1{"type":"atis-latch","atis":"","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:06:22.483Z","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:06:22.489Z","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}4{"parentUuid":null,"isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":"Begin"},"uuid":"53b9f4eb-3318-4fba-84b5-0d59288f8269","timestamp":"2026-10-30T04:06:22.493Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","timestamp":"2026-10-30T04:06:22.506Z","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/RC0017\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"75bced9e-5627-4be1-be3b-7aa6fe3b02c2","timestamp":"2026-10-30T04:06:22.506Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"a769a19d4a157f07a2ac638acdfc60772803d4e1009c291343b22ff7fff27bbe"}8{"parentUuid":"53b9f4eb-3318-4fba-84b5-0d59288f8269","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"d124d22c-c31f-4964-b464-6e1e9de4137a","timestamp":"2026-10-30T04:06:22.498Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"d124d22c-c31f-4964-b464-6e1e9de4137a","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"30f444de-727c-43fe-ad5f-ba4e6aeb2d3b","timestamp":"2026-10-30T04:06:22.498Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"30f444de-727c-43fe-ad5f-ba4e6aeb2d3b","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"73b38018-bb9e-4e6f-916b-2d0c8f4f1e37","timestamp":"2026-10-30T04:06:22.499Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}12{"parentUuid":"73b38018-bb9e-4e6f-916b-2d0c8f4f1e37","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8PaKviroy1xnirizn","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":101,"output_tokens_details":{"thinking_tokens":19},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1010,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm8PJTVzBYDRspk72UU","requestRef":"75bced9e-5627-4be1-be3b-7aa6fe3b02c2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"090f5418-05bf-4b96-b26c-b5130c91e148","timestamp":"2026-10-30T04:06:24.336Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"090f5418-05bf-4b96-b26c-b5130c91e148","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8PaKviroy1xnirizn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Bpbb5gb2NNvPVnpZUXHYC5","name":"Bash","input":{"command":"cat TASK.md; ls -laR; ls out/state 2>/dev/null && cat out/state/*"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":101,"output_tokens_details":{"thinking_tokens":19},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm8PJTVzBYDRspk72UU","requestRef":"75bced9e-5627-4be1-be3b-7aa6fe3b02c2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5f18212d-4e4f-4027-a097-83f521d410fa","timestamp":"2026-10-30T04:06:24.339Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"5f18212d-4e4f-4027-a097-83f521d410fa","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. 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/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\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\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 `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 .\ndrwxr-xr-x 27 simon-pierreboucher staff 864 oct. 30 00:06 ..\n-rw-r--r-- 1 simon-pierreboucher staff 419 oct. 29 23:43 bundle.json\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 data\n-rw-r--r-- 1 simon-pierreboucher staff 2302 oct. 29 23:43 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 5597 oct. 29 23:43 TASK.md\n\n./data:\ntotal 64\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 ..\n-rw-r--r-- 1 simon-pierreboucher staff 31657 oct. 29 23:43 firms.csv","is_error":true,"tool_use_id":"toolu_01Bpbb5gb2NNvPVnpZUXHYC5"}]},"uuid":"50fbad81-be99-4bd8-9c1c-800147d61886","timestamp":"2026-10-30T04:06:24.453Z","toolUseResult":"Error: Exit code 1\n# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. 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/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\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\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 `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 .\ndrwxr-xr-x 27 simon-pierreboucher staff 864 oct. 30 00:06 ..\n-rw-r--r-- 1 simon-pierreboucher staff 419 oct. 29 23:43 bundle.json\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 data\n-rw-r--r-- 1 simon-pierreboucher staff 2302 oct. 29 23:43 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 5597 oct. 29 23:43 TASK.md\n\n./data:\ntotal 64\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 ..\n-rw-r--r-- 1 simon-pierreboucher staff 31657 oct. 29 23:43 firms.csv","sandboxed":false,"sourceToolAssistantUUID":"5f18212d-4e4f-4027-a097-83f521d410fa","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"9d5e8d945191e9165dcc6da8fd7cd65c1268ad4b1b38b9480d5aed5d7e9fe99b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Bpbb5gb2NNvPVnpZUXHYC5","name":"Bash","input":{"command":"cat TASK.md; ls -laR; ls out/state 2>/dev/null && cat out/state/*"}}]}}16{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"cd0d3e8f-d01b-4501-85fc-f9da66f0966e","timestamp":"2026-10-30T04:06:24.458Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"75bced9e-5627-4be1-be3b-7aa6fe3b02c2","keep":2,"tail":["9d5e8d945191e9165dcc6da8fd7cd65c1268ad4b1b38b9480d5aed5d7e9fe99b","817564ce02968378c5fdb6e8029fd512a923568a4cbcabf05e46a96e50227544"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1a45577f1ca190c4166eb3876e029dbf09efbe9533dab1e1b38d53cf665e9652"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"50fbad81-be99-4bd8-9c1c-800147d61886","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}18{"type":"atis-latch","atis":"","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}19{"parentUuid":"50fbad81-be99-4bd8-9c1c-800147d61886","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8WofFQtKUmogoeNHc","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":2447,"cache_read_input_tokens":3713,"output_tokens":295,"output_tokens_details":{"thinking_tokens":65},"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":2447},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":646,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm8WX3DDesNSsxDA7xa","requestRef":"cd0d3e8f-d01b-4501-85fc-f9da66f0966e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"688f9423-b2cd-4b62-a770-faef216fbcdf","timestamp":"2026-10-30T04:06:26.071Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"688f9423-b2cd-4b62-a770-faef216fbcdf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8WofFQtKUmogoeNHc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KaTHj2HBmyqCXbSayJ8dp4","name":"Bash","input":{"command":"mkdir -p out/state; head -5 data/firms.csv; shasum -a 256 data/firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;d=pd.read_csv('data/firms.csv');print(d.shape);print(d.dtypes);print(d.describe().T);print(d.isna().sum());print(d.duplicated().sum(),d.firm_id.duplicated().sum());print(d.corr())\nprint((d.training_hours<0).sum(), d.training_hours.value_counts().head())\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2447,"cache_read_input_tokens":3713,"output_tokens":295,"output_tokens_details":{"thinking_tokens":65},"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":2447},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm8WX3DDesNSsxDA7xa","requestRef":"cd0d3e8f-d01b-4501-85fc-f9da66f0966e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1512fc64-5c83-42a8-a671-cfce12167db7","timestamp":"2026-10-30T04:06:27.337Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}21{"parentUuid":"1512fc64-5c83-42a8-a671-cfce12167db7","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KaTHj2HBmyqCXbSayJ8dp4","type":"tool_result","content":"firm_id,skill_index,training_hours,productivity_growth\n1748,-2.0128,12.679,12.167\n1202,0.0756,20.0,7.3943\n1860,1.0082,21.618,3.9187\n1341,-1.6259,8.305,13.8987\n34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df data/firms.csv\n(1200, 4)\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\n firm_id skill_index training_hours productivity_growth\nfirm_id 1.000000 0.047429 0.054160 -0.030509\nskill_index 0.047429 1.000000 0.693530 -0.786787\ntraining_hours 0.054160 0.693530 1.000000 -0.277219\nproductivity_growth -0.030509 -0.786787 -0.277219 1.000000\n12 training_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\nName: count, dtype: int64","is_error":false}]},"uuid":"163ed121-d059-4c51-934f-82f36c9a8285","timestamp":"2026-10-30T04:06:27.662Z","toolUseResult":{"stdout":"firm_id,skill_index,training_hours,productivity_growth\n1748,-2.0128,12.679,12.167\n1202,0.0756,20.0,7.3943\n1860,1.0082,21.618,3.9187\n1341,-1.6259,8.305,13.8987\n34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df data/firms.csv\n(1200, 4)\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\n firm_id skill_index training_hours productivity_growth\nfirm_id 1.000000 0.047429 0.054160 -0.030509\nskill_index 0.047429 