1{"type":"atis-latch","atis":"","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:49:53.500Z","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:49:53.504Z","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}4{"parentUuid":null,"isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":"Begin"},"uuid":"a82bdf78-11e8-4ff5-ac3d-92ebbe8a774c","timestamp":"2026-10-30T04:49:53.507Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","timestamp":"2026-10-30T04:49:53.516Z","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/RC0176\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md`.\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":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"aef1b8b8-d33a-4e7e-97b8-c6d759174829","timestamp":"2026-10-30T04:49:53.516Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1f62a7aa71e4a481ac2053fb3675b7aebdeeb3e64e9d819e329a45e1bb290d9d"}8{"parentUuid":"a82bdf78-11e8-4ff5-ac3d-92ebbe8a774c","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"a04a3c17-b009-44e5-9b15-5dac785bd691","timestamp":"2026-10-30T04:49:53.511Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"a04a3c17-b009-44e5-9b15-5dac785bd691","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"3bf91e07-4667-4aad-8482-96d20711dd74","timestamp":"2026-10-30T04:49:53.511Z","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/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"3bf91e07-4667-4aad-8482-96d20711dd74","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":"3effb35f-a84e-4076-a5fc-675d1fa5790a","timestamp":"2026-10-30T04:49:53.511Z","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/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}12{"parentUuid":"3effb35f-a84e-4076-a5fc-675d1fa5790a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSrH2t2yJ6gbsWNo4E","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SSmtvdiim5YrfUZVTzCyHS","name":"Bash","input":{"command":"cat TASK.md; ls -R data | head -50"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":730,"cache_read_input_tokens":1504,"output_tokens":63,"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":730},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpSr1QnefM3FUg88dAh","requestRef":"aef1b8b8-d33a-4e7e-97b8-c6d759174829","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"191f1d57-16c8-47c1-8179-baebdac9c9df","timestamp":"2026-10-30T04:49:55.111Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"191f1d57-16c8-47c1-8179-baebdac9c9df","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SSmtvdiim5YrfUZVTzCyHS","type":"tool_result","content":"# F6-conf-03 — Okun's law in the United States, 1960–2019: coefficient, uncertainty and stability\n\n## Scientific question\nHow strongly do quarterly changes in the US unemployment rate respond to real output growth, and has that response been stable? The estimand is the Okun coefficient β in the difference form Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, where Δu_t is the change in the quarterly-average civilian unemployment rate (percentage points) and g_t = 100·(ln GDPC1_t − ln GDPC1_{t−1}) is quarterly real GDP growth in percent (not annualised); uncertainty must be robust to heteroskedasticity and serial correlation. Stability is assessed by estimating β separately on 1960Q1–1983Q4 and 1984Q1–2019Q4 and by a classical Chow test of the joint equality of (α, β) across the two subperiods. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/GDPC1.csv` — observed data, FRED GDPC1 (US real GDP, quarterly, billions of chained 2017 dollars, SAAR; BEA), full history, raw FRED CSV (`observation_date` = first day of the quarter, `GDPC1`). Provenance in `data/README.md`.\n- `data/UNRATE.csv` — observed data, FRED UNRATE (US civilian unemployment rate, monthly, percent, SA; BLS), full history, raw FRED CSV (`observation_date` = first day of the month, `UNRATE`). Provenance in `data/README.md`.\n- `data/README.md` — provenance, retrieval dates, SHA-256.\n\n## Information-availability rules\n- Quarterly unemployment u_t is the simple average of the three monthly UNRATE values of quarter t. Δu_t = u_t − u_{t−1}.\n- The regression sample is the 240 quarters 1960Q1–2019Q4 (the 1960Q1 differences use 1959Q4 levels). Quarters after 2019Q4 are outside the question and must not enter any estimate. Subperiod 1 = 1960Q1–1983Q4, subperiod 2 = 1984Q1–2019Q4.\n- Standard errors for the full-sample β must be HAC (Newey–West with Bartlett kernel); choose and report the lag length. The Chow test is the classical sum-of-squared-residuals F-test with 2 and n − 4 degrees of freedom.\n- Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `sample_start`, `sample_end` | string | ISO date | first day of the first and last quarter in the regression sample (`1960-01-01`, `2019-10-01`) |\n| `n_sub1`, `n_sub2` | integer | quarters | observations in each subperiod |\n| `baseline_metric` | number | percentage points | RMSE of the mean-only prediction of Δu over the full sample, sqrt(mean((Δu − mean Δu)²)) |\n| `model_metric` | number | percentage points | RMSE of the full-sample OLS residuals, sqrt(mean(e²)) |\n| `effect_estimate` | number | pp per percent growth | full-sample OLS Okun coefficient β |\n| `intercept` | number | percentage points | full-sample OLS intercept α |\n| `effect_se` | number | pp per percent growth | HAC (Newey–West) standard error of β |\n| `hac_lags` | integer | quarters | Newey–West lag length used |\n| `effect_ci_low`, `effect_ci_high` | number | pp per percent growth | 95% confidence interval for β based on `effect_se` |\n| `beta_sub1`, `beta_sub2` | number | pp per percent growth | OLS slope in subperiod 1 and 2 |\n| `chow_f_stat`, `chow_p_value` | number | — | Chow F statistic and p-value |\n| `stability_conclusion` | string | — | `stable` if the Chow test does not reject at 5%, else `unstable` |\n| `conclusion` | string | — | one of the codes below (sign of β from its 95% interval) |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\n(`n_analysed` = quarters in the full-sample regression.)\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of Δu_t against g_t with the two subperiod fitted lines, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per sample (full, subperiod 1, subperiod 2) with columns `period`, `n`, `intercept`, `slope`, `slope_se` (header + three data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\nGDPC1.csv\nREADME.md\nUNRATE.csv","is_error":false}]},"uuid":"32a24c8a-4e7d-4629-ae4d-18b3170b70c2","timestamp":"2026-10-30T04:49:55.181Z","toolUseResult":{"stdout":"# F6-conf-03 — Okun's law in the United States, 1960–2019: coefficient, uncertainty and stability\n\n## Scientific question\nHow strongly do quarterly changes in the US unemployment rate respond to real output growth, and has that response been stable? The estimand is the Okun coefficient β in the difference form Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, where Δu_t is the change in the quarterly-average civilian unemployment rate (percentage points) and g_t = 100·(ln GDPC1_t − ln GDPC1_{t−1}) is quarterly real GDP growth in percent (not annualised); uncertainty must be robust to heteroskedasticity and serial correlation. Stability is assessed by estimating β separately on 1960Q1–1983Q4 and 1984Q1–2019Q4 and by a classical Chow test of the joint equality of (α, β) across the two subperiods. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/GDPC1.csv` — observed data, FRED GDPC1 (US real GDP, quarterly, billions of chained 2017 dollars, SAAR; BEA), full history, raw FRED CSV (`observation_date` = first day of the quarter, `GDPC1`). Provenance in `data/README.md`.\n- `data/UNRATE.csv` — observed data, FRED UNRATE (US civilian unemployment rate, monthly, percent, SA; BLS), full history, raw FRED CSV (`observation_date` = first day of the month, `UNRATE`). Provenance in `data/README.md`.\n- `data/README.md` — provenance, retrieval dates, SHA-256.\n\n## Information-availability rules\n- Quarterly unemployment u_t is the simple average of the three monthly UNRATE values of quarter t. Δu_t = u_t − u_{t−1}.\n- The regression sample is the 240 quarters 1960Q1–2019Q4 (the 1960Q1 differences use 1959Q4 levels). Quarters after 2019Q4 are outside the question and must not enter any estimate. Subperiod 1 = 1960Q1–1983Q4, subperiod 2 = 1984Q1–2019Q4.\n- Standard errors for the full-sample β must be HAC (Newey–West with Bartlett kernel); choose and report the lag length. The Chow test is the classical sum-of-squared-residuals F-test with 2 and n − 4 degrees of freedom.\n- Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `sample_start`, `sample_end` | string | ISO date | first day of the first and last quarter in the regression sample (`1960-01-01`, `2019-10-01`) |\n| `n_sub1`, `n_sub2` | integer | quarters | observations in each subperiod |\n| `baseline_metric` | number | percentage points | RMSE of the mean-only prediction of Δu over the full sample, sqrt(mean((Δu − mean Δu)²)) |\n| `model_metric` | number | percentage points | RMSE of the full-sample OLS residuals, sqrt(mean(e²)) |\n| `effect_estimate` | number | pp per percent growth | full-sample OLS Okun coefficient β |\n| `intercept` | number | percentage points | full-sample OLS intercept α |\n| `effect_se` | number | pp per percent growth | HAC (Newey–West) standard error of β |\n| `hac_lags` | integer | quarters | Newey–West lag length used |\n| `effect_ci_low`, `effect_ci_high` | number | pp per percent growth | 95% confidence interval for β based on `effect_se` |\n| `beta_sub1`, `beta_sub2` | number | pp per percent growth | OLS slope in subperiod 1 and 2 |\n| `chow_f_stat`, `chow_p_value` | number | — | Chow F statistic and p-value |\n| `stability_conclusion` | string | — | `stable` if the Chow test does not reject at 5%, else `unstable` |\n| `conclusion` | string | — | one of the codes below (sign of β from its 95% interval) |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\n(`n_analysed` = quarters in the full-sample regression.)