{"type":"atis-latch","atis":"","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:49:43.887Z","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","content":"Begin"} {"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:49:43.893Z","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":null,"isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":"Begin"},"uuid":"e3d536d7-05a4-4583-b73b-51e59b63c46e","timestamp":"2026-10-30T04:49:43.897Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-shape","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","timestamp":"2026-10-30T04:49:43.909Z","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/RC0174\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n\nSEPARATE REVIEW (additional)\n- After the gate passes, a separate reviewer session that has not seen your work in progress will examine `TASK.md` and everything under `out/` and may return a list of issues (file `out/review/review.json`). You will then be resumed once to address them: fix what is justified, explain in `out/report.md` (Limitations and open issues) what you disagree with, re-run the gate, and update `out/claims.json` and `out/state/phases.json`. The reviewer has no reference answers; its role is to challenge unsupported claims, violated information rules, unverified computations, and inconsistencies between your report and your results.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"2041877f-5ab1-4f8f-b48a-e0c0631e2a14","timestamp":"2026-10-30T04:49:43.909Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"246c423cfca597a8d43f9b75743037c4be3abcc4f206f189bee943b3c485f70c"} {"parentUuid":"e3d536d7-05a4-4583-b73b-51e59b63c46e","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"1a1a60f9-8c76-45f3-8d39-40b412899342","timestamp":"2026-10-30T04:49:43.901Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"1a1a60f9-8c76-45f3-8d39-40b412899342","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"78fdcde5-9139-45ff-bb9d-52566314bff5","timestamp":"2026-10-30T04:49:43.902Z","rendered":[{"content":"\nToday's date is 2026-10-30.\n"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"78fdcde5-9139-45ff-bb9d-52566314bff5","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 ","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"6244cddb-b3f8-4445-aef3-188666a1c6b9","timestamp":"2026-10-30T04:49:43.902Z","rendered":[{"content":"\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 \n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"tools-used","tools":["Bash"],"sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":"6244cddb-b3f8-4445-aef3-188666a1c6b9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSBuxLYvBr75fqXhYr","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":2811,"cache_read_input_tokens":1504,"output_tokens":136,"output_tokens_details":{"thinking_tokens":27},"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":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":512,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpSBeLpwvJeA4Q1XacC","requestRef":"2041877f-5ab1-4f8f-b48a-e0c0631e2a14","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"39421449-ba8c-474d-827a-bcdd7d03350c","timestamp":"2026-10-30T04:49:47.238Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"39421449-ba8c-474d-827a-bcdd7d03350c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSBuxLYvBr75fqXhYr","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SsBUuRoCC9EUyXPLoLh97P","name":"Bash","input":{"command":"cat TASK.md; ls -R | head -50; cat out/state/log.md 2>/dev/null","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":136,"output_tokens_details":{"thinking_tokens":27},"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":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSBeLpwvJeA4Q1XacC","requestRef":"2041877f-5ab1-4f8f-b48a-e0c0631e2a14","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"afeb4e2e-e821-4df8-9643-84986d2c565d","timestamp":"2026-10-30T04:49:47.910Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"afeb4e2e-e821-4df8-9643-84986d2c565d","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","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.\nbundle.json\ndata\ngate_spec.json\nTASK.md\n\n./data:\nGDPC1.csv\nREADME.md\nUNRATE.csv","is_error":true,"tool_use_id":"toolu_01SsBUuRoCC9EUyXPLoLh97P"}]},"uuid":"4af5114d-0ee0-48c2-89ed-cee3efed0304","timestamp":"2026-10-30T04:49:47.987Z","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.\nbundle.json\ndata\ngate_spec.json\nTASK.md\n\n./data:\nGDPC1.csv\nREADME.md\nUNRATE.csv","sandboxed":false,"sourceToolAssistantUUID":"afeb4e2e-e821-4df8-9643-84986d2c565d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"d7d6d31e9e1a467e10497dde322e302f1945c8f95295a173587bc65e9d30cab2","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01SsBUuRoCC9EUyXPLoLh97P","name":"Bash","input":{"command":"cat TASK.md; ls -R | head -50; cat out/state/log.md 2>/dev/null","description":"Read task and list workspace"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"d2aea879-cceb-485b-b650-e78cea7389da","timestamp":"2026-10-30T04:49:47.993Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"2041877f-5ab1-4f8f-b48a-e0c0631e2a14","keep":2,"tail":["d7d6d31e9e1a467e10497dde322e302f1945c8f95295a173587bc65e9d30cab2","edcd4b8387768c52cf73ef08b66e979719fffc0d1435385a50e7cac50bdd7155"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8b5735d69ab383fe400a29255843ebfa3f023c8ebfe767624983a8148d9f1c79"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"4af5114d-0ee0-48c2-89ed-cee3efed0304","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"atis-latch","atis":"","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":"4af5114d-0ee0-48c2-89ed-cee3efed0304","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSSfxmzyFig9fepZr3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VZL5WjRxGWkAc6CLfGsFUo","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json | head -80; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data and gate spec"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2655,"cache_read_input_tokens":4315,"output_tokens":143,"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":2655},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpSSNrPGuVTviQ8EZFR","requestRef":"d2aea879-cceb-485b-b650-e78cea7389da","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d4148f11-4083-4786-a954-be144e0bf4b7","timestamp":"2026-10-30T04:49:49.919Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"d4148f11-4083-4786-a954-be144e0bf4b7","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VZL5WjRxGWkAc6CLfGsFUo","type":"tool_result","content":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n{\n \"task_id\": \"F6-conf-03\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"sample_start\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"sample_end\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"n_sub1\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"n_sub2\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"intercept\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"hac_lags\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 data/GDPC1.csv\n 946 data/UNRATE.csv\n 1266 total\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 data/GDPC1.csv\n7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 data/README.md\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c data/UNRATE.csv","is_error":false}]},"uuid":"1d61db8d-34b8-4921-89a8-8b97525b603b","timestamp":"2026-10-30T04:49:49.970Z","toolUseResult":{"stdout":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n{\n \"task_id\": \"F6-conf-03\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"sample_start\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"sample_end\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"n_sub1\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"n_sub2\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"intercept\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"hac_lags\": {\n \"type\": \"integer\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n 320 data/GDPC1.csv\n 946 data/UNRATE.csv\n 1266 total\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 data/GDPC1.csv\n7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 data/README.md\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c data/UNRATE.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d4148f11-4083-4786-a954-be144e0bf4b7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"379cbd0e37f463d38627c656ffbb1f15c630fb6ad7175be4715b30b483fef85a","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01VZL5WjRxGWkAc6CLfGsFUo","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json | head -80; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data and gate spec"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"6b3a65e0-74da-403e-97af-2380020cd994","timestamp":"2026-10-30T04:49:49.974Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"d2aea879-cceb-485b-b650-e78cea7389da","keep":4,"tail":["379cbd0e37f463d38627c656ffbb1f15c630fb6ad7175be4715b30b483fef85a","1f7b13b6cc3f8c25fde0455e4d70fe3e4c96da2aa5e43e0294af10dbcab2849a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1065f5514d3618b98f32d03038030c11dc63dddc25375bac509e91c11f3034ec"} {"parentUuid":"1d61db8d-34b8-4921-89a8-8b97525b603b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSb6Uft5XwuuwB8JpY","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":1723,"cache_read_input_tokens":6970,"output_tokens":483,"output_tokens_details":{"thinking_tokens":101},"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":1723},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":639,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpSaq7Dw3bPq2iyBJ5U","requestRef":"6b3a65e0-74da-403e-97af-2380020cd994","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e950f71e-19ba-4cd8-abf9-367c18c64c66","timestamp":"2026-10-30T04:49:52.009Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e950f71e-19ba-4cd8-abf9-367c18c64c66","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSb6Uft5XwuuwB8JpY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_012g78bKmcX5jrBr6fy2bb1W","name":"Bash","input":{"command":"sed -n 80,400p gate_spec.json; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f in ['GDPC1','UNRATE']:\n d=pd.read_csv(f'data/{f}.csv',parse_dates=['observation_date'])\n print(f,d.shape,d.dtypes.to_dict(),d.isna().sum().to_dict(),d.observation_date.duplicated().sum())\n v=pd.to_numeric(d[f],errors='coerce'); print('nonnumeric',v.isna().sum(), d[v.isna()])\n fr='QS' if f=='GDPC1' else 'MS'\n full=pd.date_range(d.observation_date.min(),d.observation_date.max(),freq=fr); print('missing dates',sorted(set(full)-set(d.observation_date)))\n print(v.describe())\n\"","description":"Rest of gate spec; audit data anomalies"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1723,"cache_read_input_tokens":6970,"output_tokens":483,"output_tokens_details":{"thinking_tokens":101},"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":1723},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSaq7Dw3bPq2iyBJ5U","requestRef":"6b3a65e0-74da-403e-97af-2380020cd994","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7b22c866-e5ef-4da2-afd8-71d0410a76a5","timestamp":"2026-10-30T04:49:54.600Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"7b22c866-e5ef-4da2-afd8-71d0410a76a5","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_012g78bKmcX5jrBr6fy2bb1W","type":"tool_result","content":" \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"beta_sub1\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"beta_sub2\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"chow_f_stat\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"chow_p_value\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"stability_conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\",\n \"chronology\"\n ],\n \"ci_pairs\": [\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"chow_f_stat\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [\n [\n \"sample_start\",\n \"sample_end\"\n ]\n ],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}GDPC1 (319, 2) {'observation_date': dtype(' contract.md <<'EOF'\n# Contract — F6-conf-03 (Okun's law, US 1960Q1–2019Q4)\n\n**Question.** How strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and is that response stable across 1960–1983 vs 1984–2019?\n\n**Estimands.** β (and α) in Δu_t = α + β g_t + ε_t, OLS, 1960Q1–2019Q4 (n = 240). u_t = mean of the 3 monthly UNRATE values in quarter t; Δu_t = u_t − u_{t−1}; g_t = 100·Δln GDPC1_t (not annualised). β is a reduced-form conditional association (an \"Okun coefficient\"), meaningful as a descriptive/predictive slope under linearity and approximate stationarity of the relationship within each sample; it is not a structural causal effect. Inference: Newey–West (Bartlett) HAC SE for full-sample β, lag reported; 95% CI from that SE. Stability: subperiod OLS slopes (1960Q1–1983Q4, n=96; 1984Q1–2019Q4, n=144) and classical Chow SSR F-test, df (2, n−4), 5% level.\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 (scatter + two subperiod lines); out/table1.csv (period,n,intercept,slope,slope_se; 3 rows); out/report.md (6 sections in order); out/analysis.py; out/claims.json.\n\n**Information rules.** Only data/GDPC1.csv and data/UNRATE.csv. No quarter after 2019Q4 may enter any estimate (1959Q4 levels used only to form the 1960Q1 differences). Data vintage is the 2026 FRED vintage (as given).\n\n**Invalidating conditions.** Missing monthly UNRATE or GDPC1 values inside 1959Q4–2019Q4; incomplete quarters; using post-2019 data; non-HAC SE for full-sample β; wrong Chow df.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"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.