1{"type":"atis-latch","atis":"","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:03:06.919Z","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:03:06.924Z","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}4{"parentUuid":null,"isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":"Begin"},"uuid":"64403577-c965-439f-9e65-15dcdc0296bb","timestamp":"2026-10-30T05:03:06.929Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","timestamp":"2026-10-30T05:03:06.942Z","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/RC0219\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":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"93dd4f2a-7dba-47d2-ab09-f7667282da64","timestamp":"2026-10-30T05:03:06.942Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"ff296d072f6a4294393974b726950c19894c617e70a76367e879313aab167aca"}8{"parentUuid":"64403577-c965-439f-9e65-15dcdc0296bb","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"b0739be2-0d52-4d2f-a3a2-202ecdb2a546","timestamp":"2026-10-30T05:03:06.935Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"b0739be2-0d52-4d2f-a3a2-202ecdb2a546","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"718ee980-69ac-46ca-80bf-cb1fa879aff2","timestamp":"2026-10-30T05:03:06.935Z","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/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"718ee980-69ac-46ca-80bf-cb1fa879aff2","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":"8b22bce9-725b-4ab0-a5fe-e712f6da44c3","timestamp":"2026-10-30T05:03:06.935Z","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/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}12{"parentUuid":"8b22bce9-725b-4ab0-a5fe-e712f6da44c3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqTLsrKZfsUsX25ncKg","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":129,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":526,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqTLcErCbE19RYkw1EF","requestRef":"93dd4f2a-7dba-47d2-ab09-f7667282da64","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"788efc6f-9346-4eac-a393-72bfe510e0ea","timestamp":"2026-10-30T05:03:08.246Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"788efc6f-9346-4eac-a393-72bfe510e0ea","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqTLsrKZfsUsX25ncKg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ANfjCk3aF9VTkASUEynsUx","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":129,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqTLcErCbE19RYkw1EF","requestRef":"93dd4f2a-7dba-47d2-ab09-f7667282da64","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fc45af76-fcb1-4680-bc9c-bfa66476de4a","timestamp":"2026-10-30T05:03:08.751Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"fc45af76-fcb1-4680-bc9c-bfa66476de4a","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ANfjCk3aF9VTkASUEynsUx","type":"tool_result","content":"# F2-conf-04 — Okun's law in U.S. quarterly data with autocorrelation-robust uncertainty\n\n## Scientific question\nEstimate the Okun's-law relation between changes in the U.S. unemployment rate and real GDP growth, with uncertainty that is valid under serially correlated disturbances. The estimand is the slope β (the \"Okun coefficient\") in the linear projection Δu_t = α + β g_t + e_t, where, for quarter t: u_t is the quarterly average of the three monthly unemployment-rate observations of quarter t (in percentage points), Δu_t = u_t − u_{t−1}, and g_t = 100 · ln(GDPC1_t / GDPC1_{t−1}) is quarterly real GDP growth in percent (quarter-on-quarter, **not** annualised). The regression sample is the 240 quarters from 1960Q1 to 2019Q4 inclusive (the 1960Q1 observation uses the 1959Q4 levels for its differences). Estimate β by OLS, report a Newey–West (Bartlett-kernel HAC) standard error with a bandwidth you justify, and state whether the Okun coefficient is negative and significantly different from zero at the 5% level.\n\n## Inputs\n- `data/UNRATE.csv` — observed data: U.S. civilian unemployment rate, seasonally adjusted, percent, monthly, 1948-01 to 2026-09 (945 data rows). Columns: `observation_date` (YYYY-MM-DD), `UNRATE`. Source: U.S. Bureau of Labor Statistics via FRED (`https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`), retrieved 2026-10-30 UTC; terms in `data/README.md`.\n- `data/GDPC1.csv` — observed data: U.S. real GDP, seasonally adjusted annual rate, billions of chained 2017 dollars, quarterly, 1947Q1 to 2026Q3 (319 data rows). Columns: `observation_date` (first day of the quarter), `GDPC1`. Source: U.S. Bureau of Economic Analysis via FRED (`https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`), retrieved 2026-10-30 UTC; terms in `data/README.md`.\n- `data/README.md` — provenance, retrieval time, SHA-256 checksums and license.\n\n## Information-availability rules\n- Use only the files under `data/`. The files are the current vintage (not real-time data); treat them as given. Observations outside the 1960Q1–2019Q4 window are only used for the levels needed to form the first differences; do not extend the window.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | – | \"F2-conf-04\" |\n| `beta_hat` | number | pp of unemployment per percent of quarterly growth | OLS Okun coefficient |\n| `alpha_hat` | number | pp | OLS intercept |\n| `r_squared` | number | – | R² of the regression |\n| `se_iid` | number | – | conventional OLS standard error of `beta_hat` (independent, homoskedastic errors) — the naïve baseline |\n| `se_hac` | number | – | Newey–West (Bartlett) HAC standard error of `beta_hat` |\n| `hac_lags` | integer | quarters | bandwidth (number of lags) used for `se_hac` |\n| `beta_ci_low`, `beta_ci_high` | number | – | 95% confidence interval for β built from `se_hac` |\n| `okun_negative_5pct` | boolean | – | true if and only if β̂ < 0 and H0: β = 0 is rejected at the 5% level (two-sided) using `se_hac` |\n| `mean_growth` | number | percent | sample mean of g_t over the 240 regression quarters |\n| `first_quarter`, `last_quarter` | string | – | first and last quarter of the regression sample, formatted like \"1960Q1\" |\n| `n_analysed` | integer | – | quarters used in the regression |\n| `feasibility` | string | – | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | – | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | – | data problems detected and how handled (empty list if none) |\n| `n_input_rows` | object | – | {\"UNRATE.csv\": data rows read (excluding the header), \"GDPC1.csv\": data rows read} |\n| `random_seed` | integer or null | – | seed used, if any |\n\n- `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json` 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- `out/figure1.png` — scatter of Δu_t against g_t over the sample with the fitted line.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- This task is designed to be completed in well under 20 minutes of work.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:39 .\ndrwxr-xr-x 126 simon-pierreboucher staff 4032 oct. 30 01:03 ..\n-rw-r--r-- 1 simon-pierreboucher staff 600 oct. 29 23:39 bundle.json\ndrwxr-xr-x 5 simon-pierreboucher staff 160 oct. 29 23:37 data\n-rw-r--r-- 1 simon-pierreboucher staff 1736 oct. 29 23:39 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 4631 oct. 29 23:39 TASK.md\ndata:\nGDPC1.csv\nREADME.md\nUNRATE.csv","is_error":false}]},"uuid":"1e582836-4203-4f51-8a6b-75b0c5822007","timestamp":"2026-10-30T05:03:08.814Z","toolUseResult":{"stdout":"# F2-conf-04 — Okun's law in U.S. quarterly data with autocorrelation-robust uncertainty\n\n## Scientific question\nEstimate the Okun's-law relation between changes in the U.S. unemployment rate and real GDP growth, with uncertainty that is valid under serially correlated disturbances. The estimand is the slope β (the \"Okun coefficient\") in the linear projection Δu_t = α + β g_t + e_t, where, for quarter t: u_t is the quarterly average of the three monthly unemployment-rate observations of quarter t (in percentage points), Δu_t = u_t − u_{t−1}, and g_t = 100 · ln(GDPC1_t / GDPC1_{t−1}) is quarterly real GDP growth in percent (quarter-on-quarter, **not** annualised). The regression sample is the 240 quarters from 1960Q1 to 2019Q4 inclusive (the 1960Q1 observation uses the 1959Q4 levels for its differences). Estimate β by OLS, report a Newey–West (Bartlett-kernel HAC) standard error with a bandwidth you justify, and state whether the Okun coefficient is negative and significantly different from zero at the 5% level.\n\n## Inputs\n- `data/UNRATE.csv` — observed data: U.S. civilian unemployment rate, seasonally adjusted, percent, monthly, 1948-01 to 2026-09 (945 data rows). Columns: `observation_date` (YYYY-MM-DD), `UNRATE`. Source: U.S. Bureau of Labor Statistics via FRED (`https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`), retrieved 2026-10-30 UTC; terms in `data/README.md`.\n- `data/GDPC1.csv` — observed data: U.S. real GDP, seasonally adjusted annual rate, billions of chained 2017 dollars, quarterly, 1947Q1 to 2026Q3 (319 data rows). Columns: `observation_date` (first day of the quarter), `GDPC1`. Source: U.S. Bureau of Economic Analysis via FRED (`https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`), retrieved 2026-10-30 UTC; terms in `data/README.md`.\n- `data/README.md` — provenance, retrieval time, SHA-256 checksums and license.\n\n## Information-availability rules\n- Use only the files under `data/`. The files are the current vintage (not real-time data); treat them as given. Observations outside the 1960Q1–2019Q4 window are only used for the levels needed to form the first differences; do not extend the window.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | – | \"F2-conf-04\" |\n| `beta_hat` | number | pp of unemployment per percent of quarterly growth | OLS Okun coefficient |\n| `alpha_hat` | number | pp | OLS intercept |\n| `r_squared` | number | – | R² of the regression |\n| `se_iid` | number | – | conventional OLS standard error of `beta_hat` (independent, homoskedastic errors) — the naïve baseline |\n| `se_hac` | number | – | Newey–West (Bartlett) HAC standard error of `beta_hat` |\n| `hac_lags` | integer | quarters | bandwidth (number of lags) used for `se_hac` |\n| `beta_ci_low`, `beta_ci_high` | number | – | 95% confidence interval for β built from `se_hac` |\n| `okun_negative_5pct` | boolean | – | true if and only if β̂ < 0 and H0: β = 0 is rejected at the 5% level (two-sided) using `se_hac` |\n| `mean_growth` | number | percent | sample mean of g_t over the 240 regression quarters |\n| `first_quarter`, `last_quarter` | string | – | first and last quarter of the regression sample, formatted like \"1960Q1\" |\n| `n_analysed` | integer | – | quarters used in the regression |\n| `feasibility` | string | – | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | – | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | – | data problems detected and how handled (empty list if none) |\n| `n_input_rows` | object | – | {\"UNRATE.csv\": data rows read (excluding the header), \"GDPC1.csv\": data rows read} |\n| `random_seed` | integer or null | – | seed used, if any |\n\n- `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json` 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- `out/figure1.png` — scatter of Δu_t against g_t over the sample with the fitted line.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- This task is designed to be completed in well under 20 minutes of work.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:39 .\ndrwxr-xr-x 126 simon-pierreboucher staff 4032 oct. 30 01:03 ..\n-rw-r--r-- 1 simon-pierreboucher staff 600 oct. 29 23:39 bundle.json\ndrwxr-xr-x 5 simon-pierreboucher staff 160 oct. 29 23:37 data\n-rw-r--r-- 1 simon-pierreboucher staff 1736 oct. 29 23:39 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 4631 oct. 29 23:39 TASK.md\ndata:\nGDPC1.csv\nREADME.md\nUNRATE.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fc45af76-fcb1-4680-bc9c-bfa66476de4a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"1d7dfe540c385dd5b62cb7d50a7a889ab6c13ac5feafeddde7bf26c25968ed52","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01ANfjCk3aF9VTkASUEynsUx","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":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"ea5145c3-4c0e-4d38-9a03-b3eda44979f3","timestamp":"2026-10-30T05:03:08.819Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"93dd4f2a-7dba-47d2-ab09-f7667282da64","keep":2,"tail":["1d7dfe540c385dd5b62cb7d50a7a889ab6c13ac5feafeddde7bf26c25968ed52","436c37e95f25a94c1977ce5255982679cd59f3c92aeb25f10725c6c13af240db"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1a61f30406519f4ba6d44f7b1a619685667c714b995b2176ce6cfdf1bb01348b"}17{"parentUuid":"1e582836-4203-4f51-8a6b-75b0c5822007","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqTUpba1tCGovWxivR3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MtYkugto6WRBiU3DhKnRfz","name":"Bash","input":{"command":"cat data/README.md; shasum -a 256 data/*.csv; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; cat bundle.json gate_spec.json","description":"Inspect data files and metadata"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2314,"cache_read_input_tokens":3713,"output_tokens":147,"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":2314},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqTUYUPi7QWeYjfaPQB","requestRef":"ea5145c3-4c0e-4d38-9a03-b3eda44979f3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aa3958a8-2016-481b-931d-630fbd672785","timestamp":"2026-10-30T05:03:10.380Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}18{"parentUuid":"aa3958a8-2016-481b-931d-630fbd672785","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MtYkugto6WRBiU3DhKnRfz","type":"tool_result","content":"# Data provenance — F2-conf-04\n\nBoth files are unmodified downloads from FRED (Federal Reserve Bank of St. Louis), retrieved on 2026-10-30 03:32:42 UTC with\n`curl -L \"https://fred.stlouisfed.org/graph/fredgraph.csv?id=<SERIES>\"`. They are the current vintage as of the retrieval time (not real-time vintages).\n\n| file | series | description | units | frequency | rows (data, excl. header) | SHA-256 |\n|---|---|---|---|---|---|---|\n| `UNRATE.csv` | UNRATE | Unemployment Rate, 16 years and over, seasonally adjusted. Source: U.S. Bureau of Labor Statistics, Current Population Survey. | percent | monthly, 1948-01 to 2026-09 | 945 | `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c` |\n| `GDPC1.csv` | GDPC1 | Real Gross Domestic Product, seasonally adjusted annual rate, chained 2017 dollars. Source: U.S. Bureau of Economic Analysis, NIPA Table 1.1.6. | billions of chained 2017 dollars | quarterly, 1947Q1 to 2026Q3 | 319 | `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343` |\n\nColumns: `observation_date` (YYYY-MM-DD; for GDPC1 the first day of the quarter), and the series value. Missing values, if any, appear as an empty field.\n\nLicense / terms: the underlying series are U.S. federal government statistical releases (public domain). Redistribution through FRED is subject to the FRED® Terms of Use (https://fred.stlouisfed.org/legal/), which permit non-commercial research use with attribution: \"Source: U.S. Bureau of Labor Statistics and U.S. Bureau of Economic Analysis, retrieved from FRED, Federal Reserve Bank of St. Louis\".\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 data/GDPC1.csv\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c data/UNRATE.csv\n==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 data/GDPC1.csv\n 946 data/UNRATE.csv\n 1266 total\n{\n \"task_id\": \"F2-conf-04\",\n \"family\": \"F2\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:39:33.081711+00:00\",\n \"files\": {\n \"TASK.md\": \"b80f25d137f0d04f5223537e07525015a8d6257e5084a83ce87866da7a71a0eb\",\n \"data/GDPC1.csv\": \"1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343\",\n \"data/README.md\": \"cb177a40e235651c0792ccb9a038f2b6bed53740c22ac902f9e6ae4e47856e3c\",\n \"data/UNRATE.csv\": \"621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c\",\n \"gate_spec.json\": \"939144536131765675ba640605191be350be3312c9098770179c2db3c9096991\"\n }\n}{\n \"task_id\": \"F2-conf-04\",\n \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/figure1.png\"],\n \"results_keys\": {\n \"task_id\": {\"type\": \"string\", \"nullable\": false},\n \"beta_hat\": {\"type\": \"number\", \"nullable\": false},\n \"alpha_hat\": {\"type\": \"number\", \"nullable\": false},\n \"r_squared\": {\"type\": \"number\", \"nullable\": false},\n \"se_iid\": {\"type\": \"number\", \"nullable\": false},\n \"se_hac\": {\"type\": \"number\", \"nullable\": false},\n \"hac_lags\": {\"type\": \"integer\", \"nullable\": false},\n \"beta_ci_low\": {\"type\": \"number\", \"nullable\": false},\n \"beta_ci_high\": {\"type\": \"number\", \"nullable\": false},\n \"okun_negative_5pct\": {\"type\": \"boolean\", \"nullable\": false},\n \"mean_growth\": {\"type\": \"number\", \"nullable\": false},\n \"first_quarter\": {\"type\": \"string\", \"nullable\": false},\n \"last_quarter\": {\"type\": \"string\", \"nullable\": false},\n \"n_analysed\": {\"type\": \"integer\", \"nullable\": false},\n \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n },\n \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n \"family_checks\": [\"ci_contains_estimate\", \"positive_se\", \"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n \"ci_pairs\": [[\"beta_hat\", \"beta_ci_low\", \"beta_ci_high\"]],\n \"positive_keys\": [\"se_iid\", \"se_hac\"],\n \"chronology_pairs\": [],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-6\n}","is_error":false}]},"uuid":"f080b10a-9af7-41bd-a262-5de98ce9446d","timestamp":"2026-10-30T05:03:10.422Z","toolUseResult":{"stdout":"# Data provenance — F2-conf-04\n\nBoth files are unmodified downloads from FRED (Federal Reserve Bank of St. Louis), retrieved on 2026-10-30 03:32:42 UTC with\n`curl -L \"https://fred.stlouisfed.org/graph/fredgraph.csv?id=<SERIES>\"`. They are the current vintage as of the retrieval time (not real-time vintages).\n\n| file | series | description | units | frequency | rows (data, excl. header) | SHA-256 |\n|---|---|---|---|---|---|---|\n| `UNRATE.csv` | UNRATE | Unemployment Rate, 16 years and over, seasonally adjusted. Source: U.S. Bureau of Labor Statistics, Current Population Survey. | percent | monthly, 1948-01 to 2026-09 | 945 | `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c` |\n| `GDPC1.csv` | GDPC1 | Real Gross Domestic Product, seasonally adjusted annual rate, chained 2017 dollars. Source: U.S. Bureau of Economic Analysis, NIPA Table 1.1.6. | billions of chained 2017 dollars | quarterly, 1947Q1 to 2026Q3 | 319 | `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343` |\n\nColumns: `observation_date` (YYYY-MM-DD; for GDPC1 the first day of the quarter), and the series value. Missing values, if any, appear as an empty field.\n\nLicense / terms: the underlying series are U.S. federal government statistical releases (public domain). Redistribution through FRED is subject to the FRED® Terms of Use (https://fred.stlouisfed.org/legal/), which permit non-commercial research use with attribution: \"Source: U.S. Bureau of Labor Statistics and U.S. Bureau of Economic Analysis, retrieved from FRED, Federal Reserve Bank of St. Louis\".\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 data/GDPC1.csv\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c data/UNRATE.csv\n==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 data/GDPC1.csv\n 946 data/UNRATE.csv\n 1266 total\n{\n \"task_id\": \"F2-conf-04\",\n \"family\": \"F2\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:39:33.081711+00:00\",\n \"files\": {\n \"TASK.md\": \"b80f25d137f0d04f5223537e07525015a8d6257e5084a83ce87866da7a71a0eb\",\n \"data/GDPC1.csv\": \"1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343\",\n \"data/README.md\": \"cb177a40e235651c0792ccb9a038f2b6bed53740c22ac902f9e6ae4e47856e3c\",\n \"data/UNRATE.csv\": \"621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c\",\n \"gate_spec.json\": \"939144536131765675ba640605191be350be3312c9098770179c2db3c9096991\"\n }\n}{\n \"task_id\": \"F2-conf-04\",\n \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/figure1.png\"],\n \"results_keys\": {\n \"task_id\": {\"type\": \"string\", \"nullable\": false},\n \"beta_hat\": {\"type\": \"number\", \"nullable\": false},\n \"alpha_hat\": {\"type\": \"number\", \"nullable\": false},\n \"r_squared\": {\"type\": \"number\", \"nullable\": false},\n \"se_iid\": {\"type\": \"number\", \"nullable\": false},\n \"se_hac\": {\"type\": \"number\", \"nullable\": false},\n \"hac_lags\": {\"type\": \"integer\", \"nullable\": false},\n \"beta_ci_low\": {\"type\": \"number\", \"nullable\": false},\n \"beta_ci_high\": {\"type\": \"number\", \"nullable\": false},\n \"okun_negative_5pct\": {\"type\": \"boolean\", \"nullable\": false},\n \"mean_growth\": {\"type\": \"number\", \"nullable\": false},\n \"first_quarter\": {\"type\": \"string\", \"nullable\": false},\n \"last_quarter\": {\"type\": \"string\", \"nullable\": false},\n \"n_analysed\": {\"type\": \"integer\", \"nullable\": false},\n \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n },\n \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n \"family_checks\": [\"ci_contains_estimate\", \"positive_se\", \"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n \"ci_pairs\": [[\"beta_hat\", \"beta_ci_low\", \"beta_ci_high\"]],\n \"positive_keys\": [\"se_iid\", \"se_hac\"],\n \"chronology_pairs\": [],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-6\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"aa3958a8-2016-481b-931d-630fbd672785","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}19{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"778475c1c9126bb17e046df8bb12f9cb8d959ea4f61e3c675f87d2f2587e797f","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MtYkugto6WRBiU3DhKnRfz","name":"Bash","input":{"command":"cat data/README.md; shasum -a 256 data/*.csv; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; cat bundle.json gate_spec.json","description":"Inspect data files and metadata"}}]}}20{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"7d4e31ed-133f-49d7-b5aa-e975f2ff47ab","timestamp":"2026-10-30T05:03:10.426Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"ea5145c3-4c0e-4d38-9a03-b3eda44979f3","keep":4,"tail":["778475c1c9126bb17e046df8bb12f9cb8d959ea4f61e3c675f87d2f2587e797f","68df91452facbbd45245990d5e38aed49bad299729a4b9d06470d65e49d99d2c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"cbe49df79d9f30128f5b32d256e82e80a8bbe2225effecf704147a374c348bec"}21{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f080b10a-9af7-41bd-a262-5de98ce9446d","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}22{"type":"atis-latch","atis":"","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}23{"parentUuid":"f080b10a-9af7-41bd-a262-5de98ce9446d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqTbianmoQBsNpGtgu9","type":"message","role":"assistant","content":[{"type":"text","text":"Now a data audit script."