{"type":"atis-latch","atis":"","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:48:24.022Z","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","content":"Begin"} {"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:48:24.028Z","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":null,"isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":"Begin"},"uuid":"4cf94283-e010-4bb6-accf-8434e5497529","timestamp":"2026-10-30T04:48:24.032Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-shape","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","timestamp":"2026-10-30T04:48:24.045Z","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/RC0169\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n"}],"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}}]}} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"c4a8d125-1de8-46f2-aef3-c477a64b6757","timestamp":"2026-10-30T04:48:24.045Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"63fe633920f43d6463e6b9641c04cf4e814da770d6edc580880c7a9bdb5572d1"} {"parentUuid":"4cf94283-e010-4bb6-accf-8434e5497529","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"ab82392a-4ef4-4763-9da0-64a46e9155d0","timestamp":"2026-10-30T04:48:24.037Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"ab82392a-4ef4-4763-9da0-64a46e9155d0","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"76a31d30-7c6f-4663-bde4-ead8221c5bf3","timestamp":"2026-10-30T04:48:24.037Z","rendered":[{"content":"\nToday's date is 2026-10-30.\n"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"76a31d30-7c6f-4663-bde4-ead8221c5bf3","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 ","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"966568ee-96bf-42d3-9442-281351f28cca","timestamp":"2026-10-30T04:48:24.038Z","rendered":[{"content":"\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 \n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"tools-used","tools":["Bash"],"sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":"966568ee-96bf-42d3-9442-281351f28cca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLFGCfTYJqAbC9dFNA","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":117,"output_tokens_details":{"thinking_tokens":15},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":379,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpLEyqoWxghLmCKHM2w","requestRef":"c4a8d125-1de8-46f2-aef3-c477a64b6757","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a54de21c-c8a5-4e34-b5cb-b0ce3f0b8013","timestamp":"2026-10-30T04:48:25.334Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"a54de21c-c8a5-4e34-b5cb-b0ce3f0b8013","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLFGCfTYJqAbC9dFNA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01S9VF9Do69Pz4VQ5iNAxWRq","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":117,"output_tokens_details":{"thinking_tokens":15},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpLEyqoWxghLmCKHM2w","requestRef":"c4a8d125-1de8-46f2-aef3-c477a64b6757","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b38fb73b-c159-4b83-879b-3794776427d8","timestamp":"2026-10-30T04:48:25.913Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"b38fb73b-c159-4b83-879b-3794776427d8","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n# 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.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:42 .\ndrwxr-xr-x 103 simon-pierreboucher staff 3296 oct. 30 00:48 ..\n-rw-r--r-- 1 simon-pierreboucher staff 600 oct. 29 23:42 bundle.json\ndrwxr-xr-x 5 simon-pierreboucher staff 160 oct. 29 23:27 data\n-rw-r--r-- 1 simon-pierreboucher staff 2823 oct. 29 23:35 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 6312 oct. 29 23:35 TASK.md\ndata:\ntotal 56\ndrwxr-xr-x 5 simon-pierreboucher staff 160 oct. 29 23:27 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:42 ..\n-rw-r--r-- 1 simon-pierreboucher staff 6548 oct. 29 23:27 GDPC1.csv\n-rw-r--r-- 1 simon-pierreboucher staff 1185 oct. 29 23:27 README.md\n-rw-r--r-- 1 simon-pierreboucher staff 14211 oct. 29 23:27 UNRATE.csv","is_error":true,"tool_use_id":"toolu_01S9VF9Do69Pz4VQ5iNAxWRq"}]},"uuid":"57f644f5-dcee-4899-8c6e-d949174142b1","timestamp":"2026-10-30T04:48:26.017Z","toolUseResult":"Error: Exit code 1\n# 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.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:42 .\ndrwxr-xr-x 103 simon-pierreboucher staff 3296 oct. 30 00:48 ..\n-rw-r--r-- 1 simon-pierreboucher staff 600 oct. 29 23:42 bundle.json\ndrwxr-xr-x 5 simon-pierreboucher staff 160 oct. 29 23:27 data\n-rw-r--r-- 1 simon-pierreboucher staff 2823 oct. 29 23:35 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 6312 oct. 29 23:35 TASK.md\ndata:\ntotal 56\ndrwxr-xr-x 5 simon-pierreboucher staff 160 oct. 29 23:27 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:42 ..\n-rw-r--r-- 1 simon-pierreboucher staff 6548 oct. 29 23:27 GDPC1.csv\n-rw-r--r-- 1 simon-pierreboucher staff 1185 oct. 29 23:27 README.md\n-rw-r--r-- 1 simon-pierreboucher staff 14211 oct. 29 23:27 UNRATE.csv","sandboxed":false,"sourceToolAssistantUUID":"b38fb73b-c159-4b83-879b-3794776427d8","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"d2f4946216d07d5ac7669c3fd926672619b2c8cf874dd0a651adb4d18b4586c5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01S9VF9Do69Pz4VQ5iNAxWRq","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"329c94b7-5684-47b3-8301-43c3de91633d","timestamp":"2026-10-30T04:48:26.021Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"c4a8d125-1de8-46f2-aef3-c477a64b6757","keep":2,"tail":["d2f4946216d07d5ac7669c3fd926672619b2c8cf874dd0a651adb4d18b4586c5","4145670251279519ad5beaf44f0c317f8ebe18c7bb046906058f99c7fe770bfc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a4bccf8305c35aeefb8bae5346c85bb700851e2022104619551d7ad45f3b72f3"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"57f644f5-dcee-4899-8c6e-d949174142b1","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"type":"atis-latch","atis":"","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":"57f644f5-dcee-4899-8c6e-d949174142b1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLPbWdL8sdzEqARFMX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01B4nHjz4gBcvtBtSuTbfdeL","name":"Bash","input":{"command":"cat data/README.md gate_spec.json bundle.json; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data, provenance, gate spec"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3060,"cache_read_input_tokens":4107,"output_tokens":145,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3060},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpLPKtnmrZWGNDDRAF3","requestRef":"329c94b7-5684-47b3-8301-43c3de91633d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1f093532-5e8c-49d7-8f46-b1203eec572f","timestamp":"2026-10-30T04:48:27.845Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"1f093532-5e8c-49d7-8f46-b1203eec572f","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01B4nHjz4gBcvtBtSuTbfdeL","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{\n \"task_id\": \"F6-conf-03\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"sample_start\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"sample_end\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"n_sub1\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"n_sub2\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"intercept\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"hac_lags\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"beta_sub1\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"beta_sub2\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"chow_f_stat\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"chow_p_value\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"stability_conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\",\n \"chronology\"\n ],\n \"ci_pairs\": [\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"chow_f_stat\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [\n [\n \"sample_start\",\n \"sample_end\"\n ]\n ],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}{\n \"task_id\": \"F6-conf-03\",\n \"family\": \"F6\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:42:41.725294+00:00\",\n \"files\": {\n \"TASK.md\": \"64afb4744b89e1ab9b45cefc3fad325b1857216f04a3d3cc54ed3b1681db2a0e\",\n \"data/GDPC1.csv\": \"1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343\",\n \"data/README.md\": \"7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658\",\n \"data/UNRATE.csv\": \"621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c\",\n \"gate_spec.json\": \"bced13a911d728cc853d5a88f4412cf86338d82c325eb7891ba2f5fd86317f61\"\n }\n}==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 data/GDPC1.csv\n 946 data/UNRATE.csv\n 1266 total\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 data/GDPC1.csv\n7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 data/README.md\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c data/UNRATE.csv","is_error":false}]},"uuid":"5e40ef68-33f5-423b-bb93-d372df0282a0","timestamp":"2026-10-30T04:48:27.905Z","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{\n \"task_id\": \"F6-conf-03\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"sample_start\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"sample_end\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"n_sub1\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"n_sub2\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"intercept\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"hac_lags\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"beta_sub1\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"beta_sub2\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"chow_f_stat\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"chow_p_value\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"stability_conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\",\n \"chronology\"\n ],\n \"ci_pairs\": [\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"chow_f_stat\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [\n [\n \"sample_start\",\n \"sample_end\"\n ]\n ],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}{\n \"task_id\": \"F6-conf-03\",\n \"family\": \"F6\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:42:41.725294+00:00\",\n \"files\": {\n \"TASK.md\": \"64afb4744b89e1ab9b45cefc3fad325b1857216f04a3d3cc54ed3b1681db2a0e\",\n \"data/GDPC1.csv\": \"1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343\",\n \"data/README.md\": \"7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658\",\n \"data/UNRATE.csv\": \"621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c\",\n \"gate_spec.json\": \"bced13a911d728cc853d5a88f4412cf86338d82c325eb7891ba2f5fd86317f61\"\n }\n}==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 data/GDPC1.csv\n 946 data/UNRATE.csv\n 1266 total\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 data/GDPC1.csv\n7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 data/README.md\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c data/UNRATE.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1f093532-5e8c-49d7-8f46-b1203eec572f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"0522c5c2b853d5ad96a1578a57de533efece372c500a028b457ae05fb883f21e","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01B4nHjz4gBcvtBtSuTbfdeL","name":"Bash","input":{"command":"cat data/README.md gate_spec.json bundle.json; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data, provenance, gate spec"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"d5cd10c3-63e3-4a0f-81ce-5bd5a1b80f15","timestamp":"2026-10-30T04:48:27.909Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"329c94b7-5684-47b3-8301-43c3de91633d","keep":4,"tail":["0522c5c2b853d5ad96a1578a57de533efece372c500a028b457ae05fb883f21e","8faba1d402d1a668f47892f76ab324378fe74c6b7a1431cfb4ad036d57d39307"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1976bfaa74f603a5cb79100c28cdda2499e8a9d257dad9c61f977c8aea658ac1"} {"parentUuid":"5e40ef68-33f5-423b-bb93-d372df0282a0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLXfvgWhxEZscm5xYi","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":2652,"cache_read_input_tokens":7167,"output_tokens":444,"output_tokens_details":{"thinking_tokens":73},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2652},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":434,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpLXQ4ELcPwmJdweYsJ","requestRef":"d5cd10c3-63e3-4a0f-81ce-5bd5a1b80f15","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"176b199e-2f75-4a18-a4a0-4a3942603865","timestamp":"2026-10-30T04:48:29.536Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"176b199e-2f75-4a18-a4a0-4a3942603865","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLXfvgWhxEZscm5xYi","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QV8v2qtnuFsFZUPkvJ28T1","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f in ['GDPC1','UNRATE']:\n d=pd.read_csv(f'data/{f}.csv',na_values=['.',''])\n d['observation_date']=pd.to_datetime(d.observation_date)\n print(f,d.shape,d.dtypes.to_dict(),d.isna().sum().to_dict(),d.observation_date.duplicated().sum(),d.observation_date.min(),d.observation_date.max())\n print(d[d[f].isna()])\n freq='QS' if f=='GDPC1' else 'MS'\n full=pd.date_range(d.observation_date.min(),d.observation_date.max(),freq=freq)\n print('missing dates',set(full)-set(d.observation_date))\n print(d[f].describe())\n\"","description":"Audit both CSV files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2652,"cache_read_input_tokens":7167,"output_tokens":444,"output_tokens_details":{"thinking_tokens":73},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2652},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpLXQ4ELcPwmJdweYsJ","requestRef":"d5cd10c3-63e3-4a0f-81ce-5bd5a1b80f15","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ed45fb73-eb02-4d35-97bf-6d53dc974418","timestamp":"2026-10-30T04:48:31.897Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"ed45fb73-eb02-4d35-97bf-6d53dc974418","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QV8v2qtnuFsFZUPkvJ28T1","type":"tool_result","content":"GDPC1 (319, 2) {'observation_date': dtype(' contract.md <<'EOF'\n# Contract — F6-conf-03\n**Question.** How strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth (Okun's law, difference form), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?\n\n**Estimands.