\" > 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":1451,"cache_read_input_tokens":8693,"output_tokens":1485,"output_tokens_details":{"thinking_tokens":326},"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":1451},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSwsdoyqxraR9SC37K","requestRef":"e8c01983-efa8-4f7c-8392-dc803221b2a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"94dcadf5-c1ec-4063-86f1-e7a4ff31aff2","timestamp":"2026-10-30T04:50:08.740Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"94dcadf5-c1ec-4063-86f1-e7a4ff31aff2","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016mvKn1ka3LW1wCpiF69miR","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"3c9930c6-67df-4c8a-8429-a21d076c326f","timestamp":"2026-10-30T04:50:08.771Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"94dcadf5-c1ec-4063-86f1-e7a4ff31aff2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"8f34fdb62b3e96ccb15c6054a2f5543f6d2045829286bc264e6b677bd22bafdf","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016mvKn1ka3LW1wCpiF69miR","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract — F6-conf-03 (Okun's law, US 1960Q1–2019Q4)\n\n**Question.** How strongly does the quarterly change in the US unemployment rate respond to quarterly real GDP growth, and is that response stable across 1960–1983 vs 1984–2019?\n\n**Estimands.** β (and α) in Δu_t = α + β g_t + ε_t, OLS, 1960Q1–2019Q4 (n = 240). u_t = mean of the 3 monthly UNRATE values in quarter t; Δu_t = u_t − u_{t−1}; g_t = 100·Δln GDPC1_t (not annualised). β is a reduced-form conditional association (an \"Okun coefficient\"), meaningful as a descriptive/predictive slope under linearity and approximate stationarity of the relationship within each sample; it is not a structural causal effect. Inference: Newey–West (Bartlett) HAC SE for full-sample β, lag reported; 95% CI from that SE. Stability: subperiod OLS slopes (1960Q1–1983Q4, n=96; 1984Q1–2019Q4, n=144) and classical Chow SSR F-test, df (2, n−4), 5% level.\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 (scatter + two subperiod lines); out/table1.csv (period,n,intercept,slope,slope_se; 3 rows); out/report.md (6 sections in order); out/analysis.py; out/claims.json.\n\n**Information rules.** Only data/GDPC1.csv and data/UNRATE.csv. No quarter after 2019Q4 may enter any estimate (1959Q4 levels used only to form the 1960Q1 differences). Data vintage is the 2026 FRED vintage (as given).\n\n**Invalidating conditions.** Missing monthly UNRATE or GDPC1 values inside 1959Q4–2019Q4; incomplete quarters; using post-2019 data; non-HAC SE for full-sample β; wrong Chow df.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"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.\" > log.md","description":"Write contract, phase ledger, log"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"e4384210-7596-44c5-80b6-676cd95a7cb1","timestamp":"2026-10-30T04:50:08.774Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"e8c01983-efa8-4f7c-8392-dc803221b2a9","keep":8,"tail":["8f34fdb62b3e96ccb15c6054a2f5543f6d2045829286bc264e6b677bd22bafdf","bc129e63d9abad603734b3704ff9b3317ed52e265f8ec05913f80e90c2cf0bba"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"99253e6ab65dca08a078989aae052959bf087273939d65f4c2e7d36e074b27d8"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3c9930c6-67df-4c8a-8429-a21d076c326f","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"atis-latch","atis":"","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":"3c9930c6-67df-4c8a-8429-a21d076c326f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTyW9cxrsud1rQb6AR","type":"message","role":"assistant","content":[{"type":"text","text":"Now the analysis script."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1500,"cache_read_input_tokens":10144,"output_tokens":3974,"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":1500},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpTyEWkkKogm6nD89uQ","requestRef":"e4384210-7596-44c5-80b6-676cd95a7cb1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"40793cad-b544-4175-a699-927dcad2d057","timestamp":"2026-10-30T04:50:09.904Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"40793cad-b544-4175-a699-927dcad2d057","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpTyW9cxrsud1rQb6AR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QH6kZEUZsgYZbZ47EjRwLZ","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, US 1960Q1-2019Q4 (task F6-conf-03). Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nos.makedirs(OUT, exist_ok=True)\nSTART, END = pd.Timestamp(\"1960-01-01\"), pd.Timestamp(\"2019-10-01\")\nSPLIT = pd.Timestamp(\"1984-01-01\")\n\ngdp_raw = pd.read_csv(f\"{DATA}/GDPC1.csv\", parse_dates=[\"observation_date\"])\nur_raw = pd.read_csv(f\"{DATA}/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp_raw)), \"UNRATE.csv\": int(len(ur_raw))}\n\ndata_issues = []\n# --- audit monthly UNRATE\nur = ur_raw.copy()\nur[\"UNRATE\"] = pd.to_numeric(ur[\"UNRATE\"], errors=\"coerce\")\nmiss = ur[ur[\"UNRATE\"].isna()][\"observation_date\"]\nif len(miss):\n out_of_window = all(d > END + pd.offsets.QuarterEnd(0) for d in miss)\n data_issues.append({\n \"issue\": f\"UNRATE has {len(miss)} missing monthly value(s): {', '.join(d.strftime('%Y-%m') for d in miss)}\",\n \"handling\": (\"outside the 1959Q4-2019Q4 window needed for estimation; quarters with missing months are \"\n \"not averaged (require 3 valid months); no imputation\" if out_of_window else\n \"quarter dropped (require 3 valid months); see exclusions\")})\ndata_issues.append({\"issue\": \"Both files extend beyond 2019Q4 (to 2026); post-2019 quarters are outside the question\",\n \"handling\": \"truncated to 1959Q4-2019Q4 before any computation (1959Q4 used only as lag level)\"})\ndata_issues.append({\"issue\": \"GDPC1 is the 2026 FRED vintage (chained 2017 dollars), not real-time data; results depend on this vintage\",\n \"handling\": \"used as provided; noted as a limitation\"})\n\nur[\"q\"] = ur[\"observation_date\"].dt.to_period(\"Q\")\nqagg = ur.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nqagg = qagg[qagg[\"count\"] == 3] # complete quarters only\nu = qagg[\"mean\"].rename(\"u\")\n\ngdp = gdp_raw.copy()\ngdp[\"q\"] = gdp[\"observation_date\"].dt.to_period(\"Q\")\ngdp = gdp.set_index(\"q\")[\"GDPC1\"].astype(float)\n\ndf = pd.concat([u, gdp], axis=1, join=\"inner\").sort_index()\ndf = df[(df.index >= pd.Period(\"1959Q4\")) & (df.index <= pd.Period(\"2019Q4\"))]\n# require consecutive quarters for differencing\nassert (np.diff(df.index.astype(\"int64\")) == 1).all(), \"gap in quarterly series\"\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\n\nexcl = []\nn0 = len(df)\nd = df.dropna()\nexcl.append((\"1\", \"drop 1959Q4 (lag level only; no difference defined)\", n0, len(d), n0 - len(d),\n \"1959Q4 level is used only to form 1960Q1 differences\"))\nd = d[(d.index >= pd.Period(\"1960Q1\")) & (d.index <= pd.Period(\"2019Q4\"))]\nn_raw = n0\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\n f\"{OUT}/exclusions.csv\", index=False)\nassert len(d) == 240\n\ndef ols(sub):\n X = sm.add_constant(sub[\"g\"].values)\n return sm.OLS(sub[\"du\"].values, X).fit()\n\n# HAC lag: Newey-West (1994) rule of thumb floor(4*(T/100)^(2/9))\nn = len(d)\nhac_lags = int(np.floor(4 * (n / 100) ** (2 / 9)))\n\nfull = ols(d)\nfull_hac = full.get_robustcov_results(cov_type=\"HAC\", maxlags=hac_lags, kernel=\"bartlett\", use_correction=False)\nbeta, alpha = float(full.params[1]), float(full.params[0])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nci_lo, ci_hi = beta - z * se, beta + z * se\n\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full.resid ** 2)))\n\ns1 = d[d.index < pd.Period(\"1984Q1\")]\ns2 = d[d.index >= pd.Period(\"1984Q1\")]\nf1, f2 = ols(s1), ols(s2)\nk = 2\nssr_p, ssr_1, ssr_2 = full.ssr, f1.ssr, f2.ssr\nchow_f = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\ndef hac_se(fit, m):\n lags = int(np.floor(4 * (m / 100) ** (2 / 9)))\n return float(fit.get_robustcov_results(cov_type=\"HAC\", maxlags=lags, kernel=\"bartlett\",\n use_correction=False).bse[1])\n\ntable = pd.DataFrame([\n {\"period\": \"full_1960Q1-2019Q4\", \"n\": n, \"intercept\": alpha, \"slope\": beta, \"slope_se\": se},\n {\"period\": \"sub1_1960Q1-1983Q4\", \"n\": len(s1), \"intercept\": float(f1.params[0]),\n \"slope\": float(f1.params[1]), \"slope_se\": hac_se(f1, len(s1))},\n {\"period\": \"sub2_1984Q1-2019Q4\", \"n\": len(s2), \"intercept\": float(f2.params[0]),\n \"slope\": float(f2.params[1]), \"slope_se\": hac_se(f2, len(s2))},\n])\ntable.to_csv(f\"{OUT}/table1.csv\", index=False)\n\n# sensitivity (reported in report, stored as extra keys): HAC SE across lag lengths\nsens = {str(L): float(full.get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\",\n use_correction=False).bse[1]) for L in (0, 2, 4, 8, 12)}\n\nif ci_lo > 0: concl = \"positive_effect\"\nelif ci_hi < 0: concl = \"negative_effect\"\nelse: concl = \"no_detectable_effect\"\n\nres = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": d.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": d.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": hac_lags,\n \"effect_ci_low\": float(ci_lo), \"effect_ci_high\": float(ci_hi),\n \"beta_sub1\": float(f1.params[1]), \"beta_sub2\": float(f2.params[1]),\n \"chow_f_stat\": float(chow_f), \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": concl,\n # supplementary keys\n \"ols_classical_se\": float(full.bse[1]),\n \"r_squared\": float(full.rsquared),\n \"hac_se_by_lag\": sens,\n \"intercept_sub1\": float(f1.params[0]), \"intercept_sub2\": float(f2.params[0]),\n \"beta_sub1_hac_se\": float(table.loc[1, \"slope_se\"]), \"beta_sub2_hac_se\": float(table.loc[2, \"slope_se\"]),\n \"chow_df\": [k, int(n - 2 * k)],\n \"n_raw_quarters_window\": int(n_raw),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n json.dump(res, fh, indent=2)\n\n# figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=0.7, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=0.7, marker=\"^\", label=\"1984Q1–2019Q4\")\nfor sub, fit, ls in ((s1, f1, \"-\"), (s2, f2, \"--\")):\n xs = np.linspace(sub[\"g\"].min(), sub[\"g\"].max(), 50)\n ax.plot(xs, fit.params[0] + fit.params[1] * xs, ls, color=\"k\",\n label=f\"fit {sub.index[0]}–{sub.index[-1]}: β={fit.params[1]:.3f}\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1–2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=150)\nprint(json.dumps({k: res[k] for k in (\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\",\n \"effect_ci_high\", \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\",\n \"chow_p_value\", \"baseline_metric\", \"model_metric\")}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && grep -A6 hac_se_by 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":1500,"cache_read_input_tokens":10144,"output_tokens":3974,"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":1500},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpTyEWkkKogm6nD89uQ","requestRef":"e4384210-7596-44c5-80b6-676cd95a7cb1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e0f551cd-cb04-4721-85af-a265550098df","timestamp":"2026-10-30T04:50:38.560Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e0f551cd-cb04-4721-85af-a265550098df","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","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@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0174/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01QH6kZEUZsgYZbZ47EjRwLZ"}]},"uuid":"3fc6a1f2-fbb9-4374-a58e-0846fc792a85","timestamp":"2026-10-30T04:50:38.609Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0174/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"e0f551cd-cb04-4721-85af-a265550098df","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"074e8eb4730cb275933d95071f20f25aaa517f72f80fd2daca8acc005a845b71","message":{"role":"assistant","content":[{"type":"text","text":"Now the analysis script."},{"type":"tool_use","id":"toolu_01QH6kZEUZsgYZbZ47EjRwLZ","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, US 1960Q1-2019Q4 (task F6-conf-03). Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nos.makedirs(OUT, exist_ok=True)\nSTART, END = pd.Timestamp(\"1960-01-01\"), pd.Timestamp(\"2019-10-01\")\nSPLIT = pd.Timestamp(\"1984-01-01\")\n\ngdp_raw = pd.read_csv(f\"{DATA}/GDPC1.csv\", parse_dates=[\"observation_date\"])\nur_raw = pd.read_csv(f\"{DATA}/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp_raw)), \"UNRATE.csv\": int(len(ur_raw))}\n\ndata_issues = []\n# --- audit monthly UNRATE\nur = ur_raw.copy()\nur[\"UNRATE\"] = pd.to_numeric(ur[\"UNRATE\"], errors=\"coerce\")\nmiss = ur[ur[\"UNRATE\"].isna()][\"observation_date\"]\nif len(miss):\n out_of_window = all(d > END + pd.offsets.QuarterEnd(0) for d in miss)\n data_issues.append({\n \"issue\": f\"UNRATE has {len(miss)} missing monthly value(s): {', '.join(d.strftime('%Y-%m') for d in miss)}\",\n \"handling\": (\"outside the 1959Q4-2019Q4 window needed for estimation; quarters with missing months are \"\n \"not averaged (require 3 valid months); no imputation\" if out_of_window else\n \"quarter dropped (require 3 valid months); see exclusions\")})\ndata_issues.append({\"issue\": \"Both files extend beyond 2019Q4 (to 2026); post-2019 quarters are outside the question\",\n \"handling\": \"truncated to 1959Q4-2019Q4 before any computation (1959Q4 used only as lag level)\"})\ndata_issues.append({\"issue\": \"GDPC1 is the 2026 FRED vintage (chained 2017 dollars), not real-time data; results depend on this vintage\",\n \"handling\": \"used as provided; noted as a limitation\"})\n\nur[\"q\"] = ur[\"observation_date\"].dt.to_period(\"Q\")\nqagg = ur.