX4NhYBD122HN6tWiE+XdNRZZdM+lZqsj3ifQZC5NeJ5V3I3ZYolpbeIoQQdZScnIw1a9Ygb968PHsvKiqKb2eN+ObMmYN3797xUkn6+gpvgZRtEr284dOhI8LWr5d2/2SN2OrXh+fRIzyArY4XPlgj5yZHmvAZs0xglAgdN9xGQJQ08FPewxbrupSFkb5mpZYTQkh2ESgghYFdEPo799843Oww5lSfk+EC0cj/RmLDsw1ISKHmnZqWvZDw4GvWuejhQ8TfuaPSfdJUrA8jy1x49qWufqFChXDp0iU4OjqqeteImhC9fYuQFSv4sp6REZz/Vf/SSKVylJItX/l8JdPf9+xzFHpsvoeEZDFfb1c2FyY3LkzBBULUFE3TUzHW0FmZ9/8V40KF4L53DxzHjOENOZnEd+/xsWMnaVPoWGk97WyXaoBUsbncJomBHxocbIDLny6rZp8IIeQHWOmjffv28R4LAwYMQMCXWf3GxsYYM2YMvLy8+P+mptLZ8pqIXaiP2LePB6FFX2bVCUxN+YlNzsWLILS2hjq6H3Qfix8shjhVjLFXx+J9+Gd02nAbvuHSC1glc1nzGuMmhup9ckYIIdpCX6APexP7DL0Zzn08h6UPl/JAA9HM7IU07AIo9WLIellNlrnw9OlTvl6gQAEeXMiRI4eCHi2i6diE0IBx49mMpnSlkTygbr597RexK4L+xftjRpUZWFxzcaZ+xpvAGHTZdAcxidIeaU1LuODflsUUEuwmhCgHBRhULG12a2ZFRkYqfB/09PVh16M7PI8fg1nlytKN7ELSjh3watIEMf/9B5UTJCLZditCEkIw9PJQ3PS/qeo9IoQQ7vz58zxbr127djxDgREKhTxT4f379zxzwcbmx3VFNUFKRAQ+Dx6CwMlTkPol6864RHF4HDkM65Yt1HomUTmncuhWuBuEekKMLj8aeWxy4q+C0pmARVwssbVneZh/aWBKCCFENXxjfGEkNOLLnQt1podBQ7MX0iTcf0BZDFnAyiCzUtOPHz/m66x3FwsuODk5Ke7BIhovbONG2SQfk1KlYNutK9RJiiQFh3wOYcDlARBLpFkHaQaUHIDmeZtn+pwhLC5RVhaJ9Uhb2LYE9UgjRM3RGbWKWVlZZen+rMyGshjmyoVcGzcg+tgxBP07G+KoKF5b+3P/AbBs2BA5xo+Dvr38bKNskyqAIDE/xAYhqOhckddtJYQQVbp//z7Gjh3L6+Kmx3orzJw5k8880wax12/Af9xYiENCpRsEAtj37w/7Af2hZ5Cxj446GlF2BBp4NEARe2lJwPENC8HVxhRNSrjAykQz/gZCCNFmbQu0RXXX6jjrczZDb4Y34W8QkRjBzwGI+kj6/Bn+Y8f98HaWxWBaoYJaT0JQB2wCYd26dfHw4UO+zspsXr58mfftIiSN6M1bhKxcla400iy1K4009/5cHPpwiC+zfgsdC3X87Z9VOY89tvcqj003fLCobQnqkUaIBqAMBhVr1qyZUu+fVWwAaNWsGTxPnYRl48ay7dGnTuFDo8aIPHRYNemuqQbQj2iFRTUXYXa12RAK1OvDlBCiO96+fYs2bdqgXLlycsGFv/76C3fv3sX+/fu1IrggSUxE0OzZ8O3dWxZcMMiZE7l3bIfD0CFqG1zwifLB7YDbGRqLpgUX+LqeHrpVdoetmfo1oyaEEE0nlvzeuYKTmRO6FemW4YL0/Pvz0edcH/Q91xdRiVnL/iaKxc4D4+/fx+ehw/Dh77pICQr64X0piyFz1Qzq1avHJ60wnp6ePLiQM2dOBT5qRDtKI437Whrpn+Ew8lBdaSRRigjX/a7jY/RHue3t8rfjGcOsDJ4ieumUyW2LlR1LU480QjQEBRhUrFu3bjAxMcnUfVlT0K5dsycNTt/ODjkXzEeudWuh7+LMt0miohAwfjw+9eyJpE+fkN0i4pNRxKpqhpqtL0JfYMG9BUgWSz9wCSFEGfz8/NCvXz8ULlwYBw4ckG0vXbo0zp07hwsXLvCgg7Y0kPNp0xbhW7fJtlk1a8pLIpmWLg119Tj4Mbqc7oKhl4biZdhLvk2ULEb3zfdw/Im/qnePEEJ0QkR8Ep5+VkxZ16chT3EnQNowODIxEhaGFgr5uSRrJElJiDx8hPdh+ti5C2LOneMldX+FejH8WHR0NOrXr88npzAeHh48uODq6kpPTyInbMMGiF5Kx7UmpUvDtksXlR2hZyHPUHVPVQy4MABH38v3B81rnRfDCw/Hnvp70KtYryz93LDYRMw78xrJYmlZJEKI5qEAg4qxutwrVqzI1H1TUlIwfvx4iMXy9eyUybx6deQ5fhw2XbuwKZ98W/yt2/Bq2ozXAExNkTbdya7ZUC1W3cCrgGjZtuikaIy8MhJbX25FtzPdaFYTIUQpdXFZKSSWsr5u3TrZezBb37t3L+7du8fr5mpDCQA2MzF8+w74tG6DxLdv+TaBhQVcFiyAy9y5EFqo94UdVlqDXYBis6Y2Pd/Ea7cO3PkQV96GYNieRzj62E/Vu0gIIVqPXXduv+42Lr8J/uOfVcy+GFbXWY0CNgUwvMxwCPTkT19jkmL++HeQH0sODkbIsmV4X+svPoM68eWrLB0uymL4vpiYGDRo0AC3b0szLnPnzs2DC25ubvR0JHJEb94gZNVqvqxnbAyXbCqNxLLFzvmc40He9PJY54EkVRoEuOF/I8P31XetDw+rrGVXRMUno/PGu1j13wcM3vUQiSnZd72LEKI41INBDfTs2ZP/P3jwYCR8aZ6ZnqGhIQ8uSCQSrFmzBmFhYdi+fTuMjKSN0JRNYGYGp/HjYdWoEQImTeYXnVJFIgTPX4CokyfhPGMGTIp8LT2RFXbfK0+Rmsr/VoFAwIMaEkkqohKSkSJJRVB0ItquuYW1XcvwunzvI97zi0mMtZE1zWoihChMfHw8li9fzps0s/q4aVjDvSlTpqBXr14wUNMyQb8jJSQE/uMnIO7aNdk207Jl4TJ3Di+NpAlGlh2JzzGfYaJvgqmVpmP43ke49Fp6gcvG1JA3dSaEEKKcMTtSgShRMg/uxieJ0XvrfcxpWQxtyub67UPOgvdVc1ZFZZfKvNzdt1nMPc724E2hexTtQecBCpTw7BnCt21H9JkzsrIsacyqVYMkLg4JX3oG/ErErt0wq0j9M9LExsaiYcOGuHnzJl9nQQUWXGBBBkK+LY3kn640kuM/w2Ho7q70g8RKHzU90pQHEprmaYriDsVlt5kamKJlvpb8/6ouVf/4d8UmpqDb5ruySaTvg2MRlyimskiEaCCVBhiEQiGvL8iaYWZX6R91DjK0aNECW7duxdGjRxEaGgp7e3s0b96cHxuWOtmyZUt+wYvV92Yzag8fPgxzc/Ns20eTEiXgcfAAwjZuQuiqVUhNSuKzWHzatoNt925wGDwYgkyWe0pzZnj1DNuSkpIQHh4OW1tbHlxh4hJTMGjXQ/z3JgQx7ENo012s71oWNQuUxr7G+zD/3nxMrzI9w6wmQgjJKhbQ3bx5M6ZOnQp//69ldaysrDBmzBgMHToUZmZmWnVgYy5dRsCECRBHREg36OvDYcgQ2PXupXYN5H6G1XxdUHMBhNDH/w48w6lngXy7pbE+tveqgLyO6p2BQQgh6iqzY3aWcTzl2HPsuP2JL//vwFOExSWhf408f/T7vzfGX/xwMc9YW/9sPfLb5kd99/p/9Dt0HbuYGXP+PA8sJDx+LHebnqkprJs3g03nzjDy9ETc7Tvw+9+ob34AeMAplU3KkEhnOAvt7GDT8fcbvWqbuLg4NGrUCNevX+frrBwSCy6w8kiEfCt03TpZ1pBJ2TKwUXBppOD4YNzwuwEbYxvUzFVTtt3Nwg22xrYITQjlt7NAQ/r34IkVJyrk9yckidFzyz089pVO5HKzNcXO3hWpRxohGkqlAYZcuXLxD9nu3btjyZIleJjJWRA/wi6+Fy1aFN7e3hg0aFCmSw+pU7mk4cOHY+DAgRkG66z5E2smygYk7DZW67t27do4efIkD0RkF9bU075/P1jUrYvAyZN5ky+IxQjfuAkx587Defo0mFWqpPDfa2akzwMK4w89w/4Hn5HL1hQlXK35bW6Wblhee3mG73kR9oJnNeQ014yZt4QQ1ZcHOnjwICZMmMAbOadh2WIsqMCCC3Z2dtAmkoQEBM2bh8jde2TbDHPn5iWRTIoVhTpjDeZm3ZmFboW7Ia9NXtl2Q4Ehxh9+jsOPpOWQzI30sa1XBRSm7AVCCFE6oUAPM5oVhbOVCeaffcMTG9ztTBX+e8QSMcrmKIvnoc/5xbC6uesq/HfoipSICETu24+IXbsyNG1mGYw2nTrBunUrCC2/ZgGaVayA/OkyHtMHnPSOHEH4kqV8m23Xrvy+RHqtokmTJrh69So/HGyiJQsusMbOhHxL9Po1Qlev+VoaadYs6LFsMQWWQKqzvw5SkYoKThXkAgwsc6xToU78fbZKzioZsscUgZVB6rv9Pu56h/N1Fytj7OxdAU5Wxgr/XYQQHQgw+Pj48P+fPn3KG2T+qcmTJyMkJATaqmLFirh27Rrq1q3Lm42yrIZq1arxY8eCNdnJyNMDbtu2InL/AQQvWABJTAySfX3xqUdPWLVogRxjRkNoLQ0AKIqBUIB5rYvD08EcjYs7w+Z7qdpfRIoiMezSMMSnxGNGlRmo7VZboftCCNEuLIDL+izcZ0HTL1jJhx49evBMBm1suMeaxfmN+h+SvLxk26zbtEGOsWN4aTx1xvrvDLowCI9DHuN2wG3sbLgTjqaOPEg0/cRL7L77id/P2ECATd3LoWQuxX4eEUII+TF2cWpQrbxwtDCCKFmM+kWdFX64hAIh+pfoj7YF2iJCFJEhw2HJgyUo4VCCXzTThh5JyiB68xbh27ch+vgJpCYmyt1mWq4c78Fn8ddfWc5ktGzRAhGrVvNs94i9ezQuG1IZWBnkpk2b8oAC4+zszJdZPy9Cvl8aaTxLq+brjiNG8AlAWcXGxT7RPrjpfxNGQiO0zt9adpuVkRUK2hbEq/BXeBj8EPHJ8bzsUZrexXor7YFhjZwH73qEa+9C+bq9uRF29K7AJ5ESQjSXWvRgKF68OP/6Eyz7gWVBzJs3DyNHjoS2Kly4MG7cuMGDDGyG7evXr1GlShUeZChYsGC27guLoNu0awvzmjURNHMmT6llog4fRuzVq8gxfhwsGzZU6KCe/awBNTOmWPtFJvDasMYG0sErS5UOipfOwDnx4QT+yvUXnVwQQr772cECC+e/vH+lYSXpWPm+QoUKad1RS5VIEL55M4LZ7MIvNV2FVlZwmjkDln//DU3AeiywLyZJnMRTuFmAYcG5N9h8Qzp5wVBfgA1dy6G8h62K95YQQnTT93ovsN5qsUkpsDRWTA8jVsaDfX3bm2Hj8418uYlnE/xb7V+F/C5tkCoWI/a//3gZpPg7d+Ru0zM0hGXjxrDt0hnGfzD+EdrYwLJBfUQdPYYU/wDEXrnCAxW6HFxo1qwZn8yS1suLBRfy5cun6l0jaip07Tokvnol64dm07nTb/2cFEkK2p9ozyddulu6ywUYmM6FOyM6MRqVc1aWjauVjZXOG7HvCc6/lF6rsTE14JkLbBIpIUSzaUXBerFYjD59+qB+/fr8opC2Yw2gWN3GMmXK8HVfX19UrVoV9+7dU8n+GORwhOvyZci5fBn0HRz4NnFYGPxHjsLn/gOQnK6GuTIEx4jQft0tdN10F1Hx0otlQ0sPRfsC7Xl5pGlVplFwgRAi5927d2jfvj1/H00fXKhZsyZu377NSyVpY3AhOTAQn3r2QvD8BbLgglnlSvA4dkxjgguMgcAAi2ouwt+5/8aOBjtQ2K4wnyWbNhNKX6CH1Z1Ko2q+7CshSAjRLWxmaMyx40g8e5Yvk8yZdeoVWqy8gc8R8Uo7ZFc+X5EtV3fN2DtCF4ljYhC2ZQs+1G+Az4MGywUX9B0d4TB8GPL+dxku/876o+BCmvR9FyJ27oKuEolEvM9i2lgzR44cuHTpEgoUKKDqXSNqSvTqFULXfCmNZGIC539/XhqJff6woOq6p+uw6vEqudsMhAYo71yeL7NMhqA4+RJorIEzCzJ4Wnlm2/USFlg4/kR6fciClTHtWQEFnKhHGiHaQOkZDOwNj/ULYBdzwsLCMgzA2RvZpEmT/uh3LF68mM/kZxeEdIWDgwMfnLABC/ufHdtatWrhyJEjqFOnjkr2iV2cMqtQAcELFyFy716+jc1Y8WrcBA4jRsCmQ3ulpMf+b/9T+IYn8K/Wa25ia8/ycLE2wYSKExCTFAMLQ4sM9QZZSiAhRPcEBARg+vTp2LBhA2/mnKZkyZKYM2cOzw7T1lIK0WfOImDKFEiiomQ9dRxGjuD1kRVZ01VZkiRJcuvmhuY8yJCGZbCx9Oo+W++jayV31C6UQwV7SQjRFfG3byN4orTRZYKnJ4yqVVP1Lqk9Vr5u43Vvvtxy1U1s6VFeKf1xBpYciIrOFXHswzHUdZfvzRAQGwAJJDrToy3R2xsRO3byDHNJvHxQx7hEcdh26QrLun/z7AVFMi5eHMZFikD04gXibtxAko8PDN3doUsSExPRqlUrnD17Vu78XRsnsBDFYGXF/MeOky+N5Ob2y+8bdWUUPsd+hoWBBfoW7wt9wdfLfB0KdODVHCq5VEIOM9WPjesXdcL/6hXAysvvsblHORRzpesyhGgLpQYYWFChefPm/OL/j2b2/GmAgTV0njJlCu+/4O7uLuvrkBls5v/nz5/ltj179oz/n5yczBtVqQL73ezCF/v/Z4yNjXH48GF069aNBxZYw+yGDRti27ZtqsvkMDaG3YTxMK1XDyHTpyPZx4cPZlkJpchjx+A4dQoMf1FrMrN/f5oJDfLBKyQWvhEJeBcci+Yrb2BDl1Io6GQBIxjJPY5hCWHoeLYj6uSqg2Elh8FQqNjBtCJl9ThoIzoGdBwU9XyIjIzEwoULsXz5cp6qnsbDwwPTpk1DmzZteM8FdXq9Ker5L4mLQ+jcuYg5clS2zSCPJ3LMmQOjAgWQnC7Qoq52v9qN3W93Y/1f65HD4scnR8YCYGu30hAI9FT2Ga4M9F5Ix0Fdnguq+r3qNmZn5zXBy5bL1sNXrYZJ+fJaG6BW1POxZl5bFMtpiWd+0QiOSUSbtTexqkNJVPJUfCm7ojZFUbRsUaQky3/Gzb07F1f9rqJ13tYYWHygXM1xTX1dfu/5mXDrFqJ27kL8N42Yoa8P87//hlWnjjwIwPC9VsBr6NvjYNG2DURTXvDl0J07Yf+//0Gb/OxxZ8EFlil76tQpvm5vb88DDazngjaNT9Tx+a/Jf3/4ylVIfPOGLxuXLQuzNq1lzxfWJ+G6/3WEi8IxteJUue+r6FQRB94fQFxKHF6HvEZ+m/yy28o6lJUtK/u5l9lj0aeKG5oUdeQNnbXp9aDrr4U0dBzU5zhk9+9WaoBhyJAh+PDhA+bOnYu//voLdnZ2Cv8d/fv3h6enJ0aMGJHl7924cSO/sPQ90dHRCA+XdrRXxZMgNjaWDw4NDH5dn3TFihUwMzPDzp07+fd27NiRz8Tt2rUrVMbTA2Zr10K0YwdEu3axOlZIfPoUvm3bwZgNaDt1+uFMmaz+/ZZ6wJrW+TDy6Hu8Do7nJywdNtzFvCZ5USbX1+wF9vPGPhjLa3XvebsHwhQhuufrDnWV1eOgjegY0HH40+cDCyZs2bIFy5Yt40GGNGwWGfvcYO+XhoaGcrdp0/M/5eVLxM2cBUm6UnVGLVrApH8/xBkZIU5Fn3NZ8TT8KRY8XsCXh18djiUVlvASSczFtxEo4GgKV2sjaDN6L6TjoC7PBTY+VgV1G7MnP3gA0aNHsvXER48QfPEiDEqXhi7J6vORhV+WNvPEhFNeuOUTjbhEMXpte4jJdd1Rt6Dy++W8jXqLi77SOvhXP19F19xdIRKINP51mSY1IQFJ585DdOgQJB8/yt2mZ2UFoyZNYNSsKQQODmC5DPEKft18exxSK1SAnoUFUmNiEH34CPTY+Z+xMbTFjx53dsG0b9++sswFGxsb7N27lzd2VtX1BWVSl+e/pv/9Ke/eIWbDBumKsTEMR/yDiHTnJ8seLsOziGcQQIDu7t1hafg1++svh79Q0KwgStmWgmWqpdpdx/oQmoA89vI9HtiVoPBw5ZXKUwVdfy2koeOgPschu8ftSg0wXLt2DcOHD8eoUaOU8vN37NjB6xlevXr1tx6wXr16oV69ehlmQ/Xr1w+WlpawtbVV2RORzYBig5HM/l3sxCtnzpy8yTV7Ao8ZM4ZfWGPNS1U6m+p/o5DYrBlCpk1DIptplpIC0dZtEF+9BoepU2BSqpTc3dm+Rx45AuO4eNi0bcMv/GUGe6h297HDsH1PcfVdGOKSJBh+5B3mtiyKxsWcZPdrX6g93tx5AztjO/Qr3Q9mBmZQV7/zPNA2dAzoOPzu84HNFti+fTtv1Jx+1it7bx85ciQGDx4Mc3NzrX3+p6akIGLjRsSsWcsDvIzQ1hYOM6bDTM3LeCSKE2Ek/BowqGZdDU4vnBAUH4SGHg2Rw16awXD6eRAmnfaCvbkhtnQvg7xa3ByO3gvpOKjLc4G9h6qCOo3Z2VjVf8fODNtTduyEY+3aOpXF8DvPR/ZIbehmhynHX+HAQ3+kSFIx+Yw34lL10auKckvolLIqhRGJI7DxxUYMLjUYjvaOcrdLUiUQ6Ak07nXJ+t1F7d6DGBZYiImRu82wQAGerWDeoAEERsoNxn/vOKS2aI6obduRGhsLg9u3YalF/RK/9/eybZ06dZIFF9h705kzZ1CiRAloK1U//7Xh709NTsbn+QvwNJcEd/MLEFjGCZuKFJH7PKmWqxoPMLDyR6F6oXC3/fp+WcG2AtT1WGy++RFzzr7FtMaF0L6cK7SZrr8W0tBxUJ/jkN3jdqUGGIyMjHj5CWVgaYds9ikrCeTk5IT379/z7X5+fvz/qKgovo2lI1pbW3/3Z+TKlYt/fQ97AmT24rYy6OvrZ3kfWKYIOxZp2RxTp05FREQEFi1axEt/qIph0SIw37ObN/gKXrIEqfHxSPb2hn+37rDu0J7XFhRaSDMN4m7dQvgUacpfSr68MM/ChTB2rDZ2L4/xh55h/4PPSBanYsT+ZwiNS0afatLGRQ3yNEBRh6IQiUWwMbOBuvud54G2oWNAxyErzwd24YeVjpswYQIvz5eG3Z8FFcaNG8c/F7T5+Z/02Q8Bo0cj4eFD2TbzGjV4kzh9JWQSKgK7qHPK+xT2v9nP++asqL1C7vahJYdCmCREnXx1+LG48DIIIw88gyQVCI5Jwk2vSBTOqZpJAdmF3gvpOKjDc0FVJ0jqNGZnY9X02QtpRA8fIuXRI5hVrAhd8jvPR3bP+W1KwsXaFMsuSc/h5p59h5DYFExsVIiXuVMGQxiiR/EeaFOwDS+NlD6Y4B3ljaGXhqJ/if5o4NEgy4GG7H5d8jJI9+8jfNt2xFy8CEgkX28UCGBR+y/YdOkC03LlsjXo9e1xsO/UiQcYmOh9+2DXrp1WBeHS/73sYhIrXXz0qLQkJbsGwSZDltaBzCZdH6P8zt/PXsNpr4WQNWuQ9PYtLjUT4GZh9t7zGZ8TPiOPdR7Z/Zvma8qvY5R1KgsTfflsAHU9FjvvfMTsM2/59iknXqFyPkfkddTeCUGMrr8W0tBxUI/jkN3jdqUGGNhMoxs3bvDZRYrGZueHhITg5MmT/Ot72Q3sa/78+UrLoFBH//zzDy9F1bNnT4jFYixdupQ3gN60aZNKo6isubNt1y58sBswbRrirkrrgUbu3oPYS5fhNHkSzP/6CyErVsq+J2L1GlhVrZqlQaiBUIB5rYvD2cpYdsKy/OJ7NC2Rk9f4Y3JZZjxBDY4PxpSbUzC+wnjksvj+CSwhRDVYoJSVOWInbOz9jL3Hsf4+7CSOzQhI899///GsrTt37si2seAqux8LuLplokmapos6fhyB06ZDEhvL1/WMjJBj7BhYt2+v1if0etDD5ueb8TbiLZCqh7Jz9kNPnC4InGoMiUSCKYIrSBKnIirhaz3JwbXyonc1T9XsOCFEp7ALQunHqt8KXrQY7nv3qPX7rbpgx2hE3QLIYWWMSUee84DxphveKJHLCs1KKrcBs7lhxgtcyx8th0+0D8ZeG4tUpKKxZ2OoI0liIqJPnkL49u1IfPVK7jaBhQWsW7eGTaeOMHR1VY9xWu7cPHMy7to1JL58hYTHj2H6TQa7pvne39ukSRNevSEtuGBlZYULFy7oRHCBZM21z9dw2vs076lwtPlRSF6/R+jadfy2Up8NcLOwGOYG5vgU/UkuwMAa06tTc/r6S64iLO6b/gmpqXy8zs6/RCkSxIi+9sCZ2byo1gcXCNF1Sg0wsJnz1atX5401WT8GRUZtWM+B/fv3Z9jOgg4DBw5E/fr1eTp18S/Nq3QJ673ALrq1bdsWIpGIB1pYHT52vExN/7yR2Z8wyJkTudau5QPjoH//hTg8HClBQfg8aDBMypZFwoMHcjPB4u/cyfJMsLQTFicrE0w/8QJru5SRBRe+J0WSgtFXR+NB0AO0Pd4Wa/9ei+IOuve8IUQdseAoyzxI35iZuXLlCsaPH8970JQqVYpnJqSlo6dp1qwZZs2ahSJFikDbiaOjeWAhOl3A3ahQIeScPw9GefNCnSSLk3Ev8B4q56ws977dJn8bzLozC3pJHghPiIQk8defVyYGQoys+7WRHSGEKFP87dtyY9VviZ4+5YFe66ZN6YHIpE4VcsPB3AhDdj9C4+IuaFrCJduPHTsXYGVHGDcLN9Rzly/HpQ6Sg4IRuXcPIvbs5edP6Rl6eMCmS2dYN2sGgZmZ2o3T2nTowAMMTMTu3RodYPjZ35u+JAXLXChTpowK9pCok/TvLWnuBt7Fca/jfPn+5ztwHrtAVs60fsMhKF+nFIo5FJP1G1NXLLgQEpOYqfuaGwn5ez0hRLspNMDAmi1/izW1GD16NJ9V6uLiAqFQKHc7u6jAGkFnFZuN37p16wzbfXx8+P958uT57u26gs2iYAObxo0b83JRp06dwt9//40TJ07IzfhVBfaYWzVuBLMqlRE8dx6ijhzh21ma77dCVqyAKWsQ9hszwTpWcEOdwo5wtPh5M7HopGgkpEgHiTlMcyCvtXpdjCNEV7GTOBYo/hF2cve921lgmzW6r1SpEnRB/P378Bs9Gin+AbJttj17wmH4MAjULD338LvDWPJwCcJF4TjY9CDy23wNDjTJ0wTlnMqh/UpvRCdm8oTFWJ9mChNC1CJ7IU3AhIkwKlAAJgUKZMt+aYO6RZxwZFAVPrtVFdkf7ALgvOrz0L1Id8Qlx2W4sHfg7QGUzlEanlbZny2X8PQpL4MUfeYM72WXHssMYBniZlWqQE8F5XAzPU5bvx7VXVx4r4iY02eQMmaM2pZs/JO/Nw2bWFmuXLls2SeivlkKB98dxJ2AOzxLwdH0a7+Xyi6VseXFFtib2MP3xH7YvnvHt7NrHm4desBdhaWtlcXEUKnzmgkhakKh716s/ETu3LnlvtjMUXaxp2rVqjwA8e3tulCyQlXYMWcNsFlfBubmzZv8sfD394c60Lexgcuc2ci1cQOEP6iJnnD/Ac9i+F3fBheSUiSYeOQZ/CK/zjqxNbbF9gbb0bVwVyyosYDXZCWEqD79nM0QywqWscZK5rFSSboQXGAN4YIXL8HHrt1kwQV9R0e4bdqIHKP/p3bBBYY1b2bBBYb1W0jPzMBMLhWcEEI0KXtBJjkZnzp2QsKzZ9mxW1qjkLMlL3Wa3ulnAXgbJN+0WJkK2xXmge70WG+GmbdnosXRFljyYEm2fb5HnTwJn/Yd4NO2HaJPnJAFF/RMTWHTsQM8T52E2/p1vF+dKoILWRmnDRk2DEbNm8n+tsgDB6FpsvL3Ll68mN+f6AY2UZH1EkuPlVu7+OkiYpNjcdP/ptxtZXKUwYEmB3Cy4DKUWHWZbxOYmsJ51iyVvJYJIURRFBpKZBd1VM3d3Z3PMCJfL7ixPhgse8HLywvPnz9HlSpVeHZDXjUpm2FWuTKvE5oQGvrd2/8kiyE99rwYc/ApDj/yw/mXQdjSozw/mWEMhYb4X7n/ZfiegNgAvAh7gTq56/zR7yaEZM3WrVszpJ//TOfOnfn3qLKhfXZK8vGB3/9GQ5TuApZF3bpwmjaVB29VLTAukM/cqpqzKko4lJBtZ++lro9c+eyt1vl1N8uQEKJ5InbvyfR9JXFx+NStO1xXr4ZZhfJK3S9tde1dCC+bZGooxIZu5VDew1Yl+7H3zV6IU6XlS5zNnJX6u1IiIhC5dx8vI8RKyH5bZtamc2dYt2oJoaX0/EVTxmnx8fGY/+Ah+gmFEIjF8Nu8CZesLMEuybJ67em/WA/BzGxTxH2z8jNYxYWs/L3btm3DsGHD/vAoE3V20+8mNr/YzMssLy6/GPZ2XydMVnGpIiu59i123SGfuQd8JrSSlUZyHP0/GLqqT38FQgj5HUrNVWKz5wsVKgQHB4fv3h4aGoqXL1/yWfVEeVjmCAsysL4UT5484WWkWJDhzJkzvHa5WswIe/z4h7enZTFktRfDt2ISU/A+WNr4NCg6EW3X3MLarmVQOc/3syeSJckYdXUUnoY8RceCHTGy7Eg+ICCEKF9ak7zM8vPz04ngAguURh08iMB/ZyM1Pl42m9FpwnhYtWypFuWCWFC248mOfDYXa1CXPsDA3kNPtDgBoUC+XCIhhKg7m44dEf/oofzGVOkFUv75o/dlPToaqUlJkMTHw7dPH+RcugQWtWqparc11s7bn5AiSUW0KAWdN97B0nYl0aCYci/wfw8b/7PsupNeJ9Eyf0u526ISo/jnmhB/9pkmevMW4du3Ifr4CaR+UyLQtHx5XgbJvFYt6H1TaliTxmnLt22Fi5MzmllZwTAyCmt698HlOOl5mTZix4cCDNojUhQJEwMTnombJiY5BrcDbvPl+6H3Ucnja/a0h5UHTrc8DVeL7zdbD125Conv3vNl00oVYd2undL/BkIIUTalXo2pVasWnyn/IxcvXuT3IcrHyiSxDJNq1arx9eDgYNSsWVOuIZU617MNmjf/jzNTLI0NsKdvRdTI7yALOHTbdBfHnvj/sHYiCy4wbGbCt6mPhBDlYb1jsiIyMhLajs1s9Bs6DAETJ8mCC8bFi8Pz0EFYt2qlsuDCt++NhWwLyWZ5Xve7DlGKSO72nwUXWBk7UbJ0NhchhKgTs4oVkP/aNbkv90sXYX3oIP+fb7t+DQUePoBVixb8e1ig4fOQoYg6cVLVu69xlnUoheYlXWSfDQN3PcTWm9Jee9mJ9WNok78NttTfkqE3A+sp1PhQYxx6fwhiSdY+u1LFYsRcvIiP3brDu1kzRB04KAsu6BkawqpVS3gcOYzc27bCok4dtQou/M44jdkd+bVsUAcba2gzXRiX6oK7AXfR6WQnVN9bnY9p06voXBFCPSEK2BSAjaF89jAbk/8ouJDw7DnCNmyQlUZymTlTLSYIZUVEXBLiEuV7whBCiFIzGH51QZilH+rCjFN1YW1tjbNnz6Jdu3Y4fvw4oqOjUa9ePezduxfNmknrYqprPdvEly8RvnUb7Lp3+6PfZ2akjw3dymLcoWc48OAzksWpGLr7EYKiROhdzUPuw/0vt7+wuOZizLk7h/dmMNb/ebNoQojiWFlZZfn9TZvF3bwJ/7HjkBIcLN0gEMCuX184DBwIPQP5Cx7ZgX2+3wm8g31v9vFsr+V/LZfdJtATYECJAbxRZuM8jTP13smCCnvufsK6q16IEdEJCyFEc+np68N51kwIzM0RsX07r53v/7//QRIbC5v2NEs1swz1BVjUtiRyWBlj7RUvsNPKKcdeIDBahNH1Cqj8ghzrzXD43WFePmnNszWoUKWC3O17Xu+BlZEV3CzdUMSuiGy7OCaG9yCI2LkTyZ8/y30P66PE+itYt20LfVvVlIRS1jgtf/78GDRiBGJ37YJ5UDCqmpljz+LFSHFw4NcDvv0SsnJKmdiW1e2/+zNq166dpXLQ2j4u1UasvKeJvgl/3aZhGUpPQ5/KSiLVdqstu43d70q7KzDRM0F4uLS/2K9IkpLgP25sutJIo3n5M03xOSIeG655Y+89XyTQhCBCyDeU3s79Z4M/1nTY/gfNfYlymJiY4NChQ+jduzevnZmYmIiWLVtiw4YN6NGjh1rXsw2eOxeGuVxhUfvrB/vvYA3k5rcuDhcrYyy7JE1NnHXqFfyjEjCpUWEIBHpy9cJruNaAgVD+Al5IfAgfVFDJJEKUgwU9s3Iip6ogqbKx2a+hCxYiats22TYDFxe4zJsL07JlVbpvC+8vxOvw19CDHvxi/ZDT/OsJUrO8mXs8YkTJ2HH7EzZe90JobJIS95YQQrIPa9SZY/w4CC0sELpqFYvKInDqVEhiY2DXuzc9FJnExuTjGhSCk6Uxpp94yYMMq//7gKBoEea2Kp6hKXR2MjcwR/O8zXH4/WF0lVSE4OJVpLZvz29LEidh1p1ZfJmdR6yovQKJ3t6I2L4DkUeOYPlfIiSUB1zyCtDpPwmMSxSHbZeusKxXF9GSeEj0TaBt47SBAweib79+iLS3R8CEiXxbzQQRcnTqBE1A41Lt9STkCabcmIIPUR8wvsJ4dCjYQXZbUfuisDW25SWPCtoVzPC97HpAUlLmx6+hy1cg6f0HvmxWuRKs27WFJngTGIO1Vz7g6BN/iCXU75QQkk0BhqVLl/KvNMOHD8eECRMy3C8iIoLPoO/Zs6eid4H8gr6+PjZt2sSDOwsXLuS1Y9njwHpi/O9/GRsdq7SeLYv0x8RIU4ZTU3maufOMGbzB2Z8GvkbULcBnRU068hzsc3LzDR+ExCRieYdScoGxb4ML7KRh8KXBfAbvwhoLkcsy1x/tCyEko6wM1k1NTdGt259lN6mjpA8fEDPqfxB/kJ6IMJZNmsBp8iR+0Sq7sPe6l+Ev5WZgsvdIVjJixu0ZyG2ZG0FxQXIBhsykVm++6YMtN7x5fe00QoEeDAR6EKVQSTpCiGZj75MOQ4dAYGHBJ8kwwQsWQhwTC4fhw1Q+A1+T9KjiAUcLY/yz9zGSxBIceujHx+yrO5eBuZHS58t9l4OpA6ZWnoq2ySUgHjAe8ZKjSPD0hFG1aggXfZ3NbBWVgk99+yLu6jXZticeQkSZ68EjwQITBqyGSYmvvYomXpyI/z7/xy9cXm5zWe485HHwY/jG+MLOxA4lHUrC1MAUqpy09jvjNMuGDXnpW0lUFCIPH+avBUEWfpaqsP0fP358pho9a+u4VNOx8SzLPGJZCs7mX/u5OJg48OBCWpZC+gCDvkAfF1pfyHA94HckPH2KsI0b+bLAzIxf01D3z4F7PuFY898HXHz9JYP6CxtTAySmSBCfRGVNCSFfKXxExtIBc+fOzZdZM2E7OzvkyJFD7j7sjbRo0aKoWLEi/vnnH0XvAskEdvF+/vz5vAH32LFj+bbRo0cjJCQEc+fOzbYPu7R6tt9eWGRphra2tjA0NESqRILgefMRvmULizwgYMIEiCMjYNer1x///k4VcvMTliG7H0KULEEpN5tf/u0rHq3Ay7CXfHn67elYX3f9H+8HIeTr4H/y5MmYOXNmpg/J8uXLtSoVnR2DiF27+PteWj1mVmrDacpkWDVpkq37cvHTRSx7uAxeUV7Y32Q/Ctp+nb3VyLMRn9FVNkfZLH1msL43Yw8+lTspYaUw2pZ1Rb/qedBy9U2IYuSbXBJCiKay69EdQgtzBEyewsexYWvXQhITjRwTJ/JMB5I5jYo7w87cEH223eel9KISknlfbVV/XpuuO4iELzHxiNVrYFW1KizEhpiv3w6fbpyH3bsriPP9+j16NtYQm7JJFElwzlNMLrjAhCSEyH72txc1T3idwN43e/nyyRYn4WbgJrvt6uervGyhvYk9v0BawLaA7DZWyjBFksIvrCrCokWLMHLkyN8ap7FggnWLFvy8jjVEjz55EtatW0Pd2djYYMWKFeiVifNPbRuXaoN3Ee8w8OJAXgapd7HeGFZ6mOw2F3MXPomGBe5q5qqZ4XsVEVyQJCbCf9x4/hnAOI5R79JIiSlidN5wB/d8vvZNYXJam6BPNQ+0LZcLNeb/RwEGQohyAwwsWp8Wsffw8MCcOXPQtGlTRf8aogDsgtCYMWN4EKhfv348a4AFHcLCwrB27Vqe6aAO2MkX+xAW2tkiZOEivi14/gKkhIXD8X+j/jgY8nfhHNjVpyKuvg1Br6oev7x/2wJtcS/wHj5Gf8SUSlP+6HcTQr5KSUnBgAEDeMk2