** β (and α) in Δu_t = α + β g_t + ε_t, OLS; u_t = mean of 3 monthly UNRATE values; g_t = 100·Δln GDPC1 (quarterly, not annualised). Meaningful as a reduced-form conditional-mean association (not causal), under stationarity of (Δu, g) within the sample and a linear, time-invariant relation (the latter is tested). Uncertainty: Newey–West HAC (Bartlett) SE for full-sample β, 95% CI (normal critical value). Stability: subperiod OLS slopes and classical Chow SSR F-test, df (2, n−4).\n\n**Outputs.** out/results.json (keys: sample_start, sample_end, n_sub1, n_sub2, baseline_metric, model_metric, effect_estimate, intercept, effect_se, hac_lags, effect_ci_low, effect_ci_high, beta_sub1, beta_sub2, chow_f_stat, chow_p_value, stability_conclusion, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (period,n,intercept,slope,slope_se; 3 rows); out/report.md (6 sections); out/analysis.py; out/claims.json; plus state ledgers and exclusions.csv.\n\n**Information rules.** Only data/GDPC1.csv and data/UNRATE.csv. Sample 240 quarters 1960Q1–2019Q4; 1959Q4 levels used for the first differences; nothing after 2019Q4 enters any estimate.\n\n**Invalidity / impossibility.** Missing monthly UNRATE or GDPC1 values within 1959Q4–2019Q4; sample not equal to 240 quarters; using post-2019 data; non-HAC full-sample SE.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols | range | missing | dup dates |\n|---|---|---|---|---|---|---|\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1) | 1947-01-01 .. 2026-07-01, quarterly, no gaps | 0 | 0 |\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE) | 1948-01-01 .. 2026-09-01, monthly, no gaps in dates | 1 (2025-10-01, empty value) | 0 |\n\nUnits: GDPC1 billions chained 2017 USD SAAR (only log-differences used, so units/annualisation of the level drop out); UNRATE percent SA. GDPC1 range 2172–24611; UNRATE range 2.5–14.8 — plausible.\n\nAnomalies: UNRATE 2025-10-01 blank (BLS did not publish October 2025 during the federal shutdown). Outside the 1959Q4–2019Q4 window, so irrelevant; handled by dropping out-of-window observations.\n\nInformation availability: both files extend beyond 2019Q4 (current vintage, 2026). Post-2019Q4 rows are excluded before any computation. Note the GDPC1 vintage is 2026 (chained 2017 dollars), i.e. revised data, not real-time — acceptable since the task is a historical estimate, but noted as a limitation.\nEOF\ncat > log.md <<'EOF'\n# Log\n- 2026-10-30 P0 passed: contract written.\n- 2026-10-30 P1: audited data; hashes match README; one missing UNRATE value (2025-10) outside window. Decision: restrict to 1959Q4–2019Q4 levels; HAC lag rule floor(4(T/100)^(2/9)) = 4 for T=240.\nEOF","description":"Write contract, phase ledger, audit, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":166,"cache_read_input_tokens":10691,"output_tokens":1801,"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":166},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpLyXBffuCeBHirJs6Q","requestRef":"6e15c2ea-f3d3-4ad5-9291-534a0502f983","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1bab6b66-8933-4e46-8cd1-d6ffd3bd4780","timestamp":"2026-10-30T04:48:50.321Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"1bab6b66-8933-4e46-8cd1-d6ffd3bd4780","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017qsmfCkfW43nsdgoGaJpbk","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"59a93665-219c-4025-8961-5d3bc01e536e","timestamp":"2026-10-30T04:48:50.380Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1bab6b66-8933-4e46-8cd1-d6ffd3bd4780","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169/out/state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"6dac17c39888d9a1885a159e5c031d8be86ffdfd61d91fed7e141466f4b42b3c","message":{"role":"assistant","content":[{"type":"text","text":"Now P0/P1 state files."},{"type":"tool_use","id":"toolu_017qsmfCkfW43nsdgoGaJpbk","name":"Bash","input":{"command":"cd out/state\ncat > contract.md <<'EOF'\n# Contract — F6-conf-03\n**Question.** How strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth (Okun's law, difference form), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?\n\n**Estimands.** β (and α) in Δu_t = α + β g_t + ε_t, OLS; u_t = mean of 3 monthly UNRATE values; g_t = 100·Δln GDPC1 (quarterly, not annualised). Meaningful as a reduced-form conditional-mean association (not causal), under stationarity of (Δu, g) within the sample and a linear, time-invariant relation (the latter is tested). Uncertainty: Newey–West HAC (Bartlett) SE for full-sample β, 95% CI (normal critical value). Stability: subperiod OLS slopes and classical Chow SSR F-test, df (2, n−4).\n\n**Outputs.** out/results.json (keys: sample_start, sample_end, n_sub1, n_sub2, baseline_metric, model_metric, effect_estimate, intercept, effect_se, hac_lags, effect_ci_low, effect_ci_high, beta_sub1, beta_sub2, chow_f_stat, chow_p_value, stability_conclusion, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (period,n,intercept,slope,slope_se; 3 rows); out/report.md (6 sections); out/analysis.py; out/claims.json; plus state ledgers and exclusions.csv.\n\n**Information rules.** Only data/GDPC1.csv and data/UNRATE.csv. Sample 240 quarters 1960Q1–2019Q4; 1959Q4 levels used for the first differences; nothing after 2019Q4 enters any estimate.\n\n**Invalidity / impossibility.** Missing monthly UNRATE or GDPC1 values within 1959Q4–2019Q4; sample not equal to 240 quarters; using post-2019 data; non-HAC full-sample SE.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols | range | missing | dup dates |\n|---|---|---|---|---|---|---|\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1) | 1947-01-01 .. 2026-07-01, quarterly, no gaps | 0 | 0 |\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE) | 1948-01-01 .. 2026-09-01, monthly, no gaps in dates | 1 (2025-10-01, empty value) | 0 |\n\nUnits: GDPC1 billions chained 2017 USD SAAR (only log-differences used, so units/annualisation of the level drop out); UNRATE percent SA. GDPC1 range 2172–24611; UNRATE range 2.5–14.8 — plausible.\n\nAnomalies: UNRATE 2025-10-01 blank (BLS did not publish October 2025 during the federal shutdown). Outside the 1959Q4–2019Q4 window, so irrelevant; handled by dropping out-of-window observations.\n\nInformation availability: both files extend beyond 2019Q4 (current vintage, 2026). Post-2019Q4 rows are excluded before any computation. Note the GDPC1 vintage is 2026 (chained 2017 dollars), i.e. revised data, not real-time — acceptable since the task is a historical estimate, but noted as a limitation.\nEOF\ncat > log.md <<'EOF'\n# Log\n- 2026-10-30 P0 passed: contract written.\n- 2026-10-30 P1: audited data; hashes match README; one missing UNRATE value (2025-10) outside window. Decision: restrict to 1959Q4–2019Q4 levels; HAC lag rule floor(4(T/100)^(2/9)) = 4 for T=240.\nEOF","description":"Write contract, phase ledger, audit, log"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"0eb3b63c-7dd6-4bc6-8984-50d44cd97c8d","timestamp":"2026-10-30T04:48:50.383Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"6e15c2ea-f3d3-4ad5-9291-534a0502f983","keep":10,"tail":["6dac17c39888d9a1885a159e5c031d8be86ffdfd61d91fed7e141466f4b42b3c","b9e40313792b5851267f2167c67bc088ac73133144ad4d064080a935a98aef51"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a753dc9d26d9645b3721a8ff6ef3402bbe5a1f1aa72f154028ef5b30504a5780"} {"parentUuid":"59a93665-219c-4025-8961-5d3bc01e536e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpNBgTgrhxeP4ZB8qm6","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":1816,"cache_read_input_tokens":10857,"output_tokens":3801,"output_tokens_details":{"thinking_tokens":237},"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":1816},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2208,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpNBVYN6tnw3vo7Bq93","requestRef":"0eb3b63c-7dd6-4bc6-8984-50d44cd97c8d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4aea0513-6b05-4d84-8241-658afcac1c7d","timestamp":"2026-10-30T04:48:54.352Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169/out/state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"4aea0513-6b05-4d84-8241-658afcac1c7d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpNBgTgrhxeP4ZB8qm6","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UkrBZ2K8UDH6nmS9ty24Bh","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\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\"\nos.makedirs(OUT, exist_ok=True)\ngdp = pd.read_csv(\"data/GDPC1.csv\", na_values=[\".\"])\nun = pd.read_csv(\"data/UNRATE.csv\", na_values=[\".\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"observation_date\"] = pd.to_datetime(gdp[\"observation_date\"])\nun[\"observation_date\"] = pd.to_datetime(un[\"observation_date\"])\n\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()][\"observation_date\"].dt.strftime(\"%Y-%m-%d\").tolist()\nif miss:\n data_issues.append({\"issue\": f\"UNRATE missing value(s) at {miss} (blank in raw FRED CSV)\",\n \"handling\": \"outside the 1959Q4-2019Q4 window; dropped with all post-2019Q4 observations, no effect on estimates\"})\ndata_issues.append({\"issue\": \"Both series extend beyond 2019Q4 (to 2026) and are the 2026 vintage (revised, not real-time)\",\n \"handling\": \"all observations after 2019Q4 excluded before computation; vintage noted as limitation\"})\n\n# Quarterly unemployment = mean of 3 months; require all 3 months present\nun[\"q\"] = un[\"observation_date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\ngdp[\"q\"] = gdp[\"observation_date\"].dt.to_period(\"Q\")\ndf = gdp.set_index(\"q\")[[\"GDPC1\"]].join(uq, how=\"left\")\n\nexcl = []\ndef log(step, rule, before, after, why):\n excl.append(dict(step=step, rule=rule, n_before=before, n_after=after, n_removed=before - after, rationale=why))\n\nn0 = len(df)\nwin = df.loc[pd.Period(\"1959Q4\"):pd.Period(\"2019Q4\")].copy()\nlog(1, \"keep quarters 1959Q4-2019Q4 (GDPC1 quarters as unit)\", n0, len(win),\n \"task window; 1959Q4 needed only for lagged levels; post-2019Q4 forbidden\")\nassert (win[\"count\"] == 3).all() and win[\"GDPC1\"].notna().all(), \"incomplete data inside window\"\nwin[\"u\"] = win[\"mean\"]\nwin[\"du\"] = win[\"u\"].diff()\nwin[\"g\"] = 100 * np.log(win[\"GDPC1\"]).diff()\nreg = win.dropna(subset=[\"du\", \"g\"]).copy()\nlog(2, \"drop 1959Q4 (no lagged level, differences undefined)\", len(win), len(reg),\n \"first-difference construction\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nassert len(reg) == 240 and str(reg.index[0]) == \"1960Q1\" and str(reg.index[-1]) == \"2019Q4\"\n\ny, X = reg[\"du\"].values, sm.add_constant(reg[\"g\"].values)\nn = len(y)\n# Baseline: mean-only prediction\nbaseline_rmse = float(np.sqrt(np.mean((y - y.mean()) ** 2)))\n# Full sample OLS with Newey-West HAC (Bartlett) SE\nHAC_LAGS = int(np.floor(4 * (n / 100) ** (2 / 9))) # Newey-West (1994) rule of thumb -> 4\nols = sm.OLS(y, X).fit()\nhac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\nalpha, beta = float(ols.params[0]), float(ols.params[1])\nse = float(hac.bse[1])\nz = stats.norm.ppf(0.975)\nci = (beta - z * se, beta + z * se)\nmodel_rmse = float(np.sqrt(np.mean(ols.resid ** 2)))\n\n# Subperiods\ns1 = reg.index <= pd.Period(\"1983Q4\")\ns2 = ~s1\nfits = {}\nfor name, m in [(\"sub1\", s1), (\"sub2\", s2)]:\n Xs = sm.add_constant(reg[\"g\"].values[m])\n f = sm.OLS(y[m], Xs).fit()\n fh = sm.OLS(y[m], Xs).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\n fits[name] = (f, fh, int(m.sum()))\nssr_p = ols.ssr\nssr_u = fits[\"sub1\"][0].ssr + fits[\"sub2\"][0].ssr\nk = 2\nchow_f = float(((ssr_p - ssr_u) / k) / (ssr_u / (n - 2 * k)))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\nconclusion = \"positive_effect\" if ci[0] > 0 else (\"negative_effect\" if ci[1] < 0 else \"no_detectable_effect\")\nresults = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": reg.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": reg.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": fits[\"sub1\"][2],\n \"n_sub2\": fits[\"sub2\"][2],\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": HAC_LAGS,\n \"effect_ci_low\": float(ci[0]),\n \"effect_ci_high\": float(ci[1]),\n \"beta_sub1\": float(fits[\"sub1\"][0].params[1]),\n \"beta_sub2\": float(fits[\"sub2\"][0].params[1]),\n \"chow_f_stat\": chow_f,\n \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n # supplementary (not required)\n \"ols_classical_se_full\": float(ols.bse[1]),\n \"r_squared_full\": float(ols.rsquared),\n \"intercept_sub1\": float(fits[\"sub1\"][0].params[0]),\n \"intercept_sub2\": float(fits[\"sub2\"][0].params[0]),\n \"beta_sub1_hac_se\": float(fits[\"sub1\"][1].bse[1]),\n \"beta_sub2_hac_se\": float(fits[\"sub2\"][1].bse[1]),\n \"implied_zero_du_growth_full\": float(-alpha / beta),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh_:\n json.dump(results, fh_, indent=2)\n\nrows = [(\"full_1960Q1_2019Q4\", n, alpha, beta, se)]\nfor lab, key in [(\"sub1_1960Q1_1983Q4\", \"sub1\"), (\"sub2_1984Q1_2019Q4\", \"sub2\")]:\n f, fh, nn = fits[key]\n rows.append((lab, nn, float(f.params[0]), float(f.params[1]), float(fh.bse[1])))\npd.DataFrame(rows, columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\ng = reg[\"g\"].values\nax.scatter(g[s1], y[s1], s=14, alpha=0.6, label=\"1960Q1-1983Q4\", color=\"tab:blue\")\nax.scatter(g[s2], y[s2], s=14, alpha=0.6, label=\"1984Q1-2019Q4\", color=\"tab:orange\")\nxx = np.linspace(g.min(), g.max(), 50)\nfor key, c in [(\"sub1\", \"tab:blue\"), (\"sub2\", \"tab:orange\")]:\n a, b = fits[key][0].params\n ax.plot(xx, a + b * xx, color=c, lw=2, label=f\"fit {key}: du = {a:.2f} {b:+.3f} g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1-2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\nprint(json.dumps({k: results[k] for k in [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1816,"cache_read_input_tokens":10857,"output_tokens":3801,"output_tokens_details":{"thinking_tokens":237},"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":1816},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpNBVYN6tnw3vo7Bq93","requestRef":"0eb3b63c-7dd6-4bc6-8984-50d44cd97c8d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3b202c0b-e459-4c29-8d36-a2b809ffebb8","timestamp":"2026-10-30T04:49:19.679Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169/out/state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"3b202c0b-e459-4c29-8d36-a2b809ffebb8","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.5/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0169/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01UkrBZ2K8UDH6nmS9ty24Bh"}]},"uuid":"80a30751-c143-47e9-b8c5-0cb445e6cc77","timestamp":"2026-10-30T04:49:19.740Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.5/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0169/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"3b202c0b-e459-4c29-8d36-a2b809ffebb8","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169/out/state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"5c8f17645ef435c4b9d19e76769b455f297280a8620c34d04bb1f61374921e3b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01UkrBZ2K8UDH6nmS9ty24Bh","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\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\"\nos.makedirs(OUT, exist_ok=True)\ngdp = pd.read_csv(\"data/GDPC1.csv\", na_values=[\".