\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of Δu_t against g_t with the two subperiod fitted lines, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per sample (full, subperiod 1, subperiod 2) with columns `period`, `n`, `intercept`, `slope`, `slope_se` (header + three data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\nGDPC1.csv\nREADME.md\nUNRATE.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"191f1d57-16c8-47c1-8179-baebdac9c9df","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}14{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"e61a16ec4275b84e9fc8403b00955649275459ed4811053d361e6a402f8ffc38","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01SSmtvdiim5YrfUZVTzCyHS","name":"Bash","input":{"command":"cat TASK.md; ls -R data | head -50"}}]}}15{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"cdc34c91-11ef-4030-bd13-db347aeb08da","timestamp":"2026-10-30T04:49:55.185Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"aef1b8b8-d33a-4e7e-97b8-c6d759174829","keep":2,"tail":["e61a16ec4275b84e9fc8403b00955649275459ed4811053d361e6a402f8ffc38","dbcb3d3405b5a4ca86223283a767588c10b2b37e0fd92072886d80f879e0cc60"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"047026d227ca299a18d9850818012ad0d97529f593356df051ee26ca6296e385"}16{"parentUuid":"32a24c8a-4e7d-4629-ae4d-18b3170b70c2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSxowewnmUVeC2cVHM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019BLUMEmB71yBA73dJvyNZW","name":"Bash","input":{"command":"cd data; cat README.md; head -3 *.csv; tail -3 *.csv; wc -l *.csv; grep -c ',$\\|,\\.$' *.csv; awk -F, 'NR>1 && ($2==\"\" || $2==\".\" )' *.csv | head"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2543,"cache_read_input_tokens":2234,"output_tokens":349,"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":2543},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpSxYKJh8iMRvJw7EGm","requestRef":"cdc34c91-11ef-4030-bd13-db347aeb08da","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f57f0760-1b37-4396-87f7-dd5f6fd57f85","timestamp":"2026-10-30T04:49:57.168Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}17{"parentUuid":"f57f0760-1b37-4396-87f7-dd5f6fd57f85","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019BLUMEmB71yBA73dJvyNZW","type":"tool_result","content":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n==> GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 GDPC1.csv\n 946 UNRATE.csv\n 1266 total\nGDPC1.csv:0\nUNRATE.csv:0\n2025-10-01,","is_error":false}]},"uuid":"fd8cb3d1-87d6-40b0-9aba-b3adf4623fa5","timestamp":"2026-10-30T04:49:57.232Z","toolUseResult":{"stdout":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n==> GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 GDPC1.csv\n 946 UNRATE.csv\n 1266 total\nGDPC1.csv:0\nUNRATE.csv:0\n2025-10-01,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f57f0760-1b37-4396-87f7-dd5f6fd57f85","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}18{"parentUuid":"fd8cb3d1-87d6-40b0-9aba-b3adf4623fa5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSxowewnmUVeC2cVHM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FQgE1A7Fizmduo4S2ZihGK","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f in ['GDPC1','UNRATE']:\n d=pd.read_csv(f+'.csv',parse_dates=['observation_date']);print(f,d.dtypes.tolist(),d.observation_date.duplicated().sum(),d.observation_date.diff().dt.days.describe().to_dict(),d.iloc[:,1].describe().to_dict(),d.isna().sum().to_dict())\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2543,"cache_read_input_tokens":2234,"output_tokens":349,"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":2543},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSxYKJh8iMRvJw7EGm","requestRef":"cdc34c91-11ef-4030-bd13-db347aeb08da","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7070162b-7df5-4de2-87fb-79ae3cf68dd1","timestamp":"2026-10-30T04:49:58.756Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}19{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"7070162b-7df5-4de2-87fb-79ae3cf68dd1","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}20{"type":"atis-latch","atis":"","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}21{"parentUuid":"7070162b-7df5-4de2-87fb-79ae3cf68dd1","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FQgE1A7Fizmduo4S2ZihGK","type":"tool_result","content":"(eval):cd:1: no such file or directory: data\nGDPC1 [dtype('<M8[ns]'), dtype('float64')] 0 {'count': 318.0, 'mean': 91.30817610062893, 'std': 0.7696915317607711, 'min': 90.0, '25%': 91.0, '50%': 91.0, '75%': 92.0, 'max': 92.0} {'count': 319.0, 'mean': 10458.210203761757, 'std': 6485.0424476807175, 'min': 2172.432, '25%': 4848.918, '50%': 8920.193, '75%': 16340.058, 'max': 24611.077} {'observation_date': 0, 'GDPC1': 0}\nUNRATE [dtype('<M8[ns]'), dtype('float64')] 0 {'count': 944.0, 'mean': 30.4375, 'std': 0.8149663805854961, 'min': 28.0, '25%': 30.0, '50%': 31.0, '75%': 31.0, 'max': 31.0} {'count': 944.0, 'mean': 5.652966101694915, 'std': 1.703533753130343, 'min': 2.5, '25%': 4.3, '50%': 5.45, '75%': 6.7, 'max': 14.8} {'observation_date': 0, 'UNRATE': 1}","is_error":false}]},"uuid":"f67f7a92-2dc8-4fab-b7a1-c604f5f5128a","timestamp":"2026-10-30T04:49:58.977Z","toolUseResult":{"stdout":"(eval):cd:1: no such file or directory: data\nGDPC1 [dtype('<M8[ns]'), dtype('float64')] 0 {'count': 318.0, 'mean': 91.30817610062893, 'std': 0.7696915317607711, 'min': 90.0, '25%': 91.0, '50%': 91.0, '75%': 92.0, 'max': 92.0} {'count': 319.0, 'mean': 10458.210203761757, 'std': 6485.0424476807175, 'min': 2172.432, '25%': 4848.918, '50%': 8920.193, '75%': 16340.058, 'max': 24611.077} {'observation_date': 0, 'GDPC1': 0}\nUNRATE [dtype('<M8[ns]'), dtype('float64')] 0 {'count': 944.0, 'mean': 30.4375, 'std': 0.8149663805854961, 'min': 28.0, '25%': 30.0, '50%': 31.0, '75%': 31.0, 'max': 31.0} {'count': 944.0, 'mean': 5.652966101694915, 'std': 1.703533753130343, 'min': 2.5, '25%': 4.3, '50%': 5.45, '75%': 6.7, 'max': 14.8} {'observation_date': 0, 'UNRATE': 1}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7070162b-7df5-4de2-87fb-79ae3cf68dd1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}22{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"f6641594dec7066c79d3f0c1d8afcf82c5c284e32ed8248338644645f681271d","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_019BLUMEmB71yBA73dJvyNZW","name":"Bash","input":{"command":"cd data; cat README.md; head -3 *.csv; tail -3 *.csv; wc -l *.csv; grep -c ',$\\|,\\.$' *.csv; awk -F, 'NR>1 && ($2==\"\" || $2==\".\" )' *.csv | head"}},{"type":"tool_use","id":"toolu_01FQgE1A7Fizmduo4S2ZihGK","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f in ['GDPC1','UNRATE']:\n d=pd.read_csv(f+'.csv',parse_dates=['observation_date']);print(f,d.dtypes.tolist(),d.observation_date.duplicated().sum(),d.observation_date.diff().dt.days.describe().to_dict(),d.iloc[:,1].describe().to_dict(),d.isna().sum().to_dict())\n\""}}]}}23{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"29c5f308eaf0719eb2db8d7a6e36c8b95bcb7ab7ee5c05b5ef41e43cf5b8e7bc","message":{"role":"user","content":[{"tool_use_id":"toolu_019BLUMEmB71yBA73dJvyNZW","type":"tool_result","content":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n==> GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 GDPC1.csv\n 946 UNRATE.csv\n 1266 total\nGDPC1.csv:0\nUNRATE.csv:0\n2025-10-01,","is_error":false},{"tool_use_id":"toolu_01FQgE1A7Fizmduo4S2ZihGK","type":"tool_result","content":"(eval):cd:1: no such file or directory: data\nGDPC1 [dtype('<M8[ns]'), dtype('float64')] 0 {'count': 318.0, 'mean': 91.30817610062893, 'std': 0.7696915317607711, 'min': 90.0, '25%': 91.0, '50%': 91.0, '75%': 92.0, 'max': 92.0} {'count': 319.0, 'mean': 10458.210203761757, 'std': 6485.0424476807175, 'min': 2172.432, '25%': 4848.918, '50%': 8920.193, '75%': 16340.058, 'max': 24611.077} {'observation_date': 0, 'GDPC1': 0}\nUNRATE [dtype('<M8[ns]'), dtype('float64')] 0 {'count': 944.0, 'mean': 30.4375, 'std': 0.8149663805854961, 'min': 28.0, '25%': 30.0, '50%': 31.0, '75%': 31.0, 'max': 31.0} {'count': 944.0, 'mean': 5.652966101694915, 'std': 1.703533753130343, 'min': 2.5, '25%': 4.3, '50%': 5.45, '75%': 6.7, 'max': 14.8} {'observation_date': 0, 'UNRATE': 1}","is_error":false}]}}24{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"b6dc446e-0b6f-4038-8481-ce35dfacd1e9","timestamp":"2026-10-30T04:49:58.979Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"cdc34c91-11ef-4030-bd13-db347aeb08da","keep":4,"tail":["f6641594dec7066c79d3f0c1d8afcf82c5c284e32ed8248338644645f681271d","29c5f308eaf0719eb2db8d7a6e36c8b95bcb7ab7ee5c05b5ef41e43cf5b8e7bc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"38f7174f082e48925e27fc984cac623e7551cca7e006c37a4acda4dc98dd1ded"}25{"parentUuid":"f67f7a92-2dc8-4fab-b7a1-c604f5f5128a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTFHtDourhiRNoXjQb","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":1688,"cache_read_input_tokens":4777,"output_tokens":3799,"output_tokens_details":{"thinking_tokens":163},"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":1688},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1506,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpTF1m7nFU6k6mAeZTE","requestRef":"b6dc446e-0b6f-4038-8481-ce35dfacd1e9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7e47c736-551b-4a01-9b74-aa8e09333b7b","timestamp":"2026-10-30T04:50:01.620Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"7e47c736-551b-4a01-9b74-aa8e09333b7b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTFHtDourhiRNoXjQb","type":"message","role":"assistant","content":[{"type":"text","text":"UNRATE has one missing value (2025-10), which falls outside the sample. Next I'll write the analysis script and include checks in it."