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nqagg = qagg[qagg[\"count\"] == 3] # complete quarters only\nu = qagg[\"mean\"].rename(\"u\")\n\ngdp = gdp_raw.copy()\ngdp[\"q\"] = gdp[\"observation_date\"].dt.to_period(\"Q\")\ngdp = gdp.set_index(\"q\")[\"GDPC1\"].astype(float)\n\ndf = pd.concat([u, gdp], axis=1, join=\"inner\").sort_index()\ndf = df[(df.index >= pd.Period(\"1959Q4\")) & (df.index <= pd.Period(\"2019Q4\"))]\n# require consecutive quarters for differencing\nassert (np.diff(df.index.astype(\"int64\")) == 1).all(), \"gap in quarterly series\"\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\n\nexcl = []\nn0 = len(df)\nd = df.dropna()\nexcl.append((\"1\", \"drop 1959Q4 (lag level only; no difference defined)\", n0, len(d), n0 - len(d),\n \"1959Q4 level is used only to form 1960Q1 differences\"))\nd = d[(d.index >= pd.Period(\"1960Q1\")) & (d.index <= pd.Period(\"2019Q4\"))]\nn_raw = n0\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\n f\"{OUT}/exclusions.csv\", index=False)\nassert len(d) == 240\n\ndef ols(sub):\n X = sm.add_constant(sub[\"g\"].values)\n return sm.OLS(sub[\"du\"].values, X).fit()\n\n# HAC lag: Newey-West (1994) rule of thumb floor(4*(T/100)^(2/9))\nn = len(d)\nhac_lags = int(np.floor(4 * (n / 100) ** (2 / 9)))\n\nfull = ols(d)\nfull_hac = full.get_robustcov_results(cov_type=\"HAC\", maxlags=hac_lags, kernel=\"bartlett\", use_correction=False)\nbeta, alpha = float(full.params[1]), float(full.params[0])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nci_lo, ci_hi = beta - z * se, beta + z * se\n\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full.resid ** 2)))\n\ns1 = d[d.index < pd.Period(\"1984Q1\")]\ns2 = d[d.index >= pd.Period(\"1984Q1\")]\nf1, f2 = ols(s1), ols(s2)\nk = 2\nssr_p, ssr_1, ssr_2 = full.ssr, f1.ssr, f2.ssr\nchow_f = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\ndef hac_se(fit, m):\n lags = int(np.floor(4 * (m / 100) ** (2 / 9)))\n return float(fit.get_robustcov_results(cov_type=\"HAC\", maxlags=lags, kernel=\"bartlett\",\n use_correction=False).bse[1])\n\ntable = pd.DataFrame([\n {\"period\": \"full_1960Q1-2019Q4\", \"n\": n, \"intercept\": alpha, \"slope\": beta, \"slope_se\": se},\n {\"period\": \"sub1_1960Q1-1983Q4\", \"n\": len(s1), \"intercept\": float(f1.params[0]),\n \"slope\": float(f1.params[1]), \"slope_se\": hac_se(f1, len(s1))},\n {\"period\": \"sub2_1984Q1-2019Q4\", \"n\": len(s2), \"intercept\": float(f2.params[0]),\n \"slope\": float(f2.params[1]), \"slope_se\": hac_se(f2, len(s2))},\n])\ntable.to_csv(f\"{OUT}/table1.csv\", index=False)\n\n# sensitivity (reported in report, stored as extra keys): HAC SE across lag lengths\nsens = {str(L): float(full.get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\",\n use_correction=False).bse[1]) for L in (0, 2, 4, 8, 12)}\n\nif ci_lo > 0: concl = \"positive_effect\"\nelif ci_hi < 0: concl = \"negative_effect\"\nelse: concl = \"no_detectable_effect\"\n\nres = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": d.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": d.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": hac_lags,\n \"effect_ci_low\": float(ci_lo), \"effect_ci_high\": float(ci_hi),\n \"beta_sub1\": float(f1.params[1]), \"beta_sub2\": float(f2.params[1]),\n \"chow_f_stat\": float(chow_f), \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": concl,\n # supplementary keys\n \"ols_classical_se\": float(full.bse[1]),\n \"r_squared\": float(full.rsquared),\n \"hac_se_by_lag\": sens,\n \"intercept_sub1\": float(f1.params[0]), \"intercept_sub2\": float(f2.params[0]),\n \"beta_sub1_hac_se\": float(table.loc[1, \"slope_se\"]), \"beta_sub2_hac_se\": float(table.loc[2, \"slope_se\"]),\n \"chow_df\": [k, int(n - 2 * k)],\n \"n_raw_quarters_window\": int(n_raw),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n json.dump(res, fh, indent=2)\n\n# figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=0.7, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=0.7, marker=\"^\", label=\"1984Q1–2019Q4\")\nfor sub, fit, ls in ((s1, f1, \"-\"), (s2, f2, \"--\")):\n xs = np.linspace(sub[\"g\"].min(), sub[\"g\"].max(), 50)\n ax.plot(xs, fit.params[0] + fit.params[1] * xs, ls, color=\"k\",\n label=f\"fit {sub.index[0]}–{sub.index[-1]}: β={fit.params[1]:.3f}\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Δ unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1–2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=150)\nprint(json.dumps({k: res[k] for k in (\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\",\n \"effect_ci_high\", \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\",\n \"chow_p_value\", \"baseline_metric\", \"model_metric\")}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && grep -A6 hac_se_by out/results.json","description":"Write and run analysis script"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"a7360b6a-df07-4f6c-9e71-aa436e261e44","timestamp":"2026-10-30T04:50:38.613Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"e4384210-7596-44c5-80b6-676cd95a7cb1","keep":10,"tail":["074e8eb4730cb275933d95071f20f25aaa517f72f80fd2daca8acc005a845b71","51c1daa2944fd61180d504283d1e4da30b090a0334fccffc4f0ad6a073c97786"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"31f95534ca2f38f7cce1fdf39d573b5ed1e8949347469175c30fcda4dab5a907"} {"parentUuid":"3fc6a1f2-fbb9-4374-a58e-0846fc792a85","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWB6DYAdZcz3si9sME","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":4136,"cache_read_input_tokens":11644,"output_tokens":127,"output_tokens_details":{"thinking_tokens":14},"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":4136},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":345,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpWAnreW8bPMH865S68","requestRef":"a7360b6a-df07-4f6c-9e71-aa436e261e44","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e53cb774-99f2-4f9c-b258-d4bf8128b301","timestamp":"2026-10-30T04:50:40.429Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e53cb774-99f2-4f9c-b258-d4bf8128b301","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWB6DYAdZcz3si9sME","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01H3XePAhdMtKLr1LzNtAmB5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0174 && pwd && ls out out/state","description":"Return to workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4136,"cache_read_input_tokens":11644,"output_tokens":127,"output_tokens_details":{"thinking_tokens":14},"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":4136},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpWAnreW8bPMH865S68","requestRef":"a7360b6a-df07-4f6c-9e71-aa436e261e44","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2876f71d-bdcb-45f7-a15b-354e341ff062","timestamp":"2026-10-30T04:50:40.872Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"2876f71d-bdcb-45f7-a15b-354e341ff062","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01H3XePAhdMtKLr1LzNtAmB5","type":"tool_result","content":"/Users/simon-pierreboucher/wp29/runs/RC0174\nout:\nstate\n\nout/state:\ncontract.md\nlog.md\nphases.json","is_error":false}]},"uuid":"f8d7ede6-a088-4e35-a33c-ef3cfb647793","timestamp":"2026-10-30T04:50:40.894Z","toolUseResult":{"stdout":"/Users/simon-pierreboucher/wp29/runs/RC0174\nout:\nstate\n\nout/state:\ncontract.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2876f71d-bdcb-45f7-a15b-354e341ff062","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"0624bfbf5040a8cf92d36ee7070e63fa48b32ad987dfeddbfed1f096e9737e4c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01H3XePAhdMtKLr1LzNtAmB5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0174 && pwd && ls out out/state","description":"Return to workspace root"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"0fcfb15f-4223-48fa-9047-c9216f3416d8","timestamp":"2026-10-30T04:50:40.898Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"a7360b6a-df07-4f6c-9e71-aa436e261e44","keep":12,"tail":["0624bfbf5040a8cf92d36ee7070e63fa48b32ad987dfeddbfed1f096e9737e4c","2fb0faf0dae2e7ac4d5298eb4cb9afe12ad171c30ff1fcfac511ed7a3cb2baeb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"74e3ad77363468941820e8f865bf49a978679c9fd8eeb44c6e18281205af8e7a"} {"parentUuid":"f8d7ede6-a088-4e35-a33c-ef3cfb647793","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWLs65G5ifS9xF5XtP","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":181,"cache_read_input_tokens":15780,"output_tokens":3911,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":181},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":257,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpWLZjB13WsUcn1GW49","requestRef":"0fcfb15f-4223-48fa-9047-c9216f3416d8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"587900c1-e440-4111-b7ff-aec202b77faa","timestamp":"2026-10-30T04:50:42.575Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"587900c1-e440-4111-b7ff-aec202b77faa","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWLs65G5ifS9xF5XtP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01E6UZkW2dQpA2b9XJu1qf4T","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, US 1960Q1-2019Q4 (task F6-conf-03). Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nos.makedirs(OUT, exist_ok=True)\nFIRST_Q, LAST_Q, SPLIT_Q = pd.Period(\"1960Q1\"), pd.Period(\"2019Q4\"), pd.Period(\"1984Q1\")\n\ngdp_raw = pd.read_csv(f\"{DATA}/GDPC1.csv\", parse_dates=[\"observation_date\"])\nur_raw = pd.read_csv(f\"{DATA}/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp_raw)), \"UNRATE.csv\": int(len(ur_raw))}\n\ndata_issues = []\nur = ur_raw.copy()\nur[\"UNRATE\"] = pd.to_numeric(ur[\"UNRATE\"], errors=\"coerce\")\nur[\"q\"] = ur[\"observation_date\"].dt.to_period(\"Q\")\nmiss = ur[ur[\"UNRATE\"].isna()]\nif len(miss):\n inside = bool(((miss[\"q\"] >= FIRST_Q - 1) & (miss[\"q\"] <= LAST_Q)).any())\n data_issues.append({\n \"issue\": f\"UNRATE has {len(miss)} missing monthly value(s): \"\n + \", \".join(d.strftime('%Y-%m') for d in miss[\"observation_date\"]),\n \"handling\": (\"inside the estimation window: affected quarter dropped (3 valid months required)\" if inside else\n \"outside the 1959Q4-2019Q4 window needed for estimation, so no effect; quarters with \"\n \"missing months are never averaged (3 valid months required); no imputation\")})\ndata_issues.append({\"issue\": \"Both files extend beyond 2019Q4 (to 2026); post-2019 quarters are outside the question\",\n \"handling\": \"truncated to 1959Q4-2019Q4 before any computation (1959Q4 used only as lag level)\"})\ndata_issues.append({\"issue\": \"GDPC1 is the 2026 FRED vintage (chained 2017 dollars), not real-time data\",\n \"handling\": \"used as provided; results are conditional on this vintage (noted as limitation)\"})\n\nqagg = ur.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nqagg = qagg[qagg[\"count\"] == 3] # complete quarters only\nu = qagg[\"mean\"].rename(\"u\")\ngdp = gdp_raw.assign(q=gdp_raw[\"observation_date\"].dt.to_period(\"Q\")).set_index(\"q\")[\"GDPC1\"].astype(float)\n\ndf = pd.concat([u, gdp], axis=1, join=\"inner\").sort_index()\ndf = df[(df.index >= FIRST_Q - 1) & (df.index <= LAST_Q)]\nassert len(df) == 241 and (np.diff(df.index.asi8) == 1).all(), \"gap in quarterly series\"\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\n\nn0 = len(df)\nd = df.dropna()\npd.DataFrame([(\"1\", \"drop 1959Q4 (lag level only; difference undefined)\", n0, len(d), n0 - len(d),\n \"1959Q4 level used only to form 1960Q1 differences; post-2019Q4 rows were never in the window\")],\n columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\n f\"{OUT}/exclusions.csv\", index=False)\nassert len(d) == 240 and d.index[0] == FIRST_Q and d.index[-1] == LAST_Q\n\ndef ols(sub):\n return sm.OLS(sub[\"du\"].values, sm.add_constant(sub[\"g\"].values)).fit()\n\ndef nw_lags(m): # Newey-West (1994) rule of thumb\n return int(np.floor(4 * (m / 100) ** (2 / 9)))\n\ndef hac_se(fit, lags):\n return float(fit.get_robustcov_results(cov_type=\"HAC\", maxlags=lags, kernel=\"bartlett\",\n use_correction=False).bse[1])\n\nn = len(d)\nhac_lags = nw_lags(n)\nfull = ols(d)\nbeta, alpha = float(full.params[1]), float(full.params[0])\nse = hac_se(full, hac_lags)\nz = stats.norm.ppf(0.975)\nci_lo, ci_hi = beta - z * se, beta + z * se\n\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full.resid ** 2)))\n\ns1, s2 = d[d.index < SPLIT_Q], d[d.index >= SPLIT_Q]\nf1, f2 = ols(s1), ols(s2)\nk = 2\nssr_u = f1.ssr + f2.ssr\nchow_f = float(((full.ssr - ssr_u) / k) / (ssr_u / (n - 2 * k)))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\ntable = pd.DataFrame([\n {\"period\": \"full_1960Q1-2019Q4\", \"n\": n, \"intercept\": alpha, \"slope\": beta, \"slope_se\": se},\n {\"period\": \"sub1_1960Q1-1983Q4\", \"n\": len(s1), \"intercept\": float(f1.params[0]),\n \"slope\": float(f1.params[1]), \"slope_se\": hac_se(f1, nw_lags(len(s1)))},\n {\"period\": \"sub2_1984Q1-2019Q4\", \"n\": len(s2), \"intercept\": float(f2.params[0]),\n \"slope\": float(f2.params[1]), \"slope_se\": hac_se(f2, nw_lags(len(s2)))},\n])\ntable.to_csv(f\"{OUT}/table1.csv\", index=False)\n\nsens = {str(L): hac_se(full, L) for L in (0, 2, 4, 8, 12)}\nconcl = \"positive_effect\" if ci_lo > 0 else (\"negative_effect\" if ci_hi < 0 else \"no_detectable_effect\")\n\nres = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": d.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": d.