spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:48:23.678Z","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:48:23.684Z","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}4{"parentUuid":null,"isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":"Begin"},"uuid":"efe2d7be-d0d9-4c8c-a69e-747c7f040e76","timestamp":"2026-10-30T04:48:23.689Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","timestamp":"2026-10-30T04:48:23.702Z","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/RC0171\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/<timestamp>.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}}]}}6{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"72c9ce26-ee6a-4700-9702-f33c877401fb","timestamp":"2026-10-30T04:48:23.702Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"ed59874afae125b8050a258f639dc9f0b1db41b2e179434998ec6fb974a24ec5"}8{"parentUuid":"efe2d7be-d0d9-4c8c-a69e-747c7f040e76","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"1e5535c3-a26a-4df4-9026-968705612e72","timestamp":"2026-10-30T04:48:23.694Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"1e5535c3-a26a-4df4-9026-968705612e72","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"1479e88c-9b64-4f4a-ab8a-5b0cf73af07a","timestamp":"2026-10-30T04:48:23.694Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"1479e88c-9b64-4f4a-ab8a-5b0cf73af07a","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"c7390b7f-fa16-4eea-b4ab-87c2ac5ccefd","timestamp":"2026-10-30T04:48:23.695Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}12{"parentUuid":"c7390b7f-fa16-4eea-b4ab-87c2ac5ccefd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLEeWEMCKao1ZgHPRo","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":125,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":443,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpLEN8W4B8XtxsBq9RG","requestRef":"72c9ce26-ee6a-4700-9702-f33c877401fb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"752b9bef-7c8c-40ea-971c-f2993135535d","timestamp":"2026-10-30T04:48:26.419Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"752b9bef-7c8c-40ea-971c-f2993135535d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLEeWEMCKao1ZgHPRo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PG6njtZr5fKW1vxd2fQyRT","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":125,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpLEN8W4B8XtxsBq9RG","requestRef":"72c9ce26-ee6a-4700-9702-f33c877401fb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a01e9bb4-6192-4300-80d7-39adb24fbc91","timestamp":"2026-10-30T04:48:27.126Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"a01e9bb4-6192-4300-80d7-39adb24fbc91","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","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  102 simon-pierreboucher  staff  3264 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_01PG6njtZr5fKW1vxd2fQyRT"}]},"uuid":"d7569470-eac1-4d66-90db-17e4f9346cb6","timestamp":"2026-10-30T04:48:27.182Z","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  102 simon-pierreboucher  staff  3264 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":"a01e9bb4-6192-4300-80d7-39adb24fbc91","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"de9bfa548d43e03f20bece6a2369729f28f5d72a6e25b094f2930b0f6fe38f87","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01PG6njtZr5fKW1vxd2fQyRT","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"b0774d36-eeed-4139-9fc2-b1fce0519b04","timestamp":"2026-10-30T04:48:27.187Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"72c9ce26-ee6a-4700-9702-f33c877401fb","keep":2,"tail":["de9bfa548d43e03f20bece6a2369729f28f5d72a6e25b094f2930b0f6fe38f87","f8b63f38791955a5668049716c27e9f561e996e51f3d96271091ebcfba98e221"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7cd10389a4e47d07512a7d73adc310c203a8fa14af2935a406a75cdade0daf75"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d7569470-eac1-4d66-90db-17e4f9346cb6","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}18{"type":"atis-latch","atis":"","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}19{"parentUuid":"d7569470-eac1-4d66-90db-17e4f9346cb6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLVTUVW69M9NqHM1Dq","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ME9q3LBWijqvAYNV8HqghS","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json bundle.json; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data files and 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":3068,"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":3068},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpLVBNTY9WXKVXEjrHi","requestRef":"b0774d36-eeed-4139-9fc2-b1fce0519b04","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d8f4142c-8310-460d-a43f-8bf589c98853","timestamp":"2026-10-30T04:48:29.224Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"d8f4142c-8310-460d-a43f-8bf589c98853","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ME9q3LBWijqvAYNV8HqghS","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":"0803cde0-6f76-491c-900e-cd00abcfb502","timestamp":"2026-10-30T04:48:29.260Z","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":"d8f4142c-8310-460d-a43f-8bf589c98853","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"51df49b83ff8c60740510d7507c5aa185d0e2f6d5e60ce13634a5d60de3b7aa6","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01ME9q3LBWijqvAYNV8HqghS","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json bundle.json; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data files and gate spec"}}]}}22{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"1bb31c29-4023-4eb0-9959-a4c8819d9f48","timestamp":"2026-10-30T04:48:29.263Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"b0774d36-eeed-4139-9fc2-b1fce0519b04","keep":4,"tail":["51df49b83ff8c60740510d7507c5aa185d0e2f6d5e60ce13634a5d60de3b7aa6","f7bcfbcb56424ec26221fdf215e486d8cf56768845bf56e23f38648dfe832ed0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"80594ad4a3e7778b2db3385ca03030a16b7f635e47f0574cfd63faa9f5e655c1"}23{"parentUuid":"0803cde0-6f76-491c-900e-cd00abcfb502","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLeLHU1PxDGX34ZfJf","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":7175,"output_tokens":649,"output_tokens_details":{"thinking_tokens":108},"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":943,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpLe4f9vxRW8PtW4WjW","requestRef":"1bb31c29-4023-4eb0-9959-a4c8819d9f48","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"96ca19af-2fdc-443d-bf37-be2a598eca9d","timestamp":"2026-10-30T04:48:31.617Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"96ca19af-2fdc-443d-bf37-be2a598eca9d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpLeLHU1PxDGX34ZfJf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QPYSZtKCLxjjmDaYBeQsxd","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',dtype=str)\n    print(f,d.shape,d.columns.tolist())\n    v=pd.to_numeric(d[f],errors='coerce'); dt=pd.to_datetime(d.observation_date,errors='coerce')\n    print('nonnum',d[f][v.isna()].tolist(),'baddate',dt.isna().sum(),'dupdate',dt.duplicated().sum(),'sorted',dt.is_monotonic_increasing)\n    print(dt.min(),dt.max(),v.min(),v.max())\n    exp=pd.date_range(dt.min(),dt.max(),freq='QS' if f=='GDPC1' else 'MS'); print('gaps',len(exp)-len(dt), 'notfirstday',(dt.dt.day!=1).sum())\n    s=v[(dt>='1959-01-01')&(dt<='2019-12-01')]; print('in-window n',len(s),'na',s.isna().sum())\nd=pd.read_csv('data/UNRATE.csv',parse_dates=[0]); print(d[(d.observation_date>='2025-08-01')&(d.observation_date<='2026-01-01')])\n\"","description":"Audit data 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":7175,"output_tokens":649,"output_tokens_details":{"thinking_tokens":108},"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_011CgXpLe4f9vxRW8PtW4WjW","requestRef":"1bb31c29-4023-4eb0-9959-a4c8819d9f48","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f8792318-1838-4197-a4ce-b21e3a0f1fad","timestamp":"2026-10-30T04:48:35.421Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"f8792318-1838-4197-a4ce-b21e3a0f1fad","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QPYSZtKCLxjjmDaYBeQsxd","type":"tool_result","content":"GDPC1 (319, 2) ['observation_date', 'GDPC1']\nnonnum [] baddate 0 dupdate 0 sorted True\n1947-01-01 00:00:00 2026-07-01 00:00:00 2172.432 24611.077\ngaps 0 notfirstday 0\nin-window n 244 na 0\nUNRATE (945, 2) ['observation_date', 'UNRATE']\nnonnum [nan] baddate 0 dupdate 0 sorted True\n1948-01-01 00:00:00 2026-09-01 00:00:00 2.5 14.8\ngaps 0 notfirstday 0\nin-window n 732 na 0\n    observation_date  UNRATE\n931       2025-08-01     4.3\n932       2025-09-01     4.4\n933       2025-10-01     NaN\n934       2025-11-01     4.5\n935       2025-12-01     4.4\n936       2026-01-01     4.3","is_error":false}]},"uuid":"dfe247d7-1f59-4ad0-9399-932bc4decd00","timestamp":"2026-10-30T04:48:35.695Z","toolUseResult":{"stdout":"GDPC1 (319, 2) ['observation_date', 'GDPC1']\nnonnum [] baddate 0 dupdate 0 sorted True\n1947-01-01 00:00:00 2026-07-01 00:00:00 2172.432 24611.077\ngaps 0 notfirstday 0\nin-window n 244 na 0\nUNRATE (945, 2) ['observation_date', 'UNRATE']\nnonnum [nan] baddate 0 dupdate 0 sorted True\n1948-01-01 00:00:00 2026-09-01 00:00:00 2.5 14.8\ngaps 0 notfirstday 0\nin-window n 732 na 0\n    observation_date  UNRATE\n931       2025-08-01     4.3\n932       2025-09-01     4.4\n933       2025-10-01     NaN\n934       2025-11-01     4.5\n935       2025-12-01     4.4\n936       2026-01-01     4.3","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f8792318-1838-4197-a4ce-b21e3a0f1fad","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"6813e4568a667c06da7292fcf01ef91c5b3b97be56d9c1e5733ca0b5ece68fc6","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01QPYSZtKCLxjjmDaYBeQsxd","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',dtype=str)\n    print(f,d.shape,d.columns.tolist())\n    v=pd.to_numeric(d[f],errors='coerce'); dt=pd.to_datetime(d.observation_date,errors='coerce')\n    print('nonnum',d[f][v.isna()].tolist(),'baddate',dt.isna().sum(),'dupdate',dt.duplicated().sum(),'sorted',dt.is_monotonic_increasing)\n    print(dt.min(),dt.max(),v.min(),v.max())\n    exp=pd.date_range(dt.min(),dt.max(),freq='QS' if f=='GDPC1' else 'MS'); print('gaps',len(exp)-len(dt), 'notfirstday',(dt.dt.day!