1{"type":"atis-latch","atis":"","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:06:08.328Z","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","content":"Review"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:06:08.334Z","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}4{"parentUuid":null,"isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":"Review"},"uuid":"d7a86621-f9e7-45b6-a88a-1d8ef600e262","timestamp":"2026-10-30T05:06:08.339Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","timestamp":"2026-10-30T05:06:08.352Z","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/RC0218\nDate: 2026-10-30\n\nYou are an independent scientific reviewer. In the current working directory, `TASK.md` describes a bounded scientific task and the directory `out/` contains the deliverables submitted by another assistant (you have not seen how they were produced and you must not look for their working transcript). There is no network access. Use `~/wp29/venv/bin/python` if you need to re-run or test code. Do not modify any file under `out/` except that you must create `out/review/review.json`.\n\nReview the deliverables against `TASK.md` only. Specifically check:\n1. Does `out/results.json` contain every required key with legitimately computed values? Re-run `out/analysis.py` in a scratch copy if needed and compare.\n2. Are the information-availability rules of `TASK.md` respected by the code (for example no use of future information, no use of forbidden inputs)? Read the code to verify; do not trust the report.\n3. Are the central claims in `out/report.md` and `out/claims.json` supported by the numbers in `out/results.json`, with appropriate uncertainty and caveats? Flag any claim that is stronger than the evidence.\n4. Are counts, exclusions, units, signs and magnitudes internally consistent? Are baseline comparisons present when the task requires them?\n5. Are limitations stated honestly? Is anything declared complete that is not?\n\nYou have no reference answers; do not guess what the \"right\" number is. Report only issues you can justify from the files. Write `out/review/review.json` as {\"verdict\": \"accept\"|\"revise\", \"issues\": [{\"id\": \"R1\", \"severity\": \"critical\"|\"major\"|\"minor\", \"location\": \"<file or key>\", \"issue\": \"...\", \"suggested_fix\": \"...\"}], \"summary\": \"...\"}. Use \"revise\" if there is at least one critical or major issue. Be concise and specific. End with a one-paragraph plain-text summary.\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":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"0a775297-e9a1-473a-abc1-94361bc2784e","timestamp":"2026-10-30T05:06:08.352Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":["99833769e4310fc124186eb9e97416cea64dc8ececb015cbe8928bf0c2bd9984","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"12e215b400af18f342775f45894e03fc67fd89a85056fcf3e3db62cb15074dc4"}8{"parentUuid":"d7a86621-f9e7-45b6-a88a-1d8ef600e262","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"c42ece9d-2eac-4549-8f7d-188b43dde9c9","timestamp":"2026-10-30T05:06:08.344Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"c42ece9d-2eac-4549-8f7d-188b43dde9c9","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"68afd21b-f976-439a-9ee7-37575a4d53ae","timestamp":"2026-10-30T05:06:08.344Z","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/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"68afd21b-f976-439a-9ee7-37575a4d53ae","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":"66f9467d-27b5-479a-9514-1fb33a9e67cf","timestamp":"2026-10-30T05:06:08.344Z","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/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}12{"parentUuid":"66f9467d-27b5-479a-9514-1fb33a9e67cf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqgitnzKuzzYLBZTHsN","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":716,"cache_read_input_tokens":1504,"output_tokens":122,"output_tokens_details":{"thinking_tokens":17},"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":445,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqgieQReubgz3jPz2g6","requestRef":"0a775297-e9a1-473a-abc1-94361bc2784e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"eacfdd9b-3a27-4dc7-ac5f-4a017804fce8","timestamp":"2026-10-30T05:06:10.250Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"eacfdd9b-3a27-4dc7-ac5f-4a017804fce8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqgitnzKuzzYLBZTHsN","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015pLZmtdy5g4CyFVd9333mu","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Read task and deliverables"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":716,"cache_read_input_tokens":1504,"output_tokens":122,"output_tokens_details":{"thinking_tokens":17},"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqgieQReubgz3jPz2g6","requestRef":"0a775297-e9a1-473a-abc1-94361bc2784e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e4a502ac-ca87-4d08-a993-2f4cd5b4491c","timestamp":"2026-10-30T05:06:10.819Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"e4a502ac-ca87-4d08-a993-2f4cd5b4491c","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015pLZmtdy5g4CyFVd9333mu","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 160\ndrwxr-xr-x@ 10 simon-pierreboucher staff 320 oct. 30 01:06 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:04 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 5272 oct. 30 01:05 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 1461 oct. 30 01:05 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 503 oct. 30 01:05 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 53105 oct. 30 01:05 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 4654 oct. 30 01:05 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 1237 oct. 30 01:05 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:06 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 01:05 state\n{\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": -0.25576772774872947,\n \"alpha_hat\": 0.18438835418210964,\n \"r_squared\": 0.40825082845620597,\n \"se_iid\": 0.019960092914910015,\n \"se_hac\": 0.03583463330296578,\n \"hac_lags\": 4,\n \"beta_ci_low\": -0.326002318421742,\n \"beta_ci_high\": -0.18553313707571695,\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 value(s) at 2025-10-01\",\n \"handling\": \"outside the 1959Q4-2019Q4 span needed; dropped by window filter, no effect on estimates\"\n }\n ],\n \"n_input_rows\": {\n \"UNRATE.csv\": 945,\n \"GDPC1.csv\": 319\n },\n \"random_seed\": null,\n \"t_stat_hac\": -7.137445096377235,\n \"p_value_hac\": 9.508157930953398e-13,\n \"residual_acf_lag1\": 0.38935129370212984,\n \"se_hac_by_lags\": {\n \"0\": 0.028836223207270188,\n \"1\": 0.032358596534706116,\n \"2\": 0.034227320236154,\n \"4\": 0.03583463330296578,\n \"6\": 0.03687902855135959,\n \"8\": 0.03713550417540173,\n \"12\": 0.03640885110228042\n },\n \"beta_ci_iid_low\": -0.2948887909900262,\n \"beta_ci_iid_high\": -0.21664666450743272\n}[\n {\"id\":\"C1\",\"text\":\"The OLS Okun coefficient over 1960Q1-2019Q4 (240 quarters) is about -0.256 pp of unemployment change 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; reduced-form projection, not causal.\"},\n {\"id\":\"C2\",\"text\":\"Using a Newey-West Bartlett HAC SE with 4 lags (0.0358), the 95% CI is [-0.326, -0.186]; the coefficient is negative and significantly different from zero at 5%.\",\"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 critical value, no small-sample correction.\"},\n {\"id\":\"C3\",\"text\":\"The naive iid SE (0.0200) understates uncertainty: residuals have lag-1 autocorrelation 0.39 and the HAC SE is about 1.8 times larger.\",\"results_keys\":[\"se_iid\",\"se_hac\",\"residual_acf_lag1\",\"beta_ci_iid_low\",\"beta_ci_iid_high\"],\"status\":\"supported\",\"caveat\":\"\"},\n {\"id\":\"C4\",\"text\":\"The significance conclusion is robust to the HAC bandwidth over 0-12 lags (HAC SE between 0.0288 and 0.0371).\",\"results_keys\":[\"se_hac_by_lags\",\"beta_hat\"],\"status\":\"supported\",\"caveat\":\"Only Bartlett kernel examined.\"},\n {\"id\":\"C5\",\"text\":\"Mean quarterly real GDP growth over the sample is 0.754 percent.