1{"type":"atis-latch","atis":"","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:51:24.398Z","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:51:24.403Z","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}4{"parentUuid":null,"isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":"Begin"},"uuid":"fb8acb7a-8e8f-424d-9989-973df8232f30","timestamp":"2026-10-30T04:51:24.407Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","timestamp":"2026-10-30T04:51:24.421Z","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/RC0177\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"de6ebaab-99c8-44ff-b30d-82457e9f787b","timestamp":"2026-10-30T04:51:24.421Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"ce6731c0dbeecc6f53d3ca2615e3891b90ffd459e21633510431af61338c7aa7"}8{"parentUuid":"fb8acb7a-8e8f-424d-9989-973df8232f30","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"bd03fb32-c25b-4653-b48d-15aff9cff387","timestamp":"2026-10-30T04:51:24.412Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"bd03fb32-c25b-4653-b48d-15aff9cff387","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"183e151b-57f8-47a7-87df-9430136121f5","timestamp":"2026-10-30T04:51:24.413Z","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/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"183e151b-57f8-47a7-87df-9430136121f5","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":"5d995575-ca43-4d01-9304-5de63945030c","timestamp":"2026-10-30T04:51:24.413Z","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/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}12{"parentUuid":"5d995575-ca43-4d01-9304-5de63945030c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZaH4CmcZpyf2CayDX","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":129,"output_tokens_details":{"thinking_tokens":19},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":442,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpZZwiKGnk3NtodjLUN","requestRef":"de6ebaab-99c8-44ff-b30d-82457e9f787b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9a4c49fd-e5a3-464b-b0a4-eb480d4e6b64","timestamp":"2026-10-30T04:51:26.069Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"9a4c49fd-e5a3-464b-b0a4-eb480d4e6b64","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZaH4CmcZpyf2CayDX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Fa912ZaV5rCVRX85EniuKK","name":"Bash","input":{"command":"cat TASK.md; ls -laR; ls out/state 2>/dev/null && cat out/state/*","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":129,"output_tokens_details":{"thinking_tokens":19},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpZZwiKGnk3NtodjLUN","requestRef":"de6ebaab-99c8-44ff-b30d-82457e9f787b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0adb85af-3e79-4b7f-827e-f50ee268b02a","timestamp":"2026-10-30T04:51:26.632Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"0adb85af-3e79-4b7f-827e-f50ee268b02a","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","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 107 simon-pierreboucher staff 3424 oct. 30 00:51 ..\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\n\n./data:\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_01Fa912ZaV5rCVRX85EniuKK"}]},"uuid":"04e620e6-f99b-4ac6-9caa-1a03382a8187","timestamp":"2026-10-30T04:51:26.740Z","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 107 simon-pierreboucher staff 3424 oct. 30 00:51 ..\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\n\n./data:\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":"0adb85af-3e79-4b7f-827e-f50ee268b02a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"e2981e7a27c90521e8bef09951eb897a5a0cc08d762d480f61b80dfbf37c45f8","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Fa912ZaV5rCVRX85EniuKK","name":"Bash","input":{"command":"cat TASK.md; ls -laR; ls out/state 2>/dev/null && cat out/state/*","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"f4a1b007-be6d-4d96-9350-8593d3de55f6","timestamp":"2026-10-30T04:51:26.744Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"de6ebaab-99c8-44ff-b30d-82457e9f787b","keep":2,"tail":["e2981e7a27c90521e8bef09951eb897a5a0cc08d762d480f61b80dfbf37c45f8","16ed008e976e80144b3dba19ae511e8622ae53b6b937e3e1addd7195fb587d07"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ff61faf87c135ee664b27fcd0040deec3738b7fc93e39feb6d849064aa5b391a"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"04e620e6-f99b-4ac6-9caa-1a03382a8187","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}18{"type":"atis-latch","atis":"","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}19{"parentUuid":"04e620e6-f99b-4ac6-9caa-1a03382a8187","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZiMF2yDqrbd3yB98H","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0173stFHFRs3cL7ceQp7F2Kc","name":"Bash","input":{"command":"cat data/README.md; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*; cat bundle.json","description":"Inspect 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":3073,"cache_read_input_tokens":3713,"output_tokens":133,"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":3073},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpZi4sJWTufXQRULA34","requestRef":"f4a1b007-be6d-4d96-9350-8593d3de55f6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8d915c21-4551-4654-bd30-7334cfcaa979","timestamp":"2026-10-30T04:51:28.383Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"8d915c21-4551-4654-bd30-7334cfcaa979","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0173stFHFRs3cL7ceQp7F2Kc","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==> 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\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}","is_error":false}]},"uuid":"ca555ae7-52fa-4ecd-987f-4428887bacc3","timestamp":"2026-10-30T04:51:28.451Z","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==> 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\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}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8d915c21-4551-4654-bd30-7334cfcaa979","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"751138578c28fc56245eca0c92f8eaca1b880341b56f71f226565aef41db77c4","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_0173stFHFRs3cL7ceQp7F2Kc","name":"Bash","input":{"command":"cat data/README.md; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*; cat bundle.json","description":"Inspect data files"}}]}}22{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"04218679-fc70-4285-8a80-6b3b1db40a01","timestamp":"2026-10-30T04:51:28.454Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"f4a1b007-be6d-4d96-9350-8593d3de55f6","keep":4,"tail":["751138578c28fc56245eca0c92f8eaca1b880341b56f71f226565aef41db77c4","a3a71a3523bb9491f36b867511bfdb366c8c3afcbb6326a9b0503ef7d142e198"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8ecc8f95faefa904f167b99c0084c0523bb214a8178d1e4653a4e8cbe57c3e24"}23{"parentUuid":"ca555ae7-52fa-4ecd-987f-4428887bacc3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZqa4VjSv6EfaQcLCe","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":1472,"cache_read_input_tokens":6786,"output_tokens":569,"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":1472},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":391,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpZqHwbW1aj3csUEgP4","requestRef":"04218679-fc70-4285-8a80-6b3b1db40a01","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"701805d8-112a-4864-863e-12b71b9b5d26","timestamp":"2026-10-30T04:51:29.911Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"701805d8-112a-4864-863e-12b71b9b5d26","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZqa4VjSv6EfaQcLCe","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MUZJV5HMuJ8owLjfgX8hQh","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'); t=pd.to_datetime(d.observation_date,errors='coerce')\n print(' nonnumeric:',d[v.isna()].to_string()[:500])\n print(' baddate',t.isna().sum(),'dupdates',t.duplicated().sum(),'monotonic',t.is_monotonic_increasing)\n fr='QS' if f=='GDPC1' else 'MS'\n full=pd.date_range(t.min(),t.max(),freq=fr); print(' missing periods',len(full.difference(t)), list(full.difference(t))[:10])\n print(' min/max',v.min(),v.max())\n if f=='UNRATE': print(d[(t>='2019-07-01')&(t<'2021-01-01')].T.to_string()); print(' 1959Q4..', d[(t>='1959-10-01')&(t<'1960-04-01')].to_string())\n\"","description":"Audit data for anomalies"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1472,"cache_read_input_tokens":6786,"output_tokens":569,"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":1472},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpZqHwbW1aj3csUEgP4","requestRef":"04218679-fc70-4285-8a80-6b3b1db40a01","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fb5bbec4-df56-4f3d-bb1e-a0c69a86d3c0","timestamp":"2026-10-30T04:51:33.785Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"fb5bbec4-df56-4f3d-bb1e-a0c69a86d3c0","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MUZJV5HMuJ8owLjfgX8hQh","type":"tool_result","content":"GDPC1 (319, 2) ['observation_date', 'GDPC1']\n nonnumeric: Empty DataFrame\nColumns: [observation_date, GDPC1]\nIndex: []\n baddate 0 dupdates 0 monotonic True\n missing periods 0 []\n min/max 2172.432 24611.077\nUNRATE (945, 2) ['observation_date', 'UNRATE']\n nonnumeric: observation_date UNRATE\n933 2025-10-01 NaN\n baddate 0 dupdates 0 monotonic True\n missing periods 0 []\n min/max 2.5 14.8\n 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875\nobservation_date 2019-07-01 2019-08-01 2019-09-01 2019-10-01 2019-11-01 2019-12-01 2020-01-01 2020-02-01 2020-03-01 2020-04-01 2020-05-01 2020-06-01 2020-07-01 2020-08-01 2020-09-01 2020-10-01 2020-11-01 2020-12-01\nUNRATE 3.7 3.6 3.5 3.6 3.6 3.6 3.6 3.5 4.4 14.8 13.2 11.0 10.2 8.4 7.8 6.9 6.7 6.7\n 1959Q4.. observation_date UNRATE\n141 1959-10-01 5.7\n142 1959-11-01 5.8\n143 1959-12-01 5.3\n144 1960-01-01 5.2\n145 1960-02-01 4.8\n146 1960-03-01 5.4","is_error":false}]},"uuid":"39d9cc53-2774-450b-9dec-02a6486fcf86","timestamp":"2026-10-30T04:51:34.080Z","toolUseResult":{"stdout":"GDPC1 (319, 2) ['observation_date', 'GDPC1']\n nonnumeric: Empty DataFrame\nColumns: [observation_date, GDPC1]\nIndex: []\n baddate 0 dupdates 0 monotonic True\n missing periods 0 []\n min/max 2172.432 24611.077\nUNRATE (945, 2) ['observation_date', 'UNRATE']\n nonnumeric: observation_date UNRATE\n933 2025-10-01 NaN\n baddate 0 dupdates 0 monotonic True\n missing periods 0 []\n min/max 2.5 14.8\n 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875\nobservation_date 2019-07-01 2019-08-01 2019-09-01 2019-10-01 2019-11-01 2019-12-01 2020-01-01 2020-02-01 2020-03-01 2020-04-01 2020-05-01 2020-06-01 2020-07-01 2020-08-01 2020-09-01 2020-10-01 2020-11-01 2020-12-01\nUNRATE 3.7 3.6 3.5 3.6 3.6 3.6 3.6 3.5 4.4 14.8 13.2 11.0 10.2 8.4 7.8 6.9 6.7 6.7\n 1959Q4.. observation_date UNRATE\n141 1959-10-01 5.7\n142 1959-11-01 5.8\n143 1959-12-01 5.3\n144 1960-01-01 5.2\n145 1960-02-01 4.8\n146 1960-03-01 5.4","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fb5bbec4-df56-4f3d-bb1e-a0c69a86d3c0","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"0f182277662c1f75a70b51562337d77f4b250438f01001f03001ac02e5e6ce33","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01MUZJV5HMuJ8owLjfgX8hQh","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'); t=pd.to_datetime(d.observation_date,errors='coerce')\n print(' nonnumeric:',d[v.isna()].to_string()[:500])\n print(' baddate',t.isna().sum(),'dupdates',t.duplicated().sum(),'monotonic',t.is_monotonic_increasing)\n fr='QS' if f=='GDPC1' else 'MS'\n full=pd.date_range(t.min(),t.max(),freq=fr); print(' missing periods',len(full.difference(t)), list(full.difference(t))[:10])\n print(' min/max',v.min(),v.max())\n if f=='UNRATE': print(d[(t>='2019-07-01')&(t<'2021-01-01')].T.to_string()); print(' 1959Q4..', d[(t>='1959-10-01')&(t<'1960-04-01')].to_string())\n\"","description":"Audit data for anomalies"}}]}}27{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"691e6b37-1e3f-48d2-b5de-7e97c4ad8597","timestamp":"2026-10-30T04:51:34.083Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"04218679-fc70-4285-8a80-6b3b1db40a01","keep":6,"tail":["0f182277662c1f75a70b51562337d77f4b250438f01001f03001ac02e5e6ce33","39fca3710dbb66a8cfc3b780e3436f3e4c7c72405cac70db0edfb870d5c2cc29"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5adfe0ec8d4561b50998f4ec48ff014c9f2d49464f3f378100a056b2f1d9c59e"}28{"parentUuid":"39d9cc53-2774-450b-9dec-02a6486fcf86","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpaFeRFC59RdryDossG","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS6QgKEAgTGAI4AUIIdGhpbmtpbmcSDCrAzxkj4MNO+u3/XhoMnvw7kc0m1nTP+o1SIjDITCGH9XBxnw0jpVxr8cRty15v/1dnNWo8Ys1R3UED6V9IMdos3QRTonEBjqqqRQgqhghHjSaEcVfGZHL0GsR2il9MGjBak58RhN6rKzievwCE8+Ogj0O60aTix88mxWAeq5J9mIkQkIT7Ti61HuiFKRJh70ZukOVN3KPTdH4M4oJ/yxRUia7XpTnxhUwYzI2c/J2OI0oSMQl3smQ6YnBnfpSihiFIQKww2FOCvyUNnSQcYtgY1l2pJVN0nS/+K5kWJ9CNFmHItLw9yuHFX1WJNhGd8R7uvuRA9dN6+YvJEVDwc1T+1T5Qv30CZGFl39DI87IIjL+HwrJI0yD5tmJNZ76j/TZkziDvQIMF6/Z6HWJi6GcgB2AdTohAlTzBmLEwomAPcPhKEN3sO180/3SzsVz/KjPrhvPuabnpbYzT3cV39lMXL+LhPlvOi4yXywwLp8naMpNKsxi/n0LY0s4MzNelU3k7zhjOF5k4kyJi/7Ia29/SLLKvM748cu+OyenuLBeN/hop0SIsm517WlDLTMB4i8UmIv1PQ7fW52M+RKnLMF8PcKWKrouDd45KIxzoAvf7oqybJSaOyaeJTPrhLTdtpR/nlAHpIvpmv/Q5aVfQXj5j4AsOCHNATLYRgyjHyPIc6vTJgZInyTCtG9zCxA+VR8xmadg6Y2Ul9M4+NJNRweravKq3U7je738sUJR8tsTaP3OzK8B9n7XZujdFqTVAFdmvxA1P6mHYABJ+8K3ZrkjAeSbIViIfm5xrolmSnuZeydL/GKUYqo6m+WULvuAGwlHC4KbxyPlWXOBEaLDkVTXmJw88XalKj8l3DiQSgEGflUdG5VcWfeYq6GVsntA3eBoel+1bxwfgxBemxi9FeSzThKmUbEDfuJgqebdjyVbqVAe/v/JcsEXjIYvjQ/UQ16Rd4CeKWdphCfv1gnURD2dagP6ISBpEUCYjxDPuNwMc5XlUimuG2/C9py55igrL4k/Mgqnbldv23iPSpevINnE1utBBssGp7X2rzIA7ymy1fbFvP4o9whRZXO93FUpkoRgL+Niyqp7lmszpvTEgWjD3JsBgxHbo8ctfoMdRvZ3zger85l4UwSerSnBiBCtLYN7VmV5I7yV5UHVq7eirGhOPwE28arPV9ZjWMYD7VXdlVpfdbJhKblnVmixe2Qv9OlMIemRYpRsd0JMbSZetJcykMHrPRfOd+dPXAJyDsgXoHD1yT+bAbGLAHahxVfU5i1DW7B35tGAFWg0kazieQCWE5t0mzQ4iZ6LP2Z9QvdwINWo9op0Ny+AFnvm8jfzkgmw4rhMp8mfeWqwlPyusoNOKi2vp3MyXUIM2SsaEPdaGfRGoBIpHvDZ4Vb2LfkaeynhrNhheLMB10I6PCunQThu95CQ3oKHxqXNkCTNw0uCQLWdV0364ti+X0hyrWICetADj4VI0GAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1131,"cache_read_input_tokens":8258,"output_tokens":1291,"output_tokens_details":{"thinking_tokens":193},"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":1131},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1851,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpaFNJ3s8YZct5ku2Fu","requestRef":"691e6b37-1e3f-48d2-b5de-7e97c4ad8597","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e2722a39-87fd-4ec1-974e-23cfaba32a6d","timestamp":"2026-10-30T04:51:37.029Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"e2722a39-87fd-4ec1-974e-23cfaba32a6d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpaFeRFC59RdryDossG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01AY7ATUvW8iqgm6YgERiQM5","name":"Bash","input":{"command":"cd out/state; cat > contract.md <<'EOF'\n# Contract — F6-conf-03\n**Question:** How strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth (Okun's law, difference form), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?