1.000000 0.693530 -0.786787\ntraining_hours 0.054160 0.693530 1.000000 -0.277219\nproductivity_growth -0.030509 -0.786787 -0.277219 1.000000\n12 training_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\nName: count, dtype: int64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1512fc64-5c83-42a8-a671-cfce12167db7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}22{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"795c6d4eb8fa06cb528e6d71db65acaa1c32843b330a7f9edc2c4dab72fcca09","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KaTHj2HBmyqCXbSayJ8dp4","name":"Bash","input":{"command":"mkdir -p out/state; head -5 data/firms.csv; shasum -a 256 data/firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;d=pd.read_csv('data/firms.csv');print(d.shape);print(d.dtypes);print(d.describe().T);print(d.isna().sum());print(d.duplicated().sum(),d.firm_id.duplicated().sum());print(d.corr())\nprint((d.training_hours<0).sum(), d.training_hours.value_counts().head())\""}}]}}23{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"c904773b-958a-4e8b-ae64-b40027526849","timestamp":"2026-10-30T04:06:27.666Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"cd0d3e8f-d01b-4501-85fc-f9da66f0966e","keep":4,"tail":["795c6d4eb8fa06cb528e6d71db65acaa1c32843b330a7f9edc2c4dab72fcca09","982ac06913ee25245f8c5e9b1b90a0168260de3bfdfd38a50af91b3a09345363"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"66ac67a73232111eac6f4b3dea4e51f6e5f678c24f6c2ca2c9ede9d5f383ecce"}24{"parentUuid":"163ed121-d059-4c51-934f-82f36c9a8285","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8kXQSEKHFgpzqMfbT","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NSbqG7ER8j7vMZdLfw2oXH","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd;pd.set_option('display.width',200);d=pd.read_csv('data/firms.csv');print(d.describe().T.to_string())\nprint((d.training_hours==0).sum(),(d.training_hours<0).sum(),(d.training_hours==20).sum(), d.firm_id.min(),d.firm_id.max())\nimport statsmodels.formula.api as smf\nfor f in ['productivity_growth~training_hours','productivity_growth~training_hours+skill_index','productivity_growth~training_hours+skill_index+I(skill_index**2)']:\n m=smf.ols(f,d).fit(cov_type='HC1');print(m.params.to_string(),m.bse.to_string())\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":854,"cache_read_input_tokens":6160,"output_tokens":304,"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":854},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXm8kF41hM2eAtgu23V1","requestRef":"c904773b-958a-4e8b-ae64-b40027526849","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"16eacb2d-acab-4896-bf50-1b012003a22e","timestamp":"2026-10-30T04:06:30.283Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"16eacb2d-acab-4896-bf50-1b012003a22e","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01NSbqG7ER8j7vMZdLfw2oXH","type":"tool_result","content":" count mean std min 25% 50% 75% max\nfirm_id 1200.0 1600.500000 346.554469 1001.0000 1300.750000 1600.50000 1900.250 2200.0000\nskill_index 1200.0 -0.001467 0.994503 -3.8279 -0.642375 0.01025 0.680 2.9623\ntraining_hours 1200.0 19.945735 8.243620 -7.5850 14.580750 19.67650 25.502 51.7700\nproductivity_growth 1200.0 7.083012 4.020107 -4.0380 4.444350 7.06140 9.987 19.3889\n0 12 1 1001 2200\nIntercept 9.779468\ntraining_hours -0.135190 Intercept 0.302808\ntraining_hours 0.013897\nIntercept 2.045418\ntraining_hours 0.252224\nskill_index -4.630436 Intercept 0.200567\ntraining_hours 0.009479\nskill_index 0.078089\nIntercept 2.053483\ntraining_hours 0.252254\nskill_index -4.631547\nI(skill_index ** 2) -0.008766 Intercept 0.203161\ntraining_hours 0.009488\nskill_index 0.078348\nI(skill_index ** 2) 0.037087","is_error":false}]},"uuid":"8e9286c8-9ae4-486b-91fe-8251c34aef14","timestamp":"2026-10-30T04:06:31.023Z","toolUseResult":{"stdout":" count mean std min 25% 50% 75% max\nfirm_id 1200.0 1600.500000 346.554469 1001.0000 1300.750000 1600.50000 1900.250 2200.0000\nskill_index 1200.0 -0.001467 0.994503 -3.8279 -0.642375 0.01025 0.680 2.9623\ntraining_hours 1200.0 19.945735 8.243620 -7.5850 14.580750 19.67650 25.502 51.7700\nproductivity_growth 1200.0 7.083012 4.020107 -4.0380 4.444350 7.06140 9.987 19.3889\n0 12 1 1001 2200\nIntercept 9.779468\ntraining_hours -0.135190 Intercept 0.302808\ntraining_hours 0.013897\nIntercept 2.045418\ntraining_hours 0.252224\nskill_index -4.630436 Intercept 0.200567\ntraining_hours 0.009479\nskill_index 0.078089\nIntercept 2.053483\ntraining_hours 0.252254\nskill_index -4.631547\nI(skill_index ** 2) -0.008766 Intercept 0.203161\ntraining_hours 0.009488\nskill_index 0.078348\nI(skill_index ** 2) 0.037087","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"16eacb2d-acab-4896-bf50-1b012003a22e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"ec3e2afb588c1f395d8aba3d438fb16b22174933cef99b2e42a152ebcdd7533d","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01NSbqG7ER8j7vMZdLfw2oXH","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd;pd.set_option('display.width',200);d=pd.read_csv('data/firms.csv');print(d.describe().T.to_string())\nprint((d.training_hours==0).sum(),(d.training_hours<0).sum(),(d.training_hours==20).sum(), d.firm_id.min(),d.firm_id.max())\nimport statsmodels.formula.api as smf\nfor f in ['productivity_growth~training_hours','productivity_growth~training_hours+skill_index','productivity_growth~training_hours+skill_index+I(skill_index**2)']:\n m=smf.ols(f,d).fit(cov_type='HC1');print(m.params.to_string(),m.bse.to_string())\n\""}}]}}27{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"b8bd35c8-d587-4922-b3be-89c4f4bc4e02","timestamp":"2026-10-30T04:06:31.026Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"c904773b-958a-4e8b-ae64-b40027526849","keep":6,"tail":["ec3e2afb588c1f395d8aba3d438fb16b22174933cef99b2e42a152ebcdd7533d","01c3f263b808531d8b219729c73fa452b526fdd342a3674a659f4df1911afec3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a76cb824fc13b85f3ec5d15195ea74eef728ac140e92f6036d62b4fda07b61d0"}28{"parentUuid":"8e9286c8-9ae4-486b-91fe-8251c34aef14","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8zwqY1N9sH5gocHxB","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":729,"cache_read_input_tokens":7014,"output_tokens":317,"output_tokens_details":{"thinking_tokens":69},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":729},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":503,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm8zcUzEVNzRaNeTSjm","requestRef":"b8bd35c8-d587-4922-b3be-89c4f4bc4e02","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2b1052d6-0da6-40db-b157-fa1d6df67081","timestamp":"2026-10-30T04:06:32.658Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"2b1052d6-0da6-40db-b157-fa1d6df67081","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm8zwqY1N9sH5gocHxB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LSvMZXZoejKp52cSC6R6bw","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd;d=pd.read_csv('data/firms.csv');print(d[d.training_hours<0].to_string())\nimport statsmodels.formula.api as smf\nm=smf.ols('productivity_growth~training_hours+skill_index',d[d.training_hours>=0]).fit(cov_type='HC1');print(m.params,m.bse)\nm=smf.ols('productivity_growth~training_hours*skill_index',d[d.training_hours>=0]).fit(cov_type='HC1');print(m.params,m.bse)\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":729,"cache_read_input_tokens":7014,"output_tokens":317,"output_tokens_details":{"thinking_tokens":69},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":729},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm8zcUzEVNzRaNeTSjm","requestRef":"b8bd35c8-d587-4922-b3be-89c4f4bc4e02","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c56cf728-bad5-4053-986c-5fd978f7a1bd","timestamp":"2026-10-30T04:06:33.982Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"c56cf728-bad5-4053-986c-5fd978f7a1bd","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LSvMZXZoejKp52cSC6R6bw","type":"tool_result","content":" firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\nIntercept 2.013217\ntraining_hours 0.253538\nskill_index -4.624621\ndtype: float64 Intercept 0.208482\ntraining_hours 0.009812\nskill_index 0.078164\ndtype: float64\nIntercept 2.013721\ntraining_hours 0.253599\nskill_index -4.618218\ntraining_hours:skill_index -0.000328\ndtype: float64 Intercept 0.208647\ntraining_hours 0.009917\nskill_index 0.139922\ntraining_hours:skill_index 0.006014\ndtype: float64","is_error":false}]},"uuid":"a5a5de10-4cb7-4ef0-8dd5-2eacfb247653","timestamp":"2026-10-30T04:06:34.718Z","toolUseResult":{"stdout":" firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\nIntercept 2.013217\ntraining_hours 0.253538\nskill_index -4.624621\ndtype: float64 Intercept 0.208482\ntraining_hours 0.009812\nskill_index 0.078164\ndtype: float64\nIntercept 2.013721\ntraining_hours 0.253599\nskill_index -4.618218\ntraining_hours:skill_index -0.000328\ndtype: float64 Intercept 0.208647\ntraining_hours 0.009917\nskill_index 0.139922\ntraining_hours:skill_index 0.006014\ndtype: float64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c56cf728-bad5-4053-986c-5fd978f7a1bd","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"028d8b010adc03fb1dabde1816a013927daeebe7d446306d173cc94f9ce1c395","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LSvMZXZoejKp52cSC6R6bw","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd;d=pd.read_csv('data/firms.csv');print(d[d.training_hours<0].to_string())\nimport statsmodels.formula.api as smf\nm=smf.ols('productivity_growth~training_hours+skill_index',d[d.training_hours>=0]).fit(cov_type='HC1');print(m.params,m.bse)\nm=smf.ols('productivity_growth~training_hours*skill_index',d[d.training_hours>=0]).fit(cov_type='HC1');print(m.params,m.bse)\n\""}}]}}32{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"61d3faa6-e3d4-41cc-8721-0913debc876b","timestamp":"2026-10-30T04:06:34.722Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"b8bd35c8-d587-4922-b3be-89c4f4bc4e02","keep":8,"tail":["028d8b010adc03fb1dabde1816a013927daeebe7d446306d173cc94f9ce1c395","7dd447cbf4d93320207eeb6ccef6c152a58be8efc72017758bdb77299fe80e63"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"70a837f101c1b0bf6ece3ddaf0d2d1100f18672e127795f5afb28d515a18ca42"}33{"parentUuid":"a5a5de10-4cb7-4ef0-8dd5-2eacfb247653","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm9GiN1LG23LkAJgFG1","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":785,"cache_read_input_tokens":7743,"output_tokens":1428,"output_tokens_details":{"thinking_tokens":61},"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":785},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":473,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm9GQWRaAKqZBxRR3qZ","requestRef":"61d3faa6-e3d4-41cc-8721-0913debc876b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b8596906-c048-42ae-adea-e59e70cd8b2d","timestamp":"2026-10-30T04:06:36.162Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}34{"parentUuid":"b8596906-c048-42ae-adea-e59e70cd8b2d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm9GiN1LG23LkAJgFG1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ApwhLvu76scF6wa3pnm8Mv","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract (P0)\n**Question:** causal effect of one extra training hour per employee (programme year) on next-year productivity growth (pp/hour), simulated firm data.\n**Estimand:** linear, homogeneous coefficient on `training_hours` under selection on observables given `skill_index` (pre-programme, so a valid non-post-treatment control). Assumptions: no unobserved confounders beyond skill_index, linearity in hours and correct functional form for skill, no interference, skill_index measured without error.\n**Baseline:** OLS productivity_growth ~ 1 + training_hours (required unadjusted model).\n**Outputs:** out/results.json (naive_estimate, naive_ci_low/high, baseline_metric, model_metric, effect_estimate, effect_se, effect_ci_low/high, skill_index_coefficient, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (model, estimate, se, ci_low, ci_high), out/report.md (6 sections), out/analysis.py, out/claims.json.\n**Information rules:** only data/firms.csv; unadjusted = OLS with intercept only.\n**Invalidity:** missing confounder column, post-treatment control, impossible values driving result, no overlap. skill_index is stated pre-programme -> adjustment feasible.\nEOF\ncat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n- File: data/firms.csv, SHA-256 34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df\n- 1200 rows (excl. header) x 4 columns: firm_id int (1001-2200, unique), skill_index float (std index, mean -0.001, sd 0.99, range -3.83..2.96), training_hours float (hours/employee, mean 19.9, sd 8.2, range -7.59..51.77), productivity_growth float (% change, mean 7.08, sd 4.02, range -4.04..19.39).\n- Missing values: none. Duplicate rows: 0. Duplicate firm_id: 0.\n- Anomaly: 12 rows with negative training_hours (-7.585 to -0.133) — physically impossible (hours cannot be negative). All have low skill_index (-3.0 to -1.0). Decision: exclude from main analysis (both models estimated on the same 1188 rows); sensitivity analysis on all 1200 rows reported.\n- Correlations: skill_index vs training_hours 0.69, skill_index vs growth -0.79, training_hours vs growth -0.28 -> strong confounding by skill expected (naive slope sign opposite to adjusted).\n- Information availability: skill_index is measured the year before the programme (pre-treatment) -> legitimate control. No violating inputs.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 computed\",\"schema/missing/duplicates checked\",\"negative training_hours anomaly found (12 rows)\"],\"notes\":\"exclusions.csv written by analysis.py\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\nprintf \"# Log\\n- 2026-10-30 P0 passed: contract written.\\n- 2026-10-30 P1 passed: audit done; decision to exclude 12 negative training_hours rows, with sensitivity on all rows.\\n\" > out/state/log.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":785,"cache_read_input_tokens":7743,"output_tokens":1428,"output_tokens_details":{"thinking_tokens":61},"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":785},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm9GQWRaAKqZBxRR3qZ","requestRef":"61d3faa6-e3d4-41cc-8721-0913debc876b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f6435679-bab2-45c8-b723-51a1246cb054","timestamp":"2026-10-30T04:06:47.005Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}35{"parentUuid":"f6435679-bab2-45c8-b723-51a1246cb054","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ApwhLvu76scF6wa3pnm8Mv","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"611ef782-3c2a-408b-ba68-5391b9fa1102","timestamp":"2026-10-30T04:06:47.052Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f6435679-bab2-45c8-b723-51a1246cb054","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}36{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"eaa1d3786bcd472200611460859ed0f1707d387c658c868dd46d63790779b871","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01ApwhLvu76scF6wa3pnm8Mv","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract (P0)\n**Question:** causal effect of one extra training hour per employee (programme year) on next-year productivity growth (pp/hour), simulated firm data.\n**Estimand:** linear, homogeneous coefficient on `training_hours` under selection on observables given `skill_index` (pre-programme, so a valid non-post-treatment control). Assumptions: no unobserved confounders beyond skill_index, linearity in hours and correct functional form for skill, no interference, skill_index measured without error.\n**Baseline:** OLS productivity_growth ~ 1 + training_hours (required unadjusted model).\n**Outputs:** out/results.json (naive_estimate, naive_ci_low/high, baseline_metric, model_metric, effect_estimate, effect_se, effect_ci_low/high, skill_index_coefficient, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (model, estimate, se, ci_low, ci_high), out/report.md (6 sections), out/analysis.py, out/claims.json.\n**Information rules:** only data/firms.csv; unadjusted = OLS with intercept only.\n**Invalidity:** missing confounder column, post-treatment control, impossible values driving result, no overlap. skill_index is stated pre-programme -> adjustment feasible.\nEOF\ncat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n- File: data/firms.csv, SHA-256 34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df\n- 1200 rows (excl. header) x 4 columns: firm_id int (1001-2200, unique), skill_index float (std index, mean -0.001, sd 0.99, range -3.83..2.96), training_hours float (hours/employee, mean 19.9, sd 8.2, range -7.59..51.77), productivity_growth float (% change, mean 7.08, sd 4.02, range -4.04..19.39).\n- Missing values: none. Duplicate rows: 0. Duplicate firm_id: 0.\n- Anomaly: 12 rows with negative training_hours (-7.585 to -0.133) — physically impossible (hours cannot be negative). All have low skill_index (-3.0 to -1.0). Decision: exclude from main analysis (both models estimated on the same 1188 rows); sensitivity analysis on all 1200 rows reported.\n- Correlations: skill_index vs training_hours 0.69, skill_index vs growth -0.79, training_hours vs growth -0.28 -> strong confounding by skill expected (naive slope sign opposite to adjusted).\n- Information availability: skill_index is measured the year before the programme (pre-treatment) -> legitimate control. No violating inputs.\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 computed\",\"schema/missing/duplicates checked\",\"negative training_hours anomaly found (12 rows)\"],\"notes\":\"exclusions.csv written by analysis.py\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\nprintf \"# Log\\n- 2026-10-30 P0 passed: contract written.