=1).sum())\n    s=v[(dt>='1959-01-01')&(dt<='2019-12-01')]; print('in-window n',len(s),'na',s.isna().sum())\nd=pd.read_csv('data/UNRATE.csv',parse_dates=[0]); print(d[(d.observation_date>='2025-08-01')&(d.observation_date<='2026-01-01')])\n\"","description":"Audit data files"}}]}}27{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"fe5c9880-8741-4b7d-9e93-12d08c1c9ef1","timestamp":"2026-10-30T04:48:35.698Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"1bb31c29-4023-4eb0-9959-a4c8819d9f48","keep":6,"tail":["6813e4568a667c06da7292fcf01ef91c5b3b97be56d9c1e5733ca0b5ece68fc6","3dddfe3b35037c85e444f4380ce42aa4b4512a3daec3d5ab6e974d2bce1a1833"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b507d635296b0fdb31fb661100b7597dc1a23b977b6fe87175a8f66e831dbfba"}28{"parentUuid":"dfe247d7-1f59-4ad0-9399-932bc4decd00","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpM7wwrBsxmQQyo4GFr","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":968,"cache_read_input_tokens":9827,"output_tokens":2426,"output_tokens_details":{"thinking_tokens":563},"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":968},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":5376,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpM7b7i35PZA2gJiLmB","requestRef":"fe5c9880-8741-4b7d-9e93-12d08c1c9ef1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3c1fb790-c293-491b-b966-0d3d6c9ddf27","timestamp":"2026-10-30T04:48:42.496Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"3c1fb790-c293-491b-b966-0d3d6c9ddf27","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpM7wwrBsxmQQyo4GFr","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019qauVPqPyHGE1Xmf1W1Ag6","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract — F6-conf-03 (Okun's law, US 1960Q1–2019Q4)\n**Question.** How much does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and is that response the same before and after 1984?\n**Estimand.** β in Δu_t = α + β g_t + ε_t, with u_t = mean of the 3 monthly UNRATE values in quarter t, Δu_t = u_t − u_{t−1} (pp), and g_t = 100·Δln GDPC1_t (percent, not annualised). Sample: 240 quarters, 1960Q1–2019Q4 (the 1959Q4 levels are used only for the first differences). β is a descriptive (reduced-form) association. It is meaningful as a stable linear projection coefficient if the relation is linear and roughly stationary. It is not a causal effect.\n**Uncertainty.** Newey–West HAC (Bartlett) SE for β, with the lag length chosen and reported. 95% CI = β ± 1.96·SE.\n**Stability.** Separate OLS on 1960Q1–1983Q4 (96 quarters) and 1984Q1–2019Q4 (144 quarters). Classical Chow SSR F-test of the joint equality of (α, β), with df (2, n−4) = (2, 236).\n**Outputs.** 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. Also figure1.png, table1.csv (period,n,intercept,slope,slope_se), report.md (6 sections), analysis.py, claims.json.\n**Information rules.** No quarter after 2019Q4 may enter any estimate. Use only data/GDPC1.csv and data/UNRATE.csv.\n**Invalidity / impossibility.** The task would be infeasible if data were missing inside 1959Q4–2019Q4 or a month was missing from a quarter's average. Any use of post-2019 data would invalidate the result. Note that the GDP vintage is from 2026, so revised data differ from real-time data. That does not matter here because the question is ex post.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully; contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > out/state/data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols | range | freq | units |\n|---|---|---|---|---|---|---|\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01 | quarterly | bn chained 2017 $, SAAR |\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01 | monthly | percent, SA |\n\nBoth hashes match data/README.md and bundle.json.\n- Dates: all parse, all fall on the first day of the period, sorted, no duplicates, no gaps in the date grid.\n- GDPC1: no missing values. Range 2172.4–24611.1.\n- UNRATE: one missing value (empty), at 2025-10-01. This was presumably not published because of the 2025 federal shutdown. It lies outside the analysis window and is excluded by the 2019Q4 cutoff, so it has no effect on the results. Recorded in data_issues.\n- Analysis window: 1959Q4–2019Q4 contains 244 GDP rows from 1959-01, i.e. 241 quarters from 1959Q4. UNRATE has 723 months from 1959-10 to 2019-12. There are no NaNs in the window.\n- Availability: both files extend past 2019Q4 (to 2026). The post-2019 rows are dropped before any computation (see exclusions.csv).\n- Vintage: this is the 2026 vintage of revised GDP. That is acceptable for an ex post question but is noted as a limitation.\nEOF\necho \"- 2026-10-30 P0 passed (contract). P1 audit done: one UNRATE NaN at 2025-10 (outside window). HAC lag rule: floor(4*(n/100)^(2/9))=4.\" > out/state/log.md","description":"Write contract, 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":968,"cache_read_input_tokens":9827,"output_tokens":2426,"output_tokens_details":{"thinking_tokens":563},"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":968},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpM7b7i35PZA2gJiLmB","requestRef":"fe5c9880-8741-4b7d-9e93-12d08c1c9ef1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"09a007e1-6520-400f-9dc7-0198b9892b4a","timestamp":"2026-10-30T04:48:58.385Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"09a007e1-6520-400f-9dc7-0198b9892b4a","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019qauVPqPyHGE1Xmf1W1Ag6","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"9efd21e1-7d90-4716-9c04-05e13271fbba","timestamp":"2026-10-30T04:48:58.418Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"09a007e1-6520-400f-9dc7-0198b9892b4a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"dd21946562c53025bc57b78f6f2e07a0d7b412c83362e8bcd2990957c04485e9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019qauVPqPyHGE1Xmf1W1Ag6","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract — F6-conf-03 (Okun's law, US 1960Q1–2019Q4)\n**Question.** How much does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and is that response the same before and after 1984?\n**Estimand.** β in Δu_t = α + β g_t + ε_t, with u_t = mean of the 3 monthly UNRATE values in quarter t, Δu_t = u_t − u_{t−1} (pp), and g_t = 100·Δln GDPC1_t (percent, not annualised). Sample: 240 quarters, 1960Q1–2019Q4 (the 1959Q4 levels are used only for the first differences). β is a descriptive (reduced-form) association. It is meaningful as a stable linear projection coefficient if the relation is linear and roughly stationary. It is not a causal effect.\n**Uncertainty.** Newey–West HAC (Bartlett) SE for β, with the lag length chosen and reported. 95% CI = β ± 1.96·SE.\n**Stability.** Separate OLS on 1960Q1–1983Q4 (96 quarters) and 1984Q1–2019Q4 (144 quarters). Classical Chow SSR F-test of the joint equality of (α, β), with df (2, n−4) = (2, 236).\n**Outputs.** 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. Also figure1.png, table1.csv (period,n,intercept,slope,slope_se), report.md (6 sections), analysis.py, claims.json.\n**Information rules.** No quarter after 2019Q4 may enter any estimate. Use only data/GDPC1.csv and data/UNRATE.csv.\n**Invalidity / impossibility.** The task would be infeasible if data were missing inside 1959Q4–2019Q4 or a month was missing from a quarter's average. Any use of post-2019 data would invalidate the result. Note that the GDP vintage is from 2026, so revised data differ from real-time data. That does not matter here because the question is ex post.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully; contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > out/state/data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols | range | freq | units |\n|---|---|---|---|---|---|---|\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01 | quarterly | bn chained 2017 $, SAAR |\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01 | monthly | percent, SA |\n\nBoth hashes match data/README.md and bundle.json.\n- Dates: all parse, all fall on the first day of the period, sorted, no duplicates, no gaps in the date grid.\n- GDPC1: no missing values. Range 2172.4–24611.1.\n- UNRATE: one missing value (empty), at 2025-10-01. This was presumably not published because of the 2025 federal shutdown. It lies outside the analysis window and is excluded by the 2019Q4 cutoff, so it has no effect on the results. Recorded in data_issues.\n- Analysis window: 1959Q4–2019Q4 contains 244 GDP rows from 1959-01, i.e. 241 quarters from 1959Q4. UNRATE has 723 months from 1959-10 to 2019-12. There are no NaNs in the window.\n- Availability: both files extend past 2019Q4 (to 2026). The post-2019 rows are dropped before any computation (see exclusions.csv).\n- Vintage: this is the 2026 vintage of revised GDP. That is acceptable for an ex post question but is noted as a limitation.\nEOF\necho \"- 2026-10-30 P0 passed (contract). P1 audit done: one UNRATE NaN at 2025-10 (outside window). HAC lag rule: floor(4*(n/100)^(2/9))=4.\" > out/state/log.md","description":"Write contract, ledger, audit, log"}}]}}32{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"11d70e74-67d8-4644-85ee-2bd18d65c998","timestamp":"2026-10-30T04:48:58.422Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"fe5c9880-8741-4b7d-9e93-12d08c1c9ef1","keep":8,"tail":["dd21946562c53025bc57b78f6f2e07a0d7b412c83362e8bcd2990957c04485e9","b63972a2baba0f33fa5bd7d859f5e83c3965323e93f59567c5082ac4d284a1cc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"657f792d0379753842458682ff300372b36b35943f9fe9653cb8a00231067c96"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"9efd21e1-7d90-4716-9c04-05e13271fbba","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}34{"type":"atis-latch","atis":"","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}35{"parentUuid":"9efd21e1-7d90-4716-9c04-05e13271fbba","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpNo1Do9Gnrt7sJ4eUP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017eqGfDihG3RYnrboo1pzok","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, US 1960Q1-2019Q4 (task F6-conf-03). Run from workspace root:\n   ~/wp29/venv/bin/python out/analysis.py\nReads data/ only; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\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\", parse_dates=[\"observation_date\"])\nun = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()]\nif len(miss):\n    data_issues.append({\"issue\": f\"UNRATE missing for {', '.join(miss.observation_date.dt.strftime('%Y-%m-%d'))}\",\n                        \"handling\": \"Outside the 1959Q4-2019Q4 window; removed by the 2019Q4 cutoff, no imputation needed.\"})\ndata_issues.append({\"issue\": \"Both files extend beyond 2019Q4 (to 2026), outside the question.\",\n                    \"handling\": \"All rows after 2019-12-31 dropped before any computation.\"})\n\n# --- quarterly unemployment: simple average of the 3 months; require complete quarters in window\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\nLAG0, START, END, SPLIT = pd.Period(\"1959Q4\"), pd.Period(\"1960Q1\"), pd.Period(\"2019Q4\"), pd.Period(\"1984Q1\")\nexcl = []\ndef step(d, mask, name, rationale):\n    nb = len(d); d2 = d[mask]\n    excl.append(dict(step=len(excl) + 1, rule=name, n_before=nb, n_after=len(d2), n_removed=nb - len(d2), rationale=rationale))\n    return d2\ndf = step(df, df.index >= LAG0, \"drop quarters before 1959Q4\", \"Not needed; 1959Q4 kept only as lag level for 1960Q1 differences\")\ndf = step(df, df.index <= END, \"drop quarters after 2019Q4\", \"Information rule: post-2019Q4 quarters outside the question\")\nassert (df[\"count\"] == 3).all() and df[\"mean\"].notna().all() and df[\"GDPC1\"].notna().all(), \"incomplete data in window\"\ndf = df.assign(u=df[\"mean\"], du=df[\"mean\"].diff(), g=100 * np.log(df[\"GDPC1\"]).diff())\ndf = step(df, df.index >= START, \"drop 1959Q4 (lag-only row)\", \"First differences undefined for the 1959Q4 row in-sample\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nassert len(df) == 240 and df[[\"du\", \"g\"]].notna().all().all()\n\ndef nw_lags(n):  # Newey-West (1994) rule of thumb\n    return int(np.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(d):\n    X = sm.add_constant(d[\"g\"].values)\n    L = nw_lags(len(d))\n    r = sm.OLS(d[\"du\"].values, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\n    return r, L\n\nfull, L = fit(df)\ns1, s2 = df[df.index < SPLIT], df[df.index >= SPLIT]\nr1, L1 = fit(s1); r2, L2 = fit(s2)\n\nn = len(df); k = 2\nssr_p, ssr_1, ssr_2 = full.ssr, r1.ssr, r2.ssr\nF = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\np = float(stats.f.sf(F, k, n - 2 * k))\n\nbeta, se = float(full.params[1]), float(full.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\nconcl = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nbaseline = float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2)))\nmodel = float(np.sqrt(np.mean(full.resid ** 2)))\n\ntab = pd.DataFrame([\n    dict(period=\"full 1960Q1-2019Q4\", n=n, intercept=full.params[0], slope=full.params[1], slope_se=full.bse[1]),\n    dict(period=\"sub1 1960Q1-1983Q4\", n=len(s1), intercept=r1.params[0], slope=r1.params[1], slope_se=r1.bse[1]),\n    dict(period=\"sub2 1984Q1-2019Q4\", n=len(s2), intercept=r2.params[0], slope=r2.params[1], slope_se=r2.bse[1]),\n])\ntab.to_csv(f\"{OUT}/table1.csv\", index=False, float_format=\"%.6f\")\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1.g, s1.du, s=14, alpha=.6, label=\"1960Q1-1983Q4\", color=\"tab:blue\")\nax.scatter(s2.g, s2.du, s=14, alpha=.6, label=\"1984Q1-2019Q4\", color=\"tab:orange\", marker=\"s\")\nfor d, r, c in [(s1, r1, \"tab:blue\"), (s2, r2, \"tab:orange\")]:\n    xs = np.linspace(d.g.min(), d.g.max(), 50)\n    ax.plot(xs, r.params[0] + r.params[1] * xs, color=c, lw=2, label=f\"fit: du = {r.params[0]:.3f} + {r.params[1]:.3f} g\")\nax.axhline(0, color=\"grey\", lw=.5); ax.axvline(0, color=\"grey\", lw=.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\"); ax.set_ylabel(\"Change in unemployment rate Δu_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1-2019Q4 (Chow F={F:.2f}, p={p:.3f})\"); ax.legend(fontsize=8)\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120); plt.close(fig)\n\nres = dict(\n    task_id=\"F6-conf-03\", feasibility=\"complete\", feasibility_reason=None, data_issues=data_issues,\n    n_input_rows=n_input_rows, n_analysed=int(full.nobs), random_seed=None,\n    sample_start=str(df.index[0].start_time.date()), sample_end=str(df.index[-1].start_time.date()),\n    n_sub1=int(len(s1)), n_sub2=int(len(s2)),\n    baseline_metric=baseline, model_metric=model,\n    effect_estimate=beta, intercept=float(full.params[0]), effect_se=se, hac_lags=int(L),\n    effect_ci_low=float(lo), effect_ci_high=float(hi),\n    beta_sub1=float(r1.params[1]), beta_sub2=float(r2.params[1]),\n    chow_f_stat=float(F), chow_p_value=p,\n    stability_conclusion=\"stable\" if p >= 0.05 else \"unstable\", conclusion=concl,\n    # supplementary (not required)\n    ols_se_beta_iid=float(sm.OLS(df.du.values, sm.add_constant(df.g.values)).fit().bse[1]),\n    hac_lags_sub1=int(L1), hac_lags_sub2=int(L2), r_squared=float(full.rsquared),\n    ssr_pooled=float(ssr_p), ssr_sub1=float(ssr_1), ssr_sub2=float(ssr_2),\n    intercept_sub1=float(r1.params[0]), intercept_sub2=float(r2.params[0]),\n    se_beta_sub1=float(r1.bse[1]), se_beta_sub2=float(r2.bse[1]),\n)\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n    json.dump(res, f, indent=2)\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\", \"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":2441,"cache_read_input_tokens":10795,"output_tokens":3318,"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":2441},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpNnj6q3Q51vTyEnknV","requestRef":"11d70e74-67d8-4644-85ee-2bd18d65c998","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fd1941a8-96e8-4fe8-bd17-41dd0bda65d2","timestamp":"2026-10-30T04:49:24.769Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"fd1941a8-96e8-4fe8-bd17-41dd0bda65d2","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017eqGfDihG3RYnrboo1pzok","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 1960Q1-2019Q4,240,0.184388,-0.255768,0.035985\nsub1 1960Q1-1983Q4,96,0.254233,-0.259021,0.039217\nsub2 1984Q1-2019Q4,144,0.151686,-0.273393,0.068794\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop quarters before 1959Q4,319,268,51,Not needed; 1959Q4 kept only as lag level for 1960Q1 differences\n2,drop quarters after 2019Q4,268,241,27,Information rule: post-2019Q4 quarters outside the question\n3,drop 1959Q4 (lag-only row),241,240,1,First differences undefined for the 1959Q4 row in-sample","is_error":false}]},"uuid":"04cc7be7-3bff-46c5-9e5e-52763b698670","timestamp":"2026-10-30T04:49:25.948Z","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 1960Q1-2019Q4,240,0.184388,-0.255768,0.035985\nsub1 1960Q1-1983Q4,96,0.254233,-0.259021,0.039217\nsub2 1984Q1-2019Q4,144,0.151686,-0.273393,0.068794\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop quarters before 1959Q4,319,268,51,Not needed; 1959Q4 kept only as lag level for 1960Q1 differences\n2,drop quarters after 2019Q4,268,241,27,Information rule: post-2019Q4 quarters outside the question\n3,drop 1959Q4 (lag-only row),241,240,1,First differences undefined for the 1959Q4 row in-sample","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fd1941a8-96e8-4fe8-bd17-41dd0bda65d2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}37{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"a3fa5f211d757d17e7c440c46409324ccdb4a7777c2b56b31a1e4552c007a221","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_017eqGfDihG3RYnrboo1pzok","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, US 1960Q1-2019Q4 (task F6-conf-03). Run from workspace root:\n   ~/wp29/venv/bin/python out/analysis.py\nReads data/ only; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\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\", parse_dates=[\"observation_date\"])\nun = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ndata_issues = []\nmiss = un[un[\"UNRATE\"].isna()]\nif len(miss):\n    data_issues.append({\"issue\": f\"UNRATE missing for {', '.join(miss.observation_date.dt.strftime('%Y-%m-%d'))}\",\n                        \"handling\": \"Outside the 1959Q4-2019Q4 window; removed by the 2019Q4 cutoff, no imputation needed.\"})\ndata_issues.append({\"issue\": \"Both files extend beyond 2019Q4 (to 2026), outside the question.\",\n                    \"handling\": \"All rows after 2019-12-31 dropped before any computation.\"})\n\n# --- quarterly unemployment: simple average of the 3 months; require complete quarters in window\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\nLAG0, START, END, SPLIT = pd.Period(\"1959Q4\"), pd.Period(\"1960Q1\"), pd.Period(\"2019Q4\"), pd.Period(\"1984Q1\")\nexcl = []\ndef step(d, mask, name, rationale):\n    nb = len(d); d2 = d[mask]\n    excl.append(dict(step=len(excl) + 1, rule=name, n_before=nb, n_after=len(d2), n_removed=nb - len(d2), rationale=rationale))\n    return d2\ndf = step(df, df.index >= LAG0, \"drop quarters before 1959Q4\", \"Not needed; 1959Q4 kept only as lag level for 1960Q1 differences\")\ndf = step(df, df.index <= END, \"drop quarters after 2019Q4\", \"Information rule: post-2019Q4 quarters outside the question\")\nassert (df[\"count\"] == 3).all() and df[\"mean\"].notna().all() and df[\"GDPC1\"].notna().all(), \"incomplete data in window\"\ndf = df.assign(u=df[\"mean\"], du=df[\"mean\"].diff(), g=100 * np.log(df[\"GDPC1\"]).diff())\ndf = step(df, df.index >= START, \"drop 1959Q4 (lag-only row)\", \"First differences undefined for the 1959Q4 row in-sample\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nassert len(df) == 240 and df[[\"du\", \"g\"]].notna().all().all()\n\ndef nw_lags(n):  # Newey-West (1994) rule of thumb\n    return int(np.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(d):\n    X = sm.add_constant(d[\"g\"].values)\n    L = nw_lags(len(d))\n    r = sm.OLS(d[\"du\"].values, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\n    return r, L\n\nfull, L = fit(df)\ns1, s2 = df[df.index < SPLIT], df[df.index >= SPLIT]\nr1, L1 = fit(s1); r2, L2 = fit(s2)\n\nn = len(df); k = 2\nssr_p, ssr_1, ssr_2 = full.ssr, r1.ssr, r2.ssr\nF = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\np = float(stats.f.sf(F, k, n - 2 * k))\n\nbeta, se = float(full.params[1]), float(full.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\nconcl = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nbaseline = float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2)))\nmodel = float(np.sqrt(np.mean(full.resid ** 2)))\n\ntab = pd.DataFrame([\n    dict(period=\"full 1960Q1-2019Q4\", n=n, intercept=full.params[0], slope=full.params[1], slope_se=full.bse[1]),\n    dict(period=\"sub1 1960Q1-1983Q4\", n=len(s1), intercept=r1.params[0], slope=r1.params[1], slope_se=r1.bse[1]),\n    dict(period=\"sub2 1984Q1-2019Q4\", n=len(s2), intercept=r2.params[0], slope=r2.params[1], slope_se=r2.bse[1]),\n])\ntab.to_csv(f\"{OUT}/table1.csv\", index=False, float_format=\"%.6f\")\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1.g, s1.du, s=14, alpha=.6, label=\"1960Q1-1983Q4\", color=\"tab:blue\")\nax.scatter(s2.g, s2.du, s=14, alpha=.6, label=\"1984Q1-2019Q4\", color=\"tab:orange\", marker=\"s\")\nfor d, r, c in [(s1, r1, \"tab:blue\"), (s2, r2, \"tab:orange\")]:\n    xs = np.linspace(d.g.min(), d.g.max(), 50)\n    ax.plot(xs, r.params[0] + r.params[1] * xs, color=c, lw=2, label=f\"fit: du = {r.params[0]:.3f} + {r.params[1]:.3f} g\")\nax.axhline(0, color=\"grey\", lw=.5); ax.axvline(0, color=\"grey\", lw=.