1{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:07:00.139Z","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:07:00.143Z","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}4{"parentUuid":null,"isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":"Begin"},"uuid":"10b43a76-5f5a-4d74-9fb9-fc039b4d473b","timestamp":"2026-10-30T04:07:00.146Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","timestamp":"2026-10-30T04:07:00.155Z","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/RC0020\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/<timestamp>.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"7207f1b5-acc0-428c-922e-2697ca35982d","timestamp":"2026-10-30T04:07:00.155Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"6a7e1aa1f34f1d7909313c99712041c8f454755d4fa8c88fe4f1d6dc82cffc48"}8{"parentUuid":"10b43a76-5f5a-4d74-9fb9-fc039b4d473b","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"44eab806-11cd-4c88-9ae6-7694389a6778","timestamp":"2026-10-30T04:07:00.149Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"44eab806-11cd-4c88-9ae6-7694389a6778","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"14b31076-109f-42a0-8a92-9f0923535dfe","timestamp":"2026-10-30T04:07:00.149Z","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/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"14b31076-109f-42a0-8a92-9f0923535dfe","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":"0063cfb6-2e9d-4d56-8f80-12bde71e6917","timestamp":"2026-10-30T04:07:00.150Z","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/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}12{"parentUuid":"0063cfb6-2e9d-4d56-8f80-12bde71e6917","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBDdsN1qVDcarKQ3LG","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSgwUKEAgTGAI4AUIIdGhpbmtpbmcSDCJVmz1B1e/lsX18OxoMDq3P+qo87yUK+Q8AIjC1Scy9FjXD7M5pQcNFya6kVuB3vyKIdCspliMsdpFQL29g2cGOow+rh3kBA/cPsfUqoAR1jfMhApl0Rbni50NSzYomNRvO6gWQRtZjIhOeAq+EaMZLKojeKYRBzgEsDEFA4Np7Js0P73oHGa7v1Hym6WepS9xSOUjDBd1HQRH8d8er8QKnXDkjHnR988C2pda3fky2ACmHKLu3kNFWw5ApeXL+I/2Bvx4Qr5rDo+XJYPfRVI1OyiKH1V44KbzuYMrM82kHIyIJDzpi0SXUA9BCsZEyilj5XNl2aMfsafCzKs1gBW2ssVs3bknidc5A6IpCEH8heu51HJnJJxExzoJn0d/B2D7FmndY/TOzRhJCR/ESpo5AR6T7/bBs+i2SPSIS9Jq22mpQjUlKaMogmLjhO0Ge0VY8HSirUEiNYa1cldvgHnj7JxBZM+DCZFTYFCsu8ZG4lcVOPFMA2QBZZjjwVm6wBk4nX00R/FwAuI3aDMdqpyLFbZOuRmSxVR/dx2vqJxN3C3rfZgOPCyAkcXPsK2/Q5b0k0pooYpIzd0AkrA8Tgxdyc9BmoEkzlL2xmE1zFjPKZXkdH8XW8LrZzZovzen+6UxdtKQY8xLCoWUusJ1DX7cpKuLfUUuLenkIq2pbzg6HjRaB2+ss4WRtR9lECkz3O4OuSTj5hnuV1/Z+N87hsosAuy3zR3RUTMlUpSrHn2zn5R7bbhYjfAtWkc8jPBfQS8kYANTvIaJYZAi+n1OnV4UPDWF+3lZCao0/AOJ9UHThOUcZvdr9U3QaiOSAFCfQGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":117,"output_tokens_details":{"thinking_tokens":15},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":363,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmBDRipcFrRyy4SKASw","requestRef":"7207f1b5-acc0-428c-922e-2697ca35982d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0a6f7f5e-c537-4f44-ad01-9528c58e22c8","timestamp":"2026-10-30T04:07:02.672Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"0a6f7f5e-c537-4f44-ad01-9528c58e22c8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBDdsN1qVDcarKQ3LG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017tFsggyn5EfSr27eFasB2w","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":117,"output_tokens_details":{"thinking_tokens":15},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmBDRipcFrRyy4SKASw","requestRef":"7207f1b5-acc0-428c-922e-2697ca35982d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"755443cc-ede1-45af-8bff-9551cc0bb010","timestamp":"2026-10-30T04:07:03.265Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"755443cc-ede1-45af-8bff-9551cc0bb010","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 .\ndrwxr-xr-x 26 simon-pierreboucher staff 832 oct. 30 00:06 ..\n-rw-r--r-- 1 simon-pierreboucher staff 419 oct. 29 23:43 bundle.json\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 data\n-rw-r--r-- 1 simon-pierreboucher staff 2302 oct. 29 23:43 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 5597 oct. 29 23:43 TASK.md\ndata:\ntotal 64\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 ..