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1688,"cache_read_input_tokens":4777,"output_tokens":3799,"output_tokens_details":{"thinking_tokens":163},"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":1688},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpTF1m7nFU6k6mAeZTE","requestRef":"b6dc446e-0b6f-4038-8481-ce35dfacd1e9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2f7f0088-ece4-4231-b4ef-9f6c1d382d4d","timestamp":"2026-10-30T04:50:01.623Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"2f7f0088-ece4-4231-b4ef-9f6c1d382d4d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTFHtDourhiRNoXjQb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NLLfXJAT9iabGMShjqCGcR","name":"Bash","input":{"command":"mkdir -p out; cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root.\"\"\"\nimport json, os\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\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nissues = []\ngdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\nur = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(ur))}\n\n# --- audit ---\nfor name, d, col in [(\"GDPC1.csv\", gdp, \"GDPC1\"), (\"UNRATE.csv\", ur, \"UNRATE\")]:\n assert not d.observation_date.duplicated().any(), name + \" duplicate dates\"\n miss = d.loc[d[col].isna(), \"observation_date\"].dt.strftime(\"%Y-%m-%d\").tolist()\n if miss:\n inside = [m for m in miss if \"1959-10-01\" <= m <= \"2019-12-31\"]\n issues.append({\"issue\": f\"{name}: missing value(s) at {miss}\",\n \"handling\": \"outside 1959Q4-2019Q4 estimation window; no effect on estimates\" if not inside\n else \"inside window: quarter dropped\"})\n if (d[col].dropna() <= 0).any():\n issues.append({\"issue\": f\"{name}: non-positive values\", \"handling\": \"flagged\"})\n# monthly continuity\nmonths = pd.date_range(ur.observation_date.min(), ur.observation_date.max(), freq=\"MS\")\nassert len(months) == len(ur), \"UNRATE month gaps\"\nqs = pd.date_range(gdp.observation_date.min(), gdp.observation_date.max(), freq=\"QS\")\nassert len(qs) == len(gdp), \"GDPC1 quarter gaps\"\n\n# --- construct quarterly series ---\nur[\"q\"] = ur.observation_date.dt.to_period(\"Q\")\nuq = ur.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nuq = uq[uq[\"count\"] == 3][\"mean\"].rename(\"u\")\ng = gdp.set_index(gdp.observation_date.dt.to_period(\"Q\"))[\"GDPC1\"]\ndf = pd.concat([uq, g], axis=1).sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\ndf = df.loc[pd.Period(\"1960Q1\"):pd.Period(\"2019Q4\")]\nassert len(df) == 240 and df[[\"du\", \"g\"]].notna().all().all()\nissues.append({\"issue\": \"Observations after 2019Q4 present in both files (incl. 2020 COVID outliers); GDPC1 is the 2026 vintage (revised data, chained 2017 $)\",\n \"handling\": \"post-2019Q4 data excluded per task; current vintage used as provided (log growth rates invariant to base year)\"})\n# outlier screen on in-sample data\nz = (df[[\"du\", \"g\"]] - df[[\"du\", \"g\"]].mean()) / df[[\"du\", \"g\"]].std()\nbig = df.index[(z.abs() > 4).any(axis=1)].astype(str).tolist()\nif big:\n issues.append({\"issue\": f\"Large (|z|>4) in-sample observations: {big}\",\n \"handling\": \"retained (genuine recession/recovery quarters); influence discussed in report\"})\n\ndef ols(d, hac=None):\n X = sm.add_constant(d[\"g\"])\n m = sm.OLS(d[\"du\"], X)\n return m.fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": hac, \"kernel\": \"bartlett\"}) if hac is not None else m.fit()\n\nT = len(df)\nL = int(np.floor(4 * (T / 100) ** (2 / 9))) # Newey-West (1994) rule of thumb\nfull = ols(df, L); full_ols = ols(df)\ns1 = df.loc[:pd.Period(\"1983Q4\")]; s2 = df.loc[pd.Period(\"1984Q1\"):]\nr1, r2 = ols(s1, L), ols(s2, L)\nssr_p = full_ols.ssr; ssr_u = ols(s1).ssr + ols(s2).ssr; k = 2\nF = ((ssr_p - ssr_u) / k) / (ssr_u / (T - 2 * k))\np = float(stats.f.sf(F, k, T - 2 * k))\n\nbeta = float(full.params[\"g\"]); se = float(full.bse[\"g\"])\nz975 = stats.norm.ppf(0.975)\nlo, hi = beta - z975 * se, beta + z975 * se\nconcl = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\n# sensitivity (reported in report, not in results keys)\nsens = {f\"lags_{l}\": float(ols(df, l).bse[\"g\"]) for l in (0, 2, 4, 8, 12)}\nsens[\"ols_iid_se\"] = float(full_ols.bse[\"g\"])\nsens[\"beta_excl_z4\"] = float(ols(df.drop(pd.PeriodIndex(big, freq=\"Q\"))).params[\"g\"]) if big else beta\n# HAC-robust Wald test of break (interaction model)\nd2 = df.copy(); d2[\"D\"] = (d2.index >= pd.Period(\"1984Q1\")).astype(float); d2[\"Dg\"] = d2[\"D\"] * d2[\"g\"]\nmw = sm.OLS(d2[\"du\"], sm.add_constant(d2[[\"g\", \"D\", \"Dg\"]])).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L})\nwt = mw.wald_test(\"D = 0, Dg = 0\", use_f=True, scalar=True)\nsens[\"hac_wald_break_F\"] = float(wt.statistic); sens[\"hac_wald_break_p\"] = float(wt.pvalue)\nsens[\"sub1_hac_se\"] = float(r1.bse[\"g\"]); sens[\"sub2_hac_se\"] = float(r2.bse[\"g\"])\nsens[\"sub1_alpha\"] = float(r1.params[\"const\"]); sens[\"sub2_alpha\"] = float(r2.params[\"const\"])\nsens[\"r2_full\"] = float(full_ols.rsquared)\nsens[\"breakeven_growth_full\"] = float(-full.params[\"const\"] / beta)\njson.dump(sens, open(f\"{OUT}/sensitivity.json\", \"w\"), indent=2)\n\nres = {\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": df.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": df.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2))),\n \"model_metric\": float(np.sqrt(np.mean(full_ols.resid ** 2))),\n \"effect_estimate\": beta, \"intercept\": float(full.params[\"const\"]),\n \"effect_se\": se, \"hac_lags\": L, \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n \"beta_sub1\": float(r1.params[\"g\"]), \"beta_sub2\": float(r2.params[\"g\"]),\n \"chow_f_stat\": float(F), \"chow_p_value\": p,\n \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n \"conclusion\": concl, \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": issues, \"n_input_rows\": n_rows, \"n_analysed\": int(T), \"random_seed\": None,\n}\njson.dump(res, open(f\"{OUT}/results.json\", \"w\"), indent=2)\n\npd.DataFrame([\n {\"period\": \"full_1960Q1-2019Q4\", \"n\": T, \"intercept\": full.params[\"const\"], \"slope\": beta, \"slope_se\": se},\n {\"period\": \"sub1_1960Q1-1983Q4\", \"n\": len(s1), \"intercept\": r1.params[\"const\"], \"slope\": r1.params[\"g\"], \"slope_se\": r1.bse[\"g\"]},\n {\"period\": \"sub2_1984Q1-2019Q4\", \"n\": len(s2), \"intercept\": r2.params[\"const\"], \"slope\": r2.params[\"g\"], \"slope_se\": r2.bse[\"g\"]},\n]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nfor d, r, c, lab in [(s1, r1, \"tab:blue\", \"1960Q1–1983Q4\"), (s2, r2, \"tab:red\", \"1984Q1–2019Q4\")]:\n ax.scatter(d.g, d.du, s=12, alpha=0.6, color=c, label=f\"{lab} (n={len(d)})\")\n xs = np.linspace(d.g.min(), d.g.max(), 50)\n ax.plot(xs, r.params[\"const\"] + r.params[\"g\"] * xs, color=c,\n label=f\"fit {lab}: Δu = {r.params['const']:.2f} {r.params['g']:+.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(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1–2019Q4\"); ax.legend(fontsize=8)\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150)\nprint(json.dumps(res, indent=2)); print(json.dumps(sens, indent=2))\nEOF\n~/wp29/venv/bin/python out/analysis.py; cat out/table1.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1688,"cache_read_input_tokens":4777,"output_tokens":3799,"output_tokens_details":{"thinking_tokens":163},"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":1688},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpTF1m7nFU6k6mAeZTE","requestRef":"b6dc446e-0b6f-4038-8481-ce35dfacd1e9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"12cf6517-0643-4b2b-af95-cda33882e99d","timestamp":"2026-10-30T04:50:28.706Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}28{"parentUuid":"12cf6517-0643-4b2b-af95-cda33882e99d","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n File \"/Users/simon-pierreboucher/wp29/runs/RC0176/data/out/analysis.py\", line 12, in <module>\n gdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n return _read(filepath_or_buffer, kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n parser = TextFileReader(filepath_or_buffer, **kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n self._engine = self._make_engine(f, self.engine)\n ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n self.handles = get_handle(\n ~~~~~~~~~~^\n f,\n ^^\n ...<6 lines>...\n storage_options=self.options.get(\"storage_options\", None),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n handle = open(\n handle,\n ...<3 lines>...\n newline=\"\",\n )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/GDPC1.csv'\ncat: out/table1.csv: No such file or directory","is_error":true,"tool_use_id":"toolu_01NLLfXJAT9iabGMShjqCGcR"}]},"uuid":"ab32f1af-15c9-4c5a-8325-6432c7667114","timestamp":"2026-10-30T04:50:29.480Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n File \"/Users/simon-pierreboucher/wp29/runs/RC0176/data/out/analysis.py\", line 12, in <module>\n gdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n return _read(filepath_or_buffer, kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n parser = TextFileReader(filepath_or_buffer, **kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n self._engine = self._make_engine(f, self.engine)\n ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n self.handles = get_handle(\n ~~~~~~~~~~^\n f,\n ^^\n ...<6 lines>...\n storage_options=self.options.get(\"storage_options\", None),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n handle = open(\n handle,\n ...<3 lines>...