\n\n**Estimand:** β in Δu_t = α + β g_t + ε_t, Δu_t = change in quarterly-average UNRATE (pp), g_t = 100·Δln GDPC1 (% q/q, not annualised). OLS β is a meaningful linear-projection coefficient under stationarity of (Δu, g); it is a reduced-form association, not a structural causal effect. Inference: Newey–West HAC (Bartlett), lag reported; 95% CI from HAC SE (normal critical value). Stability: subperiod OLS slopes + classical Chow SSR F-test of (α,β) equality, F(2, n−4).\n\n**Outputs:** out/results.json (keys: sample_start, sample_end, n_sub1, n_sub2, baseline_metric, model_metric, effect_estimate, intercept, effect_se, hac_lags, effect_ci_low, effect_ci_high, beta_sub1, beta_sub2, chow_f_stat, chow_p_value, stability_conclusion, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (period,n,intercept,slope,slope_se; 3 rows); out/report.md (6 sections); out/analysis.py; out/claims.json.\n\n**Information rules:** u_t = mean of 3 monthly values; sample = 240 quarters 1960Q1–2019Q4 (1959Q4 levels used only for the first difference); nothing after 2019Q4 in any estimate; only data/GDPC1.csv, data/UNRATE.csv, data/README.md (gate_spec.json/bundle.json are not inputs and are not read, apart from bundle.json hashes not being used either).\n\n**Invalidity/impossibility:** missing monthly or quarterly values inside 1959Q4–2019Q4; sample count ≠ 240; post-2019 data entering estimates; non-HAC SEs for full-sample β.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written. P1 started.\" > log.md","description":"Write contract, phase ledger, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1131,"cache_read_input_tokens":8258,"output_tokens":1291,"output_tokens_details":{"thinking_tokens":193},"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":1131},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpaFNJ3s8YZct5ku2Fu","requestRef":"691e6b37-1e3f-48d2-b5de-7e97c4ad8597","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"daac21a8-6909-410b-bb32-4ea5bdff389e","timestamp":"2026-10-30T04:51:45.878Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"daac21a8-6909-410b-bb32-4ea5bdff389e","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01AY7ATUvW8iqgm6YgERiQM5","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"d99fc916-7e7c-4070-8443-a6a10fa7e61e","timestamp":"2026-10-30T04:51:45.930Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"daac21a8-6909-410b-bb32-4ea5bdff389e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"512df38c7cddc04f862e75276a84610de16ee187195ad6482bbe5344eb57c35f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01AY7ATUvW8iqgm6YgERiQM5","name":"Bash","input":{"command":"cd out/state; cat > contract.md <<'EOF'\n# Contract — F6-conf-03\n**Question:** How strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth (Okun's law, difference form), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?\n\n**Estimand:** β in Δu_t = α + β g_t + ε_t, Δu_t = change in quarterly-average UNRATE (pp), g_t = 100·Δln GDPC1 (% q/q, not annualised). OLS β is a meaningful linear-projection coefficient under stationarity of (Δu, g); it is a reduced-form association, not a structural causal effect. Inference: Newey–West HAC (Bartlett), lag reported; 95% CI from HAC SE (normal critical value). Stability: subperiod OLS slopes + classical Chow SSR F-test of (α,β) equality, F(2, n−4).\n\n**Outputs:** out/results.json (keys: sample_start, sample_end, n_sub1, n_sub2, baseline_metric, model_metric, effect_estimate, intercept, effect_se, hac_lags, effect_ci_low, effect_ci_high, beta_sub1, beta_sub2, chow_f_stat, chow_p_value, stability_conclusion, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (period,n,intercept,slope,slope_se; 3 rows); out/report.md (6 sections); out/analysis.py; out/claims.json.\n\n**Information rules:** u_t = mean of 3 monthly values; sample = 240 quarters 1960Q1–2019Q4 (1959Q4 levels used only for the first difference); nothing after 2019Q4 in any estimate; only data/GDPC1.csv, data/UNRATE.csv, data/README.md (gate_spec.json/bundle.json are not inputs and are not read, apart from bundle.json hashes not being used either).\n\n**Invalidity/impossibility:** missing monthly or quarterly values inside 1959Q4–2019Q4; sample count ≠ 240; post-2019 data entering estimates; non-HAC SEs for full-sample β.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written. P1 started.\" > log.md","description":"Write contract, phase ledger, log"}}]}}32{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"421b52c0-9dd9-4ecd-a7a4-202e3ed946b4","timestamp":"2026-10-30T04:51:45.934Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"691e6b37-1e3f-48d2-b5de-7e97c4ad8597","keep":8,"tail":["512df38c7cddc04f862e75276a84610de16ee187195ad6482bbe5344eb57c35f","b2e0cbe430fcf817a466f6046e0bad9b553d46cba4a994f72e1bae05d6dd98df"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ac4a6b1e970411f40549174df6119c2baf3ea5fe6bc64a813cb0e3643a1756f0"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d99fc916-7e7c-4070-8443-a6a10fa7e61e","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}34{"type":"atis-latch","atis":"","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}35{"parentUuid":"d99fc916-7e7c-4070-8443-a6a10fa7e61e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpb8MeHPHqUKNRNoGLC","type":"message","role":"assistant","content":[{"type":"text","text":"Now the analysis script (it also writes the exclusion ledger)."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1306,"cache_read_input_tokens":9389,"output_tokens":3890,"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":1306},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpb83ndmYACTbjJ6c3v","requestRef":"421b52c0-9dd9-4ecd-a7a4-202e3ed946b4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"58123d22-b5a5-439b-9d36-ba7ead3c1d5f","timestamp":"2026-10-30T04:51:46.934Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"58123d22-b5a5-439b-9d36-ba7ead3c1d5f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpb8MeHPHqUKNRNoGLC","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01N4579QeHgx2A8fjeNkfUZ5","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"F6-conf-03 Okun's law replication. 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\"; os.makedirs(OUT, exist_ok=True)\nSEED = None # no randomness used\nSTART, END = pd.Timestamp(\"1960-01-01\"), pd.Timestamp(\"2019-10-01\")\nSPLIT = pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\")\nun = pd.read_csv(\"data/UNRATE.csv\")\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"date\"] = pd.to_datetime(gdp[\"observation_date\"]); un[\"date\"] = pd.to_datetime(un[\"observation_date\"])\ngdp[\"GDPC1\"] = pd.to_numeric(gdp[\"GDPC1\"], errors=\"coerce\")\nun[\"UNRATE\"] = pd.to_numeric(un[\"UNRATE\"], errors=\"coerce\")\n\ndata_issues = []\nmiss_un = un.loc[un[\"UNRATE\"].isna(), \"observation_date\"].tolist()\nif miss_un:\n data_issues.append({\"issue\": f\"UNRATE missing (non-numeric '.') for month(s) {miss_un}\",\n \"handling\": \"Outside 1959Q4-2019Q4 window; affected quarter dropped by the window restriction, no imputation.\"})\nmiss_g = gdp.loc[gdp[\"GDPC1\"].isna(), \"observation_date\"].tolist()\nif miss_g:\n data_issues.append({\"issue\": f\"GDPC1 missing for {miss_g}\", \"handling\": \"dropped if outside window; fatal if inside\"})\ndata_issues.append({\"issue\": \"Files extend beyond 2019Q4 (GDPC1 to 2026Q3, UNRATE to 2026-09), including COVID-19 quarters\",\n \"handling\": \"Excluded by the information rule: no quarter after 2019Q4 enters any estimate.\"})\ndata_issues.append({\"issue\": \"GDPC1 is the current (2026) vintage, revised data, not real-time\",\n \"handling\": \"Used as provided; noted as limitation (estimates reflect revised GDP).\"})\n\n# Quarterly unemployment: mean of 3 months, require complete quarter\nun[\"q\"] = un[\"date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nuq.loc[uq[\"count\"] < 3, \"mean\"] = np.nan # incomplete quarter -> missing\ng = gdp.set_index(gdp[\"date\"].dt.to_period(\"Q\"))[\"GDPC1\"]\ndf = pd.DataFrame({\"u\": uq[\"mean\"], \"y\": g}).sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"y\"]).diff()\ndf[\"date\"] = df.index.to_timestamp()\n\nexcl = []\nn0 = len(df)\nstep1 = df[(df[\"date\"] >= START) & (df[\"date\"] <= END)]\nexcl.append([\"1\", \"keep quarters 1960Q1-2019Q4 (union of GDPC1/UNRATE quarterly index)\", n0, len(step1), n0 - len(step1),\n \"information rule: regression sample; pre-1960 used only as lag for 1960Q1 difference; post-2019 excluded\"])\nstep2 = step1.dropna(subset=[\"du\", \"g\"])\nexcl.append([\"2\", \"drop quarters with missing du or g\", len(step1), len(step2), len(step1) - len(step2),\n \"no missing values expected inside the window\"])\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nd = step2.copy()\nassert len(d) == 240, len(d)\nassert d[\"date\"].max() <= END\n\ndef nw_lags(n): # Newey-West (1994) plug-in rule of thumb\n return int(np.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(sub):\n X = sm.add_constant(sub[\"g\"].values); y = sub[\"du\"].values\n L = nw_lags(len(sub))\n ols = sm.OLS(y, X).fit()\n hac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\n return ols, hac, L\n\nfull_ols, full_hac, L = fit(d)\ns1 = d[d[\"date\"] < SPLIT]; s2 = d[d[\"date\"] >= SPLIT]\no1, h1, L1 = fit(s1); o2, h2, L2 = fit(s2)\n\n# baseline / model metrics\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full_ols.resid ** 2)))\nbeta = float(full_ols.params[1]); alpha = float(full_ols.params[0])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test\nn, k = len(d), 2\nssr_p, ssr_1, ssr_2 = full_ols.ssr, o1.ssr, o2.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\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nres = {\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": d[\"date\"].min().strftime(\"%Y-%m-%d\"),\n \"sample_end\": d[\"date\"].max().strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse, \"model_metric\": model_rmse,\n \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n \"beta_sub1\": float(o1.params[1]), \"beta_sub2\": float(o2.params[1]),\n \"chow_f_stat\": float(F), \"chow_p_value\": p,\n \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues, \"n_input_rows\": n_input,\n \"n_analysed\": int(n), \"random_seed\": SEED,\n # supplementary (not required)\n \"ols_classical_se\": float(full_ols.bse[1]),\n \"r_squared\": float(full_ols.rsquared),\n \"se_sub1_hac\": float(h1.bse[1]), \"se_sub2_hac\": float(h2.bse[1]),\n \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n \"intercept_sub1\": float(o1.params[0]), \"intercept_sub2\": float(o2.params[0]),\n \"ssr_pooled\": float(ssr_p), \"ssr_sub1\": float(ssr_1), \"ssr_sub2\": float(ssr_2),\n \"sensitivity_effect_se_by_lag\": {str(l): float(sm.OLS(d[\"du\"].values, sm.add_constant(d[\"g\"].values)).fit(\n cov_type=\"HAC\", cov_kwds={\"maxlags\": l, \"kernel\": \"bartlett\", \"use_correction\": True}).bse[1]) for l in (0, 2, 4, 8, 12)},\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\n\ntab = pd.DataFrame([\n [\"full_1960Q1-2019Q4\", n, alpha, beta, se],\n [\"sub1_1960Q1-1983Q4\", len(s1), o1.params[0], o1.params[1], h1.bse[1]],\n [\"sub2_1984Q1-2019Q4\", len(s2), o2.params[0], o2.params[1], h2.bse[1]],\n], columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"])\ntab.to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=.6, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=.6, marker=\"^\", label=\"1984Q1–2019Q4\")\nxs = np.linspace(d[\"g\"].min(), d[\"g\"].max(), 50)\nax.plot(xs, o1.params[0] + o1.params[1] * xs, lw=2, label=f\"fit 1: β={o1.params[1]:.3f}\")\nax.plot(xs, o2.params[0] + o2.params[1] * xs, lw=2, ls=\"--\", label=f\"fit 2: β={o2.params[1]:.3f}\")\nax.axhline(0, c=\"grey\", lw=.5); ax.axvline(0, c=\"grey\", lw=.