1{"type":"atis-latch","atis":"","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:08:45.134Z","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:08:45.141Z","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}4{"parentUuid":null,"isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":"Begin"},"uuid":"b23c5c62-0290-428f-9731-40ee602816f8","timestamp":"2026-10-30T04:08:45.146Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","timestamp":"2026-10-30T04:08:45.163Z","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/RC0023\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`.\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":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"96fcf340-ac0e-4b06-9c51-8ec8bcc42e0e","timestamp":"2026-10-30T04:08:45.163Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"50d52a4854bbea97a151efe3ff7e50646be38240eae939b212b8db122f7998b2"}8{"parentUuid":"b23c5c62-0290-428f-9731-40ee602816f8","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"febd1504-7843-4b23-a437-1ab7bcc6031d","timestamp":"2026-10-30T04:08:45.153Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"febd1504-7843-4b23-a437-1ab7bcc6031d","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"f4fa6d20-828f-4fa4-8c38-8359773c30c0","timestamp":"2026-10-30T04:08:45.153Z","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/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"f4fa6d20-828f-4fa4-8c38-8359773c30c0","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":"d4dc9444-c2b4-4537-87cd-07c98dbea574","timestamp":"2026-10-30T04:08:45.154Z","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/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}12{"parentUuid":"d4dc9444-c2b4-4537-87cd-07c98dbea574","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmJzQcqZxjpaizy6Bjp","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WBnnaE92npR4M2wGRsMXo3","name":"Bash","input":{"command":"cat TASK.md; ls -la data; find data -type f | head -50","description":"Read task and list data files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":730,"cache_read_input_tokens":1504,"output_tokens":96,"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":730},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmJz7FVEy5GWXGQ9ab6","requestRef":"96fcf340-ac0e-4b06-9c51-8ec8bcc42e0e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8f0ba20f-f274-425f-b751-f008ecc90c60","timestamp":"2026-10-30T04:08:47.780Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"8f0ba20f-f274-425f-b751-f008ecc90c60","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WBnnaE92npR4M2wGRsMXo3","type":"tool_result","content":"# 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 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\ndata/firms.csv","is_error":false}]},"uuid":"c015e330-35e6-4642-8e55-31a452512f57","timestamp":"2026-10-30T04:08:47.858Z","toolUseResult":{"stdout":"# 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 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\ndata/firms.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8f0ba20f-f274-425f-b751-f008ecc90c60","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}14{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"1f8e3b8b01de67e4c82e07461a314d47358804a5b1264227f231e35c3911020e","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01WBnnaE92npR4M2wGRsMXo3","name":"Bash","input":{"command":"cat TASK.md; ls -la data; find data -type f | head -50","description":"Read task and list data files"}}]}}15{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"8b96932f-80bf-46cb-8046-00d8b16eedd7","timestamp":"2026-10-30T04:08:47.863Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"96fcf340-ac0e-4b06-9c51-8ec8bcc42e0e","keep":2,"tail":["1f8e3b8b01de67e4c82e07461a314d47358804a5b1264227f231e35c3911020e","4d137330e1830ee01d60289080914909ebfe73aa50745b6ad14060334c0c3d2b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ecf09440f47b8f5b0c77aadfcf0ec16b62b77dffacc170b2927a41416482bfc3"}16{"parentUuid":"c015e330-35e6-4642-8e55-31a452512f57","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmK7SHe4swgVN6UjL5m","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BrZ6BN2L2Vzn8iWjB8KpEe","name":"Bash","input":{"command":"cd data; head -5 firms.csv; wc -l firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('firms.csv'); print(d.describe(include='all')); print(d.isna().sum()); print(d.firm_id.duplicated().sum(), d.duplicated().sum()); print(d.dtypes); print(d.corr())\nprint(d.sort_values('training_hours').head()); print(d.sort_values('training_hours').tail()); print(d.sort_values('productivity_growth').head(3)); print(d.sort_values('productivity_growth').tail(3))\"","description":"Audit the data"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2181,"cache_read_input_tokens":2234,"output_tokens":285,"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":2181},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmK7AfLt3vmaBwUYjL7","requestRef":"8b96932f-80bf-46cb-8046-00d8b16eedd7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a78bca63-8034-4afe-bb73-a26fd3266c2e","timestamp":"2026-10-30T04:08:50.422Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}17{"parentUuid":"a78bca63-8034-4afe-bb73-a26fd3266c2e","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BrZ6BN2L2Vzn8iWjB8KpEe","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\n 1201 firms.csv\n firm_id skill_index training_hours productivity_growth\ncount 1200.000000 1200.000000 1200.000000 1200.000000\nmean 1600.500000 -0.001467 19.945735 7.083012\nstd 346.554469 0.994503 8.243620 4.020107\nmin 1001.000000 -3.827900 -7.585000 -4.038000\n25% 1300.750000 -0.642375 14.580750 4.444350\n50% 1600.500000 0.010250 19.676500 7.061400\n75% 1900.250000 0.680000 25.502000 9.987000\nmax 2200.000000 2.962300 51.770000 19.388900\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object\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\n firm_id skill_index training_hours productivity_growth\n1140 1247 -2.9694 -7.585 13.3106\n880 1927 -2.0138 -6.388 10.4497\n1009 1483 -2.8599 -5.672 13.5980\n518 1463 -2.1087 -5.383 10.3419\n372 1425 -1.6253 -4.006 8.9215\n firm_id skill_index training_hours productivity_growth\n687 1338 2.4382 43.266 2.7879\n988 1693 2.6033 44.370 2.1735\n265 1002 1.9398 45.489 6.4246\n343 2196 1.6513 47.697 5.1932\n722 1334 1.3806 51.770 10.1090\n firm_id skill_index training_hours productivity_growth\n955 1320 2.0661 19.088 -4.0380\n832 1376 2.9623 40.969 -3.5604\n484 1169 2.2199 32.986 -3.5072\n firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n870 1417 -3.8279 5.281 19.2839\n53 1592 -1.8429 22.966 19.3889","is_error":false}]},"uuid":"7712a7eb-a2d2-4856-95da-ae4e1d313bff","timestamp":"2026-10-30T04:08:50.740Z","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\n 1201 firms.csv\n firm_id skill_index training_hours productivity_growth\ncount 1200.000000 1200.000000 1200.000000 1200.000000\nmean 1600.500000 -0.001467 19.945735 7.083012\nstd 346.554469 0.994503 8.243620 4.020107\nmin 1001.000000 -3.827900 -7.585000 -4.038000\n25% 1300.750000 -0.642375 14.580750 4.444350\n50% 1600.500000 0.010250 19.676500 7.061400\n75% 1900.250000 0.680000 25.502000 9.987000\nmax 2200.000000 2.962300 51.770000 19.388900\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object\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\n firm_id skill_index training_hours productivity_growth\n1140 1247 -2.9694 -7.585 13.3106\n880 1927 -2.0138 -6.388 10.4497\n1009 1483 -2.8599 -5.672 13.5980\n518 1463 -2.1087 -5.383 10.3419\n372 1425 -1.6253 -4.006 8.9215\n firm_id skill_index training_hours productivity_growth\n687 1338 2.4382 43.266 2.7879\n988 1693 2.6033 44.370 2.1735\n265 1002 1.9398 45.489 6.4246\n343 2196 1.6513 47.697 5.1932\n722 1334 1.3806 51.770 10.1090\n firm_id skill_index training_hours productivity_growth\n955 1320 2.0661 19.088 -4.0380\n832 1376 2.9623 40.969 -3.5604\n484 1169 2.2199 32.986 -3.5072\n firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n870 1417 -3.8279 5.281 19.2839\n53 1592 -1.8429 22.966 19.3889","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a78bca63-8034-4afe-bb73-a26fd3266c2e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}18{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"3592013eb580cc4eb7bedba29319b098b9013dd3a1744a185599d03404d4d6fe","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01BrZ6BN2L2Vzn8iWjB8KpEe","name":"Bash","input":{"command":"cd data; head -5 firms.csv; wc -l firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('firms.csv'); print(d.describe(include='all')); print(d.isna().sum()); print(d.firm_id.duplicated().sum(), d.duplicated().sum()); print(d.dtypes); print(d.corr())\nprint(d.sort_values('training_hours').head()); print(d.sort_values('training_hours').tail()); print(d.sort_values('productivity_growth').head(3)); print(d.sort_values('productivity_growth').tail(3))\"","description":"Audit the data"}}]}}19{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"0df312f3-b05d-4bc3-b2cf-84ddf406e36c","timestamp":"2026-10-30T04:08:50.743Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"8b96932f-80bf-46cb-8046-00d8b16eedd7","keep":4,"tail":["3592013eb580cc4eb7bedba29319b098b9013dd3a1744a185599d03404d4d6fe","b0308975e0fc76d79866bf12d647ba7c8b77324d2492a9da344c8d161c9f4eb3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"af0d398fcfc93532c933fbcdcfa470a18bc9fe3178dba39d61fb6e91386cdf4e"}20{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"7712a7eb-a2d2-4856-95da-ae4e1d313bff","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}21{"type":"atis-latch","atis":"","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}22{"parentUuid":"7712a7eb-a2d2-4856-95da-ae4e1d313bff","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmKKnSC2CxybxFEEEog","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":1236,"cache_read_input_tokens":4415,"output_tokens":350,"output_tokens_details":{"thinking_tokens":38},"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":1236},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":440,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmKKU5YQ5ovMpF8tRhg","requestRef":"0df312f3-b05d-4bc3-b2cf-84ddf406e36c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b87132af-5db4-4efa-8a39-bf2428b2717d","timestamp":"2026-10-30T04:08:51.962Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}23{"parentUuid":"b87132af-5db4-4efa-8a39-bf2428b2717d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmKKnSC2CxybxFEEEog","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JJdATd7iKaAQnucH3GLP6Q","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd, statsmodels.formula.api as smf; d=pd.read_csv('firms.csv'); print((d.training_hours<0).sum(), (d.training_hours==0).sum()); print(d.training_hours.value_counts().head(8)); print(d.training_hours.round(0).eq(d.training_hours).sum())\nfor s in [d, d[d.training_hours>=0]]:\n print(smf.ols('productivity_growth~training_hours+skill_index',s).fit(cov_type='HC1').summary().tables[1])\nd['n']=d.training_hours<0; print(d.groupby('n').mean())\n\"","description":"Check negative hours and heaping"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1236,"cache_read_input_tokens":4415,"output_tokens":350,"output_tokens_details":{"thinking_tokens":38},"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":1236},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmKKU5YQ5ovMpF8tRhg","requestRef":"0df312f3-b05d-4bc3-b2cf-84ddf406e36c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"efac15ce-a133-460d-b022-0d5fd8da7d6f","timestamp":"2026-10-30T04:08:54.084Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"efac15ce-a133-460d-b022-0d5fd8da7d6f","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JJdATd7iKaAQnucH3GLP6Q","type":"tool_result","content":"(eval):cd:1: no such file or directory: data\n12 0\ntraining_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\n29.737 2\n30.812 2\n14.113 2\nName: count, dtype: int64\n4\n==================================================================================\n coef std err z P>|z| [0.025 0.975]\n----------------------------------------------------------------------------------\nIntercept 2.0454 0.201 10.198 0.000 1.652 2.439\ntraining_hours 0.2522 0.009 26.609 0.000 0.234 0.271\nskill_index -4.6304 0.078 -59.297 0.000 -4.783 -4.477\n==================================================================================\n==================================================================================\n coef std err z P>|z| [0.025 0.975]\n----------------------------------------------------------------------------------\nIntercept 2.0132 0.208 9.657 0.000 1.605 2.422\ntraining_hours 0.2535 0.010 25.839 0.000 0.234 0.273\nskill_index -4.6246 0.078 -59.166 0.000 -4.778 -4.471\n==================================================================================\n firm_id skill_index training_hours productivity_growth\nn \nFalse 1601.195286 0.019303 20.183386 7.041209\nTrue 1531.666667 -2.057633 -3.581667 11.221542","is_error":false}]},"uuid":"adf659fa-24ca-4143-9e74-680ab8d9018b","timestamp":"2026-10-30T04:08:54.890Z","toolUseResult":{"stdout":"(eval):cd:1: no such file or directory: data\n12 0\ntraining_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\n29.737 2\n30.812 2\n14.113 2\nName: count, dtype: int64\n4\n==================================================================================\n coef std err z P>|z| [0.025 0.975]\n----------------------------------------------------------------------------------\nIntercept 2.0454 0.201 10.198 0.000 1.652 2.439\ntraining_hours 0.2522 0.009 26.609 0.000 0.234 0.271\nskill_index -4.6304 0.078 -59.297 0.000 -4.783 -4.477\n==================================================================================\n==================================================================================\n coef std err z P>|z| [0.025 0.975]\n----------------------------------------------------------------------------------\nIntercept 2.0132 0.208 9.657 0.000 1.605 2.422\ntraining_hours 0.2535 0.010 25.839 0.000 0.234 0.273\nskill_index -4.6246 0.078 -59.166 0.000 -4.778 -4.471\n==================================================================================\n firm_id skill_index training_hours productivity_growth\nn \nFalse 1601.195286 0.019303 20.183386 7.041209\nTrue 1531.666667 -2.057633 -3.581667 11.221542","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"efac15ce-a133-460d-b022-0d5fd8da7d6f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}25{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"42852064550225e27b4b8d5745a833ded31a68e27bd4953d7ee872818e7f8963","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JJdATd7iKaAQnucH3GLP6Q","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd, statsmodels.formula.api as smf; d=pd.read_csv('firms.csv'); print((d.training_hours<0).sum(), (d.training_hours==0).sum()); print(d.training_hours.value_counts().head(8)); print(d.training_hours.round(0).eq(d.training_hours).sum())\nfor s in [d, d[d.training_hours>=0]]:\n