\",\"results_keys\":[\"mean_growth\"],\"status\":\"supported\",\"caveat\":\"\"}\n]","is_error":false}]},"uuid":"e6106c0a-6593-4b10-b97a-d92c1b71aa60","timestamp":"2026-10-30T05:06:10.899Z","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 160\ndrwxr-xr-x@ 10 simon-pierreboucher staff 320 oct. 30 01:06 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:04 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 5272 oct. 30 01:05 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 1461 oct. 30 01:05 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 503 oct. 30 01:05 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 53105 oct. 30 01:05 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 4654 oct. 30 01:05 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 1237 oct. 30 01:05 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:06 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 01:05 state\n{\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": -0.25576772774872947,\n \"alpha_hat\": 0.18438835418210964,\n \"r_squared\": 0.40825082845620597,\n \"se_iid\": 0.019960092914910015,\n \"se_hac\": 0.03583463330296578,\n \"hac_lags\": 4,\n \"beta_ci_low\": -0.326002318421742,\n \"beta_ci_high\": -0.18553313707571695,\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 value(s) at 2025-10-01\",\n \"handling\": \"outside the 1959Q4-2019Q4 span needed; dropped by window filter, no effect on estimates\"\n }\n ],\n \"n_input_rows\": {\n \"UNRATE.csv\": 945,\n \"GDPC1.csv\": 319\n },\n \"random_seed\": null,\n \"t_stat_hac\": -7.137445096377235,\n \"p_value_hac\": 9.508157930953398e-13,\n \"residual_acf_lag1\": 0.38935129370212984,\n \"se_hac_by_lags\": {\n \"0\": 0.028836223207270188,\n \"1\": 0.032358596534706116,\n \"2\": 0.034227320236154,\n \"4\": 0.03583463330296578,\n \"6\": 0.03687902855135959,\n \"8\": 0.03713550417540173,\n \"12\": 0.03640885110228042\n },\n \"beta_ci_iid_low\": -0.2948887909900262,\n \"beta_ci_iid_high\": -0.21664666450743272\n}[\n {\"id\":\"C1\",\"text\":\"The OLS Okun coefficient over 1960Q1-2019Q4 (240 quarters) is about -0.256 pp of unemployment change 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; reduced-form projection, not causal.\"},\n {\"id\":\"C2\",\"text\":\"Using a Newey-West Bartlett HAC SE with 4 lags (0.0358), the 95% CI is [-0.326, -0.186]; the coefficient is negative and significantly different from zero at 5%.\",\"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 critical value, no small-sample correction.\"},\n {\"id\":\"C3\",\"text\":\"The naive iid SE (0.0200) understates uncertainty: residuals have lag-1 autocorrelation 0.39 and the HAC SE is about 1.8 times larger.\",\"results_keys\":[\"se_iid\",\"se_hac\",\"residual_acf_lag1\",\"beta_ci_iid_low\",\"beta_ci_iid_high\"],\"status\":\"supported\",\"caveat\":\"\"},\n {\"id\":\"C4\",\"text\":\"The significance conclusion is robust to the HAC bandwidth over 0-12 lags (HAC SE between 0.0288 and 0.0371).\",\"results_keys\":[\"se_hac_by_lags\",\"beta_hat\"],\"status\":\"supported\",\"caveat\":\"Only Bartlett kernel examined.\"},\n {\"id\":\"C5\",\"text\":\"Mean quarterly real GDP growth over the sample is 0.754 percent.\",\"results_keys\":[\"mean_growth\"],\"status\":\"supported\",\"caveat\":\"\"}\n]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e4a502ac-ca87-4d08-a993-2f4cd5b4491c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"53c77d0c3f24ab4cffeffe51fea59661e0f6b35a6e39f2266c6c9ac72d82d8f9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_015pLZmtdy5g4CyFVd9333mu","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Read task and deliverables"}}]}}16{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"01c34eef-6293-4562-967d-d121dd0a42e0","timestamp":"2026-10-30T05:06:10.905Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":"0a775297-e9a1-473a-abc1-94361bc2784e","keep":2,"tail":["53c77d0c3f24ab4cffeffe51fea59661e0f6b35a6e39f2266c6c9ac72d82d8f9","5a79f36f66e6c0b23569b82a48cc6ec16be2f96278e69e0d1bbc80df83e119cb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8e07082c85c7762f05a7112c1c8315583e692a4badd7c65a0fcabfa31ee2792d"}17{"type":"last-prompt","lastPrompt":"Review","leafUuid":"e6106c0a-6593-4b10-b97a-d92c1b71aa60","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}18{"type":"atis-latch","atis":"","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}19{"parentUuid":"e6106c0a-6593-4b10-b97a-d92c1b71aa60","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqgtm7b1RV4pVBgsFq7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01T6rhN9XdJx91hyJh2XpCkU","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/exclusions.csv; ls out/state; grep -n \",$\\|,\\s*$\" data/*.csv | head","description":"Read code, report, exclusions"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3757,"cache_read_input_tokens":2220,"output_tokens":135,"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":3757},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXqgtUWYsGPKYj8GS1ze","requestRef":"01c34eef-6293-4562-967d-d121dd0a42e0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6b49064f-6c3b-4513-b252-c2758918ff4c","timestamp":"2026-10-30T05:06:12.738Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"6b49064f-6c3b-4513-b252-c2758918ff4c","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01T6rhN9XdJx91hyJh2XpCkU","type":"tool_result","content":"\"\"\"Okun's law, U.S. 1960Q1-2019Q4, OLS with Newey-West HAC SE. Run from workspace root.\"\"\"\nimport json, math\nimport numpy as np, pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nFIRST, LAST = pd.Period(\"1960Q1\", \"Q\"), pd.Period(\"2019Q4\", \"Q\")\nissues, excl = [], []\n\nu_raw = pd.read_csv(\"data/UNRATE.csv\")\ng_raw = pd.read_csv(\"data/GDPC1.csv\")\nn_rows = {\"UNRATE.csv\": int(len(u_raw)), \"GDPC1.csv\": int(len(g_raw))}\n\n# --- unemployment: monthly -> quarterly average\nu = u_raw.copy()\nu[\"date\"] = pd.to_datetime(u[\"observation_date\"])\nu[\"UNRATE\"] = pd.to_numeric(u[\"UNRATE\"], errors=\"coerce\")\nmiss = u.loc[u[\"UNRATE\"].isna(), \"observation_date\"].tolist()\nif miss:\n issues.append({\"issue\": f\"UNRATE missing value(s) at {', '.join(miss)}\",\n \"handling\": \"outside the 1959Q4-2019Q4 span needed; dropped by window filter, no effect on estimates\"})\nu[\"q\"] = u[\"date\"].dt.to_period(\"Q\")\n# quarterly average only for quarters with all 3 monthly values present\ncnt_all = u.groupby(\"q\")[\"UNRATE\"].count()\nuq_all = u.groupby(\"q\")[\"UNRATE\"].mean()[cnt_all == 3]\n\n# --- GDP\ng = g_raw.copy()\ng[\"q\"] = pd.to_datetime(g[\"observation_date\"]).dt.to_period(\"Q\")\ng[\"GDPC1\"] = pd.to_numeric(g[\"GDPC1\"], errors=\"coerce\")\nassert g[\"GDPC1\"].notna().all() and not g[\"q\"].duplicated().any()\ngq = g.set_index(\"q\")[\"GDPC1\"]\n\n# Exclusion ledger in quarterly units, starting from the 319 GDPC1 quarters\npanel = pd.DataFrame({\"y\": gq})\nn0 = len(panel)\npanel[\"u\"] = uq_all.reindex(panel.index)\npanel = panel.dropna()\nexcl.append((\"merge_unrate\", \"keep GDPC1 quarters with a complete (3-month, non-missing) UNRATE quarterly average\",\n n0, len(panel), n0 - len(panel),\n \"UNRATE (945 monthly rows) averaged to quarters; 1947 has no UNRATE, 2025Q4 lacks Oct-2025 value\"))\nn0 = len(panel)\npanel = panel.loc[FIRST - 1:LAST]\nexcl.append((\"window\", \"keep 1959Q4-2019Q4 (1959Q4 only for differencing)\", n0, len(panel), n0 - len(panel),\n \"information rule: fixed sample window, no extension\"))\nassert len(panel) == 241 and (cnt_all.loc[FIRST - 1:LAST] == 3).all()\ndf = panel.sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"y\"] / df[\"y\"].shift(1))\nn0 = len(df)\ndf = df.loc[FIRST:LAST].dropna()\nexcl.append((\"differencing\", \"drop 1959Q4 (levels used only to form 1960Q1 differences)\", n0, len(df), n0 - len(df),\n \"first difference unavailable for base quarter\"))\nT = len(df)\nassert T == 240\n\nX = sm.add_constant(df[\"g\"].values)\ny = df[\"du\"].values\nols = sm.OLS(y, X).fit()\n# Newey-West (1994) plug-in rule of thumb: floor(4*(T/100)^(2/9))\nL = int(math.floor(4 * (T / 100) ** (2 / 9)))\nhac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": False})\n\n# manual check of HAC SE\ne = ols.resid; Xe = X * e[:, None]\nS = Xe.T @ Xe\nfor j in range(1, L + 1):\n w = 1 - j / (L + 1); G = Xe[j:].T @ Xe[:-j]; S += w * (G + G.T)\nXtXi = np.linalg.inv(X.T @ X)\nse_manual = float(np.sqrt((XtXi @ S @ XtXi)[1, 1]))\nassert abs(se_manual - hac.bse[1]) < 1e-10\n\nbeta, alpha = float(ols.params[1]), float(ols.params[0])\nse_hac = float(hac.bse[1]); z = stats.norm.ppf(0.975)\nlo, hi = beta - z * se_hac, beta + z * se_hac\np_hac = float(2 * stats.norm.sf(abs(beta / se_hac)))\n\nsens = {}\nfor l in [0, 1, 2, 4, 6, 8, 12]:\n r = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": l, \"kernel\": \"bartlett\", \"use_correction\": False})\n sens[str(l)] = float(r.bse[1])\n\nres = {\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": beta, \"alpha_hat\": alpha, \"r_squared\": float(ols.rsquared),\n \"se_iid\": float(ols.bse[1]), \"se_hac\": se_hac, \"hac_lags\": L,\n \"beta_ci_low\": float(lo), \"beta_ci_high\": float(hi),\n \"okun_negative_5pct\": bool(beta < 0 and p_hac < 0.05),\n \"mean_growth\": float(df[\"g\"].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\": issues, \"n_input_rows\": n_rows, \"random_seed\": None,\n # supplementary\n \"t_stat_hac\": float(beta / se_hac), \"p_value_hac\": p_hac,\n \"residual_acf_lag1\": float(pd.Series(e).autocorr(1)),\n \"se_hac_by_lags\": sens,\n \"beta_ci_iid_low\": float(beta - z * ols.bse[1]), \"beta_ci_iid_high\": float(beta + z * ols.bse[1]),\n}\nwith open(\"out/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\"out/exclusions.