\\n- 2026-10-30 P1 passed: audit done; decision to exclude 12 negative training_hours rows, with sensitivity on all rows.\\n\" > out/state/log.md"}}]}}37{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"e7167cb5-d75d-42d9-8f79-2f0f9ede215c","timestamp":"2026-10-30T04:06:47.056Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"61d3faa6-e3d4-41cc-8721-0913debc876b","keep":10,"tail":["eaa1d3786bcd472200611460859ed0f1707d387c658c868dd46d63790779b871","df2956fbcd36b1d3cdc246ba7909739bdb7e796268cf76ea68746778c78c0c2a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"aa5bcd4834c86075f83ea84ee8f1f48f8c71056e0c5d6e999803fc9625be5500"}38{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"611ef782-3c2a-408b-ba68-5391b9fa1102","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}39{"type":"atis-latch","atis":"","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}40{"parentUuid":"611ef782-3c2a-408b-ba68-5391b9fa1102","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmABQQjZRbjARZ1Z3vM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Wc2wLsFamzQGp6xjARrhkH","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point: run from workspace root with ~/wp29/venv/bin/python out/analysis.py\"\"\"\nimport json, os\nimport numpy as np, pandas as pd\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\nimport statsmodels.formula.api as smf\n\nSEED = None # no randomness used\nOUT = \"out\"\nd_raw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(d_raw)\n\n# Exclusions\nexcl = []\nd = d_raw.dropna()\nexcl.append((\"1\", \"drop rows with missing values\", n_raw, len(d), n_raw - len(d), \"required fields\"))\nn0 = len(d); d = d[d.training_hours >= 0].copy()\nexcl.append((\"2\", \"drop training_hours < 0\", n0, len(d), n0 - len(d), \"negative hours per employee are physically impossible (recording error)\"))\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs\ndef fit(formula, data):\n return smf.ols(formula, data).fit(cov_type=COV)\n\ndef rmse(m):\n return float(np.sqrt(np.mean(m.resid ** 2)))\n\nnaive = fit(\"productivity_growth ~ training_hours\", d)\nadj = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity models\nadj_all = fit(\"productivity_growth ~ training_hours + skill_index\", d_raw)\nnaive_all = fit(\"productivity_growth ~ training_hours\", d_raw)\nadj_q = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\n\ndef row(name, m):\n ci = m.conf_int().loc[\"training_hours\"]\n return dict(model=name, estimate=float(m.params[\"training_hours\"]), se=float(m.bse[\"training_hours\"]),\n ci_low=float(ci[0]), ci_high=float(ci[1]), n=int(m.nobs), rmse=rmse(m))\nrows = [row(\"unadjusted (main sample)\", naive), row(\"adjusted for skill_index (main sample) [estimand]\", adj),\n row(\"adjusted + skill_index^2 (sensitivity)\", adj_q), row(\"unadjusted (all 1200 rows, sensitivity)\", naive_all),\n row(\"adjusted for skill_index (all 1200 rows, sensitivity)\", adj_all)]\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nr_n, r_a = rows[0], rows[1]\nlo, hi = r_a[\"ci_low\"], r_a[\"ci_high\"]\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nn_neg = int((d_raw.training_hours < 0).sum())\nresults = {\n \"task_id\": \"F6-conf-04\",\n \"naive_estimate\": r_n[\"estimate\"], \"naive_ci_low\": r_n[\"ci_low\"], \"naive_ci_high\": r_n[\"ci_high\"],\n \"naive_se\": r_n[\"se\"],\n \"baseline_metric\": r_n[\"rmse\"], \"model_metric\": r_a[\"rmse\"],\n \"effect_estimate\": r_a[\"estimate\"], \"effect_se\": r_a[\"se\"], \"effect_se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"skill_index_se\": float(adj.bse[\"skill_index\"]),\n \"conclusion\": conclusion,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": [{\"issue\": f\"{n_neg} rows have negative training_hours (impossible values)\",\n \"handling\": \"excluded from main analysis; sensitivity estimate on all 1200 rows reported (sensitivity_all_rows_effect)\"},\n {\"issue\": \"strong confounding: skill_index correlates 0.69 with training_hours and -0.79 with productivity_growth\",\n \"handling\": \"adjusted for pre-programme skill_index by OLS\"}],\n \"n_input_rows\": {\"firms.csv\": n_raw},\n \"n_analysed\": int(adj.nobs),\n \"random_seed\": SEED,\n \"sensitivity_all_rows_effect\": rows[4][\"estimate\"], \"sensitivity_all_rows_se\": rows[4][\"se\"],\n \"sensitivity_quadratic_skill_effect\": rows[2][\"estimate\"], \"sensitivity_quadratic_skill_se\": rows[2][\"se\"],\n \"corr_skill_training\": float(d.skill_index.corr(d.training_hours)),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(results, f, indent=2)\n\n# Figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.4, color=\"grey\", label=\"firms (n=%d)\" % len(d))\nx = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(x, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * x, \"b-\", label=f\"unadjusted OLS (slope {r_n['estimate']:.3f})\")\nsm = d.skill_index.mean()\nax.plot(x, adj.params[\"Intercept\"] + adj.params[\"training_hours\"] * x + adj.params[\"skill_index\"] * sm, \"r-\",\n label=f\"adjusted for skill_index at mean (slope {r_a['estimate']:.3f})\")\nax.set_xlabel(\"training hours per employee\"); ax.set_ylabel(\"productivity growth next year (%)\")\nax.legend(); ax.set_title(\"Productivity growth vs training hours (simulated data)\")\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120)\nprint(json.dumps({k: results[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1443,"cache_read_input_tokens":8528,"output_tokens":2335,"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":1443},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmAB8nYGQhRuP95XGjk","requestRef":"e7167cb5-d75d-42d9-8f79-2f0f9ede215c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"375dc83a-71fd-4255-8a84-611049186b21","timestamp":"2026-10-30T04:07:04.135Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"375dc83a-71fd-4255-8a84-611049186b21","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Wc2wLsFamzQGp6xjARrhkH","type":"tool_result","content":"{\n \"naive_estimate\": -0.13169790632300882,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"conclusion\": \"positive_effect\",\n \"n_analysed\": 1188\n}\nmodel,estimate,se,ci_low,ci_high,n,rmse\nunadjusted (main sample),-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195,1188,3.8601022336733584\nadjusted for skill_index (main sample) [estimand],0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976,1188,1.9758571828823268\nadjusted + skill_index^2 (sensitivity),0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293,1188,1.9756470370592571\n\"unadjusted (all 1200 rows, sensitivity)\",-0.13518960504279864,0.013896968221774055,-0.16242716225177342,-0.10795204783382387,1200,3.860935650765891\n\"adjusted for skill_index (all 1200 rows, sensitivity)\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737,1200,1.9773229272347406\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values,1200,1200,0,required fields\n2,drop training_hours < 0,1200,1188,12,negative hours per employee are physically impossible (recording error)","is_error":false}]},"uuid":"c4b46605-095a-4425-a655-883cad600968","timestamp":"2026-10-30T04:07:05.233Z","toolUseResult":{"stdout":"{\n \"naive_estimate\": -0.13169790632300882,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"conclusion\": \"positive_effect\",\n \"n_analysed\": 1188\n}\nmodel,estimate,se,ci_low,ci_high,n,rmse\nunadjusted (main sample),-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195,1188,3.8601022336733584\nadjusted for skill_index (main sample) [estimand],0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976,1188,1.9758571828823268\nadjusted + skill_index^2 (sensitivity),0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293,1188,1.9756470370592571\n\"unadjusted (all 1200 rows, sensitivity)\",-0.13518960504279864,0.013896968221774055,-0.16242716225177342,-0.10795204783382387,1200,3.860935650765891\n\"adjusted for skill_index (all 1200 rows, sensitivity)\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737,1200,1.9773229272347406\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values,1200,1200,0,required fields\n2,drop training_hours < 0,1200,1188,12,negative hours per employee are physically impossible (recording error)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"375dc83a-71fd-4255-8a84-611049186b21","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"b0a96e97e5afe6516c898c62a6c30cfb940661b9f87321dceb2a6d829c22e93e","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Wc2wLsFamzQGp6xjARrhkH","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point: run from workspace root with ~/wp29/venv/bin/python out/analysis.py\"\"\"\nimport json, os\nimport numpy as np, pandas as pd\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\nimport statsmodels.formula.api as smf\n\nSEED = None # no randomness used\nOUT = \"out\"\nd_raw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(d_raw)\n\n# Exclusions\nexcl = []\nd = d_raw.dropna()\nexcl.append((\"1\", \"drop rows with missing values\", n_raw, len(d), n_raw - len(d), \"required fields\"))\nn0 = len(d); d = d[d.training_hours >= 0].copy()\nexcl.append((\"2\", \"drop training_hours < 0\", n0, len(d), n0 - len(d), \"negative hours per employee are physically impossible (recording error)\"))\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs\ndef fit(formula, data):\n return smf.ols(formula, data).fit(cov_type=COV)\n\ndef rmse(m):\n return float(np.sqrt(np.mean(m.resid ** 2)))\n\nnaive = fit(\"productivity_growth ~ training_hours\", d)\nadj = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity models\nadj_all = fit(\"productivity_growth ~ training_hours + skill_index\", d_raw)\nnaive_all = fit(\"productivity_growth ~ training_hours\", d_raw)\nadj_q = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\n\ndef row(name, m):\n ci = m.conf_int().loc[\"training_hours\"]\n return dict(model=name, estimate=float(m.params[\"training_hours\"]), se=float(m.bse[\"training_hours\"]),\n ci_low=float(ci[0]), ci_high=float(ci[1]), n=int(m.nobs), rmse=rmse(m))\nrows = [row(\"unadjusted (main sample)\", naive), row(\"adjusted for skill_index (main sample) [estimand]\", adj),\n row(\"adjusted + skill_index^2 (sensitivity)\", adj_q), row(\"unadjusted (all 1200 rows, sensitivity)\", naive_all),\n row(\"adjusted for skill_index (all 1200 rows, sensitivity)\", adj_all)]\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nr_n, r_a = rows[0], rows[1]\nlo, hi = r_a[\"ci_low\"], r_a[\"ci_high\"]\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nn_neg = int((d_raw.training_hours < 0).sum())\nresults = {\n \"task_id\": \"F6-conf-04\",\n \"naive_estimate\": r_n[\"estimate\"], \"naive_ci_low\": r_n[\"ci_low\"], \"naive_ci_high\": r_n[\"ci_high\"],\n \"naive_se\": r_n[\"se\"],\n \"baseline_metric\": r_n[\"rmse\"], \"model_metric\": r_a[\"rmse\"],\n \"effect_estimate\": r_a[\"estimate\"], \"effect_se\": r_a[\"se\"], \"effect_se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"skill_index_se\": float(adj.bse[\"skill_index\"]),\n \"conclusion\": conclusion,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": [{\"issue\": f\"{n_neg} rows have negative training_hours (impossible values)\",\n \"handling\": \"excluded from main analysis; sensitivity estimate on all 1200 rows reported (sensitivity_all_rows_effect)\"},\n {\"issue\": \"strong confounding: skill_index correlates 0.69 with training_hours and -0.79 with productivity_growth\",\n \"handling\": \"adjusted for pre-programme skill_index by OLS\"}],\n \"n_input_rows\": {\"firms.csv\": n_raw},\n \"n_analysed\": int(adj.nobs),\n \"random_seed\": SEED,\n \"sensitivity_all_rows_effect\": rows[4][\"estimate\"], \"sensitivity_all_rows_se\": rows[4][\"se\"],\n \"sensitivity_quadratic_skill_effect\": rows[2][\"estimate\"], \"sensitivity_quadratic_skill_se\": rows[2][\"se\"],\n \"corr_skill_training\": float(d.skill_index.corr(d.training_hours)),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(results, f, indent=2)\n\n# Figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.4, color=\"grey\", label=\"firms (n=%d)\" % len(d))\nx = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(x, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * x, \"b-\", label=f\"unadjusted OLS (slope {r_n['estimate']:.3f})\")\nsm = d.skill_index.mean()\nax.plot(x, adj.params[\"Intercept\"] + adj.params[\"training_hours\"] * x + adj.params[\"skill_index\"] * sm, \"r-\",\n label=f\"adjusted for skill_index at mean (slope {r_a['estimate']:.3f})\")\nax.set_xlabel(\"training hours per employee\"); ax.set_ylabel(\"productivity growth next year (%)\")\nax.legend(); ax.set_title(\"Productivity growth vs training hours (simulated data)\")\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120)\nprint(json.dumps({k: results[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv"}}]}}43{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"ea3da36f-6cc8-4b2c-9e57-824c0d404062","timestamp":"2026-10-30T04:07:05.236Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"e7167cb5-d75d-42d9-8f79-2f0f9ede215c","keep":12,"tail":["b0a96e97e5afe6516c898c62a6c30cfb940661b9f87321dceb2a6d829c22e93e","e17236a82155bdfc160c7735a870f1f0f1355381c44945f194db2a510721c0a7"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5ad57f40a82c7fa521a7e31a95457420441e155fee422c2837b798e5fc1e3fb5"}44{"parentUuid":"c4b46605-095a-4425-a655-883cad600968","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBX9L5DLX2N436Dfvs","type":"message","role":"assistant","content":[{"type":"text","text":"Now verification (P4): clean re-run and consistency checks."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2919,"cache_read_input_tokens":9971,"output_tokens":462,"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":2919},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmBWryFV9jPFFybF7hb","requestRef":"ea3da36f-6cc8-4b2c-9e57-824c0d404062","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"427a0d0a-1a35-4060-8e48-dec936fddd07","timestamp":"2026-10-30T04:07:06.063Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"427a0d0a-1a35-4060-8e48-dec936fddd07","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBX9L5DLX2N436Dfvs","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015WXrATP7apR5Vdr369qRCb","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; rm out/results.json out/table1.csv out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; ~/wp29/venv/bin/python -c \"\nimport json,pandas as pd;r=json.load(open('out/results.json'));e=pd.read_csv('out/exclusions.csv')\nprint('count', r['n_input_rows']['firms.csv']-e.n_removed.sum()==r['n_analysed'])\nprint('se>0', r['effect_se']>0)\nprint('ci contains', r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'], r['naive_ci_low']<r['naive_estimate']<r['naive_ci_high'])\nprint('rmse adj<=naive', r['model_metric']<=r['baseline_metric'])\nprint('conclusion', r['conclusion']=='positive_effect' and r['effect_ci_low']>0)\nprint('figure', __import__('os').path.getsize('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":2919,"cache_read_input_tokens":9971,"output_tokens":462,"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":2919},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmBWryFV9jPFFybF7hb","requestRef":"ea3da36f-6cc8-4b2c-9e57-824c0d404062","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f31b3a5b-a4e8-4df9-9ba3-1f8f57d8bac3","timestamp":"2026-10-30T04:07:09.094Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"f31b3a5b-a4e8-4df9-9ba3-1f8f57d8bac3","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015WXrATP7apR5Vdr369qRCb","type":"tool_result","content":"IDENTICAL\ncount True\nse>0 True\nci contains True True\nrmse adj<=naive True\nconclusion True\nfigure 89543","is_error":false}]},"uuid":"2dfbb823-2b71-40d2-96ec-90a63c8aa3bd","timestamp":"2026-10-30T04:07:10.497Z","toolUseResult":{"stdout":"IDENTICAL\ncount True\nse>0 True\nci contains True True\nrmse adj<=naive True\nconclusion True\nfigure 89543","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f31b3a5b-a4e8-4df9-9ba3-1f8f57d8bac3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}47{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"5d7aa0db2532e6297c68811c97244d5ab01f9cc2ba9d127fa46042c8b9fb7171","message":{"role":"assistant","content":[{"type":"text","text":"Now verification (P4): clean re-run and consistency checks."},{"type":"tool_use","id":"toolu_015WXrATP7apR5Vdr369qRCb","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; rm out/results.json out/table1.csv out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; ~/wp29/venv/bin/python -c \"\nimport json,pandas as pd;r=json.load(open('out/results.json'));e=pd.read_csv('out/exclusions.csv')\nprint('count', r['n_input_rows']['firms.csv']-e.n_removed.sum()==r['n_analysed'])\nprint('se>0', r['effect_se']>0)\nprint('ci contains', r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'], r['naive_ci_low']<r['naive_estimate']<r['naive_ci_high'])\nprint('rmse adj<=naive', r['model_metric']<=r['baseline_metric'])\nprint('conclusion', r['conclusion']=='positive_effect' and