\n newline=\"\",\n )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/GDPC1.csv'\ncat: out/table1.csv: No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"12cf6517-0643-4b2b-af95-cda33882e99d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}29{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"83153138c49ecb08ae5e28e9a815197e11dfc1fddcd80baa21dde896b6974ebe","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"UNRATE has one missing value (2025-10), which falls outside the sample. Next I'll write the analysis script and include checks in it."},{"type":"tool_use","id":"toolu_01NLLfXJAT9iabGMShjqCGcR","name":"Bash","input":{"command":"mkdir -p out; cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root.\"\"\"\nimport json, os\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\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nissues = []\ngdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\nur = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(ur))}\n\n# --- audit ---\nfor name, d, col in [(\"GDPC1.csv\", gdp, \"GDPC1\"), (\"UNRATE.csv\", ur, \"UNRATE\")]:\n assert not d.observation_date.duplicated().any(), name + \" duplicate dates\"\n miss = d.loc[d[col].isna(), \"observation_date\"].dt.strftime(\"%Y-%m-%d\").tolist()\n if miss:\n inside = [m for m in miss if \"1959-10-01\" <= m <= \"2019-12-31\"]\n issues.append({\"issue\": f\"{name}: missing value(s) at {miss}\",\n \"handling\": \"outside 1959Q4-2019Q4 estimation window; no effect on estimates\" if not inside\n else \"inside window: quarter dropped\"})\n if (d[col].dropna() <= 0).any():\n issues.append({\"issue\": f\"{name}: non-positive values\", \"handling\": \"flagged\"})\n# monthly continuity\nmonths = pd.date_range(ur.observation_date.min(), ur.observation_date.max(), freq=\"MS\")\nassert len(months) == len(ur), \"UNRATE month gaps\"\nqs = pd.date_range(gdp.observation_date.min(), gdp.observation_date.max(), freq=\"QS\")\nassert len(qs) == len(gdp), \"GDPC1 quarter gaps\"\n\n# --- construct quarterly series ---\nur[\"q\"] = ur.observation_date.dt.to_period(\"Q\")\nuq = ur.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nuq = uq[uq[\"count\"] == 3][\"mean\"].rename(\"u\")\ng = gdp.set_index(gdp.observation_date.dt.to_period(\"Q\"))[\"GDPC1\"]\ndf = pd.concat([uq, g], axis=1).sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\ndf = df.loc[pd.Period(\"1960Q1\"):pd.Period(\"2019Q4\")]\nassert len(df) == 240 and df[[\"du\", \"g\"]].notna().all().all()\nissues.append({\"issue\": \"Observations after 2019Q4 present in both files (incl. 2020 COVID outliers); GDPC1 is the 2026 vintage (revised data, chained 2017 $)\",\n \"handling\": \"post-2019Q4 data excluded per task; current vintage used as provided (log growth rates invariant to base year)\"})\n# outlier screen on in-sample data\nz = (df[[\"du\", \"g\"]] - df[[\"du\", \"g\"]].mean()) / df[[\"du\", \"g\"]].std()\nbig = df.index[(z.abs() > 4).any(axis=1)].astype(str).tolist()\nif big:\n issues.append({\"issue\": f\"Large (|z|>4) in-sample observations: {big}\",\n \"handling\": \"retained (genuine recession/recovery quarters); influence discussed in report\"})\n\ndef ols(d, hac=None):\n X = sm.add_constant(d[\"g\"])\n m = sm.OLS(d[\"du\"], X)\n return m.fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": hac, \"kernel\": \"bartlett\"}) if hac is not None else m.fit()\n\nT = len(df)\nL = int(np.floor(4 * (T / 100) ** (2 / 9))) # Newey-West (1994) rule of thumb\nfull = ols(df, L); full_ols = ols(df)\ns1 = df.loc[:pd.Period(\"1983Q4\")]; s2 = df.loc[pd.Period(\"1984Q1\"):]\nr1, r2 = ols(s1, L), ols(s2, L)\nssr_p = full_ols.ssr; ssr_u = ols(s1).ssr + ols(s2).ssr; k = 2\nF = ((ssr_p - ssr_u) / k) / (ssr_u / (T - 2 * k))\np = float(stats.f.sf(F, k, T - 2 * k))\n\nbeta = float(full.params[\"g\"]); se = float(full.bse[\"g\"])\nz975 = stats.norm.ppf(0.975)\nlo, hi = beta - z975 * se, beta + z975 * se\nconcl = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\n# sensitivity (reported in report, not in results keys)\nsens = {f\"lags_{l}\": float(ols(df, l).bse[\"g\"]) for l in (0, 2, 4, 8, 12)}\nsens[\"ols_iid_se\"] = float(full_ols.bse[\"g\"])\nsens[\"beta_excl_z4\"] = float(ols(df.drop(pd.PeriodIndex(big, freq=\"Q\"))).params[\"g\"]) if big else beta\n# HAC-robust Wald test of break (interaction model)\nd2 = df.copy(); d2[\"D\"] = (d2.index >= pd.Period(\"1984Q1\")).astype(float); d2[\"Dg\"] = d2[\"D\"] * d2[\"g\"]\nmw = sm.OLS(d2[\"du\"], sm.add_constant(d2[[\"g\", \"D\", \"Dg\"]])).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L})\nwt = mw.wald_test(\"D = 0, Dg = 0\", use_f=True, scalar=True)\nsens[\"hac_wald_break_F\"] = float(wt.statistic); sens[\"hac_wald_break_p\"] = float(wt.pvalue)\nsens[\"sub1_hac_se\"] = float(r1.bse[\"g\"]); sens[\"sub2_hac_se\"] = float(r2.bse[\"g\"])\nsens[\"sub1_alpha\"] = float(r1.params[\"const\"]); sens[\"sub2_alpha\"] = float(r2.params[\"const\"])\nsens[\"r2_full\"] = float(full_ols.rsquared)\nsens[\"breakeven_growth_full\"] = float(-full.params[\"const\"] / beta)\njson.dump(sens, open(f\"{OUT}/sensitivity.json\", \"w\"), indent=2)\n\nres = {\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": df.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": df.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2))),\n \"model_metric\": float(np.sqrt(np.mean(full_ols.resid ** 2))),\n \"effect_estimate\": beta, \"intercept\": float(full.params[\"const\"]),\n \"effect_se\": se, \"hac_lags\": L, \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n \"beta_sub1\": float(r1.params[\"g\"]), \"beta_sub2\": float(r2.params[\"g\"]),\n \"chow_f_stat\": float(F), \"chow_p_value\": p,\n \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n \"conclusion\": concl, \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": issues, \"n_input_rows\": n_rows, \"n_analysed\": int(T), \"random_seed\": None,\n}\njson.dump(res, open(f\"{OUT}/results.json\", \"w\"), indent=2)\n\npd.DataFrame([\n {\"period\": \"full_1960Q1-2019Q4\", \"n\": T, \"intercept\": full.params[\"const\"], \"slope\": beta, \"slope_se\": se},\n {\"period\": \"sub1_1960Q1-1983Q4\", \"n\": len(s1), \"intercept\": r1.params[\"const\"], \"slope\": r1.params[\"g\"], \"slope_se\": r1.bse[\"g\"]},\n {\"period\": \"sub2_1984Q1-2019Q4\", \"n\": len(s2), \"intercept\": r2.params[\"const\"], \"slope\": r2.params[\"g\"], \"slope_se\": r2.bse[\"g\"]},\n]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nfor d, r, c, lab in [(s1, r1, \"tab:blue\", \"1960Q1–1983Q4\"), (s2, r2, \"tab:red\", \"1984Q1–2019Q4\")]:\n ax.scatter(d.g, d.du, s=12, alpha=0.6, color=c, label=f\"{lab} (n={len(d)})\")\n xs = np.linspace(d.g.min(), d.g.max(), 50)\n ax.plot(xs, r.params[\"const\"] + r.params[\"g\"] * xs, color=c,\n label=f\"fit {lab}: Δu = {r.params['const']:.2f} {r.params['g']:+.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(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1–2019Q4\"); ax.legend(fontsize=8)\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150)\nprint(json.dumps(res, indent=2)); print(json.dumps(sens, indent=2))\nEOF\n~/wp29/venv/bin/python out/analysis.py; cat out/table1.csv"}}]}}30{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"5cd2af02-7708-4455-8f0d-7ba44aa982ba","timestamp":"2026-10-30T04:50:29.482Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"b6dc446e-0b6f-4038-8481-ce35dfacd1e9","keep":6,"tail":["83153138c49ecb08ae5e28e9a815197e11dfc1fddcd80baa21dde896b6974ebe","18f38290dff70eac5b56088c0dcba1bd758837d6f837ba5f6263f4959e30d792"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9f1a6fcc3b87a3e98a4366dd4c04cef0d3d9a8e5395d3e11033774ec4923a3dd"}31{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"ab32f1af-15c9-4c5a-8325-6432c7667114","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}32{"type":"atis-latch","atis":"","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}33{"parentUuid":"ab32f1af-15c9-4c5a-8325-6432c7667114","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpVVRkbh6FoUgXcm6wc","type":"message","role":"assistant","content":[{"type":"text","text":"The shell was still in `data/`, so the `out/` folder got created inside `data/`. I'll move it to the workspace root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4547,"cache_read_input_tokens":6465,"output_tokens":160,"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":4547},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpVV9P6rMrQPM2GSjas","requestRef":"5cd2af02-7708-4455-8f0d-7ba44aa982ba","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"52280c19-1cd9-4791-954c-947c0e0c1e09","timestamp":"2026-10-30T04:50:30.751Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}34{"parentUuid":"52280c19-1cd9-4791-954c-947c0e0c1e09","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpVVRkbh6FoUgXcm6wc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013unsKAeyyPaZMHDafZXaK2","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0176 && mv data/out ./out && ls data && ~/wp29/venv/bin/python out/analysis.py; cat out/table1.