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(6.5, 4.5))\nax.scatter(df[\"g\"], df[\"du\"], s=12, alpha=0.6)\nxs = np.linspace(df[\"g\"].min(), df[\"g\"].max(), 100)\nax.plot(xs, alpha + beta * xs, color=\"red\", label=f\"OLS: du = {alpha:.3f} {beta:+.3f} g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (%, q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(\"Okun's law, U.S. 1960Q1-2019Q4 (n=240)\"); ax.legend()\nfig.tight_layout(); fig.savefig(\"out/figure1.png\", dpi=120)\nprint(json.dumps({k: res[k] for k in [\"beta_hat\", \"se_iid\", \"se_hac\", \"hac_lags\", \"beta_ci_low\", \"beta_ci_high\", \"okun_negative_5pct\"]}, indent=1))\n# Okun's law in U.S. quarterly data, 1960Q1–2019Q4 (F2-conf-04)\n\n## Question\nHow strongly does the quarterly change in the U.S. unemployment rate move with quarterly real GDP growth? The target is the slope β in the linear projection Δu_t = α + β g_t + e_t. Here u_t is the average of the three monthly UNRATE values in quarter t (in pp), and g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) is growth in percent, quarter on quarter and not annualised. The sample is 1960Q1–2019Q4. The standard error must stay valid when the errors are serially correlated. β describes an association. It is not a causal effect.\n\n## Data and exclusions\n- `data/UNRATE.csv` has 945 monthly rows and `data/GDPC1.csv` has 319 quarterly rows (`n_input_rows`). Both SHA-256 checksums match `data/README.md` (see `out/state/data_audit.md`).\n- One data problem was found: UNRATE for 2025-10 is an empty field. It falls outside the window, so it does not affect the estimates (`data_issues`).\n- Exclusion ledger (`out/exclusions.csv`, counted in quarters):\n - Start with the 319 GDPC1 quarters. Keep only quarters with a complete 3-month UNRATE average: 5 removed (1947Q1–Q4 and 2025Q4), 314 left.\n - Restrict to 1959Q4–2019Q4: 73 removed, 241 left.\n - Drop the 1959Q4 base quarter after differencing: 1 removed, 240 left.\n- The regression uses `n_analysed` = 240 quarters, from `first_quarter` = 1960Q1 to `last_quarter` = 2019Q4. No observation after 2019Q4 enters the regression.\n\n## Method\n- **Baseline:** OLS of Δu_t on a constant and g_t, with the conventional homoskedastic, independent-errors standard error (`se_iid`).\n- **Main inference:** the same OLS point estimate with a Newey–West HAC standard error (Bartlett kernel), no small-sample degrees-of-freedom correction (`se_hac`).\n- **Bandwidth:** `hac_lags` = 4. This is the Newey–West (1994) rule of thumb floor(4·(T/100)^{2/9}) with T = 240, fixed before looking at results. A lag window of about one year also fits quarterly macro data.\n- **Confidence interval and test:** the 95% CI is β̂ ± 1.96·`se_hac`, using the asymptotic normal critical value. `okun_negative_5pct` is true only if β̂ < 0 and the two-sided HAC test of β = 0 has p < 0.05.\n- **Code check:** the HAC sandwich was also computed by hand in `out/analysis.py` and asserted equal to the statsmodels result.\n- No randomness is involved (`random_seed` = null). `out/analysis.py` also produces `out/figure1.png` (scatter of Δu_t against g_t with the fitted line).\n\n## Results\n- **Slope:** `beta_hat` = −0.2558. One extra percentage point of quarterly real GDP growth goes with a 0.256 pp smaller quarterly change in the unemployment rate.\n- **Intercept and fit:** `alpha_hat` = 0.1844 pp and `r_squared` = 0.408.\n- **Mean growth:** `mean_growth` = 0.754 percent per quarter.\n- **Significance:** the Okun coefficient is negative and significant at the 5% level (`okun_negative_5pct` = true). The HAC t-statistic is −7.14 (`t_stat_hac`), with p ≈ 9.5e−13 (`p_value_hac`).\n\n## Uncertainty\n- **Standard errors:** `se_iid` = 0.0200 and `se_hac` = 0.0358 (`hac_lags` = 4).\n- **Why they differ:** the OLS residuals are positively autocorrelated, with lag-1 autocorrelation 0.39 (`residual_acf_lag1`). Because of that, the HAC SE is about 1.8 times the naive SE.\n- **Confidence intervals:**\n - 95% HAC CI: [`beta_ci_low`, `beta_ci_high`] = [−0.326, −0.186].\n - Naive 95% CI, shown for comparison only: [`beta_ci_iid_low`, `beta_ci_iid_high`] = [−0.295, −0.217]. It is too narrow.\n- **Bandwidth sensitivity** (`se_hac_by_lags`): across L ∈ {0, 1, 2, 4, 6, 8, 12} the HAC SE ranges from 0.0288 to 0.0371. Every choice gives a CI well away from zero, so the conclusion does not depend on the bandwidth.\n\n## Limitations and open issues\n- **Data vintage:** this is the current data vintage, not real-time data. Revisions to GDP could change the estimate in other vintages.\n- **Interpretation:** β is a reduced-form projection coefficient, not a structural or causal parameter. It assumes the relationship is stable over 1960–2019, and the possibility of breaks across decades was not examined, because the task fixes the window.\n- **Inference choices:** the HAC inference is asymptotic, with a normal critical value and no small-sample correction. Fixed-b critical values or a small-sample correction would widen the interval slightly. With |t| > 7, this would not change the conclusion.\n- **Measurement:** Δu is built from quarterly averages of monthly data. This time-averaging itself creates serial correlation, which is one reason to use HAC errors.\n- Nothing in the task was infeasible (`feasibility` = \"complete\").\nstep,rule,n_before,n_after,n_removed,rationale\nmerge_unrate,\"keep GDPC1 quarters with a complete (3-month, non-missing) UNRATE quarterly average\",319,314,5,\"UNRATE (945 monthly rows) averaged to quarters; 1947 has no UNRATE, 2025Q4 lacks Oct-2025 value\"\nwindow,keep 1959Q4-2019Q4 (1959Q4 only for differencing),314,241,73,\"information rule: fixed sample window, no extension\"\ndifferencing,drop 1959Q4 (levels used only to form 1960Q1 differences),241,240,1,first difference unavailable for base quarter\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json\ndata/UNRATE.csv:935:2025-10-01,","is_error":false}]},"uuid":"25aa6e73-8912-4804-a71c-8bf4f983e1f1","timestamp":"2026-10-30T05:06:12.772Z","toolUseResult":{"stdout":"\"\"\"Okun's law, U.S. 1960Q1-2019Q4, OLS with Newey-West HAC SE. Run from workspace root.\"\"\"\nimport json, math\nimport numpy as np, pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nFIRST, LAST = pd.Period(\"1960Q1\", \"Q\"), pd.Period(\"2019Q4\", \"Q\")\nissues, excl = [], []\n\nu_raw = pd.read_csv(\"data/UNRATE.csv\")\ng_raw = pd.read_csv(\"data/GDPC1.csv\")\nn_rows = {\"UNRATE.csv\": int(len(u_raw)), \"GDPC1.csv\": int(len(g_raw))}\n\n# --- unemployment: monthly -> quarterly average\nu = u_raw.copy()\nu[\"date\"] = pd.to_datetime(u[\"observation_date\"])\nu[\"UNRATE\"] = pd.to_numeric(u[\"UNRATE\"], errors=\"coerce\")\nmiss = u.loc[u[\"UNRATE\"].isna(), \"observation_date\"].tolist()\nif miss:\n issues.append({\"issue\": f\"UNRATE missing value(s) at {', '.join(miss)}\",\n \"handling\": \"outside the 1959Q4-2019Q4 span needed; dropped by window filter, no effect on estimates\"})\nu[\"q\"] = u[\"date\"].dt.to_period(\"Q\")\n# quarterly average only for quarters with all 3 monthly values present\ncnt_all = u.groupby(\"q\")[\"UNRATE\"].count()\nuq_all = u.groupby(\"q\")[\"UNRATE\"].mean()[cnt_all == 3]\n\n# --- GDP\ng = g_raw.copy()\ng[\"q\"] = pd.to_datetime(g[\"observation_date\"]).dt.to_period(\"Q\")\ng[\"GDPC1\"] = pd.to_numeric(g[\"GDPC1\"], errors=\"coerce\")\nassert g[\"GDPC1\"].notna().all() and not g[\"q\"].duplicated().any()\ngq = g.set_index(\"q\")[\"GDPC1\"]\n\n# Exclusion ledger in quarterly units, starting from the 319 GDPC1 quarters\npanel = pd.DataFrame({\"y\": gq})\nn0 = len(panel)\npanel[\"u\"] = uq_all.reindex(panel.index)\npanel = panel.dropna()\nexcl.append((\"merge_unrate\", \"keep GDPC1 quarters with a complete (3-month, non-missing) UNRATE quarterly average\",\n n0, len(panel), n0 - len(panel),\n \"UNRATE (945 monthly rows) averaged to quarters; 1947 has no UNRATE, 2025Q4 lacks Oct-2025 value\"))\nn0 = len(panel)\npanel = panel.loc[FIRST - 1:LAST]\nexcl.append((\"window\", \"keep 1959Q4-2019Q4 (1959Q4 only for differencing)\", n0, len(panel), n0 - len(panel),\n \"information rule: fixed sample window, no extension\"))\nassert len(panel) == 241 and (cnt_all.loc[FIRST - 1:LAST] == 3).all()\ndf = panel.sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"y\"] / df[\"y\"].shift(1))\nn0 = len(df)\ndf = df.loc[FIRST:LAST].dropna()\nexcl.append((\"differencing\", \"drop 1959Q4 (levels used only to form 1960Q1 differences)\", n0, len(df), n0 - len(df),\n \"first difference unavailable for base quarter\"))\nT = len(df)\nassert T == 240\n\nX = sm.add_constant(df[\"g\"].values)\ny = df[\"du\"].values\nols = sm.OLS(y, X).fit()\n# Newey-West (1994) plug-in rule of thumb: floor(4*(T/100)^(2/9))\nL = int(math.floor(4 * (T / 100) ** (2 / 9)))\nhac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": False})\n\n# manual check of HAC SE\ne = ols.resid; Xe = X * e[:, None]\nS = Xe.T @ Xe\nfor j in range(1, L + 1):\n w = 1 - j / (L + 1); G = Xe[j:].T @ Xe[:-j]; S += w * (G + G.T)\nXtXi = np.linalg.inv(X.T @ X)\nse_manual = float(np.sqrt((XtXi @ S @ XtXi)[1, 1]))\nassert abs(se_manual - hac.bse[1]) < 1e-10\n\nbeta, alpha = float(ols.params[1]), float(ols.params[0])\nse_hac = float(hac.bse[1]); z = stats.norm.ppf(0.975)\nlo, hi = beta - z * se_hac, beta + z * se_hac\np_hac = float(2 * stats.norm.sf(abs(beta / se_hac)))\n\nsens = {}\nfor l in [0, 1, 2, 4, 6, 8, 12]:\n r = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": l, \"kernel\": \"bartlett\", \"use_correction\": False})\n sens[str(l)] = float(r.bse[1])\n\nres = {\n \"task_id\": \"F2-conf-04\",\n \"beta_hat\": beta, \"alpha_hat\": alpha, \"r_squared\": float(ols.rsquared),\n \"se_iid\": float(ols.bse[1]), \"se_hac\": se_hac, \"hac_lags\": L,\n \"beta_ci_low\": float(lo), \"beta_ci_high\": float(hi),\n \"okun_negative_5pct\": bool(beta < 0 and p_hac < 0.05),\n \"mean_growth\": float(df[\"g\"].