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1–2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"stability_conclusion\",\n \"conclusion\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && cat out/results.json | head -80","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":1306,"cache_read_input_tokens":9389,"output_tokens":3890,"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":1306},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpb83ndmYACTbjJ6c3v","requestRef":"421b52c0-9dd9-4ecd-a7a4-202e3ed946b4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"07f32eb2-7e89-4714-848a-6922ceb10e1f","timestamp":"2026-10-30T04:52:14.281Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"07f32eb2-7e89-4714-848a-6922ceb10e1f","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.5/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0177/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01N4579QeHgx2A8fjeNkfUZ5"}]},"uuid":"0f8e3794-0286-49c2-b234-6662fd6129b1","timestamp":"2026-10-30T04:52:14.344Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.5/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0177/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"07f32eb2-7e89-4714-848a-6922ceb10e1f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"ef56780ccd376769de473c9e07c8e6f0f02e1eacd38cf74a4118f48a0f0bcc2c","message":{"role":"assistant","content":[{"type":"text","text":"Now the analysis script (it also writes the exclusion ledger)."},{"type":"tool_use","id":"toolu_01N4579QeHgx2A8fjeNkfUZ5","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"F6-conf-03 Okun's law replication. 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\"; os.makedirs(OUT, exist_ok=True)\nSEED = None # no randomness used\nSTART, END = pd.Timestamp(\"1960-01-01\"), pd.Timestamp(\"2019-10-01\")\nSPLIT = pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\")\nun = pd.read_csv(\"data/UNRATE.csv\")\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"date\"] = pd.to_datetime(gdp[\"observation_date\"]); un[\"date\"] = pd.to_datetime(un[\"observation_date\"])\ngdp[\"GDPC1\"] = pd.to_numeric(gdp[\"GDPC1\"], errors=\"coerce\")\nun[\"UNRATE\"] = pd.to_numeric(un[\"UNRATE\"], errors=\"coerce\")\n\ndata_issues = []\nmiss_un = un.loc[un[\"UNRATE\"].isna(), \"observation_date\"].tolist()\nif miss_un:\n data_issues.append({\"issue\": f\"UNRATE missing (non-numeric '.') for month(s) {miss_un}\",\n \"handling\": \"Outside 1959Q4-2019Q4 window; affected quarter dropped by the window restriction, no imputation.\"})\nmiss_g = gdp.loc[gdp[\"GDPC1\"].isna(), \"observation_date\"].tolist()\nif miss_g:\n data_issues.append({\"issue\": f\"GDPC1 missing for {miss_g}\", \"handling\": \"dropped if outside window; fatal if inside\"})\ndata_issues.append({\"issue\": \"Files extend beyond 2019Q4 (GDPC1 to 2026Q3, UNRATE to 2026-09), including COVID-19 quarters\",\n \"handling\": \"Excluded by the information rule: no quarter after 2019Q4 enters any estimate.\"})\ndata_issues.append({\"issue\": \"GDPC1 is the current (2026) vintage, revised data, not real-time\",\n \"handling\": \"Used as provided; noted as limitation (estimates reflect revised GDP).\"})\n\n# Quarterly unemployment: mean of 3 months, require complete quarter\nun[\"q\"] = un[\"date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nuq.loc[uq[\"count\"] < 3, \"mean\"] = np.nan # incomplete quarter -> missing\ng = gdp.set_index(gdp[\"date\"].dt.to_period(\"Q\"))[\"GDPC1\"]\ndf = pd.DataFrame({\"u\": uq[\"mean\"], \"y\": g}).sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"y\"]).diff()\ndf[\"date\"] = df.index.to_timestamp()\n\nexcl = []\nn0 = len(df)\nstep1 = df[(df[\"date\"] >= START) & (df[\"date\"] <= END)]\nexcl.append([\"1\", \"keep quarters 1960Q1-2019Q4 (union of GDPC1/UNRATE quarterly index)\", n0, len(step1), n0 - len(step1),\n \"information rule: regression sample; pre-1960 used only as lag for 1960Q1 difference; post-2019 excluded\"])\nstep2 = step1.dropna(subset=[\"du\", \"g\"])\nexcl.append([\"2\", \"drop quarters with missing du or g\", len(step1), len(step2), len(step1) - len(step2),\n \"no missing values expected inside the window\"])\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nd = step2.copy()\nassert len(d) == 240, len(d)\nassert d[\"date\"].max() <= END\n\ndef nw_lags(n): # Newey-West (1994) plug-in rule of thumb\n return int(np.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(sub):\n X = sm.add_constant(sub[\"g\"].values); y = sub[\"du\"].values\n L = nw_lags(len(sub))\n ols = sm.OLS(y, X).fit()\n hac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\n return ols, hac, L\n\nfull_ols, full_hac, L = fit(d)\ns1 = d[d[\"date\"] < SPLIT]; s2 = d[d[\"date\"] >= SPLIT]\no1, h1, L1 = fit(s1); o2, h2, L2 = fit(s2)\n\n# baseline / model metrics\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full_ols.resid ** 2)))\nbeta = float(full_ols.params[1]); alpha = float(full_ols.params[0])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test\nn, k = len(d), 2\nssr_p, ssr_1, ssr_2 = full_ols.ssr, o1.ssr, o2.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\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nres = {\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": d[\"date\"].min().strftime(\"%Y-%m-%d\"),\n \"sample_end\": d[\"date\"].max().strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse, \"model_metric\": model_rmse,\n \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n \"beta_sub1\": float(o1.params[1]), \"beta_sub2\": float(o2.params[1]),\n \"chow_f_stat\": float(F), \"chow_p_value\": p,\n \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues, \"n_input_rows\": n_input,\n \"n_analysed\": int(n), \"random_seed\": SEED,\n # supplementary (not required)\n \"ols_classical_se\": float(full_ols.bse[1]),\n \"r_squared\": float(full_ols.rsquared),\n \"se_sub1_hac\": float(h1.bse[1]), \"se_sub2_hac\": float(h2.bse[1]),\n \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n \"intercept_sub1\": float(o1.params[0]), \"intercept_sub2\": float(o2.params[0]),\n \"ssr_pooled\": float(ssr_p), \"ssr_sub1\": float(ssr_1), \"ssr_sub2\": float(ssr_2),\n \"sensitivity_effect_se_by_lag\": {str(l): float(sm.OLS(d[\"du\"].values, sm.add_constant(d[\"g\"].values)).fit(\n cov_type=\"HAC\", cov_kwds={\"maxlags\": l, \"kernel\": \"bartlett\", \"use_correction\": True}).bse[1]) for l in (0, 2, 4, 8, 12)},\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\n\ntab = pd.DataFrame([\n [\"full_1960Q1-2019Q4\", n, alpha, beta, se],\n [\"sub1_1960Q1-1983Q4\", len(s1), o1.params[0], o1.params[1], h1.bse[1]],\n [\"sub2_1984Q1-2019Q4\", len(s2), o2.params[0], o2.params[1], h2.bse[1]],\n], columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"])\ntab.to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=.6, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=.6, marker=\"^\", label=\"1984Q1–2019Q4\")\nxs = np.linspace(d[\"g\"].min(), d[\"g\"].max(), 50)\nax.plot(xs, o1.params[0] + o1.params[1] * xs, lw=2, label=f\"fit 1: β={o1.params[1]:.3f}\")\nax.plot(xs, o2.params[0] + o2.params[1] * xs, lw=2, ls=\"--\", label=f\"fit 2: β={o2.params[1]:.3f}\")\nax.axhline(0, c=\"grey\", lw=.5); ax.axvline(0, c=\"grey\", lw=.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1–2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"stability_conclusion\",\n \"conclusion\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && cat out/results.json | head -80","description":"Write and run analysis script"}}]}}39{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"b1927fd6-1702-4462-b6e9-4dc3a6e1decd","timestamp":"2026-10-30T04:52:14.347Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"421b52c0-9dd9-4ecd-a7a4-202e3ed946b4","keep":10,"tail":["ef56780ccd376769de473c9e07c8e6f0f02e1eacd38cf74a4118f48a0f0bcc2c","13bc908027a7be91dafd3e9c8fce21a3320fcf15553c81eaa9491968296fffdc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f2df2affffaf0e887a698222daa165194b5130d2283a9e36ae1611c160076280"}40{"parentUuid":"0f8e3794-0286-49c2-b234-6662fd6129b1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpdDtKkYePxox2mAhfu","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":4052,"cache_read_input_tokens":10695,"output_tokens":122,"output_tokens_details":{"thinking_tokens":16},"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":4052},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":289,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpdDcD5MGotmGutQ9vR","requestRef":"b1927fd6-1702-4462-b6e9-4dc3a6e1decd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a6afe887-c17f-4f9d-987e-26b463894e35","timestamp":"2026-10-30T04:52:15.789Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"a6afe887-c17f-4f9d-987e-26b463894e35","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpdDtKkYePxox2mAhfu","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CJUK4Vy5kz3MbVcQgTusbo","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0177 && pwd","description":"Return to workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4052,"cache_read_input_tokens":10695,"output_tokens":122,"output_tokens_details":{"thinking_tokens":16},"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":4052},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpdDcD5MGotmGutQ9vR","requestRef":"b1927fd6-1702-4462-b6e9-4dc3a6e1decd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"054316da-d716-486c-857b-70186ab76b78","timestamp":"2026-10-30T04:52:16.155Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"054316da-d716-486c-857b-70186ab76b78","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CJUK4Vy5kz3MbVcQgTusbo","type":"tool_result","content":"/Users/simon-pierreboucher/wp29/runs/RC0177","is_error":false}]},"uuid":"928a8942-b8ee-424c-8b49-fb9a3a22884b","timestamp":"2026-10-30T04:52:16.190Z","toolUseResult":{"stdout":"/Users/simon-pierreboucher/wp29/runs/RC0177","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"054316da-d716-486c-857b-70186ab76b78","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}43{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"3e81360953ab62b63fbb013012263644cb50698a12f47e27b2f1d5722eada599","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01CJUK4Vy5kz3MbVcQgTusbo","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0177 && pwd","description":"Return to workspace root"}}]}}44{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"aa74beff-dfc5-452a-b1c2-70ded9ccdd05","timestamp":"2026-10-30T04:52:16.193Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"b1927fd6-1702-4462-b6e9-4dc3a6e1decd","keep":12,"tail":["3e81360953ab62b63fbb013012263644cb50698a12f47e27b2f1d5722eada599","8af76159a4f0414eb22b5f15976b20d56580f48063a836daa1828dee3ee54445"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"01d42e84b2296889ca9fd3681f12f02b1ab19d38fab7328384ea7d118baeef7e"}45{"parentUuid":"928a8942-b8ee-424c-8b49-fb9a3a22884b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpdMgeCg4o91A7d6qcA","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":152,"cache_read_input_tokens":14747,"output_tokens":3950,"output_tokens_details":{"thinking_tokens":39},"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":152},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":388,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpdMQmb78ck4D9mKdM1","requestRef":"aa74beff-dfc5-452a-b1c2-70ded9ccdd05","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5e0a3e96-3fe2-4810-9068-911dfbb3d910","timestamp":"2026-10-30T04:52:17.867Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"5e0a3e96-3fe2-4810-9068-911dfbb3d910","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpdMgeCg4o91A7d6qcA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GV1XEa3FMvDMBuW3ex4GVn","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"F6-conf-03 Okun's law replication. 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\"; os.makedirs(OUT, exist_ok=True)\nSEED = None # no randomness used\nSTART, END = pd.Timestamp(\"1960-01-01\"), pd.Timestamp(\"2019-10-01\")\nSPLIT = pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\")\nun = pd.read_csv(\"data/UNRATE.csv\")\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"date\"] = pd.to_datetime(gdp[\"observation_date\"]); un[\"date\"] = pd.to_datetime(un[\"observation_date\"])\ngdp[\"GDPC1\"] = pd.to_numeric(gdp[\"GDPC1\"], errors=\"coerce\")\nun[\"UNRATE\"] = pd.to_numeric(un[\"UNRATE\"], errors=\"coerce\")\n\ndata_issues = []\nmiss_un = un.loc[un[\"UNRATE\"].isna(), \"observation_date\"].tolist()\nif miss_un:\n data_issues.append({\"issue\": f\"UNRATE missing (empty value) for month(s) {miss_un}\",\n \"handling\": \"Outside 1959Q4-2019Q4 window; affected quarter set to missing and in any case excluded by the window restriction, no imputation.\"})\nmiss_g = gdp.loc[gdp[\"GDPC1\"].isna(), \"observation_date\"].tolist()\nif miss_g:\n data_issues.append({\"issue\": f\"GDPC1 missing for {miss_g}\", \"handling\": \"dropped if outside window; fatal if inside\"})\ndata_issues.append({\"issue\": \"Files extend beyond 2019Q4 (GDPC1 to 2026Q3, UNRATE to 2026-09), including COVID-19 quarters\",\n \"handling\": \"Excluded by the information rule: no quarter after 2019Q4 enters any estimate.\"})\ndata_issues.append({\"issue\": \"GDPC1 is the current (2026) vintage, revised data, not real-time\",\n \"handling\": \"Used as provided; noted as limitation (estimates reflect revised GDP).\"})\n\n# Quarterly unemployment: mean of 3 months, require complete quarter\nun[\"q\"] = un[\"date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nuq.loc[uq[\"count\"] < 3, \"mean\"] = np.nan # incomplete quarter -> missing\ng = gdp.set_index(gdp[\"date\"].dt.to_period(\"Q\"))[\"GDPC1\"]\ndf = pd.DataFrame({\"u\": uq[\"mean\"], \"y\": g}).sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"y\"]).diff()\ndf[\"date\"] = df.index.to_timestamp()\n\nexcl = []\nn0 = len(df)\nstep1 = df[(df[\"date\"] >= START) & (df[\"date\"] <= END)]\nexcl.append([\"1\", \"keep quarters 1960Q1-2019Q4 (union of GDPC1/UNRATE quarterly index)\", n0, len(step1), n0 - len(step1),\n \"information rule: regression sample; pre-1960 used only as lag for 1960Q1 difference; post-2019 excluded\"])\nstep2 = step1.dropna(subset=[\"du\", \"g\"])\nexcl.append([\"2\", \"drop quarters with missing du or g\", len(step1), len(step2), len(step1) - len(step2),\n \"no missing values expected inside the window\"])\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nd = step2.copy()\nassert len(d) == 240, len(d)\nassert d[\"date\"].max() <= END\n\ndef nw_lags(n): # Newey-West (1994) plug-in rule of thumb\n return int(np.