\"])\nun = pd.read_csv(\"data/UNRATE.csv\", na_values=[\".\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"observation_date\"] = pd.to_datetime(gdp[\"observation_date\"])\nun[\"observation_date\"] = pd.to_datetime(un[\"observation_date\"])\n\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()][\"observation_date\"].dt.strftime(\"%Y-%m-%d\").tolist()\nif miss:\n data_issues.append({\"issue\": f\"UNRATE missing value(s) at {miss} (blank in raw FRED CSV)\",\n \"handling\": \"outside the 1959Q4-2019Q4 window; dropped with all post-2019Q4 observations, no effect on estimates\"})\ndata_issues.append({\"issue\": \"Both series extend beyond 2019Q4 (to 2026) and are the 2026 vintage (revised, not real-time)\",\n \"handling\": \"all observations after 2019Q4 excluded before computation; vintage noted as limitation\"})\n\n# Quarterly unemployment = mean of 3 months; require all 3 months present\nun[\"q\"] = un[\"observation_date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\ngdp[\"q\"] = gdp[\"observation_date\"].dt.to_period(\"Q\")\ndf = gdp.set_index(\"q\")[[\"GDPC1\"]].join(uq, how=\"left\")\n\nexcl = []\ndef log(step, rule, before, after, why):\n excl.append(dict(step=step, rule=rule, n_before=before, n_after=after, n_removed=before - after, rationale=why))\n\nn0 = len(df)\nwin = df.loc[pd.Period(\"1959Q4\"):pd.Period(\"2019Q4\")].copy()\nlog(1, \"keep quarters 1959Q4-2019Q4 (GDPC1 quarters as unit)\", n0, len(win),\n \"task window; 1959Q4 needed only for lagged levels; post-2019Q4 forbidden\")\nassert (win[\"count\"] == 3).all() and win[\"GDPC1\"].notna().all(), \"incomplete data inside window\"\nwin[\"u\"] = win[\"mean\"]\nwin[\"du\"] = win[\"u\"].diff()\nwin[\"g\"] = 100 * np.log(win[\"GDPC1\"]).diff()\nreg = win.dropna(subset=[\"du\", \"g\"]).copy()\nlog(2, \"drop 1959Q4 (no lagged level, differences undefined)\", len(win), len(reg),\n \"first-difference construction\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nassert len(reg) == 240 and str(reg.index[0]) == \"1960Q1\" and str(reg.index[-1]) == \"2019Q4\"\n\ny, X = reg[\"du\"].values, sm.add_constant(reg[\"g\"].values)\nn = len(y)\n# Baseline: mean-only prediction\nbaseline_rmse = float(np.sqrt(np.mean((y - y.mean()) ** 2)))\n# Full sample OLS with Newey-West HAC (Bartlett) SE\nHAC_LAGS = int(np.floor(4 * (n / 100) ** (2 / 9))) # Newey-West (1994) rule of thumb -> 4\nols = sm.OLS(y, X).fit()\nhac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\nalpha, beta = float(ols.params[0]), float(ols.params[1])\nse = float(hac.bse[1])\nz = stats.norm.ppf(0.975)\nci = (beta - z * se, beta + z * se)\nmodel_rmse = float(np.sqrt(np.mean(ols.resid ** 2)))\n\n# Subperiods\ns1 = reg.index <= pd.Period(\"1983Q4\")\ns2 = ~s1\nfits = {}\nfor name, m in [(\"sub1\", s1), (\"sub2\", s2)]:\n Xs = sm.add_constant(reg[\"g\"].values[m])\n f = sm.OLS(y[m], Xs).fit()\n fh = sm.OLS(y[m], Xs).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\n fits[name] = (f, fh, int(m.sum()))\nssr_p = ols.ssr\nssr_u = fits[\"sub1\"][0].ssr + fits[\"sub2\"][0].ssr\nk = 2\nchow_f = float(((ssr_p - ssr_u) / k) / (ssr_u / (n - 2 * k)))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\nconclusion = \"positive_effect\" if ci[0] > 0 else (\"negative_effect\" if ci[1] < 0 else \"no_detectable_effect\")\nresults = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": reg.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": reg.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": fits[\"sub1\"][2],\n \"n_sub2\": fits[\"sub2\"][2],\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": HAC_LAGS,\n \"effect_ci_low\": float(ci[0]),\n \"effect_ci_high\": float(ci[1]),\n \"beta_sub1\": float(fits[\"sub1\"][0].params[1]),\n \"beta_sub2\": float(fits[\"sub2\"][0].params[1]),\n \"chow_f_stat\": chow_f,\n \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n # supplementary (not required)\n \"ols_classical_se_full\": float(ols.bse[1]),\n \"r_squared_full\": float(ols.rsquared),\n \"intercept_sub1\": float(fits[\"sub1\"][0].params[0]),\n \"intercept_sub2\": float(fits[\"sub2\"][0].params[0]),\n \"beta_sub1_hac_se\": float(fits[\"sub1\"][1].bse[1]),\n \"beta_sub2_hac_se\": float(fits[\"sub2\"][1].bse[1]),\n \"implied_zero_du_growth_full\": float(-alpha / beta),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh_:\n json.dump(results, fh_, indent=2)\n\nrows = [(\"full_1960Q1_2019Q4\", n, alpha, beta, se)]\nfor lab, key in [(\"sub1_1960Q1_1983Q4\", \"sub1\"), (\"sub2_1984Q1_2019Q4\", \"sub2\")]:\n f, fh, nn = fits[key]\n rows.append((lab, nn, float(f.params[0]), float(f.params[1]), float(fh.bse[1])))\npd.DataFrame(rows, columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\ng = reg[\"g\"].values\nax.scatter(g[s1], y[s1], s=14, alpha=0.6, label=\"1960Q1-1983Q4\", color=\"tab:blue\")\nax.scatter(g[s2], y[s2], s=14, alpha=0.6, label=\"1984Q1-2019Q4\", color=\"tab:orange\")\nxx = np.linspace(g.min(), g.max(), 50)\nfor key, c in [(\"sub1\", \"tab:blue\"), (\"sub2\", \"tab:orange\")]:\n a, b = fits[key][0].params\n ax.plot(xx, a + b * xx, color=c, lw=2, label=f\"fit {key}: du = {a:.2f} {b:+.3f} g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1-2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\nprint(json.dumps({k: results[k] for k in [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"7f3f5374-668c-4359-9147-cbc55b6bd9cf","timestamp":"2026-10-30T04:49:19.743Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"0eb3b63c-7dd6-4bc6-8984-50d44cd97c8d","keep":12,"tail":["5c8f17645ef435c4b9d19e76769b455f297280a8620c34d04bb1f61374921e3b","a38dcd7f61d90f9686482270cd26c750d1984959e15b9935c16e1043c10d9c29"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a0604b5157b6fc2d5f73d98023cfb522735de7e68f9f658db7de5943625c478d"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"80a30751-c143-47e9-b8c5-0cb445e6cc77","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"type":"atis-latch","atis":"","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":"80a30751-c143-47e9-b8c5-0cb445e6cc77","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQMHiiFyJeqGHnwcRr","type":"message","role":"assistant","content":[{"type":"text","text":"The previous `cd` persisted; rerunning from root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3963,"cache_read_input_tokens":12673,"output_tokens":131,"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":3963},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpQM1rCC5CsShBavgzG","requestRef":"7f3f5374-668c-4359-9147-cbc55b6bd9cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c3c3f57c-4b99-4222-946a-bf66524b8f93","timestamp":"2026-10-30T04:49:21.550Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169/out/state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"c3c3f57c-4b99-4222-946a-bf66524b8f93","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQMHiiFyJeqGHnwcRr","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_012WJZyN8SQdZRu364fD5B11","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0169 && pwd && ls out out/state","description":"Return to workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3963,"cache_read_input_tokens":12673,"output_tokens":131,"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":3963},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpQM1rCC5CsShBavgzG","requestRef":"7f3f5374-668c-4359-9147-cbc55b6bd9cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ce3cea84-f078-46f0-b735-9ccf06a044ae","timestamp":"2026-10-30T04:49:22.199Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169/out/state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"ce3cea84-f078-46f0-b735-9ccf06a044ae","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_012WJZyN8SQdZRu364fD5B11","type":"tool_result","content":"/Users/simon-pierreboucher/wp29/runs/RC0169\nout:\nstate\n\nout/state:\ncontract.md\ndata_audit.md\nlog.md\nphases.json","is_error":false}]},"uuid":"4611db27-c87b-41a7-9473-fc734908a053","timestamp":"2026-10-30T04:49:22.236Z","toolUseResult":{"stdout":"/Users/simon-pierreboucher/wp29/runs/RC0169\nout:\nstate\n\nout/state:\ncontract.md\ndata_audit.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ce3cea84-f078-46f0-b735-9ccf06a044ae","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"da155cbf60d27e09cee7ac09cab4a9a84ff594fa838ff6d52c69bf0276fab9ae","message":{"role":"assistant","content":[{"type":"text","text":"The previous `cd` persisted; rerunning from root."},{"type":"tool_use","id":"toolu_012WJZyN8SQdZRu364fD5B11","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0169 && pwd && ls out out/state","description":"Return to workspace root"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"a1902df1-54a4-4d7b-9426-9a9e83d818b7","timestamp":"2026-10-30T04:49:22.239Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"7f3f5374-668c-4359-9147-cbc55b6bd9cf","keep":14,"tail":["da155cbf60d27e09cee7ac09cab4a9a84ff594fa838ff6d52c69bf0276fab9ae","131f0fb9076390e4d0b9d850dd9bae2714844c05a7d413d088f03e6c4d4319d7"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"02346145e1e814d70e1ce43bf68b12bf3aeb39cef56cdf43327189f1d74dfc62"} {"parentUuid":"4611db27-c87b-41a7-9473-fc734908a053","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQY1tDpJmqQT7X3dop","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":192,"cache_read_input_tokens":16636,"output_tokens":3588,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":192},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":327,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpQXjG6L5sfMbtj87nq","requestRef":"a1902df1-54a4-4d7b-9426-9a9e83d818b7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"89bd848f-e0ff-4eec-902b-abd949d41550","timestamp":"2026-10-30T04:49:23.713Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"89bd848f-e0ff-4eec-902b-abd949d41550","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQY1tDpJmqQT7X3dop","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LK3wmqSwrtoSzFCYFce9S4","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\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\"\nos.makedirs(OUT, exist_ok=True)\ngdp = pd.read_csv(\"data/GDPC1.csv\", na_values=[\".\"])\nun = pd.read_csv(\"data/UNRATE.csv\", na_values=[\".\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"observation_date\"] = pd.to_datetime(gdp[\"observation_date\"])\nun[\"observation_date\"] = pd.to_datetime(un[\"observation_date\"])\n\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()][\"observation_date\"].dt.strftime(\"%Y-%m-%d\").tolist()\nif miss:\n data_issues.append({\"issue\": f\"UNRATE missing value(s) at {miss} (blank in raw FRED CSV)\",\n \"handling\": \"outside the 1959Q4-2019Q4 window; dropped with all post-2019Q4 observations, no effect on estimates\"})\ndata_issues.append({\"issue\": \"Both series extend beyond 2019Q4 (to 2026) and are the 2026 vintage (revised, not real-time)\",\n \"handling\": \"all observations after 2019Q4 excluded before computation; vintage noted as limitation\"})\n\n# Quarterly unemployment = mean of 3 months; require all 3 months present\nun[\"q\"] = un[\"observation_date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\ngdp[\"q\"] = gdp[\"observation_date\"].dt.to_period(\"Q\")\ndf = gdp.set_index(\"q\")[[\"GDPC1\"]].join(uq, how=\"left\")\n\nexcl = []\ndef log(step, rule, before, after, why):\n excl.append(dict(step=step, rule=rule, n_before=before, n_after=after, n_removed=before - after, rationale=why))\n\nn0 = len(df)\nwin = df.loc[pd.Period(\"1959Q4\"):pd.Period(\"2019Q4\")].copy()\nlog(1, \"keep quarters 1959Q4-2019Q4 (GDPC1 quarters as unit)\", n0, len(win),\n \"task window; 1959Q4 needed only for lagged levels; post-2019Q4 forbidden\")\nassert (win[\"count\"] == 3).all() and win[\"GDPC1\"].notna().all(), \"incomplete data inside window\"\nwin[\"u\"] = win[\"mean\"]\nwin[\"du\"] = win[\"u\"].diff()\nwin[\"g\"] = 100 * np.log(win[\"GDPC1\"]).diff()\nreg = win.dropna(subset=[\"du\", \"g\"]).copy()\nlog(2, \"drop 1959Q4 (no lagged level, differences undefined)\", len(win), len(reg),\n \"first-difference construction\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nassert len(reg) == 240 and str(reg.index[0]) == \"1960Q1\" and str(reg.index[-1]) == \"2019Q4\"\n\ny, X = reg[\"du\"].values, sm.add_constant(reg[\"g\"].values)\nn = len(y)\n# Baseline: mean-only prediction\nbaseline_rmse = float(np.sqrt(np.mean((y - y.mean()) ** 2)))\n# Full sample OLS with Newey-West HAC (Bartlett) SE\nHAC_LAGS = int(np.floor(4 * (n / 100) ** (2 / 9))) # Newey-West (1994) rule of thumb -> 4\nols = sm.OLS(y, X).fit()\nhac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\nalpha, beta = float(ols.params[0]), float(ols.params[1])\nse = float(hac.bse[1])\nz = stats.norm.ppf(0.975)\nci = (beta - z * se, beta + z * se)\nmodel_rmse = float(np.sqrt(np.mean(ols.resid ** 2)))\n\n# Subperiods\ns1 = reg.index <= pd.Period(\"1983Q4\")\ns2 = ~s1\nfits = {}\nfor name, m in [(\"sub1\", s1), (\"sub2\", s2)]:\n Xs = sm.add_constant(reg[\"g\"].values[m])\n f = sm.OLS(y[m], Xs).fit()\n fh = sm.OLS(y[m], Xs).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\n fits[name] = (f, fh, int(m.sum()))\nssr_p = ols.ssr\nssr_u = fits[\"sub1\"][0].ssr + fits[\"sub2\"][0].ssr\nk = 2\nchow_f = float(((ssr_p - ssr_u) / k) / (ssr_u / (n - 2 * k)))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\nconclusion = \"positive_effect\" if ci[0] > 0 else (\"negative_effect\" if ci[1] < 0 else \"no_detectable_effect\")\nresults = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": reg.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": reg.