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": hac_lags,\n \"effect_ci_low\": float(ci_lo), \"effect_ci_high\": float(ci_hi),\n \"beta_sub1\": float(f1.params[1]), \"beta_sub2\": float(f2.params[1]),\n \"chow_f_stat\": chow_f, \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": concl,\n # supplementary keys\n \"ols_classical_se\": float(full.bse[1]),\n \"r_squared\": float(full.rsquared),\n \"hac_se_by_lag\": sens,\n \"intercept_sub1\": float(f1.params[0]), \"intercept_sub2\": float(f2.params[0]),\n \"beta_sub1_hac_se\": float(table.loc[1, \"slope_se\"]), \"beta_sub2_hac_se\": float(table.loc[2, \"slope_se\"]),\n \"hac_lags_sub1\": nw_lags(len(s1)), \"hac_lags_sub2\": nw_lags(len(s2)),\n \"chow_df\": [k, int(n - 2 * k)],\n \"n_window_quarters\": int(n0),\n \"mean_du\": float(d[\"du\"].mean()), \"mean_g\": float(d[\"g\"].mean()),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n json.dump(res, fh, indent=2)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=0.7, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=0.7, marker=\"^\", label=\"1984Q1–2019Q4\")\nfor sub, fit, ls in ((s1, f1, \"-\"), (s2, f2, \"--\")):\n xs = np.linspace(sub[\"g\"].min(), sub[\"g\"].max(), 50)\n ax.plot(xs, fit.params[0] + fit.params[1] * xs, ls, color=\"k\",\n label=f\"OLS {sub.index[0]}–{sub.index[-1]}: β={fit.params[1]:.3f}\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1–2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=150)\nprint(json.dumps({k: res[k] for k in (\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\",\n \"effect_ci_high\", \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\",\n \"chow_p_value\", \"baseline_metric\", \"model_metric\", \"conclusion\",\n \"stability_conclusion\")}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && grep -A6 hac_se_by out/results.json; grep -E \"r_squared|ols_class|mean_\" out/results.json","description":"Write and run analysis script from root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":181,"cache_read_input_tokens":15780,"output_tokens":3911,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":181},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpWLZjB13WsUcn1GW49","requestRef":"0fcfb15f-4223-48fa-9047-c9216f3416d8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a7f42f43-8c1d-476f-aaf9-f65824216328","timestamp":"2026-10-30T04:51:07.770Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a7f42f43-8c1d-476f-aaf9-f65824216328","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"atis-latch","atis":"","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":"a7f42f43-8c1d-476f-aaf9-f65824216328","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01E6UZkW2dQpA2b9XJu1qf4T","type":"tool_result","content":"{\n \"effect_estimate\": -0.2557677277487258,\n \"effect_se\": 0.03583463330296569,\n \"hac_lags\": 4,\n \"effect_ci_low\": -0.32600231842173816,\n \"effect_ci_high\": -0.18553313707571345,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.0903330062337675,\n \"chow_p_value\": 0.002636323851733417,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253,\n \"conclusion\": \"negative_effect\",\n \"stability_conclusion\": \"unstable\"\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03583463330296569\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03880650875413735\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06831428793738023\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop 1959Q4 (lag level only; difference undefined),241,240,1,1959Q4 level used only to form 1960Q1 differences; post-2019Q4 rows were never in the window\n \"hac_se_by_lag\": {\n \"0\": 0.028836223207269963,\n \"2\": 0.03422732023615383,\n \"4\": 0.03583463330296569,\n \"8\": 0.03713550417540189,\n \"12\": 0.0364088511022809\n },\n \"ols_classical_se\": 0.01996009291490984,\n \"r_squared\": 0.4082508284562034,\n \"mean_du\": -0.008333333333333335,\n \"mean_g\": 0.753502755065237","is_error":false}]},"uuid":"13fa0bdb-0330-4a09-bdc2-199dff0664be","timestamp":"2026-10-30T04:51:08.978Z","toolUseResult":{"stdout":"{\n \"effect_estimate\": -0.2557677277487258,\n \"effect_se\": 0.03583463330296569,\n \"hac_lags\": 4,\n \"effect_ci_low\": -0.32600231842173816,\n \"effect_ci_high\": -0.18553313707571345,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.0903330062337675,\n \"chow_p_value\": 0.002636323851733417,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253,\n \"conclusion\": \"negative_effect\",\n \"stability_conclusion\": \"unstable\"\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03583463330296569\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03880650875413735\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06831428793738023\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop 1959Q4 (lag level only; difference undefined),241,240,1,1959Q4 level used only to form 1960Q1 differences; post-2019Q4 rows were never in the window\n \"hac_se_by_lag\": {\n \"0\": 0.028836223207269963,\n \"2\": 0.03422732023615383,\n \"4\": 0.03583463330296569,\n \"8\": 0.03713550417540189,\n \"12\": 0.0364088511022809\n },\n \"ols_classical_se\": 0.01996009291490984,\n \"r_squared\": 0.4082508284562034,\n \"mean_du\": -0.008333333333333335,\n \"mean_g\": 0.753502755065237","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a7f42f43-8c1d-476f-aaf9-f65824216328","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"a8443d7dbe5d14fe5c63d835255281f6d2d3618912a21226fb8e8a7e8d01699b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01E6UZkW2dQpA2b9XJu1qf4T","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law, US 1960Q1-2019Q4 (task F6-conf-03). Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nos.makedirs(OUT, exist_ok=True)\nFIRST_Q, LAST_Q, SPLIT_Q = pd.Period(\"1960Q1\"), pd.Period(\"2019Q4\"), pd.Period(\"1984Q1\")\n\ngdp_raw = pd.read_csv(f\"{DATA}/GDPC1.csv\", parse_dates=[\"observation_date\"])\nur_raw = pd.read_csv(f\"{DATA}/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input_rows = {\"GDPC1.csv\": int(len(gdp_raw)), \"UNRATE.csv\": int(len(ur_raw))}\n\ndata_issues = []\nur = ur_raw.copy()\nur[\"UNRATE\"] = pd.to_numeric(ur[\"UNRATE\"], errors=\"coerce\")\nur[\"q\"] = ur[\"observation_date\"].dt.to_period(\"Q\")\nmiss = ur[ur[\"UNRATE\"].isna()]\nif len(miss):\n inside = bool(((miss[\"q\"] >= FIRST_Q - 1) & (miss[\"q\"] <= LAST_Q)).any())\n data_issues.append({\n \"issue\": f\"UNRATE has {len(miss)} missing monthly value(s): \"\n + \", \".join(d.strftime('%Y-%m') for d in miss[\"observation_date\"]),\n \"handling\": (\"inside the estimation window: affected quarter dropped (3 valid months required)\" if inside else\n \"outside the 1959Q4-2019Q4 window needed for estimation, so no effect; quarters with \"\n \"missing months are never averaged (3 valid months required); no imputation\")})\ndata_issues.append({\"issue\": \"Both files extend beyond 2019Q4 (to 2026); post-2019 quarters are outside the question\",\n \"handling\": \"truncated to 1959Q4-2019Q4 before any computation (1959Q4 used only as lag level)\"})\ndata_issues.append({\"issue\": \"GDPC1 is the 2026 FRED vintage (chained 2017 dollars), not real-time data\",\n \"handling\": \"used as provided; results are conditional on this vintage (noted as limitation)\"})\n\nqagg = ur.groupby(\"q\")[\"UNRATE\"].agg([\"mean\", \"count\"])\nqagg = qagg[qagg[\"count\"] == 3] # complete quarters only\nu = qagg[\"mean\"].rename(\"u\")\ngdp = gdp_raw.assign(q=gdp_raw[\"observation_date\"].dt.to_period(\"Q\")).set_index(\"q\")[\"GDPC1\"].astype(float)\n\ndf = pd.concat([u, gdp], axis=1, join=\"inner\").sort_index()\ndf = df[(df.index >= FIRST_Q - 1) & (df.index <= LAST_Q)]\nassert len(df) == 241 and (np.diff(df.index.asi8) == 1).all(), \"gap in quarterly series\"\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\n\nn0 = len(df)\nd = df.dropna()\npd.DataFrame([(\"1\", \"drop 1959Q4 (lag level only; difference undefined)\", n0, len(d), n0 - len(d),\n \"1959Q4 level used only to form 1960Q1 differences; post-2019Q4 rows were never in the window\")],\n columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\n f\"{OUT}/exclusions.csv\", index=False)\nassert len(d) == 240 and d.index[0] == FIRST_Q and d.index[-1] == LAST_Q\n\ndef ols(sub):\n return sm.OLS(sub[\"du\"].values, sm.add_constant(sub[\"g\"].values)).fit()\n\ndef nw_lags(m): # Newey-West (1994) rule of thumb\n return int(np.floor(4 * (m / 100) ** (2 / 9)))\n\ndef hac_se(fit, lags):\n return float(fit.get_robustcov_results(cov_type=\"HAC\", maxlags=lags, kernel=\"bartlett\",\n use_correction=False).bse[1])\n\nn = len(d)\nhac_lags = nw_lags(n)\nfull = ols(d)\nbeta, alpha = float(full.params[1]), float(full.params[0])\nse = hac_se(full, hac_lags)\nz = stats.norm.ppf(0.975)\nci_lo, ci_hi = beta - z * se, beta + z * se\n\nbaseline_rmse = float(np.sqrt(np.mean((d[\"du\"] - d[\"du\"].mean()) ** 2)))\nmodel_rmse = float(np.sqrt(np.mean(full.resid ** 2)))\n\ns1, s2 = d[d.index < SPLIT_Q], d[d.index >= SPLIT_Q]\nf1, f2 = ols(s1), ols(s2)\nk = 2\nssr_u = f1.ssr + f2.ssr\nchow_f = float(((full.ssr - ssr_u) / k) / (ssr_u / (n - 2 * k)))\nchow_p = float(stats.f.sf(chow_f, k, n - 2 * k))\n\ntable = pd.DataFrame([\n {\"period\": \"full_1960Q1-2019Q4\", \"n\": n, \"intercept\": alpha, \"slope\": beta, \"slope_se\": se},\n {\"period\": \"sub1_1960Q1-1983Q4\", \"n\": len(s1), \"intercept\": float(f1.params[0]),\n \"slope\": float(f1.params[1]), \"slope_se\": hac_se(f1, nw_lags(len(s1)))},\n {\"period\": \"sub2_1984Q1-2019Q4\", \"n\": len(s2), \"intercept\": float(f2.params[0]),\n \"slope\": float(f2.params[1]), \"slope_se\": hac_se(f2, nw_lags(len(s2)))},\n])\ntable.to_csv(f\"{OUT}/table1.csv\", index=False)\n\nsens = {str(L): hac_se(full, L) for L in (0, 2, 4, 8, 12)}\nconcl = \"positive_effect\" if ci_lo > 0 else (\"negative_effect\" if ci_hi < 0 else \"no_detectable_effect\")\n\nres = {\n \"task_id\": \"F6-conf-03\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": n_input_rows,\n \"n_analysed\": int(n),\n \"random_seed\": None,\n \"sample_start\": d.index[0].start_time.strftime(\"%Y-%m-%d\"),\n \"sample_end\": d.index[-1].start_time.strftime(\"%Y-%m-%d\"),\n \"n_sub1\": int(len(s1)), \"n_sub2\": int(len(s2)),\n \"baseline_metric\": baseline_rmse,\n \"model_metric\": model_rmse,\n \"effect_estimate\": beta,\n \"intercept\": alpha,\n \"effect_se\": se,\n \"hac_lags\": hac_lags,\n \"effect_ci_low\": float(ci_lo), \"effect_ci_high\": float(ci_hi),\n \"beta_sub1\": float(f1.params[1]), \"beta_sub2\": float(f2.params[1]),\n \"chow_f_stat\": chow_f, \"chow_p_value\": chow_p,\n \"stability_conclusion\": \"stable\" if chow_p >= 0.05 else \"unstable\",\n \"conclusion\": concl,\n # supplementary keys\n \"ols_classical_se\": float(full.bse[1]),\n \"r_squared\": float(full.rsquared),\n \"hac_se_by_lag\": sens,\n \"intercept_sub1\": float(f1.params[0]), \"intercept_sub2\": float(f2.params[0]),\n \"beta_sub1_hac_se\": float(table.loc[1, \"slope_se\"]), \"beta_sub2_hac_se\": float(table.loc[2, \"slope_se\"]),\n \"hac_lags_sub1\": nw_lags(len(s1)), \"hac_lags_sub2\": nw_lags(len(s2)),\n \"chow_df\": [k, int(n - 2 * k)],\n \"n_window_quarters\": int(n0),\n \"mean_du\": float(d[\"du\"].mean()), \"mean_g\": float(d[\"g\"].mean()),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n json.dump(res, fh, indent=2)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(s1[\"g\"], s1[\"du\"], s=14, alpha=0.7, label=\"1960Q1–1983Q4\")\nax.scatter(s2[\"g\"], s2[\"du\"], s=14, alpha=0.7, marker=\"^\", label=\"1984Q1–2019Q4\")\nfor sub, fit, ls in ((s1, f1, \"-\"), (s2, f2, \"--\")):\n xs = np.linspace(sub[\"g\"].min(), sub[\"g\"].max(), 50)\n ax.plot(xs, fit.params[0] + fit.params[1] * xs, ls, color=\"k\",\n label=f\"OLS {sub.index[0]}–{sub.index[-1]}: β={fit.params[1]:.3f}\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate Δu_t (pp)\")\nax.set_title(\"Okun's law, US 1960Q1–2019Q4\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=150)\nprint(json.dumps({k: res[k] for k in (\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\",\n \"effect_ci_high\", \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\",\n \"chow_p_value\", \"baseline_metric\", \"model_metric\", \"conclusion\",\n \"stability_conclusion\")}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && grep -A6 hac_se_by out/results.json; grep -E \"r_squared|ols_class|mean_\" out/results.json","description":"Write and run analysis script from root"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"02ed83ba-39cc-4b3f-baf5-bd43ec19431e","timestamp":"2026-10-30T04:51:08.982Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"0fcfb15f-4223-48fa-9047-c9216f3416d8","keep":14,"tail":["a8443d7dbe5d14fe5c63d835255281f6d2d3618912a21226fb8e8a7e8d01699b","193b796476959a29ef151313a5881ec5901b73c52e6df3eeb4d124d13498e3ad"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0034c33bba74992d02eb406a054a67b18250cd8b7286e50d5f46261d777e466c"} {"parentUuid":"13fa0bdb-0330-4a09-bdc2-199dff0664be","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYR1fcpfXkqrRHmaqs","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":4536,"cache_read_input_tokens":15961,"output_tokens":985,"output_tokens_details":{"thinking_tokens":246},"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":4536},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2409,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpYQfbNbkSBK9sqyG6k","requestRef":"02ed83ba-39cc-4b3f-baf5-bd43ec19431e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8b48ef36-3b46-4815-803b-e406aa4f5185","timestamp":"2026-10-30T04:51:13.319Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"8b48ef36-3b46-4815-803b-e406aa4f5185","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYR1fcpfXkqrRHmaqs","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016RFiPFyEVoTn3uQKq2WB4E","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''sens = {str(L)''','''# robustness (supplementary): HAC Wald tests in the interaction model du = a + b g + c D + d D*g\nD = (d.index >= SPLIT_Q).astype(float)\nXi = np.column_stack([np.ones(n), d[\"g\"].values, D, D * d[\"g\"].values])\nfi = sm.OLS(d[\"du\"].values, Xi).fit().get_robustcov_results(cov_type=\"HAC\", maxlags=hac_lags,\n kernel=\"bartlett\", use_correction=False)\nw_joint = fi.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), use_f=False, scalar=True)\nw_slope = fi.wald_test(np.array([[0, 0, 0, 1]]), use_f=False, scalar=True)\nw_int = fi.wald_test(np.array([[0, 0, 1, 0]]), use_f=False, scalar=True)\n\nsens = {str(L)''')\ns=s.replace(''' \"n_window_quarters\"''',''' \"hac_wald_joint_p\": float(w_joint.pvalue), \"hac_wald_slope_diff_p\": float(w_slope.pvalue),\n \"hac_wald_intercept_diff_p\": float(w_int.pvalue),\n \"okun_growth_sub1\": float(-f1.params[0] / f1.params[1]), \"okun_growth_sub2\": float(-f2.params[0] / f2.params[1]),\n \"n_window_quarters\"''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && grep -E \"wald|okun\" out/results.json","description":"Add HAC Wald robustness tests"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4536,"cache_read_input_tokens":15961,"output_tokens":985,"output_tokens_details":{"thinking_tokens":246},"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":4536},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpYQfbNbkSBK9sqyG6k","requestRef":"02ed83ba-39cc-4b3f-baf5-bd43ec19431e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c1ed4700-cf21-40e4-a137-7926d152fc2a","timestamp":"2026-10-30T04:51:18.572Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"c1ed4700-cf21-40e4-a137-7926d152fc2a","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016RFiPFyEVoTn3uQKq2WB4E","type":"tool_result","content":" \"hac_wald_joint_p\": 0.004240368816511458,\n \"hac_wald_slope_diff_p\": 0.8536158012976183,\n \"hac_wald_intercept_diff_p\": 0.2499697254959754,\n \"okun_growth_sub1\": 0.9815134738876885,\n \"okun_growth_sub2\": 0.5548277280747038,","is_error":false}]},"uuid":"87a99b2b-99d7-436b-b265-bf7f5eae8d64","timestamp":"2026-10-30T04:51:19.778Z","toolUseResult":{"stdout":" \"hac_wald_joint_p\": 0.004240368816511458,\n \"hac_wald_slope_diff_p\": 0.8536158012976183,\n \"hac_wald_intercept_diff_p\": 0.2499697254959754,\n \"okun_growth_sub1\": 0.9815134738876885,\n \"okun_growth_sub2\": 0.5548277280747038,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c1ed4700-cf21-40e4-a137-7926d152fc2a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"d6197aefa19e67134ae730418abdf73ae8951509e8e736a75a3ce035c7bf47fb","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016RFiPFyEVoTn3uQKq2WB4E","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''sens = {str(L)''','''# robustness (supplementary): HAC Wald tests in the interaction model du = a + b g + c D + d D*g\nD = (d.index >= SPLIT_Q).astype(float)\nXi = np.column_stack([np.ones(n), d[\"g\"].values, D, D * d[\"g\"].values])\nfi = sm.OLS(d[\"du\"].values, Xi).fit().get_robustcov_results(cov_type=\"HAC\", maxlags=hac_lags,\n kernel=\"bartlett\", use_correction=False)\nw_joint = fi.