\n-rw-r--r-- 1 simon-pierreboucher staff 31657 oct. 29 23:43 firms.csv","is_error":true,"tool_use_id":"toolu_017tFsggyn5EfSr27eFasB2w"}]},"uuid":"29ce60af-d236-4b5e-925d-680d214593c6","timestamp":"2026-10-30T04:07:03.354Z","toolUseResult":"Error: Exit code 1\n# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 .\ndrwxr-xr-x 26 simon-pierreboucher staff 832 oct. 30 00:06 ..\n-rw-r--r-- 1 simon-pierreboucher staff 419 oct. 29 23:43 bundle.json\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 data\n-rw-r--r-- 1 simon-pierreboucher staff 2302 oct. 29 23:43 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 5597 oct. 29 23:43 TASK.md\ndata:\ntotal 64\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 ..\n-rw-r--r-- 1 simon-pierreboucher staff 31657 oct. 29 23:43 firms.csv","sandboxed":false,"sourceToolAssistantUUID":"755443cc-ede1-45af-8bff-9551cc0bb010","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"3b4486d25e2e505248a6751178cc02c96b8da8cbcfa2174f0c83bd33ef42af88","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_017tFsggyn5EfSr27eFasB2w","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"ad1a0052-6f26-4f62-8b91-b02e37a37120","timestamp":"2026-10-30T04:07:03.357Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"7207f1b5-acc0-428c-922e-2697ca35982d","keep":2,"tail":["3b4486d25e2e505248a6751178cc02c96b8da8cbcfa2174f0c83bd33ef42af88","dae4ce5808693aaa788e080db0bc363c970834aae2505ddbee3fdcc44e7e9b7f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2e4c208a560ffa51c185e27b720f9509128fdd35706d4ab2e52b9ec992ad0cc8"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"29ce60af-d236-4b5e-925d-680d214593c6","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}18{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}19{"parentUuid":"29ce60af-d236-4b5e-925d-680d214593c6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBPJoL1GUKu86Cux5Q","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01H9qWiMugRcSpdGB1KgJFPh","name":"Bash","input":{"command":"cat gate_spec.json bundle.json; head data/firms.csv; shasum -a 256 data/firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('data/firms.csv'); print(d.shape); print(d.describe().T); print(d.isna().sum()); print(d.duplicated().sum(), d.firm_id.duplicated().sum()); print(d.dtypes); print(d.corr())\"","description":"Inspect gate spec and data"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2462,"cache_read_input_tokens":4107,"output_tokens":234,"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":2462},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmBP2g53HzkT1HFaVQ4","requestRef":"ad1a0052-6f26-4f62-8b91-b02e37a37120","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7b73e473-1432-48d0-a573-bafd5ddb2436","timestamp":"2026-10-30T04:07:05.679Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"7b73e473-1432-48d0-a573-bafd5ddb2436","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01H9qWiMugRcSpdGB1KgJFPh","type":"tool_result","content":"{\n \"task_id\": \"F6-conf-04\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"naive_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"skill_index_coefficient\": {\n \"type\": \"number\",\n \"nullable\": true\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\"\n ],\n \"ci_pairs\": [\n [\n \"naive_estimate\",\n \"naive_ci_low\",\n \"naive_ci_high\"\n ],\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}{\n \"task_id\": \"F6-conf-04\",\n \"family\": \"F6\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:43:29.620094+00:00\",\n \"files\": {\n \"TASK.md\": \"f91b6d78e16573314371e5761a0e79c69721af82a9454655f56a864b34006c6e\",\n \"data/firms.csv\": \"34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df\",\n \"gate_spec.json\": \"7233dd8b32d0b3680b8275042673b5278441b86744044bd806094c4af34bd87f\"\n }\n}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\n1095,1.542,24.977,2.3425\n1679,-0.284,18.953,8.3937\n1824,-1.5044,15.155,16.7517\n1243,1.4834,38.116,5.0527\n1989,0.1293,22.56,7.153\n34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df data/firms.csv\n(1200, 4)\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\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","is_error":false}]},"uuid":"841f28b0-72fc-4e74-b577-c4365f0156e5","timestamp":"2026-10-30T04:07:05.923Z","toolUseResult":{"stdout":"{\n \"task_id\": \"F6-conf-04\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"naive_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"skill_index_coefficient\": {\n \"type\": \"number\",\n \"nullable\": true\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\"\n ],\n \"ci_pairs\": [\n [\n \"naive_estimate\",\n \"naive_ci_low\",\n \"naive_ci_high\"\n ],\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}{\n \"task_id\": \"F6-conf-04\",\n \"family\": \"F6\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:43:29.620094+00:00\",\n \"files\": {\n \"TASK.md\": \"f91b6d78e16573314371e5761a0e79c69721af82a9454655f56a864b34006c6e\",\n \"data/firms.csv\": \"34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df\",\n \"gate_spec.json\": \"7233dd8b32d0b3680b8275042673b5278441b86744044bd806094c4af34bd87f\"\n }\n}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\n1095,1.542,24.977,2.3425\n1679,-0.284,18.953,8.3937\n1824,-1.5044,15.155,16.7517\n1243,1.4834,38.116,5.0527\n1989,0.1293,22.56,7.153\n34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df data/firms.csv\n(1200, 4)\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\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","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7b73e473-1432-48d0-a573-bafd5ddb2436","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"e1577d5ee2e8988bf8e7f240ae3ec956bafddabe2bb1c204144cfc7475d03a43","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01H9qWiMugRcSpdGB1KgJFPh","name":"Bash","input":{"command":"cat gate_spec.json bundle.json; head data/firms.csv; shasum -a 256 data/firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('data/firms.csv'); print(d.shape); print(d.describe().T); print(d.isna().sum()); print(d.duplicated().sum(), d.firm_id.duplicated().sum()); print(d.dtypes); print(d.corr())\"","description":"Inspect gate spec and data"}}]}}22{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"2b50a6f3-f028-457e-96a6-c483c285d5a3","timestamp":"2026-10-30T04:07:05.925Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"ad1a0052-6f26-4f62-8b91-b02e37a37120","keep":4,"tail":["e1577d5ee2e8988bf8e7f240ae3ec956bafddabe2bb1c204144cfc7475d03a43","8a759c55f259849d0c2f9871ab49056f34449f1e383ad077082194cc88da8f8e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"659b2f8c6ae5e74309599c5b5a2397603db55bd4e222359beab37f0f3c877bdc"}23{"parentUuid":"841f28b0-72fc-4e74-b577-c4365f0156e5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBaGbf6vgP7ScDLY8A","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":2031,"cache_read_input_tokens":6569,"output_tokens":420,"output_tokens_details":{"thinking_tokens":44},"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":2031},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":405,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmBZxzxTju3Y5szgqg2","requestRef":"2b50a6f3-f028-457e-96a6-c483c285d5a3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"afbefaec-81f6-43c3-9675-d2a4eebbd711","timestamp":"2026-10-30T04:07:07.385Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"afbefaec-81f6-43c3-9675-d2a4eebbd711","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBaGbf6vgP7ScDLY8A","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01D9FREqp5oHoM67Gd2owkD4","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd, numpy as np, statsmodels.formula.api as smf\npd.set_option('display.width',200)\nd=pd.read_csv('data/firms.csv'); print(d.describe().T)\nprint((d.training_hours<0).sum(), (d.training_hours==0).sum(), d.training_hours.round(3).value_counts().head())\nfor f in ['productivity_growth~training_hours','productivity_growth~training_hours+skill_index','productivity_growth~training_hours+skill_index+I(skill_index**2)','productivity_growth~training_hours*skill_index']:\n m=smf.ols(f,d).fit(cov_type='HC1'); print(f); print(m.params.round(4).to_dict(), m.bse.round(4).to_dict())\nprint(d.firm_id.min(), d.firm_id.max())\n\"","description":"Explore data and candidate