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(sub):\n X = sm.add_constant(sub[\"g\"].values); y = sub[\"du\"].values\n L = nw_lags(len(sub))\n ols = sm.OLS(y, X).fit()\n hac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\n return ols, hac, L\n\nfull_ols, full_hac, L = fit(d)\ns1 = d[d[\"date\"] < SPLIT]; s2 = d[d[\"date\"] >= SPLIT]\no1, h1, L1 = fit(s1); o2, h2, L2 = fit(s2)\n\n# baseline / model metrics\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full_ols.resid ** 2)))\nbeta = float(full_ols.params[1]); alpha = float(full_ols.params[0])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test\nn, k = len(d), 2\nssr_p, ssr_1, ssr_2 = full_ols.ssr, o1.ssr, o2.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\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nres = {\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": d[\"date\"].min().strftime(\"%Y-%m-%d\"),\n \"sample_end\": d[\"date\"].max().strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse, \"model_metric\": model_rmse,\n \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n \"beta_sub1\": float(o1.params[1]), \"beta_sub2\": float(o2.params[1]),\n \"chow_f_stat\": float(F), \"chow_p_value\": p,\n \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues, \"n_input_rows\": n_input,\n \"n_analysed\": int(n), \"random_seed\": SEED,\n # supplementary (not required)\n \"ols_classical_se\": float(full_ols.bse[1]),\n \"r_squared\": float(full_ols.rsquared),\n \"se_sub1_hac\": float(h1.bse[1]), \"se_sub2_hac\": float(h2.bse[1]),\n \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n \"intercept_sub1\": float(o1.params[0]), \"intercept_sub2\": float(o2.params[0]),\n \"ssr_pooled\": float(ssr_p), \"ssr_sub1\": float(ssr_1), \"ssr_sub2\": float(ssr_2),\n \"sensitivity_effect_se_by_lag\": {str(l): float(sm.OLS(d[\"du\"].values, sm.add_constant(d[\"g\"].values)).fit(\n cov_type=\"HAC\", cov_kwds={\"maxlags\": l, \"kernel\": \"bartlett\", \"use_correction\": True}).bse[1]) for l in (0, 2, 4, 8, 12)},\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\n\ntab = pd.DataFrame([\n [\"full_1960Q1-2019Q4\", n, alpha, beta, se],\n [\"sub1_1960Q1-1983Q4\", len(s1), o1.params[0], o1.params[1], h1.bse[1]],\n [\"sub2_1984Q1-2019Q4\", len(s2), o2.params[0], o2.params[1], h2.bse[1]],\n], columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"])\ntab.to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=.6, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=.6, marker=\"^\", label=\"1984Q1–2019Q4\")\nxs = np.linspace(d[\"g\"].min(), d[\"g\"].max(), 50)\nax.plot(xs, o1.params[0] + o1.params[1] * xs, lw=2, label=f\"fit 1: β={o1.params[1]:.3f}\")\nax.plot(xs, o2.params[0] + o2.params[1] * xs, lw=2, ls=\"--\", label=f\"fit 2: β={o2.params[1]:.3f}\")\nax.axhline(0, c=\"grey\", lw=.5); ax.axvline(0, c=\"grey\", lw=.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1–2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"stability_conclusion\",\n \"conclusion\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && sed -n '/data_issues/,$p' out/results.json","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":152,"cache_read_input_tokens":14747,"output_tokens":3950,"output_tokens_details":{"thinking_tokens":39},"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":152},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpdMQmb78ck4D9mKdM1","requestRef":"aa74beff-dfc5-452a-b1c2-70ded9ccdd05","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6b8673b1-8bc2-4761-8682-ada6f216a60b","timestamp":"2026-10-30T04:52:42.291Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}47{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"6b8673b1-8bc2-4761-8682-ada6f216a60b","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}48{"type":"atis-latch","atis":"","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}49{"parentUuid":"6b8673b1-8bc2-4761-8682-ada6f216a60b","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GV1XEa3FMvDMBuW3ex4GVn","type":"tool_result","content":"{\n \"effect_estimate\": -0.2557677277487258,\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 \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03598488399675878\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03921717107661775\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06879369233083424\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep quarters 1960Q1-2019Q4 (union of GDPC1/UNRATE quarterly index),319,240,79,information rule: regression sample; pre-1960 used only as lag for 1960Q1 difference; post-2019 excluded\n2,drop quarters with missing du or g,240,240,0,no missing values expected inside the window\n \"data_issues\": [\n {\n \"issue\": \"UNRATE missing (empty value) for month(s) ['2025-10-01']\",\n \"handling\": \"Outside 1959Q4-2019Q4 window; affected quarter set to missing and in any case excluded by the window restriction, no imputation.\"\n },\n {\n \"issue\": \"Files extend beyond 2019Q4 (GDPC1 to 2026Q3, UNRATE to 2026-09), including COVID-19 quarters\",\n \"handling\": \"Excluded by the information rule: no quarter after 2019Q4 enters any estimate.\"\n },\n {\n \"issue\": \"GDPC1 is the current (2026) vintage, revised data, not real-time\",\n \"handling\": \"Used as provided; noted as limitation (estimates reflect revised GDP).\"\n }\n ],\n \"n_input_rows\": {\n \"GDPC1.csv\": 319,\n \"UNRATE.csv\": 945\n },\n \"n_analysed\": 240,\n \"random_seed\": null,\n \"ols_classical_se\": 0.01996009291490984,\n \"r_squared\": 0.4082508284562034,\n \"se_sub1_hac\": 0.03921717107661775,\n \"se_sub2_hac\": 0.06879369233083424,\n \"hac_lags_sub1\": 3,\n \"hac_lags_sub2\": 4,\n \"intercept_sub1\": 0.2542326539884382,\n \"intercept_sub2\": 0.15168581347724602,\n \"ssr_pooled\": 14.96928154281957,\n \"ssr_sub1\": 7.379293854646264,\n \"ssr_sub2\": 6.855297827559747,\n \"sensitivity_effect_se_by_lag\": {\n \"0\": 0.028957130333809637,\n \"2\": 0.034370831642247524,\n \"4\": 0.03598488399675878,\n \"8\": 0.03729120927832667,\n \"12\": 0.03656150942843361\n }\n}","is_error":false}]},"uuid":"a7226001-f2a8-455e-a6cd-35bcf5744839","timestamp":"2026-10-30T04:52:43.491Z","toolUseResult":{"stdout":"{\n \"effect_estimate\": -0.2557677277487258,\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 \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03598488399675878\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03921717107661775\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06879369233083424\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep quarters 1960Q1-2019Q4 (union of GDPC1/UNRATE quarterly index),319,240,79,information rule: regression sample; pre-1960 used only as lag for 1960Q1 difference; post-2019 excluded\n2,drop quarters with missing du or g,240,240,0,no missing values expected inside the window\n \"data_issues\": [\n {\n \"issue\": \"UNRATE missing (empty value) for month(s) ['2025-10-01']\",\n \"handling\": \"Outside 1959Q4-2019Q4 window; affected quarter set to missing and in any case excluded by the window restriction, no imputation.\"\n },\n {\n \"issue\": \"Files extend beyond 2019Q4 (GDPC1 to 2026Q3, UNRATE to 2026-09), including COVID-19 quarters\",\n \"handling\": \"Excluded by the information rule: no quarter after 2019Q4 enters any estimate.\"\n },\n {\n \"issue\": \"GDPC1 is the current (2026) vintage, revised data, not real-time\",\n \"handling\": \"Used as provided; noted as limitation (estimates reflect revised GDP).\"\n }\n ],\n \"n_input_rows\": {\n \"GDPC1.csv\": 319,\n \"UNRATE.csv\": 945\n },\n \"n_analysed\": 240,\n \"random_seed\": null,\n \"ols_classical_se\": 0.01996009291490984,\n \"r_squared\": 0.4082508284562034,\n \"se_sub1_hac\": 0.03921717107661775,\n \"se_sub2_hac\": 0.06879369233083424,\n \"hac_lags_sub1\": 3,\n \"hac_lags_sub2\": 4,\n \"intercept_sub1\": 0.2542326539884382,\n \"intercept_sub2\": 0.15168581347724602,\n \"ssr_pooled\": 14.96928154281957,\n \"ssr_sub1\": 7.379293854646264,\n \"ssr_sub2\": 6.855297827559747,\n \"sensitivity_effect_se_by_lag\": {\n \"0\": 0.028957130333809637,\n \"2\": 0.034370831642247524,\n \"4\": 0.03598488399675878,\n \"8\": 0.03729120927832667,\n \"12\": 0.03656150942843361\n }\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6b8673b1-8bc2-4761-8682-ada6f216a60b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"0bee9af3f3eea05cbd0caf27d9cbd5bce2a36151d828b24df6881127d97221f7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSyAYKEAgTGAI4AUIIdGhpbmtpbmcSDGbKjmbKgOpNjh2KMBoMAisBEu+h85WNeEu8IjAX1oUNexjPReumNKX8Cv+UYJtlTxMSEUNG1k9T2lzJ4qh2zkkWuXYMnF2g/IJjcPEq5QUJz/UX8BPbmCO3b2I5wgbK0ow4u1jcpsx02gKvQZFJDVU4T8U8IKg2NKF4mXr3Mh/LA7cBbSGXOKHpz7i3ZwRQW3sZExzAfZgi2A6wORXdcwhGU6eplWX6Q1bncGCiAOvmy8c1l/JlWjy0vZZYRrzGWnMwTRHvowOVl78rsEw0UqAKhgNicPXEOpjGFfW+oWTRJeju0fEoq8Dn4Aer3qTlhKeWC6GRAGDI+1cVMW2BfIrQHFr9vqilGfwFEXlbgT+C3uXHoBfSiiSLroLt8vR9/e9pggl1ItLgjLHocMrA9VheDvMa0HUdh0+Ze27gQUpFRigwM9uifI1NadAoMoh8GEts3nA4KQRTVIciFhYo7OPGeiEK5F13JmFdpgdOQjeH7+Jlaxhtag8BDOKrOXbDhJnEjH/ls5nrr44mnuAncxeU3/A2jZQQckVpckmIUuVhI+ruS9QcJKrAzA1R6woITIAK0Ac+ky+uQon3Ed8Ss9mcwemTzQJHxd9/rZg3NyqO/1DnaK6Nvx30E/VUxU4zE8zZyFBAcdfhMxs4C0CbHGMCLjFtsDYvMFxLLqHRHVbArBAIjaL3G8Cc/GOSvWZLwme9u8swKw9D8UqHHlLwUq5I8N0maJDpqY9bnnHsPk7ly0KpAuW7tBXgv40LzZRgESKoW+1r4qxrMyEJT6YI8jgxu3gLYJP2pHWRMcszORLMo10E3oe50yC6P7Bqy8aMajFIlglqS3sgLqF8imGAOJEnVbPxXC0+ccsnobUg3d0YA7w1B558DaexJw5iyrfsfEp5Io32D61PkMMN+09gTDp2Vwnwxhg+DPpOU7GIyfHWUPmnakwRZGa8TlLwxdCMdGYMQTcWdknYN85y+7rZ/nTNGNQuHdt7DbNcQjbUatgactKLmKf9DgFwmv6hjnchbhh0W6mu2S+5Czva9Pir5mk7pnXozsqb1j4o/pBmKlyAJTEkl1u35EO6FzS4TGzyXhAoa4IYAQ=="},{"type":"tool_use","id":"toolu_01GV1XEa3FMvDMBuW3ex4GVn","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"F6-conf-03 Okun's law replication. 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\"; os.makedirs(OUT, exist_ok=True)\nSEED = None # no randomness used\nSTART, END = pd.Timestamp(\"1960-01-01\"), pd.Timestamp(\"2019-10-01\")\nSPLIT = pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\")\nun = pd.read_csv(\"data/UNRATE.csv\")\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\ngdp[\"date\"] = pd.to_datetime(gdp[\"observation_date\"]); un[\"date\"] = pd.to_datetime(un[\"observation_date\"])\ngdp[\"GDPC1\"] = pd.to_numeric(gdp[\"GDPC1\"], errors=\"coerce\")\nun[\"UNRATE\"] = pd.to_numeric(un[\"UNRATE\"], errors=\"coerce\")\n\ndata_issues = []\nmiss_un = un.loc[un[\"UNRATE\"].isna(), \"observation_date\"].tolist()\nif miss_un:\n data_issues.append({\"issue\": f\"UNRATE missing (empty value) for month(s) {miss_un}\",\n \"handling\": \"Outside 1959Q4-2019Q4 window; affected quarter set to missing and in any case excluded by the window restriction, no imputation.\"})\nmiss_g = gdp.loc[gdp[\"GDPC1\"].isna(), \"observation_date\"].tolist()\nif miss_g:\n data_issues.append({\"issue\": f\"GDPC1 missing for {miss_g}\", \"handling\": \"dropped if outside window; fatal if inside\"})\ndata_issues.append({\"issue\": \"Files extend beyond 2019Q4 (GDPC1 to 2026Q3, UNRATE to 2026-09), including COVID-19 quarters\",\n \"handling\": \"Excluded by the information rule: no quarter after 2019Q4 enters any estimate.\"})\ndata_issues.append({\"issue\": \"GDPC1 is the current (2026) vintage, revised data, not real-time\",\n \"handling\": \"Used as provided; noted as limitation (estimates reflect revised GDP).\"})\n\n# Quarterly unemployment: mean of 3 months, require complete quarter\nun[\"q\"] = un[\"date\"].dt.to_period(\"Q\")\nuq = un.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nuq.loc[uq[\"count\"] < 3, \"mean\"] = np.nan # incomplete quarter -> missing\ng = gdp.set_index(gdp[\"date\"].dt.to_period(\"Q\"))[\"GDPC1\"]\ndf = pd.DataFrame({\"u\": uq[\"mean\"], \"y\": g}).sort_index()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"y\"]).diff()\ndf[\"date\"] = df.index.to_timestamp()\n\nexcl = []\nn0 = len(df)\nstep1 = df[(df[\"date\"] >= START) & (df[\"date\"] <= END)]\nexcl.append([\"1\", \"keep quarters 1960Q1-2019Q4 (union of GDPC1/UNRATE quarterly index)\", n0, len(step1), n0 - len(step1),\n \"information rule: regression sample; pre-1960 used only as lag for 1960Q1 difference; post-2019 excluded\"])\nstep2 = step1.dropna(subset=[\"du\", \"g\"])\nexcl.append([\"2\", \"drop quarters with missing du or g\", len(step1), len(step2), len(step1) - len(step2),\n \"no missing values expected inside the window\"])\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nd = step2.copy()\nassert len(d) == 240, len(d)\nassert d[\"date\"].max() <= END\n\ndef nw_lags(n): # Newey-West (1994) plug-in rule of thumb\n return int(np.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(sub):\n X = sm.add_constant(sub[\"g\"].values); y = sub[\"du\"].values\n L = nw_lags(len(sub))\n ols = sm.OLS(y, X).fit()\n hac = sm.OLS(y, X).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\n return ols, hac, L\n\nfull_ols, full_hac, L = fit(d)\ns1 = d[d[\"date\"] < SPLIT]; s2 = d[d[\"date\"] >= SPLIT]\no1, h1, L1 = fit(s1); o2, h2, L2 = fit(s2)\n\n# baseline / model metrics\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full_ols.resid ** 2)))\nbeta = float(full_ols.params[1]); alpha = float(full_ols.params[0])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test\nn, k = len(d), 2\nssr_p, ssr_1, ssr_2 = full_ols.ssr, o1.ssr, o2.