print(smf.ols('productivity_growth~training_hours+skill_index',s).fit(cov_type='HC1').summary().tables[1])\nd['n']=d.training_hours<0; print(d.groupby('n').mean())\n\"","description":"Check negative hours and heaping"}}]}}26{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"0123671e-4f92-4241-a36e-a42099880b73","timestamp":"2026-10-30T04:08:54.894Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"0df312f3-b05d-4bc3-b2cf-84ddf406e36c","keep":6,"tail":["42852064550225e27b4b8d5745a833ded31a68e27bd4953d7ee872818e7f8963","9e37466420bb2ea1bda1a06de68fc4ac466e847005e2146b9991f5c63c786286"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"93e3c91b27cd59ff7c9b80485ec96c81c96654bb362da8c04ac296cd269b6510"}27{"parentUuid":"adf659fa-24ca-4143-9e74-680ab8d9018b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmKdWJAN5UNfuqFHRpZ","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":819,"cache_read_input_tokens":5651,"output_tokens":2085,"output_tokens_details":{"thinking_tokens":59},"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":819},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":557,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmKdDBStN9GkYPVoH8b","requestRef":"0123671e-4f92-4241-a36e-a42099880b73","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"79a85e60-389c-4238-a0ec-3f7561a9ae67","timestamp":"2026-10-30T04:08:56.491Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}28{"parentUuid":"79a85e60-389c-4238-a0ec-3f7561a9ae67","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmKdWJAN5UNfuqFHRpZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PDka1HSsJ2v24t54AyXHPF","name":"Bash","input":{"command":"mkdir -p out; cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nDeterministic (no randomness used).\"\"\"\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\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# ---- data audit ----\nissues = []\nassert raw.isna().sum().sum() == 0\nassert not raw.firm_id.duplicated().any()\nneg = raw.training_hours < 0\nn_neg = int(neg.sum())\nif n_neg:\n issues.append({\n \"issue\": f\"{n_neg} firms have negative training_hours (min {raw.training_hours.min():.3f}); \"\n \"hours of training per employee cannot be negative, so these values are invalid.\",\n \"handling\": \"Excluded from the main analysis (no imputation). Sensitivity: re-estimated with them \"\n \"included; the training coefficient changes by <0.002 pp/hour.\"})\nd = raw.loc[~neg].copy()\n\ndef rmse(res):\n return float(np.sqrt(np.mean(res.resid ** 2)))\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs throughout\nnaive = smf.ols(\"productivity_growth ~ training_hours\", d).fit(cov_type=COV)\nadj = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit(cov_type=COV)\n# sensitivity checks\nadj_all = smf.ols(\"productivity_growth ~ training_hours + skill_index\", raw).fit(cov_type=COV)\nadj_q = smf.ols(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2) + I(training_hours**2)\",\n d).fit(cov_type=COV)\nadj_conv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\ndef row(name, m, var=\"training_hours\"):\n ci = m.conf_int().loc[var]\n return {\"model\": name, \"estimate\": float(m.params[var]), \"se\": float(m.bse[var]),\n \"ci_low\": float(ci[0]), \"ci_high\": float(ci[1])}\n\nrows = [row(\"unadjusted OLS (training_hours only)\", naive),\n row(\"adjusted OLS (training_hours + skill_index) [main]\", adj),\n row(\"sensitivity: adjusted, incl. negative-hours rows\", adj_all),\n row(\"sensitivity: adjusted + quadratic terms (linear coef)\", adj_q),\n row(\"sensitivity: adjusted, conventional SE\", adj_conv)]\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\nprint(pd.DataFrame(rows).to_string())\nprint(\"quadratic-term p-values:\", adj_q.pvalues.to_dict())\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\")\nx = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(x, naive.params.Intercept + naive.params.training_hours * x, color=\"C0\",\n label=f\"unadjusted OLS (slope {naive.params.training_hours:.3f})\")\nsm = d.skill_index.mean()\nax.plot(x, adj.params.Intercept + adj.params.training_hours * x + adj.params.skill_index * sm, color=\"C3\",\n label=f\"adjusted for skill_index at mean (slope {adj.params.training_hours:.3f})\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours (simulated data, n=%d)\" % len(d))\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=150)\n\nlo, hi = rows[1][\"ci_low\"], rows[1][\"ci_high\"]\nconcl = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nres = {\n \"task_id\": \"F6-conf-04\",\n \"naive_estimate\": rows[0][\"estimate\"], \"naive_ci_low\": rows[0][\"ci_low\"], \"naive_ci_high\": rows[0][\"ci_high\"],\n \"baseline_metric\": rmse(naive), \"model_metric\": rmse(adj),\n \"effect_estimate\": rows[1][\"estimate\"], \"effect_se\": rows[1][\"se\"],\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params.skill_index),\n \"conclusion\": concl, \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": issues, \"n_input_rows\": {\"firms.csv\": n_raw},\n \"n_analysed\": int(adj.nobs), \"random_seed\": None,\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\nprint(json.dumps(res, indent=2))\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":819,"cache_read_input_tokens":5651,"output_tokens":2085,"output_tokens_details":{"thinking_tokens":59},"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":819},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmKdDBStN9GkYPVoH8b","requestRef":"0123671e-4f92-4241-a36e-a42099880b73","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2d97732e-2849-49f9-a980-88b31901d260","timestamp":"2026-10-30T04:09:10.769Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"2d97732e-2849-49f9-a980-88b31901d260","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n File \"/Users/simon-pierreboucher/wp29/runs/RC0023/data/out/analysis.py\", line 13, in <module>\n raw = pd.read_csv(\"data/firms.csv\")\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n return _read(filepath_or_buffer, kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n parser = TextFileReader(filepath_or_buffer, **kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n self._engine = self._make_engine(f, self.engine)\n ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n self.handles = get_handle(\n ~~~~~~~~~~^\n f,\n ^^\n ...<6 lines>...\n storage_options=self.options.get(\"storage_options\", None),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n handle = open(\n handle,\n ...<3 lines>...\n newline=\"\",\n )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/firms.csv'","is_error":true,"tool_use_id":"toolu_01PDka1HSsJ2v24t54AyXHPF"}]},"uuid":"16a65cdc-c8c9-4152-a659-8f2ca411a16c","timestamp":"2026-10-30T04:09:11.865Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n File \"/Users/simon-pierreboucher/wp29/runs/RC0023/data/out/analysis.py\", line 13, in <module>\n raw = pd.read_csv(\"data/firms.csv\")\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n return _read(filepath_or_buffer, kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n parser = TextFileReader(filepath_or_buffer, **kwds)\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n self._engine = self._make_engine(f, self.engine)\n ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n self.handles = get_handle(\n ~~~~~~~~~~^\n f,\n ^^\n ...<6 lines>...\n storage_options=self.options.get(\"storage_options\", None),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n handle = open(\n handle,\n ...<3 lines>...