models"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2031,"cache_read_input_tokens":6569,"output_tokens":420,"output_tokens_details":{"thinking_tokens":44},"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":2031},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmBZxzxTju3Y5szgqg2","requestRef":"2b50a6f3-f028-457e-96a6-c483c285d5a3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1ee2f566-4b45-4fb6-95f0-8bb164014fdc","timestamp":"2026-10-30T04:07:09.668Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"1ee2f566-4b45-4fb6-95f0-8bb164014fdc","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01D9FREqp5oHoM67Gd2owkD4","type":"tool_result","content":" count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\n12 0 training_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\nName: count, dtype: int64\nproductivity_growth~training_hours\n{'Intercept': 9.7795, 'training_hours': -0.1352} {'Intercept': 0.3028, 'training_hours': 0.0139}\nproductivity_growth~training_hours+skill_index\n{'Intercept': 2.0454, 'training_hours': 0.2522, 'skill_index': -4.6304} {'Intercept': 0.2006, 'training_hours': 0.0095, 'skill_index': 0.0781}\nproductivity_growth~training_hours+skill_index+I(skill_index**2)\n{'Intercept': 2.0535, 'training_hours': 0.2523, 'skill_index': -4.6315, 'I(skill_index ** 2)': -0.0088} {'Intercept': 0.2032, 'training_hours': 0.0095, 'skill_index': 0.0783, 'I(skill_index ** 2)': 0.0371}\nproductivity_growth~training_hours*skill_index\n{'Intercept': 2.036, 'training_hours': 0.2521, 'skill_index': -4.6674, 'training_hours:skill_index': 0.0019} {'Intercept': 0.2024, 'training_hours': 0.0095, 'skill_index': 0.1317, 'training_hours:skill_index': 0.0054}\n1001 2200","is_error":false}]},"uuid":"91f5aa49-a7e0-4bd0-8e38-9e9e5e5dda7f","timestamp":"2026-10-30T04:07:10.176Z","toolUseResult":{"stdout":" count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\n12 0 training_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\nName: count, dtype: int64\nproductivity_growth~training_hours\n{'Intercept': 9.7795, 'training_hours': -0.1352} {'Intercept': 0.3028, 'training_hours': 0.0139}\nproductivity_growth~training_hours+skill_index\n{'Intercept': 2.0454, 'training_hours': 0.2522, 'skill_index': -4.6304} {'Intercept': 0.2006, 'training_hours': 0.0095, 'skill_index': 0.0781}\nproductivity_growth~training_hours+skill_index+I(skill_index**2)\n{'Intercept': 2.0535, 'training_hours': 0.2523, 'skill_index': -4.6315, 'I(skill_index ** 2)': -0.0088} {'Intercept': 0.2032, 'training_hours': 0.0095, 'skill_index': 0.0783, 'I(skill_index ** 2)': 0.0371}\nproductivity_growth~training_hours*skill_index\n{'Intercept': 2.036, 'training_hours': 0.2521, 'skill_index': -4.6674, 'training_hours:skill_index': 0.0019} {'Intercept': 0.2024, 'training_hours': 0.0095, 'skill_index': 0.1317, 'training_hours:skill_index': 0.0054}\n1001 2200","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1ee2f566-4b45-4fb6-95f0-8bb164014fdc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"9b228fe6a74ecfef17005313dc18d6cd4d74122424a9a79f3e7b5c0a10dba94d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSwAYKEAgTGAI4AUIIdGhpbmtpbmcSDEFhTBfbpSOr06bwmhoMxR6ok4TuQVf8cR/KIjDl7Sm0/efznc4N9IH+tbZV/fSzI2qmpDkFogqsjMZvCYfUH6hn/Rq+KDsEx5j2DiEq3QVrnP6buusfF6JMHxnKGtvFFC9cBGt49v8J9zQgVC6kTVCUXxnmHtACQRj9LpfXaa8+ewUOzCQhSctn0pIdHMn7rW+5ffGoN7EM35SWwDHixdxZ3kGu3Kp6FZ8BDrgvXUo5gRlSoQdH4HQ3LsdRt+ULt/tKlRpTphiYKyvLn8Bouic8f8siwX3qW3CvCO9dyd8EOAVgcMharfUDVPz8QyE1ZKEb2SUQWseIPjAkSUUd2xVTt7QLyHMd/ZQ1V2RnVJkItcmD7soNnzW/tsrl30ge4/JR+jRa1cr0Hrs0p+Tpy4MywHjDENZO3mUsD4H8m09iVnDpi50ixKzfwEu0G2WY+t4vF5Xqpezg3yls5bAGz0ol+Xzuvedisk4hJ0rHOacFABtkXDh3CUNrDy7cmN1oubfe8sd8z+8WxCHrbnlzAMG1BRtGfgHSzIvjKlzsxVQWZh7eNJSbyJIZRjrzrosd4xUVwCIC2VccjxeCAOG8y3V4CZuS80rLDU2wYa5e32IP9vavyzsyG7HwKmIcNO0Pi6U9chatWPjLP8e5/CDzAM4iIV8y3QSKk5yFl7PQfY1ni4nExrv5JFWcT+iK8ybyKoQJdMr+uJANCoWlo7g+7ULdFRz4Egm454lAY4bflJMl9wzQ9eM1XI3eJGDGRdnZ9r261qbjKJ2YvLLbe9JGEHKsjE3WfEKnASkmzjnmnEeUXpIdqrbpkYlsOeN6iBgQ46YojD4sqefITyhhSxPxIXmti9IetDPlcyb8IEn79LEsG24nn2+PXYcPPsYdoPBIa/vZHBv0JNp1vJeA0mfwlgb5OGHlDfs4vAOWmcCnEHfjBkVb0JYijAK/csHLg0aVkg/VwkYQucYSDEUAGWIjOBBs/PRPpPZXgFyJait2qlwjN4y/ua+K9yJCdiM/CS4fy3M7tuqWAt+TCeviJ1m9Ax0YXPZnN4gdFGWATxEvG+knQN9KWywzWfDC+00QGAE="},{"type":"tool_use","id":"toolu_01D9FREqp5oHoM67Gd2owkD4","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd, numpy