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\"); ax.set_ylabel(\"Change in unemployment rate Δu_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1-2019Q4 (Chow F={F:.2f}, p={p:.3f})\"); ax.legend(fontsize=8)\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120); plt.close(fig)\n\nres = dict(\n    task_id=\"F6-conf-03\", feasibility=\"complete\", feasibility_reason=None, data_issues=data_issues,\n    n_input_rows=n_input_rows, n_analysed=int(full.nobs), random_seed=None,\n    sample_start=str(df.index[0].start_time.date()), sample_end=str(df.index[-1].start_time.date()),\n    n_sub1=int(len(s1)), n_sub2=int(len(s2)),\n    baseline_metric=baseline, model_metric=model,\n    effect_estimate=beta, intercept=float(full.params[0]), effect_se=se, hac_lags=int(L),\n    effect_ci_low=float(lo), effect_ci_high=float(hi),\n    beta_sub1=float(r1.params[1]), beta_sub2=float(r2.params[1]),\n    chow_f_stat=float(F), chow_p_value=p,\n    stability_conclusion=\"stable\" if p >= 0.05 else \"unstable\", conclusion=concl,\n    # supplementary (not required)\n    ols_se_beta_iid=float(sm.OLS(df.du.values, sm.add_constant(df.g.values)).fit().bse[1]),\n    hac_lags_sub1=int(L1), hac_lags_sub2=int(L2), r_squared=float(full.rsquared),\n    ssr_pooled=float(ssr_p), ssr_sub1=float(ssr_1), ssr_sub2=float(ssr_2),\n    intercept_sub1=float(r1.params[0]), intercept_sub2=float(r2.params[0]),\n    se_beta_sub1=float(r1.bse[1]), se_beta_sub2=float(r2.bse[1]),\n)\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n    json.dump(res, f, indent=2)\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\", \"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"}}]}}38{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"88a172af-381f-4b2e-bdd5-b179b42f09e2","timestamp":"2026-10-30T04:49:25.952Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"11d70e74-67d8-4644-85ee-2bd18d65c998","keep":10,"tail":["a3fa5f211d757d17e7c440c46409324ccdb4a7777c2b56b31a1e4552c007a221","b41374a6f333e31b092765b6465ecb33d2fdd578290f8f0d64d25797dfdac17a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7a22106c8a99118e9b2dc6eb16227b62bf24e445b0cf5f84707d2cbe041d388d"}39{"parentUuid":"04cc7be7-3bff-46c5-9e5e-52763b698670","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQpiUFBWzCmQmtvkAx","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":3800,"cache_read_input_tokens":13236,"output_tokens":942,"output_tokens_details":{"thinking_tokens":163},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3800},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1764,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpQpS6ssgHfPxWpYcux","requestRef":"88a172af-381f-4b2e-bdd5-b179b42f09e2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f2f584d3-99d5-4770-b1c3-809481526022","timestamp":"2026-10-30T04:49:29.384Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}40{"parentUuid":"f2f584d3-99d5-4770-b1c3-809481526022","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQpiUFBWzCmQmtvkAx","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HBEMAicsniF1fPmDZD2hb6","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace(\"beta, se = float(full.params[1])\",\"\"\"# supplementary robustness: HAC Wald test of break in (alpha, beta) and in beta alone\nD = (df.index >= SPLIT).astype(float)\nXb = np.column_stack([np.ones(n), df.g.values, D, D * df.g.values])\nrb = sm.OLS(df.du.values, Xb).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\nw_joint = rb.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), scalar=True, use_f=False)\nw_slope = rb.wald_test(np.array([[0, 0, 0, 1]]), scalar=True, use_f=False)\n\nbeta, se = float(full.params[1])\"\"\")\ns=s.replace(\"    se_beta_sub1=\",\"\"\"    hac_wald_break_joint_chi2=float(w_joint.statistic), hac_wald_break_joint_p=float(w_joint.pvalue),\n    hac_wald_break_slope_chi2=float(w_slope.statistic), hac_wald_break_slope_p=float(w_slope.pvalue),\n    sigma_resid_sub1=float(np.sqrt(ssr_1 / len(s1))), sigma_resid_sub2=float(np.sqrt(ssr_2 / len(s2))),\n    se_beta_sub1=\"\"\")\nopen('analysis.py','w').write(s)\nEOF\ncd .. && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r1.json && rm -f out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; cat out/results.json","description":"Add HAC break test, rerun twice, compare"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3800,"cache_read_input_tokens":13236,"output_tokens":942,"output_tokens_details":{"thinking_tokens":163},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3800},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpQpS6ssgHfPxWpYcux","requestRef":"88a172af-381f-4b2e-bdd5-b179b42f09e2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"48a4fc02-502c-48d4-a60d-713c3478f62b","timestamp":"2026-10-30T04:49:34.709Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"48a4fc02-502c-48d4-a60d-713c3478f62b","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HBEMAicsniF1fPmDZD2hb6","type":"tool_result","content":"IDENTICAL\n{\n  \"task_id\": \"F6-conf-03\",\n  \"feasibility\": \"complete\",\n  \"feasibility_reason\": null,\n  \"data_issues\": [\n    {\n      \"issue\": \"UNRATE missing for 2025-10-01\",\n      \"handling\": \"Outside the 1959Q4-2019Q4 window; removed by the 2019Q4 cutoff, no imputation needed.\"\n    },\n    {\n      \"issue\": \"Both files extend beyond 2019Q4 (to 2026), outside the question.\",\n      \"handling\": \"All rows after 2019-12-31 dropped before any computation.\"\n    }\n  ],\n  \"n_input_rows\": {\n    \"GDPC1.csv\": 319,\n    \"UNRATE.csv\": 945\n  },\n  \"n_analysed\": 240,\n  \"random_seed\": null,\n  \"sample_start\": \"1960-01-01\",\n  \"sample_end\": \"2019-10-01\",\n  \"n_sub1\": 96,\n  \"n_sub2\": 144,\n  \"baseline_metric\": 0.32465793964999184,\n  \"model_metric\": 0.2497438816636253,\n  \"effect_estimate\": -0.2557677277487258,\n  \"intercept\": 0.18438835418210714,\n  \"effect_se\": 0.03598488399675878,\n  \"hac_lags\": 4,\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  \"stability_conclusion\": \"unstable\",\n  \"conclusion\": \"negative_effect\",\n  \"ols_se_beta_iid\": 0.01996009291490984,\n  \"hac_lags_sub1\": 3,\n  \"hac_lags_sub2\": 4,\n  \"r_squared\": 0.4082508284562034,\n  \"ssr_pooled\": 14.96928154281957,\n  \"ssr_sub1\": 7.379293854646264,\n  \"ssr_sub2\": 6.855297827559747,\n  \"intercept_sub1\": 0.2542326539884382,\n  \"intercept_sub2\": 0.15168581347724602,\n  \"hac_wald_break_joint_chi2\": 10.744106556040112,\n  \"hac_wald_break_joint_p\": 0.004644584888844005,\n  \"hac_wald_break_slope_chi2\": 0.033475422396223316,\n  \"hac_wald_break_slope_p\": 0.8548271295127583,\n  \"sigma_resid_sub1\": 0.27725014755493266,\n  \"sigma_resid_sub2\": 0.21818853066467392,\n  \"se_beta_sub1\": 0.03921717107661775,\n  \"se_beta_sub2\": 0.06879369233083424\n}","is_error":false}]},"uuid":"23da19c6-d653-45c6-b33e-e4cf6b359220","timestamp":"2026-10-30T04:49:37.044Z","toolUseResult":{"stdout":"IDENTICAL\n{\n  \"task_id\": \"F6-conf-03\",\n  \"feasibility\": \"complete\",\n  \"feasibility_reason\": null,\n  \"data_issues\": [\n    {\n      \"issue\": \"UNRATE missing for 2025-10-01\",\n      \"handling\": \"Outside the 1959Q4-2019Q4 window; removed by the 2019Q4 cutoff, no imputation needed.\"\n    },\n    {\n      \"issue\": \"Both files extend beyond 2019Q4 (to 2026), outside the question.\",\n      \"handling\": \"All rows after 2019-12-31 dropped before any computation.\"\n    }\n  ],\n  \"n_input_rows\": {\n    \"GDPC1.csv\": 319,\n    \"UNRATE.csv\": 945\n  },\n  \"n_analysed\": 240,\n  \"random_seed\": null,\n  \"sample_start\": \"1960-01-01\",\n  \"sample_end\": \"2019-10-01\",\n  \"n_sub1\": 96,\n  \"n_sub2\": 144,\n  \"baseline_metric\": 0.32465793964999184,\n  \"model_metric\": 0.2497438816636253,\n  \"effect_estimate\": -0.2557677277487258,\n  \"intercept\": 0.18438835418210714,\n  \"effect_se\": 0.03598488399675878,\n  \"hac_lags\": 4,\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  \"stability_conclusion\": \"unstable\",\n  \"conclusion\": \"negative_effect\",\n  \"ols_se_beta_iid\": 0.01996009291490984,\n  \"hac_lags_sub1\": 3,\n  \"hac_lags_sub2\": 4,\n  \"r_squared\": 0.4082508284562034,\n  \"ssr_pooled\": 14.96928154281957,\n  \"ssr_sub1\": 7.379293854646264,\n  \"ssr_sub2\": 6.855297827559747,\n  \"intercept_sub1\": 0.2542326539884382,\n  \"intercept_sub2\": 0.15168581347724602,\n  \"hac_wald_break_joint_chi2\": 10.744106556040112,\n  \"hac_wald_break_joint_p\": 0.004644584888844005,\n  \"hac_wald_break_slope_chi2\": 0.033475422396223316,\n  \"hac_wald_break_slope_p\": 0.8548271295127583,\n  \"sigma_resid_sub1\": 0.27725014755493266,\n  \"sigma_resid_sub2\": 0.21818853066467392,\n  \"se_beta_sub1\": 0.03921717107661775,\n  \"se_beta_sub2\": 0.06879369233083424\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"48a4fc02-502c-48d4-a60d-713c3478f62b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"6a342887f4c523d7184e315ab156c3ade43302dd2cb141ad02d4421ab4482acd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQStAkKEAgTGAI4AUIIdGhpbmtpbmcSDGUYIcz5yUPDWe4YfBoMDkm+7SpL9Mt8OKWkIjAJO0snhejsLmWEx4PFefmI2tK8JDS27BMSvcC2wGjKeAyU7fzhxNyDwDFZthCKnikq0QiElhV3gaEumibsKN188OVlNZ5j29xR3KoXvFjFTk+YNuafw7Epab6FS+OLC4Z4ZypQf7mk0sQ0/olESAKbqnp1DxQ9eGgnPRPt5ESwt2ZIQT3tsi3mpnl4PP4n2BP37GnXCyvJyJB7vAHCwK8l6hSaeWUGvN50BJyqGmLCUDXn8KkU6JlGE/a0R4pUzvFO/KcEQ2Ur3Zd7PDs8zkai/Fqsx3v3wbbhwBD5yenxGugsB/DqZiKesmTD7Sw/iv3a1qBfbz9S8gXs91BklSsDohdEInA/KA6d/QtoQzXK+vN+HTzlWGnBWkLE+yRp2vsrKdKb1SCz+uPHjpDbwhax6nsp1Rcdhw99vFJ+FLQoPuIC8mofN/x9/RTqMvDslPwOfydKPYyHVAAtEtjcOtps54meDEa4cSgxeoCu3UMdPLKY0BsvYla/4jrU05cNm12fvjze+9h7/AM5FW8ueJdc/CY8GYQq1oW7Oq0wgXZ3z9Y43WQY9i/zln7A8QNPMGHmPOrHh0dtWk1CHvWOR5KokxfCVMx9aUvcD6qdjvhOXQMcFz1wmOboXUHBjUMJNZmk17f82Ld9QB3W//T4gO8FMAjzI1TdJfE+TQYTE8VpHsp5NUtm0YrXc/vs0/m/0l2sGz3q1QacVZaiEco7SmqOS8yi6m6vGaOIrEph1qXgotb88RBUvjDamTwrGZR0/eQIk5U02O5RpJc63m2rxdUXJplsjTQKztpvYi6JMTg8nGK/E9aGKA4ZeqLwGQIy9o/ccv/pQpyIgZVEkgw9nPcoWmaui1GQ+ND4lbZPgt5Fol1G4SaYm3zNg+YifcghipiWlvOWXoS79pl2UPrCkgNE+Y5pvIf0+MYbmL3obcueg0LyBSA7vxv7TsFk1E4rlVvTECvVVxSWGWtDD1cej6bq8iyFQib/oiMvF9nNvh1BD9rW4/WtH7P1AfdzyiE5i8LerBHoDpXYpEan2aZ9zKzNJ7CoYSEpPDiKOcTcK5Cjk6jTJUPTOMyYgeT45V8u88Mq6pq4RLREzIhQHF/FJl++2BIaw3+daKYjZubQLaA7GmnJelEzu/l0ecV64Wjt82bImtGACyIU3ZDlLQQg/qnmsz9xoZXSUBkctB37tTG9zTKdD2KRDHDVqSorAhLmNLCjMVUy9yulH0Ktqa6ntZOlKDmEgF9j3bDHE3ACo2I64yOMy2qi5d4xNtRYzNQq87xSi/VUCOnS0qt4DbDTakXfNqj2AhUrCOBRPmJ6jahsUg35+LbOHCsSKQ2u5qPNzpC12wFdP3KdWiuH3tJTfSwGMuletvfTaTsvgPUytsm1u4EDFw276nYDOFJV27c9ke5Ge+1mGnWSvMAyNmpNZYf9lRR9MwNcYRjcsYAtml1XKB72GT4vU6xnWNcrB5wlJs2/S4GkMtFRQ0+VRR3M4dWzBT1IL2rl2LK+rZEbMuz3kZuy6wGbpCHuvHXG/f3719ZUWbb7GAE="},{"type":"tool_use","id":"toolu_01HBEMAicsniF1fPmDZD2hb6","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace(\"beta, se = float(full.params[1])\",\"\"\"# supplementary robustness: HAC Wald test of break in (alpha, beta) and in beta alone\nD = (df.index >= SPLIT).astype(float)\nXb = np.column_stack([np.ones(n), df.g.values, D, D * df.g.values])\nrb = sm.OLS(df.du.values, Xb).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\nw_joint = rb.