\n newline=\"\",\n )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/firms.csv'","sandboxed":false,"sourceToolAssistantUUID":"2d97732e-2849-49f9-a980-88b31901d260","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}30{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"013071cbb121a16bb3ad699c58cc649e3e5aa120532d4182f1abad8d528b27e6","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01PDka1HSsJ2v24t54AyXHPF","name":"Bash","input":{"command":"mkdir -p out; cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nDeterministic (no randomness used).\"\"\"\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\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# ---- data audit ----\nissues = []\nassert raw.isna().sum().sum() == 0\nassert not raw.firm_id.duplicated().any()\nneg = raw.training_hours < 0\nn_neg = int(neg.sum())\nif n_neg:\n issues.append({\n \"issue\": f\"{n_neg} firms have negative training_hours (min {raw.training_hours.min():.3f}); \"\n \"hours of training per employee cannot be negative, so these values are invalid.\",\n \"handling\": \"Excluded from the main analysis (no imputation). Sensitivity: re-estimated with them \"\n \"included; the training coefficient changes by <0.002 pp/hour.\"})\nd = raw.loc[~neg].copy()\n\ndef rmse(res):\n return float(np.sqrt(np.mean(res.resid ** 2)))\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs throughout\nnaive = smf.ols(\"productivity_growth ~ training_hours\", d).fit(cov_type=COV)\nadj = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit(cov_type=COV)\n# sensitivity checks\nadj_all = smf.ols(\"productivity_growth ~ training_hours + skill_index\", raw).fit(cov_type=COV)\nadj_q = smf.ols(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2) + I(training_hours**2)\",\n d).fit(cov_type=COV)\nadj_conv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\ndef row(name, m, var=\"training_hours\"):\n ci = m.conf_int().loc[var]\n return {\"model\": name, \"estimate\": float(m.params[var]), \"se\": float(m.bse[var]),\n \"ci_low\": float(ci[0]), \"ci_high\": float(ci[1])}\n\nrows = [row(\"unadjusted OLS (training_hours only)\", naive),\n row(\"adjusted OLS (training_hours + skill_index) [main]\", adj),\n row(\"sensitivity: adjusted, incl. negative-hours rows\", adj_all),\n row(\"sensitivity: adjusted + quadratic terms (linear coef)\", adj_q),\n row(\"sensitivity: adjusted, conventional SE\", adj_conv)]\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\nprint(pd.DataFrame(rows).to_string())\nprint(\"quadratic-term p-values:\", adj_q.pvalues.to_dict())\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\")\nx = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(x, naive.params.Intercept + naive.params.training_hours * x, color=\"C0\",\n label=f\"unadjusted OLS (slope {naive.params.training_hours:.3f})\")\nsm = d.skill_index.mean()\nax.plot(x, adj.params.Intercept + adj.params.training_hours * x + adj.params.skill_index * sm, color=\"C3\",\n label=f\"adjusted for skill_index at mean (slope {adj.params.training_hours:.3f})\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours (simulated data, n=%d)\" % len(d))\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=150)\n\nlo, hi = rows[1][\"ci_low\"], rows[1][\"ci_high\"]\nconcl = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\nres = {\n \"task_id\": \"F6-conf-04\",\n \"naive_estimate\": rows[0][\"estimate\"], \"naive_ci_low\": rows[0][\"ci_low\"], \"naive_ci_high\": rows[0][\"ci_high\"],\n \"baseline_metric\": rmse(naive), \"model_metric\": rmse(adj),\n \"effect_estimate\": rows[1][\"estimate\"], \"effect_se\": rows[1][\"se\"],\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params.skill_index),\n \"conclusion\": concl, \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": issues, \"n_input_rows\": {\"firms.csv\": n_raw},\n \"n_analysed\": int(adj.nobs), \"random_seed\": None,\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\nprint(json.dumps(res, indent=2))\nEOF\n~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"}}]}}31{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"b77c1ca2-afd9-4a5f-a678-ec48efa26be2","timestamp":"2026-10-30T04:09:11.869Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"0123671e-4f92-4241-a36e-a42099880b73","keep":8,"tail":["013071cbb121a16bb3ad699c58cc649e3e5aa120532d4182f1abad8d528b27e6","a92f0e6d91f154032e3437717f074baad9da491f502e953df0825d9a9d969146"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"def01e908a4e58ee2ecb919fa60ce74f81e30c9043d2cac150ddba28c479d699"}32{"parentUuid":"16a65cdc-c8c9-4152-a659-8f2ca411a16c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmLszhyKDJYbCvqTxUd","type":"message","role":"assistant","content":[{"type":"text","text":"The shell was still in `data/`; I'll move the file to the workspace root and rerun."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2795,"cache_read_input_tokens":6470,"output_tokens":192,"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":2795},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmLso3uAczwmUHx3scW","requestRef":"b77c1ca2-afd9-4a5f-a678-ec48efa26be2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"146121cf-890d-4fad-80d9-ac2a7474b15f","timestamp":"2026-10-30T04:09:12.761Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}33{"parentUuid":"146121cf-890d-4fad-80d9-ac2a7474b15f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmLszhyKDJYbCvqTxUd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FJDX4EqZSCFyQ3p6xpe6ap","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0023 && mkdir -p out && mv data/out/analysis.py out/ && rmdir data/out && ls data && ~/wp29/venv/bin/python out/analysis.py","description":"Relocate script and run from workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2795,"cache_read_input_tokens":6470,"output_tokens":192,"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":2795},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmLso3uAczwmUHx3scW","requestRef":"b77c1ca2-afd9-4a5f-a678-ec48efa26be2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"94d2f1e6-3833-47eb-b568-b7672aa4df41","timestamp":"2026-10-30T04:09:13.730Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023/data","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}34{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"94d2f1e6-3833-47eb-b568-b7672aa4df41","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}35{"type":"atis-latch","atis":"","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}36{"parentUuid":"94d2f1e6-3833-47eb-b568-b7672aa4df41","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FJDX4EqZSCFyQ3p6xpe6ap","type":"tool_result","content":"firms.csv\n model estimate se ci_low ci_high\n0 unadjusted OLS (training_hours only) -0.131698 0.014620 -0.160352 -0.103044\n1 adjusted OLS (training_hours + skill_index) [main] 0.253538 0.009812 0.234307 0.272770\n2 sensitivity: adjusted, incl. negative-hours rows 0.252224 0.009479 0.233646 0.270803\n3 sensitivity: adjusted + quadratic terms (linear coef) 0.242007 0.028945 0.185276 0.298738\n4 sensitivity: adjusted, conventional SE 0.253538 0.009841 0.234230 0.272846\nquadratic-term p-values: {'Intercept': 1.6126545454582234e-10, 'training_hours': 6.22028211845714e-17, 'skill_index': 0.0, 'I(skill_index ** 2)': 0.47506298393656354, 'I(training_hours ** 2)': 0.659660195892065}\n{\n \"task_id\": \"F6-conf-04\",\n \"naive_estimate\": -0.13169790632300882,\n \"naive_ci_low\": -0.1603518326928757,\n \"naive_ci_high\": -0.10304397995314195,\n \"baseline_metric\": 3.8601022336733584,\n \"model_metric\": 1.9758571828823268,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"skill_index_coefficient\": -4.624620879345756,\n \"conclusion\": \"positive_effect\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 firms have negative training_hours (min -7.585); hours of training per employee cannot be negative, so these values are invalid.