hr2227dvjyNHjnx3xhibIcZO4rQpEy4lNBT+EyYg7spV2TbjUqWQc/58GLpm/4kIuyjBggvM/jf7ManSJNltZgZmKOdULss/s0AOC9kJiamhEJ0quKFPNU84Wkp7NdiZGWb8ptTUr5lt6d7zv3tfQghRM+wCKgsU+/1vNJCcjIhduyGOjYXLv//yng0kcyp62uFA/8qYcuw5VnQszXurqdK3veREDx/C758RvG9S7uhoSKfcSRkVLAjbLl1g2bgRbhkZIT45HiKxKMPPrOBcgQcJvleGNSwhTLbM7vPtBdQrn6/w5YYeDeVuexj0EL3P9eaf2yPLjuQZiLJ9ThHhjM8Z/vNYRmIuix9nZrOgB5uYNm/ePLnSQefOncvSOM2mQ3vpxDEA4bt2wapVK7Wfyc2k/R2DBw/WmXGppmHN1tlEQCN9I+S3yS/bzrJs014/N/xuyAUYmN2Ndiv1ORi6YgXPTGbMqlSBdZuvr0F1ZKQvhJWJgdzYvX9NTzQu7iIrTUfjdULIt5Q6KvP29lbmjycKwvoxsGyBDh068OwBVj6JZRDs3r0bxsbq0diYfeDb9+kDfRsb2Qyw8E2bII6IgPOM6X98clbazYZ/fSs4RsQzHNJztXDFtgbbeColW/524K0JA2RC1A07UevYsSMPJjAGBgbYvn07b0rPSuqxnjFHjx7lpdxYebfmzZuja9eufEaZtoi9cgX+4ydAHPblAoJQCOPu3eEyeBAMlVw+IDYpFie9TqKIfRFebzZN7Vy14WjiiGIOxVDXvW6Wf65XSCzeB8eibhEn2bYCThZoXcaV98FhZS9svgkSnBlePcPP+TazjRBCNI1l/foQmJri89BhSBWJEH3sOCRx8ci5aCEERkaq3j2NwT5D9vStlGF7UoqEZ8NlFzbmD1mxMsP2mDNnvq4IBLCo/RdsunSBablycucIrLzR90oc/VPmx9n9vYr1wl9uf/ESTN9+b0xSzA+DD6EJofz/uOQ4GAnln2tB8UGYdEM6eaB9gfaYUFG+tPE/l//hgYnCtoVxfv55bPkSGGB/y7JVyzCo3yBERkZmaZxmmDs3zKpVQ9y1a0h8+QqiJ09gUrIkNAELHrRo0UInxqWahmUntD7eGlGJUWji2QT/VvtXdht7vbDXjgACVHWtmuGcXZnn7wlPniBs46Z0pZGmq9X1gvikFOy754uWZVxhafw1qDCgZh6eKcb+r1XAMcM+03idEJKtAYZGjRqhdu3aqFWrFkqVKqXMX0X+EGv0fObMGT4LJSYmhl/kq1+/Ph84WVlZqdcMMCsr+I8cxZufRh0+DHFUlPTkTMHBkI3XvbHk/Fus7VoGlfPYZ0iVTF8qJG0GUL/z/dCxUEfUc6+n0H0hRJuxE1OW6XbtS7k0c3NzHD58GHXq1OHr7GSN9fNhDQK18SKzRCTi5ZBYWaQ0Bm5ucPx3FuJdXaEnFCr197MMhfYn2iMhJQEN3BtgXo15cu91J1uehLF+1t5fXwVEY+Xl9zj1LIDXx76Rxw4W6U5aFrSRLwlBCCG6wLx6dbhtWA/f/gMgiY1F7MWL8O3XH7lWruAXnsjv+RQWj04bb2NK4yKoU1i+NG92ZS+kp2diApv27WHTqZNCsw/ZBID0kwDSG15mOAaWHMhnadubyp+3sNIvf+X6C6Gi0Az9ktKCD98LTLBzmwufLvDlc9fO4d6We3yZjcF27dqFnQY7sXXnVj5TfOfwnVkap9l06MADDGlZDDk1JMCgC+NSdcf6IT4MfgihnlAukzaHaQ4YCKRjzZv+NyFJlUCg9zXouKDGgmzf1wylkcaOgYGLC9RBeFwStt70wdZbPoiMT+b9z/rXyCO7vUxuW+zvX1ml+0gI0SxKnebx4MEDjBo1CmXLluWR/VatWmHlypV49eqVMn8t+U0sEHT58mXel4G5cuUKatasiaCgILU6ppZ//41c69fLTsRiL13Cp969IY6OVtjvuPkhFDNPvkRMYgq6b7rHa4b/ypy7c/hgZ9SVUdjxcofC9oUQbebv74/q1avLggvs/ee///6TBRe0nejVK3i3bi0XXLBq1RKehw/BuHjxbNkHd0t32UWFS76XeDZDelkJLjz6FIHeW++hwdJrOPE0AJJU8CbOe++lK0BNCCE6zLRsWbht3QLhl5nO7EL1x549IY6MVPWuaaSo+GR023wXvuEJ6Lv9Pnbf/aT038lmP7NGxT9iXLAgHEf/L9tLG7KySqx5bdpF1jQVnSti6V9LsbPhTpTJUSbDGGBe9XkYXW40KrvIX0yMEEVA70unC783fvx/CwsLPimNndezYAYr85QkYT0lkCFwwS7w/oh5jeqyC60xp88gJS17k5CfYFk41fZUQ59zfbD2yVq529gM+6Z5mqJVvlY8E+dnz7/sErJsGZK8pKVGzapWVYt+I58j4jH12AtUmXMJSy++48EFZvutjxCzgTshhKhjBkNgYCBevnyJixcv8gvX7II1m5XK3vxZ42d2QZtlOFCdQvVRpkwZXL9+HXXr1sXHjx/x+PFjVK1aldfWZD011IVZhfJw27YVvn36QhwejoT7D/Cxaze4rV8H/S8Bkj9Rzt0WLUu54uDDz0gSSzB09yMER4vQu5rnd+/PBjBpqcpWRlaok1s3Lo4S8ifevHmDevXq8fcahr3HnD17Fvny5dP6A8ua14dv2YqQxYuRmiwd2LPsLOfp02FZ70spoqSMJ+x/4m3EW95HISIxQm4WF5vd1bNoT/jH+qNV/lYwNzTP2t+SmorbXuE8Y+H6+68zIRk3W1MMrJkHLUqrbyM7QgjJbiZFiiD3ju341LMXUoKCIHryVDqO3bhBIeNYXWJhrI8a+R3gHRrHg9rjDj1DYJQIw+vkU0oZklSxGAFTpiLxJxPmEh49QvydOzCrWBHqjmU3NPBo8N3bJFESSBZK8Mb3DZAKfv5++vRpXpmAffaz2eMh8SFwt3LPMMOcXQC2MbbBjCozMmRNMCw707p9e4QsWsTHQZEHD8G+bx+l/Z1Es7DJLncC7/Dm5OkrA7ByXez5xvossIl9rJdJ+nJhPysxlt0SHj9G+GZpSTHWg0fVpZHeBMZg7ZUPOPrEXy6QwPqhtS/nhl7VPCAUqE/pJkKI5lF6Z6zChQvzryFDhvCBCLtgzYINrM4/q/G/Z88eCjComfz58+PGjRs8yMACRO/fv0eVKlV4kKFo0e+n5arq5Mx910586tUbyX5+SHz9Gj4dO/GTM0M3tz/62ax50YI2xeFibYzll97zbTNPvoJ/pAgTGxWC4JsPX3aBjs38YbOCDAWGcDL7Wm+cEJLR3bt30bBhQ95UnilRogQ/aXV2dtb6w5UcFAT/sWMRf+u2bJtpxYpwmTMbBk7Ke+9gNZbZCRnDmtulb+TYOv/vzah64huJ6Sde4sHHCLnt+RzNMahWXjQu7gz9L83gCCGEfGWUJw9y79yJTz17IvnTJyS+fQufzp2Re9MmGOSkoGxmsTH5lCaF4WxljNmnX/NtbFZuULQIM5sXVehnUJKvL/zGjOXNnH8lZMUKmFaooFa11rPi9evXfBLIp0/SjBBPT09+Lpgnj7SECvu7flRyZu2ztXgfKT1/mn1nNlbUXvHd+1m3boXQ5culAYY9e2DXq6fSy0ISzWjUXO9gPUQnRfMMm29LDzfP25yfc1d1qcpLeapr+dP0pZFyjBsLAxWd44iSxRi08yEuvg6W225jaoDulT3QtVLuDP3QCCHkd2TbWT8rs8OCCaxE0ooVK/iFa319fVSqlLFJF1G9nDlz8pIlFb/MvAkICEC1atVw8+ZNqBNDd3fk3rULRl9mPCf7+vIgg+i19ATjT7CB88i6BTCrRVGkxRM23fDGkD2P+Af199R2q41qrtXktrGZFaufrEaiOPGP94kQbcCyFP766y9ZcKFGjRo8w00XggvR587Bu2mzr8EFAwM4jh4Nt00bFRpc+BzzOcO2tvnb8v9tjGzgE+WjkN8jSU2VCy4Uy2mFNZ3L4Ozw6mheKicFFwgh5CdYCR2WySAbx378BJ9OnZH4paQGyfyYvV+NPFjSriQMhNJB+557vui3/QFvYPqn2CS5iP374d2seaaCCwzLrmZZDJo6CYRlsKcFF0qWLMknn6UFF36lbu66yGudF6b6phhbfuwP76dvawvLhtLsiWR/f8ReuaKgv4BoAlZG6/iH49j5aqfcdqFAiNI5SvNln2gf+MVKy3Ol6VCwg7SkV87KGcqBqYuQZcuR5O3Nl82qV4NVy5Yq2xdjAyFEKV+vXeS0NsG0pkVwc2xtDKuTj4ILhBDNCDCwBsHDhg3js97ZhaPOnTvj4cOHvGbjyZMnERERwcvxEPXEGlZduHCBN3tOa8TK6qKfOnUK6sQghyM/OTMpLR2IiEND8bFLV8Tfv6+Qn9+pQm6s7VIWxgbSl8vJpwHotukuohKkZU1+ZdadWVj1eBW6nOry3Yt+hOiSnTt3onHjxoiLi+Pr7POA1fJVp2byyiCJi4P/xInwGzqMN6ZnDPPkgcfePbDr2QN6AsV8HN8LvIeeZ3uiwaEGsmyFNKwEwtxqc3GhzYUMgdDMSBZL8DYoRm5bKTcbVM1rj3LuNtjSoxyODa6C+kWdMmR5EUII+T4DR0fk3r5N1ncnJTAQHzt3geil/Hs4+TUW2N7cvTzMjaRJ+mzGbsf1dxAW+/uTfFJCQ/F54CAETpoMSXx8lr43YtduaBqWpZB+Egjrx8d6YzllYRJEAZsC2Nt4LzbU3QBXC1e526ISpWOg9M2eNfl4kd/X7XQ3jL8+HisfreSlkNJrnqc5+pfoj+0NtvPmzZok/tEjhG/ezJcFFha8/Gl2ZTKxsfrhR5+RkCQ/GXJAjbwo6GTBg7D//a8mulV2h4khZQsRQjQowNCiRQusWrWKz3o4ePAgQkNDeYBh/vz5aNCgAcy+NOkl6os9RixQ1OHL4C8hIQHNmjXjFwnVidDKipdGMq9Rg69LYmJ46aSYS5cV8vP/LpwDO3tX5KmEzB3vcKy7+uGX3xcYF4jLvtJ9CIoPgpHQSCH7Q4gmWrJkCQ80p6RITyL69++PvXv3wtg4802ENVHCs2fwatkSUQcOyrbZdOwAjwP7YVy4sEJ/F2vIyIIMzP63++VuYzVqG3o25E0gsyIxRYyddz6i1oL/0GHd7QwnLWu7lMH+/pVRs4CjxpaCIIQQVRJaW8Nt0yZeUodh/cVYT4b4Bw/ogcmiqvnssbdfRThYSMfcj30j0X/HA56FkFXR58/Dq0lTxF7+cj4hEMCycWMI7e0hdEj3ZW8PPVvbDNttOnbUqMePlS9u1KiRbBJIy5YtefnK35kEwsYaxRyKyW1LSElA51OdMebqGFmgwbhECdlYKO76dST5KCbDkqgH3xhf7Hm9B4vuL8pwWyUXaSWLmOQYPA99Lndb7dy1MajkIJR0LAl9gdKreiu0NFIAK4305f0mx9ixSi1/moZlam267o0a8y7jn71PsO++r9ztVfLa4fSwajwIy0pBE0KIMij13Zo16nz37h327dvH6/jfv3+fz4hg9fy1/YKSNjE0NMSOHTtgZ2fHy1uxi4PsIiGb2TJ06FCoC4GJCVxXLEfAxImIOnoMqYmJ+DxkCJxnzIB1yxZ//PPL5LbBgQGVefZCbjtTDKud/5ffw3ox7G+ynw+kB5YcCAdTatxHdA87qR83bhzmzp0r2zZ16lRMnjxZqy9Is0aQYes38DrM+BJUEdrawnnWTFjUqvVHP5vN9LriewVO5k4oYldEtr2WWy3Ym9jzhooVnKQXqv7kZGXXnU9Yf80LQdFfZ3/uvfcJ3at4yNbNvswUJYQQ8vuE5mbItW4t/Ib/wy9oS2Jj+WQZ1+XLYV6tKh3aLCjiYoVDbMy++S5v+Dy5cZEsjTfEMTEImvUvoo4ckW0zyJULLnPnwrR0qQz3T0pKQnh4OM/+ZudNmmjp0qUYPny4bL1fv368tLFQgT0RljxYwkvesC920XhW1Vn8cbHp1BEBEyby+0Ts3sPr1RPtMPH6RN6MmfUr7FWsF6yMvgarGns2hqu5K6rkrMJLammDkCVLZUEysxrVYaWAaxA/Ex6XhK03fbD1lg8i479WV9hw3QtdKuaWZRRr8/kWIUR9KPWqwJs3b+Dn54dLly7xLzbrffbs2TAyMuK1/VmwIS3gQNSbQCDAsmXL4ODggClTpvBtrPwVy0qZNm2a2nxo6RkYwHn2bAitbRC+dSsgFiNg/HiIIyJ447A/lcfBHIcGVoaJgRCG+pmL/rMLfSy989tjFJsUi3BRONws/6whNSHqLDk5GX379sWWLVv4OnsdsMw2lr2gzVjjeb8xY3gN5jSsBqvLv/9C397+j362f6w/L7kWnBDM6xwvrLlQdhurRXuo6SHYGNv89s9n5d+23/LBphs+/MQlDTtHaVLCBVXy/tn+E0II+T6BkRFcly2F//gJiD5+HKkiEXwHDkTO+fNhWV++0Sn5uVy2pjjQvzI+hMSimGvmZ+DH3bkL/3FjkeIfINtm3bYtcowZDYEWZt+zSSATJkzg5+hp2AQQNhFE0ed3NVxr4MKnCxCliDCs9DDZdsuGDRE0bz4kUVGIPHwYDsOH8YljRDMExAXgsNdhfHr1iY9J0z9vWPCABRgkqRI8Cn6Emrlqym5j2QnsS1sksNJI7PpDNpRG+hwRjw3XvLH3ni8S0vWG1Bfo8SyFftU9qVwpISTb6WdHs+AuXbrwL+bDhw+8rj+7WM0GLuzidFq5DKLe2AckG3Da29tj8ODBfEA6Y8YMhISE8MwGRc5w+ROslrnj2DF8pnDI4sV8W/D8+UgJD4PjqFF//EHvaJEx++bmh1CExSbxi2/f3advfic7dtNuTcM1v2uYWmkq6ntI+1wQok3i4+PRtm1b3nOHYbP6du3axfsuaLOoEycROG0aL9XG6Bka8kbObIaeIk40WGaUiYEJkABc+nSJByptjW1lt/9ucIEFEzZe98K2mx8Rk/j1c5k1zGxV2hX9a+SBu732XVwhhBB1wibLuMydA4GZKSL37GWReviNGAFJ3AxYt1Jdo1BNZGtmCFuzr5+Padl5N96H8fKn6UkSExGyeIn0AuGX8ias5JHzzBmwqPn1oqg2YefgbMLHxo0b+ToboyxfvhyDBg1Syu9jTXnZJAivKC84mjrKtrNgglHLJkjYvAOS6GhEnzwJ69atlbIPRPHGXB+DF+Ev+DJ7bPNYf20GzibCWBtZ80ADm3SnrVgwOGTy5K+lkcaPh0EOxfeOECWLMf7QMxx94g+x5GvZN1NDITqUd0Ovqh5wsabgHCFENbKtrgErlZSWyXD58mU+851hZXeIZhk4cCB/3FjQiM1OXrNmDS+XtH37dp6dog7YANm+X18IbawROHUaIJEgfOMmiCMi4Tx9GvT0FffUfxUQjX7bHvALckHRIvSu5vnL7zn78SzO+Jzhy/PuzUN11+q8Pjoh2oKVCmDNnG/dusXXLS0teT8X1ixQW7GSCoEzZiD62HHZNqMCBZBzwXwY5cuX5Z8XkhCCPR/2IOxtGP6t/q9sO0sz71yoM16Hv0ab/G3kggt/4nVgNFZe/tpbhjW2b1/ODX2re9LJCiGEZPNkGacpUyC0sETY+vV8HBswYQIkcbGw7dqVHos/aIA6aOdDXH4Tgv/VK4CBNfPwcwbWUNt/zBgkvnsvu69F3bpwmjYV+ja/nxGozlhfPdZjj43NGAMDA14Sl00MUSZWIqeUY6kMWd393S+jdC0B2l2VIHzXLli1aqU2GfLk57oV7obR10fz5ZdhL+UCDO5W7vxL2yVs3Ijkj5/4MusJadW8mVJ+j5G+AD5hcbLgAguidq/sjq6VcsPaVDPLsxFCtIdSAwxbt26VBRRYqSQ2a5tdZKpevbqsPFLx4sWVuQtESdq1awcbGxveyJvNUt6/fz8iIiJw+PBhmJubq81xt2nbljfO8x85CqnJyYg6dAjiqCjkXLgAAgX1Abn2LkQ223fmyVcIiBJhQsNCP01LrJ2rNh+M7Xi1A3Orz6XgAtEqvr6+qFevHl69esXXnZyceJPAkiW1Jw36W6wRp///RiPZ31+2zbZ7dziM+AeC36zHzE7WnoY+5cv9SvZDbsvcstvaF2yvkFlQxgZfM88qedqhtJs13gbFokul3HwWlL25egSNCSFE17CLq44jR/BSGyGLpA1Sg/6dDXF0DP7P3lmAR3F1YfiLuxsJEgju7q7F3d21UCj0xymUFlqgBYq7B2hxd3cp7q4hCXHX/Z9zN7vZQAJJ2GRlzttnyszsZHfu3ZnZc+855zvOw4by5GsmOPPYXzgXiNmHH8EvKALDfC8iYPFikSlCGFpbI8fkSbBt2VJv+zg4OBgtW7bE2bNnxTaN3Xbt2oX69etr5Hwo2OpdtC/eVTGEzADoeeIBom/dgoUe2426yKvQV1h+e7kIcinqVFS5v26uuhhdfDQaF2qMHLZZX9BY24j67z/EbNsu1g1tbZFDTdJIiYkynHrshxoFXJTSzPS+lFE8be99EQDUsUJuWJhqh4oEwzBMljoY+vTpAwsLC1FjgaLeyaFQoUIFoefP6D6NGjUSDqSmTZuKaGWSvqLv+MCBA0JGSVuwbdQIRitW4O2wYUiMiED48eN4038Aci1ZDCMbm29+/4G18sPS1BhTdt8FBROsOvcCH0Kj8VfH0jAzTv0H38TIBGMqjkGnwp2Q2zZ3itfiEuOEjjrD6CLkVKBnw9u3b8V2gQIFcPjwYXh5fT2zRxchx+XHJUvwcekyEWFKGLu4wP33mbDOQH2hkJiQFIXviNZerYWDwdTQVESEqToYvoUnvmFYfOoZrr0KxPEf66QYtMzuUBrOVmaws+RnEMMwjDbgPHAAjGys8eGX6UJ+4+PChUKCj+RA9XUCPKuoX9QNs9qVwvidd+Aa6o9ScxYgIPCV8nXLypXhMXMGTDxSlzzVB96/f4/GjRvjzp07Ypvq61EQSPny5TV2TuXdyuPoq6MwSTBA64tBYh9lMeRkB4PWcNPvJnod6iVqKUTERWBe3XkpMmsb52qstoxaXSIxKgr+U35WkUYaDxO3ZPmvzGZa7b75HstOP8MTv3DMbl8KHSokzxc0KOqGukVcYWLEc2oMw0jIwXDq1ClUrVpVpFwy+knlypVF9AtFK9OE4tWrV1GzZk0cOXIEuXOnnDjXJFZVKiPP+nV4M2AgEgIDEXntGl717IU8K5Z/c8FVonsVT7jamGH45huIiU/E/ts+CAiPwbIeFWBnkfb1/6lzgbJ8Rp8aDWcLZ4wsPfKbz4thshOSQyJZJHI4EjRYJYejq+u3GdraSuyrV3j3v/8h+pY8y4CwblAf7tOnp1tSgWSOVt9djWOvjoli8MWdi6fQrfUP9UeHYh3gYuPyzed7910IFp54isP3PyjGQdh14x06VsydopA9wzAMo104dOkiIuvfjxsPJCSIOgEJ4WHyIqJaUgNNV+hQIRfyXDgM090LYJEQK/bFGRnDaeQoePTrLeSp9JXHjx+LMdvLly/Fdt68ecWYrWAmZBzVSasCrVApRyW8C3sL+zXjEBf1HmEHDyF+3DjI7GxEYBajWUo6lxSBLi9CXuBBwAMha2Vtyjaj/7x5iHstl0ayrFULdq0yL40UEROPLVffYNXZ53gfEq3cv/T0M1ELTaGOQP8agp3LDMNoH1lqQZEUEjsX9J9ixYrh/PnzKFy4sNh++PChyFqhf7UJi+LF4blpozIqKebBA7zs2g2xb96o5f0bFc8B7wFV4JAU+XvpeSA6Lr0In5CodL8HSSadfHMS/z7+F+MvjFfLeTFMdkCFnCm1XuFcoHWSx9NH5wI5AoO378DzNm2VzgUDCwvkmP4Lci1YkCG95ndh73DwxUGRufTP439SvGZhbIG2nm0/y2zIKNdeBqL3mitovuAcDt1Ldi7ktLeApRlPTDEMw+gCdi1aiN8YgyTZvZDtO/Dux9GQxconyZmvE+fnhzeDB8NuyZ9K58ITu5z4vvZI9ArLj/ehMXrbjdevX0eNGjWUzgWSKb5w4YLGnQsK3K3dUcG9Iuw7d1ZmiL7etgktd7XEhvsbROQ8kz08Dnos+lwVI0Mj/Fj+R/xc9Wfsa7OPnQskj3rtGgLXy/vJwNoaLlMmZyqrLDAiFn8dfYzqf5zA9H33UzgXqBj9rPalvyi9zDAMoy1keYhGYmIi1qxZI3QeS5QoIRZaX7t2rXiN0Q/y5MkjMhlIAkuhwU5G7JUrV6BNmOXLB8/N3jArWEBsU8TBy65dEf3okVrev7ynA7YNqYZcDhZi+5FvGNouvoCnfmHp+vs8Nnlga2oLYwNj9CnWJ8VrF95fwI4nO3D1w1XEJg2KGEYboHo7rVq1EgUDFTVayOFgowYJMm0jITgY70aOEsU2ZZGRYp958eLIt2M7HDp0SHNgQU4JSi9/FJjyWVMrdy24Wrgip3VOFHIopLbzpM+j+jCdll1E+6UXcSpJc5rwcrHCnA6lceqnOmheSn9lIBiGYfQNm3p1kXv5MhhYWortsMOH8WbY90Kmg/kyoYeP4EXLVog4fUa+w9AQxr36YW7rsXhtmwNP/cLRdvF5PPAJ1buuJBnbOnXqwN/fXxkEePr0abi7u0PbsG/fDgZJ6gez36/D2/C3okYDZXsyWc/sq7PRbk878e/ToOSi50Sd3HXQvlB7ziihOa7ISLyfMFEpjWQxYjiMMxhURbXQpu65h2q/H8ffx58gOFJeB8bY0ADty+fC0VG1sKJnBTG/wDAMA6k7GGiyiaJY+/fvL2QyQkJCxELr/fr1Q4MGDRAdneyhZXQb0vCkmgxUh4EICAgQ62TUahMmbm7w3LABFmXLiu0E/4941b2HiEJQByQxsmNoNRT3sBXbRoYGsP2CTJIqtXPXxrYW2zCj5gyUck5ZAH3Xk134+cLP6Hu4L8LjwlO89p/vf1h/bz1Ovj6JsNj0OTMYRh2T2LNmzULv3r2RkJAg9g0fPhze3t4wM9O/4sARly7heavWYkJHYGAAp4EDkZeclvnypfl3H6M+ov3e9uhxsAeW3V6W4jWqt7K2yVocaHsA3Yp2U9u5UgZVj1VXcPmFPKOEKOpui4Vdy+LoqNpi4MLarQzDMLqHVZUq8FyzGoZ28uy2iLNn8br/ACSEsf2XGgmhoXg/dize/fCDCBIgTDzzIK/3JhQcPwb/fF8LpXLJ+9I3NAaPPuhXP/7zzz+iXl54uHzs0Lp1axw6dAj29vbQRowdHWHbtAlo2jb3q0gYwwiulq7oWLijpk9NEiiCXWSQYduTbZo+Ha3Fb66KNFKdOjBt2DDD72FmbCjs9Og4edCtpakR+tXIhzP/qysCgQq66V+gFsMw+k2WOhh+/fVXER0xevRoETFBUe20fPz4EWPGjBE1Gn777besPAUmm6GIZXIgtWvXTmxHREQIo/bff//Vqu/CyN4eeVavglWtmmKbiuW97tcfYSdOquX9XW3MsXVQVbQo7YF1fSuJ7YykCDfJ1+Sz/W/C5FJOViZWcDBLGclw4vUJzL42GyNOjsDbMHlxXQVUHHbJrSXY+2wv/CL9Mt0mhlGFMtDoOT527FjlPnqez58/H4Z6pl9M8hO+s2fjdZ++iPf1FfuM3d2RZ91auP44SilXkRZO5k7KrCO6Vz+9D3Pb5BYF8tRJFS9H4VAgyuaxx6peFXBgRA2RsUBOT4ZhGEZ3sShdGp7r18PIRV5HLOr6dbzq1QvxSTKFTMrAgJDde5RdYt+lM7x27oRFUgFhFxszbB5QBbULuWBckyJoXTan3nTfwoUL0blzZ8TFySOjKcCPxmQWFvJMa22uOUKWSpuLMsz9rxhm15otMrxVSUiUB7YwmeeO/x3l+FJBM69mqJGzBmbUmIExFcZw96ZC5NWrCNogl0YiR6/L5ElflUaioKzrrwKRkJikUyrilAwwuLYXHK1MMbphIVwYVw+TmxeDh712358MwzBpkaWzQFu3bkXHjh1FhKuDiiY1RUz88ccf4rXNmzdn5SkwGoAil+m7HzhwoNgmo5YkU5YuXapV34ehhQVyL1oE2xYtxLYsJgZvhw9H8M5danl/azNjLOhS9rOiqWHRciM/o0yuOhl/1PxD6F9+asRQ+rDqZKUq132vY/HNxZhwboIoKKvK69DXmHN1DrY83CKKdjFMeoiNjUXPnj3x119/iW1yKKxcuRITJkzIlPaoNhPz7BledO6MwFWrlWnQFFnntXsXrCpVSnFsZFwktj/ejhmXZ6TYT33SuUhn1MpVC/PrzhcOB3URG5+If66+QZ81Vz4btExpXgze/Stjx5BqqF/UTe++G4ZhGCljXrgQ8m5UqS12/4HIyI378AFSJzE6Gr4zZ+J17z6I9/ER+4xdXJB7xXK4//wzDJMkphRYmRljde+KGFTL67NJQV2EznvKlCkiq1TRhokTJ2LFihUwNjaGtmNeujTMixUT626Hb6BElONnmaGtd7fGoZeHNHSGug313+Bjg9H1QFcsubkkxWvGhsZY0mAJWuRvIdaZNKSRksgxaaJ4tqRFYqIMR+/7ot2SC2i35CIO3pU/jxQ0K+mO82PrYXj9grC3/HLAEsMwjLaTpb8ab9++FRGuaVG7dm3s2qWeyVxGuzAyMhIOBZJNoqhmMm6HDBkislfIwNWWiS7S+PT443cYOdgjiIo0JSTAZ/x4JAQFwalvyhoI6iAoIhbtll5AvcKumNC0aIYKNhVzKiaW1BhdfjTaFGiDDxEfPiu6pRqZkss6V4rXHgQ+wLr768T65CqTkc8uWeYlODoY8/6bh1w2uVApRyWUckkp2cRIE0qxb9++PQ4nyQSZm5sLhyLV1tG7Qs5bt8L39z8gS5LyM7SyQo4pk2HbsmWqz7AfTv6ASz6XxHqXIl1S3E8kf6ROCSTSbd1y5TWWn3muLAZ34I6PyJpSUDW/+hwZDMMwjPZh6ukJT+9NeN23H2KfPxfLq67dkGfNavGaFIm6dw/v/zcWsc+eKffZNG6MHD9PgbFKwNunpJbd9+eRx4iJT8D4Jhmz2TUJSVYOHToUy5cvV+77+++/hbNBVyAby6FrF/hMmiy2g7Zshdu4sUr7bNrFaXgZ+hI/nf5JBHe0LdhWw2esW9iZ2uFFsDywbP+L/RhSZshnAWpM6vj9NRdxb+Rja+v69WHbvLkyQ+jTAKA9t95j2elneOKXLG285NQz4VRQjCOMjQxhbMS9zTCMfpClDgbKVHj6NGVxIFXoNW3Vf2S+HfrhJJksZ2dnjBo1SuybPHmykMuaO3eu1sioGBgawm38eBg7OsF/3jyxz2/WLCQEBcLlx8+zBTILRTAM2nAdz/0j8Nz/BT6ERuPPjqVhpgarIrdtbrGkxqBSg9DIs5HIcshpkzNN58OnhiUZ7tufbBfrA0sNTOFgoLTk8efGi8K0ZV3LishsRv8hB2GzZs2Uxdvp+b1nzx7UrCmXGtMX4gMCxKA2/GSyZBrVbPGYPQumueROupiEGJgamqZ4PjT3aq50MFAxdlUHg7oIj4nHxkuvsPLsc3wMTy72Tqfx8ENoCgcDwzAMo/+Y5MgBz40b8Kb/AETfv4+49+/xslt35Fm1SmQ5SAVZfDwCVqyA/6LFQHy82Gdoa4sckyfDtnmzDNvzGy69wsKTT5W1GWZ3KKUWmz0rodqG3bp1w44dO8S2iYkJ1q1bhy5dukDXsG3WDL6z5yAxJATBO3bA5YcRIvs8XhYPN0s3ZeBU47yNNX2qWs+r0FfwtE12OJoYmaB/qf4ig31w6cFiPMd8nYjLVxC0caNYN7Kzg/vUnz97rkTExGPL1TfCTvdJCgBSUDmfIwbXyc9dzTCM3pKlDoaGDRti0aJF4t/vvvsuxWtHjhzBkiVL0KFDh6w8BUYLGDlyJJycnNCnTx8RVUNRNFQAes2aNcLw1QbIOHAePAhGDg74MG0aeQMQsGKl0LJ1nzYNBmpIJ6bIp3418+HW22DExCdi320ffAyPwbIeFWCXziLQmcHJwkksFVDhs9e6FukqdDapbsOn2RFfcj6QhvzBFwfFeusCrT9zMEw8NxGWxpYo4VwCrQq0UnOLpAVFaoXt2YuYiHDIOnfW2Hm8evVKPMcfPXoktj08PESRwJIlS0KfCD97Fu/HT0DCx4/yHUZGcB46BM6DBonnAN0Xmx9uxu6nu7G0wVKUdElu/3d5vxODOMomSsvhl1mCI2Ox5vxLrL3wEiFRyZFSxoYGQi96SJ38n8mxMQzDMNKACuNSXaA3Q4Yg6tp18Rv2qmdP5Fm2VFlrQJ+JffkS78eOQ9StW8p9VtWqwn3GDOGAyQyuNmaiCGtMUiQy2exLe5SHrbl2jF0+JSQkBK1atRL1DwkrKyvhaGjUqBF0EXIm2Ldpg8C1a5EYGorQ/fth3749TAxNMKnKJNTLU0+MNSxNLD+zm7UlU17T3PC7gb//+1v8u7fN3hTjObJV2xVsp/YaYPpKYkQEfCYmSyO5TZqUQhqJnhPzTzzDxstvUtjpRKNibsKxUC5P2hlUDMMw+kCWF3mmor9U5LdChQro1auXWGi9SZMm4rVffvklK0+B0RJ69OiB3bt3CzkVYtOmTWjdujUiIyOhTTh06oicc+cK6SQiZPsOvB05EokxMWp5/++K54D3gMqwt5S//6Xngei49CJ8QqKgCcgoL+JYBA08G8DOzC7Fa1Ro+kDbA1jWcBmqeVRLs+bDp7JLcQlx2Pd8H7Y82oL9z/d/9pm/XvpVOCBW3Vml9vboI5GXLsFv0iREzvwdUUmZA9nNnTt3UK1aNaVzoXDhwrhw4YJeORdIr/nDbzPwZsBApXPBJHdu5N20ES7DhimdjE+CnmDD/Q0IjQ3FP4//SfEe5sbmGFFuhNqdCw8/hKH67ycw//gT5aDF1NgQPap44tRPdTCnQ2l2LjAMw0gcIxsb5FmxAlZJWYUU+f2qbz9R6FhfocnkoM2b8bxNW6VzwcDMDG4TJyL3ypWZdi4obPZN/Ssrg4AuPAsQNrtvaMqoZG3gw4cPQnpY4Vyg7PETJ07orHNBgUPnTsr1QG/vFDUxaGxSxjWl84ykYjvt6yTqzzEQtfeu+V5Dgizhs3EX1Vdg50L68fvzL8S9lY9/bRo2EFlRKfvTAAfufFDa6SZGBuhQPheO/VgLy3tWYOcCwzCSIEsdDJ6enrh27Ro6d+6Mx48fY8OGDWJ58uSJSNW8evWqOIaRBiStcvToUaUs1oEDB0R2S1BQELQJ2+8aiSJwigJw4ceOi7TzhLAwtbx/eU9HbB9SDbkcLMT2I98wtF18AY8+qOf91QUZnhTpQga8q6VritcquFXAmU5nsKnpJlEETJUPkR+QKEsU66npeR57dQx7nu3B3md7P3vtr+t/4YcTP2D21dmIS8xcMWx9ggZS/gsXKbeDlizN9oKDZ8+eFRJI79+/F9uVKlXCuXPn9OrZHf3oEV526ICgDRuU++zatIHxhgXwyWub4ljK1qH7wdbUFi4WaRd1UycFXa3hZit3zlqaGmFgLS+c+19dTG9dArkcUkbuMQzDMNKFor5zL1ooag4QsshIvBk4CGHHj0PfiPP1E237MO0XyKLkgTrmxYsj384dcOzRXUigfisV8pLNXhU57S2UDn+y2Z/6aY/N/uzZM1SvXh23khwsZJ+RnUb2mq5jmjcvrGrUUBYxj1bJUPkUGntMPj9Z1Jfrc6gPTr05BSlB44Po+JTOL6pN4WrhilLOpdDQs6HGzk3Xibh0GUHe3mLdyN4eOX7+GU/9woX8sWoNl/418go7vX+NfDjzv7qY3aE0CrjaaPDMGYZh9EQiiaRw3r17B2traxGtLibK/P3Fa1T4l1MXpUmNGjVEdA1JrVC0DUVB16pVSxSMtbCwwNq1a0WmA0kokawSZTlQ1ovDF4qyZQVWVaogz7p1eDNwoCj4HHn1Kl717IU8K5bD2Nn5m9+fpEx2DK2GPmuu4t77UKHR2HjeGRElZWKcNCCSyZCYmCivVaGS6utkZYpDI2tpvviauYNYPoWcCte6X8O7sHdC41MV0q0PjwtP0/lw2ecy7gfch42JDcZUGIM4SNvJQNkLUdeTo7Ci//sPkZcvi+szO6B7kRzEpOlL0H27bds28VzXB2SJicKp4DfnT8iSCrSRXrPV1LGYZnIYFw63R73c9TC/3vwUjrfF9RcLLVvKWFA3z/3DsfPGO/zYsFCKQcuohoXwxDcMfarng4OVqdo/l2EYhtEPDExNkfPPOfCxtkLItu2Qxcbi7Ygf4PH7TNi1SBkUoquEHjyID1OnISEkJFnOcNAgOA8ZrMxCVhc0QUg2e+81V/HAJxTvgqPQ8K8zsLM0gYmRZm32GzduoHHjxvDz8xPbJUqUEPKVOXPqj6a+Q9euiDh3TpnFkDMNyS+aXCfJJIJqYFX1qAopQHMsZ9+dxdJbS1HUsSgmV5UXxibMjMzg3cxbBMbw3It6pJHCBo3EgL3PcfKRP1b1qoD6ReX1QIhWpd3RrHRO2Fuync4wjDTJMgdDXFwcvLy8MHPmTPz000/iR83VNWUUNCNNSpUqhfPnz4u0XYq6uXv3rtgXHh6OmE+kiMgZMWHCBCxcuBB9+/bN1vO0KFkCnt6b8LpfP8S/90HMgwd42a2bKJqnKPT6LbjamGProKoYsvE6zj75CIqBCP5Es1FXIYPWy94r1f1Xul2Bf6Q/YhOTC9QqiIyTS2blssn1mSFMkUlSSuX9NHtBgf/8v2FZuXKWDxRWrlyJQYMGiQEz0b17d6xevVpr6qaoI/LRZ/x4RFy4oNxnWakSPP74HcY5cuDD7nVi3+m3p+Eb4Qs3q+QBRGHHwmo/H5q0WHTyKQ7c8QEFRJXJbY+a+ZMdeFy8mWEYhkkvBkZGcJ8+HUZW1ghct44iv/D+f2NFNq5j164625HkUPgw/VeE7tuXIsrdY9YfsChVKss+l7IItw6qgsEbrgupJGGzR2rWZicJJArECkvKsKYshr1792Z7UFZWY127Fkw8PETx8rCDhxA/bpyoOZKa7Ou8uvOw9/le5LfLL8YcUoCCt6acn4KA6ACRvTGg1ADksEqWBlO1X5mM4/fnn4h7906s381fDj89tAIM5EGzS08/S+FgIPlSa1N2LjAMI12ybLaOtPZJ/5EKTDHMp5DzidJ3S5cuLbYpY+FT54KCqKgo9OvXT0xuZjdm+fIh7+bNMC2QX2zHvXqNl126CEkVdWBtZoxVvSqKInJSgZwEZOymlsFABcgudrkoBgiqfIz6iPZ72+P8u/OQavaCgqgbN/C0Xn1RzDBw4yahOayuGiEKx8aMGTMwYMAApXPhxx9/xLp16/TGuRB27BhetGqFsIsXcL2AAbzrGsN1zGjkWbMaJu7uwnnToVAHFHcqjilVp8DWLKVMkjq58ToI/dddRZP5Z0Xhd0W29daryUXWGYZhGCajiOCucWPhPGK4fIdMBt9fpuPjsuU62ZkUEPC8ZasUzgWHbt2EJFJWOhcUUHHntX0qaYXNTtmkVM9Q4Vxo3rw5jhw5onfOBYWzzL5zZ7FO2abB27anfayBAVrmb4nizsVT7H8T+kbIJj0Pfg59g7Jp+5ToI9bLupZVBmsx307w+QsI8t4s1kNMLfFbwRbKDKUiOWzQvYpntkvXMgzDSDKDgaDizvv27cPQoUOz8mMYHSVHjhxCgoWcDYqJzC8xfPhwtGnTJtuNZxM3N+TduBFvBg0Wk7kJ/h/xqnsP5F66BJbly3/z+1O0g62FCfzD1DdJrMtYm1qLRUF0QjTGnhkriusOOz4Mf9f7W+jg6zNkrPrO/D3N1+N9fBCye7dYBMbGMC9UCOYlS8K8RHFYlCwJswIFlIWJ0wvdhyNHjsSCBQuU+2bNmiWy0PSBxMhI+P7+B4L/kRdnntvGEJeLyCcK+rSqBycjI+WxXYp0Qfdi3bPs+734PEBkLJx/GpDiNU8nSwypnR9tyuUEEhOy5PMZhmEYaUATri5Dh8LI2hq+M2aKff5z5yIxPAwuP/6oE7IpiVFRosBq0MaNyn3Grq5wnzED1jWqZ+u5aIPNvnTpUjG2Vkxs9unTB8uXL4dxBm0+XcK+fTt8XLBA7mDYsgVO/foKx0N6SEhMwMTzE3HD7wY67O2AVd+t+qw4tC5AmdxUx27tvbUiEEu1Ph4FxZRwLoHybt8+LmWAmPgEeJ98gALjfoJCGHlxqbYINrdB5XyOGFwnP+oUYslvhmGYT8nSEAyamPLx8REa+nfu3FHqeDOMgp07d6bLuUBERkZi/fr1Guk8KuhE0c1WNWuK7cSwMLzu2w9hJ09q5HykhLGBMYo4FFFqqlJ0jj5DA8YPU6Yg5vHj9P9RfDyi799H8Nat+DB5Cl60boNHFSriZZeu+DBjBkL27kXMixei5kBaUAZRly5dlM4FIyMjURNFX5wLEXfu4HnbtkrnAlHbKbkA4vHXKQtgGhmmb+CaUd4HR6HdkgvouuJyCudCITdrzO9cBsd/rI3OlfLAzDhrPp9hGIaRHo49e4oJeSQVPg5YsRIfpk37ol2gDUTduYMXbdulcC7YNm0Krz27s925oA324bRp0zBkyBClc2Hs2LFYtWqVXjsXCJJEsmkiL1xOUknhp8+k+29DY0ORIJMHbOS3zy+yU3WRbY+3YfTp0bjz8Q7W3F3zmTwUOxfUh6GBAaIXzodzRKDYPudREuYNG4laLCRvXLcw17RgGIZJjSy1RqjmAkXG3Lp1CxtVDENV6PX4+PisPA1Gi6EMhoywePFiUcCsSJEi8PDwyNbIK0NLS+RevAjvx08Q6dmymBi8/X443H/7FfatW2fbeYRFx2HFmefI72qFAi42yOlgIYrA6itUVHdCxQko5FQIdXPXhY2pDfQV0kZ+P348wo+lnOxODfMSJeDQsydi7t1D1N27wsEgi4pSvi6LjhZySrQEJe0ztLGRZziUoEyHEqLOiLG7u6h/QtlBx4/LP5cKrv/7779o1qwZdJ2ACH94b5mE3eEXMDwuHlQ62cjBQdy3+WpVw/Orf6BV/lYo7SKXa8tqXGzM4BuaHPlYKpcdhtUtgIZF3WCox/cxwzAMo1ns27aBoZUV3o0ZQ8XyELxlKxLDI+Axc4baCyN/KxSpTlJOH5csEfUjCENbW+T4eQrsdMg2CYuKE9mK+V2skd/FCp5OViILIqMkJCRgxIgRYhyk4K+//sKoUaMgFah2SOievWI9yNsbNvXqpuvvHMwdsK7xOhH5XztXbZgYade1nl6aezXHghsLEBwTDN9IX+Fk0oUMJF3AJyQKOWzNlf0Ze+Uy6jySFxaPsrRBnSWzMaCwp4bPkmEYRuIOhp49e/IPH/NFQkJCMtRDjx8/RoMGDcS6tbU1ChcuLBZyOCj+LViwoJggzQpoAEaF5GiCMmjDBjHo8Rk3HglBwXDq0xvZQXRcIn478EC5Pat9KXSskFzPICA8Bv7hMcjnbKU3UdBk8HUr2u2z/YHR8sgSR/PPi73pGtGPH+Pd8BGIffUqfcffvQsTVxfYtxwntmXx8Yh59hzRd++IiL/oO3fFe9IkggLKvIm8eEksCgwcHPBfaAgK+/oizsoKb83NsXHvXlStWhW6DkW5nZg9BMvLPAfsgSNlDVE2XzUxmWLs4iKO+bnqz1n3+QmJOP3IH/WLJkc6mRgZYmAtL+y/7YNh9QqgVkFn/p1kGIZhsgXb7xrB0HIx3g4fLgIRKGAmMTwcOefNhaG5uVZ8CzHPX+D92LGIvnNHuc+qenW4z/hNyJbqEtHxiZh9OLluW7OS7ljUrZxymyaJr70KEg4IRyvTNDNMu3fvLuouEJStsGbNGrFPSpiXLg3zYsVEQE3EuXOIfflSFPhOb7BS/5L9P9v/LPgZFt5YiAmVJ8DFUm4Xapr4xHgceHEAwdHB6Fm8Z4osBaoL5mHl8VmNCSZzPPAJFYWaqQbahr6VUK2AMxLCI+AzcZLymAIzfoEtOxcYhmE072AgeQ2G+RJ2dnaZ7iCKur5+/bpYVKGJPE9PzxROB8W/VPfhW6M9DAwN4TZhPIwdHeA//2+xz++PP5AQGAiXH0dl+2RhAdfkegXEkfu+GL/jDigYOo+jpXg9v6s1CrhYi3VabMx1M3pHlej4aIw4MQIBUQFY3GCxkE/SVUL27oPPlCkpMhDSAxUes6pSRaxTvQXzwoXEYt+undiXGBuLmEePkh0Od+8g5ukzUehRgSwoCCQ6VdY5eWBlMnES3qrUczAvXhxGNtqfORISEyJS4amAeOiBA/D5eSqKhYfBKZ8Rgq0NYFWyNHJ1XwrDdOr2ZpbouARsu/5WDFreBkXBu39lMWhR0KOKJ3pVS9+gmGEYhmHUiXXNGsizepWoLUaBB+GnTon1XIsWwcjaSmOdTZPtFJnuN3uOcH4QBubmcP3fT3Do0kUvnPFeLin790NoNDosvSjWHSxNhKOBjpFnPFjD1UKGkf274+QJeYappaWlssCz1KDv36FrF/hMmiy2g7Zshdu4sZl+v7jEOEw4NwH3A+7jqu9VkeVAEkqahO6BHgd64G7AXVgYW6CZVzM4WTgpX2/o2VCj56cPUB9feRGIJaef4dQjf+V+2iZb3W/2bBGgRNg0bgzbxnJpLoZhGObr6LdgI6P1tGrVCqdOnUr38b1790aBAgXw8OFDPHr0SPwbFhb2meHw8uVLsRw6dCjFazY2Nqk6Hug9zTMQuUVGrvOQISKT4cO0X8SEbcCKFYgPCoT71KkZLq6bESjCaXb7UnjqF45n/uGfORhoP5EoA14GRIrl2AO/FMe42ZphYK386FcjeVJeoeeqKwM4iji65X9LrE8+PxkbmmzQmXNXIIuNhe8fsxC0aZNyn1mRIoj39ycBUJUD5QWYDUk7WWW3Q9euX3x/Q1NT4SCgRUFiRISI/np2+DDOrF6DAgDymKaMmiPDmpaww4eV+0zz5YN5yRJyeaWSJWBetKjWRDtGxkXi10u/4vDLw6jmVhnjj9sqC2CTEMFP/3mg7Jjf4FGiYtaeR2w8vC+/xvIzz+GnUgBy0amnKRwMLIXEMAzDaBLLcuXguW4tXvcfIAJkIi9fxus+fZB7+TIYOzhk+/nE+frCZ8JERJw/r9xnXqoUPH7/HWZeuhtA4mRlirmdyuC5P9nsEajilTxZTDz3j1CuB0XGiWwGWlSRlfseri51EH90Lg4cOIDKlSuL/VGxCbAw1Y9M5fRi26wZfGfPQWJICIJ37IDLDyNgmMmsdb9IP0TEyfs/r21esWgaGsfUyl1LOBii4qNw4f0FtMjfQtOnpRckJspw9IGvCP658To4xWu5HCzQqJgbws+dF/XsCCNHR+SYIndmMQzDMFrgYHj9+vVXf0RJysbJyUnnJgYZ9UAFwCdMmICodERuU9TO3LlzYW9vn2JSnAqJK5wNqv++evVKOWmugJwRV69eFYsqNHGbN29epcNB1fmgqCWSGg6dO4sC0O9++p+QognZth0JwcHI+eefMDQzQ1ZA9RbqF3UTS2pUL+CE+IREMZAhZwNFR30KacB/2qKHH8LQcdlFETGlyHRQZD3kdrTUujoPA0oNEAb48+DnmFljps49Q+I+fMC7kaMQdfOmcp/TgAFisPSpgyo2NhaBgYFwdHSE6SfOgIxC+stXIiLQavZshIaGin0Nq1TBuilTYPLqFaIo0+HOHcT7pXRKxb54IRaF/i2MjWFGcmQlisO8BDkxSohtTeg4U5TXg8AHiE2MxZl3Z9HxRDwU0/kOPXugyejRWXY/EiFRcVh/4SVWn38hJggU0C3TsrQHhtYlNw7DMAzDaA8kN+O5cSNe9+2L+A8fxG//6569kHvVSpi4umbbeYTs348Pv0wXk8YCIyM4Dx0C50GDsjRgJzuggIJahVzEkhruduYYUa+AsNkpaOj5xwjExqcsvG1gZAJzMzMcOncORYsWVe6vO+cU4hNlKhkPyZkP+lqfjZwJ9m3aIHDtWiSGhopsVUXWbkbJaZ0T/zT/R9Q16FykM4wMs9dZE5sQi11Pd6GRZyPYmyePbUkS9m3YW/Qu3hsFHQpm6znpIyRXuuvGO+FYoPtMlSI5bDCkTn4hXWYQFYnnLfoqX8sxZYooLs4wDMOknyy12mjCNj2TfjRxXL9+fUybNg2lS2dPoU1GO3BwcMDChQvRr1+/rx67YMGCFM4Fgq4vKvZMS926KYt9kdPiyZMnnzke6N+IiJQGBkWHP3/+XCwHDx78TMYptayH/Pnzw8zMTKROGtna4s33wyGLjBQFet8MGIhciynVPGV2QXZQr4ibWFSLQiucDYqsh2d+4SjkllLyhvaHRcfj5ptgsahCBem8nK2E1FL1/M7oWjmP2s+78bwzCIiITblTJlOJ3DdIERF2aGQtLG+4XBjhuW2Ta1DoAhGXLuHdj6NF1CBhaG0Nj99nwiapvkhWQqn13bp1E04Lggo5//PPP+I5rEqcrx+i791Nlle6cwcJqjVTqObDgwdiwb9yXWADMzOYFykCc5E1UUL8S/q4JCumLh6FPMLDDw8xqMyg5J0JCWjq4wbv2CdocDMR5nGAkYszPGbMFFIQWUV4TDwWn3yKDRdfISwmXrnfxMgA7crlwuDa+ZHXWXNyEwzDMEzWEBQUJKRgd+/ejYCAABEs1bp1axE4Q7atrkDZAXk3kZOhn6gBFfPkCV516448a1bDNFeuLP1sCsj58MsvCD2QbHebennB448/hA0hBbxcrPFjo8LK7YREGY5f/A99fhiHMANLmDjmhl3uQujZok4K5wLZH4oAoo/hMULyJTW7nZwPf3YokyWZDpmx29WBQ+dOwsFABG3yhl3btpkOMqK6BmMrfS6z9CDgAf59/C9GVxgNKxP123F3/O/gx9M/4kPEB1GweXjZ4crXbE1t8VuN39T+mVKF7qk/Dj0S94mCKl6OwkavXchFee34/DEL8T4+Yt2mCUkjfaexc2YYhtFVstTBMGXKFOzfvx83btzAd999JyZmCZrgPXLkCMqVK4fatWuLbTru+PHjOHPmDMqWJUVwRir07SuPFvj+++9TzWSgiU9yLiiOSy+UHVOqVCmxqEJZDe/evUs16yG1rBsqRH358mWxqELGs5eXl9LhUL5Na5TavQeG4eGIvHIFr3r2RJ7ly2HsnCyNkhZkeBNRkZEICQ39LPOCIAPIztZWeWx6oXoLZXLbi+VLGBkYoLiHrXA0UCFpVSiaijIcaDE0MEjhYKCU0yGbrsPTyUpkPCjqPdhZZiySnQYp/iqyMunB1MgUXvZeKc81IRabHmxC96LdYWKkXbUm6HsNWLkS/nPnUceJfWaFCiHX3/PTXajuW1i6dCmGDh2qvL5Icmz58uUwSSXrwMTNFSZu9WBTr57y3OPevhWOBkWWQ9T9+8KppmxfTAyibt0SS5BKxgTVcBDySqKuQ0mY5PTI8GCQBqwj/+mGswkPxXZ9z/oo4FAAsW/e4P1P/0OV2zdRTQYYygDrevXg/uv0LI88MjY0wD/X3iqdC+YmhuhcMY8o4uxhnzWF5hmGYRjNsnr16lRt1tOnT4usXAqcyajNqklMcuaEJzkZ+vUXdZvi3rzBq67dRJ0GswJZk4EXfvYcfCZOTJEt6dCjB1xH/6g18otpkaod/oWJ9Yxw7uwZdGjZUplhWrVqVeyb9YvIYFUlMiYe3xV3ExJLLwMiEJcgS9VufxcUJWwTVSbuvIMXHyOUWQ9eSba7u615hiQcM2O3qwOyl61q1BCFnknyM/rWLViUKaO2949JiBG1GZ4GPxUSRWsbr0UOqxxQJ3ls8yAsVi7xu+XhFgwsNRBmRlmXaSslQiLjUoxBzU2M0Kd6Xsw58kjIIJFjoWyelE5gIY30779i3cjJSWQvMAzDMFrmYChWrBgWLVqEW7duoXjx4ileu3Pnjog4/9///ofZs2fj9u3bqF69On755Rfs3LkzK0+L0UJoINamTRusW7dORIN9/PgRzs7OIhqsZ8+eao0Go4nNXLlyiYUyZ1ShzIbUsh5oiVSZSCVoIPH06VOxkIOMyGtiipW5c8PDxAQx9x/gSoOGuN68GXJXqCCcEOSQSE3ihqJ6aMD6tUyOtwB+XLUKgHqigFRpUtJdLOQweBcchadJmQ6KrAf6l+RfyHmgyvuQKBy+5/vZ+zlbm6GAq5VSaqmgmw2qq+jQZwU0CT71wlTsfb4X59+dx191/xKRQNpAQlgY3o8fLzJcFNi2bCFqdhh+kj2QFf1CGWK0KBg3bhxmzJiR7ol+Os40d26x2DZtKn/fhAQhm6R0ONy9KzIaZHFxKWo+kMONFgVUu0S1ngM5Hr7miIu6fBlF993D2SbyKLy9z/aiz9t88J3+q/gM46RikG7jxsG+U8cskczyDY2Gm615ikFL/5r5sPDEU/Ss6om+NfKJ655hGIbRT75mq5HTQfG6LjkZ6DfYc/06vBk4SAQJ0MT/q+49kHvlSiGFqC4So6JEEWcq5qz87Bw54DHjN1hVqwZdILVIfHVIWdL4t0uXLoiJkU/aN23aFP/+++9nGaaEq605lvWoINZJFvVNUJSw2Z9/JNs9WW4pt4PFZ/bQ1ZeBeOwbjgvPAlLstzAxEhkPwuHgYiUCJnLYaaezh4o9k4OBCNq8Wa0OhpchLxEYHaiUUXK1/Da5MKql8CToCUq5JAe82ZnZoUexHvAJ9xGSr+xc+HbeBEZixdnn2Hr1DTYPrIJyKk6EHlU98V3xHJ/VLVSMz3wmJ9dayPHzFI3UoWEYhtEHstTBQJNXw4YN+8y5QJQsWVJE0v76669o3769iDIfMGAA1q9fn5WnxGgx5EQYOXKkuC7UpTefUaysrFCmTBmxfOpMePv2bapZD7Rfwcu4WHR7/QorcuVGATMzOERHo9SWLRgwew6exMbAyMhISCt9Krfk5uYmouHSw/Dhw4UzJqtS8Cl6iWou0FK3cEqjOiA85rOByuuAlI4XBZSKSsul54HKAlrnxsqj4RXsvvlODGiEwfd50kaGeRv+FqfeyIuGkyZ/YFSgVjgYoh89xtsRwxH3KilDxsQEbuPHwaFLlyyvHZGQkCCuLcpeUEC1TOhe+1YMjIxEdKOIcGzTWlm4OvrxE0TfvYuou3J5pZinT4WMkfKcgoIQceasWFQnGISsUlI9B/MSJYT0mHhPmQz+Cxeh/k0Z3jonorShJ6rdeAGfQ8tTaEl7zJkNM6+UGS3q4IlvGBafeoY9t95j2+CqKSKfyLHQpWKeDGfsMAzDMLoni6QttlpWYGRnJ7IW3nz/PSIvXhISRq979ULupUtgWbHiN79/1O3beP+/sYh9+VK5z7ZFC+SYPEn5ey9VVqxYgcGDB4vxBkHBVStXrkw1w/RTjI0Mkc/ZSixAyvpsVAhaFbKnKBOZ6jOQdEyKY+MScO99qFiI5qU8Ury+/7aPcE4oaj1QQJKmsK5dGyYeHoh7/15IbLmOHau2rNXCjoWxo+UOzL42GyPKjoChQeZlPik7YemtpaJG2OF2h2FjmixPO7T0UJ2rH6eN3H8fimVnnmHfbR/lNb301DMs7yl3wBG25iZiSQ2/WcnSSBRAZduoUTadOcMwjP6RpQ4Gmnx1cUm9qBVBxXPpGAWkLUlFeBlG26CU5zx58oilYcOGKV4LDw/H48ePUzge/nj4EMNDQ1HKzByuxiZYnycPhr57ixtRUeJYWvbuTSqWm0Eok4IccT/88AOyG6dUorOrFXDGvWnfiTTtp/5hKrUeIvDyY4QoQEekFjUyfd+DFJqY30pum9zY2HQjfjj5A36u+jPy2mW97NDXCNm7Fz6Tp0AWHa2cSM81b65ao63SIjo6WtRb2LFjh/yzjY1FllDXrl2z7DMNTE1FtCMtDuikjFiMfvAghbwSaT2rQgUmw2g5ekxs38xngNdFHNDdqBoMbawRdf26KEze+xgNvl8gCi+SPtAATv37wWX4cPHZ6uTuuxCRnXD4/gdSPxAsOvkUK3slT7RYmhoD2esHZRiGYTQA/X6mJuWpbbbat0CyhrmXLhV1osKPHxcZgq/7DxBSjjSpmxkoq/HjkqX4uGyZMtiAnBk5pk0VdcykDE34//bbb5isEkE9ZswY/PHHH3K5pW/k09oLNKFNGRgkofQ6kOqzRaTIelDUYyMHRB7HlJkTpx754d/ryUFVmoQCXOw7d4b/X3+J6yt423Y4Dxygtvd3snDC7zV//2z/Tb+bQjaJsg5MDL/u/Hkf/h4B0fJMEe8H3hhUOrl+GDsXvu2+ufwiEEtOPcPpx/4pvzsrU5TObS+O+Vofk1RbcFIdOZJGcps86RvOimEYhslSBwNFZe/atUtkMXwKPfQpFZSOUeDv7/+ZxiTDaDvW1tainggtqsSHh+PZoMFIvH4ddkZGWJc3H5bb22HHq1d4//79N30myUhp06DVyswYJXPZiUWVuIREvAqIFA4HazPjzzQy1elcUEA1GXa22gljw5Sflx5DU51QJL/v73+kkAGwrFoFOf/8M8trAyhqh7Rq1UpoQiuyc8jR0EgDkTmGFhawLFdOLAoSQkMRfe9eCnklRQSRd21D7KpmCANZCLy896PE69Sj5Izc3JBz1ixYVa6k1vOlCD1yLHw6aMlpb4E6hV2z/VpiGIZhNA/ZXrpsq6UXQzMz5Jo/T9RICNm9R9RXejPse+ScPQu2TZpk6L1inj0TWQv0e6/AqmZNuP/6q6j1JGUoW4GuD6rZoWDWrFn46aefsvyzqQh0AVcbsahC9s3H8Fi8CYoUx6hCdRu0Cfv27fBxwQK5g2HLFjj16yscD1lFZFwkJp6biNdhr3H67Wksb7gcFgbJ9bbCY8NFtgMVjlbQs3hPbH+yHU3yNUGrAq2y7NykAmXNHLnvi6Wnn+Hmm+AUr+V2tMDAml7oUCG3kDD9Gp9JI039maWRGIZhtNnBQBqkP//8M5o1ayYMqEKFCon9FOU9f/58nDp1ClOnTlUeTzr2n0rTMIyuYmxtjUJrVuP9+AkI3b8fxomJGBoSil8XL4ZB3brKrAdaqFZJcHBKQ+lLZORYTWJiRAMY61SzF8xMDLG+byV5xoN/OP699uazInWZJTXnwi+XfkE+23xC8zSrJ4fjPnzA2x9+QPSt28p9TgMHwuWHEVk6+FHg4+ODJk2aiPo3BNUzoedrpUrqnYj/FkgOwapqVbEoiP/4EVF37qDoo53YhZOQGRjgRn6DNB0M7lMmq825QNfIuacfhWOBoqJUIU3ioXUKoFUZD3FNMwzDMNKDHPcZQVdstdQwMDaG+8yZMLSylgdKxMeLrIaE8HA4dOjw1b+XJSYiaOMm+P35p3BQiPe0sIDb2P/BvlMnyTvpqWZDr169sGXLFtE3JKG6atUqsU+TkH3sYmMmlk/Z2L+yKChNGctU72HhyaeIiZdLOmkCCtaxadIYoXv2Cqmk8NNnYFOvbpZ93v2A+/CLlBcld7ZwFhKscXFxiIiPwPa72+H9yBt9SvRB/5L9lX9Dxx1tfzSF04HJPCTjNXb7bYREJdd6K+puiyF18qNpiRxCLiy9+P7+u8ieJmybNYPtJwoFDMMwjJY5GCZOnCgitZctW4ZDhw59NpkzcOBATJo0SSnlQXqTn0aBM4wuQ5ItHrNnwcjeHkGbNonU8Pdjx8F13FhU6N0bFSrI9SHPnz8vHG7pxd7eHroORZfUKuQiFuLofV/4h6k/o4FYdXcVtj2Wp8BSqvKo8qOQVURcvCgfhAcFiW1Da2t4/PE7bD4pKJ5VUJHy7777Di9eyCWEPD09cfjwYVHvQxeKTNrUrYsudergyaVfUMmtEorsXY1o3E31+IA1a2Bdr55aJioiYxMwbNN/CI2OTzFo+b5uATQukUPIBTAMwzDSxc4uZZamvttqBoaGQjLE0NYGAUuX0eANHyZPQWJ4BJz69BZjubA9exETEQ5Z587Kv4vz8cH7CRNEHQcFFqVLC1vINK/mpSs1DckBt2vXDkePHhXbFhYWopgzBeRpu91eJIetWIj1l15lmd2eXhy7dhUOBoIcYVnpYKiQowK2tdyGWVdnYWrVqUrbMzohGmvur0FMQgzW31uPrkW6pnAosHMh80THJaTIRqCMeap9tuDEU1TxcsSQOgVQq6BzhscB4WfOIGS7XD7WyNkZbpMmfsNZMgzDMNniYCDtyCVLlohCZ/v27VNOeOXNmxctWrRAsWLFlMeam5tj0KBkXUKG0RfEAG3SRBg5OuDjAnkatN/vfyAhMAguo0YKo4ikbDLiYKDjmfRjbWIt0pbpvyruVbKk6yhaL2DFSvjPn085vGKfWeHCQrfY1NMzW76u69evi8wFkpsjSpYsKZy7Hh4pC/VpEy9DXopU817Fk6P26J6gGhrkrHl9N3XnAhF17ToiL1+GVZUqmUqzpoLmqoOW3tXz4e/jT1Aujz2+r1dAFDlnKSSGYRiGkKKtRr+BriNHwsjGBn6z54h9fn/8gcSwUFhUqAC/pECxKC8vmNaogdB9+/Dhl+lIVNTUMzaGy/fD4NS/v8iKkDpknzVt2hTXrl0T21QEnMbI1apV0/Sp6STmpUvDrFhRxNx/gIhz50R9r6y0uT1tPbGo/qIU+5zMnNAmfxvserYLLfO3RLwsOVCFyRwkobv2/EtsuPQKmwdUQTGP5CLwfarnQ70iriibxyFT700SrVQbT4H7tKksjcQwDKMmssXSI0eCqjOBYaSGSDkeNkyk89LAi6LAApYvF1HupPlIKdETJkxIV/FAMzMzjadQ6xqdi3SGh7UHgqKDUNUjWZJHXZCx+n7ceISfOKHcZ9eqJXJMnSrqD2QHx44dQ5s2bUTRcaJmzZrYs2ePVkdQ7n66G79e+lVEf+Wzy4dauWopX6PISP+FKQdxqeG/cCEsK1dOtyOAChvuvPEWS08/x+Ju5USWgoK+1fOKiKiqXk7sWGAYhmFSkBFbjaLS9clWc+rXD4bWNvhA0rak0794CYxd5BmoROCChQjbth3hhw8r95kWyA+PP/6ARfHiGjpr7eLly5eiDhZlmhI5c+YUGabFJdA/8QlZI6VEth9lMfhMkmvpB23eArdxY5Hd9C/RH4PLDBbFoZnM8yYwEsvPPMc/194o5beWnXmG+Z3LKo9xtDIVS2ah+njxvr5i3bZFi2zLMGcYhpECLCbNMNmIQ5cuyPnXn4CJidgO/vdfvBs5CnaWlimKvH0Jmni9p1IsT4qERcWJCPSMQJPXnxZYo770jZAbmZkl+tEjvGjfIdm5YGKCHD9Pgfvvv2ebc2Hr1q0iIk7hXGjdurUYtGqzc4GwMrESzgXi30f/pngt8tIlRF2//tX3UGQxpCfNeu35F6gz+yTGbr8jihUuPvUsxTH2lqaolj/jqdYMwzCM/kPR5um11ZycnISNoU84dOoIjzmzRVYCEZ+ULUnE3L6dwrng2KsX8m3bxs6FJO7cuSOyFBTOBZKtvHDhgiScCwRp5vuEfN0xlxlIP9/QVh4sErxjBxLT4QBUNw5mDuxc+Abuvw/FiM03UGfOKZG1oHAuWJkawd3OQm3P0vDTpxGyI0kaycUZOSZOUMv7MgzDMHLYwcAw2YxtkybIs2wpDCzl+pxhR4/izcBB6NWxoyjwRlFvqWGcNKCjwnA0mfzff/9Bn3CyMlUWllMu1qZwsjQW/zpaJkerRMcnYuKuu99scG64vwGtdrfC+XfnM/X3Ibt342Wnzoh7/VpsG+fIgbwbNwhHUnZNUi9YsABdunQRheaIAQMGCC3ftK4jbaKBZwO0LdgWQ0oPwV91/0rxGkWhpZcg781pvhYeE4+lp5+hxh8nMHXvfbwPkTs06OuhbyijjiqGYRhGuvTt2/eLtprit//t27dCU1/h+NcX7Jo1Q84Ff8t/RFPBKEcO5Fm7Fm7jx8HQ3Dzbz08bOXfuHGrVqgUfHx+xXblyZbEvT5480Ge73cXaDKZJRXfJ1Oq9+ipCo5OL86oLCuaxb9NG/jmhoQg9cEDtn8GoHxrDXXoegF6rr6Dp32ex59Z7JCTZ5HRt/fRdYVwYVx/jmhRRy5gqISTkE2mkaaJGIsMwDKM+WAyTYTSAVbVq8Fy3Fm8GDERCcLCIwH7dsxd6rlguZG7WrV2LD1u2Iiw8DPddXNC6TRt069YNP/zwA7y9vREaGioK+Z45cwZFixbVi+/w0MhkeRwF5EwJDAyEo6MjTE1NcfFZAPqsvYLouERsvvIapkYGmNqyeKYMz2sfrmHOtTmQQYYRJ0bgQNsDcLNyS9ffJsbGwnfmTASrTIJbVasKjzlzhAxWdhnmkyZNwowZM5T7Jk+ejGnTpmllBH5YbBiOvDyCdoXapdivWihPFYeuXRF54xMnmowcAomivo/wDqgc+ynBkbFYc/4l1l54KSLnFBgbGqB12ZwYUic/8rtYq6VtDMMwjLScDMJWW7cOu3fvxsePH+Hs7CyyBxs2bCjqzD1//hwXL14Ux+3du1fUmtMXjKgtaQR4uE+ZDKsqlbP9nLQVkqrs1KkToqPlwQ1ku2/fvh1WVlaQgt0eEROPTssv4u67UDzyDcOQjdexpnclmBqrN8bRoUtnBK5bJ9aDNnnDrm1brbSFmWTCYuLRb+1VRMQmKPfldrTAwFr50aF8rhTFndWB78zfEe/nJ9ZtW7aATb16/HUwDMOoGXYwMIyGsChZEp7em/C6X3/E+/gg+v59vOzaFXlWrcaAKlXwetlycZz79Omwr1lTrK9du1ZEw9GAhQa0DRo0EFFQ+fLlk8T3WDW/E1b0rIB+664JLf11F1/B2MgQk5oVzfBAorRraTHZve3xNvxU8ad0OxfifHzw9oeRiL59W7nPafAguAwfDgMj9RrDQUFB4junCYyAgAAhuUATGORsGj9+vIiiJKjtf//9N77//ntoI9d9r2P82fHwifCBrZktGno2VL6W1vfW7lIMAhr/nHKnTKbiYEj+O6dLMTikUueZro2Gc8/APyxGuY8Gs50q5MbAWl7I7SjPHmIYhmGYzMoljRw5EkOHDk0xoaqoiUR1kN69eyfWO3fuLDILTZLkMXWZr9VHCli9GtZ160pmcjctO43qb+zcuVNklZLdQnTt2hVr1qxRXidSwMrMGKt7V0SbRRfwLjgK558GYNz22/izY2m1XiOmefPCqkYNUeiZxlPRt27BokwZtb0/k0zjeWcQEBGbPvvcylTpiKLsBCPD5NdszU3QpVIerDz3AsXcbTG4Tn40LZFDjOvUTdipUwjZtStZGmkCSyMxDMNkBexgYBgNYublhbzkZOg/ALHPniHu1Wu87NwZxq6uymOCliyFXY0awhCnwSnp7Tdv3hzHjx/H+/fvUb9+fZw9e1YUi5MCNQu6YFmP8hi0/jpiExKx6twLmBgZYmzjwhkarJgYmmBKlSlokrcJKrlXStffRFy4gHejx4ji3IShjY0oYGhTry7UzerVq4XD4NNikqdPn8bo0aOVA1a6JjZu3IiOHTtCW4mMixTOBWLxzcWon6c+DA2+PICgwYuqgyAjkDOhdRkPrDj7ApamRuhexRP9a+SDq63+RJAyDMMw2gkFfRw9elTI4lAwCE0+U9YDZTyICTgd5mv1kRR1kayqqHj99ZQv2Wk//fQT4uPjlfvIGfXnn3/q/PefGVxtzLGub0W0W3JRZJTuuPEOHvYWGPNdYbV+jkPXLsLBQARt3swOhiwio/Y5SZVuvvwaa86/wMb+leGlkj08oJYXahVyQc2CWVf/jKSRPqSQRvqFpZEYhmGyCLVbOQdY95BhMoSJuzs8N26AealSYjvh40fE3L+vfD36v/9SFLGlNPtdu3ahatWqYvvFixciJZ8GsVKhbmFXLO5WTsjdEKSxP/fo4wy/DxmzqTkXjr46isDoQOW2LDERH5cuE44ghXPBrEgR5Nu+LcucC/369fts0KpA4Vyga+HgwYNa7VwgauaqiU6FO4nMhdXfrf6qcyEzRb+paLMqA2p6YUS9Ajg/th4mNC3KzgWGYRgm2yD5ysOHD8M2qfgsBQLQZLQuF37+WvaCAv+FC3W6neqw01SdC7///jv++usvSToXFBRwtREZyIqaDAtPPoX3ZXn9MnVhXbs2TDw8xHrogYOID0y24xnNQBJZ1WYex28HHogaaMvPPE/xuputuXAwZGXGk++MmcqC9HatWmXJuI1hGIaRo3ZLhyKrKR1U34qaMUxWYuzgAM81q2FZrVq6BmvW1tbCmVcmKf33wYMHQtc1JCREMl9Ug2JuWNi1rDLd9u8TT3HmsdyA/BbOvD2DMafHoPuB7ngR8gIJoaF4O+x7+M+bRzP74hi71q2Rd7M3TLOgQB+l22dE6qhcuXLQJhISE3Ds1bHPJhfGVRqHP2v/CQdzB7V/JhX9XnLqaYp9lK3wY6PCcLCSjhQBwzAMoz3Q7/P+/fuVBaGXLFmCCToszfG17IVPsxj0lYzYaSSHNHDgQMlIRn2JSvkchTQSYWNmDE8n9cpVkkypfefOYl0WF4fg7dvV+v5MxomMTUBotNzZZmJkIDLOs9P5GHbiJEJ27xbrpA7gNmF8tn02wzCMFFG7g6F///5CF7xUqVIiRZRhmHTejFZWcOrdO83BWsSlSyn22dvbi+i4woXlKcb//fcfmjVrhoiIlJHc+kzjEu6Y16kMyMcwqLaXSLH9FhJliVh