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": fits[\"sub1\"][2],\n \"n_sub2\": fits[\"sub2\"][2],\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": HAC_LAGS,\n \"effect_ci_low\": float(ci[0]),\n \"effect_ci_high\": float(ci[1]),\n \"beta_sub1\": float(fits[\"sub1\"][0].params[1]),\n \"beta_sub2\": float(fits[\"sub2\"][0].params[1]),\n \"chow_f_stat\": chow_f,\n \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n # supplementary (not required)\n \"ols_classical_se_full\": float(ols.bse[1]),\n \"r_squared_full\": float(ols.rsquared),\n \"intercept_sub1\": float(fits[\"sub1\"][0].params[0]),\n \"intercept_sub2\": float(fits[\"sub2\"][0].params[0]),\n \"beta_sub1_hac_se\": float(fits[\"sub1\"][1].bse[1]),\n \"beta_sub2_hac_se\": float(fits[\"sub2\"][1].bse[1]),\n \"implied_zero_du_growth_full\": float(-alpha / beta),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh_:\n json.dump(results, fh_, indent=2)\n\nrows = [(\"full_1960Q1_2019Q4\", n, alpha, beta, se)]\nfor lab, key in [(\"sub1_1960Q1_1983Q4\", \"sub1\"), (\"sub2_1984Q1_2019Q4\", \"sub2\")]:\n f, fh, nn = fits[key]\n rows.append((lab, nn, float(f.params[0]), float(f.params[1]), float(fh.bse[1])))\npd.DataFrame(rows, columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\ng = reg[\"g\"].values\nax.scatter(g[s1], y[s1], s=14, alpha=0.6, label=\"1960Q1-1983Q4\", color=\"tab:blue\")\nax.scatter(g[s2], y[s2], s=14, alpha=0.6, label=\"1984Q1-2019Q4\", color=\"tab:orange\")\nxx = np.linspace(g.min(), g.max(), 50)\nfor key, c in [(\"sub1\", \"tab:blue\"), (\"sub2\", \"tab:orange\")]:\n a, b = fits[key][0].params\n ax.plot(xx, a + b * xx, color=c, lw=2, label=f\"fit {key}: du = {a:.2f} {b:+.3f} g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1-2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\nprint(json.dumps({k: results[k] for k in [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":192,"cache_read_input_tokens":16636,"output_tokens":3588,"output_tokens_details":{"thinking_tokens":24},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":192},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpQXjG6L5sfMbtj87nq","requestRef":"a1902df1-54a4-4d7b-9426-9a9e83d818b7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e1e04fba-f8d7-4ac7-8834-c6d18d66e3b5","timestamp":"2026-10-30T04:49:45.636Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e1e04fba-f8d7-4ac7-8834-c6d18d66e3b5","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LK3wmqSwrtoSzFCYFce9S4","type":"tool_result","content":"{\n \"effect_estimate\": -0.2557677277487258,\n \"effect_se\": 0.03598488399675878,\n \"effect_ci_low\": -0.3262968043702248,\n \"effect_ci_high\": -0.18523865112722682,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.0903330062337675,\n \"chow_p_value\": 0.002636323851733417,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1_2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03598488399675878\nsub1_1960Q1_1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03970255328838903\nsub2_1984Q1_2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06879369233083424\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep quarters 1959Q4-2019Q4 (GDPC1 quarters as unit),319,241,78,task window; 1959Q4 needed only for lagged levels; post-2019Q4 forbidden\n2,\"drop 1959Q4 (no lagged level, differences undefined)\",241,240,1,first-difference construction","is_error":false}]},"uuid":"a713c7e9-b125-46ee-9085-37268d2284f2","timestamp":"2026-10-30T04:49:46.838Z","toolUseResult":{"stdout":"{\n \"effect_estimate\": -0.2557677277487258,\n \"effect_se\": 0.03598488399675878,\n \"effect_ci_low\": -0.3262968043702248,\n \"effect_ci_high\": -0.18523865112722682,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.0903330062337675,\n \"chow_p_value\": 0.002636323851733417,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1_2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03598488399675878\nsub1_1960Q1_1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03970255328838903\nsub2_1984Q1_2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06879369233083424\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep quarters 1959Q4-2019Q4 (GDPC1 quarters as unit),319,241,78,task window; 1959Q4 needed only for lagged levels; post-2019Q4 forbidden\n2,\"drop 1959Q4 (no lagged level, differences undefined)\",241,240,1,first-difference construction","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e1e04fba-f8d7-4ac7-8834-c6d18d66e3b5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"f6a372556bc6c0af11a9310fe08db0baeda08103c4c43a4a89c876cb2c1a6926","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LK3wmqSwrtoSzFCYFce9S4","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\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\"\nos.makedirs(OUT, exist_ok=True)\ngdp = pd.read_csv(\"data/GDPC1.csv\", na_values=[\".\"])\nun = pd.read_csv(\"data/UNRATE.csv\", na_values=[\".\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"observation_date\"] = pd.to_datetime(gdp[\"observation_date\"])\nun[\"observation_date\"] = pd.to_datetime(un[\"observation_date\"])\n\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()][\"observation_date\"].dt.strftime(\"%Y-%m-%d\").tolist()\nif miss:\n data_issues.append({\"issue\": f\"UNRATE missing value(s) at {miss} (blank in raw FRED CSV)\",\n \"handling\": \"outside the 1959Q4-2019Q4 window; dropped with all post-2019Q4 observations, no effect on estimates\"})\ndata_issues.append({\"issue\": \"Both series extend beyond 2019Q4 (to 2026) and are the 2026 vintage (revised, not real-time)\",\n \"handling\": \"all observations after 2019Q4 excluded before computation; vintage noted as limitation\"})\n\n# Quarterly unemployment = mean of 3 months; require all 3 months present\nun[\"q\"] = un[\"observation_date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\ngdp[\"q\"] = gdp[\"observation_date\"].dt.to_period(\"Q\")\ndf = gdp.set_index(\"q\")[[\"GDPC1\"]].join(uq, how=\"left\")\n\nexcl = []\ndef log(step, rule, before, after, why):\n excl.append(dict(step=step, rule=rule, n_before=before, n_after=after, n_removed=before - after, rationale=why))\n\nn0 = len(df)\nwin = df.loc[pd.Period(\"1959Q4\"):pd.Period(\"2019Q4\")].copy()\nlog(1, \"keep quarters 1959Q4-2019Q4 (GDPC1 quarters as unit)\", n0, len(win),\n \"task window; 1959Q4 needed only for lagged levels; post-2019Q4 forbidden\")\nassert (win[\"count\"] == 3).all() and win[\"GDPC1\"].notna().all(), \"incomplete data inside window\"\nwin[\"u\"] = win[\"mean\"]\nwin[\"du\"] = win[\"u\"].diff()\nwin[\"g\"] = 100 * np.log(win[\"GDPC1\"]).diff()\nreg = win.dropna(subset=[\"du\", \"g\"]).copy()\nlog(2, \"drop 1959Q4 (no lagged level, differences undefined)\", len(win), len(reg),\n \"first-difference construction\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nassert len(reg) == 240 and str(reg.index[0]) == \"1960Q1\" and str(reg.index[-1]) == \"2019Q4\"\n\ny, X = reg[\"du\"].values, sm.add_constant(reg[\"g\"].values)\nn = len(y)\n# Baseline: mean-only prediction\nbaseline_rmse = float(np.sqrt(np.mean((y - y.mean()) ** 2)))\n# Full sample OLS with Newey-West HAC (Bartlett) SE\nHAC_LAGS = int(np.floor(4 * (n / 100) ** (2 / 9))) # Newey-West (1994) rule of thumb -> 4\nols = sm.OLS(y, X).fit()\nhac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\nalpha, beta = float(ols.params[0]), float(ols.params[1])\nse = float(hac.bse[1])\nz = stats.norm.ppf(0.975)\nci = (beta - z * se, beta + z * se)\nmodel_rmse = float(np.sqrt(np.mean(ols.resid ** 2)))\n\n# Subperiods\ns1 = reg.index <= pd.Period(\"1983Q4\")\ns2 = ~s1\nfits = {}\nfor name, m in [(\"sub1\", s1), (\"sub2\", s2)]:\n Xs = sm.add_constant(reg[\"g\"].values[m])\n f = sm.OLS(y[m], Xs).fit()\n fh = sm.OLS(y[m], Xs).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\n fits[name] = (f, fh, int(m.sum()))\nssr_p = ols.ssr\nssr_u = fits[\"sub1\"][0].ssr + fits[\"sub2\"][0].ssr\nk = 2\nchow_f = float(((ssr_p - ssr_u) / k) / (ssr_u / (n - 2 * k)))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\nconclusion = \"positive_effect\" if ci[0] > 0 else (\"negative_effect\" if ci[1] < 0 else \"no_detectable_effect\")\nresults = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": reg.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": reg.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": fits[\"sub1\"][2],\n \"n_sub2\": fits[\"sub2\"][2],\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": HAC_LAGS,\n \"effect_ci_low\": float(ci[0]),\n \"effect_ci_high\": float(ci[1]),\n \"beta_sub1\": float(fits[\"sub1\"][0].params[1]),\n \"beta_sub2\": float(fits[\"sub2\"][0].params[1]),\n \"chow_f_stat\": chow_f,\n \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n # supplementary (not required)\n \"ols_classical_se_full\": float(ols.bse[1]),\n \"r_squared_full\": float(ols.rsquared),\n \"intercept_sub1\": float(fits[\"sub1\"][0].params[0]),\n \"intercept_sub2\": float(fits[\"sub2\"][0].params[0]),\n \"beta_sub1_hac_se\": float(fits[\"sub1\"][1].bse[1]),\n \"beta_sub2_hac_se\": float(fits[\"sub2\"][1].bse[1]),\n \"implied_zero_du_growth_full\": float(-alpha / beta),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh_:\n json.dump(results, fh_, indent=2)\n\nrows = [(\"full_1960Q1_2019Q4\", n, alpha, beta, se)]\nfor lab, key in [(\"sub1_1960Q1_1983Q4\", \"sub1\"), (\"sub2_1984Q1_2019Q4\", \"sub2\")]:\n f, fh, nn = fits[key]\n rows.append((lab, nn, float(f.params[0]), float(f.params[1]), float(fh.bse[1])))\npd.DataFrame(rows, columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\ng = reg[\"g\"].values\nax.scatter(g[s1], y[s1], s=14, alpha=0.6, label=\"1960Q1-1983Q4\", color=\"tab:blue\")\nax.scatter(g[s2], y[s2], s=14, alpha=0.6, label=\"1984Q1-2019Q4\", color=\"tab:orange\")\nxx = np.linspace(g.min(), g.max(), 50)\nfor key, c in [(\"sub1\", \"tab:blue\"), (\"sub2\", \"tab:orange\")]:\n a, b = fits[key][0].params\n ax.plot(xx, a + b * xx, color=c, lw=2, label=f\"fit {key}: du = {a:.2f} {b:+.3f} g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1-2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\nprint(json.dumps({k: results[k] for k in [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"f702457d-db6b-4b12-b805-18ad2c6db9da","timestamp":"2026-10-30T04:49:46.841Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"a1902df1-54a4-4d7b-9426-9a9e83d818b7","keep":16,"tail":["f6a372556bc6c0af11a9310fe08db0baeda08103c4c43a4a89c876cb2c1a6926","f775f43849cc36e646ed99ba3b4904a230378e4116fba09ea2540c761cafb0ae"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f098f3eb1af11fcd9229e9cdd2e0cc079b81e90beda22d6ef3c362e9d1385589"} {"parentUuid":"a713c7e9-b125-46ee-9085-37268d2284f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSMF3DfCAGRm9ziJB2","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":4080,"cache_read_input_tokens":16828,"output_tokens":941,"output_tokens_details":{"thinking_tokens":183},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4080},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1608,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpSLzA5CjGu6PpPpJ1S","requestRef":"f702457d-db6b-4b12-b805-18ad2c6db9da","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"eee1c010-5254-4355-a4fb-38b8ff56e91e","timestamp":"2026-10-30T04:49:49.907Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"eee1c010-5254-4355-a4fb-38b8ff56e91e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSMF3DfCAGRm9ziJB2","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018fQCpW1EvspwGwmgva89F8","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''conclusion = \"positive_effect\"''','''# Supplementary: HAC test of slope-only difference (interaction model) and lag sensitivity\nd2 = s2.astype(float)\nXi = np.column_stack([np.ones(n), reg[\"g\"].values, d2, d2 * reg[\"g\"].values])\ninter = sm.OLS(y, Xi).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\nslope_diff_p = float(inter.pvalues[3]); int_diff_p = float(inter.pvalues[2])\nlag_sens = {str(L): float(sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"use_correction\": True}).bse[1])\n for L in (0, 2, 8, 12)}\nresid_var = {\"sub1\": float(fits[\"sub1\"][0].ssr / (fits[\"sub1\"][2] - 2)), \"sub2\": float(fits[\"sub2\"][0].ssr / (fits[\"sub2\"][2] - 2))}\n\nconclusion = \"positive_effect\"''')\ns=s.replace(''' \"implied_zero_du_growth_full\": float(-alpha / beta),\n}''',''' \"implied_zero_du_growth_full\": float(-alpha / beta),\n \"hac_slope_diff_p_value\": slope_diff_p,\n \"hac_intercept_diff_p_value\": int_diff_p,\n \"hac_se_lag_sensitivity\": lag_sens,\n \"resid_variance_sub1\": resid_var[\"sub1\"],\n \"resid_variance_sub2\": resid_var[\"sub2\"],\n}''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cat out/results.json | tail -25","description":"Add supplementary diagnostics and rerun"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4080,"cache_read_input_tokens":16828,"output_tokens":941,"output_tokens_details":{"thinking_tokens":183},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4080},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSLzA5CjGu6PpPpJ1S","requestRef":"f702457d-db6b-4b12-b805-18ad2c6db9da","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bffe0e31-6287-42bc-aac9-261ca4d084cb","timestamp":"2026-10-30T04:49:55.016Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"bffe0e31-6287-42bc-aac9-261ca4d084cb","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"type":"atis-latch","atis":"","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":"bffe0e31-6287-42bc-aac9-261ca4d084cb","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018fQCpW1EvspwGwmgva89F8","type":"tool_result","content":" \"effect_ci_high\": -0.18523865112722682,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.0903330062337675,\n \"chow_p_value\": 0.002636323851733417,\n \"stability_conclusion\": \"unstable\",\n \"conclusion\": \"negative_effect\",\n \"ols_classical_se_full\": 0.01996009291490984,\n \"r_squared_full\": 0.4082508284562034,\n \"intercept_sub1\": 0.2542326539884382,\n \"intercept_sub2\": 0.15168581347724602,\n \"beta_sub1_hac_se\": 0.03970255328838903,\n \"beta_sub2_hac_se\": 0.06879369233083424,\n \"implied_zero_du_growth_full\": 0.7209211099660549,\n \"hac_slope_diff_p_value\": 0.8548271295127585,\n \"hac_intercept_diff_p_value\": 0.25395491785679547,\n \"hac_se_lag_sensitivity\": {\n \"0\": 0.028957130333809637,\n \"2\": 0.034370831642247524,\n \"8\": 0.03729120927832667,\n \"12\": 0.03656150942843361\n },\n \"resid_variance_sub1\": 0.07850312611325812,\n \"resid_variance_sub2\": 0.04827674526450526\n}","is_error":false}]},"uuid":"3b165d2d-f649-4276-ab8e-4d481f203723","timestamp":"2026-10-30T04:49:56.341Z","toolUseResult":{"stdout":" \"effect_ci_high\": -0.18523865112722682,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.0903330062337675,\n \"chow_p_value\": 0.002636323851733417,\n \"stability_conclusion\": \"unstable\",\n \"conclusion\": \"negative_effect\",\n \"ols_classical_se_full\": 0.01996009291490984,\n \"r_squared_full\": 0.4082508284562034,\n \"intercept_sub1\": 