\",\n \"handling\": \"Excluded from the main analysis (no imputation). Sensitivity: re-estimated with them included; the training coefficient changes by <0.002 pp/hour.\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null\n}","is_error":false}]},"uuid":"f386040c-795c-4dfd-af29-a41ea2dafc08","timestamp":"2026-10-30T04:09:14.941Z","toolUseResult":{"stdout":"firms.csv\n model estimate se ci_low ci_high\n0 unadjusted OLS (training_hours only) -0.131698 0.014620 -0.160352 -0.103044\n1 adjusted OLS (training_hours + skill_index) [main] 0.253538 0.009812 0.234307 0.272770\n2 sensitivity: adjusted, incl. negative-hours rows 0.252224 0.009479 0.233646 0.270803\n3 sensitivity: adjusted + quadratic terms (linear coef) 0.242007 0.028945 0.185276 0.298738\n4 sensitivity: adjusted, conventional SE 0.253538 0.009841 0.234230 0.272846\nquadratic-term p-values: {'Intercept': 1.6126545454582234e-10, 'training_hours': 6.22028211845714e-17, 'skill_index': 0.0, 'I(skill_index ** 2)': 0.47506298393656354, 'I(training_hours ** 2)': 0.659660195892065}\n{\n \"task_id\": \"F6-conf-04\",\n \"naive_estimate\": -0.13169790632300882,\n \"naive_ci_low\": -0.1603518326928757,\n \"naive_ci_high\": -0.10304397995314195,\n \"baseline_metric\": 3.8601022336733584,\n \"model_metric\": 1.9758571828823268,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"skill_index_coefficient\": -4.624620879345756,\n \"conclusion\": \"positive_effect\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 firms have negative training_hours (min -7.585); hours of training per employee cannot be negative, so these values are invalid.\",\n \"handling\": \"Excluded from the main analysis (no imputation). Sensitivity: re-estimated with them included; the training coefficient changes by <0.002 pp/hour.\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"94d2f1e6-3833-47eb-b568-b7672aa4df41","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}37{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"c3fb4e452addffbdf5337e963d0407f24a41610dee25cefc7917d572fcd5bd96","message":{"role":"assistant","content":[{"type":"text","text":"The shell was still in `data/`; I'll move the file to the workspace root and rerun."},{"type":"tool_use","id":"toolu_01FJDX4EqZSCFyQ3p6xpe6ap","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0023 && mkdir -p out && mv data/out/analysis.py out/ && rmdir data/out && ls data && ~/wp29/venv/bin/python out/analysis.py","description":"Relocate script and run from workspace root"}}]}}38{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"ce713070-e810-4a3e-9ca3-cd2e6a24ab35","timestamp":"2026-10-30T04:09:14.945Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"b77c1ca2-afd9-4a5f-a678-ec48efa26be2","keep":10,"tail":["c3fb4e452addffbdf5337e963d0407f24a41610dee25cefc7917d572fcd5bd96","8d5804c9612914b524499f106c3afb45ead6a7da664c695bcc0d6f88f3bb114e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"08a70bc5bd3a982670a42f580dadc3d30effbca1d65b217c7e5dd6929dcacd24"}39{"type":"tools-used","tools":["Bash","Read"],"sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}40{"parentUuid":"f386040c-795c-4dfd-af29-a41ea2dafc08","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmM79ESVwXoNJ2XhJoS","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":984,"cache_read_input_tokens":9265,"output_tokens":124,"output_tokens_details":{"thinking_tokens":43},"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":984},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":395,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmM6xKvCw5sthhTQGeJ","requestRef":"ce713070-e810-4a3e-9ca3-cd2e6a24ab35","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"38017eff-a715-4d3e-ba23-98b0dee0f237","timestamp":"2026-10-30T04:09:16.242Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"38017eff-a715-4d3e-ba23-98b0dee0f237","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmM79ESVwXoNJ2XhJoS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QeGkY2i4WLjj3ihmz1wx4x","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0023/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":984,"cache_read_input_tokens":9265,"output_tokens":124,"output_tokens_details":{"thinking_tokens":43},"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":984},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmM6xKvCw5sthhTQGeJ","requestRef":"ce713070-e810-4a3e-9ca3-cd2e6a24ab35","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"277efdcd-2033-4603-ab2e-4606ea76c383","timestamp":"2026-10-30T04:09:16.506Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"277efdcd-2033-4603-ab2e-4606ea76c383","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QeGkY2i4WLjj3ihmz1wx4x","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"867cf0eb-8c59-45e7-8ac2-b3f601f192ca","timestamp":"2026-10-30T04:09:16.515Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":122404,"dimensions":{"originalWidth":1050,"originalHeight":750,"displayWidth":1050,"displayHeight":750}}},"sourceToolAssistantUUID":"277efdcd-2033-4603-ab2e-4606ea76c383","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}43{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"4201d0ed529b8b9d0fa17ebe4578d30c6893c784cfd43e5315d77dc0f66c7cf9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS6QYKEAgTGAI4AUIIdGhpbmtpbmcSDDrWsU/RPZ+ES5SVARoMsVzAy1zEDjwSuuyMIjDw4wP/ia5HfMuGpQ/Q50WXBCoYfe72hjf42vNTEvtAZAtRSuL54a2T2jTkcxkIXCMqhgb7uwAfan5+eKZra4jKeyZeJuj/hfm6Dii7QCNru9pIKT+Tq1qkzfHGWx2INtNLonHSw4UCflYXvGX+bq3tYLj7zm2hr3zV8CyTfmICAdR2PWxKWGiC6Dp/EXs00cky1kAbll+5yfTiwMWU3WcQtdvluGN0ySOMLDvTM8mN4gDEEOpSnc5Y9G+m75WMd92IG+APeV/l1VEikz8nn8/eVWJUvtbZjV02q53JoasJosCgvzle4hS9tFiGRnvrDW+/trcD5fQjr6a2M5J/a1PjVb9L3KXUlxqaxN7bV7C9Ssml6Fj1mhF377ubXB5zzTmF0p2K2mW7M2UL6kHcZCyTpmDbKVosE6X9OGHujlfKyAQJzVqbxrZwY53YwmXOKyOo8RsdctwiuUb5S3HDg5qgRhD9qDg0qkh/W86F4OaeABlWgzOfiKcXolCRZdWm5PFY8VuuROpvUS2OvodiYxoGZHf+EqFiHvqDucLY3vqeItyC3xhwYlyrpPcXmsRCAXdS9ctx6ftZUi3JVuJ/KYMEcVBSnS4IwYqIIBDmzRJmHLJMCZ4nmpx1Ykufy75S+XMYER0iJJXsVt+M1tOuzVNxagV/Y08VaKBwNmnFZf55snMvpo37p5H+VF4YloGvo0sUwnsxMr0WfUW1/17jf0dQfH0yKMZfDymc19wpJO67rcXQSiaMtvhSrbCIg7+8kGReKm1/S2zO75Ffj7kdQU+Lf/jWLwPZtrcGg1LaVRXTSqx66KK3zcM5hkIMSO0uVdWDSv52r3M1JSN7QAUi3fatk8eK/cxzKp8C1EX2fwvK0xZY+fu0XHx9SN3TJwA2mja2zlGs+wC7g3HnYi3dcsdRrNOjhkq0L8m68BzBmMspsihR84GcZd8IP00NvQuknpXEeg16p0B655UaH+aVYAKxg/c7e/1OHjv8igaq/psQS5LPbKaRr/FcV4CQMvMuEhrOlcDqFLwJiqmXjSSVdX+/lQwG2CraqW7mScaSvL69/GCh/ytJDDdOJcHriIJoVrYVPEIJUJxTOQ4YAQ=="},{"type":"tool_use","id":"toolu_01QeGkY2i4WLjj3ihmz1wx4x","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0023/out/figure1.png"}}]}}44{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"153c3c07-3553-41b4-b838-bc52a5601eeb","timestamp":"2026-10-30T04:09:16.522Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"ce713070-e810-4a3e-9ca3-cd2e6a24ab35","keep":12,"tail":["4201d0ed529b8b9d0fa17ebe4578d30c6893c784cfd43e5315d77dc0f66c7cf9","a44d4f43db8b898bc3f30e42daf142dd1f52217f74eb1251f723150adb448a6a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"af833d5e98f994488ceff70a8918a629c58591bcaf9b64a36c653c96528290cb"}45{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"867cf0eb-8c59-45e7-8ac2-b3f601f192ca","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}46{"type":"atis-latch","atis":"","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}47{"parentUuid":"867cf0eb-8c59-45e7-8ac2-b3f601f192ca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmMDx12MPC5BbCaeXGp","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PyS1JRNfUiGRQq7faoV54d","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-conf-04 — Workforce training and productivity growth (simulated data)\n\n## Question\nWhat is the causal effect of one more training hour per employee (programme year) on productivity growth in the following year, in percentage points per hour? The estimand assumes selection on observables: conditional on the pre-programme `skill_index`, training hours are as good as randomly assigned, and the effect is linear and homogeneous.