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\": issues, \"n_input_rows\": n_rows, \"random_seed\": None,\n # supplementary\n \"t_stat_hac\": float(beta / se_hac), \"p_value_hac\": p_hac,\n \"residual_acf_lag1\": float(pd.Series(e).autocorr(1)),\n \"se_hac_by_lags\": sens,\n \"beta_ci_iid_low\": float(beta - z * ols.bse[1]), \"beta_ci_iid_high\": float(beta + z * ols.bse[1]),\n}\nwith open(\"out/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\"out/exclusions.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(6.5, 4.5))\nax.scatter(df[\"g\"], df[\"du\"], s=12, alpha=0.6)\nxs = np.linspace(df[\"g\"].min(), df[\"g\"].max(), 100)\nax.plot(xs, alpha + beta * xs, color=\"red\", label=f\"OLS: du = {alpha:.3f} {beta:+.3f} g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (%, q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(\"Okun's law, U.S. 1960Q1-2019Q4 (n=240)\"); ax.legend()\nfig.tight_layout(); fig.savefig(\"out/figure1.png\", dpi=120)\nprint(json.dumps({k: res[k] for k in [\"beta_hat\", \"se_iid\", \"se_hac\", \"hac_lags\", \"beta_ci_low\", \"beta_ci_high\", \"okun_negative_5pct\"]}, indent=1))\n# Okun's law in U.S. quarterly data, 1960Q1–2019Q4 (F2-conf-04)\n\n## Question\nHow strongly does the quarterly change in the U.S. unemployment rate move with quarterly real GDP growth? The target is the slope β in the linear projection Δu_t = α + β g_t + e_t. Here u_t is the average of the three monthly UNRATE values in quarter t (in pp), and g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) is growth in percent, quarter on quarter and not annualised. The sample is 1960Q1–2019Q4. The standard error must stay valid when the errors are serially correlated. β describes an association. It is not a causal effect.\n\n## Data and exclusions\n- `data/UNRATE.csv` has 945 monthly rows and `data/GDPC1.csv` has 319 quarterly rows (`n_input_rows`). Both SHA-256 checksums match `data/README.md` (see `out/state/data_audit.md`).\n- One data problem was found: UNRATE for 2025-10 is an empty field. It falls outside the window, so it does not affect the estimates (`data_issues`).\n- Exclusion ledger (`out/exclusions.csv`, counted in quarters):\n - Start with the 319 GDPC1 quarters. Keep only quarters with a complete 3-month UNRATE average: 5 removed (1947Q1–Q4 and 2025Q4), 314 left.\n - Restrict to 1959Q4–2019Q4: 73 removed, 241 left.\n - Drop the 1959Q4 base quarter after differencing: 1 removed, 240 left.\n- The regression uses `n_analysed` = 240 quarters, from `first_quarter` = 1960Q1 to `last_quarter` = 2019Q4. No observation after 2019Q4 enters the regression.\n\n## Method\n- **Baseline:** OLS of Δu_t on a constant and g_t, with the conventional homoskedastic, independent-errors standard error (`se_iid`).\n- **Main inference:** the same OLS point estimate with a Newey–West HAC standard error (Bartlett kernel), no small-sample degrees-of-freedom correction (`se_hac`).\n- **Bandwidth:** `hac_lags` = 4. This is the Newey–West (1994) rule of thumb floor(4·(T/100)^{2/9}) with T = 240, fixed before looking at results. A lag window of about one year also fits quarterly macro data.\n- **Confidence interval and test:** the 95% CI is β̂ ± 1.96·`se_hac`, using the asymptotic normal critical value. `okun_negative_5pct` is true only if β̂ < 0 and the two-sided HAC test of β = 0 has p < 0.05.\n- **Code check:** the HAC sandwich was also computed by hand in `out/analysis.py` and asserted equal to the statsmodels result.\n- No randomness is involved (`random_seed` = null). `out/analysis.py` also produces `out/figure1.png` (scatter of Δu_t against g_t with the fitted line).\n\n## Results\n- **Slope:** `beta_hat` = −0.2558. One extra percentage point of quarterly real GDP growth goes with a 0.256 pp smaller quarterly change in the unemployment rate.\n- **Intercept and fit:** `alpha_hat` = 0.1844 pp and `r_squared` = 0.408.\n- **Mean growth:** `mean_growth` = 0.754 percent per quarter.\n- **Significance:** the Okun coefficient is negative and significant at the 5% level (`okun_negative_5pct` = true). The HAC t-statistic is −7.14 (`t_stat_hac`), with p ≈ 9.5e−13 (`p_value_hac`).\n\n## Uncertainty\n- **Standard errors:** `se_iid` = 0.0200 and `se_hac` = 0.0358 (`hac_lags` = 4).\n- **Why they differ:** the OLS residuals are positively autocorrelated, with lag-1 autocorrelation 0.39 (`residual_acf_lag1`). Because of that, the HAC SE is about 1.8 times the naive SE.\n- **Confidence intervals:**\n - 95% HAC CI: [`beta_ci_low`, `beta_ci_high`] = [−0.326, −0.186].\n - Naive 95% CI, shown for comparison only: [`beta_ci_iid_low`, `beta_ci_iid_high`] = [−0.295, −0.217]. It is too narrow.\n- **Bandwidth sensitivity** (`se_hac_by_lags`): across L ∈ {0, 1, 2, 4, 6, 8, 12} the HAC SE ranges from 0.0288 to 0.0371. Every choice gives a CI well away from zero, so the conclusion does not depend on the bandwidth.\n\n## Limitations and open issues\n- **Data vintage:** this is the current data vintage, not real-time data. Revisions to GDP could change the estimate in other vintages.\n- **Interpretation:** β is a reduced-form projection coefficient, not a structural or causal parameter. It assumes the relationship is stable over 1960–2019, and the possibility of breaks across decades was not examined, because the task fixes the window.\n- **Inference choices:** the HAC inference is asymptotic, with a normal critical value and no small-sample correction. Fixed-b critical values or a small-sample correction would widen the interval slightly. With |t| > 7, this would not change the conclusion.\n- **Measurement:** Δu is built from quarterly averages of monthly data. This time-averaging itself creates serial correlation, which is one reason to use HAC errors.\n- Nothing in the task was infeasible (`feasibility` = \"complete\").\nstep,rule,n_before,n_after,n_removed,rationale\nmerge_unrate,\"keep GDPC1 quarters with a complete (3-month, non-missing) UNRATE quarterly average\",319,314,5,\"UNRATE (945 monthly rows) averaged to quarters; 1947 has no UNRATE, 2025Q4 lacks Oct-2025 value\"\nwindow,keep 1959Q4-2019Q4 (1959Q4 only for differencing),314,241,73,\"information rule: fixed sample window, no extension\"\ndifferencing,drop 1959Q4 (levels used only to form 1960Q1 differences),241,240,1,first difference unavailable for base quarter\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json\ndata/UNRATE.csv:935:2025-10-01,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6b49064f-6c3b-4513-b252-c2758918ff4c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"94231bc2a81e719a95a669dd6069e4f6ec4f3ff6274beecf6137ff365970c594","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01T6rhN9XdJx91hyJh2XpCkU","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/exclusions.csv; ls out/state; grep -n \",$\\|,\\s*$\" data/*.csv | head","description":"Read code, report, exclusions"}}]}}22{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"a3c57be1-c4b4-40eb-af80-930c6f1466e2","timestamp":"2026-10-30T05:06:12.775Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":"01c34eef-6293-4562-967d-d121dd0a42e0","keep":4,"tail":["94231bc2a81e719a95a669dd6069e4f6ec4f3ff6274beecf6137ff365970c594","a983086abb38e6eec45e0b9dd9e5198e17d81d8bd6a376786e901e9670325c5d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0c07245c2088923dc12b97a60682badae2a893e26f860303cb31300266ece699"}23{"parentUuid":"25aa6e73-8912-4804-a71c-8bf4f983e1f1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqh2VCqnSQbTT11T99f","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSggkKEAgTGAI4AUIIdGhpbmtpbmcSDAuh8voi1N9Qydfi2hoMwCt7qecwOt4mkgrbIjBhI+AY4CeoUsUhqEpTlEk3j5InmhuQ1TW5oWkC+j0dwROwApG/k6TVe/UZOKczblcqnwi8ahVHoWsmcjq42IrmWBykJAK9ttorTonyYkTd9b8GfQxym5opQdUf74YlsKKeBeTDSLLK+iQBtK1Z96xnZExNOqt0gYNWD2lSQ41UVg1+qAqUkyLYLij/mZSVwNbabuypJuESQzUuFgE3IeXEHfGv4NfaZsDFiREnYR6JDZj7xfpdw/0em6uxUjjJUAq1Krw1DUB0xwrD8aZUXbuHKpvI12iPdKG9Ih0dtQkUrf/aPl8YWIlVa7Jy8GD/pwJBI3KRTe+Wdb+Wo4JpNc+IXFa/8BKJpthkGYpUiRW6/dkgn8ZyJ5OUingDcVdFgWATfkPTk1FNHA8EhUHL/VF31HS9D2A8dXjTOo04NZdxyqQ2GlzxOK0BD0moT+nW1V8BsbwGC1E4lxQBpeh+JA9WrX/4KabwQwfvRc6TeAv71yW2/groEpMMmu3jx9ub8fcAj93qpJO4qYCQyy0txF4x8M4gdJ7oRiC5ShJRJ87XI8evSr37Cy21wiSBa1p7OMIZjRGAacAFs6SpfWurc7EWb1AUwjJDQ9L3SLj0pfltNoBQV/Tm/QDwdGLcukNQHH+NZTai2+pkqM6YVPn8wsoXty39o5I8d8eQv5StERfgaBY9CTi4MLA1u2ZkL5SN5FH+dZ7wDbw1ODxJ0xPWfCh2EEewxnFW4D32+AU8a1koWOJc6TgwbRUhEaBgTdQDB1qM/+EMxmbbOVb3rhMmF1eC1jfL9eN9t2erVsSugBq+0wobgIswL+lgzVSq5yj6o8HgN4EbJGdT7z61m7IkOdvP9IlsZ7VztXhGE/YWJg32zD0rjbfj5u4gteAejzVq96K1c4lECLqcyN20JO3h80vL7Vi833T+TLvH2tyB1fE14gPYSetQiBwuYm5nQEeR4cV1I0vOOPILa0DlvWWtAiR+IYgfCBgbTfocbrqJg5Z3kcrWV877gzB8tBE11ZDtDbDxFy3wWzfvzezBLb0rN1OqHiAQZ/WXhMSre/fcD0Nar/z36vqFztWc9UXpVIJ5M2QE8r6fR+Po8SXUqqd3xUKVHctCqDO5b2KUlYrfJrhiV/5h2F2zW03J6aSgsZC8+DugXz+VUjjopth7p29WoP27J0fW+fowKrNFpsdNz/kRlAfVJ5SmyyPpsM9vkChwqnJavre0ys0NLzhfMn6xoJxCYeo5XCeRIW3O/99J2vdiNZ9jxwP/k6qSj987ckZDXc76nwUB1zFmArifClOwCAeGbLrwfDirgauEwzJ+n29cxI2c6W5JZQGN0VCSbIBli5xfuSXUsvYGyT4hIlt0UcoCfA8djGiGIOHTBGD/8lVzPduT1sQ42PeEOdZ2NZhbmrxvdWGvx14BteSmChgNtLcPaDVNhT6MO28xYShqoz/2Hs3VcmNGBYmfRA1H+YMFKNRCqBgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5188,"cache_read_input_tokens":5977,"output_tokens":844,"output_tokens_details":{"thinking_tokens":243},"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":5188},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2197,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqh2Dq4tuUefR3gd8EZ","requestRef":"a3c57be1-c4b4-40eb-af80-930c6f1466e2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"694fdb07-19ba-4f72-bda5-f282d2c18fe8","timestamp":"2026-10-30T05:06:16.508Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"694fdb07-19ba-4f72-bda5-f282d2c18fe8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqh2VCqnSQbTT11T99f","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DpyNdgwUDmS3uftbJ2GVwN","name":"Bash","input":{"command":"cd $(mktemp -d) && cp -r ~/wp29/runs/RC0218/data . && mkdir out && cp ~/wp29/runs/RC0218/out/analysis.py out/ && ~/wp29/venv/bin/python out/analysis.py >/dev/null && diff <(python3 -m json.tool out/results.json) <(python3 -m json.tool ~/wp29/runs/RC0218/out/results.json) && echo SAME\n~/wp29/venv/bin/python - <<'E'\nimport pandas as pd,numpy as np\nu=pd.read_csv(\"data/UNRATE.csv\",parse_dates=[0]);g=pd.read_csv(\"data/GDPC1.csv\",parse_dates=[0])\nuq=u.set_index(\"observation_date\").UNRATE.resample(\"QS\").mean()\ngq=g.set_index(\"observation_date\").GDPC1\ndu=uq.diff();gg=100*np.log(gq).diff()\nd=pd.concat([du,gg],axis=1).loc[\"1960-01-01\":\"2019-10-01\"]\nd.columns=[\"du\",\"g\"];print(len(d))\nb=np.polyfit(d.g,d.du,1);print(b,d.g.mean(),np.corrcoef(d.g,d.du)[0,1]**2)\nimport statsmodels.api as sm\nr=sm.OLS(d.du,sm.add_constant(d.g)).fit(cov_type=\"HAC\",cov_kwds={\"maxlags\":4,\"use_correction\":True});print(r.bse)\nE","description":"Re-run analysis in scratch and verify independently"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5188,"cache_read_input_tokens":5977,"output_tokens":844,"output_tokens_details":{"thinking_tokens":243},"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":5188},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqh2Dq4tuUefR3gd8EZ","requestRef":"a3c57be1-c4b4-40eb-af80-930c6f1466e2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d7d1cdd7-ba42-4ec6-88cc-59fe4fedf069","timestamp":"2026-10-30T05:06:20.652Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"d7d1cdd7-ba42-4ec6-88cc-59fe4fedf069","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DpyNdgwUDmS3uftbJ2GVwN","type":"tool_result","content":"SAME\n240\n[-0.25576773 0.18438835] 0.753502755065237 0.40825082845620336\nconst 0.043854\ng 0.035985\ndtype: float64\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RC0218","is_error":false}]},"uuid":"d94ae60a-40b8-445d-84c5-6a4e04a36717","timestamp":"2026-10-30T05:06:22.722Z","toolUseResult":{"stdout":"SAME\n240\n[-0.25576773 0.18438835] 0.753502755065237 0.40825082845620336\nconst 0.043854\ng 0.035985\ndtype: float64","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RC0218","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d7d1cdd7-ba42-4ec6-88cc-59fe4fedf069","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"2f810f17f61a21faecaab3bb8a89fb073ccf4a88774026319597fd8afb97f63b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01DpyNdgwUDmS3uftbJ2GVwN","name":"Bash","input":{"command":"cd $(mktemp -d) && cp -r ~/wp29/runs/RC0218/data . && mkdir out && cp ~/wp29/runs/RC0218/out/analysis.py out/ && ~/wp29/venv/bin/python out/analysis.py >/dev/null && diff <(python3 -m json.tool out/results.json) <(python3 -m json.tool ~/wp29/runs/RC0218/out/results.json) && echo SAME\n~/wp29/venv/bin/python - <<'E'\nimport pandas as pd,numpy as np\nu=pd.read_csv(\"data/UNRATE.csv\",parse_dates=[0]);g=pd.read_csv(\"data/GDPC1.csv\",parse_dates=[0])\nuq=u.set_index(\"observation_date\").UNRATE.resample(\"QS\").mean()\ngq=g.set_index(\"observation_date\").GDPC1\ndu=uq.diff();gg=100*np.log(gq).diff()\nd=pd.concat([du,gg],axis=1).loc[\"1960-01-01\":\"2019-10-01\"]\nd.columns=[\"du\",\"g\"];print(len(d))\nb=np.polyfit(d.g,d.du,1);print(b,d.g.mean(),np.corrcoef(d.g,d.du)[0,1]**2)\nimport statsmodels.api as sm\nr=sm.OLS(d.du,sm.add_constant(d.g)).fit(cov_type=\"HAC\",cov_kwds={\"maxlags\":4,\"use_correction\":True});print(r.bse)\nE","description":"Re-run analysis in scratch and verify independently"}}]}}27{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"fe7ff3bf-bbd7-4384-ad42-d4f0ef190005","timestamp":"2026-10-30T05:06:22.725Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":"a3c57be1-c4b4-40eb-af80-930c6f1466e2","keep":6,"tail":["2f810f17f61a21faecaab3bb8a89fb073ccf4a88774026319597fd8afb97f63b","9cd8f86926f3c4f5c2e0188d601322c387e14d1fd5b204772be39de1cb1b9328"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"13a525b508d82b07811239bc1da03e4806667d72af12d7259ec6d2f3c14b3117"}28{"type":"last-prompt","lastPrompt":"Review","leafUuid":"d94ae60a-40b8-445d-84c5-6a4e04a36717","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}29{"type":"atis-latch","atis":"","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}30{"type":"tools-used","tools":["Bash","Read"],"sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}31{"parentUuid":"d94ae60a-40b8-445d-84c5-6a4e04a36717","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqhkwrMihNfWbGUTCFd","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":943,"cache_read_input_tokens":11165,"output_tokens":384,"output_tokens_details":{"thinking_tokens":182},"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":943},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1278,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqhkkwfq811DJPoHoyy","requestRef":"fe7ff3bf-bbd7-4384-ad42-d4f0ef190005","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"371297ae-e2f4-4320-9afe-8b21543e1eae","timestamp":"2026-10-30T05:06:25.286Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"371297ae-e2f4-4320-9afe-8b21543e1eae","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqhkwrMihNfWbGUTCFd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KfHk8k26EAsEB2G9XubJpP","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0218/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":943,"cache_read_input_tokens":11165,"output_tokens":384,"output_tokens_details":{"thinking_tokens":182},"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":943},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqhkkwfq811DJPoHoyy","requestRef":"fe7ff3bf-bbd7-4384-ad42-d4f0ef190005","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1fc5237b-4505-40c1-ad0e-456113fe3bc1","timestamp":"2026-10-30T05:06:25.792Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}33{"parentUuid":"1fc5237b-4505-40c1-ad0e-456113fe3bc1","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KfHk8k26EAsEB2G9XubJpP","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"7711240a-48f7-4854-b48b-2854f4a95b8c","timestamp":"2026-10-30T05:06:25.799Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":53105,"dimensions":{"originalWidth":780,"originalHeight":540,"displayWidth":780,"displayHeight":540}}},"sourceToolAssistantUUID":"1fc5237b-4505-40c1-ad0e-456113fe3bc1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}34{"parentUuid":"7711240a-48f7-4854-b48b-2854f4a95b8c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqhkwrMihNfWbGUTCFd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0133c2RjUNKy5dY5ZG2wXRCC","name":"Bash","input":{"command":"cat out/state/data_audit.md | head -30; cd data && shasum -a 256 *.csv; grep -i sha -A3 README.md | head","description":"Check data audit and checksums"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":943,"cache_read_input_tokens":11165,"output_tokens":384,"output_tokens_details":{"thinking_tokens":182},"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":943},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXqhkkwfq811DJPoHoyy","requestRef":"fe7ff3bf-bbd7-4384-ad42-d4f0ef190005","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dead3393-0ef9-471d-8a2a-d71aaf6adbcc","timestamp":"2026-10-30T05:06:26.533Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}35{"parentUuid":"dead3393-0ef9-471d-8a2a-d71aaf6adbcc","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0133c2RjUNKy5dY5ZG2wXRCC","type":"tool_result","content":"# Data audit\n| file | SHA-256 (computed) | matches README | data rows | cols | date range | missing | dup dates | gaps |\n|---|---|---|---|---|---|---|---|---|\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | yes | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01 monthly | 1 (2025-10-01 empty field) | 0 | 0 |\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | yes | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01 quarterly | 0 | 0 | 0 |\n\nUnits: UNRATE percent (SA); GDPC1 billions chained 2017 $, SAAR. Ranges: UNRATE 2.5–14.8; GDPC1 2172.4–24611.1. All dates are first-of-period, monotonic increasing.