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), scalar=True, use_f=False)\nw_slope = rb.wald_test(np.array([[0, 0, 0, 1]]), scalar=True, use_f=False)\n\nbeta, se = float(full.params[1])\"\"\")\ns=s.replace(\"    se_beta_sub1=\",\"\"\"    hac_wald_break_joint_chi2=float(w_joint.statistic), hac_wald_break_joint_p=float(w_joint.pvalue),\n    hac_wald_break_slope_chi2=float(w_slope.statistic), hac_wald_break_slope_p=float(w_slope.pvalue),\n    sigma_resid_sub1=float(np.sqrt(ssr_1 / len(s1))), sigma_resid_sub2=float(np.sqrt(ssr_2 / len(s2))),\n    se_beta_sub1=\"\"\")\nopen('analysis.py','w').write(s)\nEOF\ncd .. && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r1.json && rm -f out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; cat out/results.json","description":"Add HAC break test, rerun twice, compare"}}]}}43{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"8d95d286-c2bf-4d9e-8dba-f48e5aa52bd2","timestamp":"2026-10-30T04:49:37.047Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"88a172af-381f-4b2e-bdd5-b179b42f09e2","keep":12,"tail":["6a342887f4c523d7184e315ab156c3ade43302dd2cb141ad02d4421ab4482acd","a1de771b4f7051ef7bf0c1e13f73e5cacee6b2e9dcb9fe05469743744c33c543"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"44773a742acb1cd2aa6a6c0ef81758bd2c6f6202b69047ad2e3dfdc4754419ae"}44{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"23da19c6-d653-45c6-b33e-e4cf6b359220","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}45{"type":"atis-latch","atis":"","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}46{"parentUuid":"23da19c6-d653-45c6-b33e-e4cf6b359220","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpReCELSbaiVnP1NnNi","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":1911,"cache_read_input_tokens":17036,"output_tokens":1472,"output_tokens_details":{"thinking_tokens":67},"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":1911},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":570,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpRdrtTZHnFKe2gzx9u","requestRef":"8d95d286-c2bf-4d9e-8dba-f48e5aa52bd2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3ae5c60d-5077-4f71-b992-3b6d52b4ecc9","timestamp":"2026-10-30T04:49:39.268Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}47{"parentUuid":"3ae5c60d-5077-4f71-b992-3b6d52b4ecc9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpReCELSbaiVnP1NnNi","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RGiXfh53ptQjzRVX6enFsK","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); e=pd.read_csv('out/exclusions.csv'); t=pd.read_csv('out/table1.csv')\nc=[]\ndef ck(name,ok): c.append(f\"- [{'PASS' if ok else 'FAIL'}] {name}\")\nck(\"n_sub1+n_sub2==n_analysed==240\", r['n_sub1']+r['n_sub2']==r['n_analysed']==240)\nck(\"n_sub1==96, n_sub2==144\", (r['n_sub1'],r['n_sub2'])==(96,144))\nck(\"exclusions: 319 - sum(removed) == 240\", 319-e.n_removed.sum()==r['n_analysed'])\nck(\"exclusions chained (n_after==next n_before; n_before-n_after==n_removed)\", all(e.n_after.iloc[:-1].values==e.n_before.iloc[1:].values) and all(e.n_before-e.n_after==e.n_removed))\nck(\"effect_se>0\", r['effect_se']>0)\nck(\"CI contains estimate and symmetric ±1.96 SE\", r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'] and abs((r['effect_ci_high']-r['effect_ci_low'])/2-1.959964*r['effect_se'])<1e-5)\nck(\"sample_start<sample_end, sample_end<=2019-10-01\", r['sample_start']<r['sample_end']<='2019-10-01')\nck(\"model_metric < baseline_metric\", r['model_metric']<r['baseline_metric'])\nck(\"R2 identity 1-(model/baseline)^2 == r_squared\", abs(1-(r['model_metric']/r['baseline_metric'])**2-r['r_squared'])<1e-10)\nck(\"ssr_pooled >= ssr_sub1+ssr_sub2\", r['ssr_pooled']>=r['ssr_sub1']+r['ssr_sub2'])\nF=((r['ssr_pooled']-r['ssr_sub1']-r['ssr_sub2'])/2)/((r['ssr_sub1']+r['ssr_sub2'])/236)\nck(\"Chow F recomputed from SSRs\", abs(F-r['chow_f_stat'])<1e-9)\nck(\"stability_conclusion consistent with p\", (r['chow_p_value']<0.05)==(r['stability_conclusion']=='unstable'))\nck(\"conclusion consistent with CI\", r['conclusion']=='negative_effect' and r['effect_ci_high']<0)\nck(\"table1 rows match results\", abs(t.slope[0]-r['effect_estimate'])<1e-6 and abs(t.slope[1]-r['beta_sub1'])<1e-6 and abs(t.slope[2]-r['beta_sub2'])<1e-6 and list(t.n)==[240,96,144])\nck(\"magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 for annualised/levels variants; q/q non-annualised ~ -0.25..-0.35)\", -0.6<r['effect_estimate']<-0.1)\nck(\"HAC SE >= iid SE (positive serial correlation expected)\", r['effect_se']>=r['ols_se_beta_iid'])\nopen('out/state/checks.md','w').write(\"# Verification checks (P4)\\n- [PASS] clean re-run: deleted results.json/table1.csv/figure1.png, re-ran analysis.py, results.json byte-identical (cmp)\\n\"+\"\\n\".join(c)+\"\\n\")\nprint(\"\\n\".join(c))\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -30","description":"Run consistency checks and gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1911,"cache_read_input_tokens":17036,"output_tokens":1472,"output_tokens_details":{"thinking_tokens":67},"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":1911},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpRdrtTZHnFKe2gzx9u","requestRef":"8d95d286-c2bf-4d9e-8dba-f48e5aa52bd2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1cf12be5-fadd-44fd-8f20-e5ac6a7c7bd0","timestamp":"2026-10-30T04:49:49.314Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"1cf12be5-fadd-44fd-8f20-e5ac6a7c7bd0","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01RGiXfh53ptQjzRVX6enFsK","type":"tool_result","content":"- [PASS] n_sub1+n_sub2==n_analysed==240\n- [PASS] n_sub1==96, n_sub2==144\n- [PASS] exclusions: 319 - sum(removed) == 240\n- [PASS] exclusions chained (n_after==next n_before; n_before-n_after==n_removed)\n- [PASS] effect_se>0\n- [PASS] CI contains estimate and symmetric ±1.96 SE\n- [PASS] sample_start<sample_end, sample_end<=2019-10-01\n- [PASS] model_metric < baseline_metric\n- [PASS] R2 identity 1-(model/baseline)^2 == r_squared\n- [PASS] ssr_pooled >= ssr_sub1+ssr_sub2\n- [PASS] Chow F recomputed from SSRs\n- [PASS] stability_conclusion consistent with p\n- [PASS] conclusion consistent with CI\n- [PASS] table1 rows match results\n- [PASS] magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 for annualised/levels variants; q/q non-annualised ~ -0.25..-0.35)\n- [PASS] HAC SE >= iid SE (positive serial correlation expected)\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: 3 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/RC0171/out/state/gate_receipts/20261030T044950.696427Z.json","is_error":false}]},"uuid":"c06c9375-5e91-4480-b332-c58bc3c23f97","timestamp":"2026-10-30T04:49:50.703Z","toolUseResult":{"stdout":"- [PASS] n_sub1+n_sub2==n_analysed==240\n- [PASS] n_sub1==96, n_sub2==144\n- [PASS] exclusions: 319 - sum(removed) == 240\n- [PASS] exclusions chained (n_after==next n_before; n_before-n_after==n_removed)\n- [PASS] effect_se>0\n- [PASS] CI contains estimate and symmetric ±1.96 SE\n- [PASS] sample_start<sample_end, sample_end<=2019-10-01\n- [PASS] model_metric < baseline_metric\n- [PASS] R2 identity 1-(model/baseline)^2 == r_squared\n- [PASS] ssr_pooled >= ssr_sub1+ssr_sub2\n- [PASS] Chow F recomputed from SSRs\n- [PASS] stability_conclusion consistent with p\n- [PASS] conclusion consistent with CI\n- [PASS] table1 rows match results\n- [PASS] magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 for annualised/levels variants; q/q non-annualised ~ -0.25..-0.35)\n- [PASS] HAC SE >= iid SE (positive serial correlation expected)\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: 3 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/RC0171/out/state/gate_receipts/20261030T044950.696427Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1cf12be5-fadd-44fd-8f20-e5ac6a7c7bd0","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}49{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"4799087d22aa1cb4962ba9688a76c25eae98f84af45270f799d6519d2125c25d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01RGiXfh53ptQjzRVX6enFsK","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); e=pd.read_csv('out/exclusions.csv'); t=pd.read_csv('out/table1.csv')\nc=[]\ndef ck(name,ok): c.append(f\"- [{'PASS' if ok else 'FAIL'}] {name}\")\nck(\"n_sub1+n_sub2==n_analysed==240\", r['n_sub1']+r['n_sub2']==r['n_analysed']==240)\nck(\"n_sub1==96, n_sub2==144\", (r['n_sub1'],r['n_sub2'])==(96,144))\nck(\"exclusions: 319 - sum(removed) == 240\", 319-e.n_removed.sum()==r['n_analysed'])\nck(\"exclusions chained (n_after==next n_before; n_before-n_after==n_removed)\", all(e.n_after.iloc[:-1].values==e.n_before.iloc[1:].values) and all(e.n_before-e.n_after==e.n_removed))\nck(\"effect_se>0\", r['effect_se']>0)\nck(\"CI contains estimate and symmetric ±1.96 SE\", r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'] and abs((r['effect_ci_high']-r['effect_ci_low'])/2-1.959964*r['effect_se'])<1e-5)\nck(\"sample_start<sample_end, sample_end<=2019-10-01\", r['sample_start']<r['sample_end']<='2019-10-01')\nck(\"model_metric < baseline_metric\", r['model_metric']<r['baseline_metric'])\nck(\"R2 identity 1-(model/baseline)^2 == r_squared\", abs(1-(r['model_metric']/r['baseline_metric'])**2-r['r_squared'])<1e-10)\nck(\"ssr_pooled >= ssr_sub1+ssr_sub2\", r['ssr_pooled']>=r['ssr_sub1']+r['ssr_sub2'])\nF=((r['ssr_pooled']-r['ssr_sub1']-r['ssr_sub2'])/2)/((r['ssr_sub1']+r['ssr_sub2'])/236)\nck(\"Chow F recomputed from SSRs\", abs(F-r['chow_f_stat'])<1e-9)\nck(\"stability_conclusion consistent with p\", (r['chow_p_value']<0.05)==(r['stability_conclusion']=='unstable'))\nck(\"conclusion consistent with CI\", r['conclusion']=='negative_effect' and r['effect_ci_high']<0)\nck(\"table1 rows match results\", abs(t.slope[0]-r['effect_estimate'])<1e-6 and abs(t.slope[1]-r['beta_sub1'])<1e-6 and abs(t.slope[2]-r['beta_sub2'])<1e-6 and list(t.n)==[240,96,144])\nck(\"magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 for annualised/levels variants; q/q non-annualised ~ -0.25..