as np, statsmodels.formula.api as smf\npd.set_option('display.width',200)\nd=pd.read_csv('data/firms.csv'); print(d.describe().T)\nprint((d.training_hours<0).sum(), (d.training_hours==0).sum(), d.training_hours.round(3).value_counts().head())\nfor f in ['productivity_growth~training_hours','productivity_growth~training_hours+skill_index','productivity_growth~training_hours+skill_index+I(skill_index**2)','productivity_growth~training_hours*skill_index']:\n m=smf.ols(f,d).fit(cov_type='HC1'); print(f); print(m.params.round(4).to_dict(), m.bse.round(4).to_dict())\nprint(d.firm_id.min(), d.firm_id.max())\n\"","description":"Explore data and candidate models"}}]}}27{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"66c237e1-0909-4949-8fbd-f05083abee52","timestamp":"2026-10-30T04:07:10.178Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"2b50a6f3-f028-457e-96a6-c483c285d5a3","keep":6,"tail":["9b228fe6a74ecfef17005313dc18d6cd4d74122424a9a79f3e7b5c0a10dba94d","f4d3868d5df31c029f9e2d491f92ca7aedd2d33dd929f6e49ed3e655c7c7c833"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4cde25800d8edd2d0c18773dd9a7e618b3c0577928a75f87b680d50a600eed89"}28{"parentUuid":"91f5aa49-a7e0-4bd0-8e38-9e9e5e5dda7f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBtSjnWVFBtGzpNxN4","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":1061,"cache_read_input_tokens":8600,"output_tokens":263,"output_tokens_details":{"thinking_tokens":67},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1061},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":386,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmBt9e2f4yKPzK5GqBC","requestRef":"66c237e1-0909-4949-8fbd-f05083abee52","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3a94df52-fda6-4a87-b7cd-85e60cf4c0c9","timestamp":"2026-10-30T04:07:11.749Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"3a94df52-fda6-4a87-b7cd-85e60cf4c0c9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBtSjnWVFBtGzpNxN4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CuLtnsPv47f3JELLBvcVaa","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nd=pd.read_csv('data/firms.csv'); print(d[d.training_hours<0]); print(d.training_hours.describe()); print(d.productivity_growth.describe()); print(d.skill_index.describe())\nprint(d.sort_values('training_hours').head(20))\"","description":"Inspect negative training hours rows"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1061,"cache_read_input_tokens":8600,"output_tokens":263,"output_tokens_details":{"thinking_tokens":67},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1061},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmBt9e2f4yKPzK5GqBC","requestRef":"66c237e1-0909-4949-8fbd-f05083abee52","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d03f9aa7-7d7d-4034-8ed0-fcf5adee3991","timestamp":"2026-10-30T04:07:12.814Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"d03f9aa7-7d7d-4034-8ed0-fcf5adee3991","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CuLtnsPv47f3JELLBvcVaa","type":"tool_result","content":" firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\ncount 1200.000000\nmean 19.945735\nstd 8.243620\nmin -7.585000\n25% 14.580750\n50% 19.676500\n75% 25.502000\nmax 51.770000\nName: training_hours, dtype: float64\ncount 1200.000000\nmean 7.083012\nstd 4.020107\nmin -4.038000\n25% 4.444350\n50% 7.061400\n75% 9.987000\nmax 19.388900\nName: productivity_growth, dtype: float64\ncount 1200.000000\nmean -0.001467\nstd 0.994503\nmin -3.827900\n25% -0.642375\n50% 0.010250\n75% 0.680000\nmax 2.962300\nName: skill_index, dtype: float64\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\n688 1248 -1.2167 -3.000 5.3598\n893 2037 -2.9950 -2.887 13.2197\n1150 1886 -2.4104 -2.726 15.8426\n772 1280 -0.9997 -2.351 6.7451\n1082 1353 -1.8188 -1.514 10.0230\n521 1755 -1.2527 -1.335 7.7379\n127 1276 -2.4212 -0.133 19.1087\n132 1090 -2.5921 0.023 12.2581\n530 1277 -0.6852 0.232 6.4566\n737 1291 -1.0179 0.858 5.6672\n322 1237 -1.5583 1.006 10.7198\n113 1485 -2.2600 1.228 14.1763\n549 2132 -1.8401 1.840 10.3878\n707 1134 -3.3725 1.906 17.7180\n1069 1062 -1.6662 2.015 