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\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nres = {\n \"task_id\": \"F6-conf-03\",\n \"sample_start\": d[\"date\"].min().strftime(\"%Y-%m-%d\"),\n \"sample_end\": d[\"date\"].max().strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse, \"model_metric\": model_rmse,\n \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n \"beta_sub1\": float(o1.params[1]), \"beta_sub2\": float(o2.params[1]),\n \"chow_f_stat\": float(F), \"chow_p_value\": p,\n \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n \"conclusion\": conclusion,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues, \"n_input_rows\": n_input,\n \"n_analysed\": int(n), \"random_seed\": SEED,\n # supplementary (not required)\n \"ols_classical_se\": float(full_ols.bse[1]),\n \"r_squared\": float(full_ols.rsquared),\n \"se_sub1_hac\": float(h1.bse[1]), \"se_sub2_hac\": float(h2.bse[1]),\n \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n \"intercept_sub1\": float(o1.params[0]), \"intercept_sub2\": float(o2.params[0]),\n \"ssr_pooled\": float(ssr_p), \"ssr_sub1\": float(ssr_1), \"ssr_sub2\": float(ssr_2),\n \"sensitivity_effect_se_by_lag\": {str(l): float(sm.OLS(d[\"du\"].values, sm.add_constant(d[\"g\"].values)).fit(\n cov_type=\"HAC\", cov_kwds={\"maxlags\": l, \"kernel\": \"bartlett\", \"use_correction\": True}).bse[1]) for l in (0, 2, 4, 8, 12)},\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\n\ntab = pd.DataFrame([\n [\"full_1960Q1-2019Q4\", n, alpha, beta, se],\n [\"sub1_1960Q1-1983Q4\", len(s1), o1.params[0], o1.params[1], h1.bse[1]],\n [\"sub2_1984Q1-2019Q4\", len(s2), o2.params[0], o2.params[1], h2.bse[1]],\n], columns=[\"period\", \"n\", \"intercept\", \"slope\", \"slope_se\"])\ntab.to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=.6, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=.6, marker=\"^\", label=\"1984Q1–2019Q4\")\nxs = np.linspace(d[\"g\"].min(), d[\"g\"].max(), 50)\nax.plot(xs, o1.params[0] + o1.params[1] * xs, lw=2, label=f\"fit 1: β={o1.params[1]:.3f}\")\nax.plot(xs, o2.params[0] + o2.params[1] * xs, lw=2, ls=\"--\", label=f\"fit 2: β={o2.params[1]:.3f}\")\nax.axhline(0, c=\"grey\", lw=.5); ax.axvline(0, c=\"grey\", lw=.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1–2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\", \"stability_conclusion\",\n \"conclusion\", \"baseline_metric\", \"model_metric\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && sed -n '/data_issues/,$p' out/results.json","description":"Write and run analysis script"}}]}}51{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"e64e9369-77dd-4cef-b6a4-0c86d8dff2ef","timestamp":"2026-10-30T04:52:43.495Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"aa74beff-dfc5-452a-b1c2-70ded9ccdd05","keep":14,"tail":["0bee9af3f3eea05cbd0caf27d9cbd5bce2a36151d828b24df6881127d97221f7","feedf22e4b97df6c4c26c626b97e1a9178eeea60b303ac213d91f099ecd5881e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a335f7aac60d6c27375935c254ab6356d5b9594864d90e52e09af6a772736280"}52{"parentUuid":"a7226001-f2a8-455e-a6cd-35bcf5744839","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpfNPrTiqnatv51YJU6","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS0gsKEAgTGAI4AUIIdGhpbmtpbmcSDFD8PhluA90TGTyc2hoM+mIZcjkf1On36yL+IjBDvR2fggyk2NSsJyG1U212GCQJDBDHxWPPgjFDhpQrAX2XR0/p/csAgKEG+6l+uhIq7wodzUxD8Ic/mMU+LqaAtN6ootWX0ctvFGh6tqox64RxwmXTqGfcSA92Gy2MsFBWD7rQBvGz7eCpnT59aOi2U+r6V7QQm4FRYNJWOm54ncMHsHLt7/yuEsmne0YRBB15EPkhbHwndce77jde01J2bjBubLrq0oaA4qbxp5P3AbrJYSnKCHGyMWb0GsVyDG6GoArGGLa6MCqs/zCvo6MPd4e3AnYtSoWtVwnpLwxKWNl7E+76fkAxI/VMYXTuQpoo97GZfrhEfuqxuczxIOVVt2/IioiAeF2GiYlX/is0PxCwJn5iYUCaLpQWyRjubc3T9Ow4/WkKCRyfemitxyCWZVUXTx+HvdjVbaZSLwTWB64BbyEAxP3Yu+bDUInhhKVHpe/tcRhHZLVBWzE86SYOxefJzPSCfKQYEe2RKRrTG0NEA+S5gfPo7OwOyMErsG8OcaM60Dkmlms8dvJ2eqlzP3Ivtw9kW/oMApLs40v4m8/O/iG3aZEJ/6BW7ysOhBDTmAf41JFZWCSXSaX/A/RO3Ib0wLeDGJ0jWbICj4ghPGC2XhWE+aBtdLN4xDsR2322bK8/AjMPpfKY9zFgyAu+oIq446owl1qrwiYziOYHyS+Pf1TvQR1LhHlcyWL8Muylm5Qhg4BJ7UhPJr+d9Gjm06X8AVKH3wZnyaH0AOigpHFYauBGtqz5g0WPNAYQYY4vM3ihIDkR6NwolQaq4EqQIR2zZFPzCMlvqoIWVzpE1MJVIfPEJCBp6Yf+ypDOnLmmfgbyKNt63MG25DjatNH3dOqgFOMykNhdUAtNSMcJUN0p09YH07JT+nbsTa82yd2UWWt8Wz2TFQ2Ef/+m6/B6FWS1P5xaf0qwBvorncCTZK0o+oWL+n9FClrB6vIY9IUc3RmRWydYUJInSpvwM840wfpRgID9wZnCTNAnDPa+JVhqF2EIceShsO6Z0gdKyO+MApqDMfFToii6kQffzqI+IXlPEaBMmqJvo0JAse6M59tgau5ihyg+iEJUwR8AXzgZ5oilukEOzCxngJx+FleGsFpgfvVjYt64sNDEi2xckek/nSciPODwHDlHHnR9Bc1OkXL1rBSIfiOG1J3YvVmf6mc9vh8EJ4zGidP7783dwMbehn3cMCaqt0389MQNZcPJjMMB4yScE7VexF4rlUsuHwvCFmvQ6uDjBYwG2GB1EmgXfdQ1eAXCsaDcRMawfYqNY9ZhaC6eZlnPF8YhlUBx1+dQVKOQHPI0afAPcHfJD/yddvUmuhVBUYrRmmCIVwHDcO5XacvQIfRpi/OYLe1bvYiBBE75tFu2/yJbzG7ssdiTmUUPeEEe5O3ZtStP0w/b9J+hv49hj5J6fnbyeONO8F9zKVusSKNLcky/zm0WD1PvMNuAMij7PYu8HAhLQFhDBl7XJMzTFUjjIsDmvCbxQPyZY1nhm+T5XsQ1OB7i+zhNIVsB6SDIpFe9djfpUiiIoEiARdXMulflzTjRpqtDpni9u6Fg8tBd8Bf/fj0FLqe0OEZUUabN824ke7zUcnQ8BUsJbmrG08ouc3d169Q/oBRweZB0xWqAUPtDn1BBP0S+/UZ4zyYtlqd98x6ELVIjp/65qw1x+TaB5qBmg8v/WZ4+LEkZp/nNtccDS4bhLOXR+0Vh4nnnfPRV2uTnDT1jie12RHrsnatQOvZtyAmlFWLSMJ5KFn7uca/ECArThW41yayuM8azyAtC2Gsf305BuoAFybfeWzdxPBdIQ+eyE5pMYuF3s3ukvtn8iULRp4AYxm9dME1w6358pdFIQMXEta9PjhMZMHy/7SvZXv31VmGqU5yBCO0/eDLrf3L9itHf5/XVTzEC9E5P01/phek7MxgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5121,"cache_read_input_tokens":14899,"output_tokens":1286,"output_tokens_details":{"thinking_tokens":288},"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":5121},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2452,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpfN9DxJomRudsKa4uw","requestRef":"e64e9369-77dd-4cef-b6a4-0c86d8dff2ef","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"911440a6-ab14-4354-b594-3dacaafd9d6e","timestamp":"2026-10-30T04:52:47.160Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"911440a6-ab14-4354-b594-3dacaafd9d6e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpfNPrTiqnatv51YJU6","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01P5FwPWZqFsSdXJGzHEiNV8","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\nadd='''\n# Supplementary robustness for the stability question (not the required Chow test):\n# HAC Wald tests in a pooled regression with subperiod-2 dummy and interaction.\nD = (d[\"date\"] >= SPLIT).astype(float).values\nXi = np.column_stack([np.ones(n), d[\"g\"].values, D, D * d[\"g\"].values])\nhi_fit = sm.OLS(d[\"du\"].values, Xi).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\nw_joint = hi_fit.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), use_f=True, scalar=True)\nw_slope = hi_fit.wald_test(np.array([[0, 0, 0, 1]]), use_f=True, scalar=True)\nvar_ratio = (ssr_1 / (len(s1) - 2)) / (ssr_2 / (len(s2) - 2))\n'''\ns=s.replace(\"conclusion = \\\"positive_effect\\\"\", add+\"\\nconclusion = \\\"positive_effect\\\"\",1)\ns=s.replace(''' \"sensitivity_effect_se_by_lag\"''',''' \"supp_hac_wald_joint_F\": float(w_joint.statistic), \"supp_hac_wald_joint_p\": float(w_joint.pvalue),\n \"supp_hac_wald_slope_F\": float(w_slope.statistic), \"supp_hac_wald_slope_p\": float(w_slope.pvalue),\n \"supp_resid_var_ratio_sub1_over_sub2\": float(var_ratio),\n \"supp_var_ratio_F_p_two_sided\": float(2 * min(stats.f.sf(var_ratio, len(s1) - 2, len(s2) - 2), stats.f.cdf(var_ratio, len(s1) - 2, len(s2) - 2))),\n \"sensitivity_effect_se_by_lag\"''')\nopen('out/analysis.py','w').write(s)\nEOF\nrm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null && grep supp out/results.json && shasum -a 256 out/results.json out/table1.csv > /tmp/h1 && ~/wp29/venv/bin/python out/analysis.py >/dev/null && shasum -a 256 out/results.json out/table1.csv | diff - /tmp/h1 && echo IDENTICAL","description":"Add supplementary HAC stability tests, 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":5121,"cache_read_input_tokens":14899,"output_tokens":1286,"output_tokens_details":{"thinking_tokens":288},"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":5121},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpfN9DxJomRudsKa4uw","requestRef":"e64e9369-77dd-4cef-b6a4-0c86d8dff2ef","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8476adcf-a7a2-4653-889d-2fdd78c76964","timestamp":"2026-10-30T04:52:54.445Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"8476adcf-a7a2-4653-889d-2fdd78c76964","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01P5FwPWZqFsSdXJGzHEiNV8","type":"tool_result","content":" \"supp_hac_wald_joint_F\": 5.372053278020056,\n \"supp_hac_wald_joint_p\": 0.0052299232796137185,\n \"supp_hac_wald_slope_F\": 0.033475422396223316,\n \"supp_hac_wald_slope_p\": 0.8549842111206409,\n \"supp_resid_var_ratio_sub1_over_sub2\": 1.6261064345399512,\n \"supp_var_ratio_F_p_two_sided\": 0.00871359597470174,\nIDENTICAL","is_error":false}]},"uuid":"c7674ae6-2ba2-48af-b316-ee87fdb2658a","timestamp":"2026-10-30T04:52:56.920Z","toolUseResult":{"stdout":" \"supp_hac_wald_joint_F\": 5.372053278020056,\n \"supp_hac_wald_joint_p\": 0.0052299232796137185,\n \"supp_hac_wald_slope_F\": 0.033475422396223316,\n \"supp_hac_wald_slope_p\": 0.8549842111206409,\n \"supp_resid_var_ratio_sub1_over_sub2\": 1.6261064345399512,\n \"supp_var_ratio_F_p_two_sided\": 0.00871359597470174,\nIDENTICAL","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8476adcf-a7a2-4653-889d-2fdd78c76964","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}55{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"d9d7c206a8f5bfa9c1730765ed10ba165486e42e0d1f5cecff8ff758923e800c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01P5FwPWZqFsSdXJGzHEiNV8","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\nadd='''\n# Supplementary robustness for the stability question (not the required Chow test):\n# HAC Wald tests in a pooled regression with subperiod-2 dummy and interaction.\nD = (d[\"date\"] >= SPLIT).astype(float).values\nXi = np.column_stack([np.ones(n), d[\"g\"].values, D, D * d[\"g\"].values])\nhi_fit = sm.OLS(d[\"du\"].values, Xi).fit(cov_type=\"HAC\", cov_kwds={\"maxlags\": L, \"kernel\": \"bartlett\", \"use_correction\": True})\nw_joint = hi_fit.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), use_f=True, scalar=True)\nw_slope = hi_fit.wald_test(np.array([[0, 0, 0, 1]]), use_f=True, scalar=True)\nvar_ratio = (ssr_1 / (len(s1) - 2)) / (ssr_2 / (len(s2) - 2))\n'''\ns=s.replace(\"conclusion = \\\"positive_effect\\\"\", add+\"\\nconclusion = \\\"positive_effect\\\"\",1)\ns=s.replace(''' \"sensitivity_effect_se_by_lag\"''',''' \"supp_hac_wald_joint_F\": float(w_joint.statistic), \"supp_hac_wald_joint_p\": float(w_joint.pvalue),\n \"supp_hac_wald_slope_F\": float(w_slope.statistic), \"supp_hac_wald_slope_p\": float(w_slope.pvalue),\n \"supp_resid_var_ratio_sub1_over_sub2\": float(var_ratio),\n \"supp_var_ratio_F_p_two_sided\": float(2 * min(stats.f.sf(var_ratio, len(s1) - 2, len(s2) - 2), stats.f.cdf(var_ratio, len(s1) - 2, len(s2) - 2))),\n \"sensitivity_effect_se_by_lag\"''')\nopen('out/analysis.py','w').write(s)\nEOF\nrm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null && grep supp out/results.json && shasum -a 256 out/results.json out/table1.csv > /tmp/h1 && ~/wp29/venv/bin/python out/analysis.py >/dev/null && shasum -a 256 out/results.json out/table1.csv | diff - /tmp/h1 && echo IDENTICAL","description":"Add supplementary HAC stability tests, rerun twice, compare"}}]}}56{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"f3f7e494-1dce-46a7-994b-be829b94a4b6","timestamp":"2026-10-30T04:52:56.923Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"e64e9369-77dd-4cef-b6a4-0c86d8dff2ef","keep":16,"tail":["d9d7c206a8f5bfa9c1730765ed10ba165486e42e0d1f5cecff8ff758923e800c","6b35dd1727a46c7e8827c6588c58593243e6ba8a23e4fa9d68e0ab4a72b3ddb1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"efcaa1adf7346ef07b1613e6f3d23b3a3bf90706a91b81ff1d38677574f58ceb"}57{"type":"tools-used","tools":["Bash","Read"],"sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}58{"parentUuid":"c7674ae6-2ba2-48af-b316-ee87fdb2658a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpgMq9Mx8Hae7vU6P1a","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":1472,"cache_read_input_tokens":20020,"output_tokens":1447,"output_tokens_details":{"thinking_tokens":31},"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":1472},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":308,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpgMYHTJU2s2qV9Kt38","requestRef":"f3f7e494-1dce-46a7-994b-be829b94a4b6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"12663261-a5c5-4c5f-8663-00730c025c47","timestamp":"2026-10-30T04:52:58.285Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}59{"parentUuid":"12663261-a5c5-4c5f-8663-00730c025c47","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpgMq9Mx8Hae7vU6P1a","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019WAusg6yZraLzT42XnQ4Dy","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); t=pd.read_csv('out/table1.csv'); e=pd.read_csv('out/exclusions.csv')\nc=[]\ndef chk(name,ok): c.append(f\"- [{'PASS' if ok else 'FAIL'}] {name}\")\nchk(\"n_sub1+n_sub2==n_analysed==240\", r['n_sub1']+r['n_sub2']==r['n_analysed']==240)\nchk(\"n_sub1==96, n_sub2==144\", (r['n_sub1'],r['n_sub2'])==(96,144))\nchk(\"sample_start=1960-01-01, sample_end=2019-10-01\", (r['sample_start'],r['sample_end'])==('1960-01-01','2019-10-01'))\nchk(\"exclusion ledger: 319 - removed = 240\", 319-e.n_removed.sum()==r['n_analysed'])\nchk(\"effect_se>0 and subperiod SEs>0\", r['effect_se']>0 and (t.slope_se>0).all())\nchk(\"CI contains estimate\", r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'])\nchk(\"CI = beta +/- 1.96*se\", abs(r['effect_ci_high']-r['effect_estimate']-1.959964*r['effect_se'])<1e-5)\nchk(\"model_metric < baseline_metric\", r['model_metric']<r['baseline_metric'])\nchk(\"R2 identity 1-(model/baseline)^2 == r_squared\", abs(1-(r['model_metric']/r['baseline_metric'])**2-r['r_squared'])<1e-10)\nchk(\"SSR_pooled >= SSR1+SSR2\", 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)\nchk(\"Chow F recomputed from SSRs with df (2,236)\", abs(F-r['chow_f_stat'])<1e-10)\nchk(\"stability_conclusion consistent with p\", (r['chow_p_value']<0.05)==(r['stability_conclusion']=='unstable'))\nchk(\"conclusion consistent with CI\", r['conclusion']=='negative_effect' and