0.2542326539884382,\n \"intercept_sub2\": 0.15168581347724602,\n \"beta_sub1_hac_se\": 0.03970255328838903,\n \"beta_sub2_hac_se\": 0.06879369233083424,\n \"implied_zero_du_growth_full\": 0.7209211099660549,\n \"hac_slope_diff_p_value\": 0.8548271295127585,\n \"hac_intercept_diff_p_value\": 0.25395491785679547,\n \"hac_se_lag_sensitivity\": {\n \"0\": 0.028957130333809637,\n \"2\": 0.034370831642247524,\n \"8\": 0.03729120927832667,\n \"12\": 0.03656150942843361\n },\n \"resid_variance_sub1\": 0.07850312611325812,\n \"resid_variance_sub2\": 0.04827674526450526\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"bffe0e31-6287-42bc-aac9-261ca4d084cb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"4c3bb3872a3a4e8f20aa848d669396dd29331e9d069777b7c2717cfb6f408482","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSgAoKEAgTGAI4AUIIdGhpbmtpbmcSDEsFzAu8y6N5fJxP8xoMf3CXSNTI/sfWux2MIjD6UKKxI4WIFBbQZ6shwJCEe3lGrtOtkCNpll5ly2QXCiIJgI0hCcc5G5eV1f3hIdkqnQkz8DCW3hLgbZPszrZhy1ax5ZR7SxFW6lw/Yz7R1kzmINa2E2LLaMkwA6wrmuuz7x2cbc8sjTEU4CbaUMEA1jxnuAnSjqcUIZjcJY+Xws82xgjdgY/Tz2u199+ln9jOxf5cxJwBbw2x7bfCUf44IiFXWjCriOTMNo1hyoyZbdQNKknV1dzf/o7QDPHYnVQ/eZHOhpQObbYP6BdMLNfGLJXW/jzkpedKV7BjktCJQDZh4k3WnNfduJb8HASddBIQDBFSGFsbDXqCNDZ1Y7aouCYiM1yij7aw2S7HSmO6fCz5drOXAGjkkPsrFUVMzkGyh/g3nW2OO0Bk1C2WShohWHx+pRqLjjwleDE1TNbSfrgZzMT67OEMNO2ADALlbwGFV1UzPAqM631XecgMvuuq1jwMgEk96SNsZQQ6dVVCqT/lj0QutsQo2Ulh1cXlM9Pqglw+psW5L9Hlt8lB/NsuqayciQT+VrsNcCdga845JA+kczmQzc6/s8JVBmE9TFgui/vZoSvvfoWYtaXiz8DHZAgyE8sPUftks9V5Z3PAsjWdJl19tF504So3ANJMWcAQUy8HYnoiPzJ6nrp6gB95OCDnUOgxMbF/mKu+dMIHTcohgl68n0ykKxQ/NQdNOIMHAo+CeLR+jpyquP/DQQqwGf0mX3Eyw00Y7cnCaFtWzPl1kW8GAYu3YhhJj/xpyG1+Q/vh+WaDz9epFYb/TLOVWfPYsWkesmVqFCDJCiyDyAq/Rt3goNL6xzHsyxs8p06cZ6p4xPGPR1t6aM/VGeRq7fJBvZAOdT6xMey5VldkyoBzb4g0D2xOz+imNgiBXKdTU4mADkOpi4DGQ7XmIRm9NIp7Wi1p2FsR41VSKpqbjuaYZ08TQFOzUpJNL6SUIvnsYSYzHOoFBxts4Ddkzbmd5bbDn46ywcPvxM/3JdopTGNjfAJ6+yMyPW4krrzvkQNWtr2CXoOPx1xEnwbuwVT0Idqh5MRQ4oJj9Mw2P1fVMT2inBAdwLbmcJv3EfdGaaWJ+cbDg7o6n21OgtlUxeumI7bUhzlHQf9eB/3gjUc3Jgi6K4n6N9WDLI2OyGpuaJuop6gO32u0tR2DDvLnbAM5InozgZrpPWOLkQf6Zx2Jpv9Xp+sExa3e/voAo1C/bQ8ceeKm6L3iMrkFbSvmZIKET7oQ42PhjtB2SBg5HsQcPkFtE0GIRS3uJWCw8ImD83VxD/LMkoexpiwm2cL7zbS9ajKDjiTgyDqU52n/BAj9xt2rC1DlA3/M6embrrDQv9UJLV/f+fiN0hgFwJmeQSabQtX2NjZV6mPHeksVjl/Npqdruh8ScQ4E5S9W/kWBRiRrcw+dJH6Zy+KyFB12kn3b3kQR6Qf8S1Xtyd5Cc7tOAvNds3rxckjz6Laz4Me0YviZIHhaISeD59hfmZAHAp8sC3IF+ZAw/WZdBDVRgrbeLsab/nEcnk/p8b5wi2p9kJ/X1dw0Y/sVTLeDXd9BIQHYaq6KBvweJUM0dxPRLOjphIirsNs/vEHvic1vEAEJ5eBGIjy4bQrPaflOJ+fhFfCeUOIry8w2u3GeFGa27Tiv0BgB"},{"type":"tool_use","id":"toolu_018fQCpW1EvspwGwmgva89F8","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''conclusion = \"positive_effect\"''','''# Supplementary: HAC test of slope-only difference (interaction model) and lag sensitivity\nd2 = s2.astype(float)\nXi = np.column_stack([np.ones(n), reg[\"g\"].values, d2, d2 * reg[\"g\"].values])\ninter = sm.OLS(y, Xi).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": HAC_LAGS, \"use_correction\": True})\nslope_diff_p = float(inter.pvalues[3]); int_diff_p = float(inter.pvalues[2])\nlag_sens = {str(L): float(sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"use_correction\": True}).bse[1])\n for L in (0, 2, 8, 12)}\nresid_var = {\"sub1\": float(fits[\"sub1\"][0].ssr / (fits[\"sub1\"][2] - 2)), \"sub2\": float(fits[\"sub2\"][0].ssr / (fits[\"sub2\"][2] - 2))}\n\nconclusion = \"positive_effect\"''')\ns=s.replace(''' \"implied_zero_du_growth_full\": float(-alpha / beta),\n}''',''' \"implied_zero_du_growth_full\": float(-alpha / beta),\n \"hac_slope_diff_p_value\": slope_diff_p,\n \"hac_intercept_diff_p_value\": int_diff_p,\n \"hac_se_lag_sensitivity\": lag_sens,\n \"resid_variance_sub1\": resid_var[\"sub1\"],\n \"resid_variance_sub2\": resid_var[\"sub2\"],\n}''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cat out/results.json | tail -25","description":"Add supplementary diagnostics and rerun"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"517300d6-ec71-4f60-b841-de638a48c08f","timestamp":"2026-10-30T04:49:56.344Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"f702457d-db6b-4b12-b805-18ad2c6db9da","keep":18,"tail":["4c3bb3872a3a4e8f20aa848d669396dd29331e9d069777b7c2717cfb6f408482","f02626a8b6011d496b917abf4a9597b3da8b42e4d89eb6f240b2be1c9f0f0f64"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4d6d8b3cf19b0a7e560f5e1f9bed98c2a19f935f5374d1e222e2740f55617d06"} {"parentUuid":"3b165d2d-f649-4276-ab8e-4d481f203723","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpT3qKPeRTZ2yEfCCC2","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":1419,"cache_read_input_tokens":20908,"output_tokens":602,"output_tokens_details":{"thinking_tokens":125},"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":1419},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":903,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpT3ZSTNFFszk8Xi8TC","requestRef":"517300d6-ec71-4f60-b841-de638a48c08f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"60dff204-72e4-4abb-8182-a8f6ef96ee5b","timestamp":"2026-10-30T04:49:58.561Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"60dff204-72e4-4abb-8182-a8f6ef96ee5b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpT3qKPeRTZ2yEfCCC2","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SzZbSi8GgEaekZGTESfkSy","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''slope_diff_p = float(inter.pvalues[3]); int_diff_p = float(inter.pvalues[2])''','''slope_diff_p = float(inter.pvalues[3]); int_diff_p = float(inter.pvalues[2])\nR = np.array([[0, 0, 1, 0], [0, 0, 0, 1]], dtype=float)\nwald = inter.wald_test(R, use_f=True, scalar=True)\nhac_joint_F, hac_joint_p = float(wald.statistic), float(wald.pvalue)''')\ns=s.replace(''' \"hac_intercept_diff_p_value\": int_diff_p,''',''' \"hac_intercept_diff_p_value\": int_diff_p,\n \"hac_joint_break_f_stat\": hac_joint_F,\n \"hac_joint_break_p_value\": hac_joint_p,''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && grep hac_joint out/results.json","description":"Add HAC joint break Wald test"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1419,"cache_read_input_tokens":20908,"output_tokens":602,"output_tokens_details":{"thinking_tokens":125},"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":1419},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpT3ZSTNFFszk8Xi8TC","requestRef":"517300d6-ec71-4f60-b841-de638a48c08f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b5bd2514-dee2-409d-b302-54412d91dee5","timestamp":"2026-10-30T04:50:01.806Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"b5bd2514-dee2-409d-b302-54412d91dee5","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SzZbSi8GgEaekZGTESfkSy","type":"tool_result","content":" \"hac_joint_break_f_stat\": 5.372053278020056,\n \"hac_joint_break_p_value\": 0.0052299232796137185,","is_error":false}]},"uuid":"ad33124b-d6f5-4a41-ba89-7f623b8358ce","timestamp":"2026-10-30T04:50:03.047Z","toolUseResult":{"stdout":" \"hac_joint_break_f_stat\": 5.372053278020056,\n \"hac_joint_break_p_value\": 0.0052299232796137185,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b5bd2514-dee2-409d-b302-54412d91dee5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"076c52ad70b3d4ba7d03fdd0eac4d311ed420e5b5084b10d24f26b66dd5c6904","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01SzZbSi8GgEaekZGTESfkSy","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''slope_diff_p = float(inter.pvalues[3]); int_diff_p = float(inter.pvalues[2])''','''slope_diff_p = float(inter.pvalues[3]); int_diff_p = float(inter.pvalues[2])\nR = np.array([[0, 0, 1, 0], [0, 0, 0, 1]], dtype=float)\nwald = inter.wald_test(R, use_f=True, scalar=True)\nhac_joint_F, hac_joint_p = float(wald.statistic), float(wald.pvalue)''')\ns=s.replace(''' \"hac_intercept_diff_p_value\": int_diff_p,''',''' \"hac_intercept_diff_p_value\": int_diff_p,\n \"hac_joint_break_f_stat\": hac_joint_F,\n \"hac_joint_break_p_value\": hac_joint_p,''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && grep hac_joint out/results.json","description":"Add HAC joint break Wald test"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"9aa17f23-7aee-4175-acce-abb90aedde1f","timestamp":"2026-10-30T04:50:03.051Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"517300d6-ec71-4f60-b841-de638a48c08f","keep":20,"tail":["076c52ad70b3d4ba7d03fdd0eac4d311ed420e5b5084b10d24f26b66dd5c6904","1c6464b3e6c1132505990ad3370eaedd414a613209ebdb8b049c62ef50f21584"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"53407e871e1b34e05dad237b819cbffe4bbc6254cbbb26c643e9bf38978a1242"} {"type":"tools-used","tools":["Bash","Read"],"sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":"ad33124b-d6f5-4a41-ba89-7f623b8358ce","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTYRXXPguAD38u5WFo","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSmQcKEAgTGAI4AUIIdGhpbmtpbmcSDIP0G9yIQ6kKYcBFWxoMLmwMZc0vaoNbQ40sIjDiKOXWsoKJdIAaaI+G86Pwbis4wmtbcAPkWxzFdNff8G6rggccMTPwZ4jv2GEl6FUqtgYCgDA96/KCs8QIX2aNPLRojDhFCPF96uh+kFp2JHn/p0tVsMWSYmKEA7i5JAzxI4rfasFfL1fJx2+7U+prYDTgumWmJMzyWjsMiv7bEXF1lAfb8SVzW7t8toeB2ptUvelIc6mhxH5Tg40k1AKp6fUhVPruAjgWa3m2s80A10kqE0/epxYiVFGnsB3Py2j5Cjwe4SjfncxokDAPh/aYOiy+1PwB2n5noBB04J30PA/pVf/ZGe1epJPG5/iHKClCzr5uxRzKcjz31bC5/CDa00ENDQdW6/ioIn2FDEG3QcJNpPdsFAAu/b6jbf5FjV8Jxx2YLGXZ11vUkRY5R5QRCm172kTDarJSb3W5cZjoTHi7QyTQd4nRmumZ/5u8hj3C62g+VWy+mDj7olHynmDflmu3BBVQqDO4oKC19ogYG7hcCoisQ6KiVrvbAdOpeh6OBwdiOGT83R+eTKXu8+kBni7gizA1r+iCqbP3NbSZ32tD9iVOmygsb52vAcPNcJZSPpOnAX0LQUJ/Pf1c7y8T9+0ouRyl4qcnKHCFlWfA7nPR+ZmQOC3gX3g/uJVc5vNLeo9sgFTKPXIfnefilWhAXzgVH8jr+ss8D5L/zaHx4Iq9BEEqNzWXvTdvzqQhvJo+j6Pv7zBru0wEwYPTh38vOH0T1uPPsOFsEc/wkE7mVF011a9WQsDmaRGh8fMYRfO5RHVODIuDVzQVyYFIlQ3F4lmmCVnJhYzRrbiGd9E9BQKQRO9v13+AjKaY2sKtPtt/hSWimkMlakhoLoCnkY32IyTSS/j5bEYRNly8+KapqYuX0+HCR9MnGdQg2fguosrxRkJ5aGO/uP5o7zLA+MAip88EV9URSbMHL31AcQHKRGF/LMvkSrP5j2skvpd/0MK07rHhYjs5qBEeilGX/RqiXnMrDp7gwtkUV0gwadT1rFUaS5uHiJ6rYAqE0Ll9Sgmj3wRuZOVvvzuejaX16ubl5LxdcXvKcnZdLXhBDen6zQTW6RpZxpiV7IugapfKmLnGFut3s0UQFcT0PYIniH2L2dHfc+R4nj6a54LioYKudYgpXisD0p0Moj4jIx6uySluC/kqx+CanL4YAQ=="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":657,"cache_read_input_tokens":22327,"output_tokens":669,"output_tokens_details":{"thinking_tokens":56},"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":657},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":403,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpTY9uNit6DjWRNq2Ab","requestRef":"9aa17f23-7aee-4175-acce-abb90aedde1f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"45d4bf50-c4f3-4578-ac45-a910ad3ff97c","timestamp":"2026-10-30T04:50:04.709Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"45d4bf50-c4f3-4578-ac45-a910ad3ff97c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTYRXXPguAD38u5WFo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PJj7ta9YeRQc2vdWTf22UE","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0169/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":657,"cache_read_input_tokens":22327,"output_tokens":669,"output_tokens_details":{"thinking_tokens":56},"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":657},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpTY9uNit6DjWRNq2Ab","requestRef":"9aa17f23-7aee-4175-acce-abb90aedde1f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2bcdac59-c0d2-4caa-a916-63a6587762bc","timestamp":"2026-10-30T04:50:05.038Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"2bcdac59-c0d2-4caa-a916-63a6587762bc","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PJj7ta9YeRQc2vdWTf22UE","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"69672ad1-e99e-4793-889d-3d8e07e61758","timestamp":"2026-10-30T04:50:05.044Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":71781,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"2bcdac59-c0d2-4caa-a916-63a6587762bc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"69672ad1-e99e-4793-889d-3d8e07e61758","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTYRXXPguAD38u5WFo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XVDp95NSHP61o836ngHtPS","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; rm out/results.json out/table1.csv out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r1.json && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd\nr=json.load(open('out/results.json'))\ne=pd.read_csv('out/exclusions.csv')\nprint('excl sum', 319-e.n_removed.sum()==r['n_analysed'])\nprint('n split', r['n_sub1']+r['n_sub2']==r['n_analysed'], r['n_sub1'],r['n_sub2'])\nprint('ci', r['effect_ci_low']0', r['effect_se']>0)\nprint('model0 True\nmodel0 True\nmodel/dev/null; cmp out/results.json /tmp/r1.json && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd\nr=json.load(open('out/results.json'))\ne=pd.read_csv('out/exclusions.csv')\nprint('excl sum', 319-e.n_removed.sum()==r['n_analysed'])\nprint('n split', r['n_sub1']+r['n_sub2']==r['n_analysed'], r['n_sub1'],r['n_sub2'])\nprint('ci', r['effect_ci_low']0', r['effect_se']>0)\nprint('model0 True\nmodel out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| check | outcome |\n|---|---|\n| Clean re-run (deleted results.json, table1.csv, figure1.png, exclusions.csv; re-ran analysis.py); results.json byte-identical | PASS |\n| Exclusion ledger: 319 GDPC1 quarters − 78 − 1 = 240 = n_analysed | PASS |\n| n_sub1 + n_sub2 = 96 + 144 = 240 = n_analysed | PASS |\n| sample_start 1960-01-01 < sample_end 2019-10-01; no quarter after 2019Q4 used (asserted in script) | PASS |\n| All 3 monthly UNRATE values present for every quarter 1959Q4–2019Q4; no missing GDPC1 (asserted) | PASS |\n| effect_se > 0; CI contains estimate; CI symmetric with z=1.96 | PASS |\n| model_metric (0.250) < baseline_metric (0.325); 1 − (model/baseline)^2 = R² (0.408) to 1e-12 | PASS |\n| Magnitude: β ≈ −0.26 pp per 1% q/q growth, in the conventional Okun range (≈ −0.3 to −0.5 per annualised-equivalent... i.e. ≈ −0.25 to −0.5 here) | PASS (plausible) |\n| Chow df = (2, 236); F > 0 | PASS |\n| Full-sample β (−0.256) lies outside [β_sub2, β_sub1] = [−0.273, −0.259]: explained by the intercept shift between subperiods (pooled fit with a common intercept tilts the slope); not an error | NOTED |\n| HAC SE sensitivity to lag length (0,2,4,8,12): 0.029–0.037, conclusion unchanged | PASS |\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . ; ls out/state/gate_receipts","description":"Write checks and run gate (P4)"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1490,"cache_read_input_tokens":22984,"output_tokens":851,"output_tokens_details":{"thinking_tokens":84},"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":1490},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpU4hw9R91Js3GNVwbV","requestRef":"b33fb11e-4e6c-4c2d-905f-03252807f89e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"580ad9d4-f0c3-4ca6-8520-070fdf190829","timestamp":"2026-10-30T04:50:18.297Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"580ad9d4-f0c3-4ca6-8520-070fdf190829","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UtYdwLtxG3zP1u2rRa891b","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (10 of 48 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:sample_start: ok\n [ok] key:sample_end: ok\n [ok] key:n_sub1: ok\n [ok] key:n_sub2: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:intercept: ok\n [ok] key:effect_se: ok\n [ok] key:hac_lags: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:beta_sub1: ok\n [ok] key:beta_sub2: ok\n [ok] key:chow_f_stat: ok\n [ok] key:chow_p_value: ok\n [ok] key:stability_conclusion: ok\n [ok] key:conclusion: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P1', 'P2', 'P3', 'P4', 'P5']\n [ok] exclusion_ledger: 2 steps consistent\n [ok] ci:effect_estimate: -0.3262968043702248 <= -0.2557677277487258 <= -0.18523865112722682\n [ok] positive:effect_se: 0.03598488399675878\n [ok] positive:chow_f_stat: 6.0903330062337675\n [ok] positive:baseline_metric: 0.32465793964999184\n [ok] positive:model_metric: 0.2497438816636253\n [ok] chronology:sample_start<=sample_end: 1960-01-01 vs 2019-10-01\n [ok] reproducibility: regenerated in 1.1s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0169/out/state/gate_receipts/20261030T045019.492534Z.json\n20261030T045019.492534Z.json","is_error":false}]},"uuid":"0a242e76-4b0c-403e-810e-e7413db13f16","timestamp":"2026-10-30T04:50:19.502Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (10 of 48 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:sample_start: ok\n [ok] key:sample_end: ok\n [ok] key:n_sub1: ok\n [ok] key:n_sub2: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:intercept: ok\n [ok] key:effect_se: ok\n [ok] key:hac_lags: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:beta_sub1: ok\n [ok] key:beta_sub2: ok\n [ok] key:chow_f_stat: ok\n [ok] key:chow_p_value: ok\n [ok] key:stability_conclusion: ok\n [ok] key:conclusion: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P1', 'P2', 'P3', 'P4', 'P5']\n [ok] exclusion_ledger: 2 steps consistent\n [ok] ci:effect_estimate: -0.3262968043702248 <= -0.2557677277487258 <= -0.18523865112722682\n [ok] positive:effect_se: 0.03598488399675878\n [ok] positive:chow_f_stat: 6.0903330062337675\n [ok] positive:baseline_metric: 0.32465793964999184\n [ok] positive:model_metric: 0.2497438816636253\n [ok] chronology:sample_start<=sample_end: 1960-01-01 vs 2019-10-01\n [ok] reproducibility: regenerated in 1.1s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0169/out/state/gate_receipts/20261030T045019.492534Z.json\n20261030T045019.492534Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"580ad9d4-f0c3-4ca6-8520-070fdf190829","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"31608d7cc82df728a4f3c0608e2bf0b7f65b79eee8049c3dc2ec77e2519ee6c2","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01UtYdwLtxG3zP1u2rRa891b","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| check | outcome |\n|---|---|\n| Clean re-run (deleted results.json, table1.csv, figure1.png, exclusions.csv; re-ran analysis.py); results.json byte-identical | PASS |\n| Exclusion ledger: 319 GDPC1 quarters − 78 − 1 = 240 = n_analysed | PASS |\n| n_sub1 + n_sub2 = 96 + 144 = 240 = n_analysed | PASS |\n| sample_start 1960-01-01 < sample_end 2019-10-01; no quarter after 2019Q4 used (asserted in script) | PASS |\n| All 3 monthly UNRATE values present for every quarter 1959Q4–2019Q4; no missing GDPC1 (asserted) | PASS |\n| effect_se > 0; CI contains estimate; CI symmetric with z=1.96 | PASS |\n| model_metric (0.250) < baseline_metric (0.325); 1 − (model/baseline)^2 = R² (0.408) to 1e-12 | PASS |\n| Magnitude: β ≈ −0.26 pp per 1% q/q growth, in the conventional Okun range (≈ −0.3 to −0.5 per annualised-equivalent... i.e. ≈ −0.25 to −0.5 here) | PASS (plausible) |\n| Chow df = (2, 236); F > 0 | PASS |\n| Full-sample β (−0.256) lies outside [β_sub2, β_sub1] = [−0.273, −0.259]: explained by the intercept shift between subperiods (pooled fit with a common intercept tilts the slope); not an error | NOTED |\n| HAC SE sensitivity to lag length (0,2,4,8,12): 0.029–0.037, conclusion unchanged | PASS |\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . ; ls out/state/gate_receipts","description":"Write checks and run gate (P4)"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"f16806b3-483a-441c-be28-9aed2f6591a7","timestamp":"2026-10-30T04:50:19.506Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"b33fb11e-4e6c-4c2d-905f-03252807f89e","keep":24,"tail":["31608d7cc82df728a4f3c0608e2bf0b7f65b79eee8049c3dc2ec77e2519ee6c2","b6859660703aa05faccc1160e963f0df016d58bf937ef56381be79f4b6277dc8"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7ec479471cc641af34c26bb47a34c2dc49a1f232ed58f167250f3809b05a42d8"} {"parentUuid":"0a242e76-4b0c-403e-810e-e7413db13f16","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpUksATd6eRZi5uaBbw","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":1908,"cache_read_input_tokens":24474,"output_tokens":474,"output_tokens_details":{"thinking_tokens":44},"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":1908},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":403,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpUkbHFgtJw6RdDuhQs","requestRef":"f16806b3-483a-441c-be28-9aed2f6591a7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c6f94a91-c4c0-48ad-8245-80d212f56c75","timestamp":"2026-10-30T04:50:21.218Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"c6f94a91-c4c0-48ad-8245-80d212f56c75","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpUksATd6eRZi5uaBbw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XaLmDct5Axnsiz7hosGn1t","name":"Bash","input":{"command":"sed -i '' 's/| Magnitude: .*| PASS (plausible) |/| Magnitude: β ≈ −0.26 pp per 1% (non-annualised) quarterly growth, consistent with the commonly cited US Okun coefficient of roughly −0.3 to −0.5 in level-gap form; order of magnitude plausible | PASS (plausible) |/' out/state/checks.md; grep Magnitude out/state/checks.md\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed (audit + exclusion ledger). P2 passed: baseline RMSE 0.3247 (mean-only). P3 passed: analysis.py written; HAC lags=4 (NW 1994 rule); supplementary HAC break tests and lag sensitivity added.\n- 2026-10-30 P4: clean rerun identical; checks.md written; gate run 1 (20261030T045019.492534Z) failed only on P5 artefacts (report, claims, phase ledger) as expected at this stage.\nEOF","description":"Fix check wording and update log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1908,"cache_read_input_tokens":24474,"output_tokens":474,"output_tokens_details":{"thinking_tokens":44},"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":1908},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpUkbHFgtJw6RdDuhQs","requestRef":"f16806b3-483a-441c-be28-9aed2f6591a7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c0e217ac-4134-4cf7-9f43-f8335af1f482","timestamp":"2026-10-30T04:50:24.409Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"c0e217ac-4134-4cf7-9f43-f8335af1f482","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XaLmDct5Axnsiz7hosGn1t","type":"tool_result","content":"| Magnitude: β ≈ −0.26 pp per 1% (non-annualised) quarterly growth, consistent with the commonly cited US Okun coefficient of roughly −0.3 to −0.5 in level-gap form; order of magnitude plausible | PASS (plausible) |","is_error":false}]},"uuid":"6ba0f67b-d48f-40f7-996b-dbd7252876aa","timestamp":"2026-10-30T04:50:24.469Z","toolUseResult":{"stdout":"| Magnitude: β ≈ −0.26 pp per 1% (non-annualised) quarterly growth, consistent with the commonly cited US Okun coefficient of roughly −0.3 to −0.5 in level-gap form; order of magnitude plausible | PASS (plausible) |","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c0e217ac-4134-4cf7-9f43-f8335af1f482","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"7a92928477d028f3b1129e5de5a6f39fa5f2a24d5f12a54110d90a80513b0cc1","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01XaLmDct5Axnsiz7hosGn1t","name":"Bash","input":{"command":"sed -i '' 's/| Magnitude: .*| PASS (plausible) |/| Magnitude: β ≈ −0.26 pp per 1% (non-annualised) quarterly growth, consistent with the commonly cited US Okun coefficient of roughly −0.3 to −0.5 in level-gap form; order of magnitude plausible | PASS (plausible) |/' out/state/checks.md; grep Magnitude out/state/checks.md\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed (audit + exclusion ledger). P2 passed: baseline RMSE 0.3247 (mean-only). P3 passed: analysis.py written; HAC lags=4 (NW 1994 rule); supplementary HAC break tests and lag sensitivity added.\n- 2026-10-30 P4: clean rerun identical; checks.md written; gate run 1 (20261030T045019.492534Z) failed only on P5 artefacts (report, claims, phase ledger) as expected at this stage.\nEOF","description":"Fix check wording and update log"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"a878c0b5-4b46-4ac7-af15-f5bfb85a331d","timestamp":"2026-10-30T04:50:24.472Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"f16806b3-483a-441c-be28-9aed2f6591a7","keep":26,"tail":["7a92928477d028f3b1129e5de5a6f39fa5f2a24d5f12a54110d90a80513b0cc1","6f659d2fc39bbdf1a2017559be22cc521433abf60e1afd2126a59e8c9eeee18a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7df9a2940e2fe48be64949e144d0dcad46a50476c794b5c1945f6e1082199a9c"} {"parentUuid":"6ba0f67b-d48f-40f7-996b-dbd7252876aa","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpV89pusEAp1cWtUDHT","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":575,"cache_read_input_tokens":26382,"output_tokens":3654,"output_tokens_details":{"thinking_tokens":42},"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":575},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":409,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpV7uCJMQkT7Pzd8s2R","requestRef":"a878c0b5-4b46-4ac7-af15-f5bfb85a331d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"83796491-bc97-4718-b8bf-12607a41d82c","timestamp":"2026-10-30T04:50:26.138Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"83796491-bc97-4718-b8bf-12607a41d82c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpV89pusEAp1cWtUDHT","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MB6wnboRxKDPjz1h3B31dk","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960–2019 (F6-conf-03)\n\n## Question\nHow strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and has that response been stable? Estimand: β in Δu_t = α + β·g_t + ε_t, 1960Q1–2019Q4, with u_t the quarterly mean of monthly UNRATE (percent) and g_t = 100·Δln GDPC1 (percent, not annualised). Stability: separate OLS on 1960Q1–1983Q4 and 1984Q1–2019Q4 plus a classical Chow F-test of joint equality of (α, β).\n\n## Data and exclusions\nInputs: `data/GDPC1.csv` (319 quarterly rows, 1947Q1–2026Q3) and `data/UNRATE.csv` (945 monthly rows, 1948-01–2026-09) (`n_input_rows`). SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Data issues (`data_issues`): one blank UNRATE value (2025-10), outside the window; both series extend past 2019Q4 and are the 2026 revised vintage. Exclusions (`out/exclusions.csv`): 319 GDPC1 quarters → 241 in 1959Q4–2019Q4 (78 removed, incl. everything after 2019Q4) → 240 after losing 1959Q4 to differencing. All three months were present in every quarter of the window. Regression sample: `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01, `n_analysed` = 240; `n_sub1` = 96, `n_sub2` = 144.\n\n## Method\n- Baseline: mean-only prediction of Δu; RMSE `baseline_metric`.\n- Main: full-sample OLS of Δu on a constant and g; point estimates `effect_estimate`, `intercept`; in-sample residual RMSE `model_metric`.\n- Uncertainty: Newey–West HAC standard error (Bartlett kernel, small-sample correction) with `hac_lags` = 4 quarters, chosen by the Newey–West (1994) rule floor(4(T/100)^{2/9}) with T = 240; 95% CI = β ± 1.96·SE (`effect_ci_low`, `effect_ci_high`). `conclusion` is set from whether this interval excludes zero.\n- Stability: OLS by subperiod (`beta_sub1`, `beta_sub2`); classical Chow F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n − 4)], df (2, 236) (`chow_f_stat`, `chow_p_value`, `stability_conclusion`). Supplementary (not required): HAC Wald tests in an interaction model with a post-1984 dummy, and HAC SE sensitivity to the lag length.\n- No randomness used (`random_seed` = null). Everything is produced by `out/analysis.py` (also `out/table1.csv`, `out/figure1.png`).\n\n## Results\n- Okun coefficient: `effect_estimate` = −0.256 pp of unemployment per 1% quarterly real GDP growth; `intercept` = 0.184 pp. So unemployment is flat when quarterly growth is about 0.72% (`implied_zero_du_growth_full`), roughly 2.9% annualised.\n- Fit: `model_metric` = 0.250 pp, compared with `baseline_metric` = 0.325 pp for the mean-only baseline (`r_squared_full` = 0.408).\n- Subperiods (Table 1, `out/table1.csv`): `beta_sub1` = −0.259 (`intercept_sub1` = 0.254) and `beta_sub2` = −0.273 (`intercept_sub2` = 0.152). The slopes are almost the same. What differs is the intercept: after 1984, unemployment stops rising at a lower growth rate, which fits slower trend growth.\n- Chow test: `chow_f_stat` = 6.09, `chow_p_value` = 0.0026 → `stability_conclusion` = `unstable`. The joint (α, β) relation is not stable. The difference appears to come from the intercept, not the slope. Testing the slope difference alone with HAC gives p = 0.85 (`hac_slope_diff_p_value`). The intercept difference alone gives p = 0.25 (`hac_intercept_diff_p_value`). The joint HAC Wald test still rejects (`hac_joint_break_f_stat` = 5.37, `hac_joint_break_p_value` = 0.0052), because the two estimates are strongly correlated.\n- Figure 1 (`out/figure1.png`): scatter of Δu against g with the two subperiod fitted lines.\n- Conclusion code: `conclusion` = `negative_effect`.\n\n## Uncertainty\nHAC SE `effect_se` = 0.036 (classical OLS SE `ols_classical_se_full` = 0.020). The HAC SE is about 1.8 times the classical one, so the residuals are serially correlated and/or heteroskedastic. 95% CI [`effect_ci_low`, `effect_ci_high`] = [−0.326, −0.185], well below zero. Changing the lag length (0, 2, 8, 12) gives SEs of 0.029–0.037 (`hac_se_lag_sensitivity`). Those choices do not change the conclusion. The subperiod HAC SEs are `beta_sub1_hac_se` = 0.040 and `beta_sub2_hac_se` = 0.069, so the two slopes cannot be told apart statistically.