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2308,"cache_read_input_tokens":6027,"output_tokens":631,"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":2308},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqTbSD5ixrR4JRGrrbC","requestRef":"7d4e31ed-133f-49d7-b5aa-e975f2ff47ab","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"714ffc51-57ac-427a-8bdd-fa6f7c352b3b","timestamp":"2026-10-30T05:03:11.282Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"714ffc51-57ac-427a-8bdd-fa6f7c352b3b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqTbianmoQBsNpGtgu9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RuaAagcfQ6Qk7wadaunPxg","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f in ['UNRATE','GDPC1']:\n d=pd.read_csv(f'data/{f}.csv',dtype=str,keep_default_na=False)\n print(f,d.shape, list(d.columns))\n v=pd.to_numeric(d[f],errors='coerce'); dt=pd.to_datetime(d.observation_date,errors='coerce')\n print('bad vals',d[v.isna()].to_string()); print('bad dates',dt.isna().sum(),'dup dates',dt.duplicated().sum())\n print('min/max',v.min(),v.max(),dt.min(),dt.max())\n s=dt.dropna().sort_values(); print('monotonic',dt.is_monotonic_increasing)\n if f=='UNRATE':\n full=pd.date_range(s.min(),s.max(),freq='MS'); print('missing months',sorted(set(full)-set(s))[:20])\n q=pd.Series(v.values,index=dt).loc['1959-10-01':'2019-12-01']; print('1959Q4-2019Q4 months',len(q),q.isna().sum())\n else:\n full=pd.date_range(s.min(),s.max(),freq='QS'); print('missing qtrs',sorted(set(full)-set(s))); print('non-qtr-start',(~dt.dt.month.isin([1,4,7,10])).sum(), (dt.dt.day!=1).sum())\n print(v.diff().abs().sort_values().tail(3))\n\"","description":"Audit both CSV files for anomalies"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2308,"cache_read_input_tokens":6027,"output_tokens":631,"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":2308},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqTbSD5ixrR4JRGrrbC","requestRef":"7d4e31ed-133f-49d7-b5aa-e975f2ff47ab","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2dad7445-41ea-4d28-8202-1f4e15d213c3","timestamp":"2026-10-30T05:03:16.047Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"2dad7445-41ea-4d28-8202-1f4e15d213c3","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01RuaAagcfQ6Qk7wadaunPxg","type":"tool_result","content":"UNRATE (945, 2) ['observation_date', 'UNRATE']\nbad vals observation_date UNRATE\n933 2025-10-01 \nbad dates 0 dup dates 0\nmin/max 2.5 14.8 1948-01-01 00:00:00 2026-09-01 00:00:00\nmonotonic True\nmissing months []\n1959Q4-2019Q4 months 723 0\nGDPC1 (319, 2) ['observation_date', 'GDPC1']\nbad vals Empty DataFrame\nColumns: [observation_date, GDPC1]\nIndex: []\nbad dates 0 dup dates 0\nmin/max 2172.432 24611.077 1947-01-01 00:00:00 2026-07-01 00:00:00\nmonotonic True\nmissing qtrs []\nnon-qtr-start 0 0\n294 1480.887\n293 1631.220\n0 NaN\nName: GDPC1, dtype: float64","is_error":false}]},"uuid":"0d287805-b6da-4997-81c0-f33cdcdf42ea","timestamp":"2026-10-30T05:03:16.308Z","toolUseResult":{"stdout":"UNRATE (945, 2) ['observation_date', 'UNRATE']\nbad vals observation_date UNRATE\n933 2025-10-01 \nbad dates 0 dup dates 0\nmin/max 2.5 14.8 1948-01-01 00:00:00 2026-09-01 00:00:00\nmonotonic True\nmissing months []\n1959Q4-2019Q4 months 723 0\nGDPC1 (319, 2) ['observation_date', 'GDPC1']\nbad vals Empty DataFrame\nColumns: [observation_date, GDPC1]\nIndex: []\nbad dates 0 dup dates 0\nmin/max 2172.432 24611.077 1947-01-01 00:00:00 2026-07-01 00:00:00\nmonotonic True\nmissing qtrs []\nnon-qtr-start 0 0\n294 1480.887\n293 1631.220\n0 NaN\nName: GDPC1, dtype: float64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2dad7445-41ea-4d28-8202-1f4e15d213c3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"b4e38ec3e855df1272b1a91c80a2ebf8634fb7c20520c3114bde0f8a629c3057","message":{"role":"assistant","content":[{"type":"text","text":"Now a data audit script."},{"type":"tool_use","id":"toolu_01RuaAagcfQ6Qk7wadaunPxg","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f in ['UNRATE','GDPC1']:\n d=pd.read_csv(f'data/{f}.csv',dtype=str,keep_default_na=False)\n print(f,d.shape, list(d.columns))\n v=pd.to_numeric(d[f],errors='coerce'); dt=pd.to_datetime(d.observation_date,errors='coerce')\n print('bad vals',d[v.isna()].to_string()); print('bad dates',dt.isna().sum(),'dup dates',dt.duplicated().sum())\n print('min/max',v.min(),v.max(),dt.min(),dt.max())\n s=dt.dropna().sort_values(); print('monotonic',dt.is_monotonic_increasing)\n if f=='UNRATE':\n full=pd.date_range(s.min(),s.max(),freq='MS'); print('missing months',sorted(set(full)-set(s))[:20])\n q=pd.Series(v.values,index=dt).loc['1959-10-01':'2019-12-01']; print('1959Q4-2019Q4 months',len(q),q.isna().sum())\n else:\n full=pd.date_range(s.min(),s.max(),freq='QS'); print('missing qtrs',sorted(set(full)-set(s))); print('non-qtr-start',(~dt.dt.month.isin([1,4,7,10])).sum(), (dt.dt.day!=1).sum())\n print(v.diff().abs().sort_values().tail(3))\n\"","description":"Audit both CSV files for anomalies"}}]}}27{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"c2f3b42a-a28c-4ba3-8c9a-40abeae10edb","timestamp":"2026-10-30T05:03:16.311Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"7d4e31ed-133f-49d7-b5aa-e975f2ff47ab","keep":6,"tail":["b4e38ec3e855df1272b1a91c80a2ebf8634fb7c20520c3114bde0f8a629c3057","e91483480b11dfbc81754b0dedb262712e51846ee1a27e010b6d41622f1b9fea"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c0fa01f38dbc39ab5324575a0172b0338c8e9ce16603ef49176c610579bb26a4"}28{"parentUuid":"0d287805-b6da-4997-81c0-f33cdcdf42ea","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqU2pSq7eTLqafqFhB7","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":947,"cache_read_input_tokens":8335,"output_tokens":1292,"output_tokens_details":{"thinking_tokens":335},"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":947},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3246,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqU2a4g5aMC2VheoK9t","requestRef":"c2f3b42a-a28c-4ba3-8c9a-40abeae10edb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"015c2243-0449-4781-a46c-8b38e4c93710","timestamp":"2026-10-30T05:03:20.541Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"015c2243-0449-4781-a46c-8b38e4c93710","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqU2pSq7eTLqafqFhB7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KFbKmyr2FGAjbYeanmFRB5","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract — F2-conf-04\n**Question.** Okun's law in U.S. quarterly data: how does the quarterly change in the unemployment rate co-move with quarterly real GDP growth, with inference robust to serial correlation?\n**Estimand.** β in the linear projection Δu_t = α + β g_t + e_t, 1960Q1–2019Q4 (240 quarters). u_t = mean of the 3 monthly UNRATE values of quarter t (pp); Δu_t = u_t − u_{t−1}; g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) (quarterly, not annualised). β is a linear-projection coefficient (descriptive, not causal); meaningful under covariance stationarity / weak dependence so that OLS is consistent for the projection and the HAC variance is consistent.\n**Outputs.** out/results.json keys: task_id, beta_hat, alpha_hat, r_squared, se_iid, se_hac, hac_lags, beta_ci_low, beta_ci_high, okun_negative_5pct, mean_growth, first_quarter, last_quarter, n_analysed, feasibility, feasibility_reason, data_issues, n_input_rows, random_seed. Also out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues), out/analysis.py, out/claims.json, out/figure1.png (scatter + fitted line), out/exclusions.csv, out/state/*.\n**Information rules.** Only data/ files (current vintage). Data outside 1960Q1–2019Q4 only for 1959Q4 levels used in first differences; no window extension.\n**Invalidity / impossibility.** Missing months in 1959Q4–2019Q4 (incomplete quarterly averages), missing GDP quarters, sample ≠ 240, using annualised growth, using post-2019 data.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > 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":947,"cache_read_input_tokens":8335,"output_tokens":1292,"output_tokens_details":{"thinking_tokens":335},"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":947},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqU2a4g5aMC2VheoK9t","requestRef":"c2f3b42a-a28c-4ba3-8c9a-40abeae10edb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fc266969-ad94-4e2b-b6d4-b011486d9ccf","timestamp":"2026-10-30T05:03:27.694Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"fc266969-ad94-4e2b-b6d4-b011486d9ccf","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KFbKmyr2FGAjbYeanmFRB5","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"4bb0e10a-095f-4670-b2a6-722175e57665","timestamp":"2026-10-30T05:03:27.722Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fc266969-ad94-4e2b-b6d4-b011486d9ccf","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"6498129a8491779bb866c78d6cf67df6c91fa41cc074e401aec3715b09b4015c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KFbKmyr2FGAjbYeanmFRB5","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract — F2-conf-04\n**Question.** Okun's law in U.S. quarterly data: how does the quarterly change in the unemployment rate co-move with quarterly real GDP growth, with inference robust to serial correlation?\n**Estimand.** β in the linear projection Δu_t = α + β g_t + e_t, 1960Q1–2019Q4 (240 quarters). u_t = mean of the 3 monthly UNRATE values of quarter t (pp); Δu_t = u_t − u_{t−1}; g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) (quarterly, not annualised). β is a linear-projection coefficient (descriptive, not causal); meaningful under covariance stationarity / weak dependence so that OLS is consistent for the projection and the HAC variance is consistent.\n**Outputs.** out/results.json keys: task_id, beta_hat, alpha_hat, r_squared, se_iid, se_hac, hac_lags, beta_ci_low, beta_ci_high, okun_negative_5pct, mean_growth, first_quarter, last_quarter, n_analysed, feasibility, feasibility_reason, data_issues, n_input_rows, random_seed. Also out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues), out/analysis.py, out/claims.json, out/figure1.png (scatter + fitted line), out/exclusions.csv, out/state/*.\n**Information rules.** Only data/ files (current vintage). Data outside 1960Q1–2019Q4 only for 1959Q4 levels used in first differences; no window extension.\n**Invalidity / impossibility.** Missing months in 1959Q4–2019Q4 (incomplete quarterly averages), missing GDP quarters, sample ≠ 240, using annualised growth, using post-2019 data.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > out/state/log.md","description":"Write contract, phase ledger, log"}}]}}32{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"b82f1936-69a2-4f34-aaf7-c3925925081b","timestamp":"2026-10-30T05:03:27.725Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"c2f3b42a-a28c-4ba3-8c9a-40abeae10edb","keep":8,"tail":["6498129a8491779bb866c78d6cf67df6c91fa41cc074e401aec3715b09b4015c","d091a17e40990adc014c0d72c6fd3afaa6705e1a57e8b4d64f4e1c56b9232bcb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1b2e78e22ebf03634faef187064bd9bf265b93165b6111ec3cd64bc28b4070e4"}33{"parentUuid":"4bb0e10a-095f-4670-b2a6-722175e57665","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqUsfYaC2AKcncQWNLz","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JdN4aXpET5E8DQ4ccaAhGS","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 (matches README & bundle.json) | data rows | cols | range |\n|---|---|---|---|---|\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | 945 | 2 (observation_date, UNRATE) | 1948-01-01 .. 2026-09-01 monthly |\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | 319 | 2 (observation_date, GDPC1) | 1947-01-01 .. 2026-07-01 quarterly |\n\nUnits: UNRATE percent (SA); GDPC1 billions of chained 2017 USD, SAAR.\n\nFindings:\n- UNRATE: no duplicate dates, no gaps in the monthly calendar, dates monotonic. Range 2.5–14.8. **One empty value at 2025-10-01** (missing observation; October 2025, outside the analysis window). All 723 months 1959-10..2019-12 present and non-missing.\n- GDPC1: no missing values, no duplicate dates, no calendar gaps, all dates are first day of quarter months. Largest absolute level changes are 2020Q2/Q3 (COVID), outside window.\n- Information-availability: files include data after 2019Q4 (and before 1959Q4). These are not used: the analysis restricts to 1959Q4 levels (for differencing) through 2019Q4. No violation remains after filtering. Data are current vintage, which is permitted.\n\nHandling: missing 2025-10 UNRATE value recorded in data_issues; it is excluded by the window filter and does not affect results. Quarterly averages are only computed from quarters with 3 non-missing months (checked in analysis.py).\nEOF\necho \"- 2026-10-30 P1: audit done; one missing UNRATE (2025-10) outside window.\" >> out/state/log.md","description":"Write data audit"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1307,"cache_read_input_tokens":9282,"output_tokens":777,"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":1307},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqUsNgoVAGzXp4KCJEe","requestRef":"b82f1936-69a2-4f34-aaf7-c3925925081b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dad12846-a5f6-4b16-b5bf-039e29361a94","timestamp":"2026-10-30T05:03:35.561Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}34{"parentUuid":"dad12846-a5f6-4b16-b5bf-039e29361a94","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JdN4aXpET5E8DQ4ccaAhGS","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"0eb90e6e-05df-4525-b589-c039a30e8739","timestamp":"2026-10-30T05:03:35.582Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"dad12846-a5f6-4b16-b5bf-039e29361a94","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}35{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"375dbdbe641cab44ddbcdb66b37a20221580654e7f4cb646626df21a893306d6","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01JdN4aXpET5E8DQ4ccaAhGS","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 (matches README & bundle.json) | data rows | cols | range |\n|---|---|---|---|---|\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | 945 | 2 (observation_date, UNRATE) | 1948-01-01 .. 2026-09-01 monthly |\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | 319 | 2 (observation_date, GDPC1) | 1947-01-01 .. 2026-07-01 quarterly |\n\nUnits: UNRATE percent (SA); GDPC1 billions of chained 2017 USD, SAAR.\n\nFindings:\n- UNRATE: no duplicate dates, no gaps in the monthly calendar, dates monotonic. Range 2.5–14.8. **One empty value at 2025-10-01** (missing observation; October 2025, outside the analysis window). All 723 months 1959-10..2019-12 present and non-missing.\n- GDPC1: no missing values, no duplicate dates, no calendar gaps, all dates are first day of quarter months. Largest absolute level changes are 2020Q2/Q3 (COVID), outside window.\n- Information-availability: files include data after 2019Q4 (and before 1959Q4). These are not used: the analysis restricts to 1959Q4 levels (for differencing) through 2019Q4. No violation remains after filtering. Data are current vintage, which is permitted.\n\nHandling: missing 2025-10 UNRATE value recorded in data_issues; it is excluded by the window filter and does not affect results. Quarterly averages are only computed from quarters with 3 non-missing months (checked in analysis.py).\nEOF\necho \"- 2026-10-30 P1: audit done; one missing UNRATE (2025-10) outside window.\" >> out/state/log.md","description":"Write data audit"}}]}}36{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"7281ce8a-3e33-4fdd-ba6b-06231bb4e615","timestamp":"2026-10-30T05:03:35.585Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"b82f1936-69a2-4f34-aaf7-c3925925081b","keep":10,"tail":["375dbdbe641cab44ddbcdb66b37a20221580654e7f4cb646626df21a893306d6","10653baa788cb0a8c3a8a4940574fb0bd531f247265c168f36e3eb9bc9acf20f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e2189659bda2e30be2285f579d48267ca865add4a69298625bade9eb18be66b8"}37{"parentUuid":"0eb90e6e-05df-4525-b589-c039a30e8739","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqVTHd77qW3YkirmyXj","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":792,"cache_read_input_tokens":10589,"output_tokens":3521,"output_tokens_details":{"thinking_tokens":347},"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":792},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2949,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqVT2Ftp8rozeJ96FjK","requestRef":"7281ce8a-3e33-4fdd-ba6b-06231bb4e615","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c0e47011-7f50-4093-a281-b94c6191f8b3","timestamp":"2026-10-30T05:03:39.452Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}38{"parentUuid":"c0e47011-7f50-4093-a281-b94c6191f8b3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqVTHd77qW3YkirmyXj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016MwrX67mtSSPQzKtUvKtwN","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, U.S. 1960Q1-2019Q4, OLS with Newey-West HAC SE. Reads only data/, writes out/.\"\"\"\nimport json, hashlib, os\nimport numpy as np, pandas as pd\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nD, O = os.path.join(ROOT, \"data\"), os.path.join(ROOT, \"out\")\nFIRST, LAST = pd.Period(\"1960Q1\", \"Q\"), pd.Period(\"2019Q4\", \"Q\")\n\ndef sha(p):\n return hashlib.sha256(open(p, \"rb\").read()).hexdigest()\n\nun = pd.read_csv(os.path.join(D, \"UNRATE.csv\"))\ngd = pd.read_csv(os.path.join(D, \"GDPC1.csv\"))\nn_rows = {\"UNRATE.csv\": int(len(un)), \"GDPC1.csv\": int(len(gd))}\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()]\nfor d in miss[\"observation_date\"]:\n data_issues.append({\"issue\": f\"UNRATE missing (empty) value at {d}\",\n \"handling\": \"Quarter containing it has <3 monthly values and is dropped; it lies outside the 1959Q4-2019Q4 levels window, so results are unaffected.\"})\n\n# quarterly average unemployment, only quarters with all 3 months\nun[\"q\"] = pd.to_datetime(un[\"observation_date\"]).dt.to_period(\"Q\")\ng = un.groupby(\"q\")[\"UNRATE\"]\nuq = g.mean()[g.count() == 3].rename(\"u\")\nn_un_q = int(un[\"q\"].nunique())\ngd[\"q\"] = pd.to_datetime(gd[\"observation_date\"]).dt.to_period(\"Q\")\ngq = gd.set_index(\"q\")[\"GDPC1\"].astype(float)\n\nledger = []\ndef log(step, rule, nb, na, why):\n ledger.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\ndf = pd.concat([gq, uq], axis=1, join=\"inner\").sort_index()\nlog(1, \"keep GDPC1 quarters that have a complete (3-month) UNRATE quarterly average\", len(gq), len(df),\n \"UNRATE starts 1948Q1 (GDPC1 starts 1947Q1); 2025Q4 lacks October 2025 UNRATE\")\n# differences only between consecutive calendar quarters\nidx = df.index\nconsec = pd.Series([False] + [idx[i] - idx[i - 1] == 1 for i in range(1, len(idx))], index=idx)\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"] / df[\"GDPC1\"].shift(1))\ndf.loc[~consec, [\"du\", \"g\"]] = np.nan\nnb = len(df); df = df.dropna(subset=[\"du\", \"g\"])\nlog(2, \"drop quarters whose previous calendar quarter is unavailable (first differences undefined)\", nb, len(df),\n \"first available quarter and quarters following a dropped quarter\")\nnb = len(df); df = df[(df.index >= FIRST) & (df.index <= LAST)]\nlog(3, \"restrict to regression window 1960Q1-2019Q4\", nb, len(df), \"task-defined sample; no extension of window\")\nassert len(df) == 240 and df.index[0] == FIRST and df.index[-1] == LAST\npd.DataFrame(ledger).to_csv(os.path.join(O, \"exclusions.csv\"), index=False)\n\n# OLS\ny = df[\"du\"].to_numpy(); x = df[\"g\"].to_numpy(); T = len(y)\nX = np.column_stack([np.ones(T), x])\nXtXi = np.linalg.inv(X.T @ X)\nb = XtXi @ X.T @ y\ne = y - X @ b\nk = X.shape[1]\nr2 = 1 - (e @ e) / np.sum((y - y.mean()) ** 2)\nse_iid = float(np.sqrt((e @ e) / (T - k) * XtXi[1, 1]))\n\ndef nw_se(L):\n \"\"\"Newey-West (1987) Bartlett-kernel HAC, no small-sample df correction.\"\"\"\n u = X * e[:, None]\n S = u.T @ u\n for l in range(1, L + 1):\n w = 1 - l / (L + 1)\n G = u[l:].T @ u[:-l]\n S += w * (G + G.T)\n V = XtXi @ S @ XtXi\n return float(np.sqrt(V[1, 1]))\n\n# Bandwidth: Newey-West (1994) / Stock-Watson rule of thumb floor(4*(T/100)^(2/9))\nL = int(np.floor(4 * (T / 100) ** (2 / 9)))\nse_hac = nw_se(L)\nz = stats.norm.ppf(0.975)\nlo, hi = float(b[1] - z * se_hac), float(b[1] + z * se_hac)\nt_hac = float(b[1] / se_hac)\np_hac = float(2 * stats.norm.sf(abs(t_hac)))\nneg = bool(b[1] < 0 and p_hac < 0.05)\n\n# cross-check with statsmodels (no df correction)\nimport statsmodels.api as sm\nm = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"use_correction\": False})\nassert abs(m.bse[1] - se_hac) < 1e-10 and abs(m.params[1] - b[1]) < 1e-12\nm0 = sm.OLS(y, X).fit()\nassert abs(m0.bse[1] - se_iid) < 1e-10\n\nsens = {str(l): nw_se(l) for l in [0, 1, 2, 4, 6, 8, 12]}\nrho1 = float(np.corrcoef(e[1:], e[:-1])[0, 1])\n\nres = {\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": float(b[1]), \"alpha_hat\": float(b[0]), \"r_squared\": float(r2),\n \"se_iid\": se_iid, \"se_hac\": se_hac, \"hac_lags\": L,\n \"beta_ci_low\": lo, \"beta_ci_high\": hi,\n \"okun_negative_5pct\": neg,\n \"mean_growth\": float(x.mean()),\n \"first_quarter\": str(df.index[0]), \"last_quarter\": str(df.index[-1]),\n \"n_analysed\": int(T),\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues, \"n_input_rows\": n_rows, \"random_seed\": None,\n # supplementary\n \"baseline_beta_ci_low_iid\": float(b[1] - z * se_iid), \"baseline_beta_ci_high_iid\": float(b[1] + z * se_iid),\n \"t_stat_hac\": t_hac, \"p_value_hac\": p_hac, \"critical_value\": float(z),\n \"se_hac_by_lags\": sens, \"resid_lag1_autocorr\": rho1,\n \"mean_du\": float(y.mean()),\n \"input_sha256\": {f: sha(os.path.join(D, f)) for f in [\"UNRATE.csv\", \"GDPC1.csv\"]},\n}\nwith open(os.path.join(O, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\nfig, ax = plt.subplots(figsize=(6.5, 4.5))\nax.scatter(x, y, s=12, alpha=0.6, label=\"quarters 1960Q1-2019Q4\")\nxs = np.linspace(x.min(), x.max(), 100)\nax.plot(xs, b[0] + b[1] * xs, \"r-\", label=f\"OLS: Δu = {b[0]:.3f} {b[1]:+.3f} g\")\nax.set_xlabel(\"Real GDP growth g_t (%, q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, U.S. 1960Q1-2019Q4 (n=240)\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.legend(fontsize=8); fig.tight_layout()\nfig.savefig(os.path.join(O, \"figure1.png\"), dpi=120)\nprint(f\"beta={b[1]:.4f} se_iid={se_iid:.4f} se_hac(L={L})={se_hac:.4f} CI=[{lo:.4f},{hi:.4f}] neg5%={neg}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/exclusions.csv","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":792,"cache_read_input_tokens":10589,"output_tokens":3521,"output_tokens_details":{"thinking_tokens":347},"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":792},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqVT2Ftp8rozeJ96FjK","requestRef":"7281ce8a-3e33-4fdd-ba6b-06231bb4e615","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4c2528f9-559d-4ad4-b8db-f0e303f80a6a","timestamp":"2026-10-30T05:04:02.913Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}39{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"4c2528f9-559d-4ad4-b8db-f0e303f80a6a","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}40{"type":"atis-latch","atis":"","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}41{"parentUuid":"4c2528f9-559d-4ad4-b8db-f0e303f80a6a","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n File \"/Users/simon-pierreboucher/wp29/runs/RC0219/out/analysis.py\", line 51, in <module>\n assert len(df) == 240 and df.index[0] == FIRST and df.index[-1] == LAST\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nAssertionError","is_error":true,"tool_use_id":"toolu_016MwrX67mtSSPQzKtUvKtwN"}]},"uuid":"fe3cb658-07a8-43ee-a444-6023ff02c4ed","timestamp":"2026-10-30T05:04:03.771Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n File \"/Users/simon-pierreboucher/wp29/runs/RC0219/out/analysis.py\", line 51, in <module>\n assert len(df) == 240 and df.index[0] == FIRST and df.index[-1] == LAST\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nAssertionError","sandboxed":false,"sourceToolAssistantUUID":"4c2528f9-559d-4ad4-b8db-f0e303f80a6a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"c91e6fe801f8d1c2aacc28c5fca39108f4408dda9413c786fcb9102d14637821","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS1gsKEAgTGAI4AUIIdGhpbmtpbmcSDDCyzIzEHkEsyZt0+hoMYCkdfHyLFtyiDaX9IjDIUWzH5BAuPvGNmRUN4z0ZDyURYttMw8bUe23DiBFwzRMi4NijxwdnzQ41Bz4Zyqwq8wqvrAS03STfJrEjQwhwun68X5hEvkpA2UOIjN09MxLCNsu/BJzjCp5jbbc1/qUZm4OSkT15G497MctxiNOHLQ03VZ3MFq1XGbOqIf9YHBgqOSQJsMt7CArGeYwrWPrs+2t2WQLD9s1+Gn1tvjFnQjgIWAY9ThqrAHhYiECraJLKiy4KoWZVex8phKU2eg1FsnEvWQjwcgYWSziLHjiKXrR3qQrCHVnwBfLqH/gZDpGZ/qhhzg302hLNCxWghjrbc2lg/wqH0L/8U3ylON8+uQGAYBnot4WYkqZ/ek2an4NkfyQSTpaQnLsPtE8LP8JlHOUIBA0r2W2luDLhbTuH1k4arNGuPuA0cRzfQTqxL77JlOwYUp7HabtIzDAb7ZCRZ9juRLQQqzxZw4H2+OCfZqvCpROiZ6a2MV/fZyzvgz3RciH8rSbWuQEiGIJGlCZTsrLWXB+X6lGDcYkbWKTxoen3N2L/pjKkl0jFKOeXQARkODvJYRu6X2Zap5unC0RUh1jRAWVxZoYoMKrXSD5HFYP2DPAOgQOCdn5hIKXwXz3suT4XQDygikLjYkXl3xR0nlw+72U7I40DN0ojBfaYgjF/Dr3noXOp2eT7Esdn5h05oDW7Jht16upFhtPyxKMLv9vQjX41wmVc3zCK/I7Ym1q0QntJXRByhAVP8KYCEXjMnCwG/Rn2n3n1f3M1ftAi/EzWUBtBvlZJyYlv7IxxWdWEQJffe2r2Pcjo8oLlSBTtxue4ffbadhEVEmAOKIPsEEfuupTgX8AUk9rnLZQ+sp6jDDiAL2uK7VDM0I8y/p3W6IwGPxD27AJgRhcAlgQSESh1/ZTbBtTxWki7hdtyYt3i6WsPy5vctmX63GTxk+C44HLv55AaerAAVK4qjFwkjCZOb8NOGhs9VlJ++Bj2t6aYrdt/ssMrAreiKEZleRBLqwSQwoBkZFSaNBByCcKgTT2GxCqTYHIlg63h+xKXVXYoE2FTAaWf+iseFaCnG6y9LlbijFx48MfWBeLgKj9thyOgHZkFHW73/kMO2WJbhdypdgoLotUjGu+Y2FGAwUQns+a4iZm2bETqLwT8r8zpPkT8shrHpuaOUj57OZfepJ0ecsvs/4edqeIKlBLptp2G0eg4rvYRsEdA3j14CPeSo+yulOpx/Ib39bcTNJJUp9jEHNeXEujc5tUT80gYRl6dbcXz06T8ztpNEUw6bs/NbgsxCexXuhntxkHV2UpzJ3aElW7zOGvzDazLC6YBmLDeeOZfwO1gBEta0x4EyLmDQPkYyb36p2BBTTvHpbf8FSqp6u95oFZfOdQnejTV010c+klV4o1lH4MIsN7kJT6VjQJuklW0HvR7A6SicrROXefLryFHhR624ju+5sUVHUdMDSOHGFsRVfiBBeoYu9Z2o/zLoNnpce6oUaTAFE0+vaA9pfpIB3PpAjneY6JcOb3IR8uzENSr1KDd2Xrazaz86JbGoL2F1cOI+4DUYJJMl1dNOiOWWqNdVfFEiHqIX6SfQEJUAqn0Vcll8mPUWD5+MRs0qW1Kb9tKiRNox45+n4dshOXWp4XGqmbHW23Vy7FViN+stUJhc+8x4cMsqjsQTMjYPzP++KLytQoAK52UC7tESluOZryY4vPCpw/lfN9rZCBlZ1MUEHdgsdEIh5UZeBblU1q0UfoZGl6Oou8X/xR80Whp2x6M6m+Hc2HlIkZDodfijqxNI6S2AEe7E/8cO5YwzsO0oF7Xc7/6tm91whtshOr5uRSo/KMeSb2AHB75IHANEPTD94RdCDTmlYuXyE0FAh8nLWDZTiYx4t0A7Ob/OiHB/EpCCvJs/lrnOa+bK6eBdsIypJT2fR6ubtU75uC7NIYYAQ=="},{"type":"tool_use","id":"toolu_016MwrX67mtSSPQzKtUvKtwN","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, U.S. 1960Q1-2019Q4, OLS with Newey-West HAC SE. Reads only data/, writes out/.