6.4579","is_error":false}]},"uuid":"71c29da4-1b88-4375-8a84-f3dd500d9ee1","timestamp":"2026-10-30T04:07:13.039Z","toolUseResult":{"stdout":" firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\ncount 1200.000000\nmean 19.945735\nstd 8.243620\nmin -7.585000\n25% 14.580750\n50% 19.676500\n75% 25.502000\nmax 51.770000\nName: training_hours, dtype: float64\ncount 1200.000000\nmean 7.083012\nstd 4.020107\nmin -4.038000\n25% 4.444350\n50% 7.061400\n75% 9.987000\nmax 19.388900\nName: productivity_growth, dtype: float64\ncount 1200.000000\nmean -0.001467\nstd 0.994503\nmin -3.827900\n25% -0.642375\n50% 0.010250\n75% 0.680000\nmax 2.962300\nName: skill_index, dtype: float64\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\n688 1248 -1.2167 -3.000 5.3598\n893 2037 -2.9950 -2.887 13.2197\n1150 1886 -2.4104 -2.726 15.8426\n772 1280 -0.9997 -2.351 6.7451\n1082 1353 -1.8188 -1.514 10.0230\n521 1755 -1.2527 -1.335 7.7379\n127 1276 -2.4212 -0.133 19.1087\n132 1090 -2.5921 0.023 12.2581\n530 1277 -0.6852 0.232 6.4566\n737 1291 -1.0179 0.858 5.6672\n322 1237 -1.5583 1.006 10.7198\n113 1485 -2.2600 1.228 14.1763\n549 2132 -1.8401 1.840 10.3878\n707 1134 -3.3725 1.906 17.7180\n1069 1062 -1.6662 2.015 6.4579","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d03f9aa7-7d7d-4034-8ed0-fcf5adee3991","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"c1267fed2858f0282ee1dfec7e372990985499cfca13bf75cc36391006d042e5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01CuLtnsPv47f3JELLBvcVaa","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nd=pd.read_csv('data/firms.csv'); print(d[d.training_hours<0]); print(d.training_hours.describe()); print(d.productivity_growth.describe()); print(d.skill_index.describe())\nprint(d.sort_values('training_hours').head(20))\"","description":"Inspect negative training hours rows"}}]}}32{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"1e2afc45-5f59-4f88-9b30-6717629a6544","timestamp":"2026-10-30T04:07:13.041Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"66c237e1-0909-4949-8fbd-f05083abee52","keep":8,"tail":["c1267fed2858f0282ee1dfec7e372990985499cfca13bf75cc36391006d042e5","473ee05cf16a87b65ef9451d5e0bee97ab52972d50f3df4e4b86e7163ccf7d7b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"44cbf209f5a5e34b1834ba6c8c888729a5904f5e2aaac5b8d5b6a14552b09100"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"71c29da4-1b88-4375-8a84-f3dd500d9ee1","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}34{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}35{"parentUuid":"71c29da4-1b88-4375-8a84-f3dd500d9ee1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmC6fTH585VyU7EHgn1","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":1221,"cache_read_input_tokens":9661,"output_tokens":1099,"output_tokens_details":{"thinking_tokens":195},"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":1221},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1886,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmC6Nr3jMhvmV5JBxQG","requestRef":"1e2afc45-5f59-4f88-9b30-6717629a6544","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b9cf10c6-f392-4c1a-a99a-a19efeb7dcc9","timestamp":"2026-10-30T04:07:16.798Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"b9cf10c6-f392-4c1a-a99a-a19efeb7dcc9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmC6fTH585VyU7EHgn1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011HJtMCNMjJMtSsfsiNu6MK","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — task F6-conf-04\n**Question.** Causal effect of one extra training hour per employee (programme year) on next-year productivity growth (pp per hour), in simulated firm data.\n**Estimand.** Coefficient on `training_hours` in a linear, homogeneous outcome model, identified under selection on observables given `skill_index` (pre-programme, so a valid non-post-treatment control). Meaningful only if no unobserved confounders remain, skill enters (approximately) linearly, and the effect is homogeneous.\n**Baseline.** Unadjusted OLS `productivity_growth ~ training_hours` (intercept only), with 95% CI and residual RMSE.\n**Outputs.