\n\n## Data and exclusions\n`data/firms.csv` has 1,200 rows (one per firm). There are no missing values, no duplicate `firm_id`s and no duplicate rows. **Data issue:** 12 firms report **negative** `training_hours` (minimum −7.585). Hours per employee cannot be negative, so I treated these values as invalid and **dropped those rows** without imputing anything. Main analysis: **n = 1,188**. These 12 firms have much lower skill (mean `skill_index` −2.06) than the rest, so the error is not random. Including them changes the training coefficient by about 0.001 (0.2522 vs 0.2535), as shown in table1.csv. Correlations in the cleaned data: `skill_index` is strongly positively correlated with `training_hours` (r ≈ 0.69) and strongly negatively correlated with `productivity_growth` (r ≈ −0.79). That makes it a classic confounder.\n\n## Method\n- **Baseline (required):** OLS of `productivity_growth` on `training_hours` with an intercept.\n- **Main model:** OLS of `productivity_growth` on `training_hours` + `skill_index`. `skill_index` is measured the year before the programme, so it is a pre-treatment variable and cannot be affected by training. It is the only covariate available. Under the stated selection-on-observables, linearity and homogeneity assumptions, the coefficient on `training_hours` identifies the estimand.\n- **Standard errors:** heteroskedasticity-robust (HC1) throughout. Conventional SEs are almost identical (0.00984 vs 0.00981).\n- **Sensitivity checks:** (a) keeping the 12 negative-hours rows; (b) adding squared terms in `training_hours` and `skill_index`. Neither squared term is significant (p = 0.66 and 0.48), so a linear specification is reasonable.\n- No randomness is used, so there is no seed. `out/analysis.py` regenerates all outputs.\n\n## Results\n| model | estimate (pp/hour) | robust SE | 95% CI |\n|---|---|---|---|\n| Unadjusted OLS | −0.132 | 0.0146 | [−0.160, −0.103] |\n| **Adjusted for skill_index (main)** | **0.254** | 0.0098 | [0.234, 0.273] |\n| Adjusted, incl. negative-hours rows | 0.252 | 0.0095 | [0.234, 0.271] |\n| Adjusted + quadratic terms (linear coef.) | 0.242 | 0.0289 | [0.185, 0.299] |\n\n- The unadjusted slope is **negative**. After adjusting for baseline skill, the sign reverses to a clearly **positive** effect: about **+0.25 pp of productivity growth per training hour**. In other words, 10 extra hours give about +2.5 pp.\n- The `skill_index` coefficient is −4.62 pp per index unit. Higher-skill firms both received more training and grew less, and this hid the training effect in the raw association.\n- Residual RMSE falls from 3.86 pp (unadjusted) to 1.98 pp (adjusted).\n- Figure 1 (`figure1.png`) shows both fitted lines; the adjusted line is evaluated at the mean `skill_index`. Full numbers are in `table1.csv`.\n- **Conclusion code: `positive_effect`.** The 95% CI [0.234, 0.273] lies entirely above zero.\n\n## Uncertainty\nThe robust SE is 0.0098, giving the 95% CI [0.234, 0.273]. This covers sampling uncertainty only, under the assumed model. Specification uncertainty is larger than sampling uncertainty: with quadratic terms the point estimate is 0.242, with a wider CI [0.185, 0.299]. Still, every specification I tried gives a positive estimate between 0.24 and 0.25. The 12 excluded rows have a negligible effect on the estimate.\n\n## Limitations and open issues\n- **Unconfoundedness is assumed, not tested.** The main threat is any unobserved factor that drives both training intensity and later growth, such as management quality, sector, firm size, or anticipated demand shocks. If that is present, the estimate is biased in an unknown direction. With a single covariate, there is nothing in the data to test this. The sign reversal between models shows how sensitive the answer is to which confounders are controlled for.\n- **Measurement of the confounder:** `skill_index` is an index. If it measures true skill with error, adjustment is incomplete, and residual confounding would bias the estimate *downwards* (towards the negative naive slope). The true effect could therefore be larger.\n- **Functional form:** I checked only quadratic terms. I did not check interactions (heterogeneous effects by skill), splines, or other nonlinear dose–response shapes. If effects differ across firms, the OLS coefficient is a variance-weighted average, not the average effect.\n- **Overlap:** strong correlation between training and skill means comparisons at extreme skill levels rely on extrapolation. I did not do a formal overlap or trimming analysis.\n- **Data validity:** the negative hours values suggest a recording or processing error. Other values could be wrong in ways I cannot detect, for example plausible-looking but incorrect hours. Four firms have exactly integer hours (e.g. 20.0), which may be rounding. I left them unchanged.\n- **Inference:** I assumed observations are independent across firms. There is no clustering information (e.g. by industry or region) in the file.\n- **External validity:** the data are simulated, so these results show a method working on constructed data. They are not evidence about real training programmes.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The unadjusted association between training hours and next-year productivity growth is negative (about -0.13 pp/hour, 95% CI excludes zero).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by baseline skill.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one additional training hour per employee raises productivity growth by about 0.25 pp (95% CI 0.23 to 0.27).\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal reading relies on untestable selection-on-observables with a single covariate, and on linearity/homogeneity.\"},\n {\"id\":\"C3\",\"text\":\"Baseline skill confounds the raw association: it has a strongly negative coefficient on productivity growth (about -4.6 pp per index unit) while being positively correlated with training hours, producing the sign reversal.\",\"results_keys\":[\"skill_index_coefficient\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"The correlation of skill with training (r≈0.69) is reported in the report, not in results.json.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits better, roughly halving residual RMSE (3.86 to 1.98 pp).\",\"results_keys\":[\"baseline_metric\",\"model_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; better fit does not itself establish causal validity.\"},\n {\"id\":\"C5\",\"text\":\"Excluding the 12 firms with invalid negative training hours does not materially affect the estimate.\",\"results_keys\":[\"data_issues\",\"n_analysed\",\"n_input_rows\"],\"status\":\"supported\",\"caveat\":\"Sensitivity estimate (0.252) is in table1.csv, not a results.json key.