r['effect_ci_high']<0)\nchk(\"table1 full row matches results\", np.isclose(t.slope[0],r['effect_estimate']) and np.isclose(t.slope_se[0],r['effect_se']) and np.isclose(t.intercept[0],r['intercept']))\nchk(\"table1 has 3 rows and required columns\", len(t)==3 and list(t.columns)==['period','n','intercept','slope','slope_se'])\nchk(\"magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 in levels-of-gap form; difference form typically -0.2 to -0.4)\", -0.6<r['effect_estimate']<-0.1)\nchk(\"hac_lags=floor(4*(240/100)^(2/9))=4\", r['hac_lags']==int(np.floor(4*(2.4)**(2/9)))==4)\nopen('out/state/checks.md','w').write(\"# Verification checks (P4)\\n\\n- [PASS] clean re-run: deleted outputs, ran analysis.py twice, SHA-256 of results.json and table1.csv identical\\n\"+\"\\n\".join(c)+\"\\n\")\nprint(open('out/state/checks.md').read())\nEOF","description":"Run internal consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1472,"cache_read_input_tokens":20020,"output_tokens":1447,"output_tokens_details":{"thinking_tokens":31},"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":1472},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpgMYHTJU2s2qV9Kt38","requestRef":"f3f7e494-1dce-46a7-994b-be829b94a4b6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5fadbc2d-200a-4cda-8ee5-c669e298a784","timestamp":"2026-10-30T04:53:08.337Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}60{"parentUuid":"5fadbc2d-200a-4cda-8ee5-c669e298a784","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019WAusg6yZraLzT42XnQ4Dy","type":"tool_result","content":"# Verification checks (P4)\n\n- [PASS] clean re-run: deleted outputs, ran analysis.py twice, SHA-256 of results.json and table1.csv identical\n- [PASS] n_sub1+n_sub2==n_analysed==240\n- [PASS] n_sub1==96, n_sub2==144\n- [PASS] sample_start=1960-01-01, sample_end=2019-10-01\n- [PASS] exclusion ledger: 319 - removed = 240\n- [PASS] effect_se>0 and subperiod SEs>0\n- [PASS] CI contains estimate\n- [PASS] CI = beta +/- 1.96*se\n- [PASS] model_metric < baseline_metric\n- [PASS] R2 identity 1-(model/baseline)^2 == r_squared\n- [PASS] SSR_pooled >= SSR1+SSR2\n- [PASS] Chow F recomputed from SSRs with df (2,236)\n- [PASS] stability_conclusion consistent with p\n- [PASS] conclusion consistent with CI\n- [PASS] table1 full row matches results\n- [PASS] table1 has 3 rows and required columns\n- [PASS] magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 in levels-of-gap form; difference form typically -0.2 to -0.4)\n- [PASS] hac_lags=floor(4*(240/100)^(2/9))=4","is_error":false}]},"uuid":"0edd0372-d4d2-4611-a395-4e9804b4c5d0","timestamp":"2026-10-30T04:53:08.636Z","toolUseResult":{"stdout":"# Verification checks (P4)\n\n- [PASS] clean re-run: deleted outputs, ran analysis.py twice, SHA-256 of results.json and table1.csv identical\n- [PASS] n_sub1+n_sub2==n_analysed==240\n- [PASS] n_sub1==96, n_sub2==144\n- [PASS] sample_start=1960-01-01, sample_end=2019-10-01\n- [PASS] exclusion ledger: 319 - removed = 240\n- [PASS] effect_se>0 and subperiod SEs>0\n- [PASS] CI contains estimate\n- [PASS] CI = beta +/- 1.96*se\n- [PASS] model_metric < baseline_metric\n- [PASS] R2 identity 1-(model/baseline)^2 == r_squared\n- [PASS] SSR_pooled >= SSR1+SSR2\n- [PASS] Chow F recomputed from SSRs with df (2,236)\n- [PASS] stability_conclusion consistent with p\n- [PASS] conclusion consistent with CI\n- [PASS] table1 full row matches results\n- [PASS] table1 has 3 rows and required columns\n- [PASS] magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 in levels-of-gap form; difference form typically -0.2 to -0.4)\n- [PASS] hac_lags=floor(4*(240/100)^(2/9))=4","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5fadbc2d-200a-4cda-8ee5-c669e298a784","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"0edd0372-d4d2-4611-a395-4e9804b4c5d0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpgMq9Mx8Hae7vU6P1a","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Xxt1pxZrbUX3CZPwALRVT3","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0177/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":1472,"cache_read_input_tokens":20020,"output_tokens":1447,"output_tokens_details":{"thinking_tokens":31},"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":1472},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpgMYHTJU2s2qV9Kt38","requestRef":"f3f7e494-1dce-46a7-994b-be829b94a4b6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7b1b1287-b611-4fbc-ad82-4b6e7af2465a","timestamp":"2026-10-30T04:53:08.760Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"7b1b1287-b611-4fbc-ad82-4b6e7af2465a","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Xxt1pxZrbUX3CZPwALRVT3","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"be9cc8d0-a6d2-42c8-a730-ddb24ca0ca73","timestamp":"2026-10-30T04:53:08.769Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":71315,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"7b1b1287-b611-4fbc-ad82-4b6e7af2465a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}63{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"6e59a41168397ba3a0547f14fb190714df1ffe5cf3cd1fac78873af4ead83dde","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019WAusg6yZraLzT42XnQ4Dy","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); t=pd.read_csv('out/table1.csv'); e=pd.read_csv('out/exclusions.csv')\nc=[]\ndef chk(name,ok): c.append(f\"- [{'PASS' if ok else 'FAIL'}] {name}\")\nchk(\"n_sub1+n_sub2==n_analysed==240\", r['n_sub1']+r['n_sub2']==r['n_analysed']==240)\nchk(\"n_sub1==96, n_sub2==144\", (r['n_sub1'],r['n_sub2'])==(96,144))\nchk(\"sample_start=1960-01-01, sample_end=2019-10-01\", (r['sample_start'],r['sample_end'])==('1960-01-01','2019-10-01'))\nchk(\"exclusion ledger: 319 - removed = 240\", 319-e.n_removed.sum()==r['n_analysed'])\nchk(\"effect_se>0 and subperiod SEs>0\", r['effect_se']>0 and (t.slope_se>0).all())\nchk(\"CI contains estimate\", r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'])\nchk(\"CI = beta +/- 1.96*se\", abs(r['effect_ci_high']-r['effect_estimate']-1.959964*r['effect_se'])<1e-5)\nchk(\"model_metric < baseline_metric\", r['model_metric']<r['baseline_metric'])\nchk(\"R2 identity 1-(model/baseline)^2 == r_squared\", abs(1-(r['model_metric']/r['baseline_metric'])**2-r['r_squared'])<1e-10)\nchk(\"SSR_pooled >= SSR1+SSR2\", 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)\nchk(\"Chow F recomputed from SSRs with df (2,236)\", abs(F-r['chow_f_stat'])<1e-10)\nchk(\"stability_conclusion consistent with p\", (r['chow_p_value']<0.05)==(r['stability_conclusion']=='unstable'))\nchk(\"conclusion consistent with CI\", r['conclusion']=='negative_effect' and r['effect_ci_high']<0)\nchk(\"table1 full row matches results\", np.isclose(t.slope[0],r['effect_estimate']) and np.isclose(t.slope_se[0],r['effect_se']) and np.isclose(t.intercept[0],r['intercept']))\nchk(\"table1 has 3 rows and required columns\", len(t)==3 and list(t.columns)==['period','n','intercept','slope','slope_se'])\nchk(\"magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 in levels-of-gap form; difference form typically -0.2 to -0.4)\", -0.6<r['effect_estimate']<-0.1)\nchk(\"hac_lags=floor(4*(240/100)^(2/9))=4\", r['hac_lags']==int(np.floor(4*(2.4)**(2/9)))==4)\nopen('out/state/checks.md','w').write(\"# Verification checks (P4)\\n\\n- [PASS] clean re-run: deleted outputs, ran analysis.py twice, SHA-256 of results.json and table1.csv identical\\n\"+\"\\n\".join(c)+\"\\n\")\nprint(open('out/state/checks.md').read())\nEOF","description":"Run internal consistency checks"}},{"type":"tool_use","id":"toolu_01Xxt1pxZrbUX3CZPwALRVT3","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0177/out/figure1.png"}}]}}64{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"1dd957afa39de7b6847ecf88328266677f6c27596b0fe9f44d6933c7e71c5a05","message":{"role":"user","content":[{"tool_use_id":"toolu_019WAusg6yZraLzT42XnQ4Dy","type":"tool_result","content":"# Verification checks (P4)\n\n- [PASS] clean re-run: deleted outputs, ran analysis.py twice, SHA-256 of results.json and table1.csv identical\n- [PASS] n_sub1+n_sub2==n_analysed==240\n- [PASS] n_sub1==96, n_sub2==144\n- [PASS] sample_start=1960-01-01, sample_end=2019-10-01\n- [PASS] exclusion ledger: 319 - removed = 240\n- [PASS] effect_se>0 and subperiod SEs>0\n- [PASS] CI contains estimate\n- [PASS] CI = beta +/- 1.96*se\n- [PASS] model_metric < baseline_metric\n- [PASS] R2 identity 1-(model/baseline)^2 == r_squared\n- [PASS] SSR_pooled >= SSR1+SSR2\n- [PASS] Chow F recomputed from SSRs with df (2,236)\n- [PASS] stability_conclusion consistent with p\n- [PASS] conclusion consistent with CI\n- [PASS] table1 full row matches results\n- [PASS] table1 has 3 rows and required columns\n- [PASS] magnitude plausible: beta in [-0.6,-0.1] (literature ~ -0.3 to -0.5 in levels-of-gap form; difference form typically -0.2 to -0.4)\n- [PASS] hac_lags=floor(4*(240/100)^(2/9))=4","is_error":false},{"tool_use_id":"toolu_01Xxt1pxZrbUX3CZPwALRVT3","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]}}65{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"dd244748-0062-4f7b-85f9-1a028796951e","timestamp":"2026-10-30T04:53:08.774Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"f3f7e494-1dce-46a7-994b-be829b94a4b6","keep":18,"tail":["6e59a41168397ba3a0547f14fb190714df1ffe5cf3cd1fac78873af4ead83dde","1dd957afa39de7b6847ecf88328266677f6c27596b0fe9f44d6933c7e71c5a05"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"db50c367b48d408e709c02a432d846aaa1f7589c30494bcf2af85cee99e89b3a"}66{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"be9cc8d0-a6d2-42c8-a730-ddb24ca0ca73","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}67{"type":"atis-latch","atis":"","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}68{"parentUuid":"be9cc8d0-a6d2-42c8-a730-ddb24ca0ca73","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXphEV9oVnHsUuUUZEnk","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":2660,"cache_read_input_tokens":21492,"output_tokens":4412,"output_tokens_details":{"thinking_tokens":96},"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":2660},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1000,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXphEEnGWaNUoDc8JWN9","requestRef":"dd244748-0062-4f7b-85f9-1a028796951e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5176bdcd-0d7f-49b4-a5a0-b0123eff22d2","timestamp":"2026-10-30T04:53:11.295Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}69{"parentUuid":"5176bdcd-0d7f-49b4-a5a0-b0123eff22d2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXphEV9oVnHsUuUUZEnk","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017v4cQK2jFG2DikUx7seCGk","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 | rows (excl. header) | cols | range | notes |\n|---|---|---|---|---|---|\n| data/GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1) | 1947-01-01 .. 2026-07-01, quarterly | bn chained 2017 $, SAAR; no missing, no duplicate dates, no gaps; min 2172.4, max 24611.1 |\n| data/UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE) | 1948-01-01 .. 2026-09-01, monthly | percent, SA; one empty value at 2025-10-01 (outside window); no duplicates, no gaps; min 2.5, max 14.8 (2020-04) |\n| data/README.md | 7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 | – | – | – | provenance |\n\nInformation availability: both files contain post-2019Q4 data (incl. COVID quarters). Handling: hard window filter 1960Q1–2019Q4 in analysis.py (1959Q4 levels used only for first differences); assertion that max date ≤ 2019-10-01. Incomplete UNRATE quarters (count<3) are set to missing (affects only 2025Q4, outside window). gate_spec.json and bundle.json are not listed as inputs and were not used.\nVintage: GDPC1 is the 2026 vintage (revised), not real-time — acceptable since the question is historical, noted as limitation.\nEOF\ncat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960–2019 (task F6-conf-03)\n\n## Question\nHow strongly do quarterly changes in the US unemployment rate (Δu_t, pp) respond to quarterly real GDP growth (g_t = 100·Δln GDPC1, % q/q, not annualised), in Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, and is the relation stable between 1960Q1–1983Q4 and 1984Q1–2019Q4?\n\n## Data and exclusions\n- `data/GDPC1.csv` (319 rows, 1947Q1–2026Q3) and `data/UNRATE.csv` (945 rows, 1948-01–2026-09) (`n_input_rows`); SHA-256 checksums match `data/README.md` (see `out/state/data_audit.md`).\n- Quarterly u_t = mean of the three monthly UNRATE values; quarters with fewer than 3 months are set to missing. Only one month is missing (2025-10), and it lies outside the sample (`data_issues`).\n- Exclusions (`out/exclusions.csv`): the 319 quarters were restricted to 1960Q1–2019Q4 (79 removed; 1959Q4 levels are used only to form the 1960Q1 differences). No missing values were found inside the window, which leaves `n_analysed` = 240 quarters, `n_sub1` = 96 and `n_sub2` = 144. No data after 2019Q4 enters any estimate, and the script asserts this.\n\n## Method\n- Baseline: a mean-only prediction of Δu, scored by RMSE (`baseline_metric`).\n- Main model: OLS of Δu_t on a constant and g_t over the full sample (`effect_estimate`, `intercept`), scored by in-sample residual RMSE (`model_metric`).\n- Uncertainty: Newey–West HAC standard error with a Bartlett kernel. The lag is set by the rule floor(4·(n/100)^{2/9}) = 4 (`hac_lags`). The 95% CI is β ± 1.96·SE (normal approximation).\n- Stability: separate OLS fits on each subperiod (`beta_sub1`, `beta_sub2`; subperiod slope SEs in `table1.csv` are also HAC, with lags 3 and 4). A classical Chow SSR F-test of equal (α, β), with F(2, 236) (`chow_f_stat`, `chow_p_value`).\n- Supplementary checks I added (`supp_*` keys): a HAC-robust Wald test using subperiod-2 dummy and interaction terms, run jointly and for the slope alone, plus a residual-variance ratio test.