** out/results.json (keys: naive_estimate, naive_ci_low, naive_ci_high, baseline_metric, model_metric, effect_estimate, effect_se, effect_ci_low, effect_ci_high, skill_index_coefficient, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (model, estimate, se, ci_low, ci_high); out/report.md (6 sections); out/analysis.py; out/claims.json; plus state files, exclusions.csv.\n**Information rules.** Only data/firms.csv. skill_index is measured before the programme -> admissible control. No imputation needed.\n**Invalidity/impossibility.** Missing key variables, a control measured post-treatment, no overlap/variation in training given skill, or a data problem that prevents estimation would make the task infeasible (premise_invalid). Unobserved confounding would invalidate the causal interpretation (untestable).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n \"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > log.md","description":"Write contract, phase ledger, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1221,"cache_read_input_tokens":9661,"output_tokens":1099,"output_tokens_details":{"thinking_tokens":195},"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":1221},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmC6Nr3jMhvmV5JBxQG","requestRef":"1e2afc45-5f59-4f88-9b30-6717629a6544","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8db30ec0-c6c2-4c32-932d-ca06ae898c1a","timestamp":"2026-10-30T04:07:23.905Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"8db30ec0-c6c2-4c32-932d-ca06ae898c1a","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011HJtMCNMjJMtSsfsiNu6MK","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"6cd96849-6294-4b2a-b9c3-f7836a32d09f","timestamp":"2026-10-30T04:07:23.925Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8db30ec0-c6c2-4c32-932d-ca06ae898c1a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"c6b4664b98975dc9f6395a1b5851b853cf1b0c2b60816d3dc34073d29c134142","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_011HJtMCNMjJMtSsfsiNu6MK","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — task F6-conf-04\n**Question.** Causal effect of one extra training hour per employee (programme year) on next-year productivity growth (pp per hour), in simulated firm data.\n**Estimand.** Coefficient on `training_hours` in a linear, homogeneous outcome model, identified under selection on observables given `skill_index` (pre-programme, so a valid non-post-treatment control). Meaningful only if no unobserved confounders remain, skill enters (approximately) linearly, and the effect is homogeneous.\n**Baseline.** Unadjusted OLS `productivity_growth ~ training_hours` (intercept only), with 95% CI and residual RMSE.\n**Outputs.** out/results.json (keys: naive_estimate, naive_ci_low, naive_ci_high, baseline_metric, model_metric, effect_estimate, effect_se, effect_ci_low, effect_ci_high, skill_index_coefficient, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (model, estimate, se, ci_low, ci_high); out/report.md (6 sections); out/analysis.py; out/claims.json; plus state files, exclusions.csv.\n**Information rules.** Only data/firms.csv. skill_index is measured before the programme -> admissible control. No imputation needed.\n**Invalidity/impossibility.** Missing key variables, a control measured post-treatment, no overlap/variation in training given skill, or a data problem that prevents estimation would make the task infeasible (premise_invalid). Unobserved confounding would invalidate the causal interpretation (untestable).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n \"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30 P0 passed: contract written.\" > log.md","description":"Write contract, phase ledger, log"}}]}}39{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"54579a68-e1e6-4601-a4b1-e3aab3ee2065","timestamp":"2026-10-30T04:07:23.928Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"1e2afc45-5f59-4f88-9b30-6717629a6544","keep":10,"tail":["c6b4664b98975dc9f6395a1b5851b853cf1b0c2b60816d3dc34073d29c134142","fe0220ee9e835f5359c515a9ff0b4d5308329dd045ddda0c232f2e3996067c6a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"193ef9ea7310c3be217519dfcec9ff87f53b67fbb65c3425b0e81bdde135ed5f"}40{"parentUuid":"6cd96849-6294-4b2a-b9c3-f7836a32d09f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmCu9BpPCwCetZe2zJK","type":"message","role":"assistant","content":[{"type":"text","text":"Now the analysis script."