\n\n## Limitations and open issues\n- **The Chow test assumes things the data do not meet.** The classical Chow F assumes homoskedastic, serially uncorrelated errors, and it was required in that form. Residual variance differs between the subperiods (`resid_variance_sub1` = 0.079 vs `resid_variance_sub2` = 0.048, i.e. the Great Moderation). The large HAC/OLS SE ratio shows the errors are not i.i.d. So the classical p-value is not exactly valid. The HAC joint Wald test (p = 0.0052) points the same way. Even so, a Wald test that allows different variances in each subperiod, or a sup-Wald test with an unknown break date, was not run. The 1984 break date is set by the task rather than estimated, which makes conventional inference a fair test of a pre-specified hypothesis. It does not show the break actually happened in 1984.\n- **What \"unstable\" means here.** The rejection applies to (α, β) jointly. The question asks whether the *response* (β) is stable, and our data give no evidence that the slope changed. Reading `stability_conclusion` = unstable as \"Okun's coefficient changed\" would overstate the result.\n- **Specification threats.** The static difference form leaves out lagged growth. Unemployment usually lags output, and this is part of why the residuals are autocorrelated. A dynamic model could give a different long-run coefficient. The relation is also treated as linear and symmetric; asymmetry between recessions and expansions was not checked. OLS treats g as exogenous. β is a reduced-form association, not a causal effect, and measurement error in GDP would bias |β| towards zero.\n- **Data vintage.** GDPC1 is the 2026 revised vintage. Results based on real-time data, or on a different benchmark revision, could differ somewhat. Not checked.\n- **Outliers and influence.** No influence diagnostics were run. Large recession quarters (e.g. 1980, 2008–09) visibly drive the fit in Figure 1.\n- **Not checked:** other kernels or bandwidth selectors (beyond the lag sensitivity reported), t versus normal critical values (with T = 240 the difference is negligible), and the robustness of the result to the break date.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4, a 1% higher quarterly real GDP growth rate is associated with a 0.256 pp smaller rise in the unemployment rate; the HAC 95% interval lies entirely below zero.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"hac_lags\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Reduced-form association from a static difference model; not causal.\"},\n {\"id\":\"C2\",\"text\":\"The Okun regression lowers the in-sample RMSE of the quarterly change in unemployment from 0.325 pp (mean-only baseline) to 0.250 pp.\",\"results_keys\":[\"baseline_metric\",\"model_metric\",\"r_squared_full\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C3\",\"text\":\"The classical Chow test rejects joint equality of intercept and slope across 1960Q1-1983Q4 and 1984Q1-2019Q4 at 5% (F = 6.09, p = 0.0026), so the relation is classified as unstable.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"hac_joint_break_p_value\"],\"status\":\"supported\",\"caveat\":\"Classical Chow assumes i.i.d. errors, which the data contradict; a HAC joint Wald test also rejects.\"},\n {\"id\":\"C4\",\"text\":\"The subperiod slopes are nearly identical (-0.259 vs -0.273) and their difference is not statistically significant; the instability is in the intercept/joint relation rather than in the Okun coefficient itself.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"beta_sub1_hac_se\",\"beta_sub2_hac_se\",\"hac_slope_diff_p_value\",\"intercept_sub1\",\"intercept_sub2\",\"hac_intercept_diff_p_value\"],\"status\":\"supported\",\"caveat\":\"The individual intercept difference is not significant either (HAC p = 0.25); the attribution to the intercept is based on point estimates and the joint test.\"},\n {\"id\":\"C5\",\"text\":\"HAC inference on the full-sample beta is robust to the choice of Newey-West lag length between 0 and 12.\",\"results_keys\":[\"hac_se_lag_sensitivity\",\"effect_se\"],\"status\":\"supported\",\"caveat\":\"Only Bartlett kernel with fixed lags examined.\"}\n]\nEOF","description":"Write report and claims ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":575,"cache_read_input_tokens":26382,"output_tokens":3654,"output_tokens_details":{"thinking_tokens":42},"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":575},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpV7uCJMQkT7Pzd8s2R","requestRef":"a878c0b5-4b46-4ac7-af15-f5bfb85a331d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"57666f16-7acd-48cb-9723-b2fab4a6c566","timestamp":"2026-10-30T04:50:55.573Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"57666f16-7acd-48cb-9723-b2fab4a6c566","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MB6wnboRxKDPjz1h3B31dk","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"ebfb1c99-341a-42d2-9363-dfe5a92c5186","timestamp":"2026-10-30T04:50:55.615Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"57666f16-7acd-48cb-9723-b2fab4a6c566","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"3d04d32f1514ad9c3b59c38df80a30ed4c7bd02bcd0044e6ef6bf88efa398a72","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01MB6wnboRxKDPjz1h3B31dk","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960–2019 (F6-conf-03)\n\n## Question\nHow strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and has that response been stable? Estimand: β in Δu_t = α + β·g_t + ε_t, 1960Q1–2019Q4, with u_t the quarterly mean of monthly UNRATE (percent) and g_t = 100·Δln GDPC1 (percent, not annualised). Stability: separate OLS on 1960Q1–1983Q4 and 1984Q1–2019Q4 plus a classical Chow F-test of joint equality of (α, β).\n\n## Data and exclusions\nInputs: `data/GDPC1.csv` (319 quarterly rows, 1947Q1–2026Q3) and `data/UNRATE.csv` (945 monthly rows, 1948-01–2026-09) (`n_input_rows`). SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Data issues (`data_issues`): one blank UNRATE value (2025-10), outside the window; both series extend past 2019Q4 and are the 2026 revised vintage. Exclusions (`out/exclusions.csv`): 319 GDPC1 quarters → 241 in 1959Q4–2019Q4 (78 removed, incl. everything after 2019Q4) → 240 after losing 1959Q4 to differencing. All three months were present in every quarter of the window. Regression sample: `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01, `n_analysed` = 240; `n_sub1` = 96, `n_sub2` = 144.\n\n## Method\n- Baseline: mean-only prediction of Δu; RMSE `baseline_metric`.\n- Main: full-sample OLS of Δu on a constant and g; point estimates `effect_estimate`, `intercept`; in-sample residual RMSE `model_metric`.\n- Uncertainty: Newey–West HAC standard error (Bartlett kernel, small-sample correction) with `hac_lags` = 4 quarters, chosen by the Newey–West (1994) rule floor(4(T/100)^{2/9}) with T = 240; 95% CI = β ± 1.96·SE (`effect_ci_low`, `effect_ci_high`). `conclusion` is set from whether this interval excludes zero.\n- Stability: OLS by subperiod (`beta_sub1`, `beta_sub2`); classical Chow F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n − 4)], df (2, 236) (`chow_f_stat`, `chow_p_value`, `stability_conclusion`). Supplementary (not required): HAC Wald tests in an interaction model with a post-1984 dummy, and HAC SE sensitivity to the lag length.\n- No randomness used (`random_seed` = null). Everything is produced by `out/analysis.py` (also `out/table1.csv`, `out/figure1.png`).\n\n## Results\n- Okun coefficient: `effect_estimate` = −0.256 pp of unemployment per 1% quarterly real GDP growth; `intercept` = 0.184 pp. So unemployment is flat when quarterly growth is about 0.72% (`implied_zero_du_growth_full`), roughly 2.9% annualised.\n- Fit: `model_metric` = 0.250 pp, compared with `baseline_metric` = 0.325 pp for the mean-only baseline (`r_squared_full` = 0.408).\n- Subperiods (Table 1, `out/table1.csv`): `beta_sub1` = −0.259 (`intercept_sub1` = 0.254) and `beta_sub2` = −0.273 (`intercept_sub2` = 0.152). The slopes are almost the same. What differs is the intercept: after 1984, unemployment stops rising at a lower growth rate, which fits slower trend growth.\n- Chow test: `chow_f_stat` = 6.09, `chow_p_value` = 0.0026 → `stability_conclusion` = `unstable`. The joint (α, β) relation is not stable. The difference appears to come from the intercept, not the slope. Testing the slope difference alone with HAC gives p = 0.85 (`hac_slope_diff_p_value`). The intercept difference alone gives p = 0.25 (`hac_intercept_diff_p_value`). The joint HAC Wald test still rejects (`hac_joint_break_f_stat` = 5.37, `hac_joint_break_p_value` = 0.0052), because the two estimates are strongly correlated.\n- Figure 1 (`out/figure1.png`): scatter of Δu against g with the two subperiod fitted lines.\n- Conclusion code: `conclusion` = `negative_effect`.\n\n## Uncertainty\nHAC SE `effect_se` = 0.036 (classical OLS SE `ols_classical_se_full` = 0.020). The HAC SE is about 1.8 times the classical one, so the residuals are serially correlated and/or heteroskedastic. 95% CI [`effect_ci_low`, `effect_ci_high`] = [−0.326, −0.185], well below zero. Changing the lag length (0, 2, 8, 12) gives SEs of 0.029–0.037 (`hac_se_lag_sensitivity`). Those choices do not change the conclusion. The subperiod HAC SEs are `beta_sub1_hac_se` = 0.040 and `beta_sub2_hac_se` = 0.069, so the two slopes cannot be told apart statistically.\n\n## Limitations and open issues\n- **The Chow test assumes things the data do not meet.** The classical Chow F assumes homoskedastic, serially uncorrelated errors, and it was required in that form. Residual variance differs between the subperiods (`resid_variance_sub1` = 0.079 vs `resid_variance_sub2` = 0.048, i.e. the Great Moderation). The large HAC/OLS SE ratio shows the errors are not i.i.d. So the classical p-value is not exactly valid. The HAC joint Wald test (p = 0.0052) points the same way. Even so, a Wald test that allows different variances in each subperiod, or a sup-Wald test with an unknown break date, was not run. The 1984 break date is set by the task rather than estimated, which makes conventional inference a fair test of a pre-specified hypothesis. It does not show the break actually happened in 1984.\n- **What \"unstable\" means here.** The rejection applies to (α, β) jointly. The question asks whether the *response* (β) is stable, and our data give no evidence that the slope changed. Reading `stability_conclusion` = unstable as \"Okun's coefficient changed\" would overstate the result.\n- **Specification threats.** The static difference form leaves out lagged growth. Unemployment usually lags output, and this is part of why the residuals are autocorrelated. A dynamic model could give a different long-run coefficient. The relation is also treated as linear and symmetric; asymmetry between recessions and expansions was not checked. OLS treats g as exogenous. β is a reduced-form association, not a causal effect, and measurement error in GDP would bias |β| towards zero.\n- **Data vintage.** GDPC1 is the 2026 revised vintage. Results based on real-time data, or on a different benchmark revision, could differ somewhat. Not checked.\n- **Outliers and influence.** No influence diagnostics were run. Large recession quarters (e.g. 1980, 2008–09) visibly drive the fit in Figure 1.\n- **Not checked:** other kernels or bandwidth selectors (beyond the lag sensitivity reported), t versus normal critical values (with T = 240 the difference is negligible), and the robustness of the result to the break date.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4, a 1% higher quarterly real GDP growth rate is associated with a 0.256 pp smaller rise in the unemployment rate; the HAC 95% interval lies entirely below zero.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"hac_lags\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Reduced-form association from a static difference model; not causal.\"},\n {\"id\":\"C2\",\"text\":\"The Okun regression lowers the in-sample RMSE of the quarterly change in unemployment from 0.325 pp (mean-only baseline) to 0.250 pp.\",\"results_keys\":[\"baseline_metric\",\"model_metric\",\"r_squared_full\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C3\",\"text\":\"The classical Chow test rejects joint equality of intercept and slope across 1960Q1-1983Q4 and 1984Q1-2019Q4 at 5% (F = 6.09, p = 0.0026), so the relation is classified as unstable.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"hac_joint_break_p_value\"],\"status\":\"supported\",\"caveat\":\"Classical Chow assumes i.i.d. errors, which the data contradict; a HAC joint Wald test also rejects.\"},\n {\"id\":\"C4\",\"text\":\"The subperiod slopes are nearly identical (-0.259 vs -0.273) and their difference is not statistically significant; the instability is in the intercept/joint relation rather than in the Okun coefficient itself.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"beta_sub1_hac_se\",\"beta_sub2_hac_se\",\"hac_slope_diff_p_value\",\"intercept_sub1\",\"intercept_sub2\",\"hac_intercept_diff_p_value\"],\"status\":\"supported\",\"caveat\":\"The individual intercept difference is not significant either (HAC p = 0.25); the attribution to the intercept is based on point estimates and the joint test.\"},\n {\"id\":\"C5\",\"text\":\"HAC inference on the full-sample beta is robust to the choice of Newey-West lag length between 0 and 12.\",\"results_keys\":[\"hac_se_lag_sensitivity\",\"effect_se\"],\"status\":\"supported\",\"caveat\":\"Only Bartlett kernel with fixed lags examined.