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), use_f=False, scalar=True)\nw_slope = fi.wald_test(np.array([[0, 0, 0, 1]]), use_f=False, scalar=True)\nw_int = fi.wald_test(np.array([[0, 0, 1, 0]]), use_f=False, scalar=True)\n\nsens = {str(L)''')\ns=s.replace(''' \"n_window_quarters\"''',''' \"hac_wald_joint_p\": float(w_joint.pvalue), \"hac_wald_slope_diff_p\": float(w_slope.pvalue),\n \"hac_wald_intercept_diff_p\": float(w_int.pvalue),\n \"okun_growth_sub1\": float(-f1.params[0] / f1.params[1]), \"okun_growth_sub2\": float(-f2.params[0] / f2.params[1]),\n \"n_window_quarters\"''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && grep -E \"wald|okun\" out/results.json","description":"Add HAC Wald robustness tests"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"824bbf19-9816-41f0-8bf2-4e379305b58d","timestamp":"2026-10-30T04:51:19.782Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"02ed83ba-39cc-4b3f-baf5-bd43ec19431e","keep":16,"tail":["d6197aefa19e67134ae730418abdf73ae8951509e8e736a75a3ce035c7bf47fb","66457f998edb8ee99678399255926add842d29a85ba03c7a2f0f02a228f52b0d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"536bd14d31fcbbf92f4ede892a182a81a46fb679e2b7d325d69c1a09cad61375"} {"parentUuid":"87a99b2b-99d7-436b-b265-bf7f5eae8d64","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZD56kFEG4iCwdQPMf","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":1084,"cache_read_input_tokens":20497,"output_tokens":1395,"output_tokens_details":{"thinking_tokens":118},"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":1084},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1061,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpZCpUc34e8ta5Qk8x6","requestRef":"824bbf19-9816-41f0-8bf2-4e379305b58d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ba523da3-1b4c-441a-baeb-cdd6c954624f","timestamp":"2026-10-30T04:51:22.483Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"ba523da3-1b4c-441a-baeb-cdd6c954624f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpZD56kFEG4iCwdQPMf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FsBjCLWjEsWvMbewgHs9ja","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && md5 -q out/table1.csv > /tmp/t1 && rm out/results.json out/table1.csv out/figure1.png out/exclusions.csv && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL && [ \"$(md5 -q out/table1.csv)\" = \"$(cat /tmp/t1)\" ] && echo TABLE_IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json'))\nc=[]\nc.append((\"n_sub1+n_sub2==n_analysed==240\", r['n_sub1']+r['n_sub2']==r['n_analysed']==240))\nc.append((\"n_sub1==96,n_sub2==144\", (r['n_sub1'],r['n_sub2'])==(96,144)))\nc.append((\"se>0\", r['effect_se']>0))\nc.append((\"ci contains estimate\", r['effect_ci_low']0\", 00))\nc.append((\"stability code consistent\", r['stability_conclusion']==('unstable' if r['chow_p_value']<0.05 else 'stable')))\nc.append((\"conclusion code consistent\", r['conclusion']=='negative_effect' and r['effect_ci_high']<0))\nc.append((\"alpha+beta*mean_g==mean_du (OLS identity)\", abs(r['intercept']+r['effect_estimate']*r['mean_g']-r['mean_du'])<1e-10))\nt=pd.read_csv('out/table1.csv'); c.append((\"table matches results\", np.isclose(t.slope[0],r['effect_estimate']) and np.isclose(t.slope[1],r['beta_sub1']) and np.isclose(t.slope[2],r['beta_sub2']) and len(t)==3))\ne=pd.read_csv('out/exclusions.csv'); c.append((\"exclusions sum: 241-1=240\", e.n_before[0]-e.n_removed.sum()==r['n_analysed']))\nc.append((\"n_input_rows match README (319,945)\", r['n_input_rows']=={'GDPC1.csv':319,'UNRATE.csv':945}))\nc.append((\"beta magnitude plausible (Okun ~ -0.2..-0.5 q/q)\", -0.60: PASS\n- ci contains estimate: PASS\n- ci symmetric width 2*1.96*se: PASS\n- model_metric<=baseline_metric: PASS\n- R2 identity 1-(model/baseline)^2: PASS\n- sample_start0: PASS\n- stability code consistent: PASS\n- conclusion code consistent: PASS\n- alpha+beta*mean_g==mean_du (OLS identity): PASS\n- table matches results: PASS\n- exclusions sum: 241-1=240: PASS\n- n_input_rows match README (319,945): PASS\n- beta magnitude plausible (Okun ~ -0.2..-0.5 q/q): PASS","is_error":false}]},"uuid":"b297d563-0a9c-41d0-ac17-22de678fd4f8","timestamp":"2026-10-30T04:51:33.162Z","toolUseResult":{"stdout":"IDENTICAL\nTABLE_IDENTICAL\n- n_sub1+n_sub2==n_analysed==240: PASS\n- n_sub1==96,n_sub2==144: PASS\n- se>0: PASS\n- ci contains estimate: PASS\n- ci symmetric width 2*1.96*se: PASS\n- model_metric<=baseline_metric: PASS\n- R2 identity 1-(model/baseline)^2: PASS\n- sample_start0: PASS\n- stability code consistent: PASS\n- conclusion code consistent: PASS\n- alpha+beta*mean_g==mean_du (OLS identity): PASS\n- table matches results: PASS\n- exclusions sum: 241-1=240: PASS\n- n_input_rows match README (319,945): PASS\n- beta magnitude plausible (Okun ~ -0.2..-0.5 q/q): PASS","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"06124091-a77a-41e1-94e2-e45c9c06ac70","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"91510eba5edb3e90df3b174f634768ae50bae9f131f15326830daefa7c89db58","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01FsBjCLWjEsWvMbewgHs9ja","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && md5 -q out/table1.csv > /tmp/t1 && rm out/results.json out/table1.csv out/figure1.png out/exclusions.csv && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL && [ \"$(md5 -q out/table1.csv)\" = \"$(cat /tmp/t1)\" ] && echo TABLE_IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json'))\nc=[]\nc.append((\"n_sub1+n_sub2==n_analysed==240\", r['n_sub1']+r['n_sub2']==r['n_analysed']==240))\nc.append((\"n_sub1==96,n_sub2==144\", (r['n_sub1'],r['n_sub2'])==(96,144)))\nc.append((\"se>0\", r['effect_se']>0))\nc.append((\"ci contains estimate\", r['effect_ci_low']0\", 00))\nc.append((\"stability code consistent\", r['stability_conclusion']==('unstable' if r['chow_p_value']<0.05 else 'stable')))\nc.append((\"conclusion code consistent\", r['conclusion']=='negative_effect' and r['effect_ci_high']<0))\nc.append((\"alpha+beta*mean_g==mean_du (OLS identity)\", abs(r['intercept']+r['effect_estimate']*r['mean_g']-r['mean_du'])<1e-10))\nt=pd.read_csv('out/table1.csv'); c.append((\"table matches results\", np.isclose(t.slope[0],r['effect_estimate']) and np.isclose(t.slope[1],r['beta_sub1']) and np.isclose(t.slope[2],r['beta_sub2']) and len(t)==3))\ne=pd.read_csv('out/exclusions.csv'); c.append((\"exclusions sum: 241-1=240\", e.n_before[0]-e.n_removed.sum()==r['n_analysed']))\nc.append((\"n_input_rows match README (319,945)\", r['n_input_rows']=={'GDPC1.csv':319,'UNRATE.csv':945}))\nc.append((\"beta magnitude plausible (Okun ~ -0.2..-0.5 q/q)\", -0.6='1959-10-01')&(u.d<'2020-01-01')]\nuq=u.UNRATE.values.reshape(-1,3).mean(1)\ng['d']=pd.to_datetime(g.observation_date); g=g[(g.d>='1959-10-01')&(g.d<'2020-01-01')]\ny=np.diff(uq); x=100*np.diff(np.log(g.GDPC1.values))\nX=np.c_[np.ones(240),x]; b=np.linalg.lstsq(X,y,rcond=None)[0]; print('indep beta',b)\ndef ssr(sl): bb=np.linalg.lstsq(X[sl],y[sl],rcond=None)[0]; return ((y[sl]-X[sl]@bb)**2).sum()\nS=ssr(slice(None));S1=ssr(slice(0,96));S2=ssr(slice(96,None))\nprint('indep chow',((S-S1-S2)/2)/((S1+S2)/236))\nEOF","description":"Independent numpy recomputation of beta and Chow"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1727,"cache_read_input_tokens":21581,"output_tokens":686,"output_tokens_details":{"thinking_tokens":80},"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":1727},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpaC3Nj2A7tvQzDCz2z","requestRef":"7f73f883-7ad5-43eb-a748-3370d23a036f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"febbe8a1-30c6-4661-962e-0652f9631d52","timestamp":"2026-10-30T04:51:39.118Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"febbe8a1-30c6-4661-962e-0652f9631d52","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013b3u1wfqYYpWpdkbp6oJ3D","type":"tool_result","content":"indep beta [ 0.18438835 -0.25576773]\nindep chow 6.090333006233767","is_error":false}]},"uuid":"3658f3d2-9531-4656-8a11-3ded553e1b04","timestamp":"2026-10-30T04:51:39.421Z","toolUseResult":{"stdout":"indep beta [ 0.18438835 -0.25576773]\nindep chow 6.090333006233767","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"febbe8a1-30c6-4661-962e-0652f9631d52","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"3658f3d2-9531-4656-8a11-3ded553e1b04","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpaCKys4mA4v6soGBTi","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013FrBafs15RAyaKuUYeZwyz","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0174/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":1727,"cache_read_input_tokens":21581,"output_tokens":686,"output_tokens_details":{"thinking_tokens":80},"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":1727},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpaC3Nj2A7tvQzDCz2z","requestRef":"7f73f883-7ad5-43eb-a748-3370d23a036f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0649b935-53f3-4f02-b97f-b4a0601b1e1d","timestamp":"2026-10-30T04:51:39.550Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"0649b935-53f3-4f02-b97f-b4a0601b1e1d","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013FrBafs15RAyaKuUYeZwyz","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"5f834443-79c4-4204-825b-f35b5f71435a","timestamp":"2026-10-30T04:51:39.558Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":94562,"dimensions":{"originalWidth":1050,"originalHeight":750,"displayWidth":1050,"displayHeight":750}}},"sourceToolAssistantUUID":"0649b935-53f3-4f02-b97f-b4a0601b1e1d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"8eaf790c3245348766f9c1212bb512f42f75ae68909bb72539e81547806fe5a1","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS8QcKEAgTGAI4AUIIdGhpbmtpbmcSDMm8zGQhaViQoC5gShoM1zK4cqdLisKvJEu0IjDtzYafnDlE81c1IXHs6bJXiytzoehd8qpEQ816U1N/6V7zpHL8biNRPa+VCatoU8cqjgdeM5nLk/jENCBEGcckKHiRWkn0C+2Bg+aDs8gUIcm6Ww1w3XXa4LN6rOnHEHQmFK7ShsJ8J5ILcyWg97AHNnDz4w9/LiE91E8AW8m6YmIm52u9SIDYGYNseoApaElWQGZCFB0BvEad5x2psHrSGifoI75Mygg5ZXI1OvdRfxrpH+BPXtTPyTQrArRqJlQ8Y39dWxwsRHqZtKXbJhvW+b/jO4l9dgZ4IIh8B8/MWPw3WU2+t6azEkX/RTA600X0pcuWP4s3lFJKpAhv31GW8onzaP9NmEee2cYr5NKoe58Y/KNANgzkL8+IzbzLnC2v2+rRlFQ7Z+jSI0122virWfIPtjzNtpECrr70goSC0E08XR1K34PpY12kAkgU6iTNLix+CgZ56wtjf8W4McW+4+mwR2LxBB8T2lTmdipcHf6OC69eI5aeAWJj+icO2qejIgT+9LPl/B4G4Wf+6hgeIHR2C4LUClPSXnAvPnbQ+XOdvRvigQrDsjHDlexeU+IjnI6aByFf2EtJTldMgucpClZjOGOe78PS3Uyw610l+UHM+jYcmaWYV4+gFTwfdyO9DD+O3dUCjT7ryb+F7jIOPkBxrU7nRPySr+iOnNUMtdbx6vOjQ/Ihe6kCRupTY/sCahiToKM8/Y4kXtrZanUtatwRZNp4+LCTtgP9CRyKw0vqXQYNbhwLnp/ELCmNyOQre/T/fibqMLyU1cupK6qotoEI3VBJtoYAeOMgGcdAc0LPSAU8+MFUBQS07S5HrJIJQrpsqskDu3BBXWqlanGbKkcvIefnb4WmADklelFStQxue3UsHKS9e3JMiTJJV9YsjSX9Nb5FjtrzloqQylVyxGQ4A6wijRNQD9qgm3AdNzh5Yckc5xlp4CQtHbmSUbaZi9Z27OYqgChjujWQHeDZ50jBLvajU4Af+GzoDiqkj4Hj4rW1UQY4YrXjszr4WzZ6+F3UDqjnmIcGkwjer0iH+Bel5wWbX9ICFfCU2OhbHhmcoQVT/0a7JvKE1XFl1JLeRy5OupTwK7wOuDTWCpoGLQkOYfvZ7p+s6HLGLKMRZq9aj1m0d7v0Bkdf9tzjJT2guFWwLQHftywal3dRzGgvEycHN5fvprYrvk+EincDdD0rb8KRucWAVU94hWpUmEZQJdzLe5B281CAS4SAuNcPFjjFPg8r5G/BqDau/WtLBuPoCytohX7b/y0G11DQD0NfGAE="},{"type":"tool_use","id":"toolu_013b3u1wfqYYpWpdkbp6oJ3D","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd,numpy as np\nu=pd.read_csv('data/UNRATE.csv'); g=pd.read_csv('data/GDPC1.csv')\nu['d']=pd.to_datetime(u.observation_date); u=u[(u.d>='1959-10-01')&(u.d<'2020-01-01')]\nuq=u.UNRATE.values.reshape(-1,3).mean(1)\ng['d']=pd.to_datetime(g.observation_date); g=g[(g.d>='1959-10-01')&(g.d<'2020-01-01')]\ny=np.diff(uq); x=100*np.diff(np.log(g.GDPC1.values))\nX=np.c_[np.ones(240),x]; b=np.linalg.lstsq(X,y,rcond=None)[0]; print('indep beta',b)\ndef ssr(sl): bb=np.linalg.lstsq(X[sl],y[sl],rcond=None)[0]; return ((y[sl]-X[sl]@bb)**2).sum()\nS=ssr(slice(None));S1=ssr(slice(0,96));S2=ssr(slice(96,None))\nprint('indep chow',((S-S1-S2)/2)/((S1+S2)/236))\nEOF","description":"Independent numpy recomputation of beta and Chow"}},{"type":"tool_use","id":"toolu_013FrBafs15RAyaKuUYeZwyz","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0174/out/figure1.png"}}]}} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"b61ec1f00490ad3b198fc563ea2682144c7b6be14de59d942c24072ea8ee6e64","message":{"role":"user","content":[{"tool_use_id":"toolu_013b3u1wfqYYpWpdkbp6oJ3D","type":"tool_result","content":"indep beta [ 0.18438835 -0.25576773]\nindep chow 6.090333006233767","is_error":false},{"tool_use_id":"toolu_013FrBafs15RAyaKuUYeZwyz","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"4e8faa18-d0f4-4a94-9985-2fb22d01dfb3","timestamp":"2026-10-30T04:51:39.569Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"7f73f883-7ad5-43eb-a748-3370d23a036f","keep":20,"tail":["8eaf790c3245348766f9c1212bb512f42f75ae68909bb72539e81547806fe5a1","b61ec1f00490ad3b198fc563ea2682144c7b6be14de59d942c24072ea8ee6e64"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"4466a41e787bea526b047fc53f5b254c1fc520f28572e9a424971354a933612e"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"5f834443-79c4-4204-825b-f35b5f71435a","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"atis-latch","atis":"","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":"5f834443-79c4-4204-825b-f35b5f71435a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpaftBnQuRABtSrJBc9","type":"message","role":"assistant","content":[{"type":"text","text":"Good. Now the audit, checks, and state files, then gate."