r['effect_ci_low']>0)\nprint('figure', __import__('os').path.getsize('out/figure1.png'))\""}}]}}48{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"2a3add92-6696-4592-a31d-aa50202892ae","timestamp":"2026-10-30T04:07:10.501Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"ea3da36f-6cc8-4b2c-9e57-824c0d404062","keep":14,"tail":["5d7aa0db2532e6297c68811c97244d5ab01f9cc2ba9d127fa46042c8b9fb7171","76369231f3300824eb4094e0f878f718abc5db945d182e8ed11044172c0b9d15"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3ada7dde4dfe4fc51f6a2b9123b39ba4fcdb9345db8b726c2a924e74e5450745"}49{"type":"tools-used","tools":["Bash","Read"],"sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}50{"parentUuid":"2dfbb823-2b71-40d2-96ec-90a63c8aa3bd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBugQcQUudB5E1iUx3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01EeTBCAgDwWQVGyVqGQyNyT","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0017/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":513,"cache_read_input_tokens":12890,"output_tokens":80,"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":513},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmBuPncU1SdgSGdvTfi","requestRef":"2a3add92-6696-4592-a31d-aa50202892ae","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5908c240-0219-43e8-be83-5bc6fcc2aa02","timestamp":"2026-10-30T04:07:11.540Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}51{"parentUuid":"5908c240-0219-43e8-be83-5bc6fcc2aa02","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01EeTBCAgDwWQVGyVqGQyNyT","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"916fba8c-ec9f-4b4d-939a-fd48c6447def","timestamp":"2026-10-30T04:07:11.547Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":89543,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"5908c240-0219-43e8-be83-5bc6fcc2aa02","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}52{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"f7afb453a0c46e67b7682b6b8c7997fdb015cb1afbce8800b12f219d2fae27b0","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01EeTBCAgDwWQVGyVqGQyNyT","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0017/out/figure1.png"}}]}}53{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"39189d26-24bf-46c2-9b3f-6fa5518059e5","timestamp":"2026-10-30T04:07:11.551Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"2a3add92-6696-4592-a31d-aa50202892ae","keep":16,"tail":["f7afb453a0c46e67b7682b6b8c7997fdb015cb1afbce8800b12f219d2fae27b0","cf7db1a019f03accc41ffeb28585d574ccf69b8230b0e033028af74842955d8d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f4624097de7736e325671d7749d24c5e25ff69feb45516f4b362ce908ac12556"}54{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"916fba8c-ec9f-4b4d-939a-fd48c6447def","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}55{"type":"atis-latch","atis":"","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}56{"parentUuid":"916fba8c-ec9f-4b4d-939a-fd48c6447def","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBzA3QvdmD6FhGKwdC","type":"message","role":"assistant","content":[{"type":"text","text":"Figure is fine. Writing checks, report, claims, and final state."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":759,"cache_read_input_tokens":13403,"output_tokens":3273,"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":759},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmBysvJT5vp6GxemCW6","requestRef":"39189d26-24bf-46c2-9b3f-6fa5518059e5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3d100cca-65a2-45f8-bca5-262b0448d029","timestamp":"2026-10-30T04:07:12.625Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}57{"parentUuid":"3d100cca-65a2-45f8-bca5-262b0448d029","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBzA3QvdmD6FhGKwdC","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017XisYiWKNcgjeTq9dcooJr","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Checks (P4)\n- Clean re-run (deleted results.json, table1.csv, figure1.png, exclusions.csv; re-ran analysis.py): results.json byte-identical -> PASS\n- Count identity 1200 - 12 removed = 1188 = n_analysed -> PASS\n- effect_se > 0 -> PASS\n- CIs contain point estimates (effect and naive) -> PASS\n- model_metric (1.976) <= baseline_metric (3.860) -> PASS (adjusted model nests the unadjusted one)\n- conclusion code consistent with CI (lower bound 0.234 > 0) -> PASS\n- Sign flip vs baseline (naive -0.132, adjusted +0.254) explained by confounding: corr(skill, hours)=0.69, skill coefficient -4.62 -> consistent with omitted-variable bias formula direction (positive x negative = negative bias) -> PASS\n- Sensitivity: all 1200 rows 0.252; quadratic skill 0.254; (exploratory, not in script) hours x skill interaction -0.0003 (SE 0.006) -> homogeneity not contradicted -> PASS\n- Information rule: only data/firms.csv read; skill_index is pre-programme -> PASS\n- figure1.png visually inspected: scatter + both lines -> PASS\nEOF\ncat > out/report.md <<'EOF'\n# Effect of training hours on productivity growth (F6-conf-04, simulated data)\n\n## Question\nWhat is the causal effect of one extra training hour per employee during the programme year on productivity growth in the following year (pp per hour)? We assume selection on observables given the pre-programme `skill_index`, and a linear, homogeneous effect.\n\n## Data and exclusions\n`data/firms.csv` has 1200 firms (`n_input_rows`) with no missing values and no duplicate rows or IDs. Twelve firms have **negative** `training_hours` (as low as −7.6 h), which cannot happen. We treat them as recording errors and drop them from the main analysis, which leaves `n_analysed` = 1188 (see `out/exclusions.csv` and `data_issues`). A sensitivity run keeps all 1200 rows. `skill_index` is measured the year before the programme, so it is a pre-treatment variable and is valid to adjust for. In this sample it correlates 0.69 with training hours (`corr_skill_training`).\n\n## Method\n- Baseline (required): OLS of `productivity_growth` on `training_hours` with an intercept.\n- Estimand model: OLS of `productivity_growth` on `training_hours` and `skill_index`. Under the stated assumption, `skill_index` is the only confounder in the file, so adjusting for it linearly identifies the effect.\n- Standard errors are HC1 (heteroskedasticity-robust) and the 95% CIs are normal-based.\n- Sensitivity checks: (a) add a quadratic skill term; (b) keep the 12 impossible rows.\n- No randomness is used (`random_seed` = null). Outputs are `out/table1.csv` (all models) and `out/figure1.png`.\n\n## Results\n- **Unadjusted model:** the slope is −0.132 pp/h (`naive_estimate`), 95% CI [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`), with residual RMSE 3.86 pp (`baseline_metric`).\n- **Adjusted model:** the effect is **+0.254 pp per hour** (`effect_estimate`), 95% CI [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`), with residual RMSE 1.98 pp (`model_metric`).\n- **Skill coefficient:** −4.62 pp per index unit (`skill_index_coefficient`).\n- **Conclusion:** `positive_effect`.\n\nThe sign flip comes from confounding. Firms with higher skill got more training but grew less, so the unadjusted slope is biased downward.\n\n## Uncertainty\nThe robust SE is 0.0098 (`effect_se`), and the 95% CI lies well above zero. Neither sensitivity check moves the estimate much:\n- quadratic skill term: 0.254 (`sensitivity_quadratic_skill_effect`, SE `sensitivity_quadratic_skill_se`);\n- all 1200 rows: 0.252 (`sensitivity_all_rows_effect`).\n\nThese intervals cover sampling uncertainty only. They do not cover uncertainty about the identifying assumptions.\n\n## Limitations and open issues\n- **Main threat: unobserved confounding.** The causal reading depends entirely on `skill_index` being the only confounder. Any unmeasured factor that drives both training and growth (management quality, sector shocks, firm size) would bias the estimate, and these data cannot test for one. The size of the sign flip shows how sensitive the result is to which variables are adjusted for.\n- **Measurement error in skill_index.** If the index is measured with error, adjustment is incomplete. Because the confounding is strong and the bias runs downward, the true effect would then be *larger* than estimated.\n- **Impossible values.** The 12 negative-hours rows point to data-quality problems that may also affect other rows without being visible. Dropping them changes little (0.254 vs 0.252).\n- **Functional form.** We assumed linearity and a homogeneous effect. We tested a quadratic skill term. An exploratory hours×skill interaction, run outside the replication script and not in results.json, was close to zero. Non-linearity in hours (e.g. diminishing returns) was not tested. Hours above about 40 are sparse, so extrapolating there is weak.\n- **Not checked:** spillovers between firms, selection of firms into the sample, and dynamics beyond one year.\n- **Simulated data.** The data are simulated, so nothing here describes real firms.\nEOF\ncat > out/claims.json <<'EOF'\n[\n{\"id\":\"C1\",\"text\":\"The unadjusted association between training hours and productivity growth is negative (-0.132 pp/h, 95% CI excludes zero).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by skill_index.\"},\n{\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one extra training hour raises next-year productivity growth by about 0.254 pp, 95% CI [0.234, 0.273].\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal only under selection on observables with skill_index as sole confounder and linear homogeneous effect.\"},\n{\"id\":\"C3\",\"text\":\"The sign flip is explained by confounding: skill is positively correlated with training and strongly negatively related to growth.