\n\nAnomalies: UNRATE 2025-10 is missing (empty field; no October 2025 household survey release). It lies outside the 1959Q4–2019Q4 span needed, so it has no effect; it is recorded in `data_issues` and removed by the window filter. analysis.py additionally asserts every quarter in 1959Q4–2019Q4 has exactly 3 non-missing months.\n\nInformation availability: files contain data after 2019Q4 (and before 1959Q4); these are excluded by the window filter (see out/exclusions.csv). No other violations.\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 GDPC1.csv\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c UNRATE.csv\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` |","is_error":false}]},"uuid":"35679a96-f8ec-430c-8872-bdb18de57344","timestamp":"2026-10-30T05:06:26.578Z","toolUseResult":{"stdout":"# Data audit\n| file | SHA-256 (computed) | matches README | data rows | cols | date range | missing | dup dates | gaps |\n|---|---|---|---|---|---|---|---|---|\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | yes | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01 monthly | 1 (2025-10-01 empty field) | 0 | 0 |\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | yes | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01 quarterly | 0 | 0 | 0 |\n\nUnits: UNRATE percent (SA); GDPC1 billions chained 2017 $, SAAR. Ranges: UNRATE 2.5–14.8; GDPC1 2172.4–24611.1. All dates are first-of-period, monotonic increasing.\n\nAnomalies: UNRATE 2025-10 is missing (empty field; no October 2025 household survey release). It lies outside the 1959Q4–2019Q4 span needed, so it has no effect; it is recorded in `data_issues` and removed by the window filter. analysis.py additionally asserts every quarter in 1959Q4–2019Q4 has exactly 3 non-missing months.\n\nInformation availability: files contain data after 2019Q4 (and before 1959Q4); these are excluded by the window filter (see out/exclusions.csv). No other violations.\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 GDPC1.csv\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c UNRATE.csv\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` |","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"dead3393-0ef9-471d-8a2a-d71aaf6adbcc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218/data","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}36{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"a9321038a4c2ba25181f4a494496516ad7b0c3114e542e50bf938a74c6e9ed8c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KfHk8k26EAsEB2G9XubJpP","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0218/out/figure1.png"}},{"type":"tool_use","id":"toolu_0133c2RjUNKy5dY5ZG2wXRCC","name":"Bash","input":{"command":"cat out/state/data_audit.md | head -30; cd data && shasum -a 256 *.csv; grep -i sha -A3 README.md | head","description":"Check data audit and checksums"}}]}}37{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"2a1e3b873acffed4c0f8545e21f00770ea143e1bfa961dacee2c6dc94033fca4","message":{"role":"user","content":[{"tool_use_id":"toolu_01KfHk8k26EAsEB2G9XubJpP","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]},{"tool_use_id":"toolu_0133c2RjUNKy5dY5ZG2wXRCC","type":"tool_result","content":"# Data audit\n| file | SHA-256 (computed) | matches README | data rows | cols | date range | missing | dup dates | gaps |\n|---|---|---|---|---|---|---|---|---|\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | yes | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01 monthly | 1 (2025-10-01 empty field) | 0 | 0 |\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | yes | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01 quarterly | 0 | 0 | 0 |\n\nUnits: UNRATE percent (SA); GDPC1 billions chained 2017 $, SAAR. Ranges: UNRATE 2.5–14.8; GDPC1 2172.4–24611.1. All dates are first-of-period, monotonic increasing.\n\nAnomalies: UNRATE 2025-10 is missing (empty field; no October 2025 household survey release). It lies outside the 1959Q4–2019Q4 span needed, so it has no effect; it is recorded in `data_issues` and removed by the window filter. analysis.py additionally asserts every quarter in 1959Q4–2019Q4 has exactly 3 non-missing months.\n\nInformation availability: files contain data after 2019Q4 (and before 1959Q4); these are excluded by the window filter (see out/exclusions.csv). No other violations.\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 GDPC1.csv\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c UNRATE.csv\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` |","is_error":false}]}}38{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"841d6f51-b0b5-4e59-9e56-fccc317b97cd","timestamp":"2026-10-30T05:06:26.582Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":"fe7ff3bf-bbd7-4384-ad42-d4f0ef190005","keep":8,"tail":["a9321038a4c2ba25181f4a494496516ad7b0c3114e542e50bf938a74c6e9ed8c","2a1e3b873acffed4c0f8545e21f00770ea143e1bfa961dacee2c6dc94033fca4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"ae6ece325770147ae7f29860b39be1a2a6f93218e002b0b164e9219e09cd8969"}39{"type":"last-prompt","lastPrompt":"Review","leafUuid":"35679a96-f8ec-430c-8872-bdb18de57344","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}40{"type":"atis-latch","atis":"","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}41{"parentUuid":"35679a96-f8ec-430c-8872-bdb18de57344","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqi3SHyUyx2ZLxBNdn4","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":2050,"cache_read_input_tokens":12108,"output_tokens":1259,"output_tokens_details":{"thinking_tokens":145},"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":2050},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1217,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqi3F8ETBXsZ1G5HFMh","requestRef":"841d6f51-b0b5-4e59-9e56-fccc317b97cd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"47dd86e2-117d-41ff-8c4c-7dc9e49504c2","timestamp":"2026-10-30T05:06:29.275Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218/data","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"47dd86e2-117d-41ff-8c4c-7dc9e49504c2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqi3SHyUyx2ZLxBNdn4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CZw6EurERaWNJrYJ4gt9LX","name":"Bash","input":{"command":"cat > out/review/review.json <<'E'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"results.json:data_issues / analysis.py\",\n \"issue\": \"The handling text for the missing 2025-10 UNRATE value is a fixed string, and it says the row is 'dropped by window filter'. In the code, 2025Q4 is actually removed at the earlier merge_unrate step (complete-quarter requirement), as exclusions.csv correctly records. The text is also written regardless of where a missing value falls. The assert that all quarters from 1959Q4 to 2019Q4 have 3 months guards the estimates, so the results are unaffected.\",\n \"suggested_fix\": \"Say that the quarter is removed by the complete-quarter merge step, and build the handling text conditionally on whether the missing date lies inside the window.\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"report.md: Method (bandwidth)\",\n \"issue\": \"The report says the bandwidth was 'fixed before looking at results'. This cannot be checked from the deliverables. The rule itself (floor(4(T/100)^{2/9}) = 4 for T=240) is computed correctly and is standard.\",\n \"suggested_fix\": \"Drop the claim, or point to a pre-registration record.\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"claims.json C4 / report Uncertainty\",\n \"issue\": \"The robustness check covers only Bartlett lags 0–12 with normal critical values. Fixed-b and small-sample variants were not computed. The report admits this, and with |t| ≈ 6.9 or more at every bandwidth the conclusion is very unlikely to change. The statement that fixed-b would 'widen the interval slightly' is asserted, not shown.\",\n \"suggested_fix\": \"Optionally report a fixed-b or df-corrected interval, or phrase the statement as an expectation.\"\n }\n ],\n \"summary\": \"The deliverables are complete and reproducible. Re-running analysis.py in a scratch copy reproduces results.json byte for byte. An independent calculation (resampled quarterly means, log differences, 1960Q1–2019Q4) gives the same beta_hat (-0.2558), alpha_hat (0.1844), R² (0.408), mean_growth (0.7535) and n = 240. The HAC SE is checked by a hand-coded sandwich, and the lag-4 rule is computed correctly. The code uses data only from 1959Q4 to 2019Q4, so the information rules are respected. Data checksums match the README. The iid baseline is present, the counts in the exclusion ledger are consistent (319→314→241→240), and the units and signs are correct. The claims match the numbers, and the limitations (current vintage, not causal, asymptotic inference, no break tests) are stated honestly. Only minor wording issues remain.