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1806,"cache_read_input_tokens":23308,"output_tokens":2047,"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":1806},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpafStk2gWChAooVRHJ","requestRef":"4e8faa18-d0f4-4a94-9985-2fb22d01dfb3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8c9cae8c-d5ae-4ea3-80ce-21997711c886","timestamp":"2026-10-30T04:51:41.518Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"8c9cae8c-d5ae-4ea3-80ce-21997711c886","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpaftBnQuRABtSrJBc9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XgbApnsscpmZEdZiJa4QFv","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\n| file | SHA-256 | rows (excl. header) | cols | range | missing | dup dates |\n|---|---|---|---|---|---|---|\n| data/GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01, quarterly, no gaps | 0 | 0 |\n| data/UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01, monthly, no date gaps | 1 (2025-10-01 empty value) | 0 |\n| data/README.md | 7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 | – | – | – | – | – |\n\nUnits: GDPC1 billions of chained 2017 USD, SAAR (range 2172–24611); UNRATE percent SA (range 2.5–14.8). No non-numeric values except the one empty UNRATE cell.\n\nAnomalies / decisions:\n- UNRATE 2025-10 missing (outside window; irrelevant). Rule: quarters are averaged only when 3 valid months exist; no imputation.\n- Both series extend to 2026 → violate the \"no post-2019Q4\" rule if used; truncated to 1959Q4–2019Q4 before any computation. 1959Q4 used only as lag level.\n- Window 1959Q4–2019Q4: 241 complete, consecutive quarters in both series (asserted in code). After differencing: 240 = 1960Q1–2019Q4.\n- GDPC1 is a 2026 vintage, not real-time; acceptable since the question is historical; noted as limitation.\nEOF\ncat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n\nReproducibility: deleted out/results.json, table1.csv, figure1.png, exclusions.csv; re-ran `out/analysis.py`; results.json byte-identical (cmp) and table1.csv identical md5 → PASS.\n\nIndependent recomputation (plain numpy lstsq, reshaping monthly into quarters): β = −0.25576773, α = 0.18438835, Chow F = 6.0903330 — identical to script → PASS.\n\nInternal consistency (all PASS):\n- n_sub1+n_sub2 = n_analysed = 240; n_sub1 = 96, n_sub2 = 144\n- effect_se > 0; CI contains estimate; CI width = 2·1.95996·SE\n- model_metric ≤ baseline_metric; R² = 1 − (model/baseline)² identity holds\n- sample_start < sample_end; dates 1960-01-01 / 2019-10-01 (no post-2019Q4 quarter)\n- Chow F > 0, p in (0,1), df (2, 236); stability_conclusion consistent with p < 0.05\n- conclusion = negative_effect consistent with CI upper bound < 0\n- OLS identity α + β·mean(g) = mean(Δu)\n- table1.csv slopes equal results keys; 3 rows\n- exclusion ledger: 241 − 1 = 240 = n_analysed\n- n_input_rows match README row counts (319, 945)\n- magnitude: β ≈ −0.26 per 1% q/q growth, within conventional Okun range; HAC SE stable across lags 2–12 (0.034–0.037)\n- figure inspected visually: two subperiod lines, labelled axes.\nEOF\ncat > 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 inputs computed and match README\",\"row/col counts, ranges, missing, duplicates recorded in data_audit.md\",\"exclusions.csv written and sums (241-1=240)\",\"availability violation (post-2019 rows) identified and handled by truncation\"],\"notes\":\"\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) computed over the same 240-quarter sample\"],\"notes\":\"baseline_metric=0.3247\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png deterministically; no randomness (random_seed null)\"],\"notes\":\"\"},\n\"P4\":{\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json and table1.csv\",\"independent numpy recomputation of beta and Chow F matches\",\"17 consistency checks PASS (checks.md)\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: data audited; post-2019 rows truncated; UNRATE 2025-10 NaN outside window.\n- 2026-10-30 P2/P3 passed: baseline RMSE and OLS/HAC(4 lags, NW rule)/Chow computed. Decision: HAC without small-sample correction, normal-based CI; subperiod SEs HAC with NW rule lags. Supplementary HAC Wald tests added.\n- 2026-10-30 P4 checks run, all PASS; running gate.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Write audit/checks/state and run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1806,"cache_read_input_tokens":23308,"output_tokens":2047,"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":1806},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpafStk2gWChAooVRHJ","requestRef":"4e8faa18-d0f4-4a94-9985-2fb22d01dfb3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7a90963c-39fd-457f-8ccd-17c9baf9b1a1","timestamp":"2026-10-30T04:51:58.398Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"7a90963c-39fd-457f-8ccd-17c9baf9b1a1","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 48 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:sample_start: ok\n [ok] key:sample_end: ok\n [ok] key:n_sub1: ok\n [ok] key:n_sub2: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:intercept: ok\n [ok] key:effect_se: ok\n [ok] key:hac_lags: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:beta_sub1: ok\n [ok] key:beta_sub2: ok\n [ok] key:chow_f_stat: ok\n [ok] key:chow_p_value: ok\n [ok] key:stability_conclusion: ok\n [ok] key:conclusion: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 1 steps consistent\n [ok] ci:effect_estimate: -0.32600231842173816 <= -0.2557677277487258 <= -0.18553313707571345\n [ok] positive:effect_se: 0.03583463330296569\n [ok] positive:chow_f_stat: 6.0903330062337675\n [ok] positive:baseline_metric: 0.32465793964999184\n [ok] positive:model_metric: 0.2497438816636253\n [ok] chronology:sample_start<=sample_end: 1960-01-01 vs 2019-10-01\n [ok] reproducibility: regenerated in 1.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0174/out/state/gate_receipts/20261030T045159.646436Z.json","is_error":true,"tool_use_id":"toolu_01XgbApnsscpmZEdZiJa4QFv"}]},"uuid":"8f198edf-c04e-4edc-8ed9-2849167e2b2c","timestamp":"2026-10-30T04:51:59.654Z","toolUseResult":"Error: Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 48 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:sample_start: ok\n [ok] key:sample_end: ok\n [ok] key:n_sub1: ok\n [ok] key:n_sub2: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:intercept: ok\n [ok] key:effect_se: ok\n [ok] key:hac_lags: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:beta_sub1: ok\n [ok] key:beta_sub2: ok\n [ok] key:chow_f_stat: ok\n [ok] key:chow_p_value: ok\n [ok] key:stability_conclusion: ok\n [ok] key:conclusion: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 1 steps consistent\n [ok] ci:effect_estimate: -0.32600231842173816 <= -0.2557677277487258 <= -0.18553313707571345\n [ok] positive:effect_se: 0.03583463330296569\n [ok] positive:chow_f_stat: 6.0903330062337675\n [ok] positive:baseline_metric: 0.32465793964999184\n [ok] positive:model_metric: 0.2497438816636253\n [ok] chronology:sample_start<=sample_end: 1960-01-01 vs 2019-10-01\n [ok] reproducibility: regenerated in 1.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0174/out/state/gate_receipts/20261030T045159.646436Z.json","sandboxed":false,"sourceToolAssistantUUID":"7a90963c-39fd-457f-8ccd-17c9baf9b1a1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"31835db7190e11d8a0236650f2cc50f517f5f59fd02905a0cb96a2075cc8f520","message":{"role":"assistant","content":[{"type":"text","text":"Good. Now the audit, checks, and state files, then gate."},{"type":"tool_use","id":"toolu_01XgbApnsscpmZEdZiJa4QFv","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\n| file | SHA-256 | rows (excl. header) | cols | range | missing | dup dates |\n|---|---|---|---|---|---|---|\n| data/GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1) | 1947-01-01 – 2026-07-01, quarterly, no gaps | 0 | 0 |\n| data/UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE) | 1948-01-01 – 2026-09-01, monthly, no date gaps | 1 (2025-10-01 empty value) | 0 |\n| data/README.md | 7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658 | – | – | – | – | – |\n\nUnits: GDPC1 billions of chained 2017 USD, SAAR (range 2172–24611); UNRATE percent SA (range 2.5–14.8). No non-numeric values except the one empty UNRATE cell.\n\nAnomalies / decisions:\n- UNRATE 2025-10 missing (outside window; irrelevant). Rule: quarters are averaged only when 3 valid months exist; no imputation.\n- Both series extend to 2026 → violate the \"no post-2019Q4\" rule if used; truncated to 1959Q4–2019Q4 before any computation. 1959Q4 used only as lag level.\n- Window 1959Q4–2019Q4: 241 complete, consecutive quarters in both series (asserted in code). After differencing: 240 = 1960Q1–2019Q4.\n- GDPC1 is a 2026 vintage, not real-time; acceptable since the question is historical; noted as limitation.\nEOF\ncat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n\nReproducibility: deleted out/results.json, table1.csv, figure1.png, exclusions.csv; re-ran `out/analysis.py`; results.json byte-identical (cmp) and table1.csv identical md5 → PASS.\n\nIndependent recomputation (plain numpy lstsq, reshaping monthly into quarters): β = −0.25576773, α = 0.18438835, Chow F = 6.0903330 — identical to script → PASS.\n\nInternal consistency (all PASS):\n- n_sub1+n_sub2 = n_analysed = 240; n_sub1 = 96, n_sub2 = 144\n- effect_se > 0; CI contains estimate; CI width = 2·1.95996·SE\n- model_metric ≤ baseline_metric; R² = 1 − (model/baseline)² identity holds\n- sample_start < sample_end; dates 1960-01-01 / 2019-10-01 (no post-2019Q4 quarter)\n- Chow F > 0, p in (0,1), df (2, 236); stability_conclusion consistent with p < 0.05\n- conclusion = negative_effect consistent with CI upper bound < 0\n- OLS identity α + β·mean(g) = mean(Δu)\n- table1.csv slopes equal results keys; 3 rows\n- exclusion ledger: 241 − 1 = 240 = n_analysed\n- n_input_rows match README row counts (319, 945)\n- magnitude: β ≈ −0.26 per 1% q/q growth, within conventional Okun range; HAC SE stable across lags 2–12 (0.034–0.037)\n- figure inspected visually: two subperiod lines, labelled axes.\nEOF\ncat > 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 inputs computed and match README\",\"row/col counts, ranges, missing, duplicates recorded in data_audit.md\",\"exclusions.csv written and sums (241-1=240)\",\"availability violation (post-2019 rows) identified and handled by truncation\"],\"notes\":\"\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE) computed over the same 240-quarter sample\"],\"notes\":\"baseline_metric=0.3247\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png deterministically; no randomness (random_seed null)\"],\"notes\":\"\"},\n\"P4\":{\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json and table1.csv\",\"independent numpy recomputation of beta and Chow F matches\",\"17 consistency checks PASS (checks.md)\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: data audited; post-2019 rows truncated; UNRATE 2025-10 NaN outside window.\n- 2026-10-30 P2/P3 passed: baseline RMSE and OLS/HAC(4 lags, NW rule)/Chow computed. Decision: HAC without small-sample correction, normal-based CI; subperiod SEs HAC with NW rule lags. Supplementary HAC Wald tests added.\n- 2026-10-30 P4 checks run, all PASS; running gate.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Write audit/checks/state and run gate"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"c9d51279-25ca-4d6a-8026-f9f93039399d","timestamp":"2026-10-30T04:51:59.658Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"4e8faa18-d0f4-4a94-9985-2fb22d01dfb3","keep":22,"tail":["31835db7190e11d8a0236650f2cc50f517f5f59fd02905a0cb96a2075cc8f520","c7a0492014a23b27f75deb3de13a6b08b330706f8abb97632db206ffbb473292"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ffabe62595a186ea90ceb3c2eeb59d516364e10627df7b3d5eb8d2a8f406d803"} {"parentUuid":"8f198edf-c04e-4edc-8ed9-2849167e2b2c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpc9c664uDBuAJQXPT4","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":3088,"cache_read_input_tokens":25114,"output_tokens":4430,"output_tokens_details":{"thinking_tokens":47},"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":3088},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":800,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpc9KUTwbRAbrQzriTV","requestRef":"c9d51279-25ca-4d6a-8026-f9f93039399d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d1df169e-8c46-41d9-9221-b2e19350f53d","timestamp":"2026-10-30T04:52:02.563Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"d1df169e-8c46-41d9-9221-b2e19350f53d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpc9c664uDBuAJQXPT4","type":"message","role":"assistant","content":[{"type":"text","text":"Expected failures are only P5 deliverables; all P4-relevant checks (keys, CI, positivity, reproducibility) pass. Now the report and claims."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3088,"cache_read_input_tokens":25114,"output_tokens":4430,"output_tokens_details":{"thinking_tokens":47},"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":3088},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpc9KUTwbRAbrQzriTV","requestRef":"c9d51279-25ca-4d6a-8026-f9f93039399d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aaba0bda-ad75-4626-b9ea-0cbee065b6f2","timestamp":"2026-10-30T04:52:02.564Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"aaba0bda-ad75-4626-b9ea-0cbee065b6f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpc9c664uDBuAJQXPT4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_012odCuzrboCte5MHRZ7RNXe","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960Q1–2019Q4 (task F6-conf-03)\n\n## Question\nHow strongly does the quarterly change in the US unemployment rate (Δu_t, pp) respond to quarterly real GDP growth (g_t = 100·Δln GDPC1, % not annualised), in Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, and is (α, β) stable between 1960Q1–1983Q4 and 1984Q1–2019Q4? β is a reduced-form association (an \"Okun coefficient\"), not a structural causal effect.\n\n## Data and exclusions\n- `data/GDPC1.csv` (319 rows) and `data/UNRATE.csv` (945 rows) (`n_input_rows`); SHA-256 of both match `data/README.md` (see `out/state/data_audit.md`).