\"\"\"\nimport json, hashlib, os\nimport numpy as np, pandas as pd\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nD, O = os.path.join(ROOT, \"data\"), os.path.join(ROOT, \"out\")\nFIRST, LAST = pd.Period(\"1960Q1\", \"Q\"), pd.Period(\"2019Q4\", \"Q\")\n\ndef sha(p):\n return hashlib.sha256(open(p, \"rb\").read()).hexdigest()\n\nun = pd.read_csv(os.path.join(D, \"UNRATE.csv\"))\ngd = pd.read_csv(os.path.join(D, \"GDPC1.csv\"))\nn_rows = {\"UNRATE.csv\": int(len(un)), \"GDPC1.csv\": int(len(gd))}\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()]\nfor d in miss[\"observation_date\"]:\n data_issues.append({\"issue\": f\"UNRATE missing (empty) value at {d}\",\n \"handling\": \"Quarter containing it has <3 monthly values and is dropped; it lies outside the 1959Q4-2019Q4 levels window, so results are unaffected.\"})\n\n# quarterly average unemployment, only quarters with all 3 months\nun[\"q\"] = pd.to_datetime(un[\"observation_date\"]).dt.to_period(\"Q\")\ng = un.groupby(\"q\")[\"UNRATE\"]\nuq = g.mean()[g.count() == 3].rename(\"u\")\nn_un_q = int(un[\"q\"].nunique())\ngd[\"q\"] = pd.to_datetime(gd[\"observation_date\"]).dt.to_period(\"Q\")\ngq = gd.set_index(\"q\")[\"GDPC1\"].astype(float)\n\nledger = []\ndef log(step, rule, nb, na, why):\n ledger.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\ndf = pd.concat([gq, uq], axis=1, join=\"inner\").sort_index()\nlog(1, \"keep GDPC1 quarters that have a complete (3-month) UNRATE quarterly average\", len(gq), len(df),\n \"UNRATE starts 1948Q1 (GDPC1 starts 1947Q1); 2025Q4 lacks October 2025 UNRATE\")\n# differences only between consecutive calendar quarters\nidx = df.index\nconsec = pd.Series([False] + [idx[i] - idx[i - 1] == 1 for i in range(1, len(idx))], index=idx)\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"] / df[\"GDPC1\"].shift(1))\ndf.loc[~consec, [\"du\", \"g\"]] = np.nan\nnb = len(df); df = df.dropna(subset=[\"du\", \"g\"])\nlog(2, \"drop quarters whose previous calendar quarter is unavailable (first differences undefined)\", nb, len(df),\n \"first available quarter and quarters following a dropped quarter\")\nnb = len(df); df = df[(df.index >= FIRST) & (df.index <= LAST)]\nlog(3, \"restrict to regression window 1960Q1-2019Q4\", nb, len(df), \"task-defined sample; no extension of window\")\nassert len(df) == 240 and df.index[0] == FIRST and df.index[-1] == LAST\npd.DataFrame(ledger).to_csv(os.path.join(O, \"exclusions.csv\"), index=False)\n\n# OLS\ny = df[\"du\"].to_numpy(); x = df[\"g\"].to_numpy(); T = len(y)\nX = np.column_stack([np.ones(T), x])\nXtXi = np.linalg.inv(X.T @ X)\nb = XtXi @ X.T @ y\ne = y - X @ b\nk = X.shape[1]\nr2 = 1 - (e @ e) / np.sum((y - y.mean()) ** 2)\nse_iid = float(np.sqrt((e @ e) / (T - k) * XtXi[1, 1]))\n\ndef nw_se(L):\n \"\"\"Newey-West (1987) Bartlett-kernel HAC, no small-sample df correction.\"\"\"\n u = X * e[:, None]\n S = u.T @ u\n for l in range(1, L + 1):\n w = 1 - l / (L + 1)\n G = u[l:].T @ u[:-l]\n S += w * (G + G.T)\n V = XtXi @ S @ XtXi\n return float(np.sqrt(V[1, 1]))\n\n# Bandwidth: Newey-West (1994) / Stock-Watson rule of thumb floor(4*(T/100)^(2/9))\nL = int(np.floor(4 * (T / 100) ** (2 / 9)))\nse_hac = nw_se(L)\nz = stats.norm.ppf(0.975)\nlo, hi = float(b[1] - z * se_hac), float(b[1] + z * se_hac)\nt_hac = float(b[1] / se_hac)\np_hac = float(2 * stats.norm.sf(abs(t_hac)))\nneg = bool(b[1] < 0 and p_hac < 0.05)\n\n# cross-check with statsmodels (no df correction)\nimport statsmodels.api as sm\nm = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"use_correction\": False})\nassert abs(m.bse[1] - se_hac) < 1e-10 and abs(m.params[1] - b[1]) < 1e-12\nm0 = sm.OLS(y, X).fit()\nassert abs(m0.bse[1] - se_iid) < 1e-10\n\nsens = {str(l): nw_se(l) for l in [0, 1, 2, 4, 6, 8, 12]}\nrho1 = float(np.corrcoef(e[1:], e[:-1])[0, 1])\n\nres = {\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": float(b[1]), \"alpha_hat\": float(b[0]), \"r_squared\": float(r2),\n \"se_iid\": se_iid, \"se_hac\": se_hac, \"hac_lags\": L,\n \"beta_ci_low\": lo, \"beta_ci_high\": hi,\n \"okun_negative_5pct\": neg,\n \"mean_growth\": float(x.mean()),\n \"first_quarter\": str(df.index[0]), \"last_quarter\": str(df.index[-1]),\n \"n_analysed\": int(T),\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues, \"n_input_rows\": n_rows, \"random_seed\": None,\n # supplementary\n \"baseline_beta_ci_low_iid\": float(b[1] - z * se_iid), \"baseline_beta_ci_high_iid\": float(b[1] + z * se_iid),\n \"t_stat_hac\": t_hac, \"p_value_hac\": p_hac, \"critical_value\": float(z),\n \"se_hac_by_lags\": sens, \"resid_lag1_autocorr\": rho1,\n \"mean_du\": float(y.mean()),\n \"input_sha256\": {f: sha(os.path.join(D, f)) for f in [\"UNRATE.csv\", \"GDPC1.csv\"]},\n}\nwith open(os.path.join(O, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\nfig, ax = plt.subplots(figsize=(6.5, 4.5))\nax.scatter(x, y, s=12, alpha=0.6, label=\"quarters 1960Q1-2019Q4\")\nxs = np.linspace(x.min(), x.max(), 100)\nax.plot(xs, b[0] + b[1] * xs, \"r-\", label=f\"OLS: Δu = {b[0]:.3f} {b[1]:+.3f} g\")\nax.set_xlabel(\"Real GDP growth g_t (%, q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, U.S. 1960Q1-2019Q4 (n=240)\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.legend(fontsize=8); fig.tight_layout()\nfig.savefig(os.path.join(O, \"figure1.png\"), dpi=120)\nprint(f\"beta={b[1]:.4f} se_iid={se_iid:.4f} se_hac(L={L})={se_hac:.4f} CI=[{lo:.4f},{hi:.4f}] neg5%={neg}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/exclusions.csv","description":"Write and run analysis script"}}]}}43{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"5b8c5b1a-310d-4961-8275-b27ca0c5ce52","timestamp":"2026-10-30T05:04:03.775Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"7281ce8a-3e33-4fdd-ba6b-06231bb4e615","keep":12,"tail":["c91e6fe801f8d1c2aacc28c5fca39108f4408dda9413c786fcb9102d14637821","a20f1e0c37c2b5a80a071c46996998294fb896f996cdc263edffc9e60ae1e8c5"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8af0bd1421710714f5e25493635aba382bc6e6c062c9a265b296e82591cb308f"}44{"parentUuid":"fe3cb658-07a8-43ee-a444-6023ff02c4ed","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqXXjadh872FJMpa2Pf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XgZ6Zuurv4XW2CLEEqqMV8","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python -c \"\nexec(open('analysis.py').read().split('assert len(df)')[0]); print(len(df), df.index[:3], df.index[-3:], type(df.index))\"","description":"Debug sample filtering"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3705,"cache_read_input_tokens":11381,"output_tokens":150,"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":3705},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqXXUwTPd82dEoDBNSP","requestRef":"5b8c5b1a-310d-4961-8275-b27ca0c5ce52","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8c97c254-73cc-4771-ab65-81041366f968","timestamp":"2026-10-30T05:04:05.291Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"8c97c254-73cc-4771-ab65-81041366f968","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n File \"<string>\", line 2, in <module>\n exec(open('analysis.py').read().split('assert len(df)')[0]); print(len(df), df.index[:3], df.index[-3:], type(df.index))\n ~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"<string>\", line 9, in <module>\nNameError: name '__file__' is not defined. Did you mean: '__name__'?","is_error":true,"tool_use_id":"toolu_01XgZ6Zuurv4XW2CLEEqqMV8"}]},"uuid":"f382ed5d-bb75-4e42-897c-654ad1f937cf","timestamp":"2026-10-30T05:04:06.142Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n File \"<string>\", line 2, in <module>\n exec(open('analysis.py').read().split('assert len(df)')[0]); print(len(df), df.index[:3], df.index[-3:], type(df.index))\n ~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"<string>\", line 9, in <module>\nNameError: name '__file__' is not defined. Did you mean: '__name__'?","sandboxed":false,"sourceToolAssistantUUID":"8c97c254-73cc-4771-ab65-81041366f968","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}46{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"1cef819d6c4331122e3f146e2c50e9d7cb00dc161b28cc80db4427afb5f8224c","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01XgZ6Zuurv4XW2CLEEqqMV8","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python -c \"\nexec(open('analysis.py').read().split('assert len(df)')[0]); print(len(df), df.index[:3], df.index[-3:], type(df.index))\"","description":"Debug sample filtering"}}]}}47{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"46d8bea8-3744-4e4e-8f60-0d2dc33fa0f9","timestamp":"2026-10-30T05:04:06.145Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"5b8c5b1a-310d-4961-8275-b27ca0c5ce52","keep":14,"tail":["1cef819d6c4331122e3f146e2c50e9d7cb00dc161b28cc80db4427afb5f8224c","a13d06ce6f1a96e7e036a12b71bf28cd3e69730390d68dfe0260e196969f4e59"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"48fb58b116343e2bc0c1217cd87804761fa4951dade136ce8c0121f9cf2b512b"}48{"parentUuid":"f382ed5d-bb75-4e42-897c-654ad1f937cf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqXhuW9pGwar4JMvK2h","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NXyagUZd2DjhqVUN58Lxc7","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\n__file__='out/analysis.py'\nexec(open('out/analysis.py').read().split('assert len(df)')[0]); print(len(df), df.index[:3], df.index[-3:], type(df.index)); print(ledger)\"","description":"Debug sample filtering"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":356,"cache_read_input_tokens":15086,"output_tokens":167,"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":356},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqXhdtHTABAjrSw1MLz","requestRef":"46d8bea8-3744-4e4e-8f60-0d2dc33fa0f9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"edc14402-764d-4a83-a01c-205f5eeb7e8e","timestamp":"2026-10-30T05:04:07.642Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"edc14402-764d-4a83-a01c-205f5eeb7e8e","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01NXyagUZd2DjhqVUN58Lxc7","type":"tool_result","content":"0 PeriodIndex([], dtype='period[Q-DEC]', name='q') PeriodIndex([], dtype='period[Q-DEC]', name='q') <class 'pandas.core.indexes.period.PeriodIndex'>\n[{'step': 1, 'rule': 'keep GDPC1 quarters that have a complete (3-month) UNRATE quarterly average', 'n_before': 319, 'n_after': 314, 'n_removed': 5, 'rationale': 'UNRATE starts 1948Q1 (GDPC1 starts 1947Q1); 2025Q4 lacks October 2025 UNRATE'}, {'step': 2, 'rule': 'drop quarters whose previous calendar quarter is unavailable (first differences undefined)', 'n_before': 314, 'n_after': 0, 'n_removed': 314, 'rationale': 'first available quarter and quarters following a dropped quarter'}, {'step': 3, 'rule': 'restrict to regression window 1960Q1-2019Q4', 'n_before': 0, 'n_after': 0, 'n_removed': 0, 'rationale': 'task-defined sample; no extension of window'}]","is_error":false}]},"uuid":"1d1f1fb3-f2c3-480f-b151-5e866210809a","timestamp":"2026-10-30T05:04:08.494Z","toolUseResult":{"stdout":"0 PeriodIndex([], dtype='period[Q-DEC]', name='q') PeriodIndex([], dtype='period[Q-DEC]', name='q') <class 'pandas.core.indexes.period.PeriodIndex'>\n[{'step': 1, 'rule': 'keep GDPC1 quarters that have a complete (3-month) UNRATE quarterly average', 'n_before': 319, 'n_after': 314, 'n_removed': 5, 'rationale': 'UNRATE starts 1948Q1 (GDPC1 starts 1947Q1); 2025Q4 lacks October 2025 UNRATE'}, {'step': 2, 'rule': 'drop quarters whose previous calendar quarter is unavailable (first differences undefined)', 'n_before': 314, 'n_after': 0, 'n_removed': 314, 'rationale': 'first available quarter and quarters following a dropped quarter'}, {'step': 3, 'rule': 'restrict to regression window 1960Q1-2019Q4', 'n_before': 0, 'n_after': 0, 'n_removed': 0, 'rationale': 'task-defined sample; no extension of window'}]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"edc14402-764d-4a83-a01c-205f5eeb7e8e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"aef4bce006b566158243cc0187ed2812c4b1a774877c852201c26f6d75563abd","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01NXyagUZd2DjhqVUN58Lxc7","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\n__file__='out/analysis.py'\nexec(open('out/analysis.py').read().split('assert len(df)')[0]); print(len(df), df.index[:3], df.index[-3:], type(df.index)); print(ledger)\"","description":"Debug sample filtering"}}]}}51{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"5717bb1c-5f91-4215-afed-af2a4541a9bc","timestamp":"2026-10-30T05:04:08.497Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"46d8bea8-3744-4e4e-8f60-0d2dc33fa0f9","keep":16,"tail":["aef4bce006b566158243cc0187ed2812c4b1a774877c852201c26f6d75563abd","38b8e0769a1e0f4810f2156c853b51be7c75c2c58451f6e4b347d648234ddec3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"04b78affc1cb899579953f919d189d289f74f28fc5b8e0e3223d1ad0db3f75a8"}52{"parentUuid":"1d1f1fb3-f2c3-480f-b151-5e866210809a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqXsyjYKb2YEmN7U8QW","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSwgYKEAgTGAI4AUIIdGhpbmtpbmcSDOvmVBe7ceYKsu1HJRoM+B6eKbgIUozfInFfIjAQ5L5AhnXAGajpiE8cAgyJ690lXJMGhn9sae9zOABrfHsbNZRZguLNK/p1WaQd4ewq3wWFRTJt2b2MIRpzoXp7Uc6OMKdwuxLafBV1gxNHfoCHgQrkN54BpaS7q3n7I2AMFFIu9EiHjXC7xgSctOe7i/4SpmUsf3HHhl0XV+KIUW7ZUPf7/YbayWd7xWpnb7xwsMNJfvR8XHMw2qXHuGZthFQo7VERgnvhKqbACp5UGnR2lOrZ83rU0h/xMFET1Kki2t2lV4xOaxDu2EkTKuQZ9TVxgVWq6O0m1ptd+/T4fulYqM67wYvYMuzrGZ5zGcl+x9mSd0RughCtkiBavbSTPHUCMO+1CxQhg+yY9xsb3v+AWVYYM0zLA6f1YvY6dnPIDP6dsohZPEkk64Kodji+i29TjqVD716a3GkSTBQNT+N/DzZ2+FPDLSSYQQdVYzxLuGqLCYqWNVwTYbTHRYpBx9EvV/3mqA3s0DE6+4z71Bk1/OX0IJ5+ICnw9zFbbLtSsqFP8+KtvRDrgxYXkaojjyNO8Ce9Exn03nP8ERKMllW3SybAVjT5j3QC2a/S6iGbXiCouHqzhjekjCRMBE5IPa0EK7OwAGwJhlWh14VFP7gQCaL+mMSIEjlB7wJi6hen1thsFKiqLSVmodXjdHPYyCp1qnj3mFVtqlZ1PV+TzwA8BVYAqW0WejwR8JE3gJ4hHn6jbLQDBj0e1XE4vQr7M86jSyx2OVeEtIAJKm7C2m8sHETwb6eTIwt2ykx8oUhE6Oxrsigalh7t38+RoNn2tuW8/tK6S+LQRViTZl2ZkO24rg2VeXJHlMUmR1jDRb3X8P/Ay+ELlBXGWVDhdFkDzdZF9A61PMe5KvQsa1oEbLhnqa5jXa64I+1pOQxEwvBm8fXbxitaFBwfvW2G9LQ30mEMxlJZaZLWikrz6YSMUlEhgdXkMKgVRSWYtVVnIhzGq8YNBReaga3jq2JLxSAeVnv1/d98LEi+bDESnv00jYZjvfHvfNp6HALmIx7F8SHS/BDR7ETj/A0+GRJF/1qw3NoYAQ=="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":574,"cache_read_input_tokens":15442,"output_tokens":230,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":574},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":371,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqXshchLYBasnubARNb","requestRef":"5717bb1c-5f91-4215-afed-af2a4541a9bc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cd4651b4-dad9-41a0-a92e-b0bd37615265","timestamp":"2026-10-30T05:04:09.870Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"cd4651b4-dad9-41a0-a92e-b0bd37615265","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqXsyjYKb2YEmN7U8QW","type":"message","role":"assistant","content":[{"type":"text","text":"Period subtraction returns an offset; use ordinals."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":574,"cache_read_input_tokens":15442,"output_tokens":230,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":574},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqXshchLYBasnubARNb","requestRef":"5717bb1c-5f91-4215-afed-af2a4541a9bc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"71fdebf1-c05d-4fe9-890d-7376e5926379","timestamp":"2026-10-30T05:04:09.871Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"71fdebf1-c05d-4fe9-890d-7376e5926379","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqXsyjYKb2YEmN7U8QW","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01YCvjgvuiUrLvcTwMwqjqkB","name":"Bash","input":{"command":"sed -i '' 's/\\[idx\\[i\\] - idx\\[i - 1\\] == 1 for/[idx[i].ordinal - idx[i - 1].ordinal == 1 for/' out/analysis.py && ~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/exclusions.csv","description":"Fix and rerun analysis"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":574,"cache_read_input_tokens":15442,"output_tokens":230,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":574},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXqXshchLYBasnubARNb","requestRef":"5717bb1c-5f91-4215-afed-af2a4541a9bc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"57554a86-f885-43a0-be16-ba71e6a71081","timestamp":"2026-10-30T05:04:10.871Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}55{"parentUuid":"57554a86-f885-43a0-be16-ba71e6a71081","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01YCvjgvuiUrLvcTwMwqjqkB","type":"tool_result","content":"beta=-0.2558 se_iid=0.0200 se_hac(L=4)=0.0358 CI=[-0.3260,-0.1855] neg5%=True\n{\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": -0.25576772774872947,\n \"alpha_hat\": 0.18438835418210958,\n \"r_squared\": 0.40825082845620597,\n \"se_iid\": 0.019960092914910018,\n \"se_hac\": 0.03583463330296579,\n \"hac_lags\": 4,\n \"beta_ci_low\": -0.326002318421742,\n \"beta_ci_high\": -0.18553313707571692,\n \"okun_negative_5pct\": true,\n \"mean_growth\": 0.7535027550652363,\n \"first_quarter\": \"1960Q1\",\n \"last_quarter\": \"2019Q4\",\n \"n_analysed\": 240,\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"UNRATE missing (empty) value at 2025-10-01\",\n \"handling\": \"Quarter containing it has <3 monthly values and is dropped; it lies outside the 1959Q4-2019Q4 levels window, so results are unaffected.\"\n }\n ],\n \"n_input_rows\": {\n \"UNRATE.csv\": 945,\n \"GDPC1.csv\": 319\n },\n \"random_seed\": null,\n \"baseline_beta_ci_low_iid\": -0.2948887909900262,\n \"baseline_beta_ci_high_iid\": -0.21664666450743272,\n \"t_stat_hac\": -7.137445096377233,\n \"p_value_hac\": 9.508157930953505e-13,\n \"critical_value\": 1.959963984540054,\n \"se_hac_by_lags\": {\n \"0\": 0.028836223207270188,\n \"1\": 0.032358596534706116,\n \"2\": 0.034227320236154,\n \"4\": 0.03583463330296579,\n \"6\": 0.03687902855135959,\n \"8\": 0.037135504175401735,\n \"12\": 0.036408851102280426\n },\n \"resid_lag1_autocorr\": 0.38935129370212984,\n \"mean_du\": -0.008333333333333335,\n \"input_sha256\": {\n \"UNRATE.csv\": \"621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c\",\n \"GDPC1.csv\": \"1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343\"\n }\n}step,rule,n_before,n_after,n_removed,rationale\n1,keep GDPC1 quarters that have a complete (3-month) UNRATE quarterly average,319,314,5,UNRATE starts 1948Q1 (GDPC1 starts 1947Q1); 2025Q4 lacks October 2025 UNRATE\n2,drop quarters whose previous calendar quarter is unavailable (first differences undefined),314,312,2,first available quarter and quarters following a dropped quarter\n3,restrict to regression window 1960Q1-2019Q4,312,240,72,task-defined sample; no extension of window","is_error":false}]},"uuid":"420d6331-9786-497b-ad17-33d736dd9059","timestamp":"2026-10-30T05:04:11.982Z","toolUseResult":{"stdout":"beta=-0.2558 se_iid=0.0200 se_hac(L=4)=0.0358 CI=[-0.3260,-0.1855] neg5%=True\n{\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": -0.25576772774872947,\n \"alpha_hat\": 0.18438835418210958,\n \"r_squared\": 0.40825082845620597,\n \"se_iid\": 0.019960092914910018,\n \"se_hac\": 0.03583463330296579,\n \"hac_lags\": 4,\n \"beta_ci_low\": -0.326002318421742,\n \"beta_ci_high\": -0.18553313707571692,\n \"okun_negative_5pct\": true,\n \"mean_growth\": 0.7535027550652363,\n \"first_quarter\": \"1960Q1\",\n \"last_quarter\": \"2019Q4\",\n \"n_analysed\": 240,\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"UNRATE missing (empty) value at 2025-10-01\",\n \"handling\": \"Quarter containing it has <3 monthly values and is dropped; it lies outside the 1959Q4-2019Q4 levels window, so results are unaffected.