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4547,"cache_read_input_tokens":6465,"output_tokens":160,"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":4547},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpVV9P6rMrQPM2GSjas","requestRef":"5cd2af02-7708-4455-8f0d-7ba44aa982ba","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a9be2883-7635-4ab2-b87c-f8ba3517d6bc","timestamp":"2026-10-30T04:50:31.439Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176/data","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}35{"parentUuid":"a9be2883-7635-4ab2-b87c-f8ba3517d6bc","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013unsKAeyyPaZMHDafZXaK2","type":"tool_result","content":"GDPC1.csv\nREADME.md\nUNRATE.csv\n{\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": \"1960-01-01\",\n \"sample_end\": \"2019-10-01\",\n \"n_sub1\": 96,\n \"n_sub2\": 144,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253,\n \"effect_estimate\": -0.2557677277487258,\n \"intercept\": 0.18438835418210714,\n \"effect_se\": 0.0358346333029657,\n \"hac_lags\": 4,\n \"effect_ci_low\": -0.32600231842173816,\n \"effect_ci_high\": -0.18553313707571345,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.090333006233798,\n \"chow_p_value\": 0.0026363238517333456,\n \"stability_conclusion\": \"unstable\",\n \"conclusion\": \"negative_effect\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"UNRATE.csv: missing value(s) at ['2025-10-01']\",\n \"handling\": \"outside 1959Q4-2019Q4 estimation window; no effect on estimates\"\n },\n {\n \"issue\": \"Observations after 2019Q4 present in both files (incl. 2020 COVID outliers); GDPC1 is the 2026 vintage (revised data, chained 2017 $)\",\n \"handling\": \"post-2019Q4 data excluded per task; current vintage used as provided (log growth rates invariant to base year)\"\n },\n {\n \"issue\": \"Large (|z|>4) in-sample observations: ['1975Q1', '2009Q1']\",\n \"handling\": \"retained (genuine recession/recovery quarters); influence discussed in report\"\n }\n ],\n \"n_input_rows\": {\n \"GDPC1.csv\": 319,\n \"UNRATE.csv\": 945\n },\n \"n_analysed\": 240,\n \"random_seed\": null\n}\n{\n \"lags_0\": 0.028836223207269963,\n \"lags_2\": 0.03422732023615383,\n \"lags_4\": 0.0358346333029657,\n \"lags_8\": 0.0371355041754019,\n \"lags_12\": 0.0364088511022809,\n \"ols_iid_se\": 0.01996009291490984,\n \"beta_excl_z4\": -0.22850787862513172,\n \"hac_wald_break_F\": 5.463105028494939,\n \"hac_wald_break_p\": 0.0047938876117560566,\n \"sub1_hac_se\": 0.03928680828959863,\n \"sub2_hac_se\": 0.06831428793738024,\n \"sub1_alpha\": 0.2542326539884382,\n \"sub2_alpha\": 0.15168581347724602,\n \"r2_full\": 0.4082508284562034,\n \"breakeven_growth_full\": 0.7209211099660549\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.0358346333029657\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03928680828959863\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06831428793738024","is_error":false}]},"uuid":"a014dd8f-e891-487c-88eb-183d900a6844","timestamp":"2026-10-30T04:50:32.317Z","toolUseResult":{"stdout":"GDPC1.csv\nREADME.md\nUNRATE.csv\n{\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": \"1960-01-01\",\n \"sample_end\": \"2019-10-01\",\n \"n_sub1\": 96,\n \"n_sub2\": 144,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253,\n \"effect_estimate\": -0.2557677277487258,\n \"intercept\": 0.18438835418210714,\n \"effect_se\": 0.0358346333029657,\n \"hac_lags\": 4,\n \"effect_ci_low\": -0.32600231842173816,\n \"effect_ci_high\": -0.18553313707571345,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.090333006233798,\n \"chow_p_value\": 0.0026363238517333456,\n \"stability_conclusion\": \"unstable\",\n \"conclusion\": \"negative_effect\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"UNRATE.csv: missing value(s) at ['2025-10-01']\",\n \"handling\": \"outside 1959Q4-2019Q4 estimation window; no effect on estimates\"\n },\n {\n \"issue\": \"Observations after 2019Q4 present in both files (incl. 2020 COVID outliers); GDPC1 is the 2026 vintage (revised data, chained 2017 $)\",\n \"handling\": \"post-2019Q4 data excluded per task; current vintage used as provided (log growth rates invariant to base year)\"\n },\n {\n \"issue\": \"Large (|z|>4) in-sample observations: ['1975Q1', '2009Q1']\",\n \"handling\": \"retained (genuine recession/recovery quarters); influence discussed in report\"\n }\n ],\n \"n_input_rows\": {\n \"GDPC1.csv\": 319,\n \"UNRATE.csv\": 945\n },\n \"n_analysed\": 240,\n \"random_seed\": null\n}\n{\n \"lags_0\": 0.028836223207269963,\n \"lags_2\": 0.03422732023615383,\n \"lags_4\": 0.0358346333029657,\n \"lags_8\": 0.0371355041754019,\n \"lags_12\": 0.0364088511022809,\n \"ols_iid_se\": 0.01996009291490984,\n \"beta_excl_z4\": -0.22850787862513172,\n \"hac_wald_break_F\": 5.463105028494939,\n \"hac_wald_break_p\": 0.0047938876117560566,\n \"sub1_hac_se\": 0.03928680828959863,\n \"sub2_hac_se\": 0.06831428793738024,\n \"sub1_alpha\": 0.2542326539884382,\n \"sub2_alpha\": 0.15168581347724602,\n \"r2_full\": 0.4082508284562034,\n \"breakeven_growth_full\": 0.7209211099660549\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.0358346333029657\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03928680828959863\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06831428793738024","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a9be2883-7635-4ab2-b87c-f8ba3517d6bc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}36{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"5919e85d9ff525da3dc4bd7ee445e27298aa660344f30f5ece0f4ba503e23145","message":{"role":"assistant","content":[{"type":"text","text":"The shell was still in `data/`, so the `out/` folder got created inside `data/`. I'll move it to the workspace root."},{"type":"tool_use","id":"toolu_013unsKAeyyPaZMHDafZXaK2","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0176 && mv data/out ./out && ls data && ~/wp29/venv/bin/python out/analysis.py; cat out/table1.csv"}}]}}37{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"72150ff7-1eca-4432-9392-dc8f3f2a73c1","timestamp":"2026-10-30T04:50:32.320Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"5cd2af02-7708-4455-8f0d-7ba44aa982ba","keep":8,"tail":["5919e85d9ff525da3dc4bd7ee445e27298aa660344f30f5ece0f4ba503e23145","121dd83e28cbcc2f11ca016c273179a6ecbf1331a9001fe3d0a26a32e905b21f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3d25a74f68a0d5f8f8036bcab4ee51dcddac9057c8a4ba4a103145d35627a1be"}38{"parentUuid":"a014dd8f-e891-487c-88eb-183d900a6844","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpVheTDwVNTrSLcfLCN","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":1350,"cache_read_input_tokens":11012,"output_tokens":605,"output_tokens_details":{"thinking_tokens":136},"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":1350},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1405,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpVhMM7UijVSKhLne52","requestRef":"72150ff7-1eca-4432-9392-dc8f3f2a73c1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4ac60714-79f6-4c60-9b6e-1326cb61c68a","timestamp":"2026-10-30T04:50:34.903Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}39{"parentUuid":"4ac60714-79f6-4c60-9b6e-1326cb61c68a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpVheTDwVNTrSLcfLCN","type":"message","role":"assistant","content":[{"type":"text","text":"The Chow test rejects, but the two slopes are almost the same, so the rejection seems to come from the intercept. To check this I'll add a slope-only HAC test."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1350,"cache_read_input_tokens":11012,"output_tokens":605,"output_tokens_details":{"thinking_tokens":136},"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":1350},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpVhMM7UijVSKhLne52","requestRef":"72150ff7-1eca-4432-9392-dc8f3f2a73c1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a887d28f-6bf3-4aca-aa4a-d527cc72bbdc","timestamp":"2026-10-30T04:50:34.905Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}40{"parentUuid":"a887d28f-6bf3-4aca-aa4a-d527cc72bbdc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpVheTDwVNTrSLcfLCN","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013byhry3bZ4aScSqF3MGXoU","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\ns=s.replace('sens[\"sub1_hac_se\"]','sens[\"hac_slope_diff\"] = float(mw.params[\"Dg\"]); sens[\"hac_slope_diff_p\"] = float(mw.pvalues[\"Dg\"])\\nsens[\"hac_intercept_diff\"] = float(mw.params[\"D\"]); sens[\"hac_intercept_diff_p\"] = float(mw.pvalues[\"D\"])\\nsens[\"breakeven_sub1\"] = float(-r1.params[\"const\"] / r1.params[\"g\"]); sens[\"breakeven_sub2\"] = float(-r2.params[\"const\"] / r2.params[\"g\"])\\nsens[\"sub1_hac_se\"]',1)\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py | tail -25; cat out/sensitivity.json | grep -E \"diff|breakeven\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1350,"cache_read_input_tokens":11012,"output_tokens":605,"output_tokens_details":{"thinking_tokens":136},"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":1350},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpVhMM7UijVSKhLne52","requestRef":"72150ff7-1eca-4432-9392-dc8f3f2a73c1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b482bca2-af49-4d9c-b84c-6d304d41d63e","timestamp":"2026-10-30T04:50:37.508Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"b482bca2-af49-4d9c-b84c-6d304d41d63e","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013byhry3bZ4aScSqF3MGXoU","type":"tool_result","content":" \"random_seed\": null\n}\n{\n \"lags_0\": 0.028836223207269963,\n \"lags_2\": 0.03422732023615383,\n \"lags_4\": 0.0358346333029657,\n \"lags_8\": 0.0371355041754019,\n \"lags_12\": 0.0364088511022809,\n \"ols_iid_se\": 0.01996009291490984,\n \"beta_excl_z4\": -0.22850787862513172,\n \"hac_wald_break_F\": 5.463105028494939,\n \"hac_wald_break_p\": 0.0047938876117560566,\n \"hac_slope_diff\": -0.014371579610773073,\n \"hac_slope_diff_p\": 0.8536158012976183,\n \"hac_intercept_diff\": -0.10254684051119209,\n \"hac_intercept_diff_p\": 0.24996972549597885,\n \"breakeven_sub1\": 0.9815134738876885,\n \"breakeven_sub2\": 0.5548277280747038,\n \"sub1_hac_se\": 0.03928680828959863,\n \"sub2_hac_se\": 0.06831428793738024,\n \"sub1_alpha\": 0.2542326539884382,\n \"sub2_alpha\": 0.15168581347724602,\n \"r2_full\": 0.4082508284562034,\n \"breakeven_growth_full\": 0.7209211099660549\n}\n \"hac_slope_diff\": -0.014371579610773073,\n \"hac_slope_diff_p\": 0.8536158012976183,\n \"hac_intercept_diff\": -0.10254684051119209,\n \"hac_intercept_diff_p\": 0.24996972549597885,\n \"breakeven_sub1\": 0.9815134738876885,\n \"breakeven_sub2\": 0.5548277280747038,\n \"breakeven_growth_full\": 0.7209211099660549","is_error":false}]},"uuid":"4db6ea68-0b68-4036-a4d1-12ef76d8709f","timestamp":"2026-10-30T04:50:38.394Z","toolUseResult":{"stdout":" \"random_seed\": null\n}\n{\n \"lags_0\": 0.028836223207269963,\n \"lags_2\": 0.03422732023615383,\n \"lags_4\": 0.0358346333029657,\n \"lags_8\": 0.0371355041754019,\n \"lags_12\": 0.0364088511022809,\n \"ols_iid_se\": 0.01996009291490984,\n \"beta_excl_z4\": -0.22850787862513172,\n \"hac_wald_break_F\": 5.463105028494939,\n \"hac_wald_break_p\": 0.0047938876117560566,\n \"hac_slope_diff\": -0.014371579610773073,\n \"hac_slope_diff_p\": 0.8536158012976183,\n \"hac_intercept_diff\": -0.10254684051119209,\n \"hac_intercept_diff_p\": 0.24996972549597885,\n \"breakeven_sub1\": 0.9815134738876885,\n \"breakeven_sub2\": 0.5548277280747038,\n \"sub1_hac_se\": 0.03928680828959863,\n \"sub2_hac_se\": 0.06831428793738024,\n \"sub1_alpha\": 0.2542326539884382,\n \"sub2_alpha\": 0.15168581347724602,\n \"r2_full\": 0.4082508284562034,\n \"breakeven_growth_full\": 0.7209211099660549\n}\n \"hac_slope_diff\": -0.014371579610773073,\n \"hac_slope_diff_p\": 0.8536158012976183,\n \"hac_intercept_diff\": -0.10254684051119209,\n \"hac_intercept_diff_p\": 0.24996972549597885,\n \"breakeven_sub1\": 0.9815134738876885,\n \"breakeven_sub2\": 0.5548277280747038,\n \"breakeven_growth_full\": 0.7209211099660549","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b482bca2-af49-4d9c-b84c-6d304d41d63e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"2d9046a6dab2cc2da9d828daec135fba463b9d7fd91a8f79b8c4bec824fd259e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"The Chow test rejects, but the two slopes are almost the same, so the rejection seems to come from the intercept. To check this I'll add a slope-only HAC test."},{"type":"tool_use","id":"toolu_013byhry3bZ4aScSqF3MGXoU","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\ns=s.replace('sens[\"sub1_hac_se\"]','sens[\"hac_slope_diff\"] = float(mw.params[\"Dg\"]); sens[\"hac_slope_diff_p\"] = float(mw.pvalues[\"Dg\"])\\nsens[\"hac_intercept_diff\"] = float(mw.params[\"D\"]); sens[\"hac_intercept_diff_p\"] = float(mw.pvalues[\"D\"])\\nsens[\"breakeven_sub1\"] = float(-r1.params[\"const\"] / r1.params[\"g\"]); sens[\"breakeven_sub2\"] = float(-r2.params[\"const\"] / r2.params[\"g\"])\\nsens[\"sub1_hac_se\"]',1)\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py | tail -25; cat out/sensitivity.json | grep -E \"diff|breakeven\""}}]}}43{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"c6d53d21-0bde-436b-9c0d-7f7a2d548a68","timestamp":"2026-10-30T04:50:38.396Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"72150ff7-1eca-4432-9392-dc8f3f2a73c1","keep":10,"tail":["2d9046a6dab2cc2da9d828daec135fba463b9d7fd91a8f79b8c4bec824fd259e","c254db8ac74d76a94b34d8fa063779d164bff7acc849602332c30032d0cd4f3b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3aecbc831458edfe782c5e3630bd4b62425e3f821c3020892eb13c952dcb015a"}44{"type":"tools-used","tools":["Bash","Read"],"sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}45{"parentUuid":"4db6ea68-0b68-4036-a4d1-12ef76d8709f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpW9cfWArhf9M3nQQoB","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":1197,"cache_read_input_tokens":12362,"output_tokens":228,"output_tokens_details":{"thinking_tokens":149},"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":1197},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1698,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpW9GLBqu6Qhe7T6RR8","requestRef":"c6d53d21-0bde-436b-9c0d-7f7a2d548a68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"84df3005-0ff1-4910-9069-b7714c400e77","timestamp":"2026-10-30T04:50:41.300Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"84df3005-0ff1-4910-9069-b7714c400e77","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpW9cfWArhf9M3nQQoB","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"Neither the intercept nor the slope differs significantly between periods on its own, but together they do, which suggests the break-even growth rate has shifted. I'm checking the figure and then writing up the report.\n\n","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":1197,"cache_read_input_tokens":12362,"output_tokens":228,"output_tokens_details":{"thinking_tokens":149},"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":1197},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4,"thinkingDisplay":"updates","apiBlockIndex":1,"requestId":"req_011CgXpW9GLBqu6Qhe7T6RR8","requestRef":"c6d53d21-0bde-436b-9c0d-7f7a2d548a68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8f7c0462-fc23-4c83-9f25-d5874e25cb67","timestamp":"2026-10-30T04:50:41.305Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}47{"parentUuid":"8f7c0462-fc23-4c83-9f25-d5874e25cb67","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpW9cfWArhf9M3nQQoB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018fMJ72Qn5xor3SUjpQY52V","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0176/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":1197,"cache_read_input_tokens":12362,"output_tokens":228,"output_tokens_details":{"thinking_tokens":149},"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":1197},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpW9GLBqu6Qhe7T6RR8","requestRef":"c6d53d21-0bde-436b-9c0d-7f7a2d548a68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dadc2280-0137-451f-b5c5-a28b8dda833a","timestamp":"2026-10-30T04:50:41.307Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"dadc2280-0137-451f-b5c5-a28b8dda833a","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018fMJ72Qn5xor3SUjpQY52V","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"b2e07182-3ef9-4ad4-9440-663234243a78","timestamp":"2026-10-30T04:50:41.333Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":97504,"dimensions":{"originalWidth":1050,"originalHeight":750,"displayWidth":1050,"displayHeight":750}}},"sourceToolAssistantUUID":"dadc2280-0137-451f-b5c5-a28b8dda833a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}49{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"f33499e66a86bcf6dd1cc8f0642c7e0e61a37545f5c427c603e5d4266e7279a8","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"thinking","thinking":"Neither the intercept nor the slope differs significantly between periods on its own, but together they do, which suggests the break-even growth rate has shifted. I'm checking the figure and then writing up the report.\n\n","signature":"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"},{"type":"tool_use","id":"toolu_018fMJ72Qn5xor3SUjpQY52V","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0176/out/figure1.png"}}]}}50{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"73d45c33-3b7d-448f-8bff-5bffc1ec9d06","timestamp":"2026-10-30T04:50:41.341Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"c6d53d21-0bde-436b-9c0d-7f7a2d548a68","keep":12,"tail":["f33499e66a86bcf6dd1cc8f0642c7e0e61a37545f5c427c603e5d4266e7279a8","d6816131e2257055995eac8050cc2900daf1faf0d56cdf7ebc65a294fe8eee32"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b0342e19935ec2b6d74fc35773c781bcb0fb0c50ef02d202f9fb624fc8f7d920"}51{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b2e07182-3ef9-4ad4-9440-663234243a78","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}52{"type":"atis-latch","atis":"","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}53{"parentUuid":"b2e07182-3ef9-4ad4-9440-663234243a78","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWN7jh7hkLN6szhPBS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011BX5E5jgUzEbJdJDFiajC2","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960Q1–2019Q4 (F6-conf-03)\n\n## Question\nHow much does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and is that response stable? Estimand: β in Δu_t = α + β·g_t + ε_t, where u_t is the quarterly mean of monthly UNRATE (pp) and g_t = 100·Δln GDPC1_t (% q/q, not annualised). Sample: 1960Q1–2019Q4. Stability is checked with subperiods 1960Q1–1983Q4 and 1984Q1–2019Q4 and a classical Chow test.\n\n## Data and exclusions\n- `GDPC1.csv`: 319 rows, 1947Q1–2026Q3, no gaps, no missing values. `UNRATE.csv`: 945 rows, 1948-01 to 2026-09, no month gaps. One value is missing (2025-10-01, empty cell). It falls outside the window, so it has no effect.\n- u_t is the mean of the three monthly values. Only complete quarters are used, and all quarters in the window are complete. The regression uses 240 quarters: 96 in subperiod 1 and 144 in subperiod 2. The 1959Q4 levels are used only to form the 1960Q1 differences.\n- Everything after 2019Q4 is excluded, as the task requires. That includes the 2020 COVID quarters, which are extreme.\n- GDPC1 is the current (2026) vintage. It is revised data, not real-time data. Log growth rates do not depend on the base year.\n- Two in-sample quarters have |z| > 4: 1975Q1 and 2009Q1. Both are genuine recession quarters, so I kept them. Their influence is examined below.\n\n## Method\n- Baseline: predict Δu by its sample mean. Model: OLS of Δu on a constant and g. Performance is measured as in-sample RMSE.\n- Full-sample inference uses Newey–West HAC standard errors with a Bartlett kernel. The lag length is L = floor(4·(T/100)^(2/9)) = 4 for T = 240, the usual Newey–West rule. The 95% CI is β ± 1.96·SE (normal approximation). Subperiod slope SEs in `table1.csv` are also HAC with L = 4.\n- Stability test: classical Chow F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(T − 4)], with F(2, 236) degrees of freedom.\n- Extra diagnostics (in `out/sensitivity.json`, also written by `analysis.py`): HAC SEs at lags 0, 2, 4, 8 and 12; β with the two |z| > 4 quarters dropped; and a HAC-robust Wald version of the break test from an interaction regression with dummies for 1984 onward.