\n- Quarterly u_t = mean of the three monthly UNRATE values; a quarter is formed only when all three months are present. The only missing monthly value (2025-10) lies outside the window and has no effect (`data_issues`).\n- Both series run to 2026; everything after 2019Q4 is cut before any computation. The window 1959Q4–2019Q4 holds 241 consecutive complete quarters (`n_window_quarters`). Dropping 1959Q4, which is used only as the lagged level, leaves 240 analysed quarters (`n_analysed`) from `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01. `out/exclusions.csv` records this step (241 − 1 = 240). Subperiods: 96 quarters (`n_sub1`) and 144 quarters (`n_sub2`).\n- The GDP data are the 2026 FRED vintage (chained 2017 dollars), not real-time data (`data_issues`).\n\n## Method\n- Baseline: predict Δu by its sample mean; the RMSE is `baseline_metric`.\n- Main model: full-sample OLS of Δu_t on a constant and g_t. The in-sample residual RMSE is `model_metric`.\n- Standard errors: Newey–West HAC with a Bartlett kernel. The lag length is set by the Newey–West (1994) rule floor(4·(T/100)^{2/9}), which gives 4 quarters for T = 240 (`hac_lags`). No small-sample df correction is applied. The 95% CI is β ± 1.96·SE (normal approximation).\n- Stability: separate OLS fits on each subperiod (`beta_sub1`, `beta_sub2`). Classical Chow F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n − 4)], with df (2, 236) (`chow_df`). Supplementary check: a HAC Wald test in a fully interacted model with a 1984Q1 dummy (`hac_wald_joint_p`, `hac_wald_slope_diff_p`, `hac_wald_intercept_diff_p`).\n- Deliverables: `out/table1.csv` (full sample and both subperiods; the subperiod slope SEs are HAC with NW-rule lags, `hac_lags_sub1`, `hac_lags_sub2`) and `out/figure1.png`, both written by `out/analysis.py`. No randomness is used (`random_seed` = null).\n\n## Results\n- Full sample: β = −0.256 (`effect_estimate`) and α = 0.184 pp (`intercept`). Each extra 1% of quarterly real GDP growth goes with about a 0.26 pp smaller rise in the unemployment rate in the same quarter. The growth rate at which unemployment is flat is about 0.98% per quarter before 1984 (`okun_growth_sub1`) and 0.55% after (`okun_growth_sub2`).\n- Fit: 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- Subperiod slopes are almost the same: −0.259 for 1960–1983 (`beta_sub1`) and −0.273 for 1984–2019 (`beta_sub2`). Intercepts are 0.254 (`intercept_sub1`) and 0.152 (`intercept_sub2`).\n- Chow test: F = 6.09 (`chow_f_stat`), p = 0.0026 (`chow_p_value`), which rejects joint equality of (α, β) at 5%. The task's coding rule therefore gives `stability_conclusion` = \"unstable\". The rejection concerns the (α, β) pair jointly. The slope point estimates hardly differ, and the HAC test of the slope difference alone gives p = 0.85 (`hac_wald_slope_diff_p`). What shifted is mainly the fitted line's level, i.e. the growth rate consistent with stable unemployment. However, the HAC test of the intercept alone is also not significant (p = 0.25, `hac_wald_intercept_diff_p`). The joint HAC test still rejects (p = 0.0042, `hac_wald_joint_p`) because the intercept and slope estimates are strongly correlated.\n- `conclusion` = \"negative_effect\": the 95% CI lies entirely below zero.\n\n## Uncertainty\n- HAC SE of β = 0.0358 (`effect_se`, 4 lags). 95% CI: [−0.326, −0.186] (`effect_ci_low`, `effect_ci_high`).\n- The classical OLS SE is 0.0200 (`ols_classical_se`), so allowing for heteroskedasticity and autocorrelation makes the SE about 1.8 times larger.\n- Sensitivity to the lag length (`hac_se_by_lag`): 0.029 (0 lags), 0.034 (2), 0.036 (4), 0.037 (8), 0.036 (12). The sign conclusion holds for every lag length.\n- Subperiod HAC SEs: 0.039 (`beta_sub1_hac_se`) and 0.068 (`beta_sub2_hac_se`).\n\n## Limitations and open issues\n- **The classical Chow test's assumptions are probably violated.** It assumes homoskedastic, serially uncorrelated errors with equal variance in both subperiods. Three things point the other way: HAC SEs are clearly larger than classical ones, residual variance probably differs between the two periods (Great Moderation), and there are visible large-residual quarters (e.g. 1980, 2008–09). The F-test's size may therefore be off. The HAC Wald test also rejects jointly (`hac_wald_joint_p`), which supports the rejection. But I did not test variance equality and did not run a Chow test with unequal variances.\n- **The \"unstable\" verdict depends on the break date.** The split at 1984Q1 is imposed. I did not search over break dates (no Quandt–Andrews or Bai–Perron test). The instability is in the intercept/slope pair, not in the slope point estimate, so it should not be read as \"Okun's coefficient changed\".\n- **Specification threats.** The model is static and contemporaneous, with no lags of g or Δu. Okun dynamics, a trend-growth slowdown (which shows up as an intercept shift), and possible nonlinearity or asymmetry between recessions and expansions were not modelled. Measurement error in quarterly GDP growth would bias β towards zero. Simultaneity means β is not causal.\n- **Data vintage.** The 2026 vintage GDPC1 includes benchmark revisions. Real-time estimates would differ, and I did not check how sensitive the results are to vintage.\n- **Inference choices.** The lag rule is ad hoc, but results barely change with lag length. The CI uses a normal rather than t approximation (negligible difference at n = 240). With only 96 and 144 quarters, the subperiod HAC SEs are less reliable.\n- **What would invalidate the result:** errors in quarterly aggregation (checked by independent recomputation, see `out/state/checks.md`), any leakage of post-2019 data (excluded by construction and assertions), or a different definition of g (e.g. annualised, which would scale β by 1/4).\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4 the full-sample OLS Okun coefficient is about -0.26 pp per 1% quarterly real GDP growth, with intercept about 0.18 pp.\",\"results_keys\":[\"effect_estimate\",\"intercept\",\"n_analysed\",\"sample_start\",\"sample_end\"],\"status\":\"supported\",\"caveat\":\"Reduced-form association, not causal; 2026 data vintage.\"},\n {\"id\":\"C2\",\"text\":\"The HAC (Newey-West, 4 lags) 95% CI for beta, [-0.326, -0.186], lies entirely below zero, so conclusion = negative_effect.\",\"results_keys\":[\"effect_se\",\"hac_lags\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Normal approximation; conclusion robust to lags 0-12 (hac_se_by_lag).\"},\n {\"id\":\"C3\",\"text\":\"Output growth explains a substantial share of quarterly unemployment changes: residual RMSE 0.250 pp vs 0.325 pp for the mean-only baseline (R2 about 0.41).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"r_squared\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C4\",\"text\":\"Subperiod slopes are nearly identical (-0.259 for 1960-1983, -0.273 for 1984-2019); the HAC test of the slope difference alone does not reject.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"hac_wald_slope_diff_p\",\"beta_sub1_hac_se\",\"beta_sub2_hac_se\"],\"status\":\"supported\",\"caveat\":\"Imposed break date.\"},\n {\"id\":\"C5\",\"text\":\"The classical Chow test rejects joint equality of (alpha, beta) across the 1984Q1 split (F = 6.09, p = 0.0026), so stability_conclusion = unstable; a HAC Wald joint test also rejects.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"chow_df\",\"hac_wald_joint_p\"],\"status\":\"supported\",\"caveat\":\"Classical Chow assumes homoskedastic, serially uncorrelated, equal-variance errors, likely violated; break date imposed; instability concerns the (alpha,beta) pair, not the slope.\"},\n {\"id\":\"C6\",\"text\":\"The growth rate consistent with stable unemployment (-alpha/beta) fell from about 0.98% to about 0.55% per quarter between subperiods.\",\"results_keys\":[\"okun_growth_sub1\",\"okun_growth_sub2\",\"intercept_sub1\",\"intercept_sub2\"],\"status\":\"supported\",\"caveat\":\"Point estimates only; the HAC test of the intercept difference alone is not significant (hac_wald_intercept_diff_p = 0.25).\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']['status']='passed'; p['P4']['checks'].append('gate run 20261030T045159.646436Z: all P4-relevant checks ok (keys, CI, positivity, chronology, exclusions, reproducibility); failures only for P5 deliverables not yet written (report, claims, phase ledger)')\np['P4']['notes']='gate receipt out/state/gate_receipts/20261030T045159.646436Z.json'\np['P5']['status']='passed'; p['P5']['checks']=['report.md written with 6 sections citing results keys','claims.json written, all keys exist','final gate run (see notes)']\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nr=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')\nEOF\necho \"- 2026-10-30 P4 passed (gate receipt 20261030T045159). P5: report and claims written; running final gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"FAIL|GATE|receipt\"","description":"Write report, claims, update ledger, run final gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3088,"cache_read_input_tokens":25114,"output_tokens":4430,"output_tokens_details":{"thinking_tokens":47},"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":3088},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpc9KUTwbRAbrQzriTV","requestRef":"c9d51279-25ca-4d6a-8026-f9f93039399d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e43615bc-6641-4954-b915-18df7c278145","timestamp":"2026-10-30T04:52:37.660Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e43615bc-6641-4954-b915-18df7c278145","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"atis-latch","atis":"","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"parentUuid":"e43615bc-6641-4954-b915-18df7c278145","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_012odCuzrboCte5MHRZ7RNXe","type":"tool_result","content":"claims keys ok\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0174/out/state/gate_receipts/20261030T045238.918440Z.json","is_error":false}]},"uuid":"de680804-78fc-4431-826c-2b25b84f962b","timestamp":"2026-10-30T04:52:38.927Z","toolUseResult":{"stdout":"claims keys ok\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0174/out/state/gate_receipts/20261030T045238.918440Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e43615bc-6641-4954-b915-18df7c278145","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"4ee2a63739eee00ba68fdc0e3cb162d72fc309c1aca08fe307c406a17eaa9dea","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Expected failures are only P5 deliverables; all P4-relevant checks (keys, CI, positivity, reproducibility) pass. Now the report and claims."},{"type":"tool_use","id":"toolu_012odCuzrboCte5MHRZ7RNXe","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960Q1–2019Q4 (task F6-conf-03)\n\n## Question\nHow strongly does the quarterly change in the US unemployment rate (Δu_t, pp) respond to quarterly real GDP growth (g_t = 100·Δln GDPC1, % not annualised), in Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, and is (α, β) stable between 1960Q1–1983Q4 and 1984Q1–2019Q4? β is a reduced-form association (an \"Okun coefficient\"), not a structural causal effect.\n\n## Data and exclusions\n- `data/GDPC1.csv` (319 rows) and `data/UNRATE.csv` (945 rows) (`n_input_rows`); SHA-256 of both match `data/README.md` (see `out/state/data_audit.md`).\n- Quarterly u_t = mean of the three monthly UNRATE values; a quarter is formed only when all three months are present. The only missing monthly value (2025-10) lies outside the window and has no effect (`data_issues`).\n- Both series run to 2026; everything after 2019Q4 is cut before any computation. The window 1959Q4–2019Q4 holds 241 consecutive complete quarters (`n_window_quarters`). Dropping 1959Q4, which is used only as the lagged level, leaves 240 analysed quarters (`n_analysed`) from `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01. `out/exclusions.csv` records this step (241 − 1 = 240). Subperiods: 96 quarters (`n_sub1`) and 144 quarters (`n_sub2`).\n- The GDP data are the 2026 FRED vintage (chained 2017 dollars), not real-time data (`data_issues`).\n\n## Method\n- Baseline: predict Δu by its sample mean; the RMSE is `baseline_metric`.\n- Main model: full-sample OLS of Δu_t on a constant and g_t. The in-sample residual RMSE is `model_metric`.\n- Standard errors: Newey–West HAC with a Bartlett kernel. The lag length is set by the Newey–West (1994) rule floor(4·(T/100)^{2/9}), which gives 4 quarters for T = 240 (`hac_lags`). No small-sample df correction is applied. The 95% CI is β ± 1.96·SE (normal approximation).\n- Stability: separate OLS fits on each subperiod (`beta_sub1`, `beta_sub2`). Classical Chow F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n − 4)], with df (2, 236) (`chow_df`). Supplementary check: a HAC Wald test in a fully interacted model with a 1984Q1 dummy (`hac_wald_joint_p`, `hac_wald_slope_diff_p`, `hac_wald_intercept_diff_p`).\n- Deliverables: `out/table1.csv` (full sample and both subperiods; the subperiod slope SEs are HAC with NW-rule lags, `hac_lags_sub1`, `hac_lags_sub2`) and `out/figure1.png`, both written by `out/analysis.py`. No randomness is used (`random_seed` = null).\n\n## Results\n- Full sample: β = −0.256 (`effect_estimate`) and α = 0.184 pp (`intercept`). Each extra 1% of quarterly real GDP growth goes with about a 0.26 pp smaller rise in the unemployment rate in the same quarter. The growth rate at which unemployment is flat is about 0.98% per quarter before 1984 (`okun_growth_sub1`) and 0.55% after (`okun_growth_sub2`).\n- Fit: 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- Subperiod slopes are almost the same: −0.259 for 1960–1983 (`beta_sub1`) and −0.273 for 1984–2019 (`beta_sub2`). Intercepts are 0.254 (`intercept_sub1`) and 0.152 (`intercept_sub2`).\n- Chow test: F = 6.09 (`chow_f_stat`), p = 0.0026 (`chow_p_value`), which rejects joint equality of (α, β) at 5%. The task's coding rule therefore gives `stability_conclusion` = \"unstable\". The rejection concerns the (α, β) pair jointly. The slope point estimates hardly differ, and the HAC test of the slope difference alone gives p = 0.85 (`hac_wald_slope_diff_p`). What shifted is mainly the fitted line's level, i.e. the growth rate consistent with stable unemployment. However, the HAC test of the intercept alone is also not significant (p = 0.25, `hac_wald_intercept_diff_p`). The joint HAC test still rejects (p = 0.0042, `hac_wald_joint_p`) because the intercept and slope estimates are strongly correlated.