\",\"results_keys\":[\"skill_index_coefficient\",\"corr_skill_training\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"Omitted-variable-bias direction argument; relies on linear model.\"},\n{\"id\":\"C4\",\"text\":\"The estimate is robust to excluding/including the 12 negative-hours rows and to a quadratic skill term.\",\"results_keys\":[\"sensitivity_all_rows_effect\",\"sensitivity_quadratic_skill_effect\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"Does not address unobserved confounding.\"},\n{\"id\":\"C5\",\"text\":\"Adding skill_index halves residual RMSE (3.86 to 1.98 pp).\",\"results_keys\":[\"baseline_metric\",\"model_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit, not a causal validity check.\"}\n]\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 computed\",\"schema/missing/duplicates checked\",\"12 negative training_hours rows found and excluded\",\"exclusions.csv identity 1200-12=1188\"],\"notes\":\"\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"naive OLS computed: -0.132 [-0.160,-0.103], RMSE 3.860\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py writes results.json, table1.csv, figure1.png, exclusions.csv; Agg backend; no randomness\"],\"notes\":\"\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json\",\"count identity\",\"se>0\",\"CI contain estimates\",\"RMSE ordering\",\"conclusion consistent\",\"figure inspected\"],\"notes\":\"see checks.md\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md six sections with results keys cited\",\"claims.json keys exist in results.json\"],\"notes\":\"\"}}\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));c=json.load(open('out/claims.json'))\nprint([k for x in c for k in x['results_keys'] if k not in r])\"\nprintf -- \"- 2026-10-30 P2/P3 passed: baseline and adjusted OLS (HC1) in analysis.py.\\n- 2026-10-30 P4 passed: clean rerun identical; checks.md.\\n- 2026-10-30 P5 passed: report and claims written. Task complete.\\n\" >> out/state/log.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":759,"cache_read_input_tokens":13403,"output_tokens":3273,"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":759},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmBysvJT5vp6GxemCW6","requestRef":"39189d26-24bf-46c2-9b3f-6fa5518059e5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"05ca757b-e7da-490f-989b-48db640a05ff","timestamp":"2026-10-30T04:07:40.026Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"05ca757b-e7da-490f-989b-48db640a05ff","isSidechain":false,"promptId":"f9cb8bd6-7bb4-4973-b86d-ab4b156f4758","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017XisYiWKNcgjeTq9dcooJr","type":"tool_result","content":"[]","is_error":false}]},"uuid":"e46c1365-23ff-47d6-b854-f5dea4daebfd","timestamp":"2026-10-30T04:07:40.110Z","toolUseResult":{"stdout":"[]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"05ca757b-e7da-490f-989b-48db640a05ff","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}59{"type":"api-request-blob","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","hash":"ed93fbdb3661d5323bba52c3ff566afe03f12c1768a62cca15f8761c9e914798","message":{"role":"assistant","content":[{"type":"text","text":"Figure is fine. Writing checks, report, claims, and final state."},{"type":"tool_use","id":"toolu_017XisYiWKNcgjeTq9dcooJr","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Checks (P4)\n- Clean re-run (deleted results.json, table1.csv, figure1.png, exclusions.csv; re-ran analysis.py): results.json byte-identical -> PASS\n- Count identity 1200 - 12 removed = 1188 = n_analysed -> PASS\n- effect_se > 0 -> PASS\n- CIs contain point estimates (effect and naive) -> PASS\n- model_metric (1.976) <= baseline_metric (3.860) -> PASS (adjusted model nests the unadjusted one)\n- conclusion code consistent with CI (lower bound 0.234 > 0) -> PASS\n- Sign flip vs baseline (naive -0.132, adjusted +0.254) explained by confounding: corr(skill, hours)=0.69, skill coefficient -4.62 -> consistent with omitted-variable bias formula direction (positive x negative = negative bias) -> PASS\n- Sensitivity: all 1200 rows 0.252; quadratic skill 0.254; (exploratory, not in script) hours x skill interaction -0.0003 (SE 0.006) -> homogeneity not contradicted -> PASS\n- Information rule: only data/firms.csv read; skill_index is pre-programme -> PASS\n- figure1.png visually inspected: scatter + both lines -> PASS\nEOF\ncat > out/report.md <<'EOF'\n# Effect of training hours on productivity growth (F6-conf-04, simulated data)\n\n## Question\nWhat is the causal effect of one extra training hour per employee during the programme year on productivity growth in the following year (pp per hour)? We assume selection on observables given the pre-programme `skill_index`, and a linear, homogeneous effect.\n\n## Data and exclusions\n`data/firms.csv` has 1200 firms (`n_input_rows`) with no missing values and no duplicate rows or IDs. Twelve firms have **negative** `training_hours` (as low as −7.6 h), which cannot happen. We treat them as recording errors and drop them from the main analysis, which leaves `n_analysed` = 1188 (see `out/exclusions.csv` and `data_issues`). A sensitivity run keeps all 1200 rows. `skill_index` is measured the year before the programme, so it is a pre-treatment variable and is valid to adjust for. In this sample it correlates 0.69 with training hours (`corr_skill_training`).\n\n## Method\n- Baseline (required): OLS of `productivity_growth` on `training_hours` with an intercept.\n- Estimand model: OLS of `productivity_growth` on `training_hours` and `skill_index`. Under the stated assumption, `skill_index` is the only confounder in the file, so adjusting for it linearly identifies the effect.\n- Standard errors are HC1 (heteroskedasticity-robust) and the 95% CIs are normal-based.\n- Sensitivity checks: (a) add a quadratic skill term; (b) keep the 12 impossible rows.\n- No randomness is used (`random_seed` = null). Outputs are `out/table1.csv` (all models) and `out/figure1.png`.\n\n## Results\n- **Unadjusted model:** the slope is −0.132 pp/h (`naive_estimate`), 95% CI [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`), with residual RMSE 3.86 pp (`baseline_metric`).\n- **Adjusted model:** the effect is **+0.254 pp per hour** (`effect_estimate`), 95% CI [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`), with residual RMSE 1.98 pp (`model_metric`).\n- **Skill coefficient:** −4.62 pp per index unit (`skill_index_coefficient`).\n- **Conclusion:** `positive_effect`.\n\nThe sign flip comes from confounding. Firms with higher skill got more training but grew less, so the unadjusted slope is biased downward.\n\n## Uncertainty\nThe robust SE is 0.0098 (`effect_se`), and the 95% CI lies well above zero. Neither sensitivity check moves the estimate much:\n- quadratic skill term: 0.254 (`sensitivity_quadratic_skill_effect`, SE `sensitivity_quadratic_skill_se`);\n- all 1200 rows: 0.252 (`sensitivity_all_rows_effect`).\n\nThese intervals cover sampling uncertainty only. They do not cover uncertainty about the identifying assumptions.\n\n## Limitations and open issues\n- **Main threat: unobserved confounding.** The causal reading depends entirely on `skill_index` being the only confounder. Any unmeasured factor that drives both training and growth (management quality, sector shocks, firm size) would bias the estimate, and these data cannot test for one. The size of the sign flip shows how sensitive the result is to which variables are adjusted for.\n- **Measurement error in skill_index.** If the index is measured with error, adjustment is incomplete. Because the confounding is strong and the bias runs downward, the true effect would then be *larger* than estimated.\n- **Impossible values.** The 12 negative-hours rows point to data-quality problems that may also affect other rows without being visible. Dropping them changes little (0.254 vs 0.252).\n- **Functional form.** We assumed linearity and a homogeneous effect. We tested a quadratic skill term. An exploratory hours×skill interaction, run outside the replication script and not in results.json, was close to zero. Non-linearity in hours (e.g. diminishing returns) was not tested. Hours above about 40 are sparse, so extrapolating there is weak.\n- **Not checked:** spillovers between firms, selection of firms into the sample, and dynamics beyond one year.\n- **Simulated data.** The data are simulated, so nothing here describes real firms.\nEOF\ncat > out/claims.json <<'EOF'\n[\n{\"id\":\"C1\",\"text\":\"The unadjusted association between training hours and productivity growth is negative (-0.132 pp/h, 95% CI excludes zero).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by skill_index.\"},\n{\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one extra training hour raises next-year productivity growth by about 0.254 pp, 95% CI [0.234, 0.273].