-0.35)\", -0.6<r['effect_estimate']<-0.1)\nck(\"HAC SE >= iid SE (positive serial correlation expected)\", r['effect_se']>=r['ols_se_beta_iid'])\nopen('out/state/checks.md','w').write(\"# Verification checks (P4)\\n- [PASS] clean re-run: deleted results.json/table1.csv/figure1.png, re-ran analysis.py, results.json byte-identical (cmp)\\n\"+\"\\n\".join(c)+\"\\n\")\nprint(\"\\n\".join(c))\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -30","description":"Run consistency checks and gate"}}]}}50{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"1d6bba05-5d2e-4ca2-bdcf-b93a48bc5999","timestamp":"2026-10-30T04:49:50.706Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"8d95d286-c2bf-4d9e-8dba-f48e5aa52bd2","keep":14,"tail":["4799087d22aa1cb4962ba9688a76c25eae98f84af45270f799d6519d2125c25d","e1ce5af81d2b17a02e4e180c1b6307174141b1ce42f3c80ac4e7da071e00b6f0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ecfe47a39f3190208094bd8df5b87eb83710e28008582d5acfd897b282dc2539"}51{"type":"tools-used","tools":["Bash","Read"],"sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}52{"parentUuid":"c06c9375-5e91-4480-b332-c58bc3c23f97","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSeXbubLtdf1FNthaF","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":2601,"cache_read_input_tokens":18947,"output_tokens":150,"output_tokens_details":{"thinking_tokens":69},"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":2601},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":469,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpSeFz53kxkFhCgy2HA","requestRef":"1d6bba05-5d2e-4ca2-bdcf-b93a48bc5999","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fcf2bd03-cbfe-4ec7-94d6-e0781524fb8e","timestamp":"2026-10-30T04:49:52.791Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"fcf2bd03-cbfe-4ec7-94d6-e0781524fb8e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSeXbubLtdf1FNthaF","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017tA2b6eyAhUzQkzibD15Zi","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0171/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":2601,"cache_read_input_tokens":18947,"output_tokens":150,"output_tokens_details":{"thinking_tokens":69},"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":2601},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSeFz53kxkFhCgy2HA","requestRef":"1d6bba05-5d2e-4ca2-bdcf-b93a48bc5999","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"95a35b25-1ecb-4402-b618-8577432de25a","timestamp":"2026-10-30T04:49:53.234Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"95a35b25-1ecb-4402-b618-8577432de25a","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017tA2b6eyAhUzQkzibD15Zi","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"d27a46ea-f0cb-4a92-ae49-93692071a885","timestamp":"2026-10-30T04:49:53.244Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":68931,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"95a35b25-1ecb-4402-b618-8577432de25a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}55{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"0f56d8a71ad44e5e876faf11baf6fd69716ae2cb858712f11b26d5745f6e651d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_017tA2b6eyAhUzQkzibD15Zi","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0171/out/figure1.png"}}]}}56{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"b86ba9a7-ff56-4b83-9d6a-45c1c5a554ad","timestamp":"2026-10-30T04:49:53.249Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"1d6bba05-5d2e-4ca2-bdcf-b93a48bc5999","keep":16,"tail":["0f56d8a71ad44e5e876faf11baf6fd69716ae2cb858712f11b26d5745f6e651d","6d4dd1200d84e9e4451cc95733f70df1b23e34254133425570fdd5e34f28f9c2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"142f26b6321f762799fb25769dbdc50cc0b9b8342cbf49f9c1309ffc97343123"}57{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d27a46ea-f0cb-4a92-ae49-93692071a885","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}58{"type":"atis-latch","atis":"","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}59{"parentUuid":"d27a46ea-f0cb-4a92-ae49-93692071a885","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSqRhPmfng2ENLm296","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":829,"cache_read_input_tokens":21548,"output_tokens":4318,"output_tokens_details":{"thinking_tokens":91},"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":829},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":671,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpSq9KNQVvzNMb7p7ir","requestRef":"b86ba9a7-ff56-4b83-9d6a-45c1c5a554ad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f48c317c-95fb-4f9e-baf2-903a18852152","timestamp":"2026-10-30T04:49:55.778Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}60{"parentUuid":"f48c317c-95fb-4f9e-baf2-903a18852152","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSqRhPmfng2ENLm296","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GtbeU4HUEVx1QLwbaLj7Pn","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960Q1–2019Q4 (F6-conf-03)\n\n## Question\nHow strongly do quarterly changes in the US unemployment rate respond to real output growth, and has that response been stable? Estimand: β in Δu_t = α + β·g_t + ε_t. Here Δu_t is the change in the quarterly-average UNRATE (pp) and g_t = 100·Δln GDPC1_t (% q/q, not annualised). The sample is 1960Q1–2019Q4. Stability is assessed with separate fits for 1960Q1–1983Q4 and 1984Q1–2019Q4 and a classical Chow test.\n\n## Data and exclusions\n- `data/GDPC1.csv` has 319 quarterly rows (1947Q1–2026Q3) and `data/UNRATE.csv` has 945 monthly rows (1948-01 – 2026-09) (`n_input_rows`). The SHA-256 hashes match the provenance README (see `out/state/data_audit.md`).\n- Data issues (`data_issues`): UNRATE has one missing value, at 2025-10-01. It lies outside the window and is removed by the 2019Q4 cutoff, so no imputation was needed. Both series extend past 2019Q4, and those rows are dropped before any computation (information rule).\n- Quarterly u_t is the simple mean of the 3 monthly values. A check confirms that every quarter in the window has all 3 months present.\n- Exclusion ledger (`out/exclusions.csv`), on the quarterly grid: 319 → drop the 51 quarters before 1959Q4 → 268 → drop the 27 quarters after 2019Q4 → 241 → drop 1959Q4, which serves only as the lag level → 240. The regression uses `n_analysed` = 240 quarters, from `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01. Subperiods have `n_sub1` = 96 and `n_sub2` = 144 quarters.\n\n## Method\n- Baseline: a mean-only prediction of Δu. Its RMSE is `baseline_metric`.\n- Main model: full-sample OLS of Δu_t on a constant and g_t. Inference uses Newey–West HAC standard errors (Bartlett kernel, small-sample correction). The lag length comes from the Newey–West rule of thumb floor(4·(n/100)^(2/9)), which gives `hac_lags` = 4 for n = 240. The 95% CI is β ± 1.96·`effect_se` (normal approximation). The `conclusion` code is set from the sign of this interval.\n- Stability: separate OLS fits on each subperiod (`beta_sub1`, `beta_sub2`). The classical Chow F-test uses F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n − 4)] with df (2, 236) (`chow_f_stat`, `chow_p_value`).\n- Supplementary diagnostic (not required): a HAC Wald test of the break, using a full-sample regression with a post-1984 dummy and a dummy×g interaction (same 4 lags). It is run both jointly and for the slope alone (`hac_wald_break_*`). This checks whether the Chow result survives heteroskedasticity and autocorrelation.\n- No randomness is involved (`random_seed` = null). `out/analysis.py` regenerates `results.json`, `table1.csv` and `figure1.png` deterministically.\n\n## Results\n- Okun coefficient (full sample): `effect_estimate` = −0.256 pp per 1% q/q growth, with `intercept` = 0.184 pp. So 1 pp of extra quarterly real growth goes with an unemployment rate about a quarter of a point lower that quarter. The model has `r_squared` = 0.41.\n- The model fits better than the baseline: residual RMSE `model_metric` = 0.250 pp versus mean-only RMSE `baseline_metric` = 0.325 pp.\n- Subperiod slopes are almost identical: `beta_sub1` = −0.259 and `beta_sub2` = −0.273. The intercepts differ: `intercept_sub1` = 0.254 and `intercept_sub2` = 0.152.\n- Chow test: `chow_f_stat` = 6.09, `chow_p_value` = 0.0026. Hence `stability_conclusion` = **unstable**: joint equality of (α, β) is rejected at 5%.\n- The rejection comes from the intercept, not the slope. The HAC Wald test of a joint break also rejects (`hac_wald_break_joint_p` = 0.0046). The HAC test of a slope-only break does not (`hac_wald_break_slope_p` = 0.85). In other words, the growth rate at which unemployment stays flat has fallen since 1984 (consistent with slower trend growth), while the Okun slope itself shows no detectable change.\n- Table 1 (`out/table1.csv`) lists n, intercept, slope and HAC slope SE for the full sample and each subperiod. Figure 1 (`out/figure1.png`) is a scatter of Δu against g with the two subperiod fitted lines.\n- `conclusion` = **negative_effect**: the 95% CI lies entirely below zero.\n\n## Uncertainty\n- The HAC SE is `effect_se` = 0.036, giving a 95% CI for β of [`effect_ci_low`, `effect_ci_high`] = [−0.326, −0.185].\n- The HAC SE is about 1.8 times the iid OLS SE (`ols_se_beta_iid` = 0.020), which points to serial correlation and/or heteroskedasticity in the residuals.\n- Subperiod HAC SEs: `se_beta_sub1` = 0.039 (3 lags) and `se_beta_sub2` = 0.069 (4 lags). The difference between the subperiod slopes (≈0.014) is far smaller than these SEs.\n- Residual dispersion differs across subperiods (`sigma_resid_sub1` = 0.277, `sigma_resid_sub2` = 0.218). The classical Chow test assumes equal error variance and no serial correlation, so its p-value is only approximate. The HAC Wald diagnostic reaches the same joint conclusion.\n- The results are sensitive to the HAC lag choice, but only one lag rule was reported. Alternative lags were not tabulated.\n\n## Limitations and open issues\n- **What would invalidate the result:** (i) If the break date is not 1984Q1. It is imposed by the task, and an endogenous break search (e.g. Quandt–Andrews) was not run. Testing at a date the data suggested would distort the size of the test. (ii) If g_t is endogenous: β is a reduced-form projection, not a causal effect. Unemployment and output are jointly determined, and measurement error in GDP growth biases |β| towards zero (attenuation). (iii) Nonlinearity or asymmetry: unemployment may rise faster in recessions than it falls in expansions. A linear model averages over this, and the large positive Δu outliers in recessions (Figure 1) have high leverage.\n- **Data vintage:** GDPC1 is the 2026 vintage, so revised GDP is used. Coefficients estimated on real-time data would differ. That does not matter for this ex post question, but it does matter for any forecasting use.\n- **Not checked:** sensitivity to the HAC lag length or to kernel/prewhitening choices; Andrews or fixed-b HAC inference; dynamic specifications (lags of g_t, the gap version of Okun's law); robustness to dropping recession quarters or outliers; trend breaks inside each subperiod (e.g. jobless recoveries after 1990, 2001 and 2009).\n- **Main threats:** The Chow test assumes homoskedastic, serially independent errors, and both assumptions look violated (see Uncertainty). The qualitative \"unstable\" verdict is backed by the HAC Wald test, but the exact p-value should not be over-interpreted. The \"unstable\" label refers to (α, β) jointly. Readers should not take it to mean that the Okun slope changed: the data do not support that.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4 the Okun coefficient is about -0.26 pp per 1% q/q real GDP growth, and its HAC 95% CI lies entirely below zero.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"hac_lags\",\"conclusion\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"Reduced-form association, not causal; HAC lag chosen by rule of thumb only.\"},\n {\"id\":\"C2\",\"text\":\"The OLS model improves on the mean-only baseline (residual RMSE 0.250 vs 0.325 pp).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"r_squared\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only.