\n- `conclusion` = \"negative_effect\": the 95% CI lies entirely below zero.\n\n## Uncertainty\n- HAC SE of β = 0.0358 (`effect_se`, 4 lags). 95% CI: [−0.326, −0.186] (`effect_ci_low`, `effect_ci_high`).\n- The classical OLS SE is 0.0200 (`ols_classical_se`), so allowing for heteroskedasticity and autocorrelation makes the SE about 1.8 times larger.\n- Sensitivity to the lag length (`hac_se_by_lag`): 0.029 (0 lags), 0.034 (2), 0.036 (4), 0.037 (8), 0.036 (12). The sign conclusion holds for every lag length.\n- Subperiod HAC SEs: 0.039 (`beta_sub1_hac_se`) and 0.068 (`beta_sub2_hac_se`).\n\n## Limitations and open issues\n- **The classical Chow test's assumptions are probably violated.** It assumes homoskedastic, serially uncorrelated errors with equal variance in both subperiods. Three things point the other way: HAC SEs are clearly larger than classical ones, residual variance probably differs between the two periods (Great Moderation), and there are visible large-residual quarters (e.g. 1980, 2008–09). The F-test's size may therefore be off. The HAC Wald test also rejects jointly (`hac_wald_joint_p`), which supports the rejection. But I did not test variance equality and did not run a Chow test with unequal variances.\n- **The \"unstable\" verdict depends on the break date.** The split at 1984Q1 is imposed. I did not search over break dates (no Quandt–Andrews or Bai–Perron test). The instability is in the intercept/slope pair, not in the slope point estimate, so it should not be read as \"Okun's coefficient changed\".\n- **Specification threats.** The model is static and contemporaneous, with no lags of g or Δu. Okun dynamics, a trend-growth slowdown (which shows up as an intercept shift), and possible nonlinearity or asymmetry between recessions and expansions were not modelled. Measurement error in quarterly GDP growth would bias β towards zero. Simultaneity means β is not causal.\n- **Data vintage.** The 2026 vintage GDPC1 includes benchmark revisions. Real-time estimates would differ, and I did not check how sensitive the results are to vintage.\n- **Inference choices.** The lag rule is ad hoc, but results barely change with lag length. The CI uses a normal rather than t approximation (negligible difference at n = 240). With only 96 and 144 quarters, the subperiod HAC SEs are less reliable.\n- **What would invalidate the result:** errors in quarterly aggregation (checked by independent recomputation, see `out/state/checks.md`), any leakage of post-2019 data (excluded by construction and assertions), or a different definition of g (e.g. annualised, which would scale β by 1/4).\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4 the full-sample OLS Okun coefficient is about -0.26 pp per 1% quarterly real GDP growth, with intercept about 0.18 pp.\",\"results_keys\":[\"effect_estimate\",\"intercept\",\"n_analysed\",\"sample_start\",\"sample_end\"],\"status\":\"supported\",\"caveat\":\"Reduced-form association, not causal; 2026 data vintage.\"},\n {\"id\":\"C2\",\"text\":\"The HAC (Newey-West, 4 lags) 95% CI for beta, [-0.326, -0.186], lies entirely below zero, so conclusion = negative_effect.\",\"results_keys\":[\"effect_se\",\"hac_lags\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Normal approximation; conclusion robust to lags 0-12 (hac_se_by_lag).\"},\n {\"id\":\"C3\",\"text\":\"Output growth explains a substantial share of quarterly unemployment changes: residual RMSE 0.250 pp vs 0.325 pp for the mean-only baseline (R2 about 0.41).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"r_squared\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C4\",\"text\":\"Subperiod slopes are nearly identical (-0.259 for 1960-1983, -0.273 for 1984-2019); the HAC test of the slope difference alone does not reject.\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"hac_wald_slope_diff_p\",\"beta_sub1_hac_se\",\"beta_sub2_hac_se\"],\"status\":\"supported\",\"caveat\":\"Imposed break date.\"},\n {\"id\":\"C5\",\"text\":\"The classical Chow test rejects joint equality of (alpha, beta) across the 1984Q1 split (F = 6.09, p = 0.0026), so stability_conclusion = unstable; a HAC Wald joint test also rejects.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\",\"chow_df\",\"hac_wald_joint_p\"],\"status\":\"supported\",\"caveat\":\"Classical Chow assumes homoskedastic, serially uncorrelated, equal-variance errors, likely violated; break date imposed; instability concerns the (alpha,beta) pair, not the slope.\"},\n {\"id\":\"C6\",\"text\":\"The growth rate consistent with stable unemployment (-alpha/beta) fell from about 0.98% to about 0.55% per quarter between subperiods.\",\"results_keys\":[\"okun_growth_sub1\",\"okun_growth_sub2\",\"intercept_sub1\",\"intercept_sub2\"],\"status\":\"supported\",\"caveat\":\"Point estimates only; the HAC test of the intercept difference alone is not significant (hac_wald_intercept_diff_p = 0.25).\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']['status']='passed'; p['P4']['checks'].append('gate run 20261030T045159.646436Z: all P4-relevant checks ok (keys, CI, positivity, chronology, exclusions, reproducibility); failures only for P5 deliverables not yet written (report, claims, phase ledger)')\np['P4']['notes']='gate receipt out/state/gate_receipts/20261030T045159.646436Z.json'\np['P5']['status']='passed'; p['P5']['checks']=['report.md written with 6 sections citing results keys','claims.json written, all keys exist','final gate run (see notes)']\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nr=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')\nEOF\necho \"- 2026-10-30 P4 passed (gate receipt 20261030T045159). P5: report and claims written; running final gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"FAIL|GATE|receipt\"","description":"Write report, claims, update ledger, run final gate"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"bbe3498a-ea81-4de7-88a1-39a52e116244","timestamp":"2026-10-30T04:52:38.930Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"c9d51279-25ca-4d6a-8026-f9f93039399d","keep":24,"tail":["4ee2a63739eee00ba68fdc0e3cb162d72fc309c1aca08fe307c406a17eaa9dea","1ff26b8b79eadfcb066a2d819fe4750ecccaaf1cb67c2f50d129a29f3ba9d7da"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c6c70ca6f95ea804c0471ec7be58c079a77ec143955b9b20128258f1331b33c7"} {"parentUuid":"de680804-78fc-4431-826c-2b25b84f962b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpf2yoxtnx9XcPaZSD1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0146VKbXqGLdFttQyqcqZgPU","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'][-1]='final gate run 20261030T045238.918440Z: PASSED (0 of 48 failed)'\np['P5']['notes']='gate receipt out/state/gate_receipts/20261030T045238.918440Z.json'\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P5 passed; final gate PASSED (receipt 20261030T045238).\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"GATE\"","description":"Record final gate receipt and reconfirm"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4532,"cache_read_input_tokens":28202,"output_tokens":333,"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":4532},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpf2hvzBUdPYSmP9ybb","requestRef":"bbe3498a-ea81-4de7-88a1-39a52e116244","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"78c9265c-b4c2-4e31-88cb-e281cf608ce7","timestamp":"2026-10-30T04:52:45.311Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"78c9265c-b4c2-4e31-88cb-e281cf608ce7","isSidechain":false,"promptId":"e91848f7-7647-421b-8071-a0af830f59c6","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0146VKbXqGLdFttQyqcqZgPU","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)","is_error":false}]},"uuid":"cb5e3dcd-3cf2-4852-9eac-06196774ba8d","timestamp":"2026-10-30T04:52:46.635Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 48 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"78c9265c-b4c2-4e31-88cb-e281cf608ce7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","hash":"f5192d8fbd9c9c69020c168b7f0c35253ca876084e619ecdb07f412d93c690d5","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_0146VKbXqGLdFttQyqcqZgPU","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'][-1]='final gate run 20261030T045238.918440Z: PASSED (0 of 48 failed)'\np['P5']['notes']='gate receipt out/state/gate_receipts/20261030T045238.918440Z.json'\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P5 passed; final gate PASSED (receipt 20261030T045238).\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"GATE\"","description":"Record final gate receipt and reconfirm"}}]}} {"type":"api-request","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","id":"91cc1413-b21e-4d73-a267-7d83da67a3cd","timestamp":"2026-10-30T04:52:46.639Z","version":"2.1.314","querySource":"sdk","shapeHash":"b2f26332d65baa2537b1492cc127041772e356596535466b26b81a20797e29d3","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":"bbe3498a-ea81-4de7-88a1-39a52e116244","keep":26,"tail":["f5192d8fbd9c9c69020c168b7f0c35253ca876084e619ecdb07f412d93c690d5","e2e7219d424732dce1df8b4fd3f7a11b78d79de2dbc81e8dd4a9219f7addd966"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ddcaac695e825f8124dbe6eb9db8a1fe3a2922be181bb88a991bf981676bca90"} {"parentUuid":"cb5e3dcd-3cf2-4852-9eac-06196774ba8d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpfbwSUBDqhSL3RVxFH","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":373,"cache_read_input_tokens":32734,"output_tokens":945,"output_tokens_details":{"thinking_tokens":22},"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":373},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6640,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpfbg4VrfqYxWSsLY59","requestRef":"91cc1413-b21e-4d73-a267-7d83da67a3cd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4d81261b-9e31-4bda-8a06-2902857b3411","timestamp":"2026-10-30T04:52:56.021Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"4d81261b-9e31-4bda-8a06-2902857b3411","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpfbwSUBDqhSL3RVxFH","type":"message","role":"assistant","content":[{"type":"text","text":"I finished the analysis. Higher GDP growth goes with a clearly smaller rise in unemployment over 1960–2019, and the test for stability rejects across the 1984 split. All phases P0–P5 are recorded as passed, and the final check of the required outputs passed with no failures.\n\n**Main estimate (240 quarters, 1960Q1–2019Q4):**\n- **Okun coefficient:** β = −0.256 per 1% quarterly real GDP growth, so each extra point of growth goes with about a quarter-point smaller rise in unemployment that quarter. The intercept is α = 0.184 pp.\n- **Uncertainty:** the Newey–West standard error is 0.0358, using 4 lags chosen by the usual Newey–West rule of thumb. The 95% interval is [−0.326, −0.186], entirely below zero, so `conclusion` = `negative_effect`. This holds whichever lag length from 0 to 12 is used.\n- **Fit:** prediction error is 0.250 pp, against 0.325 pp for simply predicting the average change (R² = 0.41).\n\n**Stability:**\n- **Slopes:** almost the same in the two subperiods: −0.259 for 1960–1983 and −0.273 for 1984–2019.\n- **Chow test:** F = 6.09, p = 0.0026, which rejects equality of intercept and slope together, so `stability_conclusion` = `unstable`.\n- **What actually changed:** mainly the level of the fitted line, not the slope. The growth rate at which unemployment stays flat fell from about 0.98% to about 0.55% per quarter. I added a check that allows for heteroskedasticity and autocorrelation: it also rejects the two parameters jointly, but tested one at a time neither the slope difference (p = 0.85) nor the intercept difference (p = 0.25) is significant.\n\n**Data:** the only data problem in range is that both files run to 2026; everything after 2019Q4 was cut before any calculation. One monthly unemployment value (October 2025) is missing, but it falls outside the sample. A separate recalculation in plain numpy gives exactly the same β and Chow F, and re-running the script reproduces identical results.\n\n**Limitations:**\n- The classical Chow test assumes errors with constant variance and no autocorrelation, which is probably not true here.\n- The 1984 break date is imposed, and I did not search for other break dates.\n- The model is static, with no lags.\n- It uses today's revised GDP figures, not the data available at the time.\n- β is an association, not a causal effect.\n\nFiles are in `out/`:\n- results.json\n- report.md\n- claims.json\n- analysis.py\n- figure1.png\n- table1.csv\n- exclusions.csv\n- state/ (working notes, check records and pass receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":373,"cache_read_input_tokens":32734,"output_tokens":945,"output_tokens_details":{"thinking_tokens":22},"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":373},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpfbg4VrfqYxWSsLY59","requestRef":"91cc1413-b21e-4d73-a267-7d83da67a3cd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2b15fd63-398e-4ae2-8a70-9a316f763fac","timestamp":"2026-10-30T04:52:57.594Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0174","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","version":"2.1.314","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2b15fd63-398e-4ae2-8a70-9a316f763fac","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01"} {"type":"cost-state","sessionId":"25e0f4db-57bd-44ed-b068-70d6766aef01","totalCostUSD":0.6250244,"totalAPIDuration":185376,"totalAPIDurationWithoutRetries":185367,"totalToolDuration":8469,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":193848,"startTime":1793335783753,"modelUsage":{"claude-opus-5-5":{"inputTokens":30,"outputTokens":21080,"thinkingTokens":1004,"cacheReadInputTokens":226447,"cacheCreationInputTokens":31603,"cacheCreationEphemeral5mInputTokens":31603,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.6250244}},"hasUnknownModelCost":false}