0c5H4903YG5y9sQsv2ndA+MmT4nUDExPkmDoV7jNnwDBpwkDdkIRCWhFxn0JFA9evXw9t4W3YW/Q93BejTo3Cvuf7UrxmbGicpQPsS88DEROfXCiOYRiGYTRNjRo1hBa/ov4CRbPToosEbd6S/mO9N0NfyYidRkWPtclO0zQtSnvgtzYl8M/gqqhe4Nts9tSwb99O2OpE8OYtkCWwXahprEyNMKiWF86NrYfprUtkm7MtITgYH35OruWW45dpMLKzy5bPZhiGkSpqdzAsX75cSHbExcUJbXjSnKRJMIZhvgxFdHxctizN198OHYbAzVuQEJ7sQHB1dRUFBD09PcX2+fPn0bZtW8TEZE67XlcHK3uH18C4xkW+2Wgl6Z7lDZejvFt5tDWtjIo/rEXca3kKtzFJWXlvgkPnTllqHJNWc1Yen5VQnYUbfjfE+pxrcxAdnz3PfoqEO/ZjbZgZq7fINsMwDMN8K5RhunnzZqVEzvjx47F48WKd61iHrl1FgdQUi7MzDBwdxb+q++lYfUWX7TRtoFtlTxR1l0uHqRtjR0fYNGks1uPev0f46TNZ8jlM+p0LF8bVx/imRYUcUnbyYcaMZGmk1q1hU6dOtn4+wzCMFDHMKkP63r176NGjB/7++2+ULVsWV65cyYqPYhi94Wup57KoKPhOm4antWrBZ+pURD98KPbnypVLFHx2d3cX20eOHEGXLl1S6L/qO8U97D6b9H8dEJmp97IxsMC0S7nR4ZfzQEys2GdVrRry7dgOi5IlkdVkVOYqODgY2kLFHBXRs1hPFHYojBWNVsDcOHsGE+amRqKwM8MwDMNoI+3atRO6/QqGDRuGDRs2QJewqlIZhc6eTbHkPXEc9ju2i39V99Ox+oou22naSGx8ImYdeoigCLnN/a04dOmiXKdiz4zmsDQzhp2lPKMkOwk7cQKhe/aKdZZGYhiGyT6ybEaGipqtWbMG+/btg7+/vyhIa2Rk9NlibGycVafAMHpXOI9IjIxE8JateNG6DV526ozgnbuQL2dOHD16FI6OjuIYSsfv27evshiw1Nh98x3q/XkqwwXkKNrpVbfuiNyyDUZJEqFOQwYj94rluBL1AFMvTEVcQhyyErsMpu+SVJamuOl38zMt1RHlRsC7mTcKORTS2HkxDMMwjLbRq1cvEXiloE+fPsJeY3QLXbLTtJ3Q6Dj0XXsVi089w4D11xAd9+2SRhZlysCsWFGxHnH2LGJfvVLDmTK6Akkj+ahII7lP/wVGtlmTMcMwDMOkJEtDPkmmhSY9qRgWSbnUqlXrs6VmzZpZeQoMo1eF8whDFSMp6tYt+Iwfjye168B5zx4cWbMGNjY24jWKjBs+fHi2FtPSBp75h2PU1puIT5Rhws47+Ofqm3T9Xfj583jRth2i79xR9nOuJYvh+sMPeBr6HKNPjcb2J9sx5NiQLJX+adiwYYaOb9WqFbKbyLhI4WzpcbAH/n38b4rXTI1MxcIwDMMwTErILps+fbpYT0hIQOfOncVYidEdWrZsqfV2mq4QF5+It0HyjONrr4Lw4z83kZj4beMWymh2VJHoykjtEEb3+fDbDCT4fxTrdm3bwrp2bU2fEsMwjGTIMgcDSSKVKVMG8+fPF3ItDx48wMmTJ1NdMsOjR4/QrVs3FC1aVESSWFpaokiRIvjxxx/h4+Oj9vYwTFaSEePXqlIl5Jz7FywrJ6efJ4aEIHDdelj+byzO1q2Llk5OoIRU0vidMGECpER+F2tMaCqPXCLG7riNnTfepnm8LDERH5cuxZv+A0TUC2FWtCjybd8Gm7p1xXZITAgMIJdgymWTC2ZGZlly7vRcU5VQ+Br03KOIyOzmechz7Hq6S1lr4WOU3JBnGIZhGObLTJw4EWPGjFEWAW7dujUuXLjA3aYDRERE4NSpU1pvp+kKTtZmWNunEhyt5IEpB+58wG8HHnzz+9o2a6YMyAreuROJ6SzKzXwZcv5ExGivBG/Y8eMI3ZskjeTmBrdxYzV9SgzDMJJC7Q4G0n2nCc0aNWogICAA//77LzZu3Kj29NC3b98KR0KbNm0wc+ZMzJs3T0T+UpHp8uXLw8/PT62fxzBaUzive3fYNmkCz3Vr4XVgPxx79YKhSrq26aPH+N3ZBSfyF8AoZxds+PNPcY9Iif41vTC2cRGxTgkco/+5hb233n92XEJIiCie7T9vvvxAinZp0wZ5N3vDNHdu5XEVclTAxqYb0bZgW0ysMjFLijxT7YzKlSvj2bNn6f6bBQsWaCT1voRzCfQv2R8OZg6YWXMmnC2c1fbeIZFxGLbpPyR8YwQbwzAMw2gjZEPMmjULAwcOFNuRkZFo2rQpbt68qelTY77AmzdvROb9nj17tN5O0yXyOlthZa8KMDeRT0usOvcCq8+9+Kb3NLSwgH2bNsogrNADB9RyrlKGHAuDNl5HZOy3y1hlBfFBQfD5eapym6WRGIZhsh+1F0Cgyf07d+6IdFCa7HdxcUFWUL9+fbF8CskudezYEWvXrsX//ve/LPlshsmqwnmqUFRbYGCgqKtgapq65IyZlxfcxo+Dy6iRCD10SNRmiEoaoDoZG2OAkxP6OTri/KLF2OLvj06zZsFAInVPhtTJj7iERPx19DFornrk1pswMTJA4xLyYtjRDx7g7YgfEPdGLqFkYGICt8mTYN+hQ6oOBC97L0yrNu2z/aGxobA1zby2J0lYkSYzZV8pambQAJYKQo4fPx5RqURdUUQcDVqpzkZ28Cb0DXLa5IShQbJPelDpQehcpLNanQtP/cKFBu+LjxEwNTKEs7Vpyu9CJhN9ZGhoSDM0yt1OSZFvDMMwDKML0G8bZZmGh4fD29tbFA5u1KgRzpw5IzKyGe3i0qVLItPE19dXbLu5uaFfv36YO3euVthpuk65PA74u3NZDN54Xdjs0/ffh7udOZqUlNvsmcGhS2cErlsn1oM2eQu5nKwIEJICJGPVf901PPwQptxna24MMxMjrbHPfX/9DQkfk6SR2rWFda1a2fbZDMMwjBy1zzS+fv0a69atQ48ePaAJPD09xb9U94FhpIKhuTnsW7cWS/SjRwjeuhUhu/cgMSIChgYGqGltDRw4iNtnz8GjVy/Yd2gPEzc36Dsj6hcUToYFJ56KiPjvvW9gaXdDVHh4AR+mTYMsJkYcZ+zhjlzz/4ZFyRIZlgrqdbAXBpYaiO5Fu2d44EJOpKFDh2LVqlXKff3798eiRYuEU6lnz57iebp79258/PgRzs7OYoBL+x0cHJDVJMoS4f3AG3Ovz8UP5X5Az+I9la+ZGJqo1blw6pEfhm++gbBoeeq1q60Z1vetBC8X6ww53RiGYRhGFzAyMhIBUWFhYdi7dy/8/f1FNva5c+eU4xlG81BNswEDBojaggRJAJNdlidPHiF1pUk7TZ9oVDwHprYsjim774mkYgoMcrExQ4W8jpl6P9O8eWFVvToizp9H9P37iL59GxalS6v9vPWdqy8DMXjDdQRExIptVxszrOhZAaVz22uNfR569ChC9+8X68Y5csBt3LhsPweGYRgmCxwMd+/eRc6cObOtb6Ojo0X0D/17//59jB0r19qjVGOGkSLmhQsjx5QpcB09GiH79+PxggWwTSp2ZRoWho8LF+LjkiWwrlsHDp06CePbgCJO9JQfGxZCbEIilp1+DoO4WNwZPQ45X1xSvk7t95gzG8YZHAhSoeOhx4YiOCYYs67OgoO5A5p7NU/335OMG2Up0ESCYqKBIuG+//57paOCBqcjR44UTghNGO6vQl/hz+t/Ij4xHvP/m49auWohr11etX4GZXBQOvyMAw9E1BpROZ8jlnQvr9TkZRiGYRh9xMTEBP/8848Yt1BdOpKAbdCgAc6ePYscOXJo+vQkDRXhpnoZf/zxh3If2W3kULCystIKO03f6Fk1L94FRWHZmeeIiU9E//XXcOzH2nC2zlztM4duXYWDgQjy9mYHQwb55+obTNx1B3EJcgO9VC47LO9RATnszKFN0kgfpiZnmLtPnw4jGxuNnhPDMIxUUbuDITXnAmmKU2TH8+fPxbaXl5eQUMqfP/83f97KlSsxfPhw5XbevHlFzQeSGEmPliYZ8qqQvBMRFxcnvPGagD6balnQv1JE6u1XWz+YmMCqdWuUadUKK8eOQ9CWLWhqawsLciYkJCD82HGxGOfMCdv27WDTujWMnZygj9fCj/W8YOTrg8JL56FQcPI97zBoEBwGD0KikVGG73djGKN7ke6YfX02yrqURV33uul+j9u3b4tBKmV8EaTPu2nTJjGpkFpbNXVP5LTIicElB2PJ7SUYUGIA3Mzc1PpcjI1PxM97H2D7jeT6GJ0q5MTkpkVgaiyPiJLys0Fq7f0SUu8LqbdfAfeD5vtAU5+rzzY7yYpQzTpyMly5cgVPnz4V9sCxY8fEhLU2o+nrMaugrBIqzrw/KSqaIGfDpEmTxPcldfskLdTRD6PqeeFtUAQO3PXF0Fr5YGtqkOn727RqVRi7uyPexwchBw7CYdQoGKnxntLn7/3YAz/8b/tt5Xazkm6Y2bq4qJWhTde/77RfkBAQINZt2raFaeVK2f57oM/XQUaRel9Ivf0KuB+0px+y+7OzXIx98uTJ+P3330UUiCpUH4GKQf/yyy/f9P6UhkpapZTFcOPGDVF4i1JU0wPJkkyb9rmmOhEaGioiUTR1EVB7KLKXIpukhtTbnxX90G7cWPyWEI86ixejpa0dOjs4IH9ShFX8u3cInP83AhcthknNmjBr2RLGZUprhU6puvog7upVtFz8K2ShoWLbwNoaVpMmAlWqICgkJNPv28CpARzLO6KgbUGEhSTrkn6JAwcOCKcoFXUkyNFK0XD0b1rPnOy6J8LiwmBpZAkjwyRNVQDN3ZqjdLXSyGudFyHBme+rTwmIiMO4fc9wxydCbBsZACNr50b70i4IDw1O9W+k9myQWnu/hNT7QurtV8D9oPk+IPtYE0jBZie5JAo+ePDgAe7duyccDpTdYE0yl1qKpq/HrICCP8i58PDhQ7Ftbm6OefPmieC44GC2T7Ljehhb2wONC9qiYh6bb763jZs3Q/yKlXRy8PXeDPOuXaAu9PH6V1DKxQiV89ji8utQDKrmgd4VcyAyLATy0Yt29EPsmTOIOHRIrBu4usKoX1+N/Bbo83WQUaTeF1JvvwLuB+3ph+y227PUwbB69Wr89ttvqFatmnAoFC9eXOwno3n27NniNcpm6N27d6Y/I1euXGJROBvIMK9YsaKYvKMCqV+CinN99913n0VDDRo0CLa2thqLGqILkSZ3Ke1Wig8mqbc/q/phzpw54j2XLVuGTcFBqOnkhAXNW8D0+nVhdIO8qydPisUkb17YdugAm5YtYGRnB13tA1liIoJWrED44iWiABlhWqQIcvz1J0ySnhtUm8HIMPPOlAaODT7b9ybsDaLjo1HQoWDyuchkwtk6depU5T7SWqaMK8pg0PQ9cdHnIqZdnoYOBTugX/F+KV5zcXJR62dRX3y/85rSuUCF4uZ3KoXq+b+cQSO1Z4PU2vslpN4XUm+/Au4HzfcB2ceaQAo2O7Xh0KFDqFevnsj+psApqstEWeAWFhbQRjR9Paobkqbq1KkTApIioikzf9u2bShXrpyk+iGzqLMfcriqp85XQrdueLl2nRjrxO3bB/chg2FglBxI8y3o+/e+qJst/nsTjDqFXLSuHxICA/F67jzldo5fpsEyd25oAn2/DjKC1PtC6u1XwP2gPf2Q3XZ7ljoYqFBp5cqVcerUKRgbJ38URepSVA7JGC1YsOCbHAyfUqpUKZQtWxaLFy/+qoMhd+7cYkkNugA0qaFJ/aXpc9AkUm9/VvUD3RfkfKOCdWcDAlBv7x6c3rMH7g8fImjrP4hLkuyJe/kSAbNnI/Dvv2HbpAkcOneCeWnNZDVktg8SQkLw/n9jEX76tHKfXbu2yDF5siiKTbz4GIGB66/hj/alUC6PeorxBUcH44czP+Bj1Ef8WftPVM9ZXfQ5TY5s2bJFedyoUaMwa9asFM9GTd0TAVEBGHN2DKITorH8znLUylMLxZ3kDuGsYlqrEmi/5CLc7c2xqldF5HOW6xl/Dak9G6TW3i8h9b6QevsVcD9otg80NUCSis1OhYOPHz8uxkgkC3X69Gl0794dO3bs0NrJCn25J0l2d8iQIULOgKhUqRJ27doFd3d3SfXDt5JV/bD2/As8/xiBaS2LZ2w8kiMHbJs0RuievYh//x6xFy/Bpl5dtZ2XvnzvF55+RFRcAuoXdVPuczY1RSM77bTP3/7xBxKDgsS6fYcOsK9TB5pEX64DdSD1vpB6+xVwP2hHP2S37ZillV0pxbdz586pTqDRPnqNjlE3UVFRGkuVZhhthnRjKbOoTZs2Ypvuk4bt2yOodm3kP3QQuVethE2jRlRxWLwui4lByK5deNm5C160aSvqOCSEy6POtZno+/fxol17pXPBwNQUOab/Ao/fflM6F94FR6HTsot44heOXquv4Pbb1NPeM8q6++tEceSIuAisuLNCTBDUqlVL6VyghzxJPfz111/pdi5kNU4WThhZfqRY/y7fd8htk/URQMU97LC2T0XsHFo93c4FhmEYhtF3PD09cfToUbi4yKOG9+3bh549e34mN8uoB3IoUKHmAQMGKJ0L3bp1EwFy6XUuMFnLn0ceYere+1h/8RWWnH6W4b936JIsixS0ebOaz0732XDpFXqsvoLhm2/ggY9mZPAyQuihwwg7KJdGMvZwh+vY/2n6lBiGYZisdjCQl4Y0p75UQCuznpwPHz6kuv/kyZO4e/cuqlSpkqn3ZRh9hya1N2/ejEbkSEi6l6iY4Lv372FdvTpy/T0fBU6cgMsPI0RhNAUxDx/iw9RpeFqrFnx+niom8bWR4O07hEMkLqkYpImHBzw3bYJDhw4pjnOzMUPFvHJJhbDoePRYdQX33n97jYFhZYahQ6EOyGOTB91tuosIuOskQwXA1dVVPKP69u0LTRKfGI+4xJQFf7oU6YIVjVbg95q/w9ZUval0UbEJmHHgAUKjU35mZS8n2FloZ0QmwzAMw2iKwoUL48iRI7BLkqmkIAWKrieJQUZ9BAUFiaz6+fPnK/fNmDFDZPpqqyyVFKmQ11EpZzrr0CPsvvkuQ39vUaYMzIoVFesRZ88i9tWrLDlPXSMuIRGTd90VC0nGRsYmYM+t99Bm4gMD8UGlhqf79Okw0uI6NQzDMFIiSx0MVAuB9N59fX0/e83Pzw/Lly8XEkqZgYxsciJQoWj6DDIMKbqH9FltbGzw559/qqEFDKOfmJmZiXT7GjVqiO1Xr14JJwPdl4SJmyuchwxBgWNHkWvJYljXrg0kpSMnRkYieOtWvGjbDi86dULwjp1IjIrSaHvEecXEwGfyFPhMnAhZbKzYZ1WzJvJu3waLkiU+O97YyBDzOpdBo2LyVOCQqDh0X3kZjz6kr1hzWhgbGmNylcloHdEazes3VzpDS5cujStXrqB69erQJC9DXqLXwV5YfHNxiv2GBoao4q5+x+z74Ch0WHYBy888x4jNN8QAhmEYhmGYL1OmTBkcPHgQVlbyLL8VK1bgp59+YieDmnj8+LEYS1K2CEH9TJJIJLGrCUlQJm1qF3LBzDYlldtj/r2FC88+prvL6Pt07NpVuR20OVmyVKoER8aKDG7KXiDokp/QtAj+911haDMffpku6i8Q9p06ieA4hmEYRk8dDB07dhTRIMTkyZPh4+ODokWLCoN4zZo1YhkzZozYRxNvkyZNytTndOnSBc7OziLC5IcffsC4cePE5B0Ve7t9+7YwyhmGSRsaSFHavaJw3aNHj0RWg+L+JagImk3dusi9bKlwNjgNHgQj5+Sia9G3bsNnwgQ8qV0HH36bgZinTzXS5bFv3+FV124I/vffpBM3gPOwYci9dAmMHdKurWBiZIiFXcuhXhFXsR0UGYduKy/hqV/mnQwkYUCD04E9ByImJkbsa9u2LQ6eOIgVb1YgMFpz8m1UeLr3od64/fE2Vt9djRt+N7L08/57HYSWC8/j7jt5uvXddyF4GxSZpZ/JMAzDMPpC1apVxaS3IuObAqh+/fVXTZ+WzkNOBQpyIyeDQpbqwoULaNWqlaZPjUmDjhVzY0T9gmI9LkGGQRuuZygoyLZZMxgmFbsM3qkdwVGagsY5rRedx4Vn8mLm1mbGWNWrAgbWyq/VzrXQQ4cQduiQMkPd9aefNH1KDMMwTFY6GCgqunjx4mLiknTHaVuRUUBFTmkh7XHaR69REbPMOjLoM0jfPDo6WtRdePjwoSgaTQXSGIb5OpR6f/jwYRQrVkxs37p1C82aNUtV2swkZ064jhyJgidPIOe8ebCsmhztnhgaiqANG/C8eQu86t4DIfv2IzEpiyCrCT97Fi/btUP0vXti29DOTjhEXIZ/LxwkX8PU2BCLu5VDrUJyreOP4bHosuIynvunLe+WFqGhoWjdujX++OMP5b4pU6bAe4s3Jl+bjN3PdqPb/m6iRoMmMDc2x4hyI8R6UceisDezz7LP2n79LTovu4SP4XInSzF3W+z+vgY8nbjeAsMwDMOkF8ow/eeff2CUZNOQXaEq6cOkH5KYWrhwIZo0aYLgYHntLcrmpSC1UqVKcVdqOaMaFET78rmU8qZ91lzBh5DodP2toYUF7JNq0CWGhCD0wAFIkZOP/NBm0QW8DJAH/ORxtMSOodVQr0hycWdtJD4gAB+mqUgj/fYrjKx5TMEwDKNNqN3BQAWxLC0tRQQI6YzXqVMHL168wOXLl4V+KC1kxD1//hzNmzdX98czDJNBKBOIIrm8vLzE9sWLF8UkOTnuUsPAxAS2jb+D55o18Dp4AI59+sDIPnmiOvLaNbwfMwZPa9eB35w5iH39Oku+E1liIvwXLcKbgYOQECKvnWBerBjybd8G61q1MvRe5iZGWN6jPKrldxLb/mEx6LriMl4FpL+gNT3TqlWrJhyfBGn3bt26FdOmTUNIXAh8I+RScYmyRFiZZJ9BTJ+nSpsCbTCjxgxsaLoB+ezyqf3zSAJp5oEHGP3vLcQmyD+7SYkc2DakKnLas54xwzAMw2QUGletXbtWuU1FiSkrnEk/cXFxQmJ3+PDhyoLZNFY9fvy4qJHFaD8UXT+zbUnULCjPpn4fEo3ea64g7JMaX2nh0KWzcj1ok7fk5MYO3fVBv7VXERYjL2ZexcsRu4dVRyE3G2gz9D2RcyEhKcvevnMnWFWtqunTYhiGYbLawUBRIHfu3MHQoUOxbt06lCxZUjgdqB4DZR3QUqFCBRgaZmn5B4ZhMoCHhweOHTsm/iVosNWpUycxGPsSZvnywW3s/1Dg9Cl4zJ4Fi/Llla+RERiwchWeNfoOr/v1R+jRo5DFyw3abyUhOBhvBg/GxwULyeoU++zat4PnZm+Y5pJHNmUUcjKs7FUBlfLJCz9HxMYjODJ9AxYq3EzPuHtJWRS5cuXC2bNnxfOOcLV0xcamG1E3d10sbrAYzhbJMlNZRVhsGCaem4jZV2d/Njhrkb8FTAzVX1yZBngD1l/DsjPPlft+qF8Qi7qWg6Wpsdo/j2EYhmGkQvfu3bFo0SLldv/+/bFt2zaNnpOu8PHjRzRs2FDU7SNoHDp37lysXLlSKT/F6AYkb0qZx0Xd5XJHDz+EYcmpZ+n6W9O8eWGVpNkfff8+om/fhpSo6uWszCTuWjkPNvSrDAcr7b/+ww4eRNiRI8nSSGNYGolhGEYbyZIZH4rcJamidu3aicgQ0nUfOHCgKKSVGlScmWEYzZIvXz7hZCBpMxqI7dmzB71798b69euVaflpYWhmBrsWLcQS/fgxgrf+g5Ddu5GYJLUUcf68WIxdXWHfvj3sO7SHibv7V6NVwvbsRUxEOGSdkyOOou7dw7sRPyDu3TuxbWBqihxTJov3/VZoEnx174oYueUGRjYohBI57b76N0uXLhXRcPFJzhN6zu3cuRM5cuRIcZydmR3+rvf3Z38fkxADU0NTtWqeUtZC38N98TDwodiulasWqnpkbaRPYqIM3VZexu23SdkkJob4s0MZNCv15e+ZYRiGYZj0QQFcJMdItZ4SExPRtWtXWFtbo3HjxtyFaUDBHy1atBAZ9YStra3IMOU+011szE2wpndFtFl8HpXzOQqbPb04dOsqxiREkLc3LEqXhlSwszTBip4VcPF5ALpXzqPV9RYUxH/8KAo7K3Cf8RtLIzEMw2gpWZpGQPJI58+fh6Ojo4gY6dOnj5iwpEWxTv8yDKMdUPH1I0eOiNoMhLe3txjMZiSF2LxQIeSYPAkFz5yG+6/TYV6ihPK1eD8/fFy8GE/rN8CbocMQfuYMZElp6p8SeekS/CZNQuTM3xF15YrYF7xtG1516ap0LlBdCE9vb7U4FxRQobOVvSp+1blA2R3Dhg0T6fYK50KPHj1ENsOnzoW0iE+Mxw8nf8Dk85MRl5C+bIn0YGhgiD7F5c/W7MiWEJ9paIBBtfKLdXc7c2wbXI2dCwzDMAyjZsaNGyccDApbpG3btiJrkvkckq2kQtkK50KBAgVw6dIldi7oATnszIW8z9xOZUQ9tfRiXbs2jD3kwS+hBw4iPkl2Rx954BOKx74pC2EXcLVGjyqeOuFcUEojJdVLse/SGVZpBKwyDMMwmidLNStooo0yGCgamjIYyMBjGEa7KVu2LPbv3y8yjyIjI7F8+XJRlH327NkZMkYNLS3l2Qrt2yPqzl0E/7NVFH+WRUVRuDvCT5wQCzkJ7Dt2hH27tjB2dlYalP4Lk2UAAhcvRsShQwjdvkO5z6pWTeScNStF/YesIiY+ATMPPMSwugXgYmOGwMBAdOjQASdOnBCvU79QYecxY8ZkqI9mXZ2F8+/kUVQJsgTMrDlTbefc1KspgmKC0DRfUziYOyA7oGyFiNhSqFPYBa425tnymQzDMAwjNX777TeRyUCSSVFRUWjWrJkYd5VXkaqUMmRHzpkzB2PHjlUGydSvX18Uy6bAN0Y/cLX93NYMj4kXwUJpYWBkBIdOneE/dy5kcXEieMl5wADoG4fvfcCorTfhZG2K3cNqwFEHpJA+hQpxhx09KtZpvOg2ZoymT4lhGIbJbgcDGbr/+9//sGTJEqHpfvjwYaF7yTCMblC9enXs2rVLFGKPjY3Fn3/+KbIaJk+enKn3syhZQiyu//sfQvbsQfCWrYh58kS8RtkIZOT7L1gAm4YNhNEvS0xA1PXryr+PuXFTLAIDAzh/PwzOQ4bAIBtquUTHJWDQhus4/dgfF559xLTajujRsQ2ePZPrvZLzhTI9MlO0vkGeBtj3bJ9wLvQu3jtT55eQmIB199fBJ9wHE6tMTPFat6LdMvWe6SEuIRFbrr5B10p5YGSY7FTpWCF3ln0mwzAMwzDywIa///5bOBk2bNiAsLAwfPfddzhz5gyKFSsm6S6KiYnBoEGDRC1ABZRxSjUXTEzUX3+K0R7ITh+26T+R1VCncNqFu+3bt8PHhQvlDobNW+DUt69wPOgD5FBbfOoZZh9+JLYjA6Ow8uxz/K9xEegSJI3kO/1X5bb7jBkwtJLXj2AYhmG0E7XPzl24cAGlS5cWETXdunUTBZ/ZucAwugfdt6RRq6i/MGXKFMybN++b3tPIxgaO3boh357dQtrIrlVLUUNBEB+PsIOH8Lp3b7wdMjTVvze0tUXu5cvgMmxYtjgXiKjYBHwIiRbrj33D0WHxWbx45ye2vby8cPHixUw5F4hK7pVE8ef59eajsGPhTL3HT2d+wtzrc7Hl0RacenMK2UFQRCx6rrqCybvuYtZheZ0HhmEYhmGyDypUvHr1arRu3VpsBwQECNtNIQckRXx9fVG3bl2lc4Fs2MWLF2PhwoXsXNBzSAqo1+orCIqME06Gu+/kNcFSw9jJCTZJdUvi3r8Xkq36AAVFjdx6U+lcIPpWz4cfG6a/RoX2SCNNU0ojOXTtCqvKlTR9WgzDMMxXUPsMHRWIpWgaKnJKxp1Cy51hGN2DBq1r165Vyv6MGjVKDGa/FXo/y3Jl4fHHHyhw+hRcx46Fqaen8nVZTEyqf+c2eTKsa9ZEduJgZYoN/SrBwUh+TsbOnnDtNB21GjTGlStXULx48W96fy97L1Rxr/JZVsINvxvp+vvmXnLnhomhCfyj/JHVPPENQ6tF50WBOML70mv4hcodMAzDMAzDZB/GxsbYsmULGjRoILbfv38vpIDeJdWqkhI3btxAxYoVReAH4eDgIOqKUa0sRv8p6GqNThXlWbQRsQnos/Yq3gZFpnm8Q9cuyvUg783QdXxDo9Fp2UXsvvlebJsYGeD3tiUxpUUxGBtlT1CWugjdtx9hR4+JdZNcueA6+kdNnxLDMAyTDtT+a9OmTRvcvXsXrVq1UvdbMwyjAbp37y6ivxQMGDBAaNiqC2MHBzj16Q2vQweRe81qGDmkXS8geOuWDBWcVgfR0dH4afgg3JnfH3GB8gG7WY4CsGs1AaZWtlnymXOuzUGvg72w7t66r7a3Xp56GFF2BLY034IOhTogKzn+wBdtFl/A60D5gM3TyRI7h1VLVQOXYRiGYZisx8zMTMhaVqtWTWxTBgNlMlANPKmwfft21KhRA2/evBHbRYsWFUEg9erV0/SpMdkEBS9NbVEcDYrKpZH8w2LQe81VhETGpXq8RZkyMCtWVKxHnD2L2FevdPa7uv02GC0XnsOtt/KsDaq3sLFfZXSulAe6Rry/P3x/VZFG+u03lkZiGIaRqoPh33//hXNSoVaGYfSDwYMHY9asWWI9MTFRyJ8dOHBA7QMDypNICApK85ioa9cRefkysosPHz6IVPv169cjISIIH/+ZDHtj+UDl9ttQMXCJiIlX62dS5sLGBxshgwyLbi6CT4SP8rUz787gjyt/fPY3A0oNQCGHrEt/JifH0tPP0H/9NVE8j6hewAm7h1VHAVebLPtchmEYhmG+jpWVFfbv348yZcqI7QcPHqBx48YICUlbJkYfIPtk+vTpaN++PSIj5cEPTZo0EVkMBQoU0PTpMdkMRer/3aUsSueSKyg89QvHgA3XEBOfkOq4w6GLShbDlq3QRY7d90WHpRfhGyrPtC7sZiPs88peTtDF+9ln6jQkJD23HLp1Y2kkhmEYHUK38uUYhtEYP/30EyZNmiTW4+Pj0a5dO5w6dUqtRqX/wkVfPc6firJlQxbDf//9J1LtL126JLYdHR1xaOcW7BvdCDntLcS+66+CRAp2ZKz6nAxlXctiUuVJMDY0xu81f4eHtYfYv+bJGow6M0o4Hw69OITs1HMd/c8t/H7wIRTd3rOqJ9b2qQR7y6T6GQzDMAzDaBR7e3scPnwYhQvLazpdv34dLVq0UE686xvUri5duogaYQpGjx6NvXv3skSvhLE0Ncaq3hWRx9FSbF95ESjs2MTEz8cOds2bi/puRPCOHUiMioKukdfZEqZJEkgNirph+9BqyJ3Udl0jdN8+hB8/LtZNcudmaSSGYRgdgx0MDMOkm19++QUjRoxQSgfRwJVS0NVB5KVLiLp+/avHZUcWA2ViUar927dvU6TaUzZDLgdLbB5QBTmSZIFo4HLiobzos7roVKQTDrQ5IOSPFJRyKKVcv/3xNrKD2PhEdFlxCTtuyKWhjA0N8FubEvilVQmY6JieK8MwDMPoO66urjh69Cjy5JFLo5w9e1YEhMTGxkKfoBoTVPdv61Z51LmJiYmoETZnzhxR2JmRNs7WZljbpyIcLE3E9r7bPvjj0MPPjjO0sIB9mzZiPTEkBKFqzs7ODiiTeEHXshhSJz+W9ygPazNj6CJxfn748Otvym2PGb/B0FI3HSUMwzBShWeIGIZJN5ROPHfuXPTp00dsh4eHixT8O3fufHMvBm3ekv5js6gYG8k//fzzz+jYsSOikqKYmjVrJrIY8ufPrzwuj5MlNg+sAlcbM/zcohial5JnGagTd2v3FNvlnctjQIkBmFd3Hv5X8X/IDkyNDVGzgFzyjgZpG/pVRrfKycW4GYZhGIbRLnLnzo1jx47Bzc1NbB86dEhIW1L2qT5AAR+UYUoZGoSLiwtOnjyptE0ZhvByscbKXhVgZiyf7th/xwchUZ/XY3Do0lm5HrTJO9trvWWU98FRCIpI6TCsU9gVYxsXgaEhic3qHtTnH6ZOE04ewqFHD1hWrKjp02IYhmEyiG66uBmG0RiGhoZYsWKFcC5QpH9QUJAoJkhRcgULFsz0+zp07YrIG/+l3CmTT/rTZ4oCDSrHqpuIiAj06tVLFApU8L///Q8zZsxINRoun7MVjo2uDVtzeXRUdjC45GCYmmavLNHIBoUQE58oHAvkWGEYhmEYRrshe4wyGWrXri3stG3btsHGxgYrV66U21Q6ire3N/r27YuYGLnefKlSpbBnzx54enLwA/M55T0dMb9zGSw59QwrelWAncXnNrtp3rywql4dEefPI/r+fUTfvg2L0qW1sjtJmnXQhuso6GqN9f0q6U02cejevQg/cUKsm+TJA9dRIzV9SgzDMEwmYAcDwzAZhibcN27cKJwMBw8ehK+vLxo0aCCcDIq0/IxiVaUyCp09m2IfpfQHBgaK+gdZObH++vVrtGrVCjdv3hTb9Fk0CO/Ro8cX/y4158LxB76oVchFJ41+0qc9/+wjahZ0Ue6jaKjxTYtq9LwYhmEYhskYJUuWFDYa2Wdkr61Zswa2trYiE5UyUnUJCjaZPHmyCPpQ0Lp1a2zYsAHW1tYaPTdGu2lcwh0Ni+WA0Rei+x26dRUOBiLI21srHQzbrr/FhB13EJuQiI/hMVhx9jmG1tH9QuZxvirSSAYGLI3EMAyjw+jeDBjDMFoBTcJTtD9Fxykm6WkQS84GXeL8+fMi1V7hXCBJgdOnT3/VuZAaK848R7911zBy603EJyRCl4iIiceQTdfRY9UV7EqqucAwDMMwjO5SuXJlUfTYzMxMbM+fPx9Tp06FLkHOkbZt26ZwLkycOFHYoOxcYNLDp86F4MhYvAlMLn5uXbs2jD3k0qShBw4iPihIazo2IVGGmQceYMy/t4RzgWhW0h19quXT9KmpRxrp55+RGBoqth16dIdlhQqaPi2GYRgmk7CDgWGYTGNhYSFS02mCnnjy5ImQS6KsA12AovmocLOfn7xIc7ly5XD16lVUqVIlw+/lHxaDv088Eev7b/uIgQANCnSBt0GRaLfkAg7fkzuHpuy+i9Doz3VqGYZhGIbRLerUqSMkkoyN5Ynrv/zyC/766y/oAq9evUL16tWxe/dusW1ubi5kkn799VedlnpiNAc5Fsjm7bHqMgLC5VJbBkZGcOgkr8Ugi4tD8LZtWvEVhUXHYcD6a1h25rly36gGhbCwa1lYmOp+MfOQ3bsRfuqUWDfxJGmkUZo+JYZhGOYbYMuMYZhvgtLtKQW/RIkSYpsKPjdt2hRhYWFa27MJCQkYPXq00PGNi5NPpFNhZ5J4ouKImcHFxgzr+1aCtZl8AL/r5nuM3X5byA5pM1dfBqLVwvN4+CFM2Y51fStla20JhmEYhmGyjubNmws5IYU0EtlAVE9Lmzl37pwIYLl9+7bYdnd3x5kzZ9ClSxdNnxqjw8w48ADP/CPwMiAS/ddfQ1Rsgthv374dDEzktm/wlq2QJcj3a4rXAZFou/gCTjyUB0GZmxhicbdy+KFBQZ2TOEtLGsl3xsxkaaSZM2FoYaHp02IYhmG+AXYwMAzzzTg5OeHIkSMoUECuBXr58mVR0yAqKkrrejckJEQMtFWj96ZPn44tW7bA0vLbihiXzeOANX0qwjIpqoj0UifuuqO1ToatV1+j64pLCIiIFdslc9phz/fVRTsYhmEYhtEfOnfujKVLlyq3Bw0aJGwfbc0wrVevHvz9/cV2hQoVRIapImOWYTLLjDYl4eViJdZvvA7GD1tuiIxjYycn2DRuLPbHvXuH8DNnNNbJl54HoNWic3jiFy623e3MsW1wNTQtKZdx0gtppClTlNJIjj17wrJcOU2fFsMwDPONsIOBYRi1QJFlx44dQ65cucT2yZMn0aFDB2WGgDZAEk6kR3zo0CGxTQ4F0vCdNGmS2qKBKuZ1xKpeFUWkEbH5yhtM3XtPGNPaAtWH+GXvfYzdfgdxCfLzalHaA/8Orgp3O44eYhiGYRh9ZODAgZgzZ45YJ7uE6k3t378f2pxh2qlTJ1EbK2fOnJo+PUYPcLAyxbo+leBsbSq2j9z3xS9JdrpD1+TsmCDvzRqtixYcJb/+y+axx+7vq6NETjvoCyG7diP89GmxburpCZeRP2j6lBiGYRg1wA4GhmHUhqenJ44fPw5XV1exTYNWGrzSgFHTHD16FJUqVcKjR4/Edp48eUSBZyocqG6q5nfCyp4VYWosf8Suv/gK0/c90AonQ2RsPPquu4bV518o941pVAh/dy4DcxPd13NlGIZhGCZtaAJ/8uTJYj0+Ph7t27fHqSQddG3MMN28efM3Z5gyjCq5HS2xundFWCTZvesuvsKKs89hUaYMzIoWFfsizp5F7OvXGum4+kXdMK5xEbQtmxObB1SBq4059IU4X1/4Kgq2GxjAfeYMlkZiGIbRE9jBwDCMWilUqJCQS7K3txfbW7duFWn4mppcp89dsGABmjRpguDgYLGPCgZSqn2ZMmWy7HNrFHTG8h7lYWokf8zShP4/195A05gbG8EsyfFBUk7LepTH9/X0Q8+VYRiGYZivM23aNIwYMUKsR0dHo0WLFrhy5YrGuu7p06eoUqVKigzTHTt2qDXDlGFUKZXLXhRLNky6vGYceIh9t31SZjFszh4JsZCoOMQlJKbYN7CWF/7sWFqvgn9oTOYzeTISk+r0OfbqxdJIDMMwegQ7GBiGUTulS5cWhZ+trOQap6tWrcKPP/6Y7U6G2NhY4dygQbQii6JPnz4psiyykjqFXUVBNmNDA9Qt7IJWZTSf3m9oaIB5ncqgQVFXbB9SDd8Vz6HpU2IYhmEYJhuhSfu5c+eid+/eYjs8PByNGzfGnTt3sv17OHHihMgwffjwodjOnTu3yDBt06ZNtp8LIy0oU2B66xLK7dH/3MLj4tVgaGMjtoN37EBiFteTe+YfjtaLzuPXffc/u0f1zbkWsmMnIs6cFeumefOyNBLDMIyewQ4GhmGyBIpE27NnD8zMzMT2vHnzRMRcdvHx40c0bNgQK1asENuGhoYi7Z6cHYpzyg4aFHPDloFVsLRHeY1EIZFT57m/vEicAiszY6zsVRFF3W2z/XwYhmEYhtE8ZBeRjdSuXTuxHRQUJOwmyibILpYsWYJGjRqJzyaqVauW5RmmDKNKt8qeGFY3v1g3MjRAhKEx7NvKnVuJISEIPXAwyzrszGN/4Vx48TFCyDRtu/5Wb7+cuA8f4DtzpnzD0FAujWSuP9JPDMMwDDsYGIbJQurVq4d///0XxsbGYpscDH/++WeW9zlF4FWsWBFnzpwR23Z2djhw4ABGjRqlkWigCnkdYWac0rnwMTwmyz83Nj4R43fcQZP5Z3HrjVweimEYhmEYhiD7bNOmTfjuu+/Etq+vLxo0aIA3b7JW0pEKOA8bNgxDhw5VZpj26tVLZDO4ubnxl8NkK2MaFUaf6nlFQFC9Im5w6KJa7Nlb7RnY9H6rz71A7zVXEBYdL/ZVyucosp31Ebk00hQkhssDnhx794Zl2bKaPi2GYRhGzXAGA8MwWQrp+m7YsEE5sT9mzBgsX748yz5v9+7dIgLu5cuXYrtgwYK4fPmycvCsDdBkf705p7Dy7PMs+4yA8Bh0X3kZW66+QUx8IoZu+g/RcZovts0wDMMwjPZAWZ1U76BmzZpi+9WrVyKTwc/PL0s+LzAwUMgxLV68WGyTfTh79mysWbMmWzNMGUYBXYM/tyiO0rntlfI9VtWri/Xoe/cQffu22oN/ftl3H4lJfovOFXNjY7/KcLLWz+s/ZMcOUTSbMM2XDy4jhmv6lBiGYZgsgB0MDMNkOZ07d07hVBg8eDA2b96s9uiYmTNnCs1e0hImKAqPnAuFCxeGthAUEYseqy4jNDoev+5/gHUX5I4QdfLAJxQtF57HlZeBYtvG3Bgz2pbUq0JxDMMwDMOoByqqvHfvXpQrV05sP3r0SARmBAerN/vxwYMHot4CZSoQNjY24nMp+ETf9OYZ3ca2c2flepC3esYsgRGx6L5KHvxDUIHpn1sUw8y2JWFqrJ/TMnE+PvCd+bt8w9AQHiyNxDAMo7fo5y8ZwzBaR//+/UUNBIUzoEePHqJGgzqIiopC9+7dMWHCBGUaMxV2pkLTDg4O0CYcrEwxrklR5fbPe+5h0+VXanv/I/c+oN2SC3gXLC9K5+VshV3DqqN2If1Mu2YYhmEY5tshOcnDhw+jaFG5jXLz5k00a9YMERERaulessmoPtezZ8/EtpeXFy5duiQ+g2G0icjYePz01ga+FvKMhtCDBxGfVCckszz6EIaWC8/hyovk4J+1fSqhT/V8eutc+0waqU9vWHB9FYZhGL2FHQwMw2QbVANh6tSpYp00dzt27Ijjx49/03u+f/8etWvXhre3t9g2MTER2RLz589X1n7QNrpWzoNpLYsrtyfuvIt/kqKZvsWIX3TyKQZuuI7IWLkUUs2Cztg5tDryu1h/8zkzDMMwDKPfODs74+jRo8iXL5/YvnDhgsgMjYmJ+Sb7ZO7cuWjevDlCQ0PFvjp16uDKlSsoVqyY2s6dYdTFu6AoXHoZjAP5qoptWWwsgrdt+6b3PP3YD2+D5ME/+ZKCf2rpefAP9VnEuXNi3dTLCy4jRmj6lBiGYZgshB0MDMNkK1OmTMGPP/4o1mnA2qpVK1y8eDFT73X16lVRzJn+VQyMjx07hgEDBkDb6VUtLyY1S85kGLvjNnbeeJup96LaCj9suYnZhx8p9/Wtng9releEnaWJWs6XYRiGYRj9J2fOnMKWcnd3F9vkcOjSpQvi4+XFaDMC2XmUwUp2X2Jiotg3aNAgHDlyBE5OTmo/d4ZRBwXdbLC0R3kcz1sZcYZyedF3670hSypInhkG1PRCm7I5UaOAM3ZJIPgn7v17+P3+R0ppJK6xwjAMo9ewg4FhmGyF0oDnzJkjBpwEpd43bdpUpOJnBMpYoIKElMFAlCxZUjgaatWqBV2hf00vjG1cRKyTstPof25h7y15ezJCfKJMpF4TJkYGmNWuFKa0KAZjI37EMwzDMAyTMUi+iBwLCifAzp070bdvX6WTID1QkWiqhbV69WqxbWRkhIULF2LJkiUi25RhtJnqBZwxoVt1nPUoLbZN/T/g8pZ96f77+ITEz8Y/v7cribV99D/4R0gjTZqMxCR5Nad+fWFRWt6PDMMwjP7Cs08Mw2Q7ZGQvXbpUFH8mqIhgo0aNRFHBr0GDW6q10K1bN2XKPmVBnD9/Hnnz5oWuMaROfvzYsJBYT5QBI7feFHUUMoK1mTFW9qqAgq7W8B5QBR0r5s6is2UYhmEYRgoUL15c1GSgQszEhg0bRH0rRa2rL3H79m1RzPlckjyKvb09Dh06hGHDhumt3jyjf7Qrnws2nZKLPT9fsRb338tlvr6EX1g0Oiy7iC1XXqfYb2ZsJIngn+B//0XEhQti3bRAfjh//72mT4lhGIbJBrRToJxhGL2HItnWr18vMhj27t0Lf39/Eel29uxZUWhw7dq12L17NwICAkQEXevWrdG2bVsxuKX9CsjZMH36dBga6q7BPqJ+QcQlJGLBiaegYfe4HXcwcdfd5ANkMuFYEW1MGpjTAN/Z2gyHRsozNnI7WuLwyFowNOSBO8MwDMMw30758uWxb98+fPfdd4iOjsaiRYuEjTZmzJhU7bRevXrh9OnT6N69u7I4dOHChYWdV7BgQf5KGJ2je79muOC9GE4+L1H2w0P0m7kTMa4ecns7FfucMhfCouNFdvGdtyGi3kJlL+nIgcW9ewe/P2YlSyPNYGkkhmEYqcAOBoZhNAalyP/zzz9o1qwZTpw4gbdv34qIt7CwMDGQVYUGrKThq4icMzc3F2n3pAusD1AWg6WpMVacfY7AiNh0/c2nQYTsXGAYhmEYRp2Q9OSOHTtEtmhcXBxmzJiBWbNmfVaTgey0n376KcV+ckxs2bJFZDAwjC5CzoOig/vA7+efxXbTFxex0qpFuv6WnAs57Myhz9C4LGzPXsREhCOxUyf4TVaVRuoHi1KlNH2KDMMwTDahuyG/DMPoBeQooAi4KlWqiG3KZPjUuaBA4VyggeqZM2f0xrlAkGQAySUZZSADISQqDgmkq8QwDMMwDJNFNGnSBJs2bVLKG6VV8Fl1/8iRI0X2AzsXGF3HoUVzRJhYiPVGr67ALP7rgUD1irhix9Bq8HSygj4TeekS/CZNQuTM3xEwZw4iLlxMlkYaztJIDMMwUoIdDAzDaBxra2tRtDm9urxUe6FAgQKQOpamRhlySDAMwzAMw2QGkrE0Nk5f8rupqSmmTJmS7uMZRpsxtLTE2fyVxbpNXBRqvbv5Vft8Rc8KsDHX/2LO/gsXKbdDvTfLV4yM4DFzJgxNTTV3cgzDMEy2ww4GhmG0AspiSE/hQCIqKkrUb5A6ZiZGmj4FhmEYhmEkwLp164REUnqIjY1lO43RK04Urqlcb/7iwuc6pSpYmRlLIgCIsheirl9P3pGYKP5x6t8fFiVLau7EGIZhGI3ADgaGYbQC1cLNWXE8wzAMwzAMkznYTmOkzAdbV/znUkisFwp+i0LBbyBFZAkJiPPzQ+TtO/jw62+fvW5gbg6noUM0cm4MwzCMZuG8VYZhtIKQkJAMHR8cHJxl58IwDMMwDMMkw3YaI3X2elVDOf/HYr3F8/P4s3we6BOJUVGI9/VFnK8f4v18k9fFvx8QT+v+/kBCQprvIYuORvSNG7BKqq3HMAzDSAd2MDAMoxXY2dll6HguGsgwDMMwDJM9sJ3GSJ0rOYrB18IeblHBqPXuFlaUaIlQM+0v4kwStAlBQUmOAnIckNPgg8q6r8hKSMxgsFda+C9cCMvKldNdW49hGIbRD9jBwDCMVtCqVSucOnUqQ8czDMMwDMMwWQ/baYzUSTQwxMG8VdH7wUGYJsZj6O0duOpWFMdzlwc0NJkui41FnJ+/cBioZhxQBoJY//AB8X5+kKWzfsqXCl0bu7mJxcDQABEXLqZ5bNS164i8fJmzGBiGYSQGOxgYhtEKevXqhQkTJogCzl/D0tJSHM8wDMMwDMNkPWynMQxwKG8ldHt0BCaJCaj97pZYPlrY4ZZLQbVnHSSGhiZnGQiHgS/iPyRJF/nJHQkJgYHf9kEGBjBycoJJkvPA2M1Vvu7qBpMcin1uMLK2Vp7Xq+49vvq2nMXAMAwjPdjBwDCMVuDg4ICFCxeiX79+Xz12wYIFLJHEMAzDMAyTTbCdxjBAiJkNzrqXQr13N5Td0e3hEdxyLpDuLAZZfDziP36UOwqSHAbKjAPfZAeCLB1BV1/CwMxMOAdMXF3ljoIcbkrngdKR4OICAxOTdL9n5KVLiLp+/avHcRYDwzCM9GAHA8MwWkPfvn3Fv99//32qmQyUuUDOBcVx+oiTlennOymKKTERhoaGKQYvqR7LMAzDMAyTBbCdxkgVVZv7nbsXoOJgKBnwArUiXuGBe2GYx0UjX2wgIi5eTFnjIMlxIJaAACAx8ZvOx8jeHsY5csgdBcJhoOI0cMsBEzdXGNrZqb0OQtDmLek/1nszyyQxDMNICHYwMAyjdYPXNm3aYN26ddi9ezc+fvwIZ2dntG7dGj179hQRdPrMoZG1PtsXGxuLwMBAODo6wtSUnQoMwzAMw2gGqdtpjDRR2OdyiaA1+DQMasK5lYCREWQREWL79dZMfpCJCUxcXJTSROQoIIdBsvOAMhBcYWhmBk3g0LUrIm/8l3KnDCqBUCmPZRiGYaQDOxgYhtE6aHA6cuRIDB06lCfWGYZhGIZhtAi20xipIpcI+mSCnebYo6O/+reGNjbyugauadc7MHJwgAFN1GspVlUqo9DZsyn2cSAUwzAMQ7CDgWEYhmEYhmEYhmEYJg0oe8F/4aI0+8fAygpWVavAhDIOUql3YGhpyX3LMAzD6C3sYGAYhmEYhmEYhmEYhslkgWOSR3Ls3p3rDjAMwzCSRHvz7xiGYRiGYRiGYRiGYbQ4e0GB/8KF4liGYRiGkRrsYGAYhmEYhmEYhmEYhslE9oKCqGvXEXn5MvchwzAMIznYwcAwDMMwDMMwDMMwDJMKQZu3pLtfgrw3cx8yDMMwkoNrMDAMwzAMwzAMwzAMw6SCQ9euiLzxX8qdMiAxMRGGhoaAQcpjGYZhGEZqsIOBYRiGYRiGYRiGYRgmFayqVEahs2dT7IuNjUVgYCAcHR1hamrK/cYwDMNIGpZIYhiGYRiGYRiGYRiGYRiGYRgmw7CDgWEYhmEYhmEYhmEYhmEYhmGYDMMOBoZhGIZhGIZhGIZhGIZhGIZhMgw7GBiGYRiGYRiGYRiGYRiGYRiGyTDsYGAYhmEYhmEYhmEYhmEYhmEYJsOwg4FhGIZhGIZhGIZhGIZhGIZhmAzDDgaGYRiGYRiGYRiGYRiGYRiGYTIMOxgYhmEYhmEYhmEYhmEYhmEYhskw7GBgGIZhGIZhGIZhGIZhGIZhGCbDGGf8T/SbiIgI8e+dO3c0dg5xcXEIDQ2Fra0tTExMIDWk3n4F3A/cB3wtSPuekFp7v4TU+0Lq7VfA/aD5PlDYxwp7WZOwza55NH09agvcD9LsB6m1Ny2k3g9Sb78qUu8LqbdfAfeD9vRDdtvt7GD4hOfPn4t/Bw0alC1fAMMwDMMwDMPoor2sDefANjvDMAzDMAzDaNZuN5DJZLJs+SQd4f3799i3bx+8vLxgZWWlMS8TDZaWLVuGkiVLQmpIvf0KuB+4D/hakPY9IbX2fgmp94XU26+A+0HzfUARUDRIad68OTw8PKBJ2GbXPJq+HrUF7gdp9oPU2psWUu8HqbdfFan3hdTbr4D7QXv6Ibvtds5g+ATq9IEDB0IboIuwatWqkCpSb78C7gfuA74WpH1PSK29X0LqfSH19ivgfuA+INhm1x74nuR+kPL1ILX2poXU+0Hq7VdF6n0h9fYr4H6QXj9wkWeGYRiGYRiGYRiGYRiGYRiGYTIMOxgYhmEYhmEYhmEYhmEYhmEYhskw7GBgGIZhGIZhGIZhGIZhGIZhGCbDsINBC8mVKxd+/vln8a8UkXr7FXA/cB/wtSDte0Jq7f0SUu8LqbdfAfcD94G2IfVrUurtV8D9IM1+kFp700Lq/SD19qsi9b6QevsVcD9Itx8MZDKZTNMnwTAMwzAMwzAMwzAMwzAMwzCMbsEZDAzDMAzDMAzDMAzDMAzDMAzDZBh2MDAMwzAMwzAMwzAMwzAMwzAMk2HYwcAwDMMwDMMwDMMwDMMwDMMwTIZhBwPDMAzDMAzDMAzDMAzDMAzDMBmGHQwMwzAMwzAMwzAMwzAMwzAMw2QYdjAwDMMwDMMwDMMwDMMwDMMwDJNh2MHAMAzDMAzDMAzDMAzDMAzDMEyGYQcDo7fIZDJNnwKjJfC1wDCM6rMgMTGRO4RRItXr4dGjRwgKCtL0aTAM22kMwwjYTmM+hW006aI6hyPV60DXYAeDhJDaJKuBgYGk2/8pUm6/4lpQ9IGU+4JJHakZLQkJCZAiT548Ef8aGhpK7jsnTpw4gatXr2r6NLSCixcvYsWKFYiOjhbXg9TYvHkzqlWrhmfPnoltKd4P2oaUbRO205ivIbVnFNtpbKdJGbbR2EYjyEanQJjIyEhJ2uq6+JvI35KecunSJfz999/44YcfMG3aNDx+/Bjh4eGQCmfPnsXMmTMxZMgQTJkyRQyg6QEl1Qm1kJAQMXiT4uCVJtMWLVqEXr16ieuB7oVPnU9SIDg4WJLff2rcv38f+/fvx4wZM7B+/Xql0aKvg7n//vsPq1evFr8Hc+bMQUREBIyMjPS2vV+aUC1SpAh+++03SToZ1qxZgwYNGuDu3buIj4+HlPH29kanTp2wZcsWnD9/HlJj7dq16Natmxi0zZ49W1wPPHDTHGynsZ2mgG01OWynsZ1GsJ0mTdhGYxuNOHToEHr27ImCBQuiZMmSWLlypWTn8/777z9s2rQJv/76q+gHf39/7bXbZYzesX79epmDg4PM2dlZZm9vLzMwMJA5OjrKfvjhB9nt27dl+s66detk1tbWsty5c8tcXFxE+6k/xo4dK3v48KFMSnh7e4t+mD17tiw0NFTsS0xMlEmFzZs3i/bb2tqKha6FnDlzyk6fPi1ej4+Pl0mBDRs2yKpXry67du2aTOps3bpVVqRIEZmRkZG4HmipVKmSLCwsTC/vjy1btsi8vLzEM9DU1FS0t169erKoqCiZlPj48aOsYsWKov3GxsayX3/9VflaQkKCTN9Zs2aNaPvIkSNlb968kUmZf/75R2ZmZiYbMmSI7PLly5+9ru/Xg+JaGDFihKxs2bLCTrp586Yk2q6NsJ3GdpoCttXksJ3GdhrbadK109hGYxuN2Lhxo5jPo/mLFi1ayEqWLCnGso8ePZJJjQ0bNshcXV1lVlZWMkNDQ2HD58mTRzZv3jzZixcvZNoGOxj0jAMHDsjMzc1lw4cPV04mbtq0SVatWjVxQdLE0rlz52T6yvnz58XDZ9SoUbL79++LfceOHZN17NhR3IzNmjWT/ffffzIpcPLkSZmFhYVod65cuWR///23pJwM27dvV94LdM3TxMmiRYvEA7pMmTKy6OhomRQ4fPiwciK9Zs2ayokkqRqtNMk+YMAA2c6dO2XPnz+Xde/eXfRNnz599M7hRBNXNEgbOnSocKrRfd+5c2fR3j179ohj6L6QwvOAaN26tSxHjhzi95D64Pfff1e+pm/fvSqrV69WOhdev36d5nFSuA7IuUKOpl69esmePXuWYv/Tp09lERERMik4FyjgJCgoSEzk0faUKVM0fWqShO00ttMUsK0mh+00ttPYTpOuncY2GttoxJEjR0TwC83nPX78WOw7deqUzMTERMxrSok9e/aIuYvvv/9edubMGVlkZKQYv1LwoI2Njaxv375aF0DODgY9gX5wKCKVJsuKFy8ue/DggfI12k9RrJTFQBOu5AnU10n2+fPni8yNK1eufPZjPHr0aDGQrl+/vtbdiOqGJpG+++47pWOBohTJ8SIVJwNlqlBUeo8ePWQvX75U7ienwsCBA8V1cO/ePZm+QxNm5FTImzevmGSma4D6RYpOBnrm0bOxf//+slevXin3x8bGysqVKycrVqyYXjmdaOLK09NTNmjQoBTtpclmMtrIeJMKiqjsOXPmyJo2bSqcLRQJQ8+BmTNnKo/Tx2ciOVqpnVOnTpW9fftWuX/VqlWyH3/8Uda1a1fZTz/9JHv37p1MCpBtQNlsZBMpGDx4sCx//vxi4FK4cGFhuD958kSmb6xcuVJkbtH3/v79e+VvJTndablz546mT1FSsJ3GdpoCttXksJ0mh+00ttOkaqexjSZtG43GYXFxcWKuhoJBVedq7t69K8ZuNH49fvy4CBLU56CgxMREWUhIiMjeoLkbhaOFoHbPmjVLjO/s7Oxk3bp1E3aEtsAOBj0iPDxcTJI1b95cuY9uUsWFSJNNJBdDF2O/fv1kgYGBMn2DJg9JFkoxia5ov4Jx48Ypo5UVD2995MKFCyKtjGShFA/lUqVKScLJQG1aunSpmERSRGmrXgsnTpwQ18D+/ftl+gxFZJOXn9pKElnULwsWLBA/RFJzMtB3//PPP8s8PDxEBIQChUPhl19+UTqd9EEihO7vnj17ymrXri27fv16itfIcKV7gwwWiuKmrLZDhw4JI0bfIaOUJpEpQoqekaVLl07hZIiJidEr5zvJQjVo0OCzCHX67imzhVJtFdJxZB/QdaDPvwsKCUkKtqDofaJRo0YiAogG8HQ/KBxPnTp10itJRbquFbJIPj4+KV6j3wfKcFVEhenDM1AXYDuN7TSCbTU5bKclw3Ya22lSs9PYRmMbTTUwmsZnNH5RZe7cueKeoHkMGsvRv+R408eAIAU0VqH7nsb0n85n0bidAgbd3d2FDT99+nRhT2jDs4EdDHqEn5+fiL4rWLBgipuNLkSaTKcodko9bdOmjZh8vnr1qkxf0/9pEkEB3WiqA2ZyQpD+Mkmk6Otg+sOHD7Jdu3al6INbt26JB/anTgZ9lAahiRIyzlKDpMPoGtm9e7fY1oYHcVZx8eJF4eFWEBAQIL57csJ96mTQx/tAlUmTJolnX2rQ84KuCX2aUKQI7cWLF6fYt2LFCmGU1alTR0Tzk3wY/WbQ9UD1SvT9OiBJHKrBsnfvXmWWh8LJQBH+7dq1E45YfYoSI3m4xo0bizYuWbJEONcpEooiJCm7iwITSMOTUm0p400RIaOvz0XqD+oLut5poE59QdKSit9Bcj717t1b6ZTRFmP9W6E2UHtVr23FvU6/iWQXUIYX2ZFM9sB2GttpCthWk8N2GttpbKdJ205jG41ttODgYBH8RnOVNF6j4D8as5JzgSbaSdqT5vBI9pZsdVIooTktfbwfnj9/LpRZqD/8/f2VbaS5XXoOUE1Jek6QOg05G74kg5udsINBzxg/fry42ShaVyENQ1GZFA1BUXo0uKS0IppkIukMQp9uyEuXLokHUokSJT5zoCjaSf1CTpjKlSt/luGgTygmTFS/30+dDPQQV0DyGarbuo5iokS1/bRO2Rx0jygcTKpeYoXTRZ8gCSDV64G+Y5ISU3UyqDqZ9DXdkAx0+nFO7ZmnkJH51MFAz05dI7XnOe2j+jTURsriUp1kJGOeBixkpCgKXeszVapUERPICqhfFFHrVLNm37594ndB138XVc+fUs5JGpDaSINWyuxSPBcIWifnE73evn17mT5DwRek70yZnpTJSZPq5HhVhbZr1Kgh7gtdn3BP73VMgzb6/ulZqK+BB9oI22lspylgW43tNLbT5LCdJl07jW201JGajUaBfyTpSW1WqK9Q/URfX1/lMTRnQwFUNLGuWlNN3+jbt68IjCbJNMU8Hdn2VFfPzc1NZCXTa9RHv/32m/J1TcIOBj2DJsiaNGkiLrLy5csLDXqaSKcLc926dcobkiaT0orm1XUUmmSkR6Zai0L1ZqObleRS9FkmKS1UnQxU9JgmXkk2hqQiSFpI1yOYv/ZQffHihbg+NmzYoNxHTgeqX0Lt17cf7dT641MnA7WfoAjXtm3b6m19irSu7aNHj4prQrV2C9VpISesom/04bunrJ3UnIhU+NnS0lKn2/q1flDc1xQZRhkcqlDkB0XGqBpn+hgh26xZM2Vx30/vCSoaRhKLZDfoomMtI1C2Cn3X9PxTTcFWzVagIA06RlVSTR/49Jmg+P7J0Uz9QVk8jOZhO01adhrBtpocttPYTmM7Tdp2GttoyUjZRiMnGwXF0UR6tWrVhMS1AkWAMEk/k62wceNGmb5y/PhxoUJDQXD0/VPQeMOGDcXcrkLalBwvFDw1ZMgQmTZgDEYnOXfuHK5du4Z79+6hcuXKKFGiBKpUqYLChQtj/vz5WLJkCdasWYP379/Dzc0NBw4cQM2aNcXf2tjYwNjYWCy6yocPH5AjR44U+xITE2FoaIgxY8bgxYsXWLp0KUxMTDB69GjRPwYGBspjbW1tYWZmptN98KW++BKlSpXC2rVr0adPH0yaNAkPHz7E+fPncePGDcybN0/0oS63X/V7To34+HjxL33/xP379zF+/Hjs27cP48aNg5GREXSRK1euiLY8ePAAtWvXhpeXF4oUKZJqf9jZ2aFXr17kYMbUqVPRr18/saxcuRJXr17FjBkzoMuk1RdpXdsJCQniX3Nzc/Ev/R3dG3v37sXIkSOh6989tY+u65YtW372vCSio6ORO3dueHh4QJf5Uj8o+qJ58+biWn/y5In4bezevbv4HZ0wYYJ4BtD3bmlpqRPfe3rbT5B9MHnyZNFme3t75d8o+sXCwkL8HtJzkX43dZ0v9cWwYcPE9+/t7Y3jx49j69at6NSpU4pnP90f1Fc5c+aEPv8eKJ4BuXLlErbBjh07hL3YtGlTDZ25fsJ2GttpCthW+3I/sJ3Gdhrbafpvp7GNxjba166DFi1aiIXo0qULYmNjlfa5Yv4uMDAQDg4OKFq0KPStL/LlyyfaVa9ePcyaNQurV6/Gli1bYGVlBXd3d+zcuRP169dXzuuYmpoq5zM0jqY9HEzm0obIi0lpMbSQ587c3Fw2Y8aMFPImFKlNhZw/lb2gQpd58uQRXj9tSKPJTPsp2lS1xkBq2rYkf0B9Q5H5hw8fThEFRVHbTZs21Xk5mPT0RVrcuXNH6K8rIjkpYlvf20+RANRORZohpdRRxg/Jauly0WPqB0oRpKwUagu1L1++fLK1a9d+8e8oe4Wksujv6G+oYJIuXgff2hckl0XHUcYTpedSpLeuXBOZaa9qhODp06eFruvAgQOVRa91kfT2A8noUbbGwYMHReYGPfu8vb2VfVGzZk2dzOTIyHWg+M1X/e2n30gqFDZx4kSZrpOeviAJxS5duojXqC6HqmQeFUSmzE8qkq4aRajvvwd0T1BKOkWMMer9PthOYzvtW+5NfbPV2E5jO43tNOnaaWyjsY2W3uuAshVJAohUR2hej+qkqdrqNJ9H2Q0KCWR964vVq1enOI4UJqjOAhV4VoVqVdBYRlGDVtNzu+xg0DHOnj0railQQRO6sQgq3Exp/nQxkvTPp9XUVSeTaFBNE6r58+eXvXr1SqaLaULUfoWB/aWJZXKs0I8wHUuDu65du4oJBXoY0Q2si5NIme2L1KBUM3IwUF/ooiROZttPRXHob3766SdZq1atZFZWVjoxkfyl75EmTEeNGiW7cOGCcCouXLhQ1Bmhdk6ePFmk1aYFyebQj5qjo6NOXgfq6AuShqLXScOQnAu6ck1kpr2q0hIkm0MOWDLcPv3d0CUy2g/lypVTOlap2C9N3ij40r2ir9cBOV0o3ZYCD6igmC7ztb4gm0Cha0zPu6FDh4r9tJCNQOnHZcqU0VkbIbPPQBqM0CCOak8YGhrq9OSlNsF2GttpCthW+7Z+YDuN7TQFbKfprp3GNhrbaOn9HYiKilJeNyT9Q/VjyU7fsWOH7M8//xTytjT/o4u2ekb6YtKkScqA6NQcj9evXxe1KEj+nuqpagPsYNAxZs+eLSYDP538un//vtAoo+gzqrtAA8VPoZuRdPtIo4v0XXUNcoh89913YjKMilmTDiHpkX1tYpkiEzt16iSyPQoUKCBqT1B/6TKZ7QtVRxX1BU2i6OJEwre0n4p829raigl18hLfuHFDposoflwo2tTT0zNFvRFF8V661unHaezYsZ/9HXHy5ElR5JQmWimjRVfJbF8onK80CUSvkcONfuS1/ZrIbHtVIeOFahFQ0V9d/D34ln6gSWbKVKDMBcVAVdPRHpq4DujvKZORIvXJrtDV6yCjfUHOZVUoWor6gAYq9LetW7fWORtBHb8HxIQJE8QxuhiAom2wncZ2GsG2mhy209hOYztNunYa22hso33L/UDznhQApAgIIuUWqicqxbkLVejZULVqVTGW16b5PHYw6Bjff/+9mBRVoIjEIyht6H//+99nA2i6gClqm7x/HTt2FIWgdbXYCxU0URThJA8mTQimNbGsOnCmdSpuTf2lyzIgme2LT6GHUKFChYTXU0rtp+uAjDO6R+g+0nWvN0HOM4o8Tu2ZQN8zvU7tnTdvXoq/o+NoYi137txaP6Ge1X2xb98+sZ8cT7pkrGSmvfQcpPuGjDOaZNe1idRv6QdysiueA3Tv67pE3rdcBxQZRMVSKbuP0ov14TrISF/89ddfKf6OHE2UYk3/qkZNSeUZqHC2UttVU9CZzMN2Gttp6rg39c1WYzuN7TSC7TRp2mlso7GNltnrgCRLqagxScJv27Yt1WBqKf0m3rx5U9ayZUtZ8+bNte7ZwA4GHWP69OniIqPIS8WAUHUineQNunXrJo6hm08VGjx/Wo9BlyC9sUWLFqXY9++//4qUoE8nlj9NIVJUm1fdp8tkpi8UKK4bXUwxVUf7iZUrV2qVpzez0HdJ2vkkaXHmzJlUU+euXbsmZC8otZDS8FShH2c/Pz+ZPvAtfREcHCxk53RJIupb2ktySAcOHJD5+vrKdJ2M9sPRo0dl+sS3XAdkD5Cmr74Y6d/SF/pgF3zr7wGjXthOYztNXfemvthqbKexncZ2mnTtNLbR2EbLzHVw7Ngxmb6S8I3XBNVjoDkMbYMdDDoGFaUlaReqo0CFjBWoXoh0gTo7O8tatGghJtZVtZZ1FdU6Ep86DNKaWCbev38v0zek3hdSb/+nXL58WbSXih+p9pHqM4FkwujHa/jw4WJbH54J6uoLxWuqEQP63F59JDP98OlzRKrXvb7B14K07wVtQep2itTbnxpsq2W+H9hO0334t5ntNL4O+D74lucBz10YKvtC1abSRtjBoEPQjUcX1LRp00SGAhUnVL3ZVA36QYMGyZycnD6rMq5PqLaXsjUUAxaSOyHI40/7KJ1K35F6X0i5/QEBAbLevXuLZ8Ivv/yi3E8/0qo/1FTQmmSxdHEiPSv7QpcnWqXW3rSQ+j0g9farIvW+kHr7tRkp2ymE1NvP96Y07RaptTctpH79S739CqTeD1JvvwLuB/3uC3Yw6CBUT4FqKdCFOGLECFl4ePhnxwwePFjm5eWl0zI4GR2w/PPPP7KiRYuKAQtJSZFeIekW6oNmaXqQel9Iuf1Xr16VVapUSTwTSJswNahQUMmSJWX6jtT6QmrtTQup94PU26+K1PtC6u3XZqRspxBSbz/fm9LsB6m1Ny2k3g9Sb78CqfeD1NuvgPtBf/uCHQw6ChngVNiDLsSuXbuKVCMFVLySDHUq+qHLxQozM2DZvn27cKxQv9jZ2emFzn5GkHpfSLn9p06dkpUqVUq098cff5S9ffs2xTOhYsWKsi5duuhtdJSU+0Jq7U0LqfeD1NuvitT7Qurt12akbKcQUm8/35vS7AeptTctpN4PUm+/Aqn3g9Tbr4D7QT/7woD+B0YnefDgARYsWIC1a9fC1tYWNWvWhKOjI65fv47nz5/j3LlzKFasGKTEqVOn0LNnT4SHh0uy/apIvS/0qf30mDYwMPjqaxcvXsSvv/6KQ4cOoXjx4qhTpw6srKxEXzx+/Bjnz59HkSJFoMtIrS+k1t60kHo/SL39qki9L6Tefn1Cn+yUzKBv7ed7U5r9ILX2poXU+0Hq7Vcg9X6QevsVcD9IuC807eFgkklPtoHCY/Xx40dRf4Eqhx88eFBWtWpVmYeHh4gEouLO9+7d0/v2h4aGpnjtwoULInXI2tpadufOHZkuI/W+kHr7Ffj7+3+1qJGiH8LCwpSF4JcvXy50+mxsbGQ5c+aU1a9fX3i/dRmp9YXU2psWUu8HqbdfFan3hdTbr21I3U6RevtV4XtTmv0gtfamhdT7QertVyD1fpB6+xVwPyQj1b5gB4OWsHTpUln//v1Trafw6QVIRnmZMmVkJ06cUL5G6TJ+fn7CiNfFugsZbX+5cuVStJ9e27Vrl3C06Lp+q9T7QurtV7Bnzx6RCvfXX3+lkBRIrR/Onz8v2qv640M/VA8fPpS9evXqs4G9riG1vpBae9NC6v0g9farIvW+kHr7tQ2p2ylSb78qfG9Ksx+k1t60kHo/SL39CqTeD1JvvwLuB+4LwlDTGRQMsG7dOgwZMgQmJiZISEhIs0sofebq1ato0aIFXFxclCky5Ciiv6V9Tk5OsLCw0Pv2UzuLFi2a4rXGjRtj//79KFOmDHQVqfeF1NuvYMOGDejWrRtiYmJQsGBBGBrKH9WqinaKlDrqh5YtW4r7nvqCSExMhLW1NQoXLow8efLAxsYGuorU+kJq7U0LqfeD1NuvitT7Qurt1zakbqdIvf2q8L0pzX6QWnvTQur9IPX2K5B6P0i9/Qq4H7gvlGjY0SV51qxZI4p5jBkzRvbmzZtU+0PhCaUoHyMjI1nbtm3TPFaq7df2YifpQep9IfX2Kzhy5IjM1tZWNnLkyDSlzhRtvHbtmszU1FSvnglS7guptTctpN4PUm+/KlLvC6m3X9uQup0i9farwvemNPtBau1NC6n3g9Tbr0Dq/SD19ivgfuC+UMU42dXAaMLT17dvX4waNQrDhg1Drly5xP6goCB8/PhRFGy2t7eHkZERYmNjcePGDfTu3RtTpkxRHqvLqLP9aRVO0RWk3hdSbz+RJFmH7du3o1y5chg4cKAy4m/Lli0ICAhASEgIOnXqJNpsZmaGvXv3omPHjvjtt9/04pkg1b6QWnvTQur9IPX2qyL1vpB6+7URqdspUm+/Ar43pdkPUmtvWki9H6TefgVS7wept18B9wP3RaqkcDcw2cahQ4dEFBAV7VCtmTBq1ChZ0aJFxWtubm6yZs2ayXx8fMRrVNA5IiJCL74lqbdfFan3hdTbrwoVAqKiPsOGDVPua9OmjczY2FhmYmIi+sLZ2Vn266+/ygIDA4X+MfWFPiK1vpBae9NC6v0g9farIvW+kHr7tQmp2ylSb/+n8L0pzX6QWnvTQur9IPX2K5B6P/y/vXsBsrKs4zj+cBEW2AUWMS5xSwiMiyFWooGiiRBqAdK4XZQ085IRMybmhZlkHC9hKTmQaFwqp2Q0LmIsmIoaUixZXJaLBhIIRqZpSMKyu+3TPE/znJ6zuy9yll32nP19PzME+56zZ8/vd+a8vZ7/vu+jnj+gB7qojjUYGklZWZnp3bu32bhxo1m5cqXfdvHFF5tHHnnE9OvXz0yfPt0MHDjQFBcXm3PPPde88cYbpkOHDiYvL880Ber5Y+pdqOePVVRU+Gs4FhYW+q+/9rWvmZdfftnMmjXLlJSUmDlz5vguZsyY4be53wJ0XTRFal2o5U2i3oN6/ph6F+r5s4n6cYp6/up4b2r2oJY3iXoP6vkD9R7U8wf0QBc11Bg54IRZsWKFPe2002xhYaH91Kc+Zbt162afeuopv5K8435L6J577vET0BEjRtgjR440qVdHPX9MvQv1/OG6xeXl5faiiy6yQ4cOtc8++6wdNGiQfeSRR1J5Kyoq/DUeR48ebTt27Gi3bNlimyK1LtTyJlHvQT1/TL0L9fzZSP04RT1/wHtTswe1vEnUe1DPH6j3oJ4/oAe6qA0DhhMkXtDM7XCC3/zmN/704u7du9v58+en7ZQc97VbDMYtlLZp0yabq9Tzx9S7UM9fWw/xv2fPnu3/A33y5Mm2U6dOdt26dWk9uL+feOIJf59bb73VNgVqXajlTaLeg3r+mHoX6vmzjfpxinr+GO9NzR7U8iZR70E9f6Deg3r+gB7o4lgwYGjEN2awbNky+9WvftXu27cvbXs4cF+0aJHfMa1cudLmOvX8MfUu1PMn9eB+G/CSSy7xOd2fX/ziF6nb3G9LOO46jm3atLHTpk2zTYlaF2p5k6j3oJ4/pt6Fev5so36cop4/xntTswe1vEnUe1DPH6j3oJ4/oAe6OJqWNS+ahPq2du1as3r1an9dtlatWpkpU6aY4cOHm/bt2/vbv/jFL5pRo0alXZfNDX/cfZ0//vGPpqCgILU6fa5Rzx9T70I9/7H0kJ+f778+fPiwv8/MmTNNnz59zMiRI81JJ53kv/93v/udv7Zx3759Ux25azvmIrUu1PImUe9BPX9MvQv1/NlG/ThFPX+M96ZmD2p5k6j3oJ4/UO9BPX9AD3RxzI46fsBx++Uvf2m7dOnir1Xap08ff9pwhw4d7Lx589Kmm9WvZxaUlJTYM888044ZMyYnV55Xzx9T70I9/7H2ECxdutReeOGF/jcihg0bZhcvXux/C6K4uNiOHTvW9uzZ0+7Zs6fRctQHtS7U8iZR70E9f0y9C/X82Ub9OEU9f4z3pmYPanmTqPegnj9Q70E9f0APdJEJBgwNyJ1G3K5dOzt16lT7yiuv+G1PP/203/H06tXLvvfee0f9/hdeeMHvrNw13bZt22ZzjXr+mHoX6vnr2sP69evttdcue15PAAAVM0lEQVRemzr1Mi8vzxYUFPgDlVy/vrFaF2p5k6j3oJ4/pt6Fev5so36cop4/xntTswe1vEnUe1DPH6j3oJ4/oAe6yBQDhgby+uuv2xEjRtiioiK7a9eutGuU3nXXXX7H41acr01ZWZn9xje+YQcOHOinpZs3b7a5Rj1/TL0L9fx16SH+jUBn+fLl9u6777Y33HCDnTt3rt29e7fNZWpdqOVNot6Dev6Yehfq+bON+nGKev4Y703NHtTyJlHvQT1/oN6Dev6AHuiiLhgwNBC3YrybWj7++OOpbWEHtH37dr9jWrBgQa3f+9prr/mDdbdT27Fjh81F6vlj6l2o56+PHpoatS7U8iZR70E9f0y9C/X82Ub9OEU9f4z3pmYPanmTqPegnj9Q70E9f0APdFEXLPLcQNzCLxMnTjRFRUVhrQvTvHlz/++wEFpZWZn/u6qqKnWb079/f3P//ff7+7Vr187kIvX8MfUu1PPXRw+5vChUbdS6UMubRL0H9fwx9S7U82cb9eMU9fwx3puaPajlTaLeg3r+QL0H9fwBPdBFXTBgqGdhhzJmzBhz5plnpm0LOyG3Y3Iry//nP//x28JO6R//+IeprKw03bt3N4WFhSYXqeePqXehnr++enC3d+3atUkcqKh1oZY3iXoP6vlj6l2o58826scp6vljvDc1e1DLm0S9B/X8gXoP6vkDeqCL45E+bsNxvRHdgXasc+fO/u94J+N2Qm3btvX3/+CDD1Lbt23bZqZMmWIeeughU15ennOvhHr+mHoX6vnru4dZs2bldA+KXajlTaLeg3r+mHoX6vmzjfpxinr+GO9NzR7U8iZR70E9f6Deg3r+gB7ooj5wBkM9WLVqlVmxYoUpLS01PXv2NKNHjzaTJk3yO6DaTpNyE0+3LZxitXXrVnPbbbf5x9i0aVNqe65Qzx9T70I9f0APul2o5U2i3oN6/ph6F+r5s43666GeP0YXmj2o5U2i3oN6/kC9B/X8AT3QRb2p08oNSHnsscdsXl6eHTRokD377LPtKaec4hd+GT9+vH3uuedqLAxTWVlp33jjDdu2bVv74IMP+tXZx44da/Pz8+3GjRtzrln1/DH1LtTzB/Sg24Va3iTqPajnj6l3oZ4/26i/Hur5Y3Sh2YNa3iTqPajnD9R7UM8f0ANd1CcGDMdhw4YNtkuXLnbq1Kl2x44dfltpaam99957bbt27ezgwYPtokWLUvevqqryf//973+3rVu3tldeeaWdOHGiv28u7pTU88fUu1DPH9CDbhdqeZOo96CeP6behXr+bKP+eqjnj9GFZg9qeZOo96CeP1DvQT1/QA90Ud8YMByH5cuX+x3MM888k7a9vLzcPvXUU7ZDhw62f//+/n6xd9991/bo0cM2b97cFhQU+Dd2LlLPH1PvQj1/QA+6XajlTaLeg3r+mHoX6vmzjfrroZ4/RheaPajlTaLeg3r+QL0H9fwBPdBFfWPAcBxmz57tT6Nyp0eFHVJs5cqVfsczcuTI1GS0oqLC7tq1y59a1bFjR7t161abq9Tzx9S7UM8f0INuF2p5k6j3oJ4/pt6Fev5so/56qOeP0YVmD2p5k6j3oJ4/UO9BPX9AD3RR3xgwHIfVq1f7HdO3v/3t1LXZwulTwbx582yLFi3s9OnT07YvXrzYbt++3eYy9fwx9S7U8wf0oNuFWt4k6j2o54+pd6GeP9uovx7q+WN0odmDWt4k6j2o5w/Ue1DPH9ADXdQ3BgzH4cCBA3bIkCG2c+fOdunSpamdUrxz+tvf/uYXf+nUqZPdu3dvagfWFKjnj6l3oZ4/oAfdLtTyJlHvQT1/TL0L9fzZRv31UM8fowvNHtTyJlHvQT1/oN6Dev6AHuiivjFgOEY7d+60L730kr3//vvt+vXr7Ztvvum3r1mzxu90zjrrLP/vsFOKd0Bz5871E9ItW7bYXKWeP6behXr+gB50u1DLm0S9B/X8MfUu1PNnG/XXQz1/jC40e1DLm0S9B/X8gXoP6vkDeqCLE4EBwzF48skn7RlnnOFXiXc7mPbt29vrrrvO7tmzx9/+8MMP+9tGjBhhn332WVtZWZn2/T/60Y/sySefnLp+W65Rzx9T70I9f0APul2o5U2i3oN6/ph6F+r5s43666GeP0YXmj2o5U2i3oN6/kC9B/X8AT3QxYnCgOFDLFq0yLZp08YWFRXZhQsX2iVLlthx48b5HZTbITlvv/22nTVrll9t/rTTTrMPPPCALSsr87dt2rTJXnDBBfYzn/mM/de//mVzjXr+mHoX6vkDetDtQi1vEvUe1PPH1LtQz59t1F8P9fwxutDsQS1vEvUe1PMH6j2o5w/ogS5OJAYMR1FSUmL79u1rr7/+ert79+6067Gdeuqp/nQqt5q8c/DgQfvrX//a9ujRw++03A5q1KhRdsCAAX7qWVpaanONev6Yehfq+QN60O1CLW8S9R7U88fUu1DPn23UXw/1/DG60OxBLW8S9R7U8wfqPajnD+iBLk605ga1Ki8vN8uWLTMVFRXmiiuuML179/bbq6qqTLdu3czQoUPN3r17zTvvvOO35+fnm8suu8y88sor5uabbzY9evTwjzFq1Cjz+9//3gwePDinmlbPH1PvQj1/QA+6XajlTaLeg3r+mHoX6vmzjfrroZ4/RheaPajlTaLeg3r+QL0H9fwBPdBFY2jZKD81B7izO/bv328mTJhgzjnnnLTtzpAhQ8zzzz9vDh06lLrN7bS6dOliZs6cmfraad489+Y46vlj6l2o5w/oQbcLtbxJ1HtQzx9T70I9f7ZRfz3U88foQrMHtbxJ1HtQzx+o96CeP6AHumgMDBgStG7d2txzzz1+8hl2Mm4H06JFC/9127Zt/VSwZcv/V+huLysrM3l5eamvc5V6/ph6F+r5A3rQ7UItbxL1HtTzx9S7UM+fbdRfD/X8MbrQ7EEtbxL1HtTzB+o9qOcP6IEuGkPuv3MakDuFqlevXmk7mTDNdG9Yx+2IgldffdXceeedprS01DQF6vlj6l2o5w/oQbcLtbxJ1HtQzx9T70I9f7ZRfz3U88foQrMHtbxJ1HtQzx+o96CeP6AHujjRGDDUkZt4up1UmIRu27bN3HTTTWbu3LmmTZs2pqlTzx9T70I9f0APul2o5U2i3oN6/ph6F+r5s43666GeP0YXmj2o5U2i3oN6/kC9B/X8AT3QRUPgEkkZChPQysrK1KlWr7/+uvne975n1qxZ4//069fPNFXq+WPqXajnD+hBtwu1vEnUe1DPH1PvQj1/tlF/PdTzx+hCswe1vEnUe1DPH6j3oJ4/oAe6aEgMGOrI7ZDc5HPz5s1mwYIF5sUXXzQvv/yy+eQnP2kUqOePqXehnj+gB90u1PImUe9BPX9MvQv1/NlG/fVQzx+jC80e1PImUe9BPX+g3oN6/oAe6KIhMGCow2rszZo185M/N/285ZZbzN69e83atWsldkrq+WPqXajnD+hBtwu1vEnUe1DPH1PvQj1/tlF/PdTzx+hCswe1vEnUe1DPH6j3oJ4/oAe6aEgMGDLkdkph9Xk3+dy/f79Zt26dGTJkiFGgnj+m3oV6/oAedLtQy5tEvQf1/DH1LtTzZxv110M9f4wuNHtQy5tEvQf1/IF6D+r5A3qgiwZlUSd79uyxl156qd2+fbtkg+r5Y+pdqOcP6EG3C7W8SdR7UM8fU+9CPX+2UX891PPH6EKzB7W8SdR7UM8fqPegnj+gB7poCM3c/zTsCKPpKi8vN61atTKq1PPH1LtQzx/Qg24XanmTqPegnj+m3oV6/myj/nqo54/RhWYPanmTqPegnj9Q70E9f0APdFHfGDAAAAAAAAAAAICMNc/8WwAAAAAAAAAAgDoGDAAAAAAAAAAAIGMMGAAAAAAAAAAAQMYYMAAAAAAAAAAAgIwxYAAAAAAAAAAAABljwAAAAAAAAAAAADLGgAEAAAAAAAAAAGSMAQMAAAAAAAAAAMgYAwYAAE6AZs2ama9//et0DQAAAGQpjtkBIHMMGAAgR23cuNHceeedZvfu3SYXLVu2zD//psTlcbkAAAAAh2P27MMxOwDULwYMAJDD/7EyY8aMnB4wuOfflLg8DBgAAAAQcMyefThmB4D6xYABAFCDtdb8+9//phkAAAAgS3HMDgDIBgwYACBHT+u96qqr/L/PP/98f63Q+HqhBw8eNNOnTzdnnXWW6dy5s2ndurXp16+fufXWW82hQ4fSHuvFF1/03/uzn/3MzJkzxwwcONDk5eWZH/7wh/52d/+bbrrJdOvWzbRp08YMHz7cPP/88/5nue+rbseOHeaKK67w92/VqpXp06ePmTZtmvnggw9S9xk1apT5+c9/7v8dnnt4DkfjHst976ZNm8yFF15o8vPzzUc+8hHz3e9+11RWVpqysjJz8803m49+9KM+w7nnnmu2b99e43Heeecdc+ONN5qePXv65+j+dl//85//TLufez7uea1evdr30bdvX99l//79U8/fcWeRhC7c9jhTdX/4wx/MeeedZ9q1a2dOPvlkc8011zDMAQAAaII4ZueYHQAUtGzsJwAAyNzEiRPN/v37zaOPPmpuv/1284lPfMJvdx+AO2+++aaZN2+eueyyy8xXvvIV07JlS/PSSy+ZmTNnmg0bNphnnnmmxmPOmjXLf8D+zW9+03Tt2tV/6O586UtfMsXFxWb8+PH+Q/2//vWvZsKECeZjH/tYjcf405/+ZC644ALTsWNHc9111/kP+t0w4KGHHjJr1671z+Gkk04yd9xxh6mqqjJr1qwxjz32WOr7zznnnA/Nvm/fPjN69Ghz+eWXm0mTJpnf/va35oEHHvAZt27dag4fPuwHKW6I4IYC7nm7IUPz5v+bqR84cMD/nJ07d5qrr77aDBs2zHfy8MMP+0HC+vXrTUFBQdrPdB27x3WZ3IDB3dcNWNzQ5rOf/aw55ZRTfA43WBk5cqS59tprE0+Rv+SSS/xwyL0ubrgzf/58/9zcawkAAICmg2N2jtkBQIIFAOSkhQsXWrcbf+GFF2rcduTIEVteXl5j+/Tp0/33lJSUpLa573fbCgsL7VtvvZV2/xUrVvjbrrnmmlq3V/+/kdNPP90OGDDAvv/++2nblyxZ4u/rnnMwefLkGt//YXr37u2/54knnkjbPmzYMNusWTP7hS98wVZVVaW2//jHP/b3X7VqVWrb7bff7rfNmTMn7TFmz57tt7uOqnc8dOhQ32mwb98+26pVK1tUVJT2GO6+Lldt3G3uOa5bty5t+7hx42zLli3twYMHM+oCAAAA2Y9j9v/jmB0AmiYukQQATZC77I87U8Bxlw567733/G/0uzMQnJKSkhrfc+WVV/rLDcWefvpp/7e7RFJs3LhxqbMmgtLSUrN582b/m/lHjhzxPy/8GTFihL8kkDvb4Hi5syLcWRUx9/juM/wpU6akXZbInU0QLtsULF261J9xUP0sA3d2gtvubq/uW9/6lu80fg7uMknx4x6Ls88+21+2KubO+HCvUa4u1g0AAIC64Zj9fzhmB4DcxoABAJqon/zkJ+b000/3l/Tp1KmT//DcrV/guIFDde4D8+rc5ZDc5XvcpYCqGzBgQNrXYa2D73//+/5nxX/c4MKtwfDWW28dd67aLs1UWFhY621he7y2gsvknru7pFLMfe062LVrV43HP/XUU2tsc+snVF+z4cMkPU715wgAAAANHLNzzA4AuY41GACgCXJrEriFjy+66CLzne98x3Tv3t3/hpRbm8GtHeDWP6iubdu2iY9X22LF1f3vKkDG/9yxY8fWep/wgf/xaNGiRca3hedW3z8z08c92nM/3ucIAACA3MIxezqO2QEgNzFgAIAcdbQP/d2Cw3369DErV65MLW7srFq1KqOf4R7DDSPcpYCqXxLptddeS/v64x//eOpD9HAppro+/4bkziJwz91dlig+i8F9/Ze//KXWswwAAACAuuCYvW44ZgeA3MElkgAgR+Xn5/u/33333Rq3uQ/53X/MxL8F5D5Av++++zL6GZdeeqn/+8EHH0zbXlxcnLokUnDGGWeYwYMHm7lz59Z6mSH38+PnerTn35DGjx9v3n77bTNv3ry07T/96U/99gkTJtT5sV2mE50HAAAA2Ytj9rrhmB0AcgdnMABAjvr0pz/tz064++67/ZoKbhFltwaBW0R40qRJ5rbbbjOf//znzcSJE837779vfvWrX6UWfj5WbjHnMWPG+A/fwyLRbg2DRx991K/v4BZ1DtxAw5054RYtdrddffXVZtCgQebQoUNm586dZsmSJebee+/1l2hyhg8fbmbPnu0XUL744ov9c3PPvbY1FurTLbfcYp588klz4403mj//+c9+MLJhwwYzf/58vzaDu72uXKbnnnvO/OAHPzC9evXynRQVFdXr8wcAAEDu4Ji9bjhmB4DcwYABAHKU+wB7wYIF/sPsG264wVRUVJjJkyf7D+mnTZvmz15wH5pPnTrVdO3a1Vx++eXmqquuMgMHDjzmn+E+IF+8eLG54447zOOPP+4vueSGB0uXLvUL0rlLJ8WGDh3qP6x3g4Tly5f7sxkKCgr8pZbcYOFzn/tc6r5f/vKX/X0XLVrkP/B3l2JauHBhgw8YOnToYNauXesXo3bP0f3MLl26mOuvv97MmDHDP9+6cp24wYUb+hw8eNBvY8AAAACgi2P2uuGYHQByRzPLqpIAgDoYMmSIH2q8+uqr9AcAAABkIY7ZAQANjTUYAABHdfjw4RrbVqxYYbZs2WJGjx5NewAAAEAj45gdANBYOIMBAHBUbi0Hdymj888/35+qvHHjRn9ppvbt2/t/9+jRgwYBAACARsQxOwCgsTBgAAAcVXFxsbnvvvvMtm3bzIEDB0ynTp38Qs533XWX6devH+0BAAAAjYxjdgBAY2HAAAAAAAAAAAAAMsYaDAAAAAAAAAAAIGMMGAAAAAAAAAAAQMYYMAAAAAAAAAAAgIwxYAAAAAAAAAAAABljwAAAAAAAAAAAADLGgAEAAAAAAAAAAGSMAQMAAAAAAAAAAMgYAwYAAAAAAAAAAJAxBgwAAAAAAAAAACBjDBgAAAAAAAAAAEDGGDAAAAAAAAAAAICMMWAAAAAAAAAAAAAZY8AAAAAAAAAAAAAyxoABAAAAAAAAAABkjAEDAAAAAAAAAADIGAMGAAAAAAAAAACQMQYMAAAAAAAAAAAgYwwYAAAAAAAAAABAxhgwAAAAAAAAAAAAk6n/AlhOgDzPetoUAAAAAElFTkSuQmCC","type":"image/png","originalSize":136671,"dimensions":{"originalWidth":1560,"originalHeight":585,"displayWidth":1560,"displayHeight":585}}},"sourceToolAssistantUUID":"4b06514b-e7d1-476d-8b22-d18eb170494b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}90{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"3234b6314675b93799e96dfd23fe66ebbf87bd19b0775b94ea47c1afd19572c2","message":{"role":"assistant","content":[{"type":"text","text":"Results.json changed (new keys only); rerun once more to confirm determinism of the final version, and view the figure."},{"type":"tool_use","id":"toolu_01B1QyAo2KBTbFAj5V1trvjP","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv > /tmp/h2; rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py >/dev/null; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv | diff - /tmp/h2 && echo IDENTICAL; ls out","description":"Second clean rerun determinism check"}},{"type":"tool_use","id":"toolu_0147Y92euW4sgQBFji6Wedc4","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0016/out/figure1.png"}}]}}91{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"f880bcae-d622-44c8-8f89-3f19b4e14a27","timestamp":"2026-10-30T05:38:02.215Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"83448b1a-80fe-46d2-8994-e99e012d05e6","keep":26,"tail":["3234b6314675b93799e96dfd23fe66ebbf87bd19b0775b94ea47c1afd19572c2","313d9f184f8fd56fdb93d3275f45410eaccc863bb8a7477c6cf00f017d414e81"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"a618ac9d5b82228632198fffb2c0e6df79c8db2b0685d75ee2bfc00348bcd2a0"}92{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"4ca4dfee-69f7-44fb-b28a-ffe19485f1ed","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}93{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}94{"parentUuid":"4ca4dfee-69f7-44fb-b28a-ffe19485f1ed","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7nGdEErGarCUHeMg1","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":1654,"cache_read_input_tokens":36994,"output_tokens":1498,"output_tokens_details":{"thinking_tokens":34},"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":1654},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":313,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt7mz123WRxZ8CHJLu2","requestRef":"f880bcae-d622-44c8-8f89-3f19b4e14a27","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"85cd38bf-8f82-4d6f-8074-4ded82076b13","timestamp":"2026-10-30T05:38:04.652Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}95{"parentUuid":"85cd38bf-8f82-4d6f-8074-4ded82076b13","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7nGdEErGarCUHeMg1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VASa7FT8NvC1HuLsvhmXAo","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; cat > out/state/checks.md <<'EOF'\n# Verification checks (P4) — 2026-10-30\n\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run (deleted results.json, forecasts.csv, table1.csv, figure1.png) regenerates byte-identical results.json/forecasts.csv/table1.csv (SHA-256 compared), done twice (before and after adding HLN sensitivity keys) | PASS |\n| 2 | forecasts.csv: 80 rows, unique (origin,horizon,model); vintage_used == origin_date | PASS |\n| 3 | Information rule: last(V) = target − h precedes origin date for every row; each forecast reads only RSAFS vintage V (code inspection: only `vintages/RSAFS_vintage_{V}` enters FUNCS); RSAFS_current used only in estimand (d) block | PASS |\n| 4 | actual_first_release equals first_release.csv yoy for every target | PASS |\n| 5 | naive, snaive recomputed independently; AR(1) recomputed with statsmodels OLS (sample 1993-02…last(V)) and iterated — matches to 1e-5 | PASS |\n| 6 | RMSE/MAE recomputed from forecasts.csv for all 8 (model,h); RMSE ≥ MAE in all cases | PASS |\n| 7 | DM statistic and p-value recomputed independently (Bartlett weights 2/3,1/3 at h=3; lag 0 at h=1); LRV > 0 at both horizons (0.809, 2.119) | PASS |\n| 8 | rel_improvement = 1 − RMSE_model/RMSE_naive recomputed | PASS |\n| 9 | Bootstrap 95% CIs of RMSE difference contain the point estimate (h1, h3) | PASS |\n| 10 | Estimand (d) recomputed independently from RSAFS_current.csv | PASS |\n| 11 | Counts: n_raw pairs 80 − 0 removed = 80 analysed; n_analysed (model) = 20 | PASS |\n| 12 | n_input_rows equal `wc -l` − 1 for all 23 files | PASS |\n| 13 | Magnitudes vs baseline: model RMSE (0.55 h1, 1.14 h3) of same order as baselines (0.94–1.67); errors in percent; h3 errors > h1 errors for naive/AR1/model as expected | PASS |\n| 14 | conclusion codes consistent with RMSE ordering and p<0.05 rule (h1: p=0.0151 → significant; h3: p=0.122 → not significant) | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) baselines computed per task definitions with same first-release evaluation rule; stored as rmse/mae_{naive,snaive,ar1}_h{1,3}\",\"independently recomputed in P4 (check 5)\"],\"notes\":\"Baselines were coded in the same script run as the model (model specification fixed in log before the run).\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"out/analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png\",\"seed 20261030 fixed for bootstrap\",\"printed output matches results.json\"],\"notes\":\"\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical (twice)\",\"14 consistency checks all PASS, see checks.md\"],\"notes\":\"\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2/P3 passed: baselines + BED model run; added HLN sensitivity keys (extra, not required). P4 passed: determinism + 14 checks.\" >> out/state/log.md","description":"Record checks and 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":1654,"cache_read_input_tokens":36994,"output_tokens":1498,"output_tokens_details":{"thinking_tokens":34},"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":1654},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt7mz123WRxZ8CHJLu2","requestRef":"f880bcae-d622-44c8-8f89-3f19b4e14a27","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"045b44e9-1baa-4755-b496-e015cd702a3f","timestamp":"2026-10-30T05:38:16.428Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}96{"parentUuid":"045b44e9-1baa-4755-b496-e015cd702a3f","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VASa7FT8NvC1HuLsvhmXAo","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"33671294-80ef-4679-b3b9-266913736931","timestamp":"2026-10-30T05:38:16.499Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"045b44e9-1baa-4755-b496-e015cd702a3f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}97{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"1d9d9b48ed0c4793d3e0fc4fe3977024c1404b4039bdf342e2907c426a7fb161","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01VASa7FT8NvC1HuLsvhmXAo","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; cat > out/state/checks.md <<'EOF'\n# Verification checks (P4) — 2026-10-30\n\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run (deleted results.json, forecasts.csv, table1.csv, figure1.png) regenerates byte-identical results.json/forecasts.csv/table1.csv (SHA-256 compared), done twice (before and after adding HLN sensitivity keys) | PASS |\n| 2 | forecasts.csv: 80 rows, unique (origin,horizon,model); vintage_used == origin_date | PASS |\n| 3 | Information rule: last(V) = target − h precedes origin date for every row; each forecast reads only RSAFS vintage V (code inspection: only `vintages/RSAFS_vintage_{V}` enters FUNCS); RSAFS_current used only in estimand (d) block | PASS |\n| 4 | actual_first_release equals first_release.csv yoy for every target | PASS |\n| 5 | naive, snaive recomputed independently; AR(1) recomputed with statsmodels OLS (sample 1993-02…last(V)) and iterated — matches to 1e-5 | PASS |\n| 6 | RMSE/MAE recomputed from forecasts.csv for all 8 (model,h); RMSE ≥ MAE in all cases | PASS |\n| 7 | DM statistic and p-value recomputed independently (Bartlett weights 2/3,1/3 at h=3; lag 0 at h=1); LRV > 0 at both horizons (0.809, 2.119) | PASS |\n| 8 | rel_improvement = 1 − RMSE_model/RMSE_naive recomputed | PASS |\n| 9 | Bootstrap 95% CIs of RMSE difference contain the point estimate (h1, h3) | PASS |\n| 10 | Estimand (d) recomputed independently from RSAFS_current.csv | PASS |\n| 11 | Counts: n_raw pairs 80 − 0 removed = 80 analysed; n_analysed (model) = 20 | PASS |\n| 12 | n_input_rows equal `wc -l` − 1 for all 23 files | PASS |\n| 13 | Magnitudes vs baseline: model RMSE (0.55 h1, 1.14 h3) of same order as baselines (0.94–1.67); errors in percent; h3 errors > h1 errors for naive/AR1/model as expected | PASS |\n| 14 | conclusion codes consistent with RMSE ordering and p<0.05 rule (h1: p=0.0151 → significant; h3: p=0.122 → not significant) | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) baselines computed per task definitions with same first-release evaluation rule; stored as rmse/mae_{naive,snaive,ar1}_h{1,3}\",\"independently recomputed in P4 (check 5)\"],\"notes\":\"Baselines were coded in the same script run as the model (model specification fixed in log before the run).\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"out/analysis.py reads only data/, writes results.json, forecasts.csv, table1.csv, figure1.png\",\"seed 20261030 fixed for bootstrap\",\"printed output matches results.json\"],\"notes\":\"\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical (twice)\",\"14 consistency checks all PASS, see checks.md\"],\"notes\":\"\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2/P3 passed: baselines + BED model run; added HLN sensitivity keys (extra, not required). P4 passed: determinism + 14 checks.\" >> out/state/log.md","description":"Record checks and update ledger"}}]}}98{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"a7106a64-ff26-49ba-923d-679cf27e9da0","timestamp":"2026-10-30T05:38:16.502Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"f880bcae-d622-44c8-8f89-3f19b4e14a27","keep":28,"tail":["1d9d9b48ed0c4793d3e0fc4fe3977024c1404b4039bdf342e2907c426a7fb161","65f9ef146eef340ce6c139c5e59b525d48f89156a184a055a629fc7cfd04b858"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"61825e71acaad3954465821178b601a25f0d13cb7c994ad86f3a33ae693bfeff"}99{"parentUuid":"33671294-80ef-4679-b3b9-266913736931","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8qLTDSwJFp3sma5f4","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":1513,"cache_read_input_tokens":38648,"output_tokens":4791,"output_tokens_details":{"thinking_tokens":65},"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":1513},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":514,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt8q55Legw4Pe61a6GA","requestRef":"a7106a64-ff26-49ba-923d-679cf27e9da0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"df550d42-4c0a-4a97-9910-34db42381564","timestamp":"2026-10-30T05:38:18.598Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}100{"parentUuid":"df550d42-4c0a-4a97-9910-34db42381564","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8qLTDSwJFp3sma5f4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SimAS4obpbACFLpscwzWom","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; cat out/table1.csv; cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from ALFRED vintages (T1-forecast)\n\n## Question\nUsing only data published at each of 10 month-end forecast origins (`first_origin` = 2025-10-31 to `last_origin` = 2026-07-31, `n_origins` = 10), how accurately could the year-over-year growth of US retail and food services sales (RSAFS, g = 100·ln(L_m/L_{m−12})) be forecast 1 and 3 months beyond the last published month, and does a model of my own design beat the no-change forecast when errors are measured against the first-release YoY of each target month?\n\n## Data and exclusions\nInputs (all SHA-256 hashes verified against `data/README.md`; row counts in `n_input_rows`): 10 RSAFS and 10 PAYEMS ALFRED vintages, UMCSENT (current), RSAFS current vintage, and `first_release.csv` (actuals).\n\n**Real-time design.** The forecast at origin V uses **only** `RSAFS_vintage_V.csv`; `vintage_used` = origin date for all 80 rows of `out/forecasts.csv`. The target is last(V)+h, where last(V) is the last month in that vintage (`last_month_by_origin`). Publication was irregular: vintages 2025-10-31 (last month 2025-08) and 2026-03-31 (last 2026-01) end two months before the origin, and vintage 2026-04-30 adds two months (2026-02 and 2026-03) at once. As a result the h=1 targets are 2025-09 … 2026-02 and 2026-04 … 2026-07 (2026-03 is never an h=1 target), and the h=3 targets are 2025-11 … 2026-04 and 2026-06 … 2026-09. Actuals are `yoy_first_release`. `RSAFS_current.csv` is used only for the revision estimand (d). PAYEMS and UMCSENT were audited but are not used by any forecast.\n\n**Exclusions.** None (`out/exclusions.csv`): all 80 (origin, horizon, model) pairs have a forecast and a first-release actual; `n_analysed` = 20 pairs for my model (10 per horizon). Other data issues are listed in `data_issues`: delayed PAYEMS release and benchmark shift; empty UMCSENT fields before 1978; a large RSAFS annual benchmark revision between the last origin vintage and the current vintage; and first releases dated at month-end granularity.\n\n## Method\n- **Baselines** (from vintage V): naive = g_{last(V)}; seasonal naive = g_{T−12}; AR(1) = OLS of g_m on a constant and g_{m−1} over 1993-02…last(V), iterated h steps.\n- **My model, \"base-effect drift\" (`model_name`, `model_description`)**: the log level h months ahead is 100·ln L_{last} + h·μ, where μ = g_{last}/12 is the mean monthly log change over the last 12 months of vintage V. The YoY forecast subtracts 100·ln L_{T−12}, which is already published in vintage V. The model keeps the recent trend. Unlike the naive forecast, which implicitly assumes each future month repeats the monthly change of the same month a year earlier, it accounts for the known base effects: the monthly changes that leave the 12-month window. Nothing is estimated and no predictor other than RSAFS vintage V is used. I fixed the specification before computing any evaluation error and did not tune it on the 10 origins. No other candidate model was evaluated.\n- **Evaluation**: RMSE and MAE against first release; DM test with d_t = e²_naive − e²_model and a Bartlett long-run variance with lag h−1, normal two-sided p-value, no HLN factor (as specified). Additional uncertainty measures: a circular block bootstrap (block length h, B = 10,000, `random_seed` = 20261030) of RMSE_model − RMSE_naive, and as a sensitivity check only, the HLN-corrected DM with t(9) p-values.\n- Protocol note: the baselines were computed in the same script run as the model rather than in a separate earlier run. The model specification had been written in `out/state/log.md` before that run.\n\n## Results\nTable 1 (`out/table1.csv`; RMSE / MAE in percentage points of YoY growth, n = 10 each):\n\n| model | h=1 RMSE | h=1 MAE | h=3 RMSE | h=3 MAE |\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| base-effect drift | 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 my model has the lowest RMSE and MAE of the four methods. Its RMSE is 44.8% below the naive forecast (`rel_improvement_rmse_h1` = 0.448). DM = 2.43, p = 0.015 (`dm_stat_h1`, `dm_pvalue_h1`), so `conclusion_code_h1` = `model_better_significant`.\n- At h=3 my model again has the lowest RMSE and MAE, 19.6% below naive (`rel_improvement_rmse_h3` = 0.196). However, DM = 1.55, p = 0.122 (`dm_stat_h3`, `dm_pvalue_h3`), so `conclusion_code_h3` = `model_better_not_significant`.\n- AR(1) improves only slightly on the naive forecast. The seasonal naive forecast is the worst method at h=1 but beats naive at h=3.\n- Revisions (estimand d): the mean absolute difference between current-vintage and first-release YoY growth of the 10 h=1 target months is 0.548 pp (`mean_abs_revision_h1_targets`). All ten revisions are negative (`mean_revision_h1_targets_current_minus_first` = −0.548; individual values in `revisions_h1_targets`), reflecting the downward benchmark revision of RSAFS levels. This is about the same size as my model's h=1 RMSE (0.550) and about half the naive h=1 RMSE: under today's data the \"truth\" would look quite different.\n- `out/figure1.png` shows first-release actuals and the naive, AR(1) and model forecasts by target month. The largest misses for every method come from the surge in first-release growth in 2026-04 to 2026-06 and the drop in 2026-07.\n\n## Uncertainty\nThere are only 10 origins per horizon, and at h=3 the errors from consecutive origins overlap. The DM test relies on asymptotic normality and a long-run variance estimated from 10 points, so its size is unreliable in samples this small.\n- At h=1 (lag 0, LRV = `dm_lrv_h1` = 0.809) the result survives the HLN small-sample correction with t(9) critical values, but only barely: `sens_dm_hln_pvalue_t_h1` = 0.047. The block bootstrap 95% interval for RMSE_model − RMSE_naive is [−0.697, −0.209] (`boot_ci95_lo_h1`, `boot_ci95_hi_h1`), which excludes zero. The h=1 evidence that the model beats naive is therefore fairly consistent across methods, but it rests on 10 observations from one short period (late 2025 to mid 2026).\n- At h=3 (lags 1–2, LRV = `dm_lrv_h3` = 2.119) the improvement is not significant: normal p = 0.122, HLN/t(9) p = `sens_dm_hln_pvalue_t_h3` = 0.277. The bootstrap interval [−0.689, 0.081] (`boot_ci95_lo_h3`, `boot_ci95_hi_h3`) includes zero. A block bootstrap with n = 10 and block length 3 is itself crude.\n- With n = 10, an observed relative improvement of about 20% is compatible with no true improvement. The h=3 result should be read as \"no evidence of a difference\", not as evidence of equal accuracy.\n\n## Limitations and open issues\n- Small evaluation sample (10 origins over a period with irregular publication). This period includes delayed releases, which change the effective horizon relative to the calendar. The results may not generalise to other periods.\n- The first-release \"truth\" is defined at month-end granularity by the task designer. Later revisions are large (estimand d), so rankings evaluated against current data could differ; I did not evaluate this, because the task specifies first-release evaluation.\n- The model's gain comes from treating the known base effects explicitly. It cannot anticipate genuine shocks such as the 2026-05/06 surge, and it ignores PAYEMS and UMCSENT. I evaluated no other model, so no claim is made about whether these predictors would help.\n- DM inference follows the task specification (normal p-values, no HLN factor). The HLN and bootstrap numbers are sensitivity checks only.\n- All tasks were completed; `feasibility` = \"complete\".\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect drift model has a lower RMSE than the naive forecast, with a relative improvement of about 45%, and the DM test (Bartlett LRV, normal) rejects equal accuracy at 5%.\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"Only 10 origins; with the HLN small-sample correction and t(9) values, p = 0.047, which is borderline.\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the model has a lower RMSE than naive (about 20% improvement), but the difference is not statistically significant.\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\",\"boot_ci95_lo_h3\",\"boot_ci95_hi_h3\"],\"status\":\"supported\",\"caveat\":\"Overlapping 3-step errors and n = 10 make the DM long-run variance imprecise.\"},\n {\"id\":\"C3\",\"text\":\"Among the baselines, AR(1) improves only slightly on naive at both horizons; seasonal naive is the worst at h=1 but beats naive at h=3.\",\"results_keys\":[\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_snaive_h1\",\"rmse_snaive_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\"],\"status\":\"supported\",\"caveat\":\"No significance test was carried out among the baselines.\"},\n {\"id\":\"C4\",\"text\":\"The first-release YoY growth of the h=1 target months has since been revised by 0.548 pp on average in absolute value, and every one of these revisions is downward.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"mean_revision_h1_targets_current_minus_first\",\"revisions_h1_targets\"],\"status\":\"supported\",\"caveat\":\"Reflects the annual benchmark revision present in the 2026-10-30 current vintage; it may be revised again.\"},\n {\"id\":\"C5\",\"text\":\"The block bootstrap 95% interval for RMSE_model - RMSE_naive excludes zero at h=1 and includes zero at h=3.\",\"results_keys\":[\"boot_ci95_lo_h1\",\"boot_ci95_hi_h1\",\"boot_ci95_lo_h3\",\"boot_ci95_hi_h3\",\"random_seed\"],\"status\":\"supported\",\"caveat\":\"A bootstrap on 10 observations is crude.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'));json.load(open('out/claims.json'))\nr=json.load(open('out/results.json'))\nimport re\nkeys=set(re.findall(r'`([a-z0-9_]+)`',open('out/report.md').read()))\nmissing=[k for k in keys if k not in r and not k.startswith(('model_better','naive_better','random')) and '_' in k]\nprint('report backticked keys not in results:',missing)\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md has the 6 required sections, each figure cites a results key\",\"claims.json valid JSON, 5 claims, each results_key exists in results.json\",\"report key citations cross-checked against results.json\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nfor c in json.load(open('out/claims.json')):\n assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok')\nEOF\necho \"- 2026-10-30 P5 passed: report.md, claims.json written; all phases passed.\" >> out/state/log.md","description":"Write report and claims, finalize ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1513,"cache_read_input_tokens":38648,"output_tokens":4791,"output_tokens_details":{"thinking_tokens":65},"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":1513},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt8q55Legw4Pe61a6GA","requestRef":"a7106a64-ff26-49ba-923d-679cf27e9da0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8b462faf-7399-491b-a0ab-207997bcbab2","timestamp":"2026-10-30T05:38:57.159Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}101{"parentUuid":"8b462faf-7399-491b-a0ab-207997bcbab2","isSidechain":false,"promptId":"abc1e41f-f1ea-4e92-b212-f27109e5b64c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SimAS4obpbACFLpscwzWom","type":"tool_result","content":"model,horizon,rmse,mae,n\nnaive,1,0.996874,0.848722,10\nnaive,3,1.42004,1.200449,10\nsnaive,1,1.674543,1.30667,10\nsnaive,3,1.316079,1.065869,10\nar1,1,0.940524,0.797651,10\nar1,3,1.187118,0.952689,10\nmodel,1,0.550298,0.486332,10\nmodel,3,1.14222,0.933977,10\nreport backticked keys not in results: ['vintage_used', 'yoy_first_release']\nclaims keys ok","is_error":false}]},"uuid":"77087f77-38d2-4062-b934-8ef7349dd27d","timestamp":"2026-10-30T05:38:57.211Z","toolUseResult":{"stdout":"model,horizon,rmse,mae,n\nnaive,1,0.996874,0.848722,10\nnaive,3,1.42004,1.200449,10\nsnaive,1,1.674543,1.30667,10\nsnaive,3,1.316079,1.065869,10\nar1,1,0.940524,0.797651,10\nar1,3,1.187118,0.952689,10\nmodel,1,0.550298,0.486332,10\nmodel,3,1.14222,0.933977,10\nreport backticked keys not in results: ['vintage_used', 'yoy_first_release']\nclaims keys ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"8b462faf-7399-491b-a0ab-207997bcbab2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}102{"type":"api-request-blob","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","hash":"518c72a42ad61533edc00e7a010f2e9065d2db32abe737d41aedce3d63b81920","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01SimAS4obpbACFLpscwzWom","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0016; cat out/table1.csv; cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth from ALFRED vintages (T1-forecast)\n\n## Question\nUsing only data published at each of 10 month-end forecast origins (`first_origin` = 2025-10-31 to `last_origin` = 2026-07-31, `n_origins` = 10), how accurately could the year-over-year growth of US retail and food services sales (RSAFS, g = 100·ln(L_m/L_{m−12})) be forecast 1 and 3 months beyond the last published month, and does a model of my own design beat the no-change forecast when errors are measured against the first-release YoY of each target month?