\"},\n {\"id\":\"C3\",\"text\":\"The classical Chow test rejects joint equality of (alpha, beta) across 1960Q1-1983Q4 and 1984Q1-2019Q4 at 5%, so the relation is classified unstable.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"n_sub1\",\"n_sub2\"],\"status\":\"supported\",\"caveat\":\"Classical Chow test assumes homoskedastic, uncorrelated errors; break date imposed.\"},\n {\"id\":\"C4\",\"text\":\"The instability comes from the intercept: subperiod slopes are nearly identical and a HAC test finds no slope break, while the HAC joint test still rejects.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"intercept_sub1\",\"intercept_sub2\",\"hac_wald_break_slope_p\",\"hac_wald_break_joint_p\"],\"status\":\"supported\",\"caveat\":\"Supplementary diagnostic beyond the required outputs; single lag choice.\"},\n {\"id\":\"C5\",\"text\":\"HAC standard errors are substantially larger than iid OLS standard errors.\",\"results_keys\":[\"effect_se\",\"ols_se_beta_iid\"],\"status\":\"supported\",\"caveat\":\"Ratio depends on lag length.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json,glob\np=json.load(open('out/state/phases.json'))\nrec=sorted(glob.glob('out/state/gate_receipts/*.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs matches README\",\"schema/dates/duplicates/gaps/NaN audited (data_audit.md)\",\"exclusions.csv: 319-78=240\"],\"notes\":\"one UNRATE NaN 2025-10 outside window\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) computed = 0.3247\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads data/ only, writes results.json/table1.csv/figure1.png; no RNG\"],\"notes\":\"HAC lags=4 by NW rule\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical (cmp)\",\"16 consistency checks all PASS (checks.md)\",f\"gate run at P4: receipt {rec[0]} - contract/repro checks ok; failures only for P5 artefacts not yet written (report sections, claims, phase terminal)\"],\"notes\":\"\"}\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md written with 6 sections citing result keys\",\"claims.json 5 claims referencing existing keys\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2-P4 passed (baseline, analysis, checks; gate run 1). P5 report + claims written. Decision: added HAC Wald break test as supplementary diagnostic.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Write report, claims, phases; 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":829,"cache_read_input_tokens":21548,"output_tokens":4318,"output_tokens_details":{"thinking_tokens":91},"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":829},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSq9KNQVvzNMb7p7ir","requestRef":"b86ba9a7-ff56-4b83-9d6a-45c1c5a554ad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"994cee6a-4c9e-49bf-bfe1-3e4af1cfc99e","timestamp":"2026-10-30T04:50:31.124Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"994cee6a-4c9e-49bf-bfe1-3e4af1cfc99e","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GtbeU4HUEVx1QLwbaLj7Pn","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0171/out/state/gate_receipts/20261030T045032.290807Z.json","is_error":false}]},"uuid":"5a820eec-980a-4fb4-b32a-f27382f2bfbf","timestamp":"2026-10-30T04:50:32.299Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0171/out/state/gate_receipts/20261030T045032.290807Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"994cee6a-4c9e-49bf-bfe1-3e4af1cfc99e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}62{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"3b0e98c64bda9ed4f8a7a3ffac42dcb4fdce57d72ac27e56317568be68f9b6e5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01GtbeU4HUEVx1QLwbaLj7Pn","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960Q1–2019Q4 (F6-conf-03)\n\n## Question\nHow strongly do quarterly changes in the US unemployment rate respond to real output growth, and has that response been stable? Estimand: β in Δu_t = α + β·g_t + ε_t. Here Δu_t is the change in the quarterly-average UNRATE (pp) and g_t = 100·Δln GDPC1_t (% q/q, not annualised). The sample is 1960Q1–2019Q4. Stability is assessed with separate fits for 1960Q1–1983Q4 and 1984Q1–2019Q4 and a classical Chow test.\n\n## Data and exclusions\n- `data/GDPC1.csv` has 319 quarterly rows (1947Q1–2026Q3) and `data/UNRATE.csv` has 945 monthly rows (1948-01 – 2026-09) (`n_input_rows`). The SHA-256 hashes match the provenance README (see `out/state/data_audit.md`).\n- Data issues (`data_issues`): UNRATE has one missing value, at 2025-10-01. It lies outside the window and is removed by the 2019Q4 cutoff, so no imputation was needed. Both series extend past 2019Q4, and those rows are dropped before any computation (information rule).\n- Quarterly u_t is the simple mean of the 3 monthly values. A check confirms that every quarter in the window has all 3 months present.\n- Exclusion ledger (`out/exclusions.csv`), on the quarterly grid: 319 → drop the 51 quarters before 1959Q4 → 268 → drop the 27 quarters after 2019Q4 → 241 → drop 1959Q4, which serves only as the lag level → 240. The regression uses `n_analysed` = 240 quarters, from `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01. Subperiods have `n_sub1` = 96 and `n_sub2` = 144 quarters.\n\n## Method\n- Baseline: a mean-only prediction of Δu. Its RMSE is `baseline_metric`.\n- Main model: full-sample OLS of Δu_t on a constant and g_t. Inference uses Newey–West HAC standard errors (Bartlett kernel, small-sample correction). The lag length comes from the Newey–West rule of thumb floor(4·(n/100)^(2/9)), which gives `hac_lags` = 4 for n = 240. The 95% CI is β ± 1.96·`effect_se` (normal approximation). The `conclusion` code is set from the sign of this interval.\n- Stability: separate OLS fits on each subperiod (`beta_sub1`, `beta_sub2`). The classical Chow F-test uses F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n − 4)] with df (2, 236) (`chow_f_stat`, `chow_p_value`).\n- Supplementary diagnostic (not required): a HAC Wald test of the break, using a full-sample regression with a post-1984 dummy and a dummy×g interaction (same 4 lags). It is run both jointly and for the slope alone (`hac_wald_break_*`). This checks whether the Chow result survives heteroskedasticity and autocorrelation.\n- No randomness is involved (`random_seed` = null). `out/analysis.py` regenerates `results.json`, `table1.csv` and `figure1.png` deterministically.\n\n## Results\n- Okun coefficient (full sample): `effect_estimate` = −0.256 pp per 1% q/q growth, with `intercept` = 0.184 pp. So 1 pp of extra quarterly real growth goes with an unemployment rate about a quarter of a point lower that quarter. The model has `r_squared` = 0.41.\n- The model fits better than the baseline: residual RMSE `model_metric` = 0.250 pp versus mean-only RMSE `baseline_metric` = 0.325 pp.\n- Subperiod slopes are almost identical: `beta_sub1` = −0.259 and `beta_sub2` = −0.273. The intercepts differ: `intercept_sub1` = 0.254 and `intercept_sub2` = 0.152.\n- Chow test: `chow_f_stat` = 6.09, `chow_p_value` = 0.0026. Hence `stability_conclusion` = **unstable**: joint equality of (α, β) is rejected at 5%.\n- The rejection comes from the intercept, not the slope. The HAC Wald test of a joint break also rejects (`hac_wald_break_joint_p` = 0.0046). The HAC test of a slope-only break does not (`hac_wald_break_slope_p` = 0.85). In other words, the growth rate at which unemployment stays flat has fallen since 1984 (consistent with slower trend growth), while the Okun slope itself shows no detectable change.\n- Table 1 (`out/table1.csv`) lists n, intercept, slope and HAC slope SE for the full sample and each subperiod. Figure 1 (`out/figure1.png`) is a scatter of Δu against g with the two subperiod fitted lines.\n- `conclusion` = **negative_effect**: the 95% CI lies entirely below zero.\n\n## Uncertainty\n- The HAC SE is `effect_se` = 0.036, giving a 95% CI for β of [`effect_ci_low`, `effect_ci_high`] = [−0.326, −0.185].\n- The HAC SE is about 1.8 times the iid OLS SE (`ols_se_beta_iid` = 0.020), which points to serial correlation and/or heteroskedasticity in the residuals.\n- Subperiod HAC SEs: `se_beta_sub1` = 0.039 (3 lags) and `se_beta_sub2` = 0.069 (4 lags). The difference between the subperiod slopes (≈0.014) is far smaller than these SEs.\n- Residual dispersion differs across subperiods (`sigma_resid_sub1` = 0.277, `sigma_resid_sub2` = 0.218). The classical Chow test assumes equal error variance and no serial correlation, so its p-value is only approximate. The HAC Wald diagnostic reaches the same joint conclusion.\n- The results are sensitive to the HAC lag choice, but only one lag rule was reported. Alternative lags were not tabulated.\n\n## Limitations and open issues\n- **What would invalidate the result:** (i) If the break date is not 1984Q1. It is imposed by the task, and an endogenous break search (e.g. Quandt–Andrews) was not run. Testing at a date the data suggested would distort the size of the test. (ii) If g_t is endogenous: β is a reduced-form projection, not a causal effect. Unemployment and output are jointly determined, and measurement error in GDP growth biases |β| towards zero (attenuation). (iii) Nonlinearity or asymmetry: unemployment may rise faster in recessions than it falls in expansions. A linear model averages over this, and the large positive Δu outliers in recessions (Figure 1) have high leverage.\n- **Data vintage:** GDPC1 is the 2026 vintage, so revised GDP is used. Coefficients estimated on real-time data would differ. That does not matter for this ex post question, but it does matter for any forecasting use.\n- **Not checked:** sensitivity to the HAC lag length or to kernel/prewhitening choices; Andrews or fixed-b HAC inference; dynamic specifications (lags of g_t, the gap version of Okun's law); robustness to dropping recession quarters or outliers; trend breaks inside each subperiod (e.g. jobless recoveries after 1990, 2001 and 2009).\n- **Main threats:** The Chow test assumes homoskedastic, serially independent errors, and both assumptions look violated (see Uncertainty). The qualitative \"unstable\" verdict is backed by the HAC Wald test, but the exact p-value should not be over-interpreted. The \"unstable\" label refers to (α, β) jointly. Readers should not take it to mean that the Okun slope changed: the data do not support that.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4 the Okun coefficient is about -0.26 pp per 1% q/q real GDP growth, and its HAC 95% CI lies entirely below zero.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"hac_lags\",\"conclusion\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"Reduced-form association, not causal; HAC lag chosen by rule of thumb only.\"},\n {\"id\":\"C2\",\"text\":\"The OLS model improves on the mean-only baseline (residual RMSE 0.250 vs 0.325 pp).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"r_squared\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only.