\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal only under selection on observables with skill_index as sole confounder and linear homogeneous effect.\"},\n{\"id\":\"C3\",\"text\":\"The sign flip is explained by confounding: skill is positively correlated with training and strongly negatively related to growth.\",\"results_keys\":[\"skill_index_coefficient\",\"corr_skill_training\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"Omitted-variable-bias direction argument; relies on linear model.\"},\n{\"id\":\"C4\",\"text\":\"The estimate is robust to excluding/including the 12 negative-hours rows and to a quadratic skill term.\",\"results_keys\":[\"sensitivity_all_rows_effect\",\"sensitivity_quadratic_skill_effect\",\"n_analysed\"],\"status\":\"supported\",\"caveat\":\"Does not address unobserved confounding.\"},\n{\"id\":\"C5\",\"text\":\"Adding skill_index halves residual RMSE (3.86 to 1.98 pp).\",\"results_keys\":[\"baseline_metric\",\"model_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit, not a causal validity check.\"}\n]\nEOF\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 computed\",\"schema/missing/duplicates checked\",\"12 negative training_hours rows found and excluded\",\"exclusions.csv identity 1200-12=1188\"],\"notes\":\"\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"naive OLS computed: -0.132 [-0.160,-0.103], RMSE 3.860\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py writes results.json, table1.csv, figure1.png, exclusions.csv; Agg backend; no randomness\"],\"notes\":\"\"},\n\"P4\":{\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json\",\"count identity\",\"se>0\",\"CI contain estimates\",\"RMSE ordering\",\"conclusion consistent\",\"figure inspected\"],\"notes\":\"see checks.md\"},\n\"P5\":{\"status\":\"passed\",\"checks\":[\"report.md six sections with results keys cited\",\"claims.json keys exist in results.json\"],\"notes\":\"\"}}\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));c=json.load(open('out/claims.json'))\nprint([k for x in c for k in x['results_keys'] if k not in r])\"\nprintf -- \"- 2026-10-30 P2/P3 passed: baseline and adjusted OLS (HC1) in analysis.py.\\n- 2026-10-30 P4 passed: clean rerun identical; checks.md.\\n- 2026-10-30 P5 passed: report and claims written. Task complete.\\n\" >> out/state/log.md"}}]}}60{"type":"api-request","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","id":"c8346221-9a96-4964-93da-fc7e1dc593e4","timestamp":"2026-10-30T04:07:40.114Z","version":"2.1.314","querySource":"sdk","shapeHash":"f50c4af6590c63cb39ac5541016cd9f831d9a6692455d7318f6ad3c5bd4bc7a3","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":"39189d26-24bf-46c2-9b3f-6fa5518059e5","keep":18,"tail":["ed93fbdb3661d5323bba52c3ff566afe03f12c1768a62cca15f8761c9e914798","b9aabfa53ebfb5d8fb5f011fb97c46d56774841af99a5f95efbbaefb04838b05"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9a522134eb91618f90b1f09130466a242e5e389137aab05cca9be5f3ab38fc79"}61{"parentUuid":"e46c1365-23ff-47d6-b854-f5dea4daebfd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmE6Fxhpjh5qqvfnQdB","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSxwcKEAgTGAI4AUIIdGhpbmtpbmcSDHm5SHuCRVkK3CbT3BoM8Sybdevfti4ubdDdIjA6/zgzd3jH9J29D6yN4tCEVkNxF1MnljjacVXsdbHhgxUvTVXKBZMlgZQMBIxlkd4q5AbmLBHQgnn/aul87mf7qNnLdl6Tys5BeqmGioB8plO/Qo38QQ2Rbr5DDbdrrtIq/mguc3hSQHWhCsmFXmVL+xlMrPQ+qAr/tCDfAcC3uGdCxYabd2MRXUvVu7dMEAoktflIxCa72uz52PZ9SehGL1T13VHDPVv5P1RJ8vr3JDq2ykpv9n26zi+bY0oSL2U8SVcxoDA6s1SEkthWiJeVSaO+rzGXjVt4VsMZgZD0Cft8va8V/BLAp/qj7hJjEJSJVU0HSuaKPpdcnwCBRyhwfNc5VU/tVp9mZ2+8UQ4+SIdJRgUa2OOMrXqQaGwi8eALNF+7W1SuGUj2wItmhtWcwKuU7eXG3oUdxE0pjUa/IwbrkGa8AO13R30NcxiTo/K+LH9F2jGU9dompAQVpdZX+j0fkS4iT03xzXxknR3s2UQJLVIb/lfYaMI+tJ1oXIwJiOAvQsWxgN3PYWCBltyZj4oO0KfdVKNZKR8r4L4YSrwGAeo1GZJdR/ZNMHcWr4GHwtnC1mpCrCxhckvBBS9BTmByKtjlu5z8+4Sq4dZSRJFmJ4Z6Aw3k7LKHfU1/9rhJOH3XzeqNyiEvjADtOBaJdQCuu52aRNF4aFV1wxkd6lDmN0sHbqx1U02KOlliqprmeRkz2eN2rG4R0vieQpa8GvfTcF41BMtwObj0s5+VGdnXbjiOOL+PhshZpTyTuL33xtSFqHueZEICTCDphFrsw2RQ5JR8/MiUM4F325OHzyfNVvsa0mancmvYQuWXBUPTgDux/ReccmGjKbFTvrB45YCQYghXIErvRE/gAH7it6NW4YucYrOs2JuoSbaSONgSnCU2e25uSiXqfZvzvNCszKMzh18zfUvIyopva0HhwzGN2PG82vtjS6xpohWkoWEPhNh3QzTe22YPIdeHR6RPJ68wLnCwLpPj0OqN8zTe7T+gUz7FxwS9+D/jS/KgiOiCMjs7MMsSOgQ/7iflaLBjZgPZg79eAUYE449j4QlaB9UKjrvP16+LJIOXv32N2B56Uz1OZbXKWGB1xP1oqpbYBjpwI4FJe9R9Saxx4CF6XCX73duPbeDTWV6g4yB6vKH05LODGy3l9IkM/XYhLjbSbX/RaDwFICiFyjJmYJz84AboSP612ecqAstO0UJJibmMlY8pYkPbGAE="}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3280,"cache_read_input_tokens":14162,"output_tokens":947,"output_tokens_details":{"thinking_tokens":56},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3280},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6650,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmE5zabbjo6Zf4BCMkB","requestRef":"c8346221-9a96-4964-93da-fc7e1dc593e4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a7fdc44e-8fd8-4163-a12d-1800f0a1ecc0","timestamp":"2026-10-30T04:07:48.044Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"a7fdc44e-8fd8-4163-a12d-1800f0a1ecc0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmE6Fxhpjh5qqvfnQdB","type":"message","role":"assistant","content":[{"type":"text","text":"After adjusting for workforce skill, one extra training hour per employee raises next-year productivity growth by about **0.254 percentage points** (95% CI 0.234 to 0.273). The conclusion code is `positive_effect`. The analysis script was re-run from a clean state and produced an identical `results.json`, and all consistency checks passed.\n\n| Model | Slope (pp per hour) | 95% CI | Residual error (RMSE, pp) |\n|---|---|---|---|\n| Unadjusted (baseline) | −0.132 | −0.160 to −0.103 | 3.86 |\n| Adjusted for `skill_index` | **+0.254** | 0.234 to 0.273 | 1.98 |\n\n- **Why the sign flips:** higher-skill firms received more training (correlation 0.69) but grew less (skill coefficient −4.62 pp per index unit). That drags the unadjusted slope downward. `skill_index` is measured the year before the programme, so adjusting for it is legitimate.\n- **Uncertainty:** the standard error is 0.0098 and is heteroskedasticity-robust (HC1). No random numbers are used, so there is no seed.\n- **Data issue:** 12 of the 1,200 firms have negative training hours, which is impossible. I treated these as recording errors and excluded them, leaving 1,188 firms in the main estimate.\n- **Robustness:** keeping those 12 rows gives 0.252, and adding a squared skill term gives 0.254.\n\n**Limitations:**\n- **Hidden confounders:** the causal reading holds only if skill is the only thing driving both training and growth. These data cannot test that, and the size of the sign flip shows how much the answer depends on what is controlled for.\n- **Skill measured with error:** if `skill_index` is measured with error, the adjustment is incomplete and the true effect would probably be larger.\n- **Untested assumptions:**\n - Non-linear effects of hours, such as diminishing returns, were not tested.\n - Data above about 40 hours is sparse.\n - Spillovers between firms and longer-run effects were not examined.\n- **Number outside the results file:** the report also mentions a hours × skill interaction close to zero (−0.0003, SE 0.006). I ran it once outside `analysis.py`, so it is not reproduced by the script or stored in `results.json`.\n- **Simulated data:** the results say nothing about real firms.\n\nEverything is in `out/`. Open `report.md` first; `state/` holds the contract, data audit, checks and log.\n- analysis.py\n- results.json\n- table1.csv\n- figure1.png\n- report.md\n- claims.json\n- exclusions.csv\n- state/"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3280,"cache_read_input_tokens":14162,"output_tokens":947,"output_tokens_details":{"thinking_tokens":56},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3280},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmE5zabbjo6Zf4BCMkB","requestRef":"c8346221-9a96-4964-93da-fc7e1dc593e4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"62aa3607-09e0-45cb-882e-2d16bc4da169","timestamp":"2026-10-30T04:07:49.358Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0017","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","version":"2.1.314","gitBranch":"HEAD"}63{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"62aa3607-09e0-45cb-882e-2d16bc4da169","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68"}64{"type":"cost-state","sessionId":"def493f8-3e47-4029-aafb-994a14b06c68","totalCostUSD":0.2876356,"totalAPIDuration":82362,"totalAPIDurationWithoutRetries":82355,"totalToolDuration":4476,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":87023,"startTime":1793333182343,"modelUsage":{"claude-opus-5-5":{"inputTokens":22,"outputTokens":9542,"thinkingTokens":270,"cacheReadInputTokens":85088,"cacheCreationInputTokens":15938,"cacheCreationEphemeral5mInputTokens":15938,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.2876356}},"hasUnknownModelCost":false}65