\"\n }\n ],\n \"n_input_rows\": {\n \"UNRATE.csv\": 945,\n \"GDPC1.csv\": 319\n },\n \"random_seed\": null,\n \"baseline_beta_ci_low_iid\": -0.2948887909900262,\n \"baseline_beta_ci_high_iid\": -0.21664666450743272,\n \"t_stat_hac\": -7.137445096377233,\n \"p_value_hac\": 9.508157930953505e-13,\n \"critical_value\": 1.959963984540054,\n \"se_hac_by_lags\": {\n \"0\": 0.028836223207270188,\n \"1\": 0.032358596534706116,\n \"2\": 0.034227320236154,\n \"4\": 0.03583463330296579,\n \"6\": 0.03687902855135959,\n \"8\": 0.037135504175401735,\n \"12\": 0.036408851102280426\n },\n \"resid_lag1_autocorr\": 0.38935129370212984,\n \"mean_du\": -0.008333333333333335,\n \"input_sha256\": {\n \"UNRATE.csv\": \"621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c\",\n \"GDPC1.csv\": \"1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343\"\n }\n}step,rule,n_before,n_after,n_removed,rationale\n1,keep GDPC1 quarters that have a complete (3-month) UNRATE quarterly average,319,314,5,UNRATE starts 1948Q1 (GDPC1 starts 1947Q1); 2025Q4 lacks October 2025 UNRATE\n2,drop quarters whose previous calendar quarter is unavailable (first differences undefined),314,312,2,first available quarter and quarters following a dropped quarter\n3,restrict to regression window 1960Q1-2019Q4,312,240,72,task-defined sample; no extension of window","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"57554a86-f885-43a0-be16-ba71e6a71081","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}56{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"923a8ebfaf19bd8ba023305561e895a2a020a776916521995cf616e0aa8a689d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Period subtraction returns an offset; use ordinals."},{"type":"tool_use","id":"toolu_01YCvjgvuiUrLvcTwMwqjqkB","name":"Bash","input":{"command":"sed -i '' 's/\\[idx\\[i\\] - idx\\[i - 1\\] == 1 for/[idx[i].ordinal - idx[i - 1].ordinal == 1 for/' out/analysis.py && ~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/exclusions.csv","description":"Fix and rerun analysis"}}]}}57{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"7f8612cd-541e-43a8-b239-96ef272d6433","timestamp":"2026-10-30T05:04:11.985Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"5717bb1c-5f91-4215-afed-af2a4541a9bc","keep":18,"tail":["923a8ebfaf19bd8ba023305561e895a2a020a776916521995cf616e0aa8a689d","7f49f2a95884447fe8e4af36caf14f272e9e89b0c7a6fa2ed278cd62d2b9b24d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c5d6b5c10d44666f806308ffaedc907d45a1c8f337826b45c93cb5737275d49d"}58{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"420d6331-9786-497b-ad17-33d736dd9059","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}59{"type":"atis-latch","atis":"","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}60{"parentUuid":"420d6331-9786-497b-ad17-33d736dd9059","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqY8vQcFUqTqud8phHn","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":1330,"cache_read_input_tokens":16016,"output_tokens":884,"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":1330},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":795,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqY8cJkpdMvRhoAqWkr","requestRef":"7f8612cd-541e-43a8-b239-96ef272d6433","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3cb2cee9-6f87-4e79-af69-86f2ae9b347f","timestamp":"2026-10-30T05:04:13.743Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"3cb2cee9-6f87-4e79-af69-86f2ae9b347f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqY8vQcFUqTqud8phHn","type":"message","role":"assistant","content":[{"type":"text","text":"Now verification: clean rerun, identity checks, and an independent hand-check of one quarter."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1330,"cache_read_input_tokens":16016,"output_tokens":884,"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":1330},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqY8cJkpdMvRhoAqWkr","requestRef":"7f8612cd-541e-43a8-b239-96ef272d6433","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5cfda098-d87c-4a09-b85f-4b64a61a57ae","timestamp":"2026-10-30T05:04:13.744Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"5cfda098-d87c-4a09-b85f-4b64a61a57ae","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqY8vQcFUqTqud8phHn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01W3spwYZA5P7ZaJUbeJGQ8G","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; rm -f out/results.json out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r1.json && echo IDENTICAL; ls out\n~/wp29/venv/bin/python -c \"\nimport pandas as pd, numpy as np, json\nr=json.load(open('out/results.json'))\nu=pd.read_csv('data/UNRATE.csv',index_col=0); g=pd.read_csv('data/GDPC1.csv',index_col=0)['GDPC1']\nu59=u.loc['1959-10-01':'1959-12-01','UNRATE'].mean(); u60=u.loc['1960-01-01':'1960-03-01','UNRATE'].mean()\nprint('1960Q1 du',u60-u59,'g',100*np.log(g['1960-01-01']/g['1959-10-01']))\nprint('ci contains', r['beta_ci_low']<r['beta_hat']<r['beta_ci_high'], 'se>0', r['se_iid']>0 and r['se_hac']>0)\nprint('ci symmetric', np.isclose(r['beta_hat']-r['beta_ci_low'], r['beta_ci_high']-r['beta_hat']))\nprint('alpha check', r['mean_du']-r['beta_hat']*r['mean_growth'], r['alpha_hat'])\ne=pd.read_csv('out/exclusions.csv'); print('ledger', 319-e.n_removed.sum(), (e.n_before-e.n_removed==e.n_after).all(), (e.n_after.shift(-1).dropna()==e.n_before.iloc[1:].values).all())\nprint('neg rule', (r['beta_hat']<0 and abs(r['beta_hat']/r['se_hac'])>1.959964)==r['okun_negative_5pct'])\nprint('4*(2.4)^(2/9)=',4*2.4**(2/9))\n\"","description":"Rerun for reproducibility and run consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1330,"cache_read_input_tokens":16016,"output_tokens":884,"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":1330},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXqY8cJkpdMvRhoAqWkr","requestRef":"7f8612cd-541e-43a8-b239-96ef272d6433","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"55d00cb2-9437-4638-8786-70fe108afceb","timestamp":"2026-10-30T05:04:19.505Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}63{"parentUuid":"55d00cb2-9437-4638-8786-70fe108afceb","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01W3spwYZA5P7ZaJUbeJGQ8G","type":"tool_result","content":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\n1960Q1 du -0.4666666666666668 g 2.2237183500352184\nci contains True se>0 True\nci symmetric True\nalpha check 0.1843883541821096 0.18438835418210958\nledger 240 True False\nneg rule True\n4*(2.4)^(2/9)= 4.859050115969828","is_error":false}]},"uuid":"4e2c55dd-ca34-4b9a-b78b-397106821f6e","timestamp":"2026-10-30T05:04:20.891Z","toolUseResult":{"stdout":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\n1960Q1 du -0.4666666666666668 g 2.2237183500352184\nci contains True se>0 True\nci symmetric True\nalpha check 0.1843883541821096 0.18438835418210958\nledger 240 True False\nneg rule True\n4*(2.4)^(2/9)= 4.859050115969828","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"55d00cb2-9437-4638-8786-70fe108afceb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}64{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"e2eb5213be788789002ee34598f81b1ea0068b956c2b0c4dacc6b8e4ebaf3cd2","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Now verification: clean rerun, identity checks, and an independent hand-check of one quarter."},{"type":"tool_use","id":"toolu_01W3spwYZA5P7ZaJUbeJGQ8G","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; rm -f out/results.json out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r1.json && echo IDENTICAL; ls out\n~/wp29/venv/bin/python -c \"\nimport pandas as pd, numpy as np, json\nr=json.load(open('out/results.json'))\nu=pd.read_csv('data/UNRATE.csv',index_col=0); g=pd.read_csv('data/GDPC1.csv',index_col=0)['GDPC1']\nu59=u.loc['1959-10-01':'1959-12-01','UNRATE'].mean(); u60=u.loc['1960-01-01':'1960-03-01','UNRATE'].mean()\nprint('1960Q1 du',u60-u59,'g',100*np.log(g['1960-01-01']/g['1959-10-01']))\nprint('ci contains', r['beta_ci_low']<r['beta_hat']<r['beta_ci_high'], 'se>0', r['se_iid']>0 and r['se_hac']>0)\nprint('ci symmetric', np.isclose(r['beta_hat']-r['beta_ci_low'], r['beta_ci_high']-r['beta_hat']))\nprint('alpha check', r['mean_du']-r['beta_hat']*r['mean_growth'], r['alpha_hat'])\ne=pd.read_csv('out/exclusions.csv'); print('ledger', 319-e.n_removed.sum(), (e.n_before-e.n_removed==e.n_after).all(), (e.n_after.shift(-1).dropna()==e.n_before.iloc[1:].values).all())\nprint('neg rule', (r['beta_hat']<0 and abs(r['beta_hat']/r['se_hac'])>1.959964)==r['okun_negative_5pct'])\nprint('4*(2.4)^(2/9)=',4*2.4**(2/9))\n\"","description":"Rerun for reproducibility and run consistency checks"}}]}}65{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"537b3b3e-7fd9-4d29-8fc9-49aeabe4425a","timestamp":"2026-10-30T05:04:20.895Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"7f8612cd-541e-43a8-b239-96ef272d6433","keep":20,"tail":["e2eb5213be788789002ee34598f81b1ea0068b956c2b0c4dacc6b8e4ebaf3cd2","da911a5b217bf48b7c86c198c807c5abf69cf41f17f199675e496e9361d7ef19"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8823d1f27006620748621baab83606336375bbdd683ddc4490b117eb6f9607f6"}66{"parentUuid":"4e2c55dd-ca34-4b9a-b78b-397106821f6e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqYo4qrpZr6ArphKCuD","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":1030,"cache_read_input_tokens":17346,"output_tokens":471,"output_tokens_details":{"thinking_tokens":141},"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":1030},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1424,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqYnmjK8giZfW1JJVpx","requestRef":"537b3b3e-7fd9-4d29-8fc9-49aeabe4425a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f6ab9569-279a-4ef9-bba6-bd8f2fea64a7","timestamp":"2026-10-30T05:04:23.450Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}67{"parentUuid":"f6ab9569-279a-4ef9-bba6-bd8f2fea64a7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqYo4qrpZr6ArphKCuD","type":"message","role":"assistant","content":[{"type":"text","text":"The chain check expression was wrong (compared next step's n_after); redo it correctly and check the 1960Q1 row in-sample."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1030,"cache_read_input_tokens":17346,"output_tokens":471,"output_tokens_details":{"thinking_tokens":141},"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":1030},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqYnmjK8giZfW1JJVpx","requestRef":"537b3b3e-7fd9-4d29-8fc9-49aeabe4425a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"258f1156-50cc-403e-b71d-cc2d9f4b6f18","timestamp":"2026-10-30T05:04:23.450Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}68{"parentUuid":"258f1156-50cc-403e-b71d-cc2d9f4b6f18","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqYo4qrpZr6ArphKCuD","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_012CcKvzokNNavBg5FwnAR1P","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\ne=pd.read_csv('out/exclusions.csv'); print((e.n_after.values[:-1]==e.n_before.values[1:]).all())\n__file__='out/analysis.py'\nexec(open('out/analysis.py').read().split('# OLS')[0]); print(df.loc['1960Q1'])\"","description":"Correct ledger chain check and verify first row"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1030,"cache_read_input_tokens":17346,"output_tokens":471,"output_tokens_details":{"thinking_tokens":141},"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":1030},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXqYnmjK8giZfW1JJVpx","requestRef":"537b3b3e-7fd9-4d29-8fc9-49aeabe4425a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c3d78de6-2eb4-412f-855b-9fbe24419056","timestamp":"2026-10-30T05:04:24.912Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}69{"parentUuid":"c3d78de6-2eb4-412f-855b-9fbe24419056","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqYo4qrpZr6ArphKCuD","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01H96E7EhnmRg6q6HpR9pzbn","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0219/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":1030,"cache_read_input_tokens":17346,"output_tokens":471,"output_tokens_details":{"thinking_tokens":141},"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":1030},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":3,"requestId":"req_011CgXqYnmjK8giZfW1JJVpx","requestRef":"537b3b3e-7fd9-4d29-8fc9-49aeabe4425a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"361cd30f-b6f3-4511-9d34-2efb34070eb2","timestamp":"2026-10-30T05:04:25.351Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}70{"type":"tools-used","tools":["Bash","Read"],"sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}71{"parentUuid":"c3d78de6-2eb4-412f-855b-9fbe24419056","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_012CcKvzokNNavBg5FwnAR1P","type":"tool_result","content":"True\nGDPC1 3517.181000\nu 5.133333\ndu -0.466667\ng 2.223718\nName: 1960Q1, dtype: float64","is_error":false}]},"uuid":"408964ed-9da3-49a4-ae7c-44c26465a946","timestamp":"2026-10-30T05:04:25.745Z","toolUseResult":{"stdout":"True\nGDPC1 3517.181000\nu 5.133333\ndu -0.466667\ng 2.223718\nName: 1960Q1, dtype: float64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c3d78de6-2eb4-412f-855b-9fbe24419056","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}72{"parentUuid":"361cd30f-b6f3-4511-9d34-2efb34070eb2","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01H96E7EhnmRg6q6HpR9pzbn","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"iVBORw0KGgoAAAANSUhEUgAAAwwAAAIcCAYAAABb3ilUAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAASdAAAEnQB3mYfeAAA06tJREFUeJzsnQd8FFUXxU96QkjovXcUUEAUFVAECwIqWMCCiqhYsfcuYsHesKECNuyA+qGICIjYaIKA9F5DCSG97vc7b5i4SXZTdze72fPnN2x2Znbemzezs+++d8+9IQ6HwwEhhBBCCCGEcEGoq5VCCCGEEEIIIYNBCCGEEEIIUSyaYRBCCCGEEEK4RQaDEEIIIYQQwi0yGIQQQgghhBBukcEghBBCCCGEcIsMBiGEEEIIIYRbZDAIIYQQQggh3CKDQQghhBBCCOEWGQxCCCGEEEIIt8hgEEIIIYQQQrhFBoMQQgghhBDCLTIYhBBCCCGEEG6RwSCEEEIIIYRwiwwGIYQQQgghhFtkMAghhBBCCCHcIoNBCCGEEEII4RYZDEIIIYQQQgi3yGAQQgghhBBCuEUGgxB+zuTJkxESEmJeqzp9+/Y15yqEECXx6KOPIjo6Gtu3b1djueHFF19EREQE1qxZozYSFUIGgxA+ZPHixbjqqqvQunVrxMTEID4+Hl26dMHdd9+NnTt3Bsy1aNmypenci4JtQmNny5YtJRpE8+bNK3XTzZ49G0OHDkXjxo0RGRmJWrVqoX379rjooovw6quvwuFwVOgyHDp0CM899xwuu+wyHH300QgPDzd1/Omnn4r93NKlS00dGjRoYOrVvHlz3Hjjjdi7d2+xn5szZ445n4YNGyIqKsqc11lnnYWZM2e63P+3337DwIEDUbt2bfOdOeaYY/Dyyy8jNzfXbRk5OTl47733cOaZZ6J+/fqmfnxlOTS83X3233//NZ3Q8847z5wP24ELj1dWeF1++OEHjBkzBl27djXXjZ3bDh064Lbbbiu2nQ4ePGj24T1lt9GoUaOwY8cOl/t/+eWXppw+ffqYZwrrPGLEiGLrl5ycjAcffBAdO3Y09WL92D68PsWRmJiIsWPH4oQTTsg/J7bVJZdcUqb7+pdffkFYWJip60MPPYSyQiOB9+3o0aPRrFkzVDYLFy7EPffcg+OPPx716tUz161Vq1a45pprsGHDhlIdY926dYiNjS3x+q1evRrDhg0z97R9T/G+TU9PL7LvDTfcYOpz1113Vej8hOBDTQjhZfLy8hz33HMPe3aO8PBwx9lnn23e33bbbY4TTjjBrK9WrZrjiy++KPLZSZMmme189RdatGjhOPXUUz1+XB7T6msFHmwT1n3z5s0lnt/cuXNLdcwnn3wy/54ZPHiw48477zT3zQUXXOCoV6+e2ZadnV2hei9btswch0vTpk0dDRo0MH/Pnj3b7We+/fZbR0REhCMkJMRx7rnnOu666y5TP77nMbZu3eryc3fffXd+Oddee63j/vvvd1xzzTWObt26mW2FmT59uiMsLMwRGxvrGDVqlCmnQ4cO5hgXXnihyzK2b99ujsd9eC4jR4405Vx11VWOhg0bmvU9e/Z07Nmzp8hnX3rpJbOdZXbs2NERHR1d7jZOT083n42MjHScfvrp5trx+37MMcfk123dunVFPrd//35H+/btzT79+vVz3HvvvY7zzjvPvK9fv75j48aNRT5z7LHHmu3Vq1c39ebfl112mdu6HTx40HH00Ueb/Tp16uS49dZbHVdffbWjbt26Zt27777r8nPz58/P3+eoo45y3HTTTY777rvP3I98fnE9r2tJ7XX48GFHy5YtTX35mQcffNBRVlhOaGioud7+AK8n69O7d2/TnrzeJ598sjk/3r+//fZbsZ9nm/G3wG4Td9fvjz/+MG3N798ll1xingc9evQwn+nVq5cjIyOjyGfGjx9vti9cuNBj5yuCj8D8ZRYiwHj88cfNA5s/kitXriyy/csvvzSdE3ZUfv755wLbZDAEp8GwZcsWcz/Ex8c7VqxYUWR7bm6u44cffjDGaEVg5/Gnn35yHDhwwLy/8sorizUY2BG2jYqvvvqqwLZPPvnErD/nnHOKfO6dd94x23j8zMzMItuzsrIKvE9KSjJGETvcixYtKlD+SSedZI41derUAp9JTU11dO7cOb8cvi+83T4/drIK12PNmjWmQ5aWllbgmpbHYOD5jBs3zrRv4et23XXXmePSyCrM6NGjzbY77rijwPpXXnnFrD/rrLOKfIbPDBofvBd4b5VkMNxyyy1mn/PPP7/Aue3du9fRrFkzR0xMTJGO+KpVq0zHl53i1157rch9t23bNkf37t3NcceMGVNs29B4q1WrVr5BXFaD4dChQ6bTfMYZZzj8hWeeecaxc+fOIuvtc+R9WdJvBO91+zq7un45OTnGUOP2GTNmFLinaLRx/dNPP13kc6wXr1tx94QQJSGDQQgvww4kR4g5IuSq42fz5ptvmgc+R1D5A1CSwcCOSJ8+fcyo7lNPPWXWPfroo247pKyH3ZFyxu5Acftbb71lftiioqLMaCZH8fjjXJoZBo4ajh071oxYxsXFmZGy1q1bO4YNG+ZYvHhxuWcY2KljB4WzMs2bNzc/quxs9O/f3zFz5swixzjxxBNNW6ekpBRYf8opp5hjc6TamdWrV5v1l19+ucOfDIbPPvvM7MvRZV9SksEwZ86c/A63KzjazXuSBo8NRz3Z+ef1c2UsuOK9994z5VxxxRVu68Br6swTTzxh1nNk1/k75AzX2yO/nFEojooYDMXBDpw9I+BMcnKy6ayzY87vU+F62/VxNctgUxqDgUYB93E1eGHPsrAD6wy/b1zPGQV37Nq1y3w3ud/SpUtd7sNZI27/8MMP859tZTUY7Gelq5kQ5+cc/x4+fLijTp065pl23HHHmdkxX8JOPq8p68TZI1fQIOZvBO/f4q6fu/ue8J7gNt4jrgYR+vbta9qAhrgQ5UEaBiG8zKRJk4wPNP22qVdwB31dGzVqhLVr12L+/PnFHnPbtm3o1asX/vjjD3zwwQe4//77K1xP+t9yOfbYY3HTTTehSZMmmDhxoql3SXDwYcCAAXjkkUeMDzXPhb6zPXv2NL7Kv//+e7nrRX/uW2+91fhcn3HGGbjjjjtw7rnnYtmyZca3/d133y2wf//+/ZGdnY0FCxbkr0tLSzNtRQr7aNvv+Tl/ok6dOuZ106ZNxfrr+5o9e/aYV+pwXMH1vB9+/vnnAjqMffv24fzzz0doaCj+97//Yfz48XjllVfc3hv253lfFeaUU05BtWrVjL4hMzMzfz3vV0KfeJbjCq6n7z556623UBlQhEqoF3GG9yj90PndjouLK1JvagzI3LlzvXYN7XXO35PNmzeb9/TL5zPCHXx+8btP3n777SLbExIScO2112LIkCElaiyKw9bX9O7d2+0+W7duNToLaoouv/xyDB8+HCtXrjT6lIq2X1mgHsG+ztRsFIbXm/WjzuW+++4r9ljFfSd43aht4nnzmVEY3lP8rvB5LER5KPi0EkJ4nF9//dW8nn766cV/GcPDcdppp+GTTz4xAjr+7Yrly5fj7LPPRmpqqhGKlnTc0sLOyj///GMEjIRGTr9+/cyP619//WV+fG0KC3v5Q8zOGzsC06ZNK7AtLy8PSUlJ5a4XhZX8EWzatGmB9TwmfwTZgaFgl4JYwjo/+eSTpoNj/7DSeMjKyjIGBzuvGzduRJs2bQp0jPg5f+LEE09EixYtzDXhvTBy5EhjgFGk6qrj4Svq1q2b34l0hd1ZoeFrs2jRIvNKgWa3bt3M/VLYAKBwl+JMG/vz7AS5+q5QULpq1SpT3lFHHWVEsDSkua0kQT7bk/uxDIqPKdz2Je+//77Ljl9x50zatWuXL46t6DXcvXu3uYYUupd0/exn2HHHHWe+j8XB7xjFyK46pjQW+DyoqKHG+nBgwl07EQqwH3vsMSMGtrn00ktNm7N+zs9XCv8ppC8LfNaxk18SX3zxhRns4Pe5Zs2aRbbTSOB1YBCBwgZkYUpzf/De4GI/32woxia8LoMHDy6x3kIURgaDEF6GP8ykNJE87H127drlcjs7uxdccIEZfeSDn7MBnoKzA7axQPjjxYhO7GwXNhjcYXfaC4+MltTJKA6OahY2FkiNGjVM5Jg777zTdEjZ6SQnn3yy6Zg6j5Dyb57P448/btqQ7/mDys4LOxb8ofWHSCvOMFrKN998gyuvvNJcA3vGhG3MH3+OmF599dWmfXwJjTR2fNjmM2bMMCO2Np9//rkxaO1oOs4jy4QdNXZQeS7sbLGjxOgtP/74o4m45BxlxzYyeZ1dYa9nZ8/5e8aZGVf3oTPczv1oLDA6mS8NBrYb70N+h8eNG1dgW1nPubwMGjTIzMyxM/3pp5/mG6CcBXrppZeKXL/yPMMKR3SikcT7+bPPPqtQe9Pw53Xjd7a4EMw0tgtHX+IMDZ9xfJ45w/bkNSkLjGBVksHA+5vRq/jsYXjTwvA59Nprr+GZZ54pYri5oiL3B6OSERrVQpQHGQxCBAgcgWXHij+U33//fYHOvSfo0aOH2x9/586DK/hjxx/PqVOnmtkAdiLpLsBjMqRlReFIsj1qyc5LRkZGge3OIWlpLNBo4MzIgQMHTMeQU/nsZJ900kmms8IfaoZj5Kgef1zZ+fZHGEKUrlcMx8vzYX3pwsN24PLOO++Y9RUxyMpjyNCViDMedDGiexjvScZ5/+6778x98PfffxdwCaJhRthxYqeRnS1CFz3OSDEsJN3weG68Rr6k8L1UFjgqXbhzVtzIM0d+zznnHOMyx4564VFgX8GwqLNmzTLPFNaV7nicsaQBSFdEdirduXSVp105I8kwsTQKGQ60IvA7TUq653lermbi+Ewr7AbH+7Gi4YkLQyOZM8E0wiZMmFDkvuZ9Y88actDD2zAsMdm/f7/XyxJVExkMQngZjuwwvntpkgvZ+zDuemH4I8eOBn9gvDEa7mq63J4iL8mHnj/M7JSzI8JOyL333mvWcxSVI+RPP/00qlevXm5XKboL0UWKHRt2UOmOwA4NO6bs5Dj7sRPux/qwM82/2el+4IEHzDYeiz7Q7CB4Ur9gd7DszrEr7G1l7YzR8HI26DhCynblaD5HRsvqTlFRrrjiCnMPUofAWQG6xtEtiDkO2FHidWGM+ML3Ft2RbGPBhloEjvwybwLPy+5Y2aOl7tzZ7PX2se0RVHYo6Rde3CwDt9sdT2c3qLLCdqeBXJqRZxoLdIOhJofGAu/jwpT1nMsLtQac6XjiiSeMkffGG28YNyUaztQL0QB0vn5225blGebcrpwJ5PVgORXFvq4lGXru2ojPtOK+o56A3wE+Z+hCROOa+UkKQy0W70E+i0rrYliR+8PO0VDS7JsQ7pDBIISX4Ug7O678YaAPrzvYKbddMuj2UZinnnrKdMwoomZnlx2swh1P+72rRFMVdWMoCY740Z2BCxMVccSYwsfXX3/dlP3hhx+W67h02+CPHduwsG86DREaDIWx9Qhsc7YJOwi2UcBtnAlhZ5sGA90a3OlFyoL9Y85OgDtBsD26V9EOH93D2K7UrziLi30J28xVu9GYcPaZJpxBKO687dFi58RT/AxnVtjRpu+8M7y/6e7Bzp/d1pxxoxHDDiu/RxzddQe38xisT0VG+YtL0ucMBwx4//HeoE+7sxuXM3Y7udMorF+/3rwW57tfWjjTxnuIizP2/eR8/Wxx8ZIlS8x3ubj71xYkO18zzoyxM+vOOKPmiAvbZfr06cXWm2Vz1tI2+DyBJzUMnAHlteaMG2cWXBkLdpvwfqcmyRUff/yxWeh2SgO8oveH3V7OhqAQZUEGgxBehtPO7OzT9YKuNZ06dXK5H318qV3gj8Kpp55aZDt91Tl6T4EvR3I5qs4ISc5CObvj5WokkJ0vX9G2bVuzUGTIHyhXnfrSQuOD0+muhKzuokmxs8NZCFu7wFE1e+TaNhxofFFcTrcfW8hbEewfds4EOXe2nH+w+YPO62j/8FcEO4qOp10pKtrx+vbbb03HkOJXG7Y5DTNmqKXxVtjQtUXQFDLb0LBjh4nZkplF2Bm6YzHyFXUrzhoOupk9/PDD5vtGcasrH3eWz+2EI+oVdb0pCYrWadixw/z1118b/YA7KIzlvcr7kkJZ50hJrDddEoknDFx38JlC+N21oVHGa8jvE10D2bl3BbUFdqQq58/TiOT1Kgy/D7yW7HjTwOAMVGmgKxtnDQ8fPmy+5xXFUxoG6jZ43/KZRWE370d30J3PlRsoDQ4+m2jI8pnn7HpqB3Tgd6JwZDyK1WlIULvhasCCBgwpjVBbCJeUKxirEKJMPPzwwyZGNvMSMAFSYaZNm2ZidZcmcRvjeo8YMSI/8ZJzwismneJ65mdwjh3PpEp27PXi8jAUxo4JzvwOxbFp0yaXseEZb545EZjTobx5GJioiuuWL19eYD1jsNsZil1lwWZSLDs7buEET0ygx/Xcfvvtt7usi33s0mK3FbMYF056xRj6TFbF7cw8XJgNGzY4/v333wLX8s8//zTnZScRc4b78drzeDfeeGOJx/JkHgZSOEeAnRSNWZ/5WcbJL4y97cUXXyywftasWSZvQ82aNQvk/GC8eGYVLkviNubeYB4QO99G4bbje663My2XlCW4onkYmEWbOQD43WaSvdJQnsRtZc3DwPuROR8K88EHH5hr4SqPBXM2MD8En1FvvPFGkc/u2LEjP+Mw8wTwOVUS5c3DwCzK7u5Rd/lmvJ1NnnlHWrVqZRKkuXoelZbirl9xiduY+dxd4jbCfCbc/s8//5S7biK40QyDED6A4f0oKmSkDI5E02ebMw3UJDAc6Z9//mlGFukqU9LoIf1dp0yZYsS9jHTCkSrOPHCklfoGjrpy1I5uKxyR4qgfR31ZZml8kMsD3XtYD46s05edGgyK/TizwHO0NQ3lgWJJCjTpFkHBJF1/OFvC0IoXXnihOXdXcESU/tn0Jy6sUeB7unTZfxfG9nEuS/hSjgYyxOuzzz5rROB0r+BoH0dBGZmJI3xc/8ILL7isK33h6WZj+/hztolRqm6++WZz7vwsrzlHIDnCyFj6nMVhdKuSjlUSjFRku0vZITQ5kvzRRx/lu19wseH9x/PgOdMfnrMnvMdYN/rAX3/99UXKoHsGR4Xpu808DBxNZh3pgsJ25r3sHP2FI8ccreY1ZjkXX3yxmWmiaJq+4VxfWKxOQTbbhsJizthxpJa5OuiDz+8B37OOPDbvzcLRt9gGbAvn94TRqOzZCobBdOdG4gwDBfBaULPAV848uco5wfvb2cWHsx90meKzgjNW/B7TpYn15Wwd27EwbEPblcfOscCyOLtJOIP2/PPP5+/P0X66JHEWiCPZnGXhrAY/w+8v3aYKz7zwecX24/ecbjasB59VnAXhiDqvKY/L+5QzKd4M/ctIcbz/+FzwVFjpisJ7lC5qnCnhK5/5heH1KO130hVsU7qk8rnO+58LZyA488NnIl1Zb7/9dpfPM7qKcWazc+fO5S5fBDmVbbEIEUxw1JgjPRzhjo6ONiN2HBHliJm70U53mZ6ZzfPmm282284888z80dTExETHNddcYzLrcnSWx3/77bdLlem5vDMMrPv9999vRiY5cstymzRp4hgwYIDLbMzucDf6x+ysPXv2NJlxa9SoYWYM5s+f77ZtCLNq27MEf/31V4Ftn3zyiVnP7KquRsv//vvvEkdp3fHdd9+Z2Q22A4/PrNcceX3yySeLZJ8uLks068V6ckaiS5cuZqSao7vMpMsRdo4kuholLk3GaXefcbcUvv6///67ybzdsGFDM4PEuvF9Sdc6ISHB3LPM+Gx/bsiQIeZ74Y5ff/3VHJszEPzOMBM5ZymKG8Hm7MrEiRNNdmLOUnDU1z6Xc845x7F7926Xn7O/I8UtpcnSXdpjubtOBw4ccNxyyy357cR25gyVu2eEneHd3cLrW7h9ONPSvn17R7Vq1czCDN28RzlTVBys22OPPWayJsfHxxco56GHHjJZvUtLeWcYSNeuXR2NGjUqch9U1gxDaa51ae6d0swQcZaaMwr8/vBZ265dO8cjjzzicjbSnsUrTWZzIYojhP9VttEihBD+xKuvvmpGful/7k5zIgILO5EfIwBR+1KR6EiiIIyOxpwOnPGh7sQXiQU5G0udBGczSpONPpjhjAzveSasdJfDQYiSkMEghBAufmAZtaqkiC0isKDbEyOV0S3Q1/krqjoUNjMSGsP90m2muKRqnoBjnQxkwEhDdN3ydnmBCt0A6SbFQRC6NwpRXmQwCCGECBqov6B2gp0oah2EZ2AGZuoumB+BBjcjGXmbFStWmBkGGoFMOCeKwiSfDOFKHZlzRD0hyooMBiGEEEIIIYRbvBuAWgghhBBCCBHQyGAQQgghhBBCuEUGgxBCCCGEEEIGgxBCCCGEEKLsaIZBCCGEEEII4RbF2KoEDh06ZJKoNGvWDFFRUZVRBSGEEEIIUYXJzMzE9u3bceqpp6JmzZoVOpYMhkqAxsKQIUMqo2ghhBBCCBFETJ8+Heedd16FjiGDoRLgzIJ9Adu2bVsZVRBCVAJTp07FJZdcorYXQgjhdTZs2GAGqO1+Z0WQwVAJ2G5INBY6depUGVUQQlQCjRo10ndeCCGET/GE+7tEz0IIIYQQQgi3yGAQQgghhBBCuEUuSUIIIYTwKHl5edi7d6+J0sK/hRCeJywsDLVq1UJ8fDy8jQwGIYQQQngMGgjbtm1Denq66dBwCQkJUQsL4UEcDgfS0tKQkZGB6OhoREZGwpvIYBBCCCGEx+DMAo2F2rVro379+jIWhPASqampxjjft28fmjRpAm8iDYMQQgghPAbdkDirIGNBCO8SGxuL8PBwZGVlebkkGQxCCCGE8LBLktyQhPANoaGhxj3J6+V4vQQhhBBCBBXSLAhRtb5rMhiEEEIIIYQQbpHBIIQQQgghhHCLDAYhhBBCiEqiZcuWePfdd31e7vLly3H22WejYcOGxq3lp59+KrLPv//+a/apW7euiXo1atQoJCcnF9jn0KFDuPHGG9GoUSNUr14d7dq1w48//lhABH/TTTeZY8TFxWHw4MHYvn17gWPwmHfffTdat26NmJgYNGjQACNGjMCmTZsK7Pfqq6+iZ8+eqFatGpo2bVqq83zxxRdx3HHHoUaNGkaIz/JXrVpVYJ/ExERcdtllZp+aNWuav3lenm6r5FKep01OTg6OP/54U+aGDRtQmchgEEIIIYRfkpKZg+0H08xrVcOTkW1yc3PLnCCPcfvPP/98fPfddy63Hz58GGeeeSa6d++OnTt3mg7xxo0bceWVVxY4h9NPPx1JSUlYvHgxUlJS8PPPP6NDhw75+9xxxx1YsGABlixZYo7DzvS5556bX1+GBj3llFMwf/58fPnll+YYixYtQkREhOksr1u3Lv9YjRs3xj333IMHH3yw1OfJPAUvv/wy9uzZg61bt6Jjx46mzgz9a8NOO8MB8/zYMeffzucZ6YG2Kst52jz11FOmvfwCh/A5K1eupJzdvIrgJTkj27HtQKp5FcHB66+/XtlVEMLrbNy40SwVISsn1/Hl4u2O2z9d5rhmyiLzyvdc7w327t3rGDp0qKNGjRqOVq1aOT766CPzOz137lyzfdKkSY4mTZoU+Myjjz7q6NWrV4Hvd6dOnRxxcXGOBg0aOEaMGOHYt29fkf0feughR6NGjRxHHXWUY8CAAY6QkBBHVFSUIzY21nH00Ufn7z9lyhTHMccc44iPjzfrp06dmr+N9WL9uK5du3aOyMhIx+7dux2fffaZ2Zd1qFOnjqN///6lOn8ea/bs2QXWzZw501GtWjVHbu5/bc59WN9t27aZ9++++645l4yMDJfHTU9Pd8TExDimT5+ev45tEh4e7vjll1/M+yeffNK0u3Nb2bC9Bg4cWGS9q+tRWhITE835Ll261LzfsmWLef/333/n78O/uW7r1q0ea6sny3ieS5YscbRp08axfPlyU+b69evL/H3zZH9TMwxC+Jjs3Dx8tWQHHpm+EmO/W21e+Z7rhRBCAN/8vQvTlu3Epv2pyMrJM698z/XegCPMzJpL1xCOlE+dOrXMx6C7ytdff21cWf78808zYjxmzJgC+/zxxx9mRNku5/vvv0fz5s3x+uuvmxFn21Vm8uTJeOihh/Dee+8Zd5m3334bo0ePxq+//lrgeJ999hl+//13M8JNdx+ex2uvvWbe79ixAw888EC524R9Y3ux4awA3//999/m/ezZs82I/XXXXYd69eoZV5vbb7/djKaTtWvXmpH8E044If8YdNlp1aoVli1bZt5z1J5uQlxfGI7Qswy6NXkKuksxf0H79u3Ne55LVFQUjj322Px9+DdnFezz9ERbleU8+cp1b7zxBuLj4+EPyGAQoor/EAohRCBB96OFG/ab144N49C4Zox5dV7vSehCws7ac889Z9w/uDz99NNlPs4FF1xgOqGMi9+iRQvcd999BXz5CX3WH374YURHRxs//OL87ul206NHD3O83r17Y/jw4caQcOaZZ55BnTp1TIeXfu40RugOs3//flNGv379UF5OPvlkY4TQ6GCnn+00btw4s40GCWE5c+fONUYDDRT69vP9XXfdVWA/6gKcqVWrVv624rIUU6eQnZ2NgwcPwhOsWLEC119/vXFRotFg15HahcKwznYdPdFWZTlP3iPUatDNyV+QwSBEFf4hFEKIQCMxNQvJmTmoERORH2Oer3zP9dzuSdjRJRz1tnH+u7RwdoEdRwprOSp8+eWXmw4g9QU2NCRKEzd//fr1uPPOO02n1V4467FrV8GBJed60gD54YcfTKedGoIuXbrglVdeQXlhmTze0qVLTb1PPfVUXHrppWabPUrO86QRROOIRgtnGO69917TFvZ24iwgJpw1sbdxZoIdbHfXhgaTq1F5V1B0bS/0/3fmr7/+Qv/+/TF27Fhcc801+etZD2owCsM6l3Z0v2Yp2qq05/nbb7/h888/N0ajPyGDQYgq/EMohBCBRq3YSMRFhSMpPTvfxYOvfM/13O5J7Gg7W7ZsyV/n/Dfh6LHtZmPj3Hlnh++iiy4yLkjbtm0zo8offvhhft1t2CksjKt1dG+iOwo7rfZCl6WZM2cW+9k+ffpg2rRpZuSfrknsvHP2pLx069bNfD4hIcGIgRkJiYbJiSeeaLZT5FscNFwYDYjiXhvWje3LY5NBgwaZ83I1i8A25CwJZ05KA9vIXpzdsebMmWNG6zmLdPPNNxf4TNeuXY0LEGcfbPg3Bd3c5qm2GlTK8+SsFEXXNL5oQNhtTLeuJ554ApWFDAYhqvAPoRBCBBrVo8LRq21d87pmTzJ2HUo3r87rPQndRDjyzOg7HPnmUtj3n51BhsSkZoC+6fPmzcMXX3yRv50dVK5nB4+uQJwhKK1bE40D+vo7c9ttt5nOITvaPC47tPybkYbcwShArBONCw5EcdSbr+HhrtuLvz2MIMSF0CWGfzOUpw3Lo6HEdYx0xHo99thj+S48I0eONNuff/5583kaS+yUDxs2zGxnW1x11VV45JFHzDa2IWdOjj76aPTq1cvsc+uttxqjjR1q+vtzRoZhV6+++mozYj9+/Pj8+rAerCPLInb9nY2ywtCAGjp0qAldy/oWhjMCAwcONG5UNGa48O9zzjnH6Es81Va3lvI8GVWK9w/34WIbid988405RqVRYdm0KDOKkhTcMNLHZRP/cJz3+q+OK97707zyPdeLqo2iJIlgIBCjJDHC0HnnnWciErVs2bJIlCTy5ptvOpo2bWoiEF188cWO22+/vUCUpKefftrRsGFDR/Xq1R0nnXSS45VXXjHHyM7OdhlVyeb77783kY4YQadLly7561mH7t27m/WMeHTqqac65s+fXyBKkn1ssmvXLke/fv0ctWrVMhGXGGHnhRdecHvOmzdvNscovLCeNjfccIOjdu3aJtIRoy9NnDixyHF+++03R8+ePU2UoGbNmjnuuusuR1paWv52RlC68cYbzXFYL0YDsiMH2Rw6dMhx5513mrZnxCfWg+XZkYxsWDdXdea5uIPHDA0NNWU7L2xfmwMHDjguueQSc/25XHrppSaakqfb6lApz9PVdarsKEkh/K/yzJXghFEQOnfujJUrV6JTp06VXR3hYxgNiQJnahbohhR3ZNTs3K6NERGmSb+qzIQJE0wCIyGqMnYSKrpUVJSUI66anH319MxCcXCUmO4hFPD27dvXZ+UKi08//dREXuKoOvUAVZVPPXCexX3fPNnf9N23TwhhoFFwwXFNcVbnhpXyQyiEEIECn416PgYfF198sfH/p1D5pJNOMiFOqyIXB9B5qpciRCWhH0IhhBDCNcwGHQycGyDnKYNBCCGEEMK5cxQeXqyQVohgQw7TQgghhBBCCLfIYBBCCCGEEEK4RQaDEEIIIYQQwi0yGIQQQgghhBBukcEghBBCCCGEcIsMBiGEEEIIIYRbZDAIIYQQIuhZsmSJiYlfu3Ztk0zrqKOOwlNPPYXs7Oz8tpk3bx5CQkJMJmhXLF++HIMHD0b9+vURFxeHFi1a4Pzzz0dWVlaZ25dZplkWk3v5Azz37t27m7Zp1aoV3nzzzWL3nzNnDvr37486deqY89iwYUORfWbNmoUTTjgBNWrUQIMGDTBy5EgcPHjQ5fGGDh1qjvPTTz95ve4vvvgijjvuOFMvXsvBgwebrMnOMAM4E61Vr149f3njjTcK7LNjxw5cdtllpg14PzDb8ooVKxCIyGAQQgghRFDz888/o3fv3jj66KOxevVqHDp0CG+//TYmT56MIUOGIC8vr8RjpKam4vTTT0ePHj2wadMmHD58GL/++ivOOOOMcuV0YOeTBsy0adOwd+9eVCZbt27FoEGDcPXVV5u2Ybvcd999pm7uiI2NxRVXXIEPPvjA5fZ9+/bhvPPOw7Bhw4yRsHLlStNuN998c5F9eYy0tDSf1T0jIwMvv/wy9uzZYz7fsWNHc23T09ML7HfPPfcgJSUlf7nxxhvzt/GceE81bNgQ69atM/fD9OnTzfuAxCF8zsqVK/nkMK9CiODh9ddfr+wqCOF1Nm7caJZAon379o7LLrusyPrVq1c7wsPDHVOnTjXv586da36/s7Ozi+y7ePFis+3AgQMVrs+uXbscERERjn///dfRp08fxxNPPFFg+5VXXlmkvqeeeqrjwQcfdHiDxx57zNG1a9cC62677TZHv379Svzs5s2bTbusX7++wPqlS5ea9YcOHcpf99prrzk6duxYYL/t27c7mjVr5ti6davZf/bs2T6ru01iYqIpm3UubXs/9NBDjuOOO65Mdd2zZ4/jvPPOc9SoUcPRqlUrx0cffWTK5X1Xnu+bJ/ubmmEQQgghRNDC0V8udIcpDN2S6DLz3XfflXicDh06oFGjRhg+fDg++eQTrF271uV+NWvWNNuL45133jHlcmT7mmuuMe9zc3NRETj6zbLdLXS7ccfff/9t6uPM8ccfj2XLlpW7Pl27dsU555xj3IPo9sXR/E8//dS4cNlwZmbUqFF46KGH0Lx583KV44m6//jjj2bGpH379gXWs+61atUy14mzFpxlsJk9ezZat25tXKno5sb744knnij2Ol566aVm++bNm42L3Oeffw5/IbyyKyCEEEKIKs5tt7Hn5tsyu3YFXn65xN3oGkOaNGnicnvTpk2RkJBQ4nHow/7nn3/ipZdewvjx441rE33Xb731VtOZpP89oVtMcbDDOHHiRDz55JPm/UUXXYRbbrnFGC104SkvdHEq7GNfWuhOU7izzI4y15cXtgeNtDFjxhiDgOdN960HH3ywQIecRsPo0aPLXU5F607NwfXXX29clGg02FDfQkOBxtY///xjzoUd/c8++8xs379/P/766y/jTsWOP+8HGmXUPdx7771FyqHega5x1EqwfoT3wDfffAN/QAaDEEIIIbwLjYX58/2ylevVq2ded+7caWYUXHXkKJQtDc2aNTOCWVvTwI4iO7uceXA1g+GKGTNmmJFqGgokJiYGl1xyiensV8RgqAjx8fFFDJ3ExESzvrzMnz/fCLo5q0CtRnJyMu6++24jlP7tt9+MnoEj8n/88Uepj3n22WdjwYIF5u8+ffrg+++/r1Dd2eGn/mHs2LFmpseZk08+Of/vY4891hiKts6B14zH50zGiBEj8vfhLM/XX3/t0mDg/UcolLdp2bIl/AUZDEIIIYTw/mi/n5bJ0ee2bduakWB2+JyhWxE7ja6EuCXB0eirrroKr7/+OpYuXVpqg4GGAQ0ERvSxYWeVnU9GGmJdGXGHhowzu3btKva4HCX/6KOP3G63O9ju3IdoyDizePFidOvWDeWFn6eBZrsgcVSdMynsWHNGhx3/AwcOmGhFzlxwwQXG7YtuWoVxVf/y1p1RnlgWZxZGluLahYZaXv62wJ1RmSjkLi32DBdF1hTf23/7DY4gIDk52fHII484zjrrLEetWrWMAGTSpEml+iz34/6ult27d5erPhI9CxGcSPQsgoFAFD3/+OOPjqioKMf9999vhKdZWVmOBQsWODp06GD6Djk5OQVEzykpKY709PT8JTMz0wiUKU5es2aNEUXzGJ999pkjMjLS8cUXX5SqHmvXrnWEhIQ4Fi5cWOD4XLp06eK44447zH6TJ082wliWyXJeeuklI872luh5y5YtjpiYGMcbb7xhzvWXX34x5X/11VduP5Obm2vqzfZgm61atcq8t9vy999/N20+Y8YMs+/hw4cdo0ePdjRt2tSRl5fnSE1NNYJn54XHoQC9LMLy8tT966+/dsTFxbm9bnv27HF8//335j5gXdmvo8B56NChBUTwFK6zvjxn7tO8eXPH888/77bcvn37Os4991wjsuYyZMgQvxE9B4XBYCv0eaF4McpjMIwdO9bx4YcfFlh445cHGQxCBCcyGEQwEIgGA/nrr78cgwcPdtSsWdMRHR1tIifRAGAn08Y2GAovvXr1cuzYscNELmJ0m9jYWHOc7t27OyZOnFigHG5j9BtXMHqPu0FKLrVr13akpaUZg+S6664zg6ANGjRwPProo16NkmSfO6MNsW1atGjhmDBhQoHtAwYMMHVy3t/VOTj3vz755BPHscce64iPj3fUqVPHHGP58uVu61CeKEnlqXvLli0doaGh5lo5Lx8duW40Qo4//nhTb65v06aN4+677zZGjzPffPONo3Pnzo5q1ao5Wrdu7Xj66aeNcVRcdKxzzjnHHJd1eP/9980507iqbIMhhP+hipOZmWn81Rj7ltNQnNabNGlSqaaYGK+XU4qLFi0ysZU9AQUtnTt3NlNVTOIhhAgOJkyYgJtuuqmyqyGEV6HvOWGEGCFE+WGEJ7pO0d2MOpiyft882d8MirCqUVFRHkmUQUFORcOaCSGEEEIIURh27Kl3YaJAalTuuOMOnHbaaW6NBV8SFAaDJ+AFo+KdIiSq+devX1/ZVRJCCCGEEFWEpKQkEzmKonaKvevWrYuPP/4Y/oCiJJUADQS6LtkGAxNpMGQaw2nRCmQIteKg0t+O8WzDKAdCCCGEEELY9OrVyyQR9EdkMJTAsGHDzGIzZMgQnHXWWTjllFNMQo233nqrxPBojz/+uGeulhBCCCGEED5GBkM56N27N3r27ImffvqpxH2ZpMNOvuI8w0DDQwghhKiKBEE8FSH85rtmZxEPGIMhLS0Ns2fPxsKFC00KbKbF5knQB4vJOTjVwqQozqm1AxW6IjGhS0nUr1/fLEIIIUQwwARWWVlZPuvICBHM5OXlITw8PDBEz//884/x82ckoqFDh5rQgRxF54OCDwz6YzHTIbdxH+7LzwQyDGNlp5MXQgghxH+RCRlRkBo+zTQI4T1SU1ORk5ODyMhIeJsKmyRMz/3VV1+ZHAWPPfYYzjjjDJPSOiwsrMB+fHhw1uHHH3/El19+aeLK0lVn6tSp8Bd2795tFOpt2rRBRESEWUfBcmHDYObMmUb8zBTmQgghhPiPBg0amPxHBw8eNL+p7A9opkEIz0JjnDN5nNHzxQB2hQ0GVpTJ0Lp27VrsfnxgdOnSxSx33nmnSUYxfvx4+ArOcBw6dMgkvyDffvutiXFLxowZgxo1auD+++/HlClTsHnzZrRs2dJsYzQkGjc0iLgPIyO9//77xiXpgQce8Fn9hRBCiECA/YLmzZtj7969xnCgy4QQwrPQCGckz1q1agXGDEN5ZwhoYPhyduH555/H1q1b899//fXXZiEjRowwxoC7GZT//e9/ZmaEGg0mz7j22mvx6KOPmlEUIYQQQhQ1Gvwh2ZQQwjMETZSkLVu2lLjP5MmTzeLMuHHjzCKEEEIIIUQw4hWDgVOQEydONL7+dkedLj4DBw7ENddcg+joaG8UK4QQQgghhPDHKEnOUBdAdyMKgpcvX26EGFz4N9dxm60dEEIIIYQQQgSZwXDTTTcZrcDnn3+OnTt3Yv78+Wbh35999hm2bdtm9hFCCCGEEEIEoUvSnDlzcPvtt+PCCy8sso1hVBll6LXXXvN0sUJUOVIyc5CYmoVasZGoHhU0ciMhhBBC+Bke74XExcUVm9mYidu4jxDCNdm5efjm711YuGE/kjNzEBcVjl5t6+Lcro0REebxSUEhhBBCiGLxeO/jqquuMpGGGIK0MCkpKZg0aRKuvvpqTxcrRJWBxsK0ZTuxaX8qsnLyzCvfc70QQgghRMDPMFDUzLwFHTt2xJVXXom2bdua9evXr8cHH3yA2rVr45hjjsnPgWBz/vnne7oqQgSkGxJnFvjasWGcSczSqEY01uxJNuvP6txQ7klCCCGECGyD4eKLL87/+8knnyyynRGSLrnkEpPS2oadotzcXE9XRYiAg5oFuiHViIkw3wvCV77nem6XnkEIIYQQAW0wzJ0719OHFCJooMCZmoVNyalmZoHGAo3rpPRstK4ba7YLIYQQQgS0wXDqqad6+pBCBA3VjwicE5IzjRsSZxZoLNjrNbsghBBCCF/jtViNdDFasmRJgUzPxx13HMLCwrxVpBBVAkZDInaUJM4s2FGShBBCCCGqhMHAKEn3338/EhIS8rUKdK1gxuennnoKo0aN8kaxQlQJGDr1guOaGoGz8jAIIYQQosoZDG+//TZuuOEGEy3pscceQ/v27c36tWvXmm3XXnstsrKycP3113u6aCGqFHQ/kguSEEIIIaqcwTB+/Hj06dMHP/30EyIiIvLXn3baaSb/Qr9+/fDss8/KYBBCCCGEECIYE7ft2bMHw4YNK2As2HAdw67u3bvX08UKIYQQQgghAsFg6NatG9atW+d2O7fRXUkIIYQQQggRhC5Jr732GgYNGoTWrVtj9OjRiImJMevT09Px1ltv4fPPP8fMmTM9XawQQgghhBAiEAyGkSNHmtCpd9xxB+655x40bmyFgty1axdycnLM+yuvvLLAZxhBafny5Z6uihBCCCGEEMLfDIbatWujTp06aNeuXYH1zMMghBBCCCGECHKDYd68eZ4+pBBCCCGEEKKqiJ6FEEIIIYQQVYcKGwy///57pXxWCCGEEEIIEQAGAxOxMSkbox+lpaWVuH9KSgo++eQTnHLKKejfv39FixdCCCGEEEL4s4aBeRXGjh2Lyy+/3CRm69mzJ7p3745WrVqhVq1acDgcSExMxObNm7F48WL89ddfJlrSFVdcgY8//tgzZyGEEEIIIYTwT4OhWbNmmDhxIp5++ml8+OGHmDFjBt544w2Td8EZ5mPo0aMHxo0bZ4yLevXqVbRoIYQQQgghRKBESapbty5uv/12s3AGYdu2bThw4IDZxjCrzZs3R3i4x4MyCSGEEEIIIbyIV3rwNAyY6ZmLEEIIIYQQInBRWFUhhBBCCCGEW2QwCCGEEEIIIdwig0EIIYQQQgjhFhkMQgghhBBCCLfIYBBCCCGEEEL4zmBg5uc5c+a43T537lyzjxBCCCGEECIIDYZ58+Zh7969brcnJCRg/vz5ni5WCCGEEEIIESguSSEhIW63bdiwAXFxcd4oVgghhBBCCOGPidumTJliFptx48Zh4sSJRfY7dOgQVqxYgYEDB3qiWCGEEEIIIUQgGAxpaWnYt29f/vvk5GSEhoYWmXWIjY3F9ddfj0ceecQTxQohhBBCCCECwWC44YYbzEJatWqFV155Beeee64nDi2EEEIIIYSoShqGzZs3l8lYSExMNFGTli1b5umqCCGEEEIIIQI9D0NWVpaJrETDQQghhBBCCOFfVLrBIIQQQgghhPBfZDAIIYQQQggh3CKDQQghhBBCCOEWGQxCCCGEEEIIt8hgEEIIIYQQQrhFBoMQQgghhBDCfw2GsLAwtGjRAjExMZVdFSGEEEIIIYQ3Mj1XhLp165pkb0IIIYQQQoggMBiYtbkkQkJCMGfOHE8XLYQQQgghhPB3gyEvL88YBM7k5uZi69at2L59O9q2bYsmTZp4ulghhBBCCCFEIBgM8+bNc7vtu+++w+jRo/Hiiy96ulghhBBCCCFEoIueBw8ejBEjRuC2227zZbFCCCGEEEKIQImS1KZNGyxatMjXxQohhBBCCCH83WDIycnB559/biIjCSGEEEIIIYJQwzBq1CiX6w8dOoQ//vgDe/bskYZBCCGEEEKIYDUYfv755yJRkvi+Vq1a6N27N6655hqceeaZni5WCCGEEEIIEQgGw5YtWzx9SCGEEEIIIUSwiJ7379+P119/3dfFCiGEEEIIIfzVYEhLS8Mnn3yCQYMGmaRtt956qy+KFUIIIYQQQvibS5JzxudZs2bh448/xowZM5CamoqaNWuasKpr1671VrFCCCGEEEIIf55hYCSkMWPGoFGjRiZR27fffouhQ4ea17179+KKK67wdJHCi6Rk5mD7wTTzKkQwou+AEEKIYMcjMwycMeBMAt2ONm3ahNjYWGMsDB8+HGeffTaioqLy9y0cQUn4J9m5efjm711YuGE/kjNzEBcVjl5t6+Lcro0REeZz6YsQPkffASGEEMKDBsNRRx1ljIJzzjkHzzzzjNEqxMTEeOLQopKgsTBt2U4zulojJgKbklORkJxptl1wXFNdF1Hl0XdACCGEsPDIUHFkZCQyMzOxdetWbN++HQcOHIA/kZKSgkcffRQDBgxA7dq1zSzH5MmTS/15Jp0bPXo06tWrZ2ZPTjvtNCxduhRVFRoJnFnga8eGcWhcM8a8Oq8Xoiqj74AQQgjhYYOB2oR33nnHzCrcddddaNGiBXr16oXXXnsNu3fvRmXDUK5jx47Fv//+i2OPPbbM4m3OmNDd6uabb8azzz6LhIQE9O3bF+vXr0dVJDE1y7ghcWbBdiHjK99zPbcLUZXRd0AIIYTwsMFQo0YNk8F53rx5JnHbU089ZUb1GT61WbNmpnP91ltvYd++fagMKMCm4cIZkOeee65Mn/3yyy/x22+/mRkJzlLcdNNN5jzDwsLM+6pIrdhIo1lISs+Gw+Ew6/jK91zP7UJUZfQdEEIIIf7D4+pVGgj33nsvli9fbpY77rjDCKFvvPFGNG7cGK+88gp8DfUVDRs2LNdnaTA0aNAA559/fv46uiYNGzbMhIulK1ZVo/oRgTNf1+xJxq5D6ebVeb0QVRl9B4QQQoj/8Gq4my5duhgXnm3btuHnn3/GlVdeiYyMDAQSy5YtQ/fu3REaWrCpTjjhBJOQbt26daiKMBrS0G5N0LpuLCLDQ80r33O9EMGAvgNCCCGEhc+GiumWxOWNN97A//73PwQKdGU65ZRTXLo5kV27dhnDyB3UOxR2xdqwYQP8HYZOZTSkszo3NP7cdNHQzIIIJvQdEEIIISx87lvCiEpM5BYopKenF8gjYRMdHZ2/vThoID3++OMIVGgkyFAQwYy+A0IIIYIdOaOXACM/udIp2K5VJeWboHbjoosuKjLDMGTIkLJfLSFEsaFQNRsmhBBCeB4ZDKWMsFQYex2F3MVRv359swghvIMyMgshhBDeRQZDCXTt2hULFiww+Richc9//vknqlWrhvbt23v5EgkhikMZmYUQQogAjpIUaHDWYM2aNcjOzs5fd+GFF5rEdF9//XWBRHBffPEFzjnnHJf6BiGEb1BGZiGEECLAZxjYAWeUoLZt2yI2NhaVyeuvv45Dhw6ZqEbk22+/xY4dO8zfY8aMMcnn7r//fkyZMgWbN29Gy5Yt8w2GE088EVdddRVWr16NunXrGiFzbm5uQIuZhQiWjMwS7QshhBB+OMPAhGYdO3ZE06ZNTQ4Duu/YI/PdunXD9OnT4Wuef/55PPzww3jzzTfNe84Y8D2XxMREt59jRueZM2di+PDhePXVV3H33Xcbo4F5JTp06ODDMxBCFEYZmYUQQogANBg4cs+syOxUP/roo3A4HPnbuK5JkyaYNGkSfM2WLVtMXVwt9mzC5MmTC7y3qVWrFt59911j8KSmpmLevHno0aOHz89BCFEQZWQWQgghAtBgGDt2rEl09uuvv+Kmm24qsv2kk04y2ZOFEMITKCOzEEIIEWAahpUrV+LFF190u71BgwZG1yCEEJ5AGZmFEEKIADMYGGqUbjvu2LRpE+rUqePpYoUQQY4yMgshhBAB4pJ02mmnmUhDOTk5Rbbt2bMHEydOxJlnnunpYoUQQgghhBCBYDA8+eSTJlzp8ccfj7ffftuEOJw1axYeeughdOnSxYiKKYYWQgghhBBCBKHBwFCjFDzT7YghS2kgPPfcc3jqqaeMwcCsyYWjEAkhhBBCCCGCKHFbp06d8NNPP5n8Bhs2bEBeXh5at26NevXqeaM4IYQQQgghRCCFVWWkJDt/AV2TevbsmW8srFq1yuwjhBBCCCGECEKD4bHHHsOKFSvcbqcx8fjjj3u6WCGEEEIIIUQgGAwlcfDgQURGRvq6WAEgJTMH2w+mmVchhBBCCCF8pmH45ZdfMG/evPz3X3/9tdEuFObQoUP47LPPjPhZ+I7s3Dx88/cuLNywH8mZOYiLCkevtnVNhlwmvRJCCCGEEMKrBsPcuXPz3YwYRpUGAxdXHH300Xjttdc8UawoJTQWpi3baWYWasREYFNyKhKSM822C45rqnYUQgghhBBu8cjw8j333IN9+/YhISHBhFF96623zHvnZf/+/UhLSzMaBoqghW+gkcCZBb52bBiHxjVjzKvzeiGEEEIIIbw6wxATE2MWsnnzZhMRqVq1ap44tKggialZxg2JMwuc/SF85Xuu5/bqUV6JriuEEEIIIaoAHndgb9GihYwFP6JWbKTRLCSlZ5vZH8JXvud6bheBg4TrQgghhPA1XhlaZlhV6hSWLl2KpKQkk7jNGY5wb9y40RtFi0JUPyJwpmZhzZ5kM7NAY8Fer9mFwEDCdSGEEEJUGYOB0ZIGDBhgkrb16NEDy5YtQ79+/ZCRkYHff//dZIE+7rjjPF2sKAZGQyJ2lKTWdWPzoySJwEDCdSGEEEJUGYPhkUceQevWrfHHH38gKysL9evXxwMPPGCMhj///BNnn302xo8f7+liRTEwdCqjIZ3VuaHRLNANSTMLgStc5wxdoxrRZsaI63lddT2FEEIIETAaBrohXX311YiPj0dYWJhZl5uba14ZHem6667Dww8/7OliRSlgp7JZ7WrqXFZB4boQQgghRMAYDOHh4YiLizN/16xZExERESbcqg1nH1avXu3pYoWoski4LoQQQogqZTC0bdsW69evzx8F7dixI6ZNm5a//X//+x8aNmzo6WKFqLI4C9TphrTrULp5lXBdCCGEEAFpMAwcOBBTp05FTo6VEOyOO+4wWZ/btWtnlm+++ca4JQkhSg8F6kO7NTGC9cjwUPPK9xKuCyGEECLgRM/UJ9x66635+oUrr7zS/P3VV1+Z1wcffBAjR470dLFCVGkkXBdCCCFElTAYsrOz8e+//6J27dr54kwyYsQIswghKgbdkBQRSQghhBAB65IUGhpqcizQBUkIIYR7lLVbCCFEUM4w0OWoRYsWyMzM9ORhhRCiyqCs3UIIIRDsoucxY8bgnXfewcGDBz19aCGEqDJZuzftT0VWTp555XuuF0IIIYJC9MwkbVFRUWjTpg0uvPBCtGzZEjExMQX2ob7h9ttv93TRQgjh1+Q5oKzdQgghAg6PGwx33XVX/t/vvfeey31kMAghgpG8PEeJWbslahdCCFHlDYbNmzd7+pDCE6SnA8OGARdfDJx/PlBo1kd4T9jKTiCzNasjKEJDQxAXFY5NyaloVCPaGAsOhwNJ6dkmtwbvEyGEEKLKGwwUPQs/5KuvgO++s5aaNRnrFrjmGuDYYyu7ZlUSCVuFK0JDYLJ2JyRnmmzdnFmgsaCs3UIIIYJK9Cz8lLQ0oG5d6+9Dh4DXXwe6dgWOPx546y0gKamya1ilkLBVuENZu4UQQgQaMhiChdGjgZ07gS+/BAYMoOO0tX7xYuCGG4DGjYGrrgIWLgQcjsqubcC7IS3csN+8dmwYh8Y1Y8yr83oRvNhZu8cO6YxHBh9tXvme64UQQgh/RL9QwURkJHDBBcD33wNbtgCPPQY0b/7fDMTkyUDv3sBRRwHPPw8kJFR2jQMSahZKErYKQTekZrWrSdsihBDC75HBEKzQUHj0UWDTJsuAuPBCICLC2rZ2LXD33UCTJtb6H35gvNzKrnHAQOEqha30TaegldjCVq6XsFUIIYQQgYQMhmAnLMxyUfriC2DHDmtmoUMHa1tOjiWWPvtsoHVr4PHHgW3bKrvGfo+zgJXC1l2H0s2rhK1CCCGECEQ8bjD069cPc+bMcbt97ty5Zh/hh9SvD9x5J/Dvv8CCBcCVV/4XfpWGAl2YWra0DAgaEllyrXGHhK1CCCGEqCp4PKzqvHnzcA3DdbohISEB8+fP93SxwpPQ755aBi6vvAJMnQq8+y6wZIkliKaLEpd69Syj4uqrgY4ddQ1cCFvP6txQeRiEEEIIEdB4xSXJFnq6YsOGDYiLi/NGscIb1KgBXH+9FU1p6VLgppusdWTfPsuFiSLpPn2AKVOA1FRdByckbBVCCCFEoOORGYYpU6aYxWbcuHGYOHFikf0OHTqEFStWYODAgZ4oVviabt2s/A3PPWe5JPEa//KLte3XX63llluASy+1ksJ17/5f+FYhhBBCCBG8MwxpaWnYt2+fWUhycnL+e3vZv38/oqKicP311+NdureIwIW6BmaKpmsZIyrdey/QoIG17fBhKxFcjx6WwTBhApCYWNk1rnIwl8P2g2lVNqdDVT8/X6A2FEII4SlCHHbcRw/RqlUrvPLKKzj33HM9edgqxapVq9C5c2esXLkSnTp1QpUgOxv43/8srQPDtObl/bctOtoKz8pZh1NO0axDRZo5N89kkWYCOOZ0iDsSkYki66qQ+Kuqn9+ECRNwE936vEhVb0MhhBC+7296XPS8efNmTx9SBALM4TBkiLUwPCuTwL33npUgLiMD+Ogja2nXzhJJUyzdsGFl1zrgYEdw2rKdZvSYieA2JaciITnTbKPIOtCp6ufnC9SGQgghPI3XhpvolkSLZsGCBfjll1+KLKIK07Qp8NBDwMaNwOzZwPDhVpZpsn49cN991j5Dh1qzEsz3IEqEnWiOGvO1Y8M4NK4ZY16d1wcyVf38fIHaUAghhDfw+AwDtQpjxozBV199hVwX2YHpAcUoSq62iSpGaChw+unWsn+/NcNAl6VVq6zM0dOnWwszSl91FTBqFH3aKrvWfktiapZxMeHIux2JjK98z/XczqhMgUpVPz9foDYUQgjhDTz+6zt69Gh8++23uOWWW9CnTx/UqlXL00WIQKRuXeC224BbbwX+/NMyHD791ArDunMnQ2tZC40Lah3o2hQVVdm19itqxUYaf3S66TSqEW060zTAk9Kz0bpurNkeyFT18/MFakMhhBABYTD8+OOPuP322/Hss896+tCiKsCR4xNPtJaXXrKMBmodaESQn36yljp1gMsvt4yHqiIMryDVj4hX6dO/Zk+yGXlnZ9peH+ij71X9/HyB2lAIIURAaBiqVauGli1bevqwoirCBH7XXgv88QewYoU1+1C7trXtwAHg5ZeBzp2Bk06yjIqUFAQ7jHQztFsTM+IeGR5qXvme66sCVf38fIHaUAghhN+HVb3jjjvwzz//YDbFriJ4wqp6CkZUoq6BSeF+/rngturVgYsvtoyM448P6vCsFLfSX50uKFVx5L2qnp8vwqpW9TYUQghRBcKqXnjhhZg/fz4GDBhg9AzNmjVDWFhYkf26M6mXEIVhzgYaBVw2bQLefx+YNAnYtcuaYaD2gUuXLlZ4ViaQo/tSkMEOYFXuBFb18/MFakMhhBCewuO/yL17987/29Usg6IkiVLTurUlhH7sMSsZHA0FhmFlhKV//rFE1PfcA5x/vqV1OO00KzJTMWjUVVSEyrh/Kvue9VX5lX2eQggh3OPxp/IkjgYL4UnCw4FzzrGW3bv/SwrHPA9ZWZZwmgsNDM46jBwJNC7o867st6IiVMb9U9n3rK/Kr+zzFEIIUQkGw5XM4CuEt2jUCLj/fuDee4H5861Zh6++AjIzLRemBx8EHn4YGDTIMh4GDjRZqJX9VlSEyrh/Kvue9VX5lX2eQgghSsarwze7d+/G8uXLkcpY+0J4Eroe0QXp448tfcOrr1q6BpKXB3z7rZXLoXlzZN19L9b+ulQZhEXAZE+u7IzNviq/ss9TCCFEJRoMM2bMQMeOHdG0aVMjbv7zSIx9ZoHu1q0bpk2b5o1iRbDCUKxjxgDLlwN//cXsgVZEJbJnDyKffxYP3HYenn7tFnRbMBPhmRlFMggLUZHsyVWhzMoov7LPUwghRCUZDMzyfP7556Nu3bp49NFHjcjZhuuaNGmCyfRBF8LTsMPBcKtvv21pHRhh6eST8zcftXYphr9yPx64tj/Oefcp1Fq/2vhLK4OwKE32ZCaRs59ndgZqb90/lVFmZZRf2ecphBCikgyGsWPH4pRTTsGvv/7qMt74SSedhGXLlnm6WCEKwhmGq64CFi5kIGKsu+xaJFevYTbFpCbj5O8/xcvPXIWHxl6J6pPfAw4fVgsKlzhnmmYG6l2H0s2rNzNQV0aZlVF+ZZ+nEEKISjIYmBxi2LBhbrc3aNAACQkJni5WCPccfTRaTXkLP/24BFNuexarOp+IvCPuD7VXrwCuv94SU9sGhmdzGYoqQGVkT67sjM2+Kr+yz1MIIUTJeHz4plq1asWKnDdt2oQ6QZhoS1QuDM849KQ2SOl+OxJTb0L6vl2I/eRDy21pxw4gLc0K18qlY0crr8MVVwD16unSCXP/MGLPWZ0b+ixXQGWUWRnlV/Z5CiGEqIQZhtNOOw1TpkxBTk7R6BZ79uzBxIkTceaZZ3q6WCFKBTsizWpXQ2yHtsDjjwNbtgAzZ1rJ35jvgaxZA9x1F9CkCcDZsh9/tCIviaDHvn982aGtjDIro/zKPk8hhBA+NBiefPJJ7NixA8cffzzefvttE/Fi1qxZeOihh9ClSxcjaKMYWgi/ICwMOPtsK5cDZxqefRZo397alp0NfPEFcNZZVlK4sWOB7dsru8ZCVAkYMnX7wTSFThVCiGA0GDp06GAEz3Q7evjhh42B8Nxzz+Gpp54yBsOCBQvQsmVLTxcrRMVp0AC4+25rhuGXXyyXpJgYa9vWrQAN3RYtrGRwX39tZZkWQpQ5s/NXS3bgkekrMfa71eaV77leCCGEf+KVud9OnTrhp59+QmJiIjZs2IC8vDy0bt0a9eQPLgIBCqL79LGWV14Bpk61MkovXWoJor//3lrq12dqcyujdIcOlV1rIQICZXYWQojAw6uZnmvVqmVck3r27FnpxkJmZibuvfdeNG7cGDExMaZOs2fPLvFzjz32mHGrKrxER0f7pN6ikqlZE7jhBmDJEmu58UaghhWeFYz29dxzlkj6lFOAKVMs8bQQwiXK7CyEEIGJ19Rlv/zyi4mIxFkG5+RthB3u22+/Hb5k5MiR+PLLL3HbbbehXbt2JnncwIEDMXfuXPTu3bvEz7/55puobmcPNq7vYV6usfA7une3FhoJ1Dxw1oGuS2TBAmu55RbgssusKEvcVwhRpszOEj0LIUQQGAx///03hg8fblyRChsKlWUw/PXXX/j000+NluIuRr8B3dOvQOfOnXHPPffgt99+K/EYF154oclULQSqVQMuv9xa1q61QrMyHCtnHJgA7s03raVrV8twuPRSTrep4UTQY2d23pScikY1os1vgZ3ZmfkXlNlZCCGCxCXpmmuuMYnZ3nrrLWM8bN68ucjCmQdfwpkFzgiMHj06fx1diq6++mr8/vvv2F6KyDf8UTt8+LBbI0gEKdQujB9vRViiEJqC6NAjX6u//wZuvhlo3NgyLubPV1I4EdQos7MQQgQmHp9hWLVqFcaOHYtrr70W/sKyZcvQvn17xMfHF1h/wgknmFcaNs2aNSv2GBRtp6SkIDY2FkOGDMELL7xgslYLYYiIAIYOtRYaoJxxeO89K7pSRgbw0UfW0q6dNetAsbTuHxGE2BmcF27Yb9yQOLPQq21dZXYWQohgMhioD7B9U/2F3bt3o1GjRkXW2+t27dpVrHD75ptvxkknnYSoqCgTFnbChAnGzWnx4sVFjJDCcLZl3759BdbRXUtUYWh8Pvww8OCDwJw5ltZh2jQrr8P69cC991rbzjnHMh6Y50GaGBEkKLOzEEIEHh43GBhV6M4778Qll1yCJsyU6wekp6ebzn5h7EhH3O6OW2+9tcD7Cy64wMxMXHbZZXjjjTdw3333FVs293mcGYVF8EHXpDPOsBYajZxhmDgR+PdfgJnQaURwadoUuOoqYNQoQDlKRBC5J0ngLIQQQWownH/++cjIyDAJ3Pr374+mTZsWiSjEGYhXGN/eRzCMKsOqFob1tLeXhUsvvdQYRcw1UZLBcOONN+Kiiy4qMsNAtyYRRDCsMIX+t90G/P675a706adWGFbqH554Ahg3Djj9dGvW4bzzABdGrhBCCCFEwBsM8+fPxw033IC0tDR8++23LvfxtcFA16OdO3e6dFUizM1QVqh5OHjwYIn71a9f3yxCGOiud/LJ1vLSS8Bnn1kuS3/9ZQmimRuES506VqZpJoXr1EmNdySGP8NuMpKOu5Hp0uwjhBBCiLLh8V/UMWPGGL9+RiZicrSSfPx9QdeuXU2+BUY5cq7Pn3/+mb+9LDBS0pYtW9CtWzeP11UEEbwXGRyAy4oVluFAt6XERODAAcug4HLSSdasw7BhgFMukGAhOzfPZAe2RbIMy2mLZOkPX9p9hBBCCFE+PP5LSnebu+++G2eccYZfGAt2DoXc3Fy88847+evoojRp0iRj1NgRkrZt24Y1a9YU+GxhwbKdxI3rBwwY4IPai6DgmGOAV1+lAh/45BOgX7//ttGFiTMNFOkzNLA9GxEk0BCYtmwnNu1PRVZOnnnle64vyz5CCCGE8JMZhk6dOiEpKQn+BI0C6gjuv/9+E7Wobdu2mDJlipkleI++5EdgMje6VDnnWmjRooVJRNelSxcjkv71119NEjjOSlx33XWVdEaiykIh/iWXWMvGjVZSuEmT6D8HpKRYomkuXbpYsw4jRgC1a6OqQhcjzhrwtWPDOOPOyIRfa/Ykm/VndW5o9itpH7knCSGEEH40w/D888/j7bffNmFH/YkPPvgAt912Gz788EPccsstyM7OxnfffYdTTjml2M8xGhLPhdGf+PlFixaZ7NC//PILqjHjrxDeok0b4MknOfUFfPMNcO65/4Vf/ecfhvCyksIxk/TPPwN5eVXuWlCPQBejGjER+eGa+cr3XM/tpdlHCCGEEH40w8CEZnFxcSZvwdFHH43mzZu7jJI0Y8YM+BLODjz33HNmcce8efOKrJvI0VwhKpPwcCtnAxe6LE2ZYukdmDGd0b+mTrWW1q0t16WRIy1DohhBMAkEcTDrRz3CpuRUM2vAZwdnAJPSs03CL/tcosNDsSMxDXWrRyIyPMzlPkIIIYQoHx7vKaxYscL8qNNQYGbk1atXF9nH3xK7CREw0BC4/34r+dv8+ZZ70tdfW4YDDQgmhHvkEWDgQMtlaeBAZIeE5guCkzKycSg1GwgBalWLQHx0hF+Lg2nMsH4JyZnGxYizBjQE7PVR4da57UrKwN6kTOxJSkD9+GhjQMQdOTd/NoiEEEKIQMDjv6TUBQghfJAU7rTTrIXhfT/+2DIe6KqUmwswpDGXRo2wccAFWNi2LzbVaIj07FzsTEynvYDGtaIRExFuOuPkguOa+uVlozFD7AhInDWwjRxb7JyTm4d68ZFIOJyJfcmZaFUnFkO7Ncn/rBBCCCH8yGDIyspCZKRcAITwGRQ9jxkD3HwzsHix5a7ESEsUSe/ejY6TXseLeB3rO5+AqV3OwPdtT0JmeAQys/PQpXEsNuxL9WtxMGc+aMywfs5uVM6C6KMaxZuZy+ycXKzenWyMIe7vj7MmQgghRKDh8V/TBg0aYPTo0ViwYIGnDy2EKA66+h1/PPD221ZUpffeQ+YJJ+ZvbrfyLzwy9Un88PwluO+HN9F8xwZk5ToCRhxMI6FZ7Wr5Ro0rsXNEeBjqxUUhIzvP789HCCGECFqDgeFLv/rqK/Tt2xctW7bEQw89hH///dfTxQghioMJ3kaNQvYvCzD++S8xo99wpMbVNJtqpCdj2O/T8cGro3HXw5ej5+wvUTc3I+DEwbYgmpoGOxSyLXbm+kA7H+F5OPu0/WCaeRVCCFF+PO5/wORoEyZMMCFLP/74YxM16emnnzZZkS+//HJcfPHFZhZCCOF9OBrftm9PfFGjKT485zp0WzYfp/36LU7etNRsb75xFW7cuAo5019H+IKLLaE0M0sHQGCCkgTR/uheJXyDMn8LIYRn8YqDb0REBIYOHYovv/wSe/fuNUZEjRo1cOedd5qsygMHDsQnn3yC9PR0bxQvhHCCwl8KgJs3qoVN/QbhhTtfww1jv8C3516NxNqW8R6ekW4liOvVC+jcGXjpJWD//oA5NwqhI8NDzavEzkKZv4UQwrOEOJzTGnuRxYsXY/z48cZdyYb5Gqh3YFK02NhYBAurVq1C586dsXLlSpMZWwhf4DIPQ3QYqs//2YqwxKhKOU6uGxERwNCh1qxD//5WZKYAODd/nlng7OtNN91U2dWo0vBeeGT6Smzan5qf+Zs/c5yFokE5dkhnv75HhBDCH/ubXu0BbN68GePGjcNRRx2Fnj17Yv78+bj55ptN5uS///7buCi9+uqruOKKK7xZDSFEIdFw/t/VooCzz7ZyOWzfDowfD7RrZ7VXdjbw+efAmWdaSeGeeMLaJwAE0SJ4UeZvIYTwPB43GA4cOIA33ngDJ598Mtq2bYsnn3zSWDfTp0/Hrl27jIHQo0cPHHPMMXj99dcxduxY/PDDD56uhhCijKTUqovt19yMlBWrrKRwl1/OFOnWxq1brYRwLVsCgwYB06ZZBoXwCBLneg6J4YUQwvN4fDiuUaNGyMnJwUknnWQMh+HDh6NmTSs6iys4RVK/fn1PV0MIUSGBaGucO2kyIl59FZg61XJZWrYMyMsDZs60Fn5vR44Err4aaN9e7V0OJM71PBLDCyFEAMwwPPDAA1i/fj0WLlyI6667rlhjgQwePNi4Lgkh/FAgyu/vDTcAS5cCS5ZYf8fHWx9MSACefRbo0AE49VTgww+BtDRdRk+1vSg3EsMLIYSfGwwUMLdp08bThxVCeAHnbMkUiDauGWNendfn07078MYbVlK4KVOAPn3+2/bLLwC1SI0bAxT1cjZCeK7tRbmyg1Pg/Mjgo80r3yvztxBC+JHoOTc3F1OmTMGwYcOM2JkL//7ggw/MNiFEAAtEq1WzjAMaCWvWAHffDdSrZ21LSrKMChoXxx0HvPkmcOiQj88qMJA41/tIDC+EEH5qMCQlJaFXr14YNWoUfvzxR2RnZ5tl9uzZuOqqq9C7d28cPnzY08UKISpDIEp3JLol7dgBMGQyIy7ZSd/oxnTjjdasg21g+CaKs09ExRU9pq/Fuc719YXIWkJuIYSoOnhc9Pzggw9iyZIleO2113DttdeaJG6ERsO7776LW265xezD7UKIKiIQjYwEzj/fWhh6lUng3n/fiq7EBI3UN3ChOJp5HWhA+CDjuzdExZ46pq/Euc71TcrIxqHUbCAEqFUtAvHRERVuD1+0uRBCiCpmMEybNg033nijWZyh4XDDDTfg33//NRmgZTAI4R+wI0fsDh6TW9kdvHLRrJkVgvWhh4A5c6wIS9OnW2FY160D7rmH0RGAc8+1jAfmeQgLgzdFxRztZod8U3Kq6aAT+rRX9jE93vYl1Dc9Oxc7E9NpL6BxrWjERIRXuD180eZCCCGqmMHAPAwd6Kbgho4dO+LgwYOeLlYIUUGB6FmdG3o2WzIzQ59xhrXs22fNMLz7LvDvv1ZGaSaL49K0KTBqFHDVVVaeBy+JiqnNaFQj2ozmcz3Pt6zn6eljeq3tXdS3Tb1YLNmaiKjwUOP6lJmdhy6NY7FhX2q528MXbS6EEKLy8fj8MJO1ffPNN263c5uiKAkRZAJRiqLvuIN56oGFCy3jgOJpQv3D2LFWNumzzgK++ALItEak/U1U7C2hsrfa3rm+WbkOZOc6jJESFRFm/ua6itbdF+0jhBCiihkMdEWi2HngwIHmdcuWLWaZNWsWBg0aZMTPN998s6eLFUIEAuxEnnyypW9geNa33wZ69LC2Ufj744/AsGHWrMOdd1qzEeXEG6LiQMsi7FzfyLAQRISFGI1BZnau+ZvrylL3koTMgdY+JSHhthBCWIR7w2BISEjAM888Y4yEwjqGRx55xGgZhBBBDhPAjR5tLcuXA++9Z7ktMQzr/v3Aiy9aCw0Mah1oSMTGVqqoONCyCDvXd+O+VDOzsD8ly2gYoiJCjTtSaepeWiFzoLWPOyTcFkKIgnjl6c3kbZxF+Omnn7CVUVIAtGjRAqeffjrq1q3rjSKFEIHMsccCr74KjB/PyAmW1mHuXGvbb79Zy623ApdcYhkPnJWww7f6WFTsC6GyJ3GuL6MkVY8MdxklyVNC5kBrH1dIuC2EEAUJcdjzxsJnrFq1Cp07d8bKlSvRqVMntbwQrtiwwXJdYojWPXuKGhg0HC67DKhVq8T2Y0fX06Li8hxzwoQJuImZsCsB5/qS0tadn3tk+kps2p+aL2TmzwZnEGgMMIuyq2N4o819QXnPVwghqnJ/s8JPvW3btpXrc82bN69o0UKIqkzbtsBTTwGPPw58/70VnnXmTCAvz3JhGjMGuOsu4MILgauvBk491YrM5AJ28DzdyfPGMb1J4fqWtu6lETK7OlagtU9Fz1cIIaoyFX7qtWzZMv+hWhZyc3MrWrQQIhhg8kfmbOCyc+d/SeE2b7aiKX38sbW0aWMZDiNHAo0aVXatqwy2kJluSAyRao+4U5vAEfdAEzKXRLCdrxBC+MRgeP/998tlMAghRJlp0sRKCMfEb9Q4UOvAXA5ZWcDGjdb6hx8GBg+2XJYGDADCNRpcEQJJyOwJN6jynm+gumAJIURpqPBTbSRH84QQwpfQ9ah/f2s5cMCaYaDL0sqVnL4EZsywlsaNrZwPTAzHPA+iXPi7kNnTUY3Kcr6KqCSECAa8OgzCadx9zPBq8jbV00yEEMLz1KkD3HKLpWn46y9r1mHqVCA1Fdi1C3jySWuhccFZhyFDgOhoXYky4O2M1P4W1ags56uISkKIYMDjidvI6tWrceGFFyI+Ph6NGjUyC//mOiq1hRDC49A1smdPa6aBSeFoOJx44n/b58yxwrJy1oEhWv/5RxfBn7KBlxMaCZwJ4CujGjWuGWNendd763y9WbYQQvgTHn/qL1iwAGeffTby8vJw3nnnoX379mb92rVr8c033+D777/HDz/8gD59+ni6aCGEsIiLswTQXDhIwaRwH3wAHDwIJCZaOR+4nHCCNetw8cXWZ0TAUZlRjRRRSQgRLHj8KXr77bejfv36mD9/Ppo1a1Zg2/bt23HKKafgjjvuwKJFizxdtBBCFKVzZ+Cll4BnngGmT7dmHn76ydpGFyYut98ODB9uGQ+clajigRwCSaBbUl29GdWIZe9MTKd/LZq4mGlQRCUhRLAQ7o0kEU888UQRY4Fw3Q033GAyQQshhE+JirKMAi4MycpZB4Zopc6BegeGauXC5Dacmbj8cqCKZaYPJIFuaevqjShOLJuaiM8WbceuQ+lgdtMmNWIw/PhmGNq9SX75gRRBSgghKoLHfyFatGiBTMZGd0NWVpZLY0IIIXxGq1bAuHHA1q3Ad99ZQuiwMGvbqlXAHXdYIVzpqsTZCCaLqwLYAl1mMc7KyTOvfM/1gVxXGhFDuzUxMwqR4aHmle/LG8WJZbz7yyas25OMlIwcpGbmYO3eZExcsKlI+Z4uWwgh/BGPD3888sgjxi1p0KBB6Nq1a4Fty5Ytw2uvvYaXX37Z08UKIUTZYY6GQYOsZc8eYMoUy2VpwwYrt8Nnn1lLy5b/JYVrWvaoO/5AYYEuXXfowsORca5nRCB/GREva109GcWJZc5bl4B9KZmICAsxx3I4YGYO9qdkYt7ahALl+3sEKSGE8AQef6r98ccfaNCgAY477jicfPLJaNu2rVm/fv16/P777+jcubN55WLDH4NXXnnF01URQojS07AhcO+9wD33AL/8YhkOX34JZGQAW7ZYCeEefRQ4+2xL60Ajg1moA4RAEuiWt65cV9Fz4LETU7MRGhJiZgyAECNpoWFAV6XEtGyX5XuibCGE8Fc8/nR7/fXX8/9euHChWZz5559/zOKMDAYhhN+Id9k7PPVUa2EkpU8+sUK1Ll9uuSb973/W0qCBNePAmYd27fy+jdj59ZY42NOURkzsLeE2j1crNgJ5Dgcys3NRLTLMzDDQWOC6WtUi/KqtglkQL4TwHR5/GjCcqhBCVAnxbq1awE03ATfeCCxdahkOTAp3+DCwdy8wfry10LjgrMMFFwAxMfDXNooKDzUdYH8X6BYnJj6xdR3MWrnHa9eeZfRtXx9rdydjd1IGEg5ncpLBGA00Xvp2qO9XbRWMgnghhO+pek89IUSVx+fZdTnrcNxx1vLCC5arEl2Wfv3V2j5/vrXcfDMwYoRlPBTScPlDG8VGhqFF7WrIzMkznUKO1tudQn/DrpPdgbXrmutweP3as2yW4ypKkj+2lSdQxmohRKUZDJxtSEpKMlPJhaldu7Y3ixZCVFEqXbwbGwtceaW1rFljhWelWHrfPiApCZgwwVpoXNBwYHbpGjXgL21EY+HeszuayEP+7HbiSkxMHpm+0uvXnmUP69EMA7s0KjYPQ1Wh0r9TQgi/x+PzjNnZ2Rg3bhxat26NqKgo1K1bF/Xq1SuyCCGEtwSxPqNjR+C554AdO6xZhwED/kv6tmQJcMMNQKNGltbBno3wgzaisdAsQDrArKNdV19fe5bZoWEcOjSKD4i2qhLfKSGEX+LxJ+B1112HKVOm4MQTT8SQIUNQw8cja0KIqo1fZteNjLT0C1y2bbMSwjEJHP9OT7dmILgwo/TzzwNXXAHUr19l2shZKEsKi2bLKqR1t79fXvsqgNpVCOFzg+GLL77A5ZdfjsmTJ3v60EII4f/ZdZs3t8KvPvQQMHu25bI0YwanX63cDnffDdx/P3DeeZbL0hln/Jc0LsDayFkom5SRjUOp2UYgzEhC8dEROLFNHVAA8MemA6US0pYkvPX7ax+gqF2FECXh8adrtWrVzOyCEEL4WhDrV4JUGgF0UeKSkAB8+CGwc6e1LScH+Oora2Hm+1GjgKuuAlq0CKg2chbKpmfnGn9/OrQ0rhWNmIhwrNyZZATDsVHhpRIol0Z4GxDXPgBRuwohiiPE4UqRXAFuu+02bNiwAd99950nD1ulWLVqlUlgt3LlSnTq1KmyqyNEwBJoMeMnTJiAmxg9ieFZP//ccleyoe/4mWdasw7nnmu5OflxG/G4FCBv2p+KNvVisWRrIpIzcoyLUHxMBI5tWgO/rN9v9u3XsT4iw5nPwGFmBtjJHzukc4H6OB/PFt6WtH8gXftAQe0qRNVhlQf7mx5/yj777LMYNWoUBg8ebF6bNWuGMBfT7d27d/d00UKIICMgs+v26mUtzG7/