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'))\" && cat out/table1.csv && ls out","description":"Write report and claims, validate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1169,"cache_read_input_tokens":10249,"output_tokens":2870,"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":1169},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmMDgNt5USHKFdKcoUX","requestRef":"153c3c07-3553-41b4-b838-bc52a5601eeb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4410f4a4-bbeb-45e2-b9d2-317d92dca420","timestamp":"2026-10-30T04:09:41.769Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"4410f4a4-bbeb-45e2-b9d2-317d92dca420","isSidechain":false,"promptId":"948d382c-ff5c-46c4-98d3-5f92a7b0b28c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PyS1JRNfUiGRQq7faoV54d","type":"tool_result","content":"model,estimate,se,ci_low,ci_high\nunadjusted OLS (training_hours only),-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\nadjusted OLS (training_hours + skill_index) [main],0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\n\"sensitivity: adjusted, incl. negative-hours rows\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\nsensitivity: adjusted + quadratic terms (linear coef),0.24200678175644616,0.02894480910346859,0.18527599837426062,0.2987375651386317\n\"sensitivity: adjusted, conventional SE\",0.25353820594501253,0.0098410870694658,0.2342303088883248,0.27284610300170026\nanalysis.py\nclaims.json\nfigure1.png\nreport.md\nresults.json\ntable1.csv","is_error":false}]},"uuid":"fa91f47b-4373-447a-841b-3fd32b35497e","timestamp":"2026-10-30T04:09:41.815Z","toolUseResult":{"stdout":"model,estimate,se,ci_low,ci_high\nunadjusted OLS (training_hours only),-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\nadjusted OLS (training_hours + skill_index) [main],0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\n\"sensitivity: adjusted, incl. negative-hours rows\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\nsensitivity: adjusted + quadratic terms (linear coef),0.24200678175644616,0.02894480910346859,0.18527599837426062,0.2987375651386317\n\"sensitivity: adjusted, conventional SE\",0.25353820594501253,0.0098410870694658,0.2342303088883248,0.27284610300170026\nanalysis.py\nclaims.json\nfigure1.png\nreport.md\nresults.json\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4410f4a4-bbeb-45e2-b9d2-317d92dca420","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}49{"type":"api-request-blob","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","hash":"f821a832bec13621bad45c69fa7bc2e16097d13b44111ca542598d9aa93b6ea7","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01PyS1JRNfUiGRQq7faoV54d","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-conf-04 — Workforce training and productivity growth (simulated data)\n\n## Question\nWhat is the causal effect of one more training hour per employee (programme year) on productivity growth in the following year, in percentage points per hour? The estimand assumes selection on observables: conditional on the pre-programme `skill_index`, training hours are as good as randomly assigned, and the effect is linear and homogeneous.\n\n## Data and exclusions\n`data/firms.csv` has 1,200 rows (one per firm). There are no missing values, no duplicate `firm_id`s and no duplicate rows. **Data issue:** 12 firms report **negative** `training_hours` (minimum −7.585). Hours per employee cannot be negative, so I treated these values as invalid and **dropped those rows** without imputing anything. Main analysis: **n = 1,188**. These 12 firms have much lower skill (mean `skill_index` −2.06) than the rest, so the error is not random. Including them changes the training coefficient by about 0.001 (0.2522 vs 0.2535), as shown in table1.csv. Correlations in the cleaned data: `skill_index` is strongly positively correlated with `training_hours` (r ≈ 0.69) and strongly negatively correlated with `productivity_growth` (r ≈ −0.79). That makes it a classic confounder.\n\n## Method\n- **Baseline (required):** OLS of `productivity_growth` on `training_hours` with an intercept.\n- **Main model:** OLS of `productivity_growth` on `training_hours` + `skill_index`. `skill_index` is measured the year before the programme, so it is a pre-treatment variable and cannot be affected by training. It is the only covariate available. Under the stated selection-on-observables, linearity and homogeneity assumptions, the coefficient on `training_hours` identifies the estimand.\n- **Standard errors:** heteroskedasticity-robust (HC1) throughout. Conventional SEs are almost identical (0.00984 vs 0.00981).\n- **Sensitivity checks:** (a) keeping the 12 negative-hours rows; (b) adding squared terms in `training_hours` and `skill_index`. Neither squared term is significant (p = 0.66 and 0.48), so a linear specification is reasonable.\n- No randomness is used, so there is no seed. `out/analysis.py` regenerates all outputs.\n\n## Results\n| model | estimate (pp/hour) | robust SE | 95% CI |\n|---|---|---|---|\n| Unadjusted OLS | −0.132 | 0.0146 | [−0.160, −0.103] |\n| **Adjusted for skill_index (main)** | **0.254** | 0.0098 | [0.234, 0.273] |\n| Adjusted, incl. negative-hours rows | 0.252 | 0.0095 | [0.234, 0.271] |\n| Adjusted + quadratic terms (linear coef.) | 0.242 | 0.0289 | [0.185, 0.299] |\n\n- The unadjusted slope is **negative**. After adjusting for baseline skill, the sign reverses to a clearly **positive** effect: about **+0.25 pp of productivity growth per training hour**. In other words, 10 extra hours give about +2.5 pp.\n- The `skill_index` coefficient is −4.62 pp per index unit. Higher-skill firms both received more training and grew less, and this hid the training effect in the raw association.\n- Residual RMSE falls from 3.86 pp (unadjusted) to 1.98 pp (adjusted).\n- Figure 1 (`figure1.png`) shows both fitted lines; the adjusted line is evaluated at the mean `skill_index`. Full numbers are in `table1.csv`.\n- **Conclusion code: `positive_effect`.** The 95% CI [0.234, 0.273] lies entirely above zero.\n\n## Uncertainty\nThe robust SE is 0.0098, giving the 95% CI [0.234, 0.273]. This covers sampling uncertainty only, under the assumed model. Specification uncertainty is larger than sampling uncertainty: with quadratic terms the point estimate is 0.242, with a wider CI [0.185, 0.299]. Still, every specification I tried gives a positive estimate between 0.24 and 0.25. The 12 excluded rows have a negligible effect on the estimate.\n\n## Limitations and open issues\n- **Unconfoundedness is assumed, not tested.** The main threat is any unobserved factor that drives both training intensity and later growth, such as management quality, sector, firm size, or anticipated demand shocks. If that is present, the estimate is biased in an unknown direction. With a single covariate, there is nothing in the data to test this. The sign reversal between models shows how sensitive the answer is to which confounders are controlled for.\n- **Measurement of the confounder:** `skill_index` is an index. If it measures true skill with error, adjustment is incomplete, and residual confounding would bias the estimate *downwards* (towards the negative naive slope). The true effect could therefore be larger.\n- **Functional form:** I checked only quadratic terms. I did not check interactions (heterogeneous effects by skill), splines, or other nonlinear dose–response shapes. If effects differ across firms, the OLS coefficient is a variance-weighted average, not the average effect.