\"\n}\nE\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON and validate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2050,"cache_read_input_tokens":12108,"output_tokens":1259,"output_tokens_details":{"thinking_tokens":145},"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":2050},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqi3F8ETBXsZ1G5HFMh","requestRef":"841d6f51-b0b5-4e59-9e56-fccc317b97cd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1edd7e0d-8234-466d-ab4d-3f9c37c6b4eb","timestamp":"2026-10-30T05:06:39.118Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218/data","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}43{"parentUuid":"1edd7e0d-8234-466d-ab4d-3f9c37c6b4eb","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n(eval):1: no such file or directory: out/review/review.json\nTraceback (most recent call last):\n File \"<frozen runpy>\", line 198, in _run_module_as_main\n File \"<frozen runpy>\", line 88, in _run_code\n File \"/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/lib/python3.14/json/tool.py\", line 119, in <module>\n main()\n ~~~~^^\n File \"/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/lib/python3.14/json/tool.py\", line 88, in main\n infile = open(options.infile, encoding='utf-8')\nFileNotFoundError: [Errno 2] No such file or directory: 'out/review/review.json'","is_error":true,"tool_use_id":"toolu_01CZw6EurERaWNJrYJ4gt9LX"}]},"uuid":"f84cdd7d-1968-4346-9dcc-1430dd48cb0c","timestamp":"2026-10-30T05:06:39.180Z","toolUseResult":"Error: Exit code 1\n(eval):1: no such file or directory: out/review/review.json\nTraceback (most recent call last):\n File \"<frozen runpy>\", line 198, in _run_module_as_main\n File \"<frozen runpy>\", line 88, in _run_code\n File \"/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/lib/python3.14/json/tool.py\", line 119, in <module>\n main()\n ~~~~^^\n File \"/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/lib/python3.14/json/tool.py\", line 88, in main\n infile = open(options.infile, encoding='utf-8')\nFileNotFoundError: [Errno 2] No such file or directory: 'out/review/review.json'","sandboxed":false,"sourceToolAssistantUUID":"1edd7e0d-8234-466d-ab4d-3f9c37c6b4eb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218/data","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}44{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"8c29e48d0cee25a1197abdbb95fe3ee8fcebaa179c50d3875ad48cb2c14599f5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01CZw6EurERaWNJrYJ4gt9LX","name":"Bash","input":{"command":"cat > out/review/review.json <<'E'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"results.json:data_issues / analysis.py\",\n \"issue\": \"The handling text for the missing 2025-10 UNRATE value is a fixed string, and it says the row is 'dropped by window filter'. In the code, 2025Q4 is actually removed at the earlier merge_unrate step (complete-quarter requirement), as exclusions.csv correctly records. The text is also written regardless of where a missing value falls. The assert that all quarters from 1959Q4 to 2019Q4 have 3 months guards the estimates, so the results are unaffected.\",\n \"suggested_fix\": \"Say that the quarter is removed by the complete-quarter merge step, and build the handling text conditionally on whether the missing date lies inside the window.\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"report.md: Method (bandwidth)\",\n \"issue\": \"The report says the bandwidth was 'fixed before looking at results'. This cannot be checked from the deliverables. The rule itself (floor(4(T/100)^{2/9}) = 4 for T=240) is computed correctly and is standard.\",\n \"suggested_fix\": \"Drop the claim, or point to a pre-registration record.\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"claims.json C4 / report Uncertainty\",\n \"issue\": \"The robustness check covers only Bartlett lags 0–12 with normal critical values. Fixed-b and small-sample variants were not computed. The report admits this, and with |t| ≈ 6.9 or more at every bandwidth the conclusion is very unlikely to change. The statement that fixed-b would 'widen the interval slightly' is asserted, not shown.\",\n \"suggested_fix\": \"Optionally report a fixed-b or df-corrected interval, or phrase the statement as an expectation.\"\n }\n ],\n \"summary\": \"The deliverables are complete and reproducible. Re-running analysis.py in a scratch copy reproduces results.json byte for byte. An independent calculation (resampled quarterly means, log differences, 1960Q1–2019Q4) gives the same beta_hat (-0.2558), alpha_hat (0.1844), R² (0.408), mean_growth (0.7535) and n = 240. The HAC SE is checked by a hand-coded sandwich, and the lag-4 rule is computed correctly. The code uses data only from 1959Q4 to 2019Q4, so the information rules are respected. Data checksums match the README. The iid baseline is present, the counts in the exclusion ledger are consistent (319→314→241→240), and the units and signs are correct. The claims match the numbers, and the limitations (current vintage, not causal, asymptotic inference, no break tests) are stated honestly. Only minor wording issues remain.\"\n}\nE\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON and validate"}}]}}45{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"e431c0df-45a2-4997-ac0e-6f748184e7af","timestamp":"2026-10-30T05:06:39.184Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":"841d6f51-b0b5-4e59-9e56-fccc317b97cd","keep":10,"tail":["8c29e48d0cee25a1197abdbb95fe3ee8fcebaa179c50d3875ad48cb2c14599f5","a015bf43717a157469b07c2d408efcf511b22bf9b1b1fcaaf9e474dd11d19957"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8e730f307fb3cc9e23a328458f65142467ec9840ecea0c75c6943ae9c8a92891"}46{"parentUuid":"f84cdd7d-1968-4346-9dcc-1430dd48cb0c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqiyNEri14FKrb2YGqv","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":1569,"cache_read_input_tokens":14158,"output_tokens":1196,"output_tokens_details":{"thinking_tokens":48},"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":1569},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":412,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqiy8qwVf5SeXH5NEum","requestRef":"e431c0df-45a2-4997-ac0e-6f748184e7af","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bcf88c28-5ddf-4572-a9a3-9d1309ca0527","timestamp":"2026-10-30T05:06:41.536Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218/data","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}47{"parentUuid":"bcf88c28-5ddf-4572-a9a3-9d1309ca0527","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqiyNEri14FKrb2YGqv","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Y1q6SFqcaCgFgWnhjyTzYD","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0218 && cat > out/review/review.json <<'E'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"results.json:data_issues / analysis.py\",\n \"issue\": \"The handling text for the missing 2025-10 UNRATE value is a fixed string, and it says the row is 'dropped by window filter'. In the code, 2025Q4 is actually removed at the earlier merge_unrate step (complete-quarter requirement), as exclusions.csv correctly records. The text is also written regardless of where a missing value falls. The assert that all quarters from 1959Q4 to 2019Q4 have 3 months guards the estimates, so the results are unaffected.\",\n \"suggested_fix\": \"Say that the quarter is removed by the complete-quarter merge step, and build the handling text conditionally on whether the missing date lies inside the window.\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"report.md: Method (bandwidth)\",\n \"issue\": \"The report says the bandwidth was 'fixed before looking at results'. This cannot be checked from the deliverables. The rule itself (floor(4(T/100)^{2/9}) = 4 for T=240) is computed correctly and is standard.\",\n \"suggested_fix\": \"Drop the claim, or point to a pre-registration record.\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"claims.json C4 / report Uncertainty\",\n \"issue\": \"The robustness check covers only Bartlett lags 0–12 with normal critical values. Fixed-b and small-sample variants were not computed. The report admits this, and with |t| ≈ 6.9 or more at every bandwidth the conclusion is very unlikely to change. The statement that fixed-b would 'widen the interval slightly' is asserted, not shown.\",\n \"suggested_fix\": \"Optionally report a fixed-b or df-corrected interval, or phrase the statement as an expectation.\"\n }\n ],\n \"summary\": \"The deliverables are complete and reproducible. Re-running analysis.py in a scratch copy reproduces results.json byte for byte. An independent calculation (resampled quarterly means, log differences, 1960Q1–2019Q4) gives the same beta_hat (-0.2558), alpha_hat (0.1844), R² (0.408), mean_growth (0.7535) and n = 240. The HAC SE is checked by a hand-coded sandwich, and the lag-4 rule is computed correctly. The code uses data only from 1959Q4 to 2019Q4, so the information rules are respected. Data checksums match the README. The iid baseline is present, the counts in the exclusion ledger are consistent (319→314→241→240), and the units and signs are correct. The claims match the numbers, and the limitations (current vintage, not causal, asymptotic inference, no break tests) are stated honestly. Only minor wording issues remain.