6aeW8UCBNMduZs2yFgaGoM6BSeGOOsov28hZKJuV60B2rsO4DdHu4d+pWbkmWzLh9sjw4rM1lzW7c0Be+wBA7SqEcIXHn7aZmZkmnOr3339vlsJwxIg/Arm5uZ4uWgghAgcGhLjuOmtZtszSOnz0kRWalSFame/hhReQe9LJCBt9LXDRRVZIVx+OBBdXhrNQtm71SESEhSAjOzd/hoE5H5gZmXZQemY2cnLzTNI4Ho+CZWaedne8kgTN7urlj6Pj/lgnIYQoKx5/enFWYdq0abj44ovRs2dPRUkSQoiS6NYNeP11E6I154svkPjKm6i39A+zKez334Dff4PjllsQcumlyLlqFGaENcLCjaUTEnsr66+zUHbjvlRERYRhf0qW0TBERYRiy4E0RIaFGDH0vHX7EcqPOWCyTefk5WH892vKLGh2V6+zuzTE9/94L/uzt9pQCCGC1mCYNWsWxowZg5deesnThxZCiKpNTAxmdOqHaTd0QNz2zRi06Hv0+vU71Eo+iJDkZODttxH+9tvo0bQdDpw0GMv6DMSm0BiPZzoubdZfZ6EsDYPqxu/IipKUmJZNpyI4HDQhHMjJtWYb8hx5yMlzGK1CWQXN7uq1eMtBbE9M913m71KgzMlCiKqExw2G+Ph4tG3b1tOHFUKIKo9zxt2mxxyNhcd2wm9X3oK4OT/i3MXf4+jlCxGSl4cWO9Zj9BcvIXv6BKw88XR81W0AFlbv7ZGMvGXJ+usuGzOjJb08ey027Us54hMfhn0pWcZlibqGjOw8dGkSa2YmnI/p6njOuRxc1Wv1rsP49WAqasZEolPjeL/IUqzMyUKIqobH50WvvfZaTJ06VRoFIYQoI66Ev46ISKw5sT9evu1F/P3rcky74AYk1LVG3COys9BtwUyMe/UW3Hvbech58ilg926fZ/11zsbMhVqF5EzLOLDcb6zjhB8RRTPTNIXQ7o7pfLyS6hUTGYaMrFxTpr9kKVbmZCFEVcPjwy5HH300ZsyYYaIgXXnllW6jJJ1//vmeLloIEeAEu0C0JOFv405t8eFFo/HBqZdg4P41OGHO1+j05xyE52Sjwd7twBOPwvHUWOQOHIRwCqWZAyI83OdZf7kP3ZIoeqYvf0xEKEJDgNzcPISFhhrBs9E3FHPMwveCu3qlZ+UiOjIMaVmW4Nofsj8rc7LwJMH+XBT+gcfvvOHDh+f/fdddd7ncR1GShBDOSCBqUZLwt0F8dP72/9U/Gr+OOhZ554zBGctm48zfvkXD7RsRkpuL8G+/Ab79Bo4mTRDChHBMDNeqlc+y/nKfvh3qm8/vTsrA/tQso2HgTAMNB84K0B3J1TGLuxdc1YsRmeiKRA2Dv2R/VuZk4Qn0XBT+hMefpHPnzvX0IYUQVRwJRP+jJOFv4e1xLRvj37ZX4Yd+w9Bk/T8Y9OdM9PzzR8RkpSOEmaXHjbOW00+3ksINGQJERXk96y/3zc1z4LNF27EzKR2IBKIjQlGbsw+xkagRHeHymMXdC+7qVThKkj9kf1bmZFFR9FwUVTrTsygZZXoWAuXO8BvImEzPN93kETcEezvdexii1Ln9ItJSUP/7GTjnr5loseGfgh+sUwe4/HIrKVznzhWqQ2nPY+fBNJPJukmtGLPO3TFLey8oD4Oo6gTTc1EEaaZn5wRuS5cuRUJCAnr16oW6det6qyghRABT1gy/wUJJGXft7dsPphVpv+xq1bGo//lYftaFeKJ1Hhp++Qnw4YfAwYPAgQPAyy9by4knWrMOdCWtXr3MdSjteXRoFF9kXUXuBXf18scsxf5YJ+H/6Lko/A2vZI959dVX0ahRI/Tu3duIm1esWGHW79+/3xgO77//vjeKFUIEILZAlH7n9oSnLVrl+soQrVb2yCKNAL66eu+u/djBSMmwMio7t1/IMcdg+yNPIWXTVmDqVKBfv/8+/McflsHQqJH1yvdennQu7nwqei+U1Fbe+qwQnkbPReFveHzYY9KkSbjttttMpuczzzzTZH62obHQr18/fPrppwXWCyGCFwlEXQscYyPDEBMRhvTsXKRm5brNFMzMyVz2HM7AlgOpiI4IM1qBJjVjzHq6K+WLh9v1xrk/DkPE1i0AB24mTQJ27QJSUoD33rMWuinRXYluS3Rf8hBlzR5dFgFzRcShEpYKf0TPRVHlDYYXXngB5513Hj755BMc4NR3IY477jgzAyGEEDYSiBYVOK7dk4zDJgpQOFrVre42ezE/t/VgmjEUCJOjOfjPAWw7mGaMjaLZj1tbQujHHgN++AF4913gu+8Y9xRYuRK4/Xbg3nuBoUOtmQfOSoSG+jx7dGkFzBURh0pYKvwVPRdFlTYYNmzYgFtuucXt9tq1a7s0JIQQwUtxGX6DgcKZgXPyHNh6IBVZuXkm5Vn9uCiX2YvtzzEHwclt6pjP0WDYtC/VRCaqFROJo4vLfswcDYMHWwsTvn3wgWU8bNgAZGUBn31mLS1bWrMOI0cCTZv6PHt0cfdCRbIqKyOz8GeC/bkoqriGoWbNmkar4I7Vq1ejYcOGni5WCFEFcJXhNxgFjpk5ecjOdRiXopw8mPeushcX/hw7GHHREYiLDjfZj2PKkv2YOgbOKqxbx/jYwGWX/Rd+dcsW4OGHgRYtLONixgwgO7vc51ea+pT2XqhIVmVlZBaBQLA+F0UVNxgGDhyId955B4cOHXIZ3mnixIk499xzPV2sEEJUGYEjDYWIMMtwCA+1dAquxL/uhJFpR7IfMwtymcXD7HT37Qt89JE160AX0mOOsbbl5QH/+5+Vy6F5c+C++4D168t8fmWqjxePLWGpEEJUksEwbtw45ObmmrivDz30kBnpmTJlCkaMGIEePXqgfv36eOSRRzxdrBBCBCzOol660uxLzkSeA4gMCwW7wLYIuLD4t/Dndh36L9tx7zZ1TRZkvt9+MBXLth1CCBw4rkWt/M+XGBmoVi1gzBjg77+BRYuA664D4uKsbXv2AOPHA+3bI/eUUy0DIz3d7Tke1SjeiLHteq7adRjhoSHF1qc0kYvctUFxQmn7uKmZOaZeMU71KumzpUVRl9Q+QlQlPD6/1bhxYyxZsgQPPPAAPvvsMzPS8+GHHyIuLg6XXHIJnnnmGeVkEEKIEgSO3ZvXLBAlyZ34t7jsx9+t2I1P/9qGf3YeRmZOLqLCw/DV0h1GvxwWEoo/Nh0oXVQhzjr06IHsbt3xvxF3IO3jqTh21lfotNlKChe24BdgwS9wjBmDELoyUSjdtWuBCESHM7KNm1VoCLAvOcOUGx8dgUVbDiKC0ygO5NentBGiSmqDwm1l12fB+n1Yn5Bi6sRjUzAeFkqXrpAKZ4lW1CW1jxBVEa84xHEW4d133zXLvn37kJeXh3r16iG0glE2hBAi2ASOJWVbLk4YGRYSYlxz2InlaH5engPr96bglZ/WG61DbFR4maIKmYhCaxKxrdUpODzyJDTdvQXDlv+Ic1f8hJqpSQihK+qECdbSowf+OeMC/NDoBOwLjTLl5OY5kJyRbV4pyGZdtxxIw+pdm8xMil2f0kaIKk0bFKn/sp3YdjAVyek5yMzNQ3KGZbg0rhmNnq3q4JKezSs0s6CoS2ofIaoiXu/B01Bo0KBBpRsLzDx97733mhmQmJgY9OzZE7Nnzy7VZ3fu3Ilhw4YZQXd8fLwJG7tp0yav11kIEXwUFjiWVvBYeD8aGvPWJuBgapYZra8fF4368VHGcOA6uj21qReLxjVjTHQh54hBrrC30wDhLAGNkbQ27fDK2dfhggc+wzNXjcWaY0+G44jwGIsXo/vT9+O1uwbhoa+exUl71qBt3WqmbB6jXYPqpuy29WKxLyUT+1Os+tSLizLHd44QVZr6ldRW9udpiPC4oaEhaBgfZc6D5aVm5uLf3YfLcqlKjNhU2rYNFtQ+QgQuXplhSExMxNSpU02nmn/bQjQb6hreY4IgHzJy5Eh8+eWXJqlcu3btMHnyZCPQnjt3rslI7Y6UlBScdtppSEpKMm5WEREReOmll3Dqqafi77//Rh0PJjYSQghPwZH2xDR27q3oSXYEIbr/ODhYbzrlDkSGF40q5KrDbUcUqhYZZjr91jFDERkeioyQMCzreTo29j0bjx9bHY2nfYqcd99D+M4diM7KQI+535hlT+OWaNLlTHzX9XRk5dYzZbMOrCPh3/RNKhwhyp55KK5+pWkPfp6Row6kwtSb9ed5sDyeV0WOX9qITcEc6UbtI0Tg4vEn16xZs3DhhRciNTXVjMbXomiuEPaD1Ff89ddfJrv0c889h7vuususu+KKK4ww+5577sFvv/3m9rNvvPEG1q9fb45x/PHHm3Vnn322+SyT1D311FM+Ow8hgpGSXHKC4fzK0wbct1a1COQ52AHPMwM3fPRmmxCtpl+OyLCQAlGF6L/vLqqQHVFoT1KG8fVnvofcvFyjM+B61rFmTATCWrVEyv0PYec1t2LO6x/j2B++xIkrf0VYbi4a7tqC23e9g5t/eh+re/TFn/3Px9/tuyM3zwoby/rwlTIFHrd6VFiBCFGu6ldS29jbaSBQdL39oDVDkpGdh5gIhq/NQ2R4GA6lZZvZDOfjl6Xdua+JThUeamZvmAuC51KatvUWpa2/r75j9j1EFzN/aB8hROnx+JPhzjvvNHkWvv76a3Tp0gX+AGcWwsLCMHr06Px10dHRuPrqq82swfbt29GsWTO3n6WhYBsLpGPHjujfvz8+//xzGQxCeImqLh4tzflVpA3Y8evbob6J+rM7KcO4/RihABNosuMWHYGN+1LN6Dc7bCVFBrK3U0twKC3LdOgPHXHvScu0/qZxcuPHS0058dXCsbl2J7w5pB3qnHEI5/8zB+ct/QEt9m1HRG4Ojv3zJ7PsqlEf07qeiVnHn431e2OQmevA/pQs5OQ6cCA1Gyt2JplOOOvrXL+S2qaw4JqzLQeSM83fGTmWAZWalWNmN3gu0eG5qB4djlkr9xjB+Pf/7ClVuxeuB2dfGH2J7k01q0WWqm09TWnvG19/x5zvITuaV2W0jxDCTzI9cyTfX4wFsmzZMrRv397MeDhzwgknmFe6FrkyGCjWXrFiBUaNGlVkGz/7448/Ijk52USAEkJ4lqouHi3N+VW0Ddjxo8D4s0XbTeZndu7pV3/hcU0KREkqbWQge/vHf2w1HWNOUHCUmGVw5uJgSiZ2ZKUbu4Sd7+R0S+B8MLYm3j3xAnzY+0KMcuzC8XOmofNvsxCdnYnGSQm4af5HuOGXj7Go3fH4ottZONi+J+KrRxl3JI7Wt6oTi6HdmhSoX0lt47w9PTsHuxIzjEETFxNh6pdFf6cjcPahXnwkcnLzzGcWbzmI7YnppWr3wvXgMdjO4aGWu1ZFoy6Vh9LeN5XxHSttRCshRBU3GKgPYCfan9i9ezcaMYtpIex1u3btcvm5gwcPGrF0SZ/t0KGD27ITEhJMpKjCRpUQovTiSHZK6cLAUUmuZzScQB6NLM35kYq2AUeJhx3fDAOPaYSdB9NMeNQmtWLyP8f1ZXFF4fFY7rx1CWaUvmWdGCzfkXQkQRyQkpWLyFBqA2CMBboT4Yjx0KlRPHYcysDqOsdgddtjsG/gDRiy5hf0mj8DzTatRqjDgZ7r/jJLSnwtLO17Ln7vex7mh9ZF41rRplx71Luk9uvdrm7+doqqF29NNG5U1CxwtuKElrXMvimMkBQTgc6N4xERHmZmHVbvOoxfD6aiZkwkOjWOL7bdi6sH63xz37Zo4uMMvaX97lTWd6y0Ea2EEP5FiKOwIrmCzJgxAzfddBN+/fVXtGzZEv5AmzZtTKd+5syZBdZTlM1tFDFTDF0Yuio1b94c48ePN1oHZ95//33j0sTZi65du7ot+7HHHsPjjz/uctuDDz7o0hgRItihOwpdaPh4CndyjTCjtyEhqFc9CuFH/O8DCQaBoK6rNOdH/LENnOvOSEPUMnDInj8kHMG3Bcz23+ZdCEyuA4Z1tX9wzCj8kfMKz8pEZMphVEtPMYaDM1mRUUirFofq9WojPDysSB1ctU3NahFGk1C4jnCqS26uw0RiYnI8kwfiCJwpcbXeVbv7431a2jr5Y92FEJ4fMH/yySexcuVKdOrUqULH8rhZP2fOHBNK9aijjsIZZ5xhXH2oH3CGD6NXXnkFvoJhVDlTUJiMjIz87e4+R8rzWZsbb7wRF110UZEZhiFDhphEdhW9gEJUJt4SS/K4j0xfiU37U/NHP9mx4egnXRiuHtI5IEclJ0yYYAZUSnN+xNU+HAHnSPCYIZ3RID66VOU6C38PpWblzzSQsl4/57ozDOriLYnGD91EN3I4EBlizTAwx4E9w8BR/B4tamHDvlQ0Y7khwPaD6fnnlZqTi5W7DiMrORWD1v+G85Z8j7arlxQoNzcuDnkXX4KI60YjpfOxuP+rFdiwLwVHN4o3omXn9htzdkeM/36NqSNnGP7cfNDoLsJCQ40wm9ml1+1NsaIWRYcXmWFITM8qMMNgH7tZ7Rhc7jRrwLYorh4l3afe+P6U9rvjvB/byETMCgsx1yiQv2NCiP9YtWqVMRg8gcefBq+//nr+3999953LfXxtMHAUn7kUXFlehLkZXFG7dm1ERUXl71eWzzonseMiRFXC22LJqi6OLO35Oe8TFx2OrQdSTXSfXIfDdIhLanPnzMbr9iZjz+EMoymIDg8z4UUpfubCxGVlEVNz372HM0yWZoqJ07JywLmE2KgwZOdRGxBitAJ0+eEYdVREqOmI2kJsQt95CoMzcnKRcDjT/C7ERUXj8w6n4sM2vdHy4C4MXjQT562Yg3qpiQhLTkbYxHeAie8gu30nHNPtLKxo1Qs/J2Wgfnx0AWE0DSm+7k5Kx9y1+0zb8rwBuk45TFuwHTmCzvadsybB5Khgu9C4oaFADYN9bYzIOyvX6CCen73O3O8ntq5jDJ9dSRnYm5SJPUkJRerh7j715ventPcWX09sUwcrdyaZ8+dsEGeFOLPA9YH+HRNCeBaPPxEoFPY36DLEfAuHDx8uIHz+888/87e7gsnmKN5evHhxkW38bOvWrSV4FkGJL8SSVV0cWZrzc96HnVxG84mJCDedfI4Ml9TmzpmN9ydnmc45O+aMapSX4jAhUlvUrWaOWVYxNYXB6xKSGZMV1SLDTYecnc5a1SNRJzbKREk6nJZjOtUM7+pslNh88tc27EtMN38zYVtaZrbJvMzPbKjZCE+dOhLP9hqBM7YsNhmle29YjDBHHmqtW4Vr163CFRGvY/ZRfTD9uLOReNyJBYTRfP1i8XYTFcm4R4XSTcoagWfUqNrVaCiFIyoiDAmHM7AvOQut6lri6sJRkuiy40AucvLyjFia9/s/O5OMMUTDi4JpGj3uBNq+/v6U+rtzxJWs0KqiK4UQQU9QDCEwL8Tzzz+Pd955Jz8PA92MJk2aZDI+2xGStm3bhrS0NBM21fmz9913nzEaevToYdatXbsWP//8c/6xhAgmfCWWrOriyNKcn70PRbx0H2FbF3aTcdfmzpmNuW9OnsMcj4M6DtPVDTEzFelZeejSONbMAJT2+jF6EZeG8TFoUaea0QQYd57dh9G2XnU8NPho07G24+q7Oj8jnl6bYGYn6M5DY+OvzQeMsUCDiL70PEZuRATmHdULq3v2Q+SuXRiwZBaGrfgRTQ7tRVR2FgavmGOWhO+bo8bN1yOiyVVAw4YmihMjQ4UfyegcHso65mH34QwTTpWzEEc3rmHaMisn19S9cQ1LXE0DyL42OxPT8frP641BZN/vdatH4uc1CeY8+nesb9yZss0xkosItCvj+1Oae4vlM0oWk+Id07RGvksSQ+1yPQXxVen7JoSoGEHxNKBRQB3B/fffb6IWtW3bFlOmTMGWLVsKZJxmMrf58+cXyExNDcLEiRMxaNAgYyAw0/OLL76IBg0amJwTQgQbvs7WymNV5Y5Lac6PHWfO3bIjXdo2d85svPewlbSNCcs41E6XmLDQENNJ57HZWSzL9bOPbedzsKkfF22iJ/GYzWpXK3COro7BffkZ+v4zdwEjnZoMz7kOs5gkbkcGvHPzgMQ6DfBGr4vxwWmX4uqsLejzywx0+nMOwnOyUX/PNuChB4BHHwbOOQeHBg9DdnotY8xEhtvlMxFcmBFBW1GTrLZk+Xbdnc+fr8wAzfXO93vh7NQR4cygHWZmSejqVFwb+vL7U9y95VwPnj+zbhNlpRZCuMLjmVnoxkORc0mLr/nggw9MJKQPP/wQt9xyC7Kzs43G4pRTTin2c8yxMG/ePLPfuHHj8PDDD+PYY481hgXF3UIEG3a2VvpF28a1na2V65WtFUVGcrcfTDOvnmpzdviTM7LNKLq7Nrc/Q9/7yHDOSFguOZxhMP7qeVYkIwqhObLs6vq5q3tJ9wCPWdI5Fz4GDQVqpDlzwfpGR1oZnjkLwm41B+ztLNV5ISFYdVQPTLr5KTz0+vd4d+gY7Gna2jpwbi4wfTo6XHMpvnnxcoyePRn1D1ihs3Nzc5GRbekq6PrEmYWS7l+eC38o2db2ubK92Ham/Qplyy7pO+Av3x9/qUegfSc98X0WIhDx+LDdI488kj9qYsOHNEfzp/Mh3qEDBg8eDF/DzM5MKMfFHTQMXNG0aVN88cUXXqydEIFDVRckewpXwtb6GTlmfVmFrXbbUrT828YDZoScC8XEjPBjRyNym5k5Pcu45tgaBu7NAKdM3hYT+Z8g2b5+JYly3d0DHI1nXSjILknM6+oY7LYynCmOCKhDQ7KQm5dn3IGowWCd7fCs89btMwYQZ02qdz8HGy+9Gk80TEH45EnAp58Cqamof3g/bvh1Kq779VP83qorPulyJna1OxFZ4RHYeiDNaBma1opBTERYsZmkdxxKR0JyhjlHumDR2KhbPcoYHmy7snwH/OX74y/18CUVEZtX9czzQpSEx58IzDvgDkYWOvHEE03WZSFE4FLVBcmewJWwNToj26wvj7DVFhpvSEgxxgI7ztERodh2MM3tMe3rwShJ6/cmG//9kqIklVaU6+oeoLHA+qRm5ZZKzFv4GN2b1zKdd4q7WXZsZDgOpvwn1ubx6Up1MDXTzERQl8H3uQ5ga2I6ZrRqgQvefRd46SVjNOROnIiwRYtAyXKvzcvMcjAmHtM6n4bPu5yJ9fVbGI1Cx4bxxWaSrhMbaWZ02O6caejQIC4/StIfG8uWLdufvj/+Ug9fURGxeVXPPC+EzxO3lcTTTz9t3IJWr16NYI6L27lzZ48k0hCiKuZhCHTcxcLHvz8iq93pGFuOGPf2MWkw2EJjdpbt+PrFHbMseRhKiuNfuBznY9u5D0rzOVf1s+vh/J4wS3Vadi7e/3WzmRlISs8yo/ychUjNzDWhUDlD0K5+9SLlpC1eit/vH48ev85EjYyUAuUubdLRRFg6fM5QjLv8pBLbwM6BMdYpB0ZFvgP+8v3xl3p4k7Le1576rBBVpb/p8zs8NjYWmzdv9nWxQggvUNUFyeXFnbCV7jPlFbbaxzSdOiehcWlEqs7XqXCyN3di6dKKcu1j06+7vGLewvdR4fcdGsWb41N8zJmRA6nM7WCJmZnEOTuXoV3DXJZzoHVHTBp+B+7veTl6r1qAi/6ehZO2LDfbuu9cY5b0WW8jd8Fw4KbrgeOPd9sGbHuKzynqdlfXQPz++Es9vElFxOa+DvQghD/iU8c7WjivvvqqXJKEEFUad4JSus6UV1BaWqExE6pVRNCZlpljXJ1clcP13G4f21kA6k6YzdwE/KFh/Zz3L6141N6Pn7dF3JRssNPOMKmWJiQEaVm5+W1buF7MA5EVEYHvju6LkZc9jbNvfg9vnjwce6vXNmXEZKah+geTGFIPOPZY1J/0FhpkpQScILikNvWWYNfXQuDylFcRkXcwC8SFsPG4SdyqVasiomdy6NAhJCUloVq1akb8LIQQVRV3gtKjQ6zszeUZjXR3zNgjQuOnZ/6L9QkpJlFZ/BH3nD7t6pVL0EndAA0DZmKuWS2ySKZjlmlrDahXsAWg9Ou3hdnpWTnmWOxfUXR9w0dLTDboGtXY8coxsVJrxkaghpss065EpjzP6tHh5ngUPu85nGkMCYqf2R7MUDxr5X8J1+x69Wlfz7QZ9RVMvra2egM8f8rleP3UEbhg7z+4fsNcNF74sxVh6Z9/EHXXnXg8IhJ/dT0V3584CNuO6YlDmbl+KwguSZDrLcGur4XAFSmvIiLvYBSIC1EYj9/lp556ahGDwUzl1qqFNm3a4OKLL0bt2taojhBCVFVcCUrjMyIqJCh1JzTeejANOxLTjbHAkfeU9Bwzur8/Jatcgk52qjmOygzH7JAXznS8dk+ySQgXHxOOVnWr5wtAWb8WtasZnQXrR4E1fw3osnEgJcuKsBQdhtSMXHN86igORGS5FI+6EpnSUOHx68dFmTKSChlHLG/a30WFqece2xjX9mmNT//aho37U004VeYeaFMvFp3PH4F63e4F9u4BpkwBmJtn40aEZWfhpEWzzZJQrwkW9RsKjLwSZ/qhILgkQa63BLu+FgJXtLyKiLyDTSAuhNcNhsmTJ3v6kEIIEXC4yrY75d2FFRp5LXxMW2hMATD1EWEhVlZjjuCzo85OfUnZg4vLPMzMx6N6tzJiYzvTMSMTbT2QiqzcPFMGO+/2/ozGREugXvUoEx6VbkLxMWHYlZRpXDgY2jU5PcfkLmDOnszsXBMWltmFnetZXJ0YHen+gUcZw4Xn75xRmsJUV59h5mIKU5m92BZQM5szDZb8dmncGLj/fuDee4H58y3D4csvgcxM1N+3E4M+ex344g1g4EDgmmuAQYOA/IRwlUdJmaOZJdwbmaV9lfHdk+VVJHt8Vc88L0RJKHiwEEJ4EXYqmPXY09mveUx2ljnaScEvhb/s1ISEWLMC1OVSIGyLMt1RnKCTImO6gThnOmaHnWWZjMx5VqI1e/9DqdlITMs2bkMmp0I4k6/REYn5EkJM8jUaHuHhoUdcZRxFskyXVCeutzNJU8Btt21phakUUHdrXgsdGsa5viahocBppwEffQTs2gW8+irQpYu1jdnuvvsOGDIEaN4ceOABYMMGVCYlnTeNu5LaxRvllve4viivIt9Jb3yfhQgEZDAIIfwOZVMtHbYYkyP5FP6yc08hMDvUFAZTd1BaQSc7XCkZ2cgxx/hP0NmiTmyRjMwsKyM7j8pPk+2Yn9ufkmnCvLJ8uh+ZzMychQhhujUrq3RuHjM2hyDniCHC47jKMl1cZuvo8FBT1trdhwuIXt0JU/kZZrfmZ1yJZIu91+g+O2YMsHw50n79DSlXjoIjLs7atns344QD7doB/foBn3wCZGSUWdjNbXTxKnw+paUkQW7h6+cpwa6vhcASHgtRuchEFkL4DcqmWjacxZjsqOU6LCFwlNEcwOQnKEmUSQOAC8XKWw6k5ieEa1armvksR/GdBZ9x0eFGK0E9Q0JKJmav3muMAfYZ14Ukm2PyfShCzCxCWlYOwkOAXIQYd6a4mHBLw5CXh7oRYcYdqbB41FVma4qoye5D6Vi0JdEkTWtSIwbDj2+God2bFBGmsp5b9qfiUFq2ETvf8PHSAvuT0gho8+/JHTFI7ncD6px2NS7c9Du6z/4aob//Zu00d65ZsuJrYNnJZ2NOr3PwT52WxQq7eVz643+2aDt2HUq3NB1O9Sut61pJgtzC189Tgl1fC4ElPBaicpHBIITwG5RNtewUyOZ8JEoSO6htnaIkldTmFE3TUCDsnHNOoHntavmfdRZ8rtubbPQS1ChwJoNaBufsnyFHltwQB0IdDpNcrWGNGDMzUFKUpOIyWzPZHGdMrNmUUESEh2Lt3mRMXLDJzFrQv9y5ntx2KD3bdMzDEYpUjuQ77U9KI6AtfE+uSXfg5Wa9MfS14bgg5rCldaBY+sABRB5OQp8fPjXLP43b46tuA7C89wAciIsvcmwe991fNmF3UkZ+wxU+n7LeA+4Eud4S7PpaCCzhsRCVhwwGIYRf4GsRZVXBlRDaFgKX1F52m7MTfnKbOmYGgJ1zZlOmNoGL6ZwfKYMCWgqLOZuQkpltRNXUN6TTPemIocC+uImqRPelsBAc16IW7jqjA5rUrmb2cc7gXJx41C6/YXw0mtSMxspdh41ImrksePw6sZFG7E1Xo3lrE/LvD7ueD3z9D3YmpiMiMsyUwTpzBJz7/7R6j9FRlHSvlXhPMsPvCy8g5dGx+OqRCThm1lc4du0iYyh12bXOLOk/voN/ep2Fr7oPwMLqkebYZN66BOxLyTRuWYXr53w+5bkHCreptwS7vhYCS3gsROWhX18hhF+gbKq+z9ZbuM3ZeWWnrDY74y4y2NIQoWlg5ULINp1uKp9pKHCWgVpUHseM3zOzdWgoMrLyUM2pboUzOpdUN3ZCw8MtUTePHRYWYlyemHvBzjFAobVzXbOOGBscqacBRVOGdbP335eSZWZUShJIl/aeTMwJwa/d++HnY/qiVco+NJ/xGQYt+QENkvYhJjsDJ8ybYZZdjVshe8NopA27BImp2UYI7qp+hc/HU/eAtzI6+zpTdDBkphbC3/DaN2716tXYtGkTEhMT8wVRzlxxxRXeKloIEYDYoka6hnAUlx0zW0RJVwdlU638Nrf335uUcURU7TCdXhs+6unOxOwL1nPfYdyOKpLZmnWrWz3S6CxMtuw8ByLDws1MBjvXNB6Yydm5DJPdOTbCbOOsBKNIsTr2/vWq0whhZuz0Ys+7tO3jvF9Kwyb4YMBVeKPPJThp41Jc+Pcs9P73d4Tl5qDxrs3Aw/ej5thHcEf3UzGxfT/81bpbkfoVPh8hhKhyBsPGjRsxYsQI/PXXXy4NBcKHrgwGIYQzEjX+B11gSuu6U9Ey6DJUWuGq8zVitmW7k2tsBmMsUPAME2mJo+X146LRt31981lGCyqtmxRzJfCgx7WshV1J6Vi9+7AZiadxkgvr+AdSrfLZke/boX6R4x7TpCb+3XkYe5MzjYFj/xo1rhmD04+23IKoTSjuvAvfk9RjMOoS93e334Z9qYiKCMUBRyjmtu6Bdcf1QcP0JAxY+iMG/zUTcds2ISQ7G93//Alv/vkTdtaoj2ldz8L0rmcgI74e6sVFmYzZvhhBL+4+c95WmrqUdX9fH08IUTE8/i287rrr8M8//+Dll19Gnz59TIZnIYQoDcEuanSOEsUsxsxrQP8ejjgzo7GrKD4VKYNtzOzJzWrFID07F6lZuSW2ubPImoJkGg5MT2AiGVEw7QCiIqwsyhf1aGYiN1H3UFwkIrte05ZaUYN2JqWb6Yqo8DBz/pnZFFY7TMQfQncj5yhJdp2cz43i7zjmhsjINmFfOesRGxmO7s1r4ewuDfPLL+le43vOarBejOhE24hJ33heVmjY0CL3LsuuHhXxn7C7UTwiz7wX0ce+DDCy0rvvwvH55wjJyECTpATcPP9D3PDLx1jQujt+OHEwFjWsZlymKnqt3VG4negCZdeV1ygmIiz/fijumhU+VknXuKx188TxhBB+ajAsXLgQDzzwAMYwdrUQQpSBYBc1OkfkYYeNol12UBvXikZMRLjLKD4VKYMj5fuSM00bsxN9Srt6Jba5O5E1XxnCNC0zG9WiIkwW5Vkr95QqEpFdL0YIYtQgzlhkm1wNFAWHmkRZfK0RE47BxzRGj5a1jUFBIbVzXQuf24HUTHOcWrFRaFIzxtRz56F0fP/PHlN+ae41lmtpIUJQu1okasdGICUz15TFzNr2ebi6d0mRY/fpY5aQV17BsvFvoMYnH6D1trUIc+Sh78bFZjk442X81msQfr72Wpx1wanw7n2Wg12J1gwMrxkjUVHMHh8TjlZ1qxd7zVy1eUn7l6VunjieEMIzeNxcr1u3LmrUqOHpwwohgohgzKbqHJGHo/P0vbeTpHGEvW292AL7VLQMRv2hew5f+X7JlsQyGWj2NbKzLfOV2ZO7tahtXom7sgqfA/9mZCBGCOI516kWifAwo6A2I/mcUTi6UZyJxrRka6Lp2DJjs3NdC59b/bgoY2xl51nJ5lrWjcXRjeOLlF/SvWbvz7KPaVoDzWrHuj2Pwscr7tgpMdXxYdeBuPWud3HtLW/hi+MHIyU61myrnXIIg2d9jLMu7Ivc3n2ADz4A0tLgCZzrzXuK9xbvMbYRjQVONTBULtuObVjcuRZ3P5XnPvX08YQQfmwwXH/99fjoo4+Qm8sHjxBCiNLgHJEnK5fuLg4zak33Hv7Ndc7RecpDaaL+eIqylMW/6RZDjQLPOe+IFiI8NMSss/I9FH/+hcujkUHPJXaE2X58X55z9Vab2cel4Hl1o3Z4YchtGPbIVxh74T1Y1uqY/P3CFv4KXHkl0KgRcOONwNKl5SqvuPuM9xjb3USXys4zbca2K6nNPN02vrw/hRBlw+PDd+3btzfGwrHHHotRo0ahWbNmCAuzEgI5c/7553u6aCGECFgKRwXiqK9JouZwmIzNkWEhpY4Y5U4wWtFIVEaQnJju0h2osIA2LTPHZIymy1NJZZmoRtWsqEb0YWeSN0ZBysxjFCYYdyd357/3cAa2HmCbRRU4N3Z6GcmJnd4aMSHghMWhVEsA3a5B9VJHIfJW9C77uHuSMvKvdUZMJGYcczrmHH8Wjj68BxetmI2+f85EaEICcPgw8Oab1tKtG3DNNcCllwI1a5bpPnA+H0aLYtmHmUgPMLqJ0LAQJGfmgXIROzJVSVGzPNU2ipQmRBAZDMOHD8//+6677nK5Dx8qmoEQQoj/cI60Q3EtR333p2QZ1xBG3WH0HXfRi0orGC1vJCojSF5mCZJ3HUq3/N2PCI4HH9vIaAJcCWgp2qbh8O/uw6hZLdJtWfybkY5YJ2oYsnKzkMMMbQ4HwkJDERNZ9PzTsnLwxLer8evG/cjIykV0ZJipU0xEaP65sZ5Whzgbc9YkGJeb0NAQZOTkYuY/uzG0W5MShbTeit7lfFwej65Xew5nIopJ7wAkt2yDxKGnIPSYd4DvvjNCafzwA4zCfNky4KabgDvvBC66yDIeqI04Mipf3H1QJKJTeKgRN1PYbefZsMLjIr9upYma5Ym2UaQ0IYLIYJg7d66nDymEEEGBc6QdRkmqHhnuMkpSRQSj5YlExeO++4slSDaEAGv3JhuR8rJtidiemO5SQMuZAv7NzMycJSiuLOdoRCZKUqTDjHgziRyXwudPY+H7lXuMvz07vQdSsnA4LRtHNYo35fDcGBGJI/grdx0yGgSmlKN5QK0Ez8dZtFwZ0bucI06tT0gxBleN6Ai0rV8dfdrVs7bToBk61Fq2bwcmTwbeew/YuhXIyAA+/NBa2re3DIcrrsA3O7KLvQ+cz2fN3mREhoUiN9RhrhFneaLDw8yMTUnXzBttE+yR0oTwV0Ic7pIlCK+xatUqdO7cGStXrkSnTp3U0kIECRMmTMBNHBn2Qh4GfobhSzftTzVCUds9hCO/7HSNHdLZrQtRSce9/+sV+HX9fjPbwf35q2FGxfPyTPhQdujbN6iOxVsTzWg+y46LDjc5HjhbwrCtN/drZ4yIsuRh4P6uzp9uSBe+9ZsxEhrGRyEkhK4zeWaEvk71SEy56gQzc8AO77jvVmPB+v3mczWrRZiIRzwef/h6t6uLp88/ptQj4d7KDWAf1444VeLxOcswZ4416zBtGpCdnb/JER6Of7qfgunHnY30vv2B8HC39wHbkffMrqQMdGhQ3Wga6Pq1oYzXzPkclIdBiKrZ3wyeECRCCBEg2BF2nN97QjBa+JilPW5iqiVIZoeW0ws8PDvknBFIy8pFk1phBQS0VkK3/4TaGTl5RtxbmvK4DyMgFV7nDDULdEPizAKNBetcQ817rucMwgmt6phkcXSRopFghUe19mUd2TGny1Thdimpbt6I3FXm4/I8zjjDWvbtAz76CJg4Efj3X4Tk5OCYv342y6HPG2BJvyFY3G8IasTULnIf2C5INPgiwsMQcaQKZb1m5ToHHx9PCFExKvxtPO200xAaGopZs2YhPDwc/fr1K/Ez/BGbw9ERIYQIEjgCS798vpZ3xLa4UVxvinNrxVqCZIZ6ZSfSzvBMT3cmMaM2gCPTtoCWZUdHhJdJqF3SuTvTok4sIiNCkZySZfRwDKzBGQYKnGPZ+Q0NMceggRMVFmIMGyDPtAeNHZ4H11BnUd52KQslXUtS7tH5evWA228HbrsN+P13ZL/9DvI++wxRmRmoeWAv+n/xNk778h0s73A8Vgy4ELWGHFXknlmflGJmhOgCxshUFRXXV3RfT1BSeRWpj7JQi2Ckwt9aPoDzOD16BP5tj24V9xkhhAgGnAWo1VIyjQtIWTPnntimjlGh/rHpgNvst94U5/ZtXx9rd1uC5ITDmUbDwMc4DZMeLWoZDYMR0EaEIjuFOZkdqBsRZtyRylJ+abL8ch+6R0WEhhoDbPuhdJMRmgZNKEIQHhKC1+dtzM+STWMm15GHjExL1GvDuvO8vNl5dXktW9cx9fpj4wHPZvPm7+7JJyPi5JMxY9S92P/eBzhl/nS027YGoQ4Huq35yyz46Fmjc8DVVyOqQ0czK7PncLqZtaHBwKVprZgKievLu68nKKm8itRHWahFMFPhJ+W8efOKfS+EEMGMsxC5k8NhNAZlzZy7cmeSGRGPjQovNvutN8W5jOJTmihJ1DTYUZIo4C1L+aURbdv7MNRs3excHEzNMh05CnfZwWWG4h2J6f9lya4ZjZoxETiUnmNCtHJGhAnBWHdvC2ldnc8/O5NMvapFhXstm/fA3h3wTfWb8Oag4aixfjX6LfwWPRd+j8jkJGD/fuDFF82SdEwPtOx2Fmq3OQmJEVEmtCtpUbtahcX15dnXE5RUXkXqoyzUIpiRg6AQQniJwplrw5NDzStnALj+rM4Ni81WzNlaxspnSFDCTMOR4WFmdNzVMThCyk4P13nS/YPHHdajGQZ2aeQyD0PhMklZy3d17oXPk9j7HN0oHp0a10BaZjb+2XnYdHbrVI8yORaYDdrOIUA3pZ6t6mDd3hTTljf3b4d2DeK87hbj6nyYX+PnI9fylEZxWL4j6b96ZuehS+NYM1Pj6t4oCwXvg/aodfcwROZlWwJpCqWPRDOsu2IxrluxGFfGxOLvXgOw4JTzsCCupWkzLq5G3EtznZzdrkq7rycoqTyK3MtbH1+fixD+hu5uIYTwEmUVIrvan8LhUKe/TaTVYo7hbXFuh4ZxHhNqlyfLb+F9qkVFoF5cFDbtSzH6Cucs2dzFFl/TeAkNCzXhQn3RsSvpWjL3gat6Fnddy0rBaxJuJXrjsmEDDk94G3mTJqFm0gFEp6fixJ++Msvwpm2xsO8QJPW4FdXbNK3QPV3W+7+ilFQe3a7KWx9fn4sQ/obnHQiFEMJP4GggI+XwtTKwRaXUEtjaLVuIzPXuMuc670/hMP3zufDvko4RqG1ZmrZytw/rxFwPKRk5+eJruilR3My/bfF1Se1V+BxLe86u9ivpWsZGhpW7nhWmbVuEPvM0xr3xA54c/QxW9zgVeUciSDXfsQGXfPQ8GndqC1x2mTUb4aRTLM11stuDovOy3P8VpaS6USxfeHt2Tq7JRs6s5MXVp6zfZSGqGjKHhRBVDn8RJxYWInfKzTOvZc2cW696lNENUETsKTGzv7VlaUXbzvswso8JsZpN95kQ7EvJRPKWbCPcpUtNabNkFz5HduZjIsKMxoAzAe7OubQZlZ3PhzMcrNfWg+nlyubtyfY+qUNDTEvri0XH9EbLixPRY/63OOOP/6HBvp0IycwEPvnEWtq0AUaNAkaORPXGjd1eJwq6Z63cU6A96HLFmR9PCvHLew81iI/O387s48z4TRE/Zwp4vVl3d/e1slCLYEcGgxCiyuFP4kRnIXJIUki5MucWjpLky+y3vmzL0oi2nfdZtzfZdOopFm5WOwbbD6abbNPsqHZoEFfqLNmFz3HtnsMmPCyF1a3qxro955LaxuW1LBQlqazZvD1JwfpFYellNyDm4Qdx3qF1CJ/0PvDVV0BWFrBxI/Dgg8AjjwCDBuG8q0YhpMux+HXLoQLXicL4wu1B44siahpwvrh3S7qH7NdP/tqGfdTjMDJtXBRy8vJM3Yu7r5WFWgQzyvRcCSjTsxDeo6wZj31Zr/fefgtXX3e9V/IwVKW2LM15Omcp7tQ4Pr9uq3YdRuMa0aZujCpV0nEKnyNzNvy1+QD2pWShflwUerSsbXITFD7nsrSNV/MweLO9DxwAPv7YSgq3cmXBDzVqhKwRV2D/8BGI79zRrCquPe49u2Ppslh7+5zs7OVfrcCGfSlGPM9AAmW5r5WHQQQKAZHpeefOnfjll1+QkJCACy64AE2bNjUJdpKSklCjRg2TaEcIITyNv4oTWWZ4WEiFMuf6OvttZbVlac7TOUuxc934Pu/I9gbxJR+n8Dlm5uSC6RroSkMhsokWdCScrfM5l6VtSnMtK1Mw67a969QBbrkFGDMGWLTIirA0dSqQkgLs3o3I58aj8XPjgX79cGD4CKSHtnfbHrwezWpXq/xzOnLNmcm6fly0MRbKel/7+nsohD/gcWdeWul33HEHWrVqhcsuu8z8vW7dOrMtJSUFLVu2xGuvvebpYoUQwiBxYnC0pV035mFIzshGWlaOeeX7stSt8DnSUAgPxZGwoiH5YU8LnzNfo8NDkZCcgayc3DK3TWUL8ssEDYATTgDeeccYCnjvPeCkk/7b/vPPqHPdKLxw20Bc9MFzaLB5rd/cK6UVpPtDXYXwZzxuIj/33HN45ZVXcO+996J///4444wz8rdxZuH888/HV199hduYxl4IITyMxInB0ZbsyHPZnZSG9QnJJvM0E7OxTp0bx5tt5T1HdiGZCC7PARNBp/A5U+xMgSzdofYmZWJPUgLqx0cbAyLuiA7BE1mS/ZLq1S0BNJdVqyzj4YMPjPtStdTDGDz/S2D+l9jU6mj80HMQ9vcagF5tW/j8XimPIN0f7msh/BWPfysmTpyIK664Ak899RQO0P+xEMcccwy+//57TxcrhBD5SJxY9duSncFtB9NMp566Ay5hoQxbCrOe20sryi58jt2b1yoQJanwOdti55zcPNSLjzSRdmhYtKoTi6HdmngsS7LfQ59oZo1++mlgxgzkTZyI0J9+Mptab16NGzevRs6MCQi9eDhw7bXAiSdasxU+oDyCdH+4r4UIGoNh+/btOPnkk91uj42NxeHDhz1drBBC5OOtjMfBiD+2pZ1193BGjoksBEcIYqPCkJqZi+pRYUjOyClT9l135+hOrGxn/D2qkSW2Ziz/1buT0bhWtDmGu5mCKpstOCoKGDYMocOGAZs3I2viewidMhnhu3YiPD0NmDTJWo4+GrjmGuDyy4G6db1WndK2s7/d10L4Mx6f/6xfv74xGtyxZMkSNG/e3NPFCiFEEdgBoNBSHYGq1Za24Jjx/SlMZoIwileZy4CC5ZjIsALZoct7jq7O2ZXYOSI8zITmZD6I4sosbTbrgKZVK0Q+NQ7h27YC//sfMHQoEH6k/VavBu64A2jcGBg+HJg9u0BSOE9Rlnb2p/taiKAyGKhReOutt7Bp06b8dfYX9scff8TkyZNx0UUXebpYIYQQFRDZBpII1xatpmVZGZLpr+5w5JlIPJQupB9JtlYR8aq79qiIYDaoxLaMhDhwIPD113Q9AMaPB9q1s7ZlZwOffw6ceaaVFO6JJ4AdOzxWdFC1swgIUgLo+eoOj5vUjz/+OObOnYuuXbuiT58+xlgYP348Hn74Yfz+++/o1q0bHnjgAU8XK4QQohwi20AU4TqLVtkJZMKwPYczERUWagTLTLhWXvFqSe1REcFs0IptGzYE7rkHuPtuYMECKzzrF18AGRnAli1WQrjHHgMGDLBclgYPBiIiyl1c0Laz8DuyA/D56g6Pf2sYCemPP/7ACy+8gC+//BLR0dGYP38+2rRpg0cffRR33303YmJiPF2sEEKIcog/A1WEa4tTF6zfh/UJKTickY0a0RFoW786+rSrV27xamnaoyKC2aAW29Lb4JRTrOXVV4FPPrGSwv39t+WaNHOmtdSvD4wcCVx9NdC+fbmKCup2Fn7DNwH6fHWFMj1XAsr0LERwMmHCBNx0000+K6+kbMTMvjv++zV+lxW7LNjCZOoYKppJuKyZrSuS8VfZgp1YssQKz8qs0oWDotC44KzDBRcA1cqe+E3tLCqLlDI+T/y9vxlY8yFCCCE8Jv7ceiA14EW4tmi1QXx0hcWrZRUlV0QwK7GtE8cdB7zxhpUUbsoUoE+f/7b98gtwxRWWUJrG9rJlamcRECRWsSAHHjdtRjGZSzGwseim1LRpU/Tt2xcnOWeLFEII4XHxJ6fBGVbSHuGiPzdHuFrUiS12uztxqD+M2nqjDiW1F2cxKFz0xGyGP7apr3B7rpxBoHHAZc0a4P33gcmTgX37gKQky6jg0r27NetwySVAzZqVeSpClPt5Emjie48/lX7++Wekp6djH7/gbLBatcxrYmKiea1Xrx7y8vJMUjc23llnnWW0DtXKMdUohBCi/OJPjsqXRRzqDwI+b9bBXXsxfCszRz898998vQTzP7Rz0kuUt2x/aFNfUaZz7dgRePZZYNw44LvvLKH0Dz8w3BGwdClw443AnXcCjLpI46F3b58lhRMiGMX3Hn8aMYtzVFQUHnvsMWMU2Mv+/fuN6JmC54ULFxoDgpGTfvjhB/MqhBDC87AzxuzD9gg5X52zEZe03ZWAjz65HGHnK99zva/wdh1ctUeL2tVM9uil2xKxKzEdB1KysPNQOpZuO1Thsv2hTX1Fuc41MpLx2i0xNCMqPf44YOdySk8HPvjA0jnQwHjuOWDvXp+djxAlUZbna9CJnvv374927dqZXAyuuP76602OBuZkIJdeeqkxILZu3YpgQaJnIYITX4uey+LyUprtlS3g82UdnMXUFIZvSEhBUnoWUjJzUSOGMf5zEBcdjrgjMw3lKdsf2tRXePRcc3OBOXOsWYfp0628DjZMEnfuudasA/M8MB+EEJVMSiW5HPq16JkhVY899li327ntt99+y3/PXA17NSIghBBepSSRbUnb/UHA58s62O3BkXAem9mjmUWaBkRISOiRHBYO465U3rL9oU19hUfPlUYAjQEmf9u5E3jhBeCoo6xtOTlWsjgmjWvVysrvEEQDksI/qV4FMop73GCoWbNm/uyBK+iCxFwNNikpKYiPj/d0NYQQQngQf8ieWxl1sMtk9mhmkaYBwazS9Mdnlmlmmy5v2f7Qpr7Ca+darx5wxx0cSgUWLrTyN9iaSGaYpgsTDQcmhfvySyCr6hhhQgS0wXDttddixowZuPDCCzFnzhzjasSFf3Pdd999Z/axmTlzpskKLYQQwn9xFurRjWTXoXTz6ksBX2XUwT42s0ezm5uXZ2WVZnbpPAfMCHl5y/aHNi3OhYIRofjqCbx+rpy1OPlkYNIkKzwr3aJ79LC20UCZNcsSSDdpAtx1F/Dvvx45LyGCBY8/jShsZpSkl156CdOmTSuwLSwsDHfccYfZh2RkZGDkyJE45phjPF0NIYQQHsYfsudWRh2cs0obLYOLKEkVPba/ZCT2ZtQmn50rvRauu85amEWaSeE++gg4dAjYv99yYeLSq5eVTXrYMCA21rN1EKKK4bVMzwkJCfkzDKRFixZGEF2fKd+DHImehQhOKlP07En8IWdAZdTBk1ml/TUPw1dLdpjIRayPcxhIRna54LimgXuujKhEbQOF0vPmFdwWF2fldKBQmrMSCs8qqgirPCh69to3lYbBJfwCCiGEqFKwk1fZ4r3KqIM3y/SHNmVHnqP/fLUjGTHhFF2HuP6szg09UsdKOdeYGOCyy6xl/fr/ksLt2QMkJwPvvGMtDNpCw4H7HckjJYTwosGQnJxsZheYb8HVJMYpjJsshBBCiICJZFTZRo1HaNcOePppYOxYK78DZx34mpcHLF8OjBlj6RwuvNByWTr1VCC0aiXRE6KsePybzyRtN998M7766ivkMlbykUgI9sPH/tveJoQQQgj/iWS0KTnVzCzk5DmQkZ2Lg6lZRq9RlaI2GSIigPPOsxaGZ+WMA/UOmzcDmZnAxx9bS5s2luHACEyNGvmtO5kQ3sTjdzYjIH377be45ZZbTI6FWprSE0IIIfweO2LRnsMZ+G3jAWMscImKCEXnxvGIYlzZqgqjJz34IHD//cDcudasAzUPDMO6cSPwwAPAww8DgwdbLksDBiA7JNRrAnEhqrzBwBwMt99+O5599llPH1oIIYQQXoSd3cVbDppoUDQWoiPCEB0Rim0H00zn2FPCZ7+Frkf9+1vLgQNWdCUaDytXWhmmZ8ywlsaNsWHABfi1bV9sjm9g3LY4M5OQnGkOU+XbSQQdHjeBq1WrhpYtW3r6sEIIIYTwMpk5eWZpGB+NU9vXM8vJbeoiNSs3XxAdNNSpA9x6K7BiBfDHH9bMgh1+ddcuHPX+a3jpgQvw/Ft3YMDKeehcO7KAcFyIqoTHDYYRI0YUyb8ghBBCiMARPht//OgIhIeFFhE+Bx3UYPbsCUycaCWFe/ddZPY4IX9z25V/4ZKX7sUDo0/HjdNeRfyGNcHZTqJK43GXJGZznj9/PgYMGIDRo0ejWbNmJmFbYbp37+7pooUQotxIuCh8gb/fZ4WFzzQWGKyE+RiYaC2Qhc8eaXvmbLj6amSPuBKvvDYdHWd+gf6LZiE2JQnVUg7jzDmfmyV3xvEUdQIXX2x9RogAx+NPq969e+f/PXv27CLbFSVJCOFPeDOzrRCBdp/Zwmf64jP/gnPyNq73RyOnMtqe7dDmtBPxec1m+ODc63Hamt/Qe940HLt2idketmgRwOX224Hhwy13phNPVFI4EbB4/Js/adIkTx9SCCG8BjsSzpltJVwUwX6fsSNN7A42ZxbsDnYg4q22d26nv2ufhY2nDcIZMWk488+ZCJs8yegckJpqJYnjwky7NBxGjADq1vXY+QkRkAbDlVdeCX/j0KFDuOeee4y2Ii0tDSeccAJeeOGFUrlFjRw5ElOmTCmyvkOHDlizZo2XaiyEqEqZbUVwE2j3GUfd2ZFmvfzZfaqy295tO517MvD4Y8CsWVaEpW+/tSIsrVplzTjcey8wdKhlPPTrp6RwIiAIzCdAGcjLy8OgQYOwfPly3H333ahbty7eeOMN9O3bF0uWLEE7ZnwsgaioKLzLL70TNWrU8GKthRC+IGgy24pKJVDvM9bJH+vlb23vsp3Cw4FBg6yFQukPPrCMhw0brNwOn31mLYwqaSeFa+pfM01COOOVJ0FGRobJ9Lx06VIkJSWZTrsz/LK+x2yKPuDLL7/Eb7/9hi+++MIIssmwYcPQvn17PProo/jkk09KPEZ4eLiJ/iSEqFpUZYGn8B90nwV52zM7NGcV7rkH+OUXy3D48kt2loAtW6yEcI8+Cpx9tiWUHjjQykItRFU2GLZu3YrTTjsNW7ZsQc2aNY3BULt2beMWlJuba0b4q1evDl9Bg6FBgwY4//zz89fVq1fPGA0fffQRMjMzzQxCSbDuqampiI+P93KNhRC+oioKPIX/oftMbW/gDMepp1rLq68CH39sGQ/Ll9MdAvjf/6ylYUNrxmHUKKAUXhBC+AKPh2ag2w+NhD/++APr1q0zlvxnn32GlJQUjB8/HjExMZhFvz4fsWzZMqNVCGX2RieoY6CegXUsCe5HQ4FuSDR+brrpJnM+QojAh8LFod2amNHGyPBQ88r3gSrwFP6J7jO1fQFq1QJuvpmdFGDxYuD66/8Lv7pnD/DMM0D79sBpp1mGRXp6JbagEF6YYfj5559x4403mg75wYMHzToaDRzFpzHx77//4rbbbsP/aEX7gN27d+OUU04psr4RpwhNssZd6NKli9vPcz8Kpml00LXqhx9+MBoIaiLmzZtn3JWKIyEhAfv27SuwbgN9GIUQfkFVEngK/0X3mdre7azDccdZy/PPA198YSWI++03a/u8edZSsyZw2WWWULpr10psTRGsePxXkaPxLSniAcyoPP0FOeNgc9JJJ+Guu+4q17HZYc+iWKgU0EBh2enp6S5djqKjo80rtxfH008/XeD9xRdfbPQPDz74oHF34vvioHHx+OOPl6rOQojKoyoIPIX/o/tMbe+W2FjLFYnLv/8C1HoySuP+/Qz3CEyYYC00Lmg4XHIJI7BUYouKYMLjLknNmzfHjh07zN8cfW/SpIlxT7JZvXp1fme9rPzyyy/Gpak0y9q1a81n+Dd1Cq6E2fb2snL77bcbF6effvqpxH0527Jy5coCy/Tp08tcphBCCCGChKOOsmYcdu60Zh3OOuu/pG9LlgA33GCJqWlc/PorXTkqu8aiiuPx4bR+/fphxowZJgKRnceAo/SJiYlmhuDDDz/EFVdcUa5jd+zYsdSJ4WyXI77SLakw9rrGjcvup0wjo06dOvkuV8VRv359swghhBBClInISIARHrls3QpMnmzNPGzfbukaOAPBpUMHa9aB/Sv1OUQgGAz33XcfFi1alB996IEHHjA6AbrvhIWF4dJLL8WLL75YrmM3bNjQGCBloWvXrliwYIExVpyFz3/++SeqVatm3IvKSnJyMvbv32+iLQkhhBBCeJ0WLazwqw89BNDDgRGWZswAsrMBelXcfTdw//3AeedZ4VlPPx0IC9OFEf7rknTBBRfk6wbofsSkZ5xhYCd78uTJPg1NytwLe/fuxddff52/jvVgXoZzzjmngL5h48aNZnF2W6JxUJgnnnjCCLkHDBjggzMQQgghhDgCjQC6KNFViS7gzz1HFwxrW04O8NVXAPsnrVsD1FBu26amExWmyiv8aDCceOKJuOqqq4x+ws70zLwKhcXI/fv3N6/MIUH27NmDbt264ZJLLjHuUIQhYWfOnGmMhfNoxQshhBBCVAZ0P2IgmTvvtCIrMcLS559b7ko0FB57zDIaaGDQZemccyw3JyH8wWDgbMLUqVOxadMm8zdH4ysr0zPdoNjBZ0jXV1991URFOv74481MRwf6/BUDE88NHjwYs2fPxpQpU4yR0bZtWzz11FMm0lPh3A5CCCFEVSclM6fCIYg9cYxAKNNnUBDdq5e1vPIKMHWqZTwsXWoJon/4wVroSn3llcDVV/83KyFEKQhxFO7NVxCOwHNU386KXIvJSQoXGhJijIlgZdWqVejcubOJmNSpU6fKro4QwkdMmDDBJH4UIhDJzs3DN3/vwsIN+5GcmYO4IxnRmZSOeSZ8dYzKqHfAwsRwHKD96CPAKcS9gcYFZx0uusgK6SqqHKs82N/0uIl95513GnEyNQPFJUQTQgghRODATve0ZTvNSH2NmAhsSk5FQrIVtpzJD311jMqod8DSrRvw+uuWzoHaBgql58+3ti1caC233gpceqllPHTv/l/4ViGc8LhpzSzGt9xyi4wFIYQQoorAzjZH6PnasWEcGteMMa/O631xjMqod5WAOadGjLCyRjOi0r33Ag0aWNsOHwbeegvo0eM/AyMxsbJrLKq6wdCuXTuXkYWEEEIIEZjQ9z/5yAg93YoJX/me67ndF8eojHpXORhO/plnrFwO06YBgwYBtiZz+XJgzBgmqbIMDM5GKCmc8IbBMG7cOBOFyI40JIQQQojAhkJh+v4npWfnBzLhK99zPbf74hiVUe8qS0QEMGQI8N13VlK4J54AWra0tmVkAB9/DPTt+5+B4SIJrggeKqxhoPtRYZjQ7KijjsIZZ5yBZs2amUhFztC6f4UqfiGEEEL4PdWPCIXp+79mT7IZoWen215fmqhDnjhGZdQ7KGja1EoI98ADwM8/W1oHzj5kZdHX3EoIx+2DB1taB+Z5CFfbBRMVvtqv09fNDd/RanWBDAYhhBAisGBUIWJHG2pdNzY/2pAvj1EZ9Q4a6JrEDNFc9u+3oisxPOvq1UBurpVZmkuTJsBVVwGjRgGtWlV2rUUghlUVJaOwqkIEJwqrKqoCysMQZLCb+McfVnjWTz8FUlMLbqdxwVkHujdFRVVWLYWX+5tVPACxEEIIITwJ3Xia1a5WIXceTxwjEMqsElAsftJJlpsSdQyccejZ87/tP/0EXHyxJZS+/XZg5crKrK3wEh4xGDIyMnD99dfjtddeK3Y/Zlq+4YYbkJ2d7YlihRBCCCGEr4iLs2YTOOOwYgWFrEDt2ta2gweBl18GmIOLBgZnJFJSdG2qCB4xGN555x1MnjwZgxiaqxi4fdKkSXiXVqoQQgghhAhMaBgwgM3OncDUqUD//v9to0FBw6JRI+Daa4E//1R41gDHIwbD559/jgsuuACtW7cudr82bdrgoosuwlTeWEIIIYQQIrCJjrZckuiatHEj8OCDlnsS4QwDB4lPPBE45hjLwDhwoLJrLCrLYPjnn3/Qu3fvUu178sknYwWnsYQQQgghRNWBA8fjxll5Hb79FjjvPMAOrU9tw223WcbEJZcAc+YAeXmVXWPhS4MhKysLkZGlS37C/TIzMz1RrBBCCCGE8DeYo4E5G6ZPtzJKP/003UysbcztwGhLjK7Uti3w5JOWW5Oo+gZD48aNTcim0sD9uL8QQgghhKjiUMdw333AunVWUrjLLvsv/OrmzVZCuObNgXPOsXI8KDBO1TUYTj/9dHzwwQdISEgodj9u537MAC2EEEKI4M3lsP1gmnkVQZQU7rTTrGRwu3YBjKxJXQOhaxKT/TKXA40HZpZmhmlRtQyGe++914RW7devH/6kEt4FXN+/f3+z39133+2JYoUQQggRQGTn5uGrJTvwyPSVGPvdavPK91wvggiGYr35ZuDvv4FFi4DRo62QrWTPHuCZZ4B27SwD4+OPgfT0yq5x0OOR7CWMjsRISZdccokRNfN9ly5dEBcXh+TkZOOGtHHjRlSrVg2ffvqpiZYkhBBCiODim793YdqynWZmoUZMBDYlpyIh2dI1XnBc08qunqiMpHA9eljLiy8CX3xhRVVauNDaPm+etdSsCYwYYYVqPfZYXadKwGOZnpljgdGPRo8ebWYRpk+fjg8//NC8pqWl4dprr8Xy5ctxDn3UhBBCCBFU0EhYuGG/ee3YMA6Na8aYV+f1IoiJjQVGjgT+396dwNtY7X8c/5nnUBROIkMJGaNQ0agSGRJNFA23lJQGlbimuqWBcovKX6RuaVB0042uqEgTZYhMicyVeWb/X9+1Pefus+3n2Ps4Z+99zvm8X69jO88+Z5/nedazn71+a/3WWl9+abZokVnv3mZlygSf27LFbMQIs3r1zBo10gJgZtu2JXqPc5VMCxikcuXK9tJLL9nq1att69atqY9r1qyxkSNHHnWdBgAAkDP9tXOfbT/cs5BHLcuugTmP+17b9TzgnHGG2dNPB2dPmjDBrGXLYG+EfPed2e23BwdTd+tmNmsWi8Jlt4AhlNKRUlJS3CMAAMjdShcraCUK5betu/dbIBBw2/So77VdzwNpaMr+jh3NPvkkOKNSv35mJx9OXdu1y2zMGLNmzcxq1QqmNG3axAnMbgEDAACAp3ih/NasWhn3uHj9dlu7Zbd7DN0O+KpUyWzAALNffzX7+GOzdu2C6z3Izz8HU5hSUsyuucbs009ZFC6TETAAAIC4aFOvgrWrn2JVyhSzgvnzukd9r+1AVLRy9OWXm73/vtmaNWZPPWV22mnB57SGgwZOK4VJafADBwYXjsMxI2AAAABxUSBfXjcb0sC2ta3flTXdo77XdiBmJ51kpqn6Fy82++ILs65dzYoUCT63apVZ//7BnokrrggGGFplGhnCOxQAAMSV0o8qHl+UNCRkDg2IPvdcs9deCy4K9+KLZg0bBp/TeJkpU8w6dDCrWNHswQfNlizhzMeIgAEAAAA5g9ZsuOOO4GxKP/xg1qOHWcmSwec2bjQbOtSsRg2z8883Gzs2OHgaR0XAAAAAgJynfv3g+g3qdRg3LhgkeJTCpHUfND2rAozvv0/kniY9AgYAAADkXEWLmt14o9mMGcF0JKUlafyDaAG4kSODq003aBBMZ9JCcUiDgAEAAAC5g2ZUevLJ4OxJEyeatWpllvdwdXju3GAKk3odunQJBhiH1wzJ7QgYAAAAkLsUKGDWtq3ZRx8F13bQFKyaUUn27DF7/XWzFi3MTj89OHXrhg2WmxEwAACAhNqx94Ct/nOXewTiTrMnPfaY2YoVwUXftPibAgpZutTsoYeCK0y3bx9cNO7gwVxXSCyrCAAAEmL/wUM2ad5a+2rZZtu+94CVOLzqsxZyY20GxJ1Sky65JPi1eXOwl+HVV80WLTI7cCCYwqQvBQ8332zWrZtZ5cq5oqDoYQAAAAmhYGHi3N9txeadtu/AIfeo77UdSKgyZczuvddswQKzWbOCwYEGT4tWmB40KLia9KWXmk2YYLZ3b44uMAIGAAAQd0o/Us+CHmuUK2EVShVxj6HbgaRYFK5JE7PRo83WrTN7+WWzRo2Cz2lA9NSpZp06maWkmN13n9nChZYTETAAAIC4+2vnPpeGVLJIAcujSpmrm+Vx32u7ngeSynHHmd16q9k335j9+KNZz55mpUsHn/vjD7PnnjOrXdusaVOz//s/sx07LKcgYAAAAHFXulhBN2Zh6+79Fjg8daUe9b2263kgadWpYzZ8eHBRuDffNLvwwv89N3u2WffuwelZb7stGGBk8+lZCRgAAEDcFT88wFmPi9dvt7VbdrvH0O1A0itc2Ozaa80++8xs2TKzRx4JBgqiHoZXXjE7+2yzunXNNm2y7IqAAQAAJIRmQ2pXP8WqlClmBfPndY/6XtuBbKdqVbMhQ8x++81s0iSzNm3M8uULPnfoUHAgdTZF+A4AABJCU6d2aHiytaxdzo1ZUBoSPQvI9vLnN2vdOvillKWxY4NTsR4eq5MdETAAAICEUpBAoIAcqUIFs4cftuyOlCQAAAAAvggYAABA0tO6DKv/3MX6DEACkJIEAACS1v6Dh9zKz1rMTeszlDg8i5IGRmsMBICsR8AAAACSloKFiXN/dz0LWtRtxfadtnH7XvecBkwDyHqE5gAAICkpSFDPgh5rlCthFUoVcY+h2wFkPQIGAACQlDTV6vbDPQt5Dk9JqUd9r+16HkDWI2AAAABJSesyaMzC1t37LRAIuG161PfarucBZD3GMAAAgKRU/PAAZ41ZWLx+u+tZULDgbWftBiA+CBgAAEDS0mxI4s2SVKVMsdRZkgDEBwEDAABIWpo6VbMhtaxdzo1ZUBoSPQtAfBEwAACApKcggUABSAwGPQMAAADwRcAAAAAAwBcBAwAAAABfBAwAAAAAfBEwAAAAAPBFwAAAAADAFwEDAAAAAF8EDAAAAAB8ETAAAAAA8EXAAAAAAMAXAQMAAAAAXwQMAAAAAHzl938KWWXv3r3ucdmyZZxkIBdZt26dLVy4MNG7AQDIBZYdrmd69c5jQcCQAKtXr3aPbdu2TcSfB5BAQ4YM4fwDAOJa72zQoMExvUaeQCAQyLQ9QlS2bNliM2bMsIoVK1qhQoWyffSqwOeDDz6watWqJXp3cBjlknwok+RDmSQfyiT5UCbJKZpyUc+CgoXmzZtbqVKljunv0cOQACq0q666ynISXay1atVK9G4gDOWSfCiT5EOZJB/KJPlQJtmzXI61Z8HDoGcAAAAAvggYAAAAAPgiYAAAAADgi4ABx6Rs2bLWv39/94jkQbkkH8ok+VAmyYcyST6USXKKd7kwSxIAAAAAX/QwAAAAAPBFwAAAAADAFwEDAAAAAF8EDAAAAAB8ETAAAAAA8EXAgEz12WefWbdu3ey0006zokWLWpUqVeyWW26xdevWcaYTROe+T58+dsEFF1iJEiUsT5489vnnn1MecbJ371576KGHrEKFClakSBE7++yzberUqZz/BNqxY4ebjvCyyy6z448/3r0nXnvtNcokQb799lu76667rFatWlasWDE75ZRT7JprrrFffvmFMkmQhQsXWseOHd1nuD7Ly5QpY+eff75NnjyZMkkiQ4YMcfev2rVrZ/nfImBAplLFSJXRdu3a2fPPP2+dO3e2CRMmWP369W39+vWc7QRYsmSJPfnkk/b777/bmWeeSRnE2U033WTPPvusXX/99TZ8+HDLly+fXXHFFfbll19SFgmyefNmGzhwoP38889Wt25dyiHBdH9677337KKLLnLvkdtuu81mzpxpDRo0sAULFiR693KlVatW2fbt261r166uTB577DG3vU2bNvbyyy8nevdgZmvWrLHHH3/cBdnxwDoMyFS6yZ977rmWN2/eNNuaN29ujz76qA0ePJgzHme66e/fv9+1pL777ruu1Wj69OnWokULyiKLffPNN65HYejQoXb//fe7bXv27HGtQSeeeKLNmjWLMkhQr89ff/1l5cqVs++++84aNWpkY8aMccEd4k/vg7POOssKFiyYum3p0qWugePqq6+28ePHUyxJ4ODBg9awYUN3D1u8eHGidyfX69y5s23atMmVixpBsjq4pocBmUpdlqHBgrdNlVW15iH+lIak84/4U4CmHgW1mHoKFy5s3bt3t9mzZ9vq1asplgQoVKiQCxaQHJo2bZomWJDq1au7FCU+N5KH7mUVK1a0LVu2JHpXcr2ZM2e6z5dhw4bF7VwQMCAu+cL6Ug4kkJvMnTvXjec57rjj0mxv3Lixe5w3b16C9gxIboFAwDZs2MDnRoLt3LnTtV4vX77cnnvuOZsyZYpLHUPiqEfh7rvvduND45lmnD9ufwm5liLgffv2WadOnRK9K0DcB5yXL1/+iO3etrVr11IiQARvvPGGG3elsSZInN69e9uoUaPc/5U90L59exsxYgRFkkAjR450Y0ymTZsW179LwABfhw4dchX9aLv4NVI/UrfZgAED3IwXF154IWc7CcoE8bN7925XDuGUluQ9DyAt5cf36NHDmjRp4gbdInF69erlxpGocUMTmKh1O9rPIGS+P/74w/r16+cGoZctW9biiZQk+FJlX9NARvOlmXgi3fQ1W5IGeL766quc6SQoE8SXykEDbMNp0KD3PID/0Wx6rVq1spIlS6aOAULi1KhRwy6++GLr0qWLffTRRy69uHXr1i5lDPHXt29fNyZRKUnxRg8D0r1RaOaQaISnXWgw56WXXupu+h9//LEbeIvElgniT2WgtIpw3rokWpsBQNDWrVvt8ssvd4Nqv/jiC94fSUi9DbfffrtbI+P0009P9O7kKkuXLnVT2irNOzSdVQ1Qmgnx119/dePlsmqSEwIG+NIsIhmZZlBdZgoW1LKqhdyouCa+TJAY9erVc1PYbtu2Lc3A5zlz5qQ+DyBY6VHLtSqiys2uWbMmpyUJeWmUCu4QX2p8Ulpyz5493Ve4U0891e65554smzmJgAGZPqOCFqXSha2KkqbGA3IrtcY9/fTTrlXIW4dBgbR6ibQ+g6YoBHI75cVrUgxNNfzhhx+6sQtIrI0bN7q1YkKpFXvcuHEulZKALv6U3j1x4sSIaUpab0kL7FWtWjXL/j4BAzKVVrPVYlXdunVz82eHzqFdvHhxa9u2LWc8AbwF8xYuXOgeX3/99dSVhnWzQdZQUKCF8h5++GH3AVytWjUbO3as6zoePXo0pz2BNNOLUl+8rv3Jkye7lVNF+cFKp0T8ZuKZNGmS62H4888/j1io7YYbbqAo4kxpR+oZ1TpKKSkpbmyJZq7S2MRnnnnGfZ4jvjQ1faQ6lNejkNX1K1Z6RqaqXLmym+4rkkqVKrmKEuIvvdmSGLyW9akWmtFClSCtLlynTh0bNGiQtWzZMov/MjJ6r1q5cqV7HvGhVednzJjh+zz3qPh76623XKPG/PnzXZqxxiFqlWcF023atEnAHiG99088VnomYAAAAADgi2lVAQAAAPgiYAAAAADgi4ABAAAAgC8CBgAAAAC+CBgAAAAA+CJgAAAAAOCLgAEAAACALwIGAAAAAL4IGAAAAAD4ImAAkGG//vqr5cmTx1577TXOYoKpHO666y7Lru6880675JJLEr0byKH+/ve/u/dIqMqVK9tNN90U1/3QvVL7oXun55xzzrEHH3wwrvsBxIqAAcjmvA8g7yt//vyWkpLiPgh///13SyYbN260Pn362JlnnmnFixe3woULW7Vq1ezmm2+2L7/8Mt3j0s9WqFDBWrZsac8//7xt377dt1LgfRUtWtRq1qxpffv2tW3btll2N2vWLHeMW7ZssWS1aNEit4+hFaKjWblypb366qv2yCOPpG7bu3ev3X333Va2bFk7+eSTbfDgwUf83po1a9x19NVXX1k8HTp0yO3XU089ZdnFrl27XLl8/vnnid4VhHnooYfsn//8p61fv55zg6SVP9E7ACBzDBw40E499VTbs2ePff31167CrUr4ggULXGU70b755htr1aqVq+h37tzZ/va3v1mhQoVcZfGDDz5w+ztjxgw7//zzIx7X/v373QeqKjy9evWyZ5991iZNmmR16tQ54m+99NJLriK5Y8cO+/TTT23IkCH23//+11Usw1sZs1vAMGDAABcMlipVypI1YNA+tmjRwrXgRmP48OGujC+44ILUbUOHDrVx48bZo48+6q4ZXQdVq1a1a6+9NvVnHnjgAWvTpo01a9bM4n0tb9682V3P2SlgULmIygZmS5Yssbx5E99uetVVV9lxxx1nL774orvOgWREwADkEJdffrmdddZZ7v+33HKLlSlTxp588klXqb7mmmsSum9//fWXtW3b1vV+zJs3z2rUqJHmebUev/XWW1akSJF0j0sefvhhV/m/8sorXWXx559/PuL3rr76anf8osCkQ4cO9v7777tAqkmTJllWIVOPBmKjQPCNN95w5RTqo48+st69e6emaqxevdpdy17AoGB48uTJtnjx4rif8o8//tgqVapktWrVivvfRuZRg0UyUNCie5YCZAV12blRAzlX4kNrAFnivPPOc4/Lly9Ps10VLH04HX/88a7nQZVxVcRC/fnnn3b//fenpg6p9UsV9x9//DFD+zJy5Ehbt26dDRs27IhgQfQBqYpgo0aNonq9Cy+80B577DFbtWqVjR8/PqqfF/VmpEevpyCkWLFiduKJJ9q9995r//nPf9z+haZyqIW2du3a9v3337seEQUKXjqN0q66d+9uJ510kju/devWtbFjx6b5Ow0aNLD27dun2aZzrb/z008/pW57++233TYFRUonUYu6qDXeS7sKT/1Rb432TZUhVWg/+eSTo56fWI49Peol6tixo/u/egu8fUzv91XxV2v9xRdfnGb77t27rXTp0qnf63pVUOalBN1zzz0umFC60rFS+pOOV2lGJUqUcOdB6U7ad533cP/+97/T9C4EAgEX9GpfdC3o2BcuXHhMOfLeNaYeG72eXlephpHSoI52zeka0bGJVyH1O7ZY7wEqW73WhAkTXE+ezoH24aKLLrJly5Zl6Jgi5fmH/q3Q6+mLL75w19wpp5zirvmKFSu6stT1czTh5aPgVeenevXq7hhOOOEEO/fcc23q1Kkx30NF14DuPWrQ8NLqdO1GovE7eg+qQQVIRvQwADmU92EbWunSB5jSN/QhrbEEqhzqg16t/++99561a9fO/dyKFStcxVMfxKqcbtiwwUaNGmXNmzd3H/YaSxALtQTrQzO8knwsbrzxRldJV8rRrbfemu7PekGTKgB+du7c6T7cFdioMlquXDl78803bfr06RF//o8//nAVKKVX3XDDDa6ypkqKKkWqKGkAss7dO++84yolGneg1/WCuX/9619pKmcqG7U0qgLkpVnp/6ronXHGGe7c/fLLL+73nnvuudQeFK8i6FW+1ZOiAcSq+Gqsh3pXfvvtt0w9dj8Knnr27On+rspG+y3eo1+alSqB9evXT7NdwePLL7/szqdSy3Tc3qDu0aNHuyDDC6COlXrkFHhed9111rRpU9eD5ZdupLS4uXPnpkkd6devn6sMXnHFFe7rhx9+sEsvvdT27dt3zD1zl112mSt79RK+++67Lt9dlXhdexLNNadrRGl6d9xxh3uPe+/DSOl8nljvAf/4xz/c9asgY+vWrS4IuP76623OnDkxH1MsdKwKJHVsusaVLvbCCy+4gE/PxUIB1BNPPOGuh8aNG7txT999950rT29AfrT3UF0nCooOHDiQ+nO6niP1okrDhg3do9Imw98LQFIIAMjWxowZE9Bbedq0aYFNmzYFVq9eHXj33XcDZcuWDRQqVMh977nooosCZ555ZmDPnj2p2w4dOhRo2rRpoHr16qnb9PzBgwfT/J2VK1e61xs4cGCabfrb2of0lC5dOlCvXr0jtm/bts3ts/e1Y8eOI47r22+/9X3dkiVLBurXr5/6ff/+/d3vLFmyxL2e9m/UqFFuv0866aTAzp07fV/rmWeecb/7wQcfpG7bvXt3oEaNGm779OnTU7c3b97cbRs5cmSa1xg2bJjbPn78+NRt+/btCzRp0iRQvHhxd7zyzjvvuJ9btGiR+37SpEluH9u0aRPo1KlT6u/WqVMn0K5du9Tvhw4d6n5PxxVO2wsWLBhYtmxZ6rYff/zRbX/hhRd8jzvWYz8a79ii/Z0bbrghcMIJJxyxXddtrVq13Gvp67zzzgts3749sGXLFndtv/XWW4HMMG/ePPf6d955Z5rt1113nduuayrU6NGjA0WKFAns2rXLfb9x40Z33lu1auXeS55HHnnE/X7Xrl0ztF/eNTZu3LjUbXv37g2UK1cu0KFDh5ivOb0fIh2Pn2jvASpnve4ZZ5zh9s8zfPhwt33+/PkxH5P33g+/zr2/FXpteeUQ6oknngjkyZMnsGrVqiPuDaEqVaqUpnzq1q3ryjE90d5De/Xq5f7enDlzUrfpWtE9y+89rOvojjvuSPfvA4lCShKQQyilQy2J6pJXd7latNRN7qVsqBVbLadq1dMgUrXQ6kst5Zp5aOnSpamzKqlr3xsMePDgQfczSks4/fTTXWtbrNRSp9+P1Eugffa+1NIYC71mpNmStJ96PbWM3n777W4mJqWRpDfGQKk7ajVUOopH6QZ+vRc6R5rdKTy3Xa3zoQNzCxQo4Frd1UquQd2h6WIzZ85M7UlQi7paMfV/UeuwBqx7PxvtNaCBwR61ICuVRK3F6Yn12DOTrq3QXjCPrlu15OtLrbpKQ1F5K2VE5dupUyfXo3L22We7a17nOCMt+ioz0e+H0sB6v59Xy7HXUjxt2jT3dzWjU2juud/vx0LHq94rT8GCBV3Ld2h5RnvNxSrWe4DeC9o/j3fdhl970RxTLEJb7NVTpnuaeokUQ+vaiYUmEtC1pnthJLHcQ1Uumi5Vx+bRPUm9Ln70PtDrAcmIgAHIITQtn3Jt1cWvtAh98IQO6lPKgj5ElfsfWknXV//+/VNzoUV5tkp7US6vXkPpL/o55dcr3SBWSo9R5SWc0jq0z+E5wtHSa+q1wyk1QK+pSqaOWxVvr8vfj/KHVdkOH3CoYCMSVbBDK0jea+ichc+84qXk6HlR+pJ+zgsO9KgKllJ61q5d6ypPSk1QOcQSMCiPO1IlRGkgmXnsmS3YQXIkVXzr1avnpsbVOVXuuGaS0axKqrwpbUipIEo9UXkrhz5WOna9dmigJaoYh1OOu/5OaLqSV6Yqz1B6v0QKhGKhoCm8TMLLM9prLlax3gPCrz3v2MOvvWiOKRZKt1P6lcYTKBjRPiptSmK9V+l+pED9tNNOcylSSnkLHVMUyz3UK5dwka4rj16bAc9IVoxhAHIItWR5swmpEqXBesrJ1tSB+iD1Btspx1itYZF4FcTHH3/cfSh269bNBg0a5D6MVSFRq6nfoL30aKCzBkuqwqVKoCe9HOqjUY6yKgSRKrWqeHs5/lnFLxc5Wiqfzz77zOWga/C08uA1IFStnAogNNBZ5RZLPnO+fPliqpAnA+WdR1tZ1GBWtU5r0Pjrr7/urkvNmiUaAK2AwZs6NCuoR0O9ZQrI4yGR5RnrPSDafY3m5/wqzerpCP9evXIKHtU7qfuMelbVyq8gItZ7le4bGu/04YcfurFRWhtEQZMmbdC4hljuoRmhYCWr71tARhEwADmQPpQ1eE+pEyNGjHCD7qpUqeKeU4U9fEaacOql0O9qcGlmfKBpClRNaTpx4sRMm+JVFUbx++COlabJ1GDO8Fa+8JlejvYaapFUxSK0xdeb+lPPe9RzMGbMGDedrCo+SqPQ7yiQ8AIGbQutYGVV62NmHHtG91GVPE2rquCvZMmSvj+naVY1QNpLF1FPTPny5VOf1yDcjCxUqGNXeamiGNr6q0A7nNLa1NsRur6EV6baL+89Jps2bcpwq3ms+x/NNRdruWT2PSAWXu9E+AKF4b0l8+fPdxMBaEaoLl26pG7PaI+lKDBSepW+1IOpIEKDoRUwxHIP1XmPlNoU6boSXbtKbUtvggAgkUhJAnIozZyiXgdNZarF3DRVprZpphPNhhNOFRyPKqnhLYNK+8joytGawURpOGoh1gf8sbaYKo9YrZ4ao5BeTnAsFHjo+EKnR9R5e+WVV6J+DbU8a3YUTYfq0SwpmrVFvQVeqoR4qUZaK0M9LV5lWdvV86DZWcLTkdR6Kpm90nNmHHtG91HrYqj81cviRxWp++67z63YretYdD0poNH5FQVYyuWPlTczj2Z2CqX3TTjlpYfPnqSKoyqQKuPQ6zjS72eFaK85b/xOtOWS2feAWHjpYd4YH1FQrVmGwvdRQvdT/1fKWkZoLEIonT/1GGjaXYnlHqpyUSOJZm0KfV7BcSTe9a9GAiAZ0cMA5GDKwdW0iJrXXAtjaZyDWrCVn6sBrWox03SJs2fPdik+3hzr6hFQPq9a2fQBppY8fdCFtqDG2mqn3oXWrVu7OeI1FakG+aqipQW5vOkPI+XgT5kyxbWWqhKkfVWwoBZEteCpgptZq1hrcLR6YzR4VFNRqvVax+y9fjQttLfddpurTCgdQhUAtUSrpVbjEVSBDB1voYqIKrhqcdSAWY9aNL3B3+EBgzcOQ6sf6xzq/OmcepX0RB67R2MOVJFTIKReA+W/a8pWr6IfTtej0pI0eNhbLyOcVwH0pqX1KmQ9evRInQpVAaRagUOnFVZA2bVrV3f9p7e/Om6NjdD+6rUUsIX3rmgNDwUlmp40lPLXlaKiHj29b7RfGmyr6zZSS7zXOxG+xkBGRXvNKYVOvSMKLJSjr/ekUuD0FUlm3wNiofVDNGBY6WZKN9K+qifOCw5De6cUXOj8K5DRAH+NX8poz47OjwICvc/0NxW061x60/lKtPdQpcipF1RTyOq69aZV9XqEwumepvsfU6oiaSVsfiYAmSK96Uc1LWLVqlXd14EDB9y25cuXB7p06eKmMixQoEAgJSUlcOWVV7qpWD2aMrB3796B8uXLuykkmzVrFpg9e7abFlFfsU6r6lm3bl3ggQceCNSsWdO9rqZorFKlitufmTNnRjwu70tTDmqfL7nkEjdlozddZChv6kRNIZkRK1ascNMqat80dafOwXvvvede8+uvv079OZ0DTfkZyYYNGwI333xzoEyZMm6fNQWj3/np2LGje+233347zZSYRYsWdb+rqU3DDRo0yJVZ3rx500zPqP/36NHjiJ8PnzryWI89Gq+88oor13z58kU1xWrPnj0D1apVi/jc+vXrAyVKlHBTz4abMmWKm/q1VKlS7hoKnTZX03nqb/fp0+eo+6vzrH3Q9K7FihULtG7d2k3rGjoN6YgRI9yUmPv374/4PhswYEDq+6VFixaBBQsWRDz3ui7OOeeco+6T3zWm19PrZuSamzVrVqBhw4buZ442xWq09wBvqlNNpxsq0r0hlmPSferiiy9OnRJZ09ROnTr1iOtJUxPr5zSFrI7/1ltvTZ1OOPRvRzOt6uDBgwONGzd215OOWdfWkCFD3HsyfN+Odg+Vn376yR1z4cKF3c/ovatpecOnVdX1o/Pct29f3/IAEi2P/kl00AIAyUqttEqlUuuhZkbKTeJ17JoVSq3FapXXCsGZQT0GauXV2ASlL2WEelY0+41y2NVzoBQVLdIVLbX2q8Xa6+HQOBG1nms8ht/CcMh9tECeesp0rYaOywGSCWMYAOAwzVgUSnn8SvfQ9Ig5PVhI5LErraN79+5uteDMolWqtRZBRoOFcKr4K3g61n3SmA2CBYRS+p7SnggWkMwYwwAAh7Vv397lESuvXfns48ePd+Mn/AYq5qZjV0BxtHntlfcdvjZFtMLHBhwrb1xMZlFvxbHSmAt9AaE0/gFIdgQMABAyW5DmXlclWbOyaBCkBltqVeHcfuwaLBu+snWkFnS1xAMAchbGMAAAjkrTSC5cuDDdn9HsMse6ujEAIPkQMAAAAADwxaBnAAAAAL4IGAAAAAD4ImAAAAAA4IuAAQAAAIAvAgYAAAAAvggYAAAAAPgiYAAAAADgi4ABAAAAgC8CBgAAAAC+CBgAAAAA+CJgAAAAAOCLgAEAAACALwIGAAAAAL4IGAAAAACYn/8Hv0kqLasxtDQAAAAASUVORK5CYII=","media_type":"image/png"}}]}]},"uuid":"1e3c532a-cdaa-454c-8a1e-c5ac831e791a","timestamp":"2026-10-30T05:04:25.751Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":54335,"dimensions":{"originalWidth":780,"originalHeight":540,"displayWidth":780,"displayHeight":540}}},"sourceToolAssistantUUID":"361cd30f-b6f3-4511-9d34-2efb34070eb2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}73{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"2b5f03ecbdc595c80d42ed6dab625de794fb6ca6fea83e659f547295548b3cda","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSywgKEAgTGAI4AUIIdGhpbmtpbmcSDN50jWdB6GLZwx5CXhoME/PTx68P8B/tTVZmIjAFkbWgpxsRFVSn9GJzaqngre1QPrlsADOktD3YKnoAGATjJx3TVPDCCt7Vu4/pu9Qq6AeSne3T9rJb/Eq0ZTvslK+X1BIlo3sBRaJQsoHIeU0DheGjm50xQYzJievK88Pzmo84JgsZaYASnze2Cy+pwjGquJBHwnPJsaZyTXfmmTm1Nfwn14S6SuzI8vGloYZpQO6S6g2fjCYSd25e2+2W6RwlEauR7v4MFI+CWxdM94DpEo9OSHxd+xJXzx6iRHJ8Mi1s3i/3BA6TsbCiR0IWwxaNKYBCDs5WWK+Fp20NaYF4LyLVDssWfii6usfu3RfEUJUf3ZCUVvxLCH9ziwO8kGdC8Srap3AS0RQCx6T4d8Q9xXaSOhIYfXnEZwKkCkSL9bRS841KVhaNmX+Iw4L7V9L7iAQAaCTL94QLsp+zajT8+JhmsiOZd5E4LxUxkbvAwn92q8McLhTNfRDk2bL4bnY8xRdBH/7hwU5f79NN4mRFayQSZdXPWRyQIUO5e3vcYyjkmcCsK1/wnJXYXsBlzucgXzrBAEFND917dHSxdxSyVnlVx2IqqQtwpkUF5yI2lgSRGW/nmFC9bFCIwz9VFVfaRMCXsaQNHy5INWAYsm/uInyyIiWLVrc9qB0bBQlOQ/+rZrw9A/pCMsyUEMuW7zqsEurip1C0bUrAa79BPup483fO8PudbPDG6hD7jZDQVEfbNOUUMxDV+gIz8DB0iKNafjhoGWPsAe4BRQmFq4zNJmCTPbGMcASz2Fn6yYF/moeB++PdbxFIrYqXBJLmA15aLaErorDyVVlV1iqOcJLxkrDozqS+KXlL/sz+C65sMFJM5UaaQY0CN8xYn+K6aUxwR2298o2jT1iVMbcpx/96wqa36t6gq2NWKPyekHZkd9i5RxPNVy4xeV2SEwRnA+567tC6qZGb2IOsZSqYQJIYQ0l1Y67iSC6uJaqtxJv7b0oKaITKlLcTLom4iG+NJIlcCkWvxlcfBrjrqAWXfI1BrQ6lLY1vPLPlDDDMYo8+OUvye7m58XSthoh2uUmVhmovjp5wn8YFkf7cUZxRS1F3djDaAGyyWGPR/SEqR/VvL2M3/R1Uf5wcG/6JimdJ/1d39cHCUzq8SfKDQ/zONLCDoAQsY9UOENhxk+rx670QiPYoNhbNU9eLnMeCsz9jhe8vANVE0HKgNYN89S9LJIEW8qfrGA6plt/G7CTIeXsTnjjF5mHh9YUMccbPIf5c1thXCfh3+uBImkEFF9ShDHuZhEGINUbZpkhGLgxi16bm7/9KC/MtJxlvVvsxL1HFKu5VeC3SWSCePyT7IkxJANLYNO/iIWZDRSIxydGrUNZLrKDNra23VLsp7sy4hihk3wtVd7ffdpXuEBYM7AWmq4oFKU8CjkcS6iIsGAE="},{"type":"text","text":"The chain check expression was wrong (compared next step's n_after); redo it correctly and check the 1960Q1 row in-sample."},{"type":"tool_use","id":"toolu_012CcKvzokNNavBg5FwnAR1P","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\ne=pd.read_csv('out/exclusions.csv'); print((e.n_after.values[:-1]==e.n_before.values[1:]).all())\n__file__='out/analysis.py'\nexec(open('out/analysis.py').read().split('# OLS')[0]); print(df.loc['1960Q1'])\"","description":"Correct ledger chain check and verify first row"}},{"type":"tool_use","id":"toolu_01H96E7EhnmRg6q6HpR9pzbn","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0219/out/figure1.png"}}]}}74{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"9d0bae71-4881-402a-916f-999cafdbb4a9","timestamp":"2026-10-30T05:04:25.754Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"537b3b3e-7fd9-4d29-8fc9-49aeabe4425a","keep":22,"tail":["2b5f03ecbdc595c80d42ed6dab625de794fb6ca6fea83e659f547295548b3cda","20942e01c209337798c73e6c762989766311cf13336dc5e8380ef21d3cfc30f8"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"806bffedf78a876babb019a1f1c00321816f0885b7fbc8034c135bdea7160160"}75{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"1e3c532a-cdaa-454c-8a1e-c5ac831e791a","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}76{"type":"atis-latch","atis":"","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}77{"parentUuid":"1e3c532a-cdaa-454c-8a1e-c5ac831e791a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqZ9koMbaskkQAh3zvR","type":"message","role":"assistant","content":[{"type":"text","text":"Everything checks out. Now I'll write the checks file, report, claims, and final ledger."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1144,"cache_read_input_tokens":18376,"output_tokens":3652,"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":1144},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqZ9UfygdfZei4ig7Tn","requestRef":"9d0bae71-4881-402a-916f-999cafdbb4a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8f36030a-3938-457f-a86a-7ac6a5cf52d3","timestamp":"2026-10-30T05:04:27.132Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"8f36030a-3938-457f-a86a-7ac6a5cf52d3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqZ9koMbaskkQAh3zvR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01A6RhZNWFduy9aVUoRrvGVh","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| check | outcome |\n|---|---|\n| Clean re-run (deleted results.json, figure1.png, exclusions.csv; reran analysis.py) gives byte-identical results.json | PASS (`cmp` identical) |\n| Input SHA-256 equal to README / bundle.json | PASS |\n| Sample: n=240, first 1960Q1, last 2019Q4 (asserted in script) | PASS |\n| Hand computation of 1960Q1: Δu = 5.1333−5.6000 = −0.4667, g = 2.2237 — equals script row | PASS |\n| OLS β and iid SE equal statsmodels OLS; HAC SE equals statsmodels HAC(maxlags=4, use_correction=False) to 1e-10 (asserted) | PASS |\n| se_iid > 0, se_hac > 0 | PASS |\n| CI contains β̂ and is symmetric (β̂ ± 1.96·se_hac) | PASS |\n| α̂ = mean(Δu) − β̂·mean(g) | PASS |\n| okun_negative_5pct consistent with β̂<0 and |t|>1.96 | PASS |\n| Exclusion ledger: 319 − (5+2+72) = 240 = n_analysed; n_before−n_removed=n_after; steps chain | PASS (an initial chain check had a coding error in the check itself; corrected and passed) |\n| Magnitude vs baseline: se_hac/se_iid ≈ 1.8, consistent with positive residual lag-1 autocorrelation 0.39; β̂ ≈ −0.26 is in the conventional Okun range for q/q non-annualised growth | PASS |\n| Bandwidth sensitivity: se_hac in [0.032, 0.037] for lags 1–12; conclusion unchanged | PASS |\n| No data outside 1959Q4–2019Q4 enters the regression (window filter after differencing) | PASS |\nEOF\ncat > out/report.md <<'EOF'\n# Okun's law in U.S. quarterly data, 1960Q1–2019Q4 (F2-conf-04)\n\n## Question\nHow large is the Okun coefficient β in the linear projection Δu_t = α + β g_t + e_t, where u_t is the quarterly average of monthly UNRATE (pp) and g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) is quarter-on-quarter real GDP growth (percent, not annualised)? Is it negative and significant at the 5% level when the uncertainty allows for serially correlated errors? β is a descriptive projection coefficient. It is not a causal effect.\n\n## Data and exclusions\nInputs are FRED current-vintage files: `UNRATE.csv` with 945 data rows and `GDPC1.csv` with 319 data rows (`n_input_rows`). Their SHA-256 values match `data/README.md`. The full audit is in `out/state/data_audit.md`. UNRATE has one empty value, at 2025-10-01 (`data_issues`). That quarter lies outside the window used, so the gap has no effect. Unemployment is averaged by quarter only when all 3 months are present.\n\nExclusion ledger (`out/exclusions.csv`), counted in GDPC1 quarters (319):\n1. Keep only quarters that have a complete UNRATE quarterly average: 319 → 314. This removes 1947Q1–Q4, before UNRATE starts, and 2025Q4.\n2. Drop quarters with no preceding calendar quarter, where the first difference is undefined: 314 → 312. This removes 1948Q1 and 2026Q1.\n3. Restrict to the 1960Q1–2019Q4 window: 312 → 240.\n\nThe result is n = 240 quarters (`n_analysed`), running from `first_quarter` = 1960Q1 to `last_quarter` = 2019Q4. The 1959Q4 levels are used only to form the 1960Q1 differences.\n\n## Method\n- **Estimator.** OLS of Δu_t on a constant and g_t.\n- **Baseline.** The conventional homoskedastic, independent-errors standard error (`se_iid`).\n- **Main inference.** A Newey–West HAC standard error with Bartlett kernel and no small-sample degrees-of-freedom correction (`se_hac`). It is implemented by hand and cross-checked against statsmodels.\n- **Bandwidth.** The Newey–West/Stock–Watson rule of thumb L = floor(4·(T/100)^{2/9}) = floor(4.86) = 4 quarters (`hac_lags`). I chose it before looking at the results. It is a standard automatic choice for T = 240, and four quarters covers one year of dependence, which suits quarterly macro data.\n- **CI and test.** The 95% CI is β̂ ± 1.96·se_hac, using a normal critical value (`critical_value`). The test is a two-sided z-test of H0: β = 0.\n- **Randomness.** None is used (`random_seed` = null).\n- **Figure.** `out/figure1.png` plots Δu_t against g_t with the OLS line.\n\n## Results\n- β̂ = −0.256 (`beta_hat`). A quarter with 1 percentage point higher q/q real GDP growth goes with an unemployment rate about 0.26 pp lower than it would otherwise be in that quarter.