\n- There is no randomness (`random_seed` = null). `out/analysis.py` regenerates every output deterministically.\n\n## Results\n| period | n | α | β | HAC SE(β) |\n|---|---|---|---|---|\n| full 1960Q1–2019Q4 | 240 | 0.184 | −0.256 | 0.036 |\n| 1960Q1–1983Q4 | 96 | 0.254 | −0.259 | 0.039 |\n| 1984Q1–2019Q4 | 144 | 0.152 | −0.273 | 0.069 |\n(Source: `out/table1.csv`, and `intercept`, `effect_estimate`, `effect_se`, `beta_sub1`, `beta_sub2`, `intercept_sub1`, `intercept_sub2`, `se_sub1_hac`, `se_sub2_hac`.)\n\n- **Coefficient:** β = −0.256 (`effect_estimate`). A 1 percentage-point higher quarterly real GDP growth (about 4 pp annualised) goes with a quarter-on-quarter fall of about 0.26 pp in the unemployment rate. The implied growth rate that keeps unemployment unchanged is −α/β ≈ 0.72% per quarter (from `intercept` and `effect_estimate`).\n- **Fit:** the residual RMSE is 0.250 pp (`model_metric`), against 0.325 pp for the mean-only baseline (`baseline_metric`); R² = 0.41 (`r_squared`).\n- **Conclusion code:** `negative_effect` (`conclusion`), because the 95% CI lies entirely below zero.\n- **Stability:** the Chow test rejects equality of (α, β): F = 6.09, p = 0.0026 (`chow_f_stat`, `chow_p_value`), so `stability_conclusion` = `unstable`. The rejection comes from the intercept, not the slope:\n - The subperiod slopes are almost identical: −0.259 vs −0.273 (`beta_sub1`, `beta_sub2`).\n - The HAC Wald test of slope equality alone gives p = 0.85 (`supp_hac_wald_slope_p`).\n - The intercept falls from 0.254 to 0.152 (`intercept_sub1`, `intercept_sub2`).\n - The joint HAC Wald test also rejects, p = 0.005 (`supp_hac_wald_joint_p`).\n- Figure: `out/figure1.png` shows the scatter of Δu against g with the two subperiod fitted lines.\n\n## Uncertainty\n- HAC SE(β) = 0.036 (`effect_se`); 95% CI [−0.326, −0.185] (`effect_ci_low`, `effect_ci_high`). The HAC SE is about 1.8 times the classical OLS SE of 0.020 (`ols_classical_se`).\n- The SE barely depends on the lag choice: 0.029 at lag 0 and 0.034–0.037 at lags 2–12 (`sensitivity_effect_se_by_lag`). The sign conclusion holds at every lag tried.\n- The subperiod-2 slope is estimated less precisely (HAC SE 0.069, `se_sub2_hac`).\n\n## Limitations and open issues\n- **Validity of the classical Chow test.** It assumes homoskedastic, serially uncorrelated errors with the same variance in both subperiods. That assumption fails here: the residual variance in subperiod 1 is about 1.63 times that in subperiod 2, and a variance-ratio F-test gives p = 0.009 (`supp_resid_var_ratio_sub1_over_sub2`, `supp_var_ratio_F_p_two_sided`). The classical p-value (`chow_p_value`) may therefore be miscalibrated. The HAC Wald test (`supp_hac_wald_joint_p` = 0.005) supports the same rejection, which makes it more credible, but neither test allows for unequal variances explicitly in the classical form required by the task.\n- **What \"unstable\" means.** The instability is in the intercept, i.e. the growth rate that keeps unemployment unchanged, which reflects trend productivity and labour-force growth. There is no evidence that the Okun slope itself changed. Reading `unstable` as \"the output–unemployment sensitivity changed\" would be wrong.\n- **Fixed, chosen break date.** The 1984Q1 break was imposed, not estimated. A Chow test at a chosen date says nothing about whether this is the best break date, or whether there are several breaks or gradual drift. No sup-F or rolling analysis was done (it is outside the task).\n- **Reduced form, not causal.** β is a contemporaneous association. Omitted dynamics, such as lagged growth, would change it, and simultaneity rules out a causal reading. Residual serial correlation is handled only through the HAC SEs; the model was not re-specified.\n- **Data vintage.** GDPC1 is the 2026 vintage. Revised data can differ from real-time data, and the BLS household-survey methodology changed over the period (e.g. 1994). Neither was examined.\n- **Inference approximations.** The HAC lag uses a rule of thumb; small-sample HAC bias was not corrected beyond the degrees-of-freedom correction, and the CI uses a normal critical value. Large recession outliers, such as 1980 and 2008–09, were not tested for influence.\n- **What would invalidate the result.** A misaligned quarterly average, data after 2019 leaking into the sample, or a non-stationary relation. The first two were checked (`out/state/checks.md`); the third was not tested formally.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The full-sample Okun coefficient is about -0.26 pp per 1% quarterly real GDP growth, and its 95% HAC confidence interval lies below zero (negative_effect).\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"hac_lags\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Reduced-form contemporaneous association; HAC lag chosen by rule of thumb, but the SE is insensitive across lags 0-12.\"},\n {\"id\":\"C2\",\"text\":\"Output growth explains a substantial share of the variance of the change in unemployment: residual RMSE 0.250 pp vs a mean-only baseline of 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% (unstable).\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\"],\"status\":\"supported\",\"caveat\":\"The classical test assumes equal error variances, which are rejected (variance-ratio p≈0.009); a HAC Wald test gives the same conclusion.\"},\n {\"id\":\"C4\",\"text\":\"The instability comes from the intercept; the subperiod slopes are almost identical and their equality is not rejected.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"intercept_sub1\",\"intercept_sub2\",\"supp_hac_wald_slope_p\",\"supp_hac_wald_joint_p\"],\"status\":\"supported\",\"caveat\":\"Supplementary test, not required by the task; the break date is imposed.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor c in json.load(open('out/claims.json')): assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok', -r['intercept']/r['effect_estimate'], r['effect_se']/r['ols_classical_se'])\"","description":"Write audit, report, claims; validate claim keys"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2660,"cache_read_input_tokens":21492,"output_tokens":4412,"output_tokens_details":{"thinking_tokens":96},"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":2660},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXphEEnGWaNUoDc8JWN9","requestRef":"dd244748-0062-4f7b-85f9-1a028796951e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"15b65752-58eb-426f-9f66-88bba4d160e9","timestamp":"2026-10-30T04:53:49.088Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}70{"parentUuid":"15b65752-58eb-426f-9f66-88bba4d160e9","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017v4cQK2jFG2DikUx7seCGk","type":"tool_result","content":"claims keys ok 0.7209211099660549 1.8028415073097532","is_error":false}]},"uuid":"ce3444f2-a8a3-4768-9c40-c2e1a687752e","timestamp":"2026-10-30T04:53:49.167Z","toolUseResult":{"stdout":"claims keys ok 0.7209211099660549 1.8028415073097532","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"15b65752-58eb-426f-9f66-88bba4d160e9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}71{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"0cdc3ee204dd583c766d95757d6ff63f9994f54a35efbfa210255612870b69e6","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_017v4cQK2jFG2DikUx7seCGk","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 | rows (excl. header) | cols | range | notes |\n|---|---|---|---|---|---|\n| data/GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1) | 1947-01-01 .. 2026-07-01, quarterly | bn chained 2017 $, SAAR; no missing, no duplicate dates, no gaps; min 2172.4, max 24611.1 |\n| data/UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE) | 1948-01-01 .. 2026-09-01, monthly | percent, SA; one empty value at 2025-10-01 (outside window); no duplicates, no gaps; min 2.5, max 14.8 (2020-04) |\n| data/README.md | 7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 | – | – | – | provenance |\n\nInformation availability: both files contain post-2019Q4 data (incl. COVID quarters). Handling: hard window filter 1960Q1–2019Q4 in analysis.py (1959Q4 levels used only for first differences); assertion that max date ≤ 2019-10-01. Incomplete UNRATE quarters (count<3) are set to missing (affects only 2025Q4, outside window). gate_spec.json and bundle.json are not listed as inputs and were not used.\nVintage: GDPC1 is the 2026 vintage (revised), not real-time — acceptable since the question is historical, noted as limitation.\nEOF\ncat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960–2019 (task F6-conf-03)\n\n## Question\nHow strongly do quarterly changes in the US unemployment rate (Δu_t, pp) respond to quarterly real GDP growth (g_t = 100·Δln GDPC1, % q/q, not annualised), in Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, and is the relation stable between 1960Q1–1983Q4 and 1984Q1–2019Q4?\n\n## Data and exclusions\n- `data/GDPC1.csv` (319 rows, 1947Q1–2026Q3) and `data/UNRATE.csv` (945 rows, 1948-01–2026-09) (`n_input_rows`); SHA-256 checksums match `data/README.md` (see `out/state/data_audit.md`).\n- Quarterly u_t = mean of the three monthly UNRATE values; quarters with fewer than 3 months are set to missing. Only one month is missing (2025-10), and it lies outside the sample (`data_issues`).\n- Exclusions (`out/exclusions.csv`): the 319 quarters were restricted to 1960Q1–2019Q4 (79 removed; 1959Q4 levels are used only to form the 1960Q1 differences). No missing values were found inside the window, which leaves `n_analysed` = 240 quarters, `n_sub1` = 96 and `n_sub2` = 144. No data after 2019Q4 enters any estimate, and the script asserts this.\n\n## Method\n- Baseline: a mean-only prediction of Δu, scored by RMSE (`baseline_metric`).\n- Main model: OLS of Δu_t on a constant and g_t over the full sample (`effect_estimate`, `intercept`), scored by in-sample residual RMSE (`model_metric`).\n- Uncertainty: Newey–West HAC standard error with a Bartlett kernel. The lag is set by the rule floor(4·(n/100)^{2/9}) = 4 (`hac_lags`). The 95% CI is β ± 1.96·SE (normal approximation).\n- Stability: separate OLS fits on each subperiod (`beta_sub1`, `beta_sub2`; subperiod slope SEs in `table1.csv` are also HAC, with lags 3 and 4). A classical Chow SSR F-test of equal (α, β), with F(2, 236) (`chow_f_stat`, `chow_p_value`).\n- Supplementary checks I added (`supp_*` keys): a HAC-robust Wald test using subperiod-2 dummy and interaction terms, run jointly and for the slope alone, plus a residual-variance ratio test.\n- There is no randomness (`random_seed` = null). `out/analysis.py` regenerates every output deterministically.\n\n## Results\n| period | n | α | β | HAC SE(β) |\n|---|---|---|---|---|\n| full 1960Q1–2019Q4 | 240 | 0.184 | −0.256 | 0.036 |\n| 1960Q1–1983Q4 | 96 | 0.254 | −0.259 | 0.039 |\n| 1984Q1–2019Q4 | 144 | 0.152 | −0.273 | 0.069 |\n(Source: `out/table1.csv`, and `intercept`, `effect_estimate`, `effect_se`, `beta_sub1`, `beta_sub2`, `intercept_sub1`, `intercept_sub2`, `se_sub1_hac`, `se_sub2_hac`.)\n\n- **Coefficient:** β = −0.256 (`effect_estimate`). A 1 percentage-point higher quarterly real GDP growth (about 4 pp annualised) goes with a quarter-on-quarter fall of about 0.26 pp in the unemployment rate. The implied growth rate that keeps unemployment unchanged is −α/β ≈ 0.72% per quarter (from `intercept` and `effect_estimate`).\n- **Fit:** the residual RMSE is 0.250 pp (`model_metric`), against 0.325 pp for the mean-only baseline (`baseline_metric`); R² = 0.41 (`r_squared`).\n- **Conclusion code:** `negative_effect` (`conclusion`), because the 95% CI lies entirely below zero.\n- **Stability:** the Chow test rejects equality of (α, β): F = 6.09, p = 0.0026 (`chow_f_stat`, `chow_p_value`), so `stability_conclusion` = `unstable`. The rejection comes from the intercept, not the slope:\n - The subperiod slopes are almost identical: −0.259 vs −0.273 (`beta_sub1`, `beta_sub2`).\n - The HAC Wald test of slope equality alone gives p = 0.85 (`supp_hac_wald_slope_p`).\n - The intercept falls from 0.254 to 0.152 (`intercept_sub1`, `intercept_sub2`).\n - The joint HAC Wald test also rejects, p = 0.005 (`supp_hac_wald_joint_p`).\n- Figure: `out/figure1.png` shows the scatter of Δu against g with the two subperiod fitted lines.\n\n## Uncertainty\n- HAC SE(β) = 0.036 (`effect_se`); 95% CI [−0.326, −0.185] (`effect_ci_low`, `effect_ci_high`). The HAC SE is about 1.8 times the classical OLS SE of 0.020 (`ols_classical_se`).\n- The SE barely depends on the lag choice: 0.029 at lag 0 and 0.034–0.037 at lags 2–12 (`sensitivity_effect_se_by_lag`). The sign conclusion holds at every lag tried.\n- The subperiod-2 slope is estimated less precisely (HAC SE 0.069, `se_sub2_hac`).\n\n## Limitations and open issues\n- **Validity of the classical Chow test.** It assumes homoskedastic, serially uncorrelated errors with the same variance in both subperiods. That assumption fails here: the residual variance in subperiod 1 is about 1.63 times that in subperiod 2, and a variance-ratio F-test gives p = 0.009 (`supp_resid_var_ratio_sub1_over_sub2`, `supp_var_ratio_F_p_two_sided`). The classical p-value (`chow_p_value`) may therefore be miscalibrated. The HAC Wald test (`supp_hac_wald_joint_p` = 0.005) supports the same rejection, which makes it more credible, but neither test allows for unequal variances explicitly in the classical form required by the task.\n- **What \"unstable\" means.** The instability is in the intercept, i.e. the growth rate that keeps unemployment unchanged, which reflects trend productivity and labour-force growth. There is no evidence that the Okun slope itself changed. Reading `unstable` as \"the output–unemployment sensitivity changed\" would be wrong.