\"\n}\nE\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON with absolute path and validate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1569,"cache_read_input_tokens":14158,"output_tokens":1196,"output_tokens_details":{"thinking_tokens":48},"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":1569},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqiy8qwVf5SeXH5NEum","requestRef":"e431c0df-45a2-4997-ac0e-6f748184e7af","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bc13be3f-9eb4-4268-8d68-38d80dfe0390","timestamp":"2026-10-30T05:06:48.582Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218/data","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"bc13be3f-9eb4-4268-8d68-38d80dfe0390","isSidechain":false,"promptId":"14c9ad63-b2f7-472a-96fb-08241493e8c9","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Y1q6SFqcaCgFgWnhjyTzYD","type":"tool_result","content":"ok","is_error":false}]},"uuid":"72f3f846-6b13-4081-a5ff-c3fed8b43504","timestamp":"2026-10-30T05:06:48.645Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"bc13be3f-9eb4-4268-8d68-38d80dfe0390","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}49{"type":"api-request-blob","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","hash":"a07e0df201f383dd8ae5a8d56a92a15da9b3425c783d91f989bf7bff3a297a46","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Y1q6SFqcaCgFgWnhjyTzYD","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0218 && cat > out/review/review.json <<'E'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"results.json:data_issues / analysis.py\",\n \"issue\": \"The handling text for the missing 2025-10 UNRATE value is a fixed string, and it says the row is 'dropped by window filter'. In the code, 2025Q4 is actually removed at the earlier merge_unrate step (complete-quarter requirement), as exclusions.csv correctly records. The text is also written regardless of where a missing value falls. The assert that all quarters from 1959Q4 to 2019Q4 have 3 months guards the estimates, so the results are unaffected.\",\n \"suggested_fix\": \"Say that the quarter is removed by the complete-quarter merge step, and build the handling text conditionally on whether the missing date lies inside the window.\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"report.md: Method (bandwidth)\",\n \"issue\": \"The report says the bandwidth was 'fixed before looking at results'. This cannot be checked from the deliverables. The rule itself (floor(4(T/100)^{2/9}) = 4 for T=240) is computed correctly and is standard.\",\n \"suggested_fix\": \"Drop the claim, or point to a pre-registration record.\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"claims.json C4 / report Uncertainty\",\n \"issue\": \"The robustness check covers only Bartlett lags 0–12 with normal critical values. Fixed-b and small-sample variants were not computed. The report admits this, and with |t| ≈ 6.9 or more at every bandwidth the conclusion is very unlikely to change. The statement that fixed-b would 'widen the interval slightly' is asserted, not shown.\",\n \"suggested_fix\": \"Optionally report a fixed-b or df-corrected interval, or phrase the statement as an expectation.\"\n }\n ],\n \"summary\": \"The deliverables are complete and reproducible. Re-running analysis.py in a scratch copy reproduces results.json byte for byte. An independent calculation (resampled quarterly means, log differences, 1960Q1–2019Q4) gives the same beta_hat (-0.2558), alpha_hat (0.1844), R² (0.408), mean_growth (0.7535) and n = 240. The HAC SE is checked by a hand-coded sandwich, and the lag-4 rule is computed correctly. The code uses data only from 1959Q4 to 2019Q4, so the information rules are respected. Data checksums match the README. The iid baseline is present, the counts in the exclusion ledger are consistent (319→314→241→240), and the units and signs are correct. The claims match the numbers, and the limitations (current vintage, not causal, asymptotic inference, no break tests) are stated honestly. Only minor wording issues remain.\"\n}\nE\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON with absolute path and validate"}}]}}50{"type":"api-request","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","id":"4b83fdb8-4e68-4b2c-b089-f4dcb19d07eb","timestamp":"2026-10-30T05:06:48.649Z","version":"2.1.314","querySource":"sdk","shapeHash":"85f695ead04022895fe251f220e6248611ed444b115520c61c6f1d09d2c22d40","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":"e431c0df-45a2-4997-ac0e-6f748184e7af","keep":12,"tail":["a07e0df201f383dd8ae5a8d56a92a15da9b3425c783d91f989bf7bff3a297a46","fd5444520d02448dee54cd4e30e7fea259ea2820147ed5673997871f131e4271"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ea8c509234704567c874193572becab6f80919cbde9791b330e509974e0f187b"}51{"parentUuid":"72f3f846-6b13-4081-a5ff-c3fed8b43504","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqjfrp1mRVF7DT46xws","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1203,"cache_read_input_tokens":15727,"output_tokens":784,"output_tokens_details":{"thinking_tokens":73},"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":1203},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6968,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXqjfahT5JWtbTsMQx9u","requestRef":"4b83fdb8-4e68-4b2c-b089-f4dcb19d07eb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"64f24d3f-0917-4253-80ef-0b19637a2eb6","timestamp":"2026-10-30T05:06:57.225Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}52{"parentUuid":"64f24d3f-0917-4253-80ef-0b19637a2eb6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXqjfrp1mRVF7DT46xws","type":"message","role":"assistant","content":[{"type":"text","text":"The verdict is **accept**: I found no critical or major issues, only three minor wording points. The review is saved at `out/review/review.json`.\n\n- **Reproducibility:** I re-ran `out/analysis.py` in a scratch copy and it regenerated `results.json` identically.\n- **Independent check:** I rebuilt the regression separately from the raw data (quarterly averages, log differences, 1960Q1–2019Q4) and got the same results:\n - slope β̂ = −0.2558\n - intercept 0.1844\n - R² = 0.408\n - mean growth 0.7535% per quarter\n - 240 quarters\n- **HAC standard error:** the code checks the Newey–West result against its own hand-coded calculation. The bandwidth rule floor(4·(T/100)^{2/9}) correctly gives 4 lags for 240 quarters.\n- **Data rules:** only data from 1959Q4 to 2019Q4 are used, with 1959Q4 serving only to form the first differences. The input file checksums match `data/README.md`.\n- **Consistency:** the exclusion counts add up (319 → 314 → 241 → 240), units and signs are correct, the naive standard-error baseline is reported, and the figure is right.\n- **Claims and limitations:** the claims match the numbers, and the limitations are stated honestly (current data vintage, not causal, asymptotic inference, no test for structural breaks).\n\nThe three minor issues:\n1. **Missing-value note:** the text in `data_issues` says the missing October 2025 unemployment value was removed by the window filter. The code actually removes it at the earlier merge step, which `exclusions.csv` records correctly. The note is also a fixed string rather than computed. The estimates are unaffected.\n2. **Bandwidth claim:** the report says the bandwidth was \"fixed before looking at results\", which can't be verified from the files.\n3. **Small-sample claim:** the statement that fixed-b or small-sample critical values would widen the interval \"slightly\" is asserted, not computed. With |t| of about 6.9 or more at every bandwidth tried, the conclusion is very unlikely to change."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1203,"cache_read_input_tokens":15727,"output_tokens":784,"output_tokens_details":{"thinking_tokens":73},"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":1203},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXqjfahT5JWtbTsMQx9u","requestRef":"4b83fdb8-4e68-4b2c-b089-f4dcb19d07eb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6d72aad1-8edc-4734-86e7-ea11a2cf0259","timestamp":"2026-10-30T05:06:57.227Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0218","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","version":"2.1.314","gitBranch":"HEAD"}53{"type":"last-prompt","lastPrompt":"Review","leafUuid":"6d72aad1-8edc-4734-86e7-ea11a2cf0259","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}54{"type":"atis-latch","atis":"","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889"}55{"type":"cost-state","sessionId":"1f590296-9cc1-499a-a493-11f8d2acb889","totalCostUSD":0.18424579999999996,"totalAPIDuration":46551,"totalAPIDurationWithoutRetries":46546,"totalToolDuration":2318,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":49053,"startTime":1793336768184,"modelUsage":{"claude-opus-5-5":{"inputTokens":16,"outputTokens":4724,"thinkingTokens":708,"cacheReadInputTokens":62859,"cacheCreationInputTokens":15426,"cacheCreationEphemeral5mInputTokens":15426,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.18424579999999996}},"hasUnknownModelCost":false}56