\n- α̂ = 0.184 pp (`alpha_hat`). R² = 0.408 (`r_squared`).\n- Mean quarterly growth in the sample is 0.754% (`mean_growth`). The implied growth rate that keeps unemployment unchanged is −α̂/β̂ ≈ 0.72% per quarter, calculated from `alpha_hat` and `beta_hat`.\n- The HAC standard error is 0.0358 with 4 lags (`se_hac`, `hac_lags`). The 95% CI is [−0.326, −0.186] (`beta_ci_low`, `beta_ci_high`), with t = −7.14 (`t_stat_hac`) and p ≈ 9.5e−13 (`p_value_hac`).\n- The Okun coefficient is negative and significantly different from zero at 5%: `okun_negative_5pct` = true.\n\n## Uncertainty\nThe baseline iid standard error is 0.0200 (`se_iid`), giving a CI of [−0.295, −0.217] (`baseline_beta_ci_low_iid`, `baseline_beta_ci_high_iid`). The residuals are positively autocorrelated, with first-order autocorrelation 0.39 (`resid_lag1_autocorr`). As a result the HAC standard error is about 1.8 times the iid one, so the iid interval overstates precision.\n\nThe HAC standard error changes little with the bandwidth: from 0.032 to 0.037 across lags 1–12 (`se_hac_by_lags`). With 0 lags (heteroskedasticity-robust only) it is 0.029. The significance conclusion is the same at every bandwidth tried.\n\n## Limitations and open issues\n- The data are the current vintage, not real-time. Revisions to GDP would change the numbers somewhat.\n- β is a reduced-form projection. It is not a structural or causal effect, and it may vary over time, which this analysis does not test.\n- The HAC inference is asymptotic, uses a normal critical value and a fixed rule-of-thumb bandwidth, and has no small-sample correction. Fixed-b or other refinements would widen the interval slightly. With |t| ≈ 7 they would not change the conclusion.\n- Contemporaneous Δu uses quarterly averages of monthly data, which itself induces some serial correlation. The HAC standard error is designed to absorb this.\n- No part of the task was infeasible (`feasibility` = \"complete\").\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The OLS Okun coefficient over 1960Q1-2019Q4 (n=240) is about -0.256 pp of unemployment per percent of quarterly real GDP growth, with intercept 0.184 and R^2 0.408.\",\"results_keys\":[\"beta_hat\",\"alpha_hat\",\"r_squared\",\"n_analysed\",\"first_quarter\",\"last_quarter\"],\"status\":\"supported\",\"caveat\":\"Current-vintage data; descriptive linear projection, not causal.\"},\n {\"id\":\"C2\",\"text\":\"The Newey-West (Bartlett, 4 lags) standard error is 0.0358, giving a 95% CI of [-0.326, -0.186]; the Okun coefficient is negative and significant at the 5% level.\",\"results_keys\":[\"se_hac\",\"hac_lags\",\"beta_ci_low\",\"beta_ci_high\",\"okun_negative_5pct\",\"t_stat_hac\",\"p_value_hac\"],\"status\":\"supported\",\"caveat\":\"Asymptotic normal inference, rule-of-thumb bandwidth, no small-sample correction.\"},\n {\"id\":\"C3\",\"text\":\"Residuals are positively autocorrelated (lag-1 0.39) and the HAC SE is about 1.8 times the naive iid SE (0.0200), so iid inference overstates precision.\",\"results_keys\":[\"se_iid\",\"se_hac\",\"resid_lag1_autocorr\",\"baseline_beta_ci_low_iid\",\"baseline_beta_ci_high_iid\"],\"status\":\"supported\",\"caveat\":\"\"},\n {\"id\":\"C4\",\"text\":\"The significance conclusion is robust to the HAC bandwidth (lags 0-12 give SEs 0.029-0.037).\",\"results_keys\":[\"se_hac_by_lags\"],\"status\":\"supported\",\"caveat\":\"Only a finite set of bandwidths tried.\"},\n {\"id\":\"C5\",\"text\":\"Mean quarterly real GDP growth in the sample is 0.754%; the implied unemployment-stabilising growth rate is about 0.72% per quarter.\",\"results_keys\":[\"mean_growth\",\"alpha_hat\",\"beta_hat\"],\"status\":\"supported\",\"caveat\":\"The 0.72% figure is a derived ratio -alpha_hat/beta_hat with no reported uncertainty.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));print(-r['alpha_hat']/r['beta_hat'])\nfor c in json.load(open('out/claims.json')): assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok')\"","description":"Write checks, report, claims; validate claim keys"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1144,"cache_read_input_tokens":18376,"output_tokens":3652,"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":1144},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqZ9UfygdfZei4ig7Tn","requestRef":"9d0bae71-4881-402a-916f-999cafdbb4a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"86bd024e-7574-4bc0-ada4-f000807712af","timestamp":"2026-10-30T05:04:56.333Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}79{"parentUuid":"86bd024e-7574-4bc0-ada4-f000807712af","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01A6RhZNWFduy9aVUoRrvGVh","type":"tool_result","content":"0.7209211099660541\nclaims keys ok","is_error":false}]},"uuid":"e6a7e1dc-8318-4c2b-ae4e-98b0a19d2d1f","timestamp":"2026-10-30T05:04:56.373Z","toolUseResult":{"stdout":"0.7209211099660541\nclaims keys ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"86bd024e-7574-4bc0-ada4-f000807712af","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}80{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"82b437718f1dcc505159bb17211a4371c23a8fa16deb9642d42300959f2df775","message":{"role":"assistant","content":[{"type":"text","text":"Everything checks out. Now I'll write the checks file, report, claims, and final ledger."},{"type":"tool_use","id":"toolu_01A6RhZNWFduy9aVUoRrvGVh","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| check | outcome |\n|---|---|\n| Clean re-run (deleted results.json, figure1.png, exclusions.csv; reran analysis.py) gives byte-identical results.json | PASS (`cmp` identical) |\n| Input SHA-256 equal to README / bundle.json | PASS |\n| Sample: n=240, first 1960Q1, last 2019Q4 (asserted in script) | PASS |\n| Hand computation of 1960Q1: Δu = 5.1333−5.6000 = −0.4667, g = 2.2237 — equals script row | PASS |\n| OLS β and iid SE equal statsmodels OLS; HAC SE equals statsmodels HAC(maxlags=4, use_correction=False) to 1e-10 (asserted) | PASS |\n| se_iid > 0, se_hac > 0 | PASS |\n| CI contains β̂ and is symmetric (β̂ ± 1.96·se_hac) | PASS |\n| α̂ = mean(Δu) − β̂·mean(g) | PASS |\n| okun_negative_5pct consistent with β̂<0 and |t|>1.96 | PASS |\n| Exclusion ledger: 319 − (5+2+72) = 240 = n_analysed; n_before−n_removed=n_after; steps chain | PASS (an initial chain check had a coding error in the check itself; corrected and passed) |\n| Magnitude vs baseline: se_hac/se_iid ≈ 1.8, consistent with positive residual lag-1 autocorrelation 0.39; β̂ ≈ −0.26 is in the conventional Okun range for q/q non-annualised growth | PASS |\n| Bandwidth sensitivity: se_hac in [0.032, 0.037] for lags 1–12; conclusion unchanged | PASS |\n| No data outside 1959Q4–2019Q4 enters the regression (window filter after differencing) | PASS |\nEOF\ncat > out/report.md <<'EOF'\n# Okun's law in U.S. quarterly data, 1960Q1–2019Q4 (F2-conf-04)\n\n## Question\nHow large is the Okun coefficient β in the linear projection Δu_t = α + β g_t + e_t, where u_t is the quarterly average of monthly UNRATE (pp) and g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) is quarter-on-quarter real GDP growth (percent, not annualised)? Is it negative and significant at the 5% level when the uncertainty allows for serially correlated errors? β is a descriptive projection coefficient. It is not a causal effect.\n\n## Data and exclusions\nInputs are FRED current-vintage files: `UNRATE.csv` with 945 data rows and `GDPC1.csv` with 319 data rows (`n_input_rows`). Their SHA-256 values match `data/README.md`. The full audit is in `out/state/data_audit.md`. UNRATE has one empty value, at 2025-10-01 (`data_issues`). That quarter lies outside the window used, so the gap has no effect. Unemployment is averaged by quarter only when all 3 months are present.\n\nExclusion ledger (`out/exclusions.csv`), counted in GDPC1 quarters (319):\n1. Keep only quarters that have a complete UNRATE quarterly average: 319 → 314. This removes 1947Q1–Q4, before UNRATE starts, and 2025Q4.\n2. Drop quarters with no preceding calendar quarter, where the first difference is undefined: 314 → 312. This removes 1948Q1 and 2026Q1.\n3. Restrict to the 1960Q1–2019Q4 window: 312 → 240.\n\nThe result is n = 240 quarters (`n_analysed`), running from `first_quarter` = 1960Q1 to `last_quarter` = 2019Q4. The 1959Q4 levels are used only to form the 1960Q1 differences.\n\n## Method\n- **Estimator.** OLS of Δu_t on a constant and g_t.\n- **Baseline.** The conventional homoskedastic, independent-errors standard error (`se_iid`).\n- **Main inference.** A Newey–West HAC standard error with Bartlett kernel and no small-sample degrees-of-freedom correction (`se_hac`). It is implemented by hand and cross-checked against statsmodels.\n- **Bandwidth.** The Newey–West/Stock–Watson rule of thumb L = floor(4·(T/100)^{2/9}) = floor(4.86) = 4 quarters (`hac_lags`). I chose it before looking at the results. It is a standard automatic choice for T = 240, and four quarters covers one year of dependence, which suits quarterly macro data.\n- **CI and test.** The 95% CI is β̂ ± 1.96·se_hac, using a normal critical value (`critical_value`). The test is a two-sided z-test of H0: β = 0.\n- **Randomness.** None is used (`random_seed` = null).\n- **Figure.** `out/figure1.png` plots Δu_t against g_t with the OLS line.\n\n## Results\n- β̂ = −0.256 (`beta_hat`). A quarter with 1 percentage point higher q/q real GDP growth goes with an unemployment rate about 0.26 pp lower than it would otherwise be in that quarter.\n- α̂ = 0.184 pp (`alpha_hat`). R² = 0.408 (`r_squared`).\n- Mean quarterly growth in the sample is 0.754% (`mean_growth`). The implied growth rate that keeps unemployment unchanged is −α̂/β̂ ≈ 0.72% per quarter, calculated from `alpha_hat` and `beta_hat`.\n- The HAC standard error is 0.0358 with 4 lags (`se_hac`, `hac_lags`). The 95% CI is [−0.326, −0.186] (`beta_ci_low`, `beta_ci_high`), with t = −7.14 (`t_stat_hac`) and p ≈ 9.5e−13 (`p_value_hac`).\n- The Okun coefficient is negative and significantly different from zero at 5%: `okun_negative_5pct` = true.\n\n## Uncertainty\nThe baseline iid standard error is 0.0200 (`se_iid`), giving a CI of [−0.295, −0.217] (`baseline_beta_ci_low_iid`, `baseline_beta_ci_high_iid`). The residuals are positively autocorrelated, with first-order autocorrelation 0.39 (`resid_lag1_autocorr`). As a result the HAC standard error is about 1.8 times the iid one, so the iid interval overstates precision.\n\nThe HAC standard error changes little with the bandwidth: from 0.032 to 0.037 across lags 1–12 (`se_hac_by_lags`). With 0 lags (heteroskedasticity-robust only) it is 0.029. The significance conclusion is the same at every bandwidth tried.\n\n## Limitations and open issues\n- The data are the current vintage, not real-time. Revisions to GDP would change the numbers somewhat.\n- β is a reduced-form projection. It is not a structural or causal effect, and it may vary over time, which this analysis does not test.\n- The HAC inference is asymptotic, uses a normal critical value and a fixed rule-of-thumb bandwidth, and has no small-sample correction. Fixed-b or other refinements would widen the interval slightly. With |t| ≈ 7 they would not change the conclusion.\n- Contemporaneous Δu uses quarterly averages of monthly data, which itself induces some serial correlation. The HAC standard error is designed to absorb this.\n- No part of the task was infeasible (`feasibility` = \"complete\").\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The OLS Okun coefficient over 1960Q1-2019Q4 (n=240) is about -0.256 pp of unemployment per percent of quarterly real GDP growth, with intercept 0.184 and R^2 0.408.\",\"results_keys\":[\"beta_hat\",\"alpha_hat\",\"r_squared\",\"n_analysed\",\"first_quarter\",\"last_quarter\"],\"status\":\"supported\",\"caveat\":\"Current-vintage data; descriptive linear projection, not causal.\"},\n {\"id\":\"C2\",\"text\":\"The Newey-West (Bartlett, 4 lags) standard error is 0.0358, giving a 95% CI of [-0.326, -0.186]; the Okun coefficient is negative and significant at the 5% level.\",\"results_keys\":[\"se_hac\",\"hac_lags\",\"beta_ci_low\",\"beta_ci_high\",\"okun_negative_5pct\",\"t_stat_hac\",\"p_value_hac\"],\"status\":\"supported\",\"caveat\":\"Asymptotic normal inference, rule-of-thumb bandwidth, no small-sample correction.\"},\n {\"id\":\"C3\",\"text\":\"Residuals are positively autocorrelated (lag-1 0.39) and the HAC SE is about 1.8 times the naive iid SE (0.0200), so iid inference overstates precision.\",\"results_keys\":[\"se_iid\",\"se_hac\",\"resid_lag1_autocorr\",\"baseline_beta_ci_low_iid\",\"baseline_beta_ci_high_iid\"],\"status\":\"supported\",\"caveat\":\"\"},\n {\"id\":\"C4\",\"text\":\"The significance conclusion is robust to the HAC bandwidth (lags 0-12 give SEs 0.029-0.037).\",\"results_keys\":[\"se_hac_by_lags\"],\"status\":\"supported\",\"caveat\":\"Only a finite set of bandwidths tried.\"},\n {\"id\":\"C5\",\"text\":\"Mean quarterly real GDP growth in the sample is 0.754%; the implied unemployment-stabilising growth rate is about 0.72% per quarter.\",\"results_keys\":[\"mean_growth\",\"alpha_hat\",\"beta_hat\"],\"status\":\"supported\",\"caveat\":\"The 0.72% figure is a derived ratio -alpha_hat/beta_hat with no reported uncertainty.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));print(-r['alpha_hat']/r['beta_hat'])\nfor c in json.load(open('out/claims.json')): assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok')\"","description":"Write checks, report, claims; validate claim keys"}}]}}81{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"4d2282de-e5a9-400c-8d85-a23d8c271a8b","timestamp":"2026-10-30T05:04:56.377Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"9d0bae71-4881-402a-916f-999cafdbb4a9","keep":24,"tail":["82b437718f1dcc505159bb17211a4371c23a8fa16deb9642d42300959f2df775","351da854e9430949f904edcb2bb0cd374553b9586baca596ffb9baf36e24961d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0ccb554e7f04473f9e1942485ed311b64490d93249a9133a5dd82d779150597a"}82{"parentUuid":"e6a7e1dc-8318-4c2b-ae4e-98b0a19d2d1f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqbQaa6Em8u6UUMFyvb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SbwW9bRrvfP9M8AF3hRVdp","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimand, outputs, info rules, invalidity conditions\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs computed and match README\",\"row/col counts, date ranges, gaps, duplicates, missing values inspected\",\"exclusion ledger written and sums to n_analysed (319-79=240)\",\"info-availability: post-2019 / pre-1959Q4 data excluded by window\"],\"notes\":\"One missing UNRATE value (2025-10) outside window.\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline se_iid and iid CI computed (baseline_beta_ci_low_iid/high_iid) with same estimator and critical value\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, exclusions.csv, figure1.png\",\"HAC SE cross-checked against statsmodels (assert)\",\"no randomness; random_seed null\"],\"notes\":\"hac_lags=4 via floor(4*(T/100)^(2/9)).\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean re-run produced byte-identical results.json\",\"CI contains estimate; SEs positive; alpha identity; ledger sums; hand check 1960Q1; bandwidth sensitivity -- see out/state/checks.md\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md has all 6 required sections with result keys cited\",\"claims.json keys all exist in results.json\"],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: exclusions ledger 319->314->312->240.\n- 2026-10-30 Decision: HAC bandwidth L=4 (NW rule of thumb), Bartlett, no df correction, normal critical value.\n- 2026-10-30 P2/P3 passed: beta=-0.2558, se_iid=0.0200, se_hac=0.0358.\n- 2026-10-30 P4 passed: reproducible, all consistency checks pass.\n- 2026-10-30 P5 passed: report and claims written. Task complete.\nEOF\nls out out/state","description":"Finalize phase ledger and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3672,"cache_read_input_tokens":19520,"output_tokens":855,"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":3672},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqbQQu7dAyrDyeNip6T","requestRef":"4d2282de-e5a9-400c-8d85-a23d8c271a8b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"605c5c82-94ae-4141-bf8b-b2f51b176fb6","timestamp":"2026-10-30T05:05:04.600Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}83{"parentUuid":"605c5c82-94ae-4141-bf8b-b2f51b176fb6","isSidechain":false,"promptId":"4b70d210-03e9-41ba-9a80-788653e33b3d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SbwW9bRrvfP9M8AF3hRVdp","type":"tool_result","content":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json","is_error":false}]},"uuid":"0e80f469-1c72-4508-a542-31e575fcd023","timestamp":"2026-10-30T05:05:04.618Z","toolUseResult":{"stdout":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"605c5c82-94ae-4141-bf8b-b2f51b176fb6","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}84{"type":"api-request-blob","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","hash":"8033305129a528ca814491a2059776ff9618aeb8d570e76ea30975acdacc3e89","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01SbwW9bRrvfP9M8AF3hRVdp","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimand, outputs, info rules, invalidity conditions\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs computed and match README\",\"row/col counts, date ranges, gaps, duplicates, missing values inspected\",\"exclusion ledger written and sums to n_analysed (319-79=240)\",\"info-availability: post-2019 / pre-1959Q4 data excluded by window\"],\"notes\":\"One missing UNRATE value (2025-10) outside window.\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline se_iid and iid CI computed (baseline_beta_ci_low_iid/high_iid) with same estimator and critical value\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, exclusions.csv, figure1.png\",\"HAC SE cross-checked against statsmodels (assert)\",\"no randomness; random_seed null\"],\"notes\":\"hac_lags=4 via floor(4*(T/100)^(2/9)).\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean re-run produced byte-identical results.json\",\"CI contains estimate; SEs positive; alpha identity; ledger sums; hand check 1960Q1; bandwidth sensitivity -- see out/state/checks.md\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md has all 6 required sections with result keys cited\",\"claims.json keys all exist in results.json\"],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: exclusions ledger 319->314->312->240.\n- 2026-10-30 Decision: HAC bandwidth L=4 (NW rule of thumb), Bartlett, no df correction, normal critical value.\n- 2026-10-30 P2/P3 passed: beta=-0.2558, se_iid=0.0200, se_hac=0.0358.\n- 2026-10-30 P4 passed: reproducible, all consistency checks pass.\n- 2026-10-30 P5 passed: report and claims written. Task complete.\nEOF\nls out out/state","description":"Finalize phase ledger and log"}}]}}85{"type":"api-request","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","id":"286abecc-9cef-4bc5-b0e0-24944b8fb949","timestamp":"2026-10-30T05:05:04.622Z","version":"2.1.314","querySource":"sdk","shapeHash":"44a1757dad1ee6183f671947d6f624eb650cfb712ff9ab3a520a563062d4fc8a","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":"4d2282de-e5a9-400c-8d85-a23d8c271a8b","keep":26,"tail":["8033305129a528ca814491a2059776ff9618aeb8d570e76ea30975acdacc3e89","18ff12fe229ba029f13fee7a029869a71e862833cd4b309521b7e00b4db88d18"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ae4022ce9d53efe6eaf5abc22edaa9d6a8b17d1a16f38c9f0494f107b59a046c"}86{"parentUuid":"0e80f469-1c72-4508-a542-31e575fcd023","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqc1vpwu3AqHTehieFP","type":"message","role":"assistant","content":[{"type":"text","text":"I estimated the Okun coefficient: β̂ = −0.256. It is negative and significant at the 5% level using the autocorrelation-robust standard error, so `okun_negative_5pct` is true. All six phases are marked passed, and a clean rerun of `out/analysis.py` gives an identical `out/results.json`.\n\nThe regression covers the 240 quarters from 1960Q1 to 2019Q4. A quarter with 1 percentage point higher real GDP growth (quarter-on-quarter, not annualised) goes with an unemployment rate about 0.26 points lower.\n\n| Quantity | Value |\n|---|---|\n| β̂ (Okun coefficient) | −0.256 |\n| α̂ (intercept) | 0.184 |\n| R² | 0.408 |\n| Conventional standard error (baseline) | 0.0200 |\n| Newey–West standard error, 4 lags | 0.0358 |\n| 95% confidence interval | [−0.326, −0.186] |\n| t-statistic | −7.14 |\n| Mean quarterly growth | 0.754% |\n\n- **Bandwidth:** I used 4 lags, from the standard rule of thumb floor(4·(T/100)^(2/9)) for T = 240. The robust standard error stays between 0.032 and 0.037 for 1 to 12 lags, and the conclusion holds at every bandwidth tried.\n- **Why the robust error matters:** the residuals are positively autocorrelated (0.39 at lag 1), so the robust standard error is about 1.8 times the conventional one. The conventional interval makes the estimate look more precise than it is.\n- **Data:** UNRATE has one missing value, October 2025. It falls outside the window and does not affect the results, and it is recorded under `data_issues`. The exclusion steps take the 319 GDP quarters down to 314, then 312, then 240.\n\n**Limitations:**\n- The data are today's revised figures, not what was available in real time.\n- β is a descriptive relationship, not a causal effect, and I did not test whether it changes over time.\n- The inference relies on large-sample approximations with a rule-of-thumb bandwidth and no small-sample correction. With t ≈ −7, refinements would be unlikely to change the conclusion.\n\nFiles are in `out/`:\n- results.json\n- report.md\n- analysis.py\n- claims.json\n- figure1.png\n- exclusions.csv\n- state/ (contract, data audit, checks, phase ledger, log)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":928,"cache_read_input_tokens":23192,"output_tokens":822,"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":928},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqc1eiWLFVbQUN8jaYh","requestRef":"286abecc-9cef-4bc5-b0e0-24944b8fb949","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"395e8f5e-25e0-4d9e-94be-cf9cc6a89cda","timestamp":"2026-10-30T05:05:11.665Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0219","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","version":"2.1.314","gitBranch":"HEAD"}87{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"395e8f5e-25e0-4d9e-94be-cf9cc6a89cda","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}88{"type":"atis-latch","atis":"","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018"}89{"type":"cost-state","sessionId":"8e784c1b-7a63-46df-9fec-29cf941b6018","totalCostUSD":0.4229218,"totalAPIDuration":118877,"totalAPIDurationWithoutRetries":118868,"totalToolDuration":6258,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":124886,"startTime":1793336586787,"modelUsage":{"claude-opus-5-5":{"inputTokens":30,"outputTokens":13728,"thinkingTokens":955,"cacheReadInputTokens":175809,"cacheCreationInputTokens":22616,"cacheCreationEphemeral5mInputTokens":22616,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.4229218}},"hasUnknownModelCost":false}90