\n\n## Results\n| sample | n | α | β | HAC SE(β) |\n|---|---|---|---|---|\n| full 1960Q1–2019Q4 | 240 | 0.184 | −0.256 | 0.036 |\n| 1960Q1–1983Q4 | 96 | 0.254 | −0.259 | 0.039 |\n| 1984Q1–2019Q4 | 144 | 0.152 | −0.273 | 0.068 |\n\n- Full sample: β = −0.256 and α = 0.184. Each extra 1% of quarterly real GDP growth goes with an unemployment rate about 0.26 pp lower than otherwise. The growth rate at which unemployment stays flat is −α/β ≈ 0.72% per quarter.\n- Fit: RMSE falls from 0.325 pp (mean-only baseline) to 0.250 pp (OLS). R² is 0.41.\n- Stability: the Chow F is 6.09 (p = 0.0026), so the classical test **rejects** equality of (α, β) at 5%. The `stability_conclusion` is therefore `unstable`.\n- The two slopes are almost identical (−0.259 vs −0.273). The rejection comes from a shift in the intercept/slope combination, not from a change in β alone:\n - The flat-unemployment growth rate falls from about 0.98% to about 0.55% per quarter. This fits slower trend growth after 1984.\n - In the HAC interaction regression, the slope difference alone is −0.014 (p = 0.85) and the intercept difference alone is −0.10 (p = 0.25). Their joint HAC Wald test still rejects (F = 5.46, p = 0.005). The individual estimates are imprecise because they are highly correlated.\n - So the Okun *slope* looks stable. The *relationship as a whole* (α, β) does not.\n- Figure: `figure1.png`. Table: `table1.csv`.\n\n## Uncertainty\n- HAC SE(β) = 0.0358 with L = 4. 95% CI: [−0.326, −0.186]. The interval lies entirely below zero, so `conclusion = negative_effect`.\n- Sensitivity of SE(β) to the lag choice:\n - iid OLS: 0.020\n - L = 0: 0.029\n - L = 2: 0.034\n - L = 8: 0.037\n - L = 12: 0.036\n \n The sign conclusion holds for every lag choice. Positive autocorrelation makes the iid SE much too small.\n- Dropping 1975Q1 and 2009Q1 moves β to −0.229. The estimate depends somewhat on a few deep-recession quarters but stays clearly negative.\n- The classical Chow test assumes iid homoskedastic errors, which the HAC diagnostics show is false. Its p-value is therefore optimistic. The HAC-robust joint test gives the same answer (p ≈ 0.005), which makes the rejection more credible.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n - β is a reduced-form correlation, not a causal effect. Δu and g are determined together, and the static difference form leaves out lags of g. Okun responses are known to be spread over several quarters, so the contemporaneous β probably understates the cumulative response.\n - If the errors have stronger long-memory dependence than a Bartlett kernel with 4 lags can capture, the CI is too narrow. The lag sensitivity above suggests this effect is modest.\n- **Break date:** the 1984Q1 split is imposed by the task (start of the Great Moderation), not estimated. I did not run Quandt–Andrews or Bai–Perron tests. Rejection at one fixed date does not show that 1984 is the true break date, and it does not rule out several breaks or gradual drift.\n- **The Chow test answers a joint question.** Its rejection should not be read as \"Okun's coefficient changed\". In these data the slopes are statistically indistinguishable, and the instability is in the intercept, i.e. in trend productivity and labour-force growth.\n- **Data vintage:** current-vintage GDP includes decades of revisions and benchmark changes. Results from real-time data, or from GDI instead of GDP, could differ, especially for the noisy quarterly growth figures. I checked neither.\n- **Not checked:**\n - asymmetry between recessions and expansions\n - level / gap versions of Okun's law\n - HP- or CBO-gap specifications\n - nonlinearity\n - robustness to excluding entire recessions\n- **Outliers:** two quarters have notable leverage (1975Q1, 2009Q1). Robust regression was not used.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4 the Okun coefficient is about -0.26 pp of unemployment per 1% quarterly real GDP growth, and its HAC 95% interval lies below zero.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"hac_lags\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"Reduced-form, contemporaneous association; not causal; omits lagged growth.\"},\n {\"id\":\"C2\",\"text\":\"Real GDP growth substantially improves on a mean-only prediction of the change in unemployment (RMSE 0.325 -> 0.250 pp).\",\"results_keys\":[\"baseline_metric\",\"model_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C3\",\"text\":\"The classical Chow test rejects equality of (alpha, beta) between 1960Q1-1983Q4 and 1984Q1-2019Q4 at the 5% level.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"n_sub1\",\"n_sub2\"],\"status\":\"supported\",\"caveat\":\"Classical test assumes iid errors; a HAC-robust Wald version (in sensitivity.json, not results.json) also rejects. Break date imposed, not estimated.\"},\n {\"id\":\"C4\",\"text\":\"The subperiod slopes are nearly identical (-0.259 vs -0.273), so the instability is driven by the intercept / break-even growth rather than by the Okun slope itself.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"intercept\"],\"status\":\"supported\",\"caveat\":\"Point estimates support it; the separate HAC tests of slope (p=0.85) and intercept (p=0.25) differences are reported in sensitivity.json, not in results.json; individually imprecise.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;r=json.load(open('out/results.json'));[print(k) for c in json.load(open('out/claims.json')) for k in c['results_keys'] if k not in r]\"; ls out"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1273,"cache_read_input_tokens":13559,"output_tokens":3371,"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":1273},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpWMrN95kd6RhVr9mVn","requestRef":"73d45c33-3b7d-448f-8bff-5bffc1ec9d06","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a8980435-45ad-42bb-86e5-9eb1a13c9ea4","timestamp":"2026-10-30T04:51:11.392Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"a8980435-45ad-42bb-86e5-9eb1a13c9ea4","isSidechain":false,"promptId":"7ae6acf5-dd5e-424a-a8ba-3e8ed6dba17e","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011BX5E5jgUzEbJdJDFiajC2","type":"tool_result","content":"analysis.py\nclaims.json\nfigure1.png\nreport.md\nresults.json\nsensitivity.json\ntable1.csv","is_error":false}]},"uuid":"20477cc9-d0f3-44b2-92c2-9054ab612c03","timestamp":"2026-10-30T04:51:11.443Z","toolUseResult":{"stdout":"analysis.py\nclaims.json\nfigure1.png\nreport.md\nresults.json\nsensitivity.json\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a8980435-45ad-42bb-86e5-9eb1a13c9ea4","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}55{"type":"api-request-blob","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","hash":"5283dbeae6863bcbfcd59f89475827b773fbdad0da319e95212988de3e20039c","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_011BX5E5jgUzEbJdJDFiajC2","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960Q1–2019Q4 (F6-conf-03)\n\n## Question\nHow much does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and is that response stable? Estimand: β in Δu_t = α + β·g_t + ε_t, where u_t is the quarterly mean of monthly UNRATE (pp) and g_t = 100·Δln GDPC1_t (% q/q, not annualised). Sample: 1960Q1–2019Q4. Stability is checked with subperiods 1960Q1–1983Q4 and 1984Q1–2019Q4 and a classical Chow test.\n\n## Data and exclusions\n- `GDPC1.csv`: 319 rows, 1947Q1–2026Q3, no gaps, no missing values. `UNRATE.csv`: 945 rows, 1948-01 to 2026-09, no month gaps. One value is missing (2025-10-01, empty cell). It falls outside the window, so it has no effect.\n- u_t is the mean of the three monthly values. Only complete quarters are used, and all quarters in the window are complete. The regression uses 240 quarters: 96 in subperiod 1 and 144 in subperiod 2. The 1959Q4 levels are used only to form the 1960Q1 differences.\n- Everything after 2019Q4 is excluded, as the task requires. That includes the 2020 COVID quarters, which are extreme.\n- GDPC1 is the current (2026) vintage. It is revised data, not real-time data. Log growth rates do not depend on the base year.\n- Two in-sample quarters have |z| > 4: 1975Q1 and 2009Q1. Both are genuine recession quarters, so I kept them. Their influence is examined below.\n\n## Method\n- Baseline: predict Δu by its sample mean. Model: OLS of Δu on a constant and g. Performance is measured as in-sample RMSE.\n- Full-sample inference uses Newey–West HAC standard errors with a Bartlett kernel. The lag length is L = floor(4·(T/100)^(2/9)) = 4 for T = 240, the usual Newey–West rule. The 95% CI is β ± 1.96·SE (normal approximation). Subperiod slope SEs in `table1.csv` are also HAC with L = 4.\n- Stability test: classical Chow F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(T − 4)], with F(2, 236) degrees of freedom.\n- Extra diagnostics (in `out/sensitivity.json`, also written by `analysis.py`): HAC SEs at lags 0, 2, 4, 8 and 12; β with the two |z| > 4 quarters dropped; and a HAC-robust Wald version of the break test from an interaction regression with dummies for 1984 onward.\n\n## Results\n| sample | n | α | β | HAC SE(β) |\n|---|---|---|---|---|\n| full 1960Q1–2019Q4 | 240 | 0.184 | −0.256 | 0.036 |\n| 1960Q1–1983Q4 | 96 | 0.254 | −0.259 | 0.039 |\n| 1984Q1–2019Q4 | 144 | 0.152 | −0.273 | 0.068 |\n\n- Full sample: β = −0.256 and α = 0.184. Each extra 1% of quarterly real GDP growth goes with an unemployment rate about 0.26 pp lower than otherwise. The growth rate at which unemployment stays flat is −α/β ≈ 0.72% per quarter.\n- Fit: RMSE falls from 0.325 pp (mean-only baseline) to 0.250 pp (OLS). R² is 0.41.\n- Stability: the Chow F is 6.09 (p = 0.0026), so the classical test **rejects** equality of (α, β) at 5%. The `stability_conclusion` is therefore `unstable`.\n- The two slopes are almost identical (−0.259 vs −0.273). The rejection comes from a shift in the intercept/slope combination, not from a change in β alone:\n - The flat-unemployment growth rate falls from about 0.98% to about 0.55% per quarter. This fits slower trend growth after 1984.