\"}\n]\nEOF","description":"Write report and claims ledger"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"95f9c067-25aa-4b9a-a177-2ffeccbe1d1f","timestamp":"2026-10-30T04:50:55.618Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"a878c0b5-4b46-4ac7-af15-f5bfb85a331d","keep":28,"tail":["3d04d32f1514ad9c3b59c38df80a30ed4c7bd02bcd0044e6ef6bf88efa398a72","662cfbafe6e2f8a17d200985ee172267a763b1975e128fb39f80de2127a8d53f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"92619ff67ca50cefd89aa6ab3d5ab27f57998246eb1c064abc72473823a29820"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"ebfb1c99-341a-42d2-9363-dfe5a92c5186","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"type":"atis-latch","atis":"","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"parentUuid":"ebfb1c99-341a-42d2-9363-dfe5a92c5186","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpXRDoKEkbDWu5nkFDT","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":3669,"cache_read_input_tokens":26957,"output_tokens":858,"output_tokens_details":{"thinking_tokens":88},"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":3669},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":700,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpXQvwJH91okuxxTKbE","requestRef":"95f9c067-25aa-4b9a-a177-2ffeccbe1d1f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c4b2547f-77cc-4722-99e7-99bfbd56ad0d","timestamp":"2026-10-30T04:50:57.866Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"c4b2547f-77cc-4722-99e7-99bfbd56ad0d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpXRDoKEkbDWu5nkFDT","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017FtJhB2c3fC18k1nvrPWED","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimands, outputs, rules, invalidity conditions\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs computed and match README\",\"row/col counts, date ranges, gaps, duplicates, missing values audited (data_audit.md)\",\"exclusion ledger 319-78-1=240 verified\"],\"notes\":\"One blank UNRATE (2025-10) outside window\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) computed = 0.3247 on the same 240-quarter sample\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png, exclusions.csv\",\"no randomness; random_seed null\",\"HAC lags=4 by NW(1994) rule\"],\"notes\":\"\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json\",\"consistency checks in checks.md all PASS\",\"gate run 1: receipt out/state/gate_receipts/20261030T045019.492534Z.json — failures only for not-yet-written P5 artefacts (report, claims, phase ledger); contract, CI, positivity, chronology, exclusion ledger, reproducibility all ok\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md with six required sections, each number cites a results key\",\"claims.json written; all keys exist in results.json\",\"final gate run (see receipts)\"],\"notes\":\"\"}}\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\nr=json.load(open('out/results.json')); c=json.load(open('out/claims.json'))\nprint([k for x in c for k in x['results_keys'] if k not in r])\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"","description":"Finalize phases and run final gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3669,"cache_read_input_tokens":26957,"output_tokens":858,"output_tokens_details":{"thinking_tokens":88},"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":3669},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpXQvwJH91okuxxTKbE","requestRef":"95f9c067-25aa-4b9a-a177-2ffeccbe1d1f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"44edb6bd-3a18-4901-8fca-4d8c136cc064","timestamp":"2026-10-30T04:51:03.561Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"44edb6bd-3a18-4901-8fca-4d8c136cc064","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017FtJhB2c3fC18k1nvrPWED","type":"tool_result","content":"[]\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0169/out/state/gate_receipts/20261030T045104.837144Z.json","is_error":false}]},"uuid":"546c205f-72b1-4c66-8cc6-77c0a929bf9e","timestamp":"2026-10-30T04:51:04.844Z","toolUseResult":{"stdout":"[]\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0169/out/state/gate_receipts/20261030T045104.837144Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"44edb6bd-3a18-4901-8fca-4d8c136cc064","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"2f932a7f80236e8761ded1a41040e4c4e52ff3395ab86f87d815ae5c8f6bb3cd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_017FtJhB2c3fC18k1nvrPWED","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimands, outputs, rules, invalidity conditions\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs computed and match README\",\"row/col counts, date ranges, gaps, duplicates, missing values audited (data_audit.md)\",\"exclusion ledger 319-78-1=240 verified\"],\"notes\":\"One blank UNRATE (2025-10) outside window\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) computed = 0.3247 on the same 240-quarter sample\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png, exclusions.csv\",\"no randomness; random_seed null\",\"HAC lags=4 by NW(1994) rule\"],\"notes\":\"\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json\",\"consistency checks in checks.md all PASS\",\"gate run 1: receipt out/state/gate_receipts/20261030T045019.492534Z.json — failures only for not-yet-written P5 artefacts (report, claims, phase ledger); contract, CI, positivity, chronology, exclusion ledger, reproducibility all ok\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md with six required sections, each number cites a results key\",\"claims.json written; all keys exist in results.json\",\"final gate run (see receipts)\"],\"notes\":\"\"}}\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\nr=json.load(open('out/results.json')); c=json.load(open('out/claims.json'))\nprint([k for x in c for k in x['results_keys'] if k not in r])\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"","description":"Finalize phases and run final gate"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"192aa0ae-4b53-4261-b759-2f7806a99d95","timestamp":"2026-10-30T04:51:04.847Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"95f9c067-25aa-4b9a-a177-2ffeccbe1d1f","keep":30,"tail":["2f932a7f80236e8761ded1a41040e4c4e52ff3395ab86f87d815ae5c8f6bb3cd","b78e6fbf2446af6103a46d6fc4b16ac078fabedf74b4dbe9791213d2b7ed82fe"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"099eecc755a1f0dd5d86afd82f2b4fafca5f7107c6d25903f897cea17459ecfb"} {"parentUuid":"546c205f-72b1-4c66-8cc6-77c0a929bf9e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpY6hqep4eSGHaUNALR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MsQ99ZFsc23m4TaRrm7k5u","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; d=json.load(open(p))\nd['P5']['checks'][-1]=\"final gate run 2: receipt out/state/gate_receipts/20261030T045104.837144Z.json PASSED (0 of 48 failed)\"\njson.dump(d,open(p,'w'),indent=1)\nEOF\necho \"- 2026-10-30 P5 passed: report, claims written; gate run 2 (20261030T045104.837144Z) PASSED. Task complete.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record receipt and confirm gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":956,"cache_read_input_tokens":30626,"output_tokens":313,"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":956},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpY6RyKnqjhFQ7zG44g","requestRef":"192aa0ae-4b53-4261-b759-2f7806a99d95","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a050914c-827d-430a-98da-18a21fc90942","timestamp":"2026-10-30T04:51:08.074Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"a050914c-827d-430a-98da-18a21fc90942","isSidechain":false,"promptId":"f1abe550-c839-453e-86a3-50749a1a8dd0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MsQ99ZFsc23m4TaRrm7k5u","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)","is_error":false}]},"uuid":"17d2853a-a3d5-4edc-a45c-31a68970ec30","timestamp":"2026-10-30T04:51:09.415Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a050914c-827d-430a-98da-18a21fc90942","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","hash":"1edb771fb4b49d7f6a81ab58a598a17fe5ed72fcfa617fa3fb251e48d5fa26e8","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MsQ99ZFsc23m4TaRrm7k5u","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np='out/state/phases.json'; d=json.load(open(p))\nd['P5']['checks'][-1]=\"final gate run 2: receipt out/state/gate_receipts/20261030T045104.837144Z.json PASSED (0 of 48 failed)\"\njson.dump(d,open(p,'w'),indent=1)\nEOF\necho \"- 2026-10-30 P5 passed: report, claims written; gate run 2 (20261030T045104.837144Z) PASSED. Task complete.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record receipt and confirm gate"}}]}} {"type":"api-request","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","id":"e5c2e5df-bef7-4108-9f8a-d427ed5ff9e1","timestamp":"2026-10-30T04:51:09.419Z","version":"2.1.314","querySource":"sdk","shapeHash":"c3c94937d96da46f69f6d4c09f4ff501be59660c9cdf3cce35bc2dad0b838ad3","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":"192aa0ae-4b53-4261-b759-2f7806a99d95","keep":32,"tail":["1edb771fb4b49d7f6a81ab58a598a17fe5ed72fcfa617fa3fb251e48d5fa26e8","abaf470c1f21b6e1036f5fc607f05d1d3b3ff35da874be352254676c0c069666"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c43f40e4d6a60e037e39924efd7565cad6368ee55cbbd2ec86f9b3a2edc15f93"} {"parentUuid":"17d2853a-a3d5-4edc-a45c-31a68970ec30","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYSDrY3D1fNLUPvUaE","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSyAYKEAgTGAI4AUIIdGhpbmtpbmcSDMrjycMY6P4UKvKaGhoMZYnRIjfPbrAj7BvcIjAq+xSodLA0+jalLbSl8lYaPm72MUpMLqr9bUrx8TOmEc0Q56uxqzWYUUYtevoaspAq5QWJeR34bOPmpgqR5JhVmT3/GXT0CwRJy1hBuiufRWJrxUtZGX+p45wPd36iazvx/eoalYH7zhcaiiHDUhxbDxC1TS1eXjMK2hgrK4F8ZXtYFxSPwBBo4QqbRVhORPA29EfV3gP6JvL9xTcsl0BugUkMkVONem2OJ1wZRImREO240rVrzX0mcFpxOZbG1KpG621teTYGD8vdbilwnttkO+QmTxm7tku8P/HvD25pUuuMh1GOP/D9JxobPVFLn0+rmcgBFNaowY1OJv24QaMT+fLSNHkvgOoh0u2SR9TN3gzx7fdXxJz8JV+9Dtw7+ohk26Tpa7i09y7YvRcuLpgxbOzdwceSnc4XI3tMbaXV8RZOeadYhDdtftxOLVbpca0L2vxAiZveH59E9u0gDEXw/hrSSuJ4ce8BqvYGakhXLhSCNcaAWYrxVIu4oE8V+Hchd+didSC9ymhiAZEzj6nrtPTknSlKgfkt20fl3sIwg+V7lkh9tg+r4116Ds0LJtWPT/YkfXfFjuhOEJs4vilVatJfhSa0kFxb6GuzILGM0l9uzqsuWV/TujwcYxHHNcAbJyrszqHcEOUZuQQu/lvqc76uWPugozJtbgnKPaFH7ELKnzKpzom52ndyUKLtjesoDOCzzedyBCzsasVdHEcBOBqkDaQVx73V+Ov1Y4wR4oXM1O5etjyVi/rtLGZTXuX77UtgxmEhg2/o4TFzrYTh/nzWmyK+Opj2BtHKk6lHQgyz0ol6KHKNB8LfKKSxiYLCCCuQYjWErbQ4bQ5j3JiNilv3t5jy2VAHDHe6XNDT/KNb81E94yc0wZKhrhd0MTEc7E1rPnFgkWWm40dO2T4wLxnG8SPcF0KfHX7OuBT1xrZt5wl8Io8iaZrrrCQ19UsqunecnRl+1ZWEkKipu7opDXpe/8n5onxSkz59tglRJ58fPLstRlGkFHRdjyYQroakI2OmHa+HqxcpidSNYL3gxjtHmZJ7wgIYAQ=="}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":353,"cache_read_input_tokens":31582,"output_tokens":1105,"output_tokens_details":{"thinking_tokens":19},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":353},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6730,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpYRwjNL6vXmaVGayzr","requestRef":"e5c2e5df-bef7-4108-9f8a-d427ed5ff9e1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e34952b6-4421-4bd6-b48c-e48008f960af","timestamp":"2026-10-30T04:51:17.400Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e34952b6-4421-4bd6-b48c-e48008f960af","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYSDrY3D1fNLUPvUaE","type":"message","role":"assistant","content":[{"type":"text","text":"The analysis is finished. Over 1960Q1–2019Q4, faster GDP growth is clearly tied to smaller rises in unemployment. The Chow test rejects stability, but the slope itself looks unchanged between the two periods; what moved is the intercept. The final gate run passed all 48 checks, and re-running `out/analysis.py` from a clean state gives an identical `out/results.json`.\n\n**Main estimate (240 quarters, 1960Q1–2019Q4):**\n- **Okun coefficient:** β = −0.256 percentage points of unemployment per 1% quarterly (not annualised) real GDP growth.\n- **Uncertainty:** the Newey–West standard error, using 4 lags, is 0.036, giving a 95% interval of [−0.326, −0.185]. The interval lies entirely below zero, so the conclusion code is `negative_effect`.\n- **Lag choice:** using 0 to 12 lags instead gives standard errors between 0.029 and 0.037, which doesn't change the conclusion.\n- **Fit:** the regression's error (RMSE) is 0.250 pp, against 0.325 pp for simply predicting the average change (R² = 0.41).\n- **Zero-change point:** unemployment holds steady at about 0.72% quarterly growth, roughly 2.9% annualised.\n\n**Stability:**\n- **Slopes by period:** −0.259 for 1960Q1–1983Q4 (96 quarters) and −0.273 for 1984Q1–2019Q4 (144 quarters).\n- **Chow test:** F = 6.09, p = 0.0026, so the result is classified as `unstable`.\n- **What drives the rejection:** the intercept falls from 0.254 to 0.152, while the slopes barely differ. Testing the slope difference alone gives p = 0.85. A joint test that allows for serial correlation also rejects (p = 0.005).\n- **Reading the \"unstable\" label:** the response of unemployment to growth itself shows no sign of change. What shifted after 1984 is the growth rate at which unemployment stops rising.\n\n**Limitations (discussed in the report):**\n- The classical Chow test assumes errors that are uncorrelated over time with constant variance. That assumption fails here: residual variance is 0.079 before 1984 and 0.048 after, and the robust standard error is 1.8 times the classical one.\n- The 1984 break date is set by the task, not estimated.\n- The model has no lagged growth terms and doesn't allow recessions to behave differently from expansions.\n- The GDP figures are the revised 2026 data, not what was known at the time.\n- I ran no checks on whether a few large recession quarters drive the fit.\n- One unemployment value is missing (October 2025), but it falls after 2019 and has no effect on any estimate.\n\nI added a few extra results beyond what the task asked for: the robust break tests, the lag-length comparison and the variance of residuals in each period. Everything was computed from the provided data with no random elements.\n\nFiles are in `out/`:\n- `results.json`\n- `report.md`\n- `analysis.py`\n- `table1.csv`\n- `figure1.png`\n- `claims.json`\n- `exclusions.csv`\n- `state/` (records of each step, plus the gate receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":353,"cache_read_input_tokens":31582,"output_tokens":1105,"output_tokens_details":{"thinking_tokens":19},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":353},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpYRwjNL6vXmaVGayzr","requestRef":"e5c2e5df-bef7-4108-9f8a-d427ed5ff9e1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fa64e551-04e9-4797-b44c-e6b397d73995","timestamp":"2026-10-30T04:51:20.437Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0169","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","version":"2.1.314","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"fa64e551-04e9-4797-b44c-e6b397d73995","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290"} {"type":"cost-state","sessionId":"c68c16b6-da25-49c0-ba21-831cddab1290","totalCostUSD":0.6040034000000001,"totalAPIDuration":166718,"totalAPIDurationWithoutRetries":166709,"totalToolDuration":9663,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":176551,"startTime":1793335703893,"modelUsage":{"claude-opus-5-5":{"inputTokens":36,"outputTokens":19620,"thinkingTokens":1017,"cacheReadInputTokens":296522,"cacheCreationInputTokens":30431,"cacheCreationEphemeral5mInputTokens":30431,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.6040034000000001}},"hasUnknownModelCost":false}