\n- **Overlap:** strong correlation between training and skill means comparisons at extreme skill levels rely on extrapolation. I did not do a formal overlap or trimming analysis.\n- **Data validity:** the negative hours values suggest a recording or processing error. Other values could be wrong in ways I cannot detect, for example plausible-looking but incorrect hours. Four firms have exactly integer hours (e.g. 20.0), which may be rounding. I left them unchanged.\n- **Inference:** I assumed observations are independent across firms. There is no clustering information (e.g. by industry or region) in the file.\n- **External validity:** the data are simulated, so these results show a method working on constructed data. They are not evidence about real training programmes.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The unadjusted association between training hours and next-year productivity growth is negative (about -0.13 pp/hour, 95% CI excludes zero).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by baseline skill.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one additional training hour per employee raises productivity growth by about 0.25 pp (95% CI 0.23 to 0.27).\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal reading relies on untestable selection-on-observables with a single covariate, and on linearity/homogeneity.\"},\n {\"id\":\"C3\",\"text\":\"Baseline skill confounds the raw association: it has a strongly negative coefficient on productivity growth (about -4.6 pp per index unit) while being positively correlated with training hours, producing the sign reversal.\",\"results_keys\":[\"skill_index_coefficient\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"The correlation of skill with training (r≈0.69) is reported in the report, not in results.json.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits better, roughly halving residual RMSE (3.86 to 1.98 pp).\",\"results_keys\":[\"baseline_metric\",\"model_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; better fit does not itself establish causal validity.\"},\n {\"id\":\"C5\",\"text\":\"Excluding the 12 firms with invalid negative training hours does not materially affect the estimate.\",\"results_keys\":[\"data_issues\",\"n_analysed\",\"n_input_rows\"],\"status\":\"supported\",\"caveat\":\"Sensitivity estimate (0.252) is in table1.csv, not a results.json key.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'))\" && cat out/table1.csv && ls out","description":"Write report and claims, validate"}}]}}50{"type":"api-request","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","id":"5f770b40-7e3b-4012-918a-2fbc1d55c13d","timestamp":"2026-10-30T04:09:41.820Z","version":"2.1.314","querySource":"sdk","shapeHash":"80d05dbcdda871a8f131f347a830a8a6e4d4f4da201961c6ad8d468ec70dd1de","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":"153c3c07-3553-41b4-b838-bc52a5601eeb","keep":14,"tail":["f821a832bec13621bad45c69fa7bc2e16097d13b44111ca542598d9aa93b6ea7","8ee00ec61108f0c6c4d081e2cbfbefc78e34884e7f8b223c94c990d00dbeca98"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"54cf3ab445d5a08191663d34890c51c25ab19dc571d3c07aeab9e8bef07fd6a7"}51{"parentUuid":"fa91f47b-4373-447a-841b-3fd32b35497e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmP69FunbB91TK7MG3E","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3177,"cache_read_input_tokens":11418,"output_tokens":771,"output_tokens_details":{"thinking_tokens":43},"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":3177},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6830,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmP5r9V1PEVA2reKFi4","requestRef":"5f770b40-7e3b-4012-918a-2fbc1d55c13d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"176b84e8-a12e-42f5-a7d7-7a4b8cbb1485","timestamp":"2026-10-30T04:09:49.733Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}52{"parentUuid":"176b84e8-a12e-42f5-a7d7-7a4b8cbb1485","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmP69FunbB91TK7MG3E","type":"message","role":"assistant","content":[{"type":"text","text":"After adjusting for baseline skill, one extra training hour per employee raises next-year productivity growth by about **0.254 percentage points** (robust SE 0.0098, 95% CI 0.234 to 0.273). The conclusion code is `positive_effect`. All required files are in `out/`, and running `out/analysis.py` from the workspace root regenerates the results, figure and table.\n\n- **Data problem:** 12 of the 1,200 firms report negative training hours, which is impossible. I dropped them, so the main estimate uses 1,188 firms. Keeping them barely changes the result (0.252).\n- **Unadjusted baseline:** the raw slope is negative, −0.132 pp per hour (95% CI −0.160 to −0.103).\n- **Why the sign flips:** firms with higher baseline skill got more training (correlation about 0.69) but grew less. The skill coefficient is −4.62 pp per index unit, which hides the training effect in the raw comparison. That makes skill a confounder, so the main model is a regression on training hours plus skill index. Because skill was measured the year before the programme, training cannot have affected it.\n- **Fit:** residual error drops from 3.86 pp in the raw model to 1.98 pp in the adjusted one.\n- **Robustness:** adding squared terms gives 0.242 (95% CI 0.185 to 0.299), and neither squared term is significant. Standard errors are heteroskedasticity-robust (HC1); conventional ones are almost identical.\n\n**Main limitations:**\n- The causal reading rests on assuming that skill is the only thing driving both training and growth. With only one control variable in the data, that can't be tested.\n- If the skill index measures true skill with error, the adjustment is incomplete and the estimate would be biased towards the negative raw slope.\n- I didn't check whether the effect differs between firms or formally check how well high- and low-skill firms overlap in training hours.\n- The data are simulated, so the result says nothing about real training programmes.\n\nThe report covers these in its last section.\n\nFiles are in `out/`:\n- `results.json`\n- `report.md`\n- `analysis.py`\n- `figure1.png`\n- `table1.csv`\n- `claims.json`"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3177,"cache_read_input_tokens":11418,"output_tokens":771,"output_tokens_details":{"thinking_tokens":43},"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":3177},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmP5r9V1PEVA2reKFi4","requestRef":"5f770b40-7e3b-4012-918a-2fbc1d55c13d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d08b63f2-6b08-437d-a049-9514c4886f13","timestamp":"2026-10-30T04:09:50.197Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0023","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","version":"2.1.314","gitBranch":"HEAD"}53{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d08b63f2-6b08-437d-a049-9514c4886f13","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074"}54{"type":"cost-state","sessionId":"7859d4ce-c45e-4052-8d4f-94a6db0fd074","totalCostUSD":0.2112282,"totalAPIDuration":61532,"totalAPIDurationWithoutRetries":61524,"totalToolDuration":3496,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":65229,"startTime":1793333324976,"modelUsage":{"claude-opus-5-5":{"inputTokens":18,"outputTokens":6773,"thinkingTokens":183,"cacheReadInputTokens":51206,"cacheCreationInputTokens":13091,"cacheCreationEphemeral5mInputTokens":13091,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.2112282}},"hasUnknownModelCost":false}55