\n- **Fixed, chosen break date.** The 1984Q1 break was imposed, not estimated. A Chow test at a chosen date says nothing about whether this is the best break date, or whether there are several breaks or gradual drift. No sup-F or rolling analysis was done (it is outside the task).\n- **Reduced form, not causal.** β is a contemporaneous association. Omitted dynamics, such as lagged growth, would change it, and simultaneity rules out a causal reading. Residual serial correlation is handled only through the HAC SEs; the model was not re-specified.\n- **Data vintage.** GDPC1 is the 2026 vintage. Revised data can differ from real-time data, and the BLS household-survey methodology changed over the period (e.g. 1994). Neither was examined.\n- **Inference approximations.** The HAC lag uses a rule of thumb; small-sample HAC bias was not corrected beyond the degrees-of-freedom correction, and the CI uses a normal critical value. Large recession outliers, such as 1980 and 2008–09, were not tested for influence.\n- **What would invalidate the result.** A misaligned quarterly average, data after 2019 leaking into the sample, or a non-stationary relation. The first two were checked (`out/state/checks.md`); the third was not tested formally.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The full-sample Okun coefficient is about -0.26 pp per 1% quarterly real GDP growth, and its 95% HAC confidence interval lies below zero (negative_effect).\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"hac_lags\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Reduced-form contemporaneous association; HAC lag chosen by rule of thumb, but the SE is insensitive across lags 0-12.\"},\n {\"id\":\"C2\",\"text\":\"Output growth explains a substantial share of the variance of the change in unemployment: residual RMSE 0.250 pp vs a mean-only baseline of 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% (unstable).\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\"],\"status\":\"supported\",\"caveat\":\"The classical test assumes equal error variances, which are rejected (variance-ratio p≈0.009); a HAC Wald test gives the same conclusion.\"},\n {\"id\":\"C4\",\"text\":\"The instability comes from the intercept; the subperiod slopes are almost identical and their equality is not rejected.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"intercept_sub1\",\"intercept_sub2\",\"supp_hac_wald_slope_p\",\"supp_hac_wald_joint_p\"],\"status\":\"supported\",\"caveat\":\"Supplementary test, not required by the task; the break date is imposed.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor c in json.load(open('out/claims.json')): assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok', -r['intercept']/r['effect_estimate'], r['effect_se']/r['ols_classical_se'])\"","description":"Write audit, report, claims; validate claim keys"}}]}}72{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"1890a7c8-32d8-4454-8b4e-d2df9f18bb40","timestamp":"2026-10-30T04:53:49.175Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"dd244748-0062-4f7b-85f9-1a028796951e","keep":20,"tail":["0cdc3ee204dd583c766d95757d6ff63f9994f54a35efbfa210255612870b69e6","a03dcbc421aeca77a87ec6428c117bbb13c312c5f2787e604aa32eaf6f54dcc7"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"24be2a0b05a588c1a1541369e37d22ed291a1094d7cf8ef4ad7e1f16aa0a7a49"}73{"parentUuid":"ce3444f2-a8a3-4768-9c40-c2e1a687752e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpkDFKbcJ24eYbvrGwe","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LEMpCPwEH1K5xpErQHzXZ5","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of all inputs computed and match README\",\"row/col counts, date ranges, gaps, duplicates, missing values checked (1 missing UNRATE month 2025-10, outside window)\",\"exclusions.csv: 319-79=240\"],\"notes\":\"post-2019 data excluded by hard filter + assertion\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) = 0.3247 computed on same 240-quarter sample\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png, exclusions.csv\",\"no randomness (random_seed null)\",\"Agg backend\"],\"notes\":\"HAC lag 4 via floor(4(n/100)^(2/9)); supplementary HAC Wald + variance-ratio tests added\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean rerun x2: identical SHA-256 of results.json and table1.csv\",\"17 internal consistency checks all PASS (out/state/checks.md)\",\"figure inspected visually\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md with six required sections in order, keys cited\",\"claims.json keys all exist in results.json\"],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: data audited, hashes match; 2025-10 UNRATE missing (outside window).\n- 2026-10-30 P2/P3 passed: analysis.py written; HAC lag 4; decided to add supplementary HAC Wald/variance-ratio tests because classical Chow assumes equal variances.\n- 2026-10-30 P4 passed: deterministic rerun, all checks pass.\n- 2026-10-30 P5 passed: report and claims written. Task complete.\nEOF\nls out out/state","description":"Finalize phase ledger and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4441,"cache_read_input_tokens":24152,"output_tokens":785,"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":4441},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpkCxDGhVociuad8iWf","requestRef":"1890a7c8-32d8-4454-8b4e-d2df9f18bb40","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7c2f355a-a78b-46dc-bc6b-8ae77fdb5114","timestamp":"2026-10-30T04:53:55.869Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}74{"parentUuid":"7c2f355a-a78b-46dc-bc6b-8ae77fdb5114","isSidechain":false,"promptId":"4cf67aea-abba-4a84-8406-86b64a9299e6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LEMpCPwEH1K5xpErQHzXZ5","type":"tool_result","content":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json","is_error":false}]},"uuid":"387ea48e-a7cf-4595-99ef-0b2861c776f2","timestamp":"2026-10-30T04:53:55.911Z","toolUseResult":{"stdout":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7c2f355a-a78b-46dc-bc6b-8ae77fdb5114","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}75{"type":"api-request-blob","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","hash":"aa1710556acd8574ffc1740026f219fd1dca6dc24e2945ce4435f8b6eeca875f","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01LEMpCPwEH1K5xpErQHzXZ5","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of all inputs computed and match README\",\"row/col counts, date ranges, gaps, duplicates, missing values checked (1 missing UNRATE month 2025-10, outside window)\",\"exclusions.csv: 319-79=240\"],\"notes\":\"post-2019 data excluded by hard filter + assertion\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) = 0.3247 computed on same 240-quarter sample\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png, exclusions.csv\",\"no randomness (random_seed null)\",\"Agg backend\"],\"notes\":\"HAC lag 4 via floor(4(n/100)^(2/9)); supplementary HAC Wald + variance-ratio tests added\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean rerun x2: identical SHA-256 of results.json and table1.csv\",\"17 internal consistency checks all PASS (out/state/checks.md)\",\"figure inspected visually\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md with six required sections in order, keys cited\",\"claims.json keys all exist in results.json\"],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: data audited, hashes match; 2025-10 UNRATE missing (outside window).\n- 2026-10-30 P2/P3 passed: analysis.py written; HAC lag 4; decided to add supplementary HAC Wald/variance-ratio tests because classical Chow assumes equal variances.\n- 2026-10-30 P4 passed: deterministic rerun, all checks pass.\n- 2026-10-30 P5 passed: report and claims written. Task complete.\nEOF\nls out out/state","description":"Finalize phase ledger and log"}}]}}76{"type":"api-request","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","id":"8d4d856d-9e5b-4f2b-be3f-8d0dff166e10","timestamp":"2026-10-30T04:53:55.915Z","version":"2.1.314","querySource":"sdk","shapeHash":"aede631846d9b63faea20be6486a5aebf4836803a4f365f2e4a4ba96da8f8761","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":"1890a7c8-32d8-4454-8b4e-d2df9f18bb40","keep":22,"tail":["aa1710556acd8574ffc1740026f219fd1dca6dc24e2945ce4435f8b6eeca875f","13dd09a37620153aadfdd58fe6ae6d12682427a45dd061e7a2341cc0d18dd0d7"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e8ab33102b7686c713789f75856b2a5d04885cdde23d3ac44c7f70836a4f7bdc"}77{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"387ea48e-a7cf-4595-99ef-0b2861c776f2","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}78{"type":"atis-latch","atis":"","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}79{"parentUuid":"387ea48e-a7cf-4595-99ef-0b2861c776f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpki3gcsXBT6g2QK6Z7","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":864,"cache_read_input_tokens":28593,"output_tokens":1131,"output_tokens_details":{"thinking_tokens":45},"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":864},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":7789,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpkhm5SPFvFvVQrxc1D","requestRef":"8d4d856d-9e5b-4f2b-be3f-8d0dff166e10","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b145ed09-4b7b-4f91-bba5-901e8466437a","timestamp":"2026-10-30T04:54:05.019Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}80{"parentUuid":"b145ed09-4b7b-4f91-bba5-901e8466437a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpki3gcsXBT6g2QK6Z7","type":"message","role":"assistant","content":[{"type":"text","text":"I've finished the task: real GDP growth is clearly linked to falls in US unemployment over 1960Q1–2019Q4. The classical Chow test says the relationship is unstable, but the instability is in the intercept, not the Okun coefficient itself. All required files are written, the script gives identical results when re-run from scratch, and all internal consistency checks pass.\n\n**Main results** (240 quarters; 96 in 1960Q1–1983Q4 and 144 in 1984Q1–2019Q4):\n\n| Quantity | Value |\n|---|---|\n| Okun coefficient β (full sample) | −0.256 pp per 1% quarterly growth |\n| Standard error (Newey–West, 4 lags) | 0.036 |\n| 95% confidence interval | [−0.326, −0.185] |\n| Error of the fitted model | 0.250 pp |\n| Error of the baseline (always predicting the average change) | 0.325 pp |\n| β, 1960Q1–1983Q4 | −0.259 |\n| β, 1984Q1–2019Q4 | −0.273 |\n| Chow test | F = 6.09, p = 0.0026 |\n\n- **Effect:** a 1-point higher quarterly growth rate goes with about a 0.26-point fall in unemployment that quarter. The interval lies entirely below zero, so the conclusion code is `negative_effect`.\n- **Lag choice:** the standard error barely moves across lags 0 to 12, so the sign conclusion holds whichever lag is used.\n- **Stability:** the Chow test rejects equal intercept and slope across the two subperiods, so `stability_conclusion` is `unstable`.\n- **Source of the instability:** the two slopes are almost the same. The difference is in the intercept, which drops from 0.254 to 0.152, meaning the growth rate that keeps unemployment unchanged is lower after 1984.\n\n**Extra checks I added (not required by the task):**\n- A robust test of whether the slope alone differs between subperiods gives p = 0.85, so there is no evidence the slope changed.\n- The same robust test on intercept and slope together gives p = 0.005, agreeing with the Chow test.\n\n**Limitations:**\n- **Chow test assumption:** the classical test assumes both subperiods have equally noisy errors. They don't: the earlier period's residual variance is about 1.6 times the later one's (p = 0.009). The Chow p-value may therefore be off, though the robust test backs up the rejection.\n- **Fixed break date:** 1984Q1 was imposed by the task, not estimated, and I didn't look for other or gradual breaks.\n- **Not causal:** β is a same-quarter association.\n- **Revised data:** GDP is the 2026 revised series, not what was known at the time.\n\n**Data:** one monthly unemployment value is missing (October 2025). It falls outside the sample, so nothing was dropped or filled in inside 1960–2019. No data after 2019Q4 enters any estimate, and the script checks this.\n\nFiles are in `out/` (state notes, checks and the run log are in `out/state/`):\n- `results.json`\n- `report.md`\n- `analysis.py`\n- `table1.csv`\n- `figure1.png`\n- `claims.json`\n- `exclusions.csv`"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":864,"cache_read_input_tokens":28593,"output_tokens":1131,"output_tokens_details":{"thinking_tokens":45},"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":864},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpkhm5SPFvFvVQrxc1D","requestRef":"8d4d856d-9e5b-4f2b-be3f-8d0dff166e10","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d22c8bd7-e34f-4663-801e-92d16c83eeaf","timestamp":"2026-10-30T04:54:08.131Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0177","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","version":"2.1.314","gitBranch":"HEAD"}81{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d22c8bd7-e34f-4663-801e-92d16c83eeaf","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1"}82{"type":"cost-state","sessionId":"c9108923-2d23-4b68-98bc-95bf42f649a1","totalCostUSD":0.5556186,"totalAPIDuration":159362,"totalAPIDurationWithoutRetries":159353,"totalToolDuration":4629,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":163878,"startTime":1793335884260,"modelUsage":{"claude-opus-5-5":{"inputTokens":26,"outputTokens":19145,"thinkingTokens":794,"cacheReadInputTokens":164248,"cacheCreationInputTokens":27953,"cacheCreationEphemeral5mInputTokens":27953,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.5556186}},"hasUnknownModelCost":false}83