\n - In the HAC interaction regression, the slope difference alone is −0.014 (p = 0.85) and the intercept difference alone is −0.10 (p = 0.25). Their joint HAC Wald test still rejects (F = 5.46, p = 0.005). The individual estimates are imprecise because they are highly correlated.\n - So the Okun *slope* looks stable. The *relationship as a whole* (α, β) does not.\n- Figure: `figure1.png`. Table: `table1.csv`.\n\n## Uncertainty\n- HAC SE(β) = 0.0358 with L = 4. 95% CI: [−0.326, −0.186]. The interval lies entirely below zero, so `conclusion = negative_effect`.\n- Sensitivity of SE(β) to the lag choice:\n - iid OLS: 0.020\n - L = 0: 0.029\n - L = 2: 0.034\n - L = 8: 0.037\n - L = 12: 0.036\n \n The sign conclusion holds for every lag choice. Positive autocorrelation makes the iid SE much too small.\n- Dropping 1975Q1 and 2009Q1 moves β to −0.229. The estimate depends somewhat on a few deep-recession quarters but stays clearly negative.\n- The classical Chow test assumes iid homoskedastic errors, which the HAC diagnostics show is false. Its p-value is therefore optimistic. The HAC-robust joint test gives the same answer (p ≈ 0.005), which makes the rejection more credible.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n - β is a reduced-form correlation, not a causal effect. Δu and g are determined together, and the static difference form leaves out lags of g. Okun responses are known to be spread over several quarters, so the contemporaneous β probably understates the cumulative response.\n - If the errors have stronger long-memory dependence than a Bartlett kernel with 4 lags can capture, the CI is too narrow. The lag sensitivity above suggests this effect is modest.\n- **Break date:** the 1984Q1 split is imposed by the task (start of the Great Moderation), not estimated. I did not run Quandt–Andrews or Bai–Perron tests. Rejection at one fixed date does not show that 1984 is the true break date, and it does not rule out several breaks or gradual drift.\n- **The Chow test answers a joint question.** Its rejection should not be read as \"Okun's coefficient changed\". In these data the slopes are statistically indistinguishable, and the instability is in the intercept, i.e. in trend productivity and labour-force growth.\n- **Data vintage:** current-vintage GDP includes decades of revisions and benchmark changes. Results from real-time data, or from GDI instead of GDP, could differ, especially for the noisy quarterly growth figures. I checked neither.\n- **Not checked:**\n - asymmetry between recessions and expansions\n - level / gap versions of Okun's law\n - HP- or CBO-gap specifications\n - nonlinearity\n - robustness to excluding entire recessions\n- **Outliers:** two quarters have notable leverage (1975Q1, 2009Q1). Robust regression was not used.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4 the Okun coefficient is about -0.26 pp of unemployment per 1% quarterly real GDP growth, and its HAC 95% interval lies below zero.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"hac_lags\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"Reduced-form, contemporaneous association; not causal; omits lagged growth.\"},\n {\"id\":\"C2\",\"text\":\"Real GDP growth substantially improves on a mean-only prediction of the change in unemployment (RMSE 0.325 -> 0.250 pp).\",\"results_keys\":[\"baseline_metric\",\"model_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C3\",\"text\":\"The classical Chow test rejects equality of (alpha, beta) between 1960Q1-1983Q4 and 1984Q1-2019Q4 at the 5% level.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"n_sub1\",\"n_sub2\"],\"status\":\"supported\",\"caveat\":\"Classical test assumes iid errors; a HAC-robust Wald version (in sensitivity.json, not results.json) also rejects. Break date imposed, not estimated.\"},\n {\"id\":\"C4\",\"text\":\"The subperiod slopes are nearly identical (-0.259 vs -0.273), so the instability is driven by the intercept / break-even growth rather than by the Okun slope itself.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"intercept\"],\"status\":\"supported\",\"caveat\":\"Point estimates support it; the separate HAC tests of slope (p=0.85) and intercept (p=0.25) differences are reported in sensitivity.json, not in results.json; individually imprecise.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;r=json.load(open('out/results.json'));[print(k) for c in json.load(open('out/claims.json')) for k in c['results_keys'] if k not in r]\"; ls out"}}]}}56{"type":"api-request","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","id":"a9ff5f59-d011-46f0-b164-b6d3511e80bd","timestamp":"2026-10-30T04:51:11.447Z","version":"2.1.314","querySource":"sdk","shapeHash":"3d9735a086763e381a15b1bf89c2c1e18b510b1586214bbd7f0a0b7db826b3eb","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":"73d45c33-3b7d-448f-8bff-5bffc1ec9d06","keep":14,"tail":["5283dbeae6863bcbfcd59f89475827b773fbdad0da319e95212988de3e20039c","58dccc557d6691dbeeb9c9e0d42dbf89f9d1b39f76e25c70b10a1273fdefd649"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"188ffb9bac43df9c18c42e072c06916edfee7a8a51de3896a0714c5a4cba4950"}57{"parentUuid":"20477cc9-d0f3-44b2-92c2-9054ab612c03","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYarWKB7FnoifeF4Sn","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":3385,"cache_read_input_tokens":14832,"output_tokens":925,"output_tokens_details":{"thinking_tokens":13},"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":3385},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6309,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpYaae75aRpTKJxUn6q","requestRef":"a9ff5f59-d011-46f0-b164-b6d3511e80bd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8f6bf708-4ede-4c41-8f0a-4ae26ee41868","timestamp":"2026-10-30T04:51:18.871Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"8f6bf708-4ede-4c41-8f0a-4ae26ee41868","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYarWKB7FnoifeF4Sn","type":"message","role":"assistant","content":[{"type":"text","text":"I estimated Okun's law for the US over 1960Q1–2019Q4. Unemployment reliably falls when output grows, but the classical Chow test says the relationship is not stable across the two subperiods. Rerunning `~/wp29/venv/bin/python out/analysis.py` regenerates the results, figure and table.\n\n**Main results** (240 quarters):\n- **Okun coefficient:** β = −0.256 (α = 0.184). Each extra 1% of quarterly real GDP growth goes with an unemployment rate about 0.26 points lower.\n- **Uncertainty:** the robust standard error is 0.036, using Newey–West with 4 lags (the standard rule of thumb for 240 quarters). The 95% interval is [−0.326, −0.186], entirely below zero, so the conclusion is `negative_effect`.\n- **Fit:** prediction error drops from 0.325 points (predicting the average change every quarter) to 0.250 points with the regression.\n\n**Stability:**\n- **Chow test:** F = 6.09, p = 0.0026, so it rejects at 5% and the result is recorded as `unstable`.\n- **The slope itself did not change:** −0.259 before 1984 and −0.273 after. A robust test of the slope difference alone gives p = 0.85.\n- **What shifted is the intercept:** the growth rate at which unemployment stays flat fell from about 0.98% to about 0.55% per quarter. A robust version of the joint test also rejects (p = 0.005). Read the instability as slower trend growth, not as a change in how unemployment responds to growth.\n\n**Data checks:** the one missing unemployment value (October 2025) is outside the sample, and all post-2019 data is excluded as required. Two extreme recession quarters, 1975Q1 and 2009Q1, were kept; dropping them moves β to −0.229, still clearly negative.\n\n**Limitations:**\n- β is a correlation, not a causal effect, and leaves out lagged growth, so it probably understates the full response over several quarters.\n- The 1984 break date was set by the task. I did not test whether the true break is elsewhere or whether there are several.\n- The GDP figures are today's revised data, not what was known at the time.\n- I did not check recession/expansion asymmetry or other forms of Okun's law (e.g. output-gap versions).\n\nTwo things in the claims file: claims C3 and C4 rely on figures that are only in `sensitivity.json`, not in `results.json`. Their caveats say so.\n\nFiles are in `out/`:\n- `results.json`\n- `report.md`\n- `analysis.py`\n- `figure1.png`\n- `table1.csv`\n- `claims.json`\n- `sensitivity.json` (extra diagnostics, not required by the task)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3385,"cache_read_input_tokens":14832,"output_tokens":925,"output_tokens_details":{"thinking_tokens":13},"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":3385},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpYaae75aRpTKJxUn6q","requestRef":"a9ff5f59-d011-46f0-b164-b6d3511e80bd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"01f791aa-fecd-4d87-81ec-5e5f3dc9e430","timestamp":"2026-10-30T04:51:20.624Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0176","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","version":"2.1.314","gitBranch":"HEAD"}59{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"01f791aa-fecd-4d87-81ec-5e5f3dc9e430","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c"}60{"type":"cost-state","sessionId":"9a8f32a1-cd46-4b27-b476-502eb676db7c","totalCostUSD":0.28698599999999996,"totalAPIDuration":84341,"totalAPIDurationWithoutRetries":84338,"totalToolDuration":2788,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":87243,"startTime":1793335793407,"modelUsage":{"claude-opus-5-5":{"inputTokens":18,"outputTokens":9500,"thinkingTokens":461,"cacheReadInputTokens":66745,"cacheCreationInputTokens":16713,"cacheCreationEphemeral5mInputTokens":16713,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.28698599999999996}},"hasUnknownModelCost":false}61