\n\n## Data and exclusions\nInputs (all SHA-256 hashes verified against `data/README.md`; row counts in `n_input_rows`): 10 RSAFS and 10 PAYEMS ALFRED vintages, UMCSENT (current), RSAFS current vintage, and `first_release.csv` (actuals).\n\n**Real-time design.** The forecast at origin V uses **only** `RSAFS_vintage_V.csv`; `vintage_used` = origin date for all 80 rows of `out/forecasts.csv`. The target is last(V)+h, where last(V) is the last month in that vintage (`last_month_by_origin`). Publication was irregular: vintages 2025-10-31 (last month 2025-08) and 2026-03-31 (last 2026-01) end two months before the origin, and vintage 2026-04-30 adds two months (2026-02 and 2026-03) at once. As a result the h=1 targets are 2025-09 … 2026-02 and 2026-04 … 2026-07 (2026-03 is never an h=1 target), and the h=3 targets are 2025-11 … 2026-04 and 2026-06 … 2026-09. Actuals are `yoy_first_release`. `RSAFS_current.csv` is used only for the revision estimand (d). PAYEMS and UMCSENT were audited but are not used by any forecast.\n\n**Exclusions.** None (`out/exclusions.csv`): all 80 (origin, horizon, model) pairs have a forecast and a first-release actual; `n_analysed` = 20 pairs for my model (10 per horizon). Other data issues are listed in `data_issues`: delayed PAYEMS release and benchmark shift; empty UMCSENT fields before 1978; a large RSAFS annual benchmark revision between the last origin vintage and the current vintage; and first releases dated at month-end granularity.\n\n## Method\n- **Baselines** (from vintage V): naive = g_{last(V)}; seasonal naive = g_{T−12}; AR(1) = OLS of g_m on a constant and g_{m−1} over 1993-02…last(V), iterated h steps.\n- **My model, \"base-effect drift\" (`model_name`, `model_description`)**: the log level h months ahead is 100·ln L_{last} + h·μ, where μ = g_{last}/12 is the mean monthly log change over the last 12 months of vintage V. The YoY forecast subtracts 100·ln L_{T−12}, which is already published in vintage V. The model keeps the recent trend. Unlike the naive forecast, which implicitly assumes each future month repeats the monthly change of the same month a year earlier, it accounts for the known base effects: the monthly changes that leave the 12-month window. Nothing is estimated and no predictor other than RSAFS vintage V is used. I fixed the specification before computing any evaluation error and did not tune it on the 10 origins. No other candidate model was evaluated.\n- **Evaluation**: RMSE and MAE against first release; DM test with d_t = e²_naive − e²_model and a Bartlett long-run variance with lag h−1, normal two-sided p-value, no HLN factor (as specified). Additional uncertainty measures: a circular block bootstrap (block length h, B = 10,000, `random_seed` = 20261030) of RMSE_model − RMSE_naive, and as a sensitivity check only, the HLN-corrected DM with t(9) p-values.\n- Protocol note: the baselines were computed in the same script run as the model rather than in a separate earlier run. The model specification had been written in `out/state/log.md` before that run.\n\n## Results\nTable 1 (`out/table1.csv`; RMSE / MAE in percentage points of YoY growth, n = 10 each):\n\n| model | h=1 RMSE | h=1 MAE | h=3 RMSE | h=3 MAE |\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| base-effect drift | 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 my model has the lowest RMSE and MAE of the four methods. Its RMSE is 44.8% below the naive forecast (`rel_improvement_rmse_h1` = 0.448). DM = 2.43, p = 0.015 (`dm_stat_h1`, `dm_pvalue_h1`), so `conclusion_code_h1` = `model_better_significant`.\n- At h=3 my model again has the lowest RMSE and MAE, 19.6% below naive (`rel_improvement_rmse_h3` = 0.196). However, DM = 1.55, p = 0.122 (`dm_stat_h3`, `dm_pvalue_h3`), so `conclusion_code_h3` = `model_better_not_significant`.\n- AR(1) improves only slightly on the naive forecast. The seasonal naive forecast is the worst method at h=1 but beats naive at h=3.\n- Revisions (estimand d): the mean absolute difference between current-vintage and first-release YoY growth of the 10 h=1 target months is 0.548 pp (`mean_abs_revision_h1_targets`). All ten revisions are negative (`mean_revision_h1_targets_current_minus_first` = −0.548; individual values in `revisions_h1_targets`), reflecting the downward benchmark revision of RSAFS levels. This is about the same size as my model's h=1 RMSE (0.550) and about half the naive h=1 RMSE: under today's data the \"truth\" would look quite different.\n- `out/figure1.png` shows first-release actuals and the naive, AR(1) and model forecasts by target month. The largest misses for every method come from the surge in first-release growth in 2026-04 to 2026-06 and the drop in 2026-07.\n\n## Uncertainty\nThere are only 10 origins per horizon, and at h=3 the errors from consecutive origins overlap. The DM test relies on asymptotic normality and a long-run variance estimated from 10 points, so its size is unreliable in samples this small.\n- At h=1 (lag 0, LRV = `dm_lrv_h1` = 0.809) the result survives the HLN small-sample correction with t(9) critical values, but only barely: `sens_dm_hln_pvalue_t_h1` = 0.047. The block bootstrap 95% interval for RMSE_model − RMSE_naive is [−0.697, −0.209] (`boot_ci95_lo_h1`, `boot_ci95_hi_h1`), which excludes zero. The h=1 evidence that the model beats naive is therefore fairly consistent across methods, but it rests on 10 observations from one short period (late 2025 to mid 2026).\n- At h=3 (lags 1–2, LRV = `dm_lrv_h3` = 2.119) the improvement is not significant: normal p = 0.122, HLN/t(9) p = `sens_dm_hln_pvalue_t_h3` = 0.277. The bootstrap interval [−0.689, 0.081] (`boot_ci95_lo_h3`, `boot_ci95_hi_h3`) includes zero. A block bootstrap with n = 10 and block length 3 is itself crude.\n- With n = 10, an observed relative improvement of about 20% is compatible with no true improvement. The h=3 result should be read as \"no evidence of a difference\", not as evidence of equal accuracy.\n\n## Limitations and open issues\n- Small evaluation sample (10 origins over a period with irregular publication). This period includes delayed releases, which change the effective horizon relative to the calendar. The results may not generalise to other periods.\n- The first-release \"truth\" is defined at month-end granularity by the task designer. Later revisions are large (estimand d), so rankings evaluated against current data could differ; I did not evaluate this, because the task specifies first-release evaluation.\n- The model's gain comes from treating the known base effects explicitly. It cannot anticipate genuine shocks such as the 2026-05/06 surge, and it ignores PAYEMS and UMCSENT. I evaluated no other model, so no claim is made about whether these predictors would help.\n- DM inference follows the task specification (normal p-values, no HLN factor). The HLN and bootstrap numbers are sensitivity checks only.\n- All tasks were completed; `feasibility` = \"complete\".\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the base-effect drift model has a lower RMSE than the naive forecast, with a relative improvement of about 45%, and the DM test (Bartlett LRV, normal) rejects equal accuracy at 5%.\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"Only 10 origins; with the HLN small-sample correction and t(9) values, p = 0.047, which is borderline.\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the model has a lower RMSE than naive (about 20% improvement), but the difference is not statistically significant.\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\",\"boot_ci95_lo_h3\",\"boot_ci95_hi_h3\"],\"status\":\"supported\",\"caveat\":\"Overlapping 3-step errors and n = 10 make the DM long-run variance imprecise.\"},\n {\"id\":\"C3\",\"text\":\"Among the baselines, AR(1) improves only slightly on naive at both horizons; seasonal naive is the worst at h=1 but beats naive at h=3.\",\"results_keys\":[\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_snaive_h1\",\"rmse_snaive_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\"],\"status\":\"supported\",\"caveat\":\"No significance test was carried out among the baselines.\"},\n {\"id\":\"C4\",\"text\":\"The first-release YoY growth of the h=1 target months has since been revised by 0.548 pp on average in absolute value, and every one of these revisions is downward.\",\"results_keys\":[\"mean_abs_revision_h1_targets\",\"mean_revision_h1_targets_current_minus_first\",\"revisions_h1_targets\"],\"status\":\"supported\",\"caveat\":\"Reflects the annual benchmark revision present in the 2026-10-30 current vintage; it may be revised again.\"},\n {\"id\":\"C5\",\"text\":\"The block bootstrap 95% interval for RMSE_model - RMSE_naive excludes zero at h=1 and includes zero at h=3.\",\"results_keys\":[\"boot_ci95_lo_h1\",\"boot_ci95_hi_h1\",\"boot_ci95_lo_h3\",\"boot_ci95_hi_h3\",\"random_seed\"],\"status\":\"supported\",\"caveat\":\"A bootstrap on 10 observations is crude.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'));json.load(open('out/claims.json'))\nr=json.load(open('out/results.json'))\nimport re\nkeys=set(re.findall(r'`([a-z0-9_]+)`',open('out/report.md').read()))\nmissing=[k for k in keys if k not in r and not k.startswith(('model_better','naive_better','random')) and '_' in k]\nprint('report backticked keys not in results:',missing)\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md has the 6 required sections, each figure cites a results key\",\"claims.json valid JSON, 5 claims, each results_key exists in results.json\",\"report key citations cross-checked against results.json\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nfor c in json.load(open('out/claims.json')):\n assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok')\nEOF\necho \"- 2026-10-30 P5 passed: report.md, claims.json written; all phases passed.\" >> out/state/log.md","description":"Write report and claims, finalize ledger"}}]}}103{"type":"api-request","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","id":"ae3749cf-d510-416d-87e9-28cbc32bb32e","timestamp":"2026-10-30T05:38:57.214Z","version":"2.1.314","querySource":"sdk","shapeHash":"0a9073d0b2200096f2a1bcb4bb5a7f8e1d9d7d3aee40d94d79711e0cb9bb8d57","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":"a7106a64-ff26-49ba-923d-679cf27e9da0","keep":30,"tail":["518c72a42ad61533edc00e7a010f2e9065d2db32abe737d41aedce3d63b81920","d34a59730526ab4e07c2a0d689e721f12dae95d03adbb66cbc7428360a29c1be"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"34db1feecda77e8eae32065c8385985668aa395baf5d09f984ad09411e8a0e89"}104{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"77087f77-38d2-4062-b934-8ef7349dd27d","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}105{"type":"atis-latch","atis":"","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}106{"parentUuid":"77087f77-38d2-4062-b934-8ef7349dd27d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtBqTioWqBJfMQBHpsm","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":4984,"cache_read_input_tokens":40161,"output_tokens":1047,"output_tokens_details":{"thinking_tokens":15},"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":4984},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6476,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtBqBrjABJ4rmZRMQt2","requestRef":"ae3749cf-d510-416d-87e9-28cbc32bb32e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aa600a18-9287-4464-9c95-2eb30876a256","timestamp":"2026-10-30T05:39:05.100Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}107{"parentUuid":"aa600a18-9287-4464-9c95-2eb30876a256","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtBqTioWqBJfMQBHpsm","type":"message","role":"assistant","content":[{"type":"text","text":"My model beats the no-change (naive) forecast at both horizons, but the advantage is statistically significant only one month ahead. All six protocol phases passed, every required file is written, and two clean re-runs of `out/analysis.py` reproduced the outputs byte for byte.\n\n**My model (\"base-effect drift\").** It uses only the retail-sales vintage published at each origin. It assumes sales keep growing at their average monthly rate of the past 12 months. It then subtracts the already-published level from a year earlier, so it captures the known \"base effects\": the monthly changes that drop out of the 12-month window. Nothing is estimated, and the employment and consumer-sentiment series are not used. I fixed this design before computing any errors and tested no other model.\n\n**Results** (errors against the first-published value, in percentage points of growth; 10 origins per horizon):\n\n| | 1 month ahead | 3 months ahead |\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| Improvement over naive | 45% | 20% |\n| Diebold–Mariano test | 2.43, p = 0.015 (significant) | 1.55, p = 0.12 (not significant) |\n\n- **Other baselines:** AR(1) is only slightly better than naive. Seasonal naive is the worst method one month ahead but beats naive three months ahead.\n- **Revisions:** the growth figures for the 10 one-month-ahead target months have since been revised by 0.548 points on average, and every revision was downward. That is about as large as my model's one-month error, because a recent annual revision lowered sales levels by up to 4.6%.\n- **Publication delays:** two vintages (2025-10-31 and 2026-03-31) ended two months before their date, and the 2026-04-30 vintage added two months at once. As the task requires, targets count from the last month actually published, so March 2026 is never a one-month-ahead target.\n- **Exclusions:** none; all 80 forecast–actual pairs were evaluated.\n\n**Limitations:**\n- **Few origins:** 10 origins over a period of disrupted publication is a small sample. The one-month result only just survives a small-sample correction to the test (p = 0.047), though a bootstrap interval also excludes zero. The three-month improvement is consistent with no real gain.\n- **No shocks captured:** the model cannot anticipate genuine shocks such as the May–June 2026 surge, the largest miss for every method.\n- **Single period:** all results come from late 2025 to mid 2026 and may not hold in other periods.\n- **Protocol ordering:** the baselines were computed in the same run as my model rather than in a separate earlier step, although the model design was logged first.\n\nFiles are in `out/`:\n- `analysis.py`\n- `results.json`\n- `forecasts.csv`\n- `table1.csv`\n- `figure1.png`\n- `report.md`\n- `claims.json`\n- `exclusions.csv`\n- `state/` (work log and checks)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4984,"cache_read_input_tokens":40161,"output_tokens":1047,"output_tokens_details":{"thinking_tokens":15},"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":4984},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtBqBrjABJ4rmZRMQt2","requestRef":"ae3749cf-d510-416d-87e9-28cbc32bb32e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a088fbb4-a657-4bb8-8b15-9ead8389ed92","timestamp":"2026-10-30T05:39:07.921Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0016","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","version":"2.1.314","gitBranch":"HEAD"}108{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a088fbb4-a657-4bb8-8b15-9ead8389ed92","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c"}109{"type":"cost-state","sessionId":"df46db7b-af6d-4eca-a0de-1c0f1ebb1f1c","totalCostUSD":0.7786278,"totalAPIDuration":218231,"totalAPIDurationWithoutRetries":218227,"totalToolDuration":5647,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":223663,"startTime":1793338524285,"modelUsage":{"claude-opus-5-5":{"inputTokens":34,"outputTokens":24185,"thinkingTokens":3256,"cacheReadInputTokens":382934,"cacheCreationInputTokens":43641,"cacheCreationEphemeral5mInputTokens":43641,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.7786278}},"hasUnknownModelCost":false}110