\"},\n {\"id\":\"C3\",\"text\":\"The classical Chow test rejects joint equality of (alpha, beta) across 1960Q1-1983Q4 and 1984Q1-2019Q4 at 5%, so the relation is classified unstable.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"n_sub1\",\"n_sub2\"],\"status\":\"supported\",\"caveat\":\"Classical Chow test assumes homoskedastic, uncorrelated errors; break date imposed.\"},\n {\"id\":\"C4\",\"text\":\"The instability comes from the intercept: subperiod slopes are nearly identical and a HAC test finds no slope break, while the HAC joint test still rejects.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"intercept_sub1\",\"intercept_sub2\",\"hac_wald_break_slope_p\",\"hac_wald_break_joint_p\"],\"status\":\"supported\",\"caveat\":\"Supplementary diagnostic beyond the required outputs; single lag choice.\"},\n {\"id\":\"C5\",\"text\":\"HAC standard errors are substantially larger than iid OLS standard errors.\",\"results_keys\":[\"effect_se\",\"ols_se_beta_iid\"],\"status\":\"supported\",\"caveat\":\"Ratio depends on lag length.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json,glob\np=json.load(open('out/state/phases.json'))\nrec=sorted(glob.glob('out/state/gate_receipts/*.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs matches README\",\"schema/dates/duplicates/gaps/NaN audited (data_audit.md)\",\"exclusions.csv: 319-78=240\"],\"notes\":\"one UNRATE NaN 2025-10 outside window\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) computed = 0.3247\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads data/ only, writes results.json/table1.csv/figure1.png; no RNG\"],\"notes\":\"HAC lags=4 by NW rule\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical (cmp)\",\"16 consistency checks all PASS (checks.md)\",f\"gate run at P4: receipt {rec[0]} - contract/repro checks ok; failures only for P5 artefacts not yet written (report sections, claims, phase terminal)\"],\"notes\":\"\"}\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md written with 6 sections citing result keys\",\"claims.json 5 claims referencing existing keys\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2-P4 passed (baseline, analysis, checks; gate run 1). P5 report + claims written. Decision: added HAC Wald break test as supplementary diagnostic.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Write report, claims, phases; run final gate"}}]}}63{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"079dbec0-7121-47e2-99bd-9469de43f0fd","timestamp":"2026-10-30T04:50:32.303Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"b86ba9a7-ff56-4b83-9d6a-45c1c5a554ad","keep":18,"tail":["3b0e98c64bda9ed4f8a7a3ffac42dcb4fdce57d72ac27e56317568be68f9b6e5","f12475d2dffb04ef6a51c0814a7e9664da6285bf630473a240f7e35ae024272f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b631d72514d82d0d5a706d69f245fca767236e9a610237b42dac72ee95414cfe"}64{"parentUuid":"5a820eec-980a-4fb4-b32a-f27382f2bfbf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpViPMX95G4Pcgntob4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015eTQABGVuVCpupP2CTBNdE","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,glob\np=json.load(open('out/state/phases.json'))\nrec=sorted(glob.glob('out/state/gate_receipts/*.json'))[-1]\np['P5']['checks'].append(f\"final gate PASSED (0/48 failed): receipt {rec}\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate passed; all phases passed.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | head -1","description":"Record final receipt and reconfirm gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4413,"cache_read_input_tokens":22377,"output_tokens":307,"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":4413},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpVi7V3YHBdtcgJFNm6","requestRef":"079dbec0-7121-47e2-99bd-9469de43f0fd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ffd04fd2-de57-4fc3-a44c-60c2636dbe54","timestamp":"2026-10-30T04:50:35.876Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}65{"parentUuid":"ffd04fd2-de57-4fc3-a44c-60c2636dbe54","isSidechain":false,"promptId":"71c02f14-3686-4422-937d-c8005928e78c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015eTQABGVuVCpupP2CTBNdE","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)","is_error":false}]},"uuid":"2a9b50f5-8190-4051-9420-b59c13a17b96","timestamp":"2026-10-30T04:50:37.020Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ffd04fd2-de57-4fc3-a44c-60c2636dbe54","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}66{"type":"api-request-blob","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","hash":"e03799fa8a0ceb45f195dfcad3df91dbf0edad877623ee19a2c437f60a7e2626","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_015eTQABGVuVCpupP2CTBNdE","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,glob\np=json.load(open('out/state/phases.json'))\nrec=sorted(glob.glob('out/state/gate_receipts/*.json'))[-1]\np['P5']['checks'].append(f\"final gate PASSED (0/48 failed): receipt {rec}\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate passed; all phases passed.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | head -1","description":"Record final receipt and reconfirm gate"}}]}}67{"type":"api-request","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","id":"fef2c575-c6d5-45a3-8acb-36722294a17b","timestamp":"2026-10-30T04:50:37.024Z","version":"2.1.314","querySource":"sdk","shapeHash":"0492252ed9c1b0a9679e74450ebbe9b52a002933cff9b9b1d2571f23eb8a3c9b","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":"079dbec0-7121-47e2-99bd-9469de43f0fd","keep":20,"tail":["e03799fa8a0ceb45f195dfcad3df91dbf0edad877623ee19a2c437f60a7e2626","65535f31cc52867844b9b161e27095c77fed75481d1e5b06bc5e7bdcb7a299f9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c4b9d6da5f17dbb435a7429f2c12ae9e3696e74a181857e2b1d577e580ede5cf"}68{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2a9b50f5-8190-4051-9420-b59c13a17b96","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}69{"type":"atis-latch","atis":"","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}70{"parentUuid":"2a9b50f5-8190-4051-9420-b59c13a17b96","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpW4e2Cao7ByrjY9UfJ","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":347,"cache_read_input_tokens":26790,"output_tokens":1006,"output_tokens_details":{"thinking_tokens":21},"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":347},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6686,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpW4KAqpFNdvUMdyaCE","requestRef":"fef2c575-c6d5-45a3-8acb-36722294a17b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dde21603-4d55-45b0-837b-786ad7e0e879","timestamp":"2026-10-30T04:50:45.472Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}71{"parentUuid":"dde21603-4d55-45b0-837b-786ad7e0e879","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpW4e2Cao7ByrjY9UfJ","type":"message","role":"assistant","content":[{"type":"text","text":"Over 1960Q1–2019Q4, a 1% faster quarterly real GDP growth goes with an unemployment rate about 0.26 points lower that quarter. The Chow test rejects stability at the 1984 split, but that comes from the intercept: the slope itself barely changed. The final gate check passed (0 of 48 failed), and re-running `out/analysis.py` from scratch reproduces the results exactly.\n\n**Main results (240 quarters):**\n\n| Sample | Quarters | Slope (Okun coefficient) | Intercept |\n|---|---|---|---|\n| Full, 1960Q1–2019Q4 | 240 | −0.256 | 0.184 |\n| 1960Q1–1983Q4 | 96 | −0.259 | 0.254 |\n| 1984Q1–2019Q4 | 144 | −0.273 | 0.152 |\n\n- **Uncertainty:** the Newey–West standard error is 0.036, using 4 lags from the standard rule of thumb. The 95% interval is [−0.326, −0.185], entirely below zero, so the conclusion code is `negative_effect`.\n- **Fit:** the regression's error is 0.250 points, against 0.325 for the baseline that just predicts the average change.\n- **Stability:** the Chow test gives F = 6.09, p = 0.0026, so the relation is classified `unstable`.\n- **Where the break is:** I added an extra test, not required by the task, that allows for heteroskedasticity and serial correlation. It also rejects a joint break in intercept and slope (p = 0.005), but finds no break in the slope alone (p = 0.85). In plain terms, the growth rate at which unemployment holds steady has fallen since 1984, while the slope looks unchanged.\n\n**Limitations:**\n- **Break date:** 1984Q1 is fixed by the task; I didn't search for a break date from the data.\n- **Chow test assumptions:** it assumes equal error variance and no serial correlation, and both look violated here. Its exact p-value is therefore approximate, though the extra test agrees on the overall verdict.\n- **Not causal:** the coefficient is an association. Errors in measured GDP growth would tend to shrink its size.\n- **Data vintage:** the GDP data are the revised 2026 release, not what was known at the time.\n- **Not checked:** other lag lengths, other model specifications (such as lagged growth or nonlinear effects), and robustness to outliers.\n- **Data issue:** one unemployment value is missing (October 2025). It falls after the 2019 cutoff, so it has no effect.\n\nEverything is in `out/`; start with `report.md`, which has the full write-up and the failure discussion.\n- `analysis.py`\n- `results.json`\n- `figure1.png`\n- `table1.csv`\n- `report.md`\n- `claims.json`\n- `exclusions.csv`\n- `state/` (contract, data audit, checks, log, phase ledger, gate receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":347,"cache_read_input_tokens":26790,"output_tokens":1006,"output_tokens_details":{"thinking_tokens":21},"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":347},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpW4KAqpFNdvUMdyaCE","requestRef":"fef2c575-c6d5-45a3-8acb-36722294a17b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c597067b-8fc8-433e-81f3-5d47690f34f3","timestamp":"2026-10-30T04:50:47.194Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0171","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","version":"2.1.314","gitBranch":"HEAD"}72{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"c597067b-8fc8-433e-81f3-5d47690f34f3","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77"}73{"type":"cost-state","sessionId":"153bb266-579a-4255-aafb-3bcc6f9e1a77","totalCostUSD":0.4560894,"totalAPIDuration":135954,"totalAPIDurationWithoutRetries":135946,"totalToolDuration":7525,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":143656,"startTime":1793335703545,"modelUsage":{"claude-opus-5-5":{"inputTokens":24,"outputTokens":14858,"thinkingTokens":1105,"cacheReadInputTokens":153342,"cacheCreationInputTokens":25633,"cacheCreationEphemeral5mInputTokens":25633,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.4560894}},"hasUnknownModelCost":false}74