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1114,"cache_read_input_tokens":10882,"output_tokens":3231,"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":1114},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmCtx2TNicxjaykyBi8","requestRef":"54579a68-e1e6-4601-a4b1-e3aab3ee2065","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"09ec5620-f366-4b9b-8019-d0ac02ce5631","timestamp":"2026-10-30T04:07:24.930Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"09ec5620-f366-4b9b-8019-d0ac02ce5631","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmCu9BpPCwCetZe2zJK","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GMaGjjxJiBzmS3b9eoohRJ","name":"Bash","input":{"command":"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\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nDeterministic: no randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA = \"data/firms.csv\"\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\n\nraw = pd.read_csv(DATA)\nn_raw = len(raw)\ncols = [\"firm_id\", \"skill_index\", \"training_hours\", \"productivity_growth\"]\nassert list(raw.columns) == cols\n\nexcl = []\ndata_issues = []\nd = raw.copy()\n\n# Step 1: missing values (none expected)\nnb = len(d); d = d.dropna(subset=cols); excl.append((\"1\", \"drop rows with missing values\", nb, len(d), \"required variables must be observed\"))\n# Step 2: duplicate firm_id (none expected)\nnb = len(d); d = d.drop_duplicates(subset=\"firm_id\"); excl.append((\"2\", \"drop duplicate firm_id\", nb, len(d), \"one row per firm\"))\n# Step 3: negative training hours (physically impossible)\nn_neg = int((d.training_hours < 0).sum())\nnb = len(d); d = d[d.training_hours >= 0]; excl.append((\"3\", \"drop training_hours < 0\", nb, len(d),\n \"hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.\"))\nif n_neg:\n data_issues.append({\"issue\": f\"{n_neg} rows have negative training_hours (min {raw.training_hours.min():.3f}), which is physically impossible\",\n \"handling\": \"excluded from the main analysis; sensitivity analysis re-estimates both models on all 1200 rows (keys sens_all_rows_*)\"})\ndata_issues.append({\"issue\": \"training_hours is strongly correlated with pre-programme skill_index (r = %.3f), and skill_index is strongly negatively related to productivity_growth: the unadjusted slope is confounded\" % raw[[\"skill_index\",\"training_hours\"]].corr().iloc[0,1],\n \"handling\": \"skill_index (measured before the programme) is included as a control in the model that targets the estimand\"})\n\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"rationale\"]).assign(\n n_removed=lambda x: x.n_before - x.n_after)[[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]].to_csv(\n os.path.join(OUT, \"exclusions.csv\"), index=False)\n\nCOV = \"HC1\" # heteroskedasticity-robust standard errors\ndef fit(formula, df):\n return smf.ols(formula, df).fit(cov_type=COV)\n\ndef rmse(m):\n return float(np.sqrt(np.mean(m.resid ** 2)))\n\nnaive = fit(\"productivity_growth ~ training_hours\", d)\nadj = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# robustness checks (not the main estimate)\nquad = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\ninter = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nnaive_all = fit(\"productivity_growth ~ training_hours\", raw)\nadj_all = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\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\ntable = pd.DataFrame([\n row(\"M1 unadjusted: growth ~ hours\", naive),\n row(\"M2 adjusted (main): growth ~ hours + skill_index\", adj),\n row(\"R1 adds skill_index^2\", quad),\n row(\"R2 adds hours x skill_index (effect at skill_index=0)\", inter),\n row(\"S1 unadjusted, all 1200 rows incl. negative hours\", naive_all),\n row(\"S2 adjusted, all 1200 rows incl. negative hours\", adj_all),\n])\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\nnci = naive.conf_int().loc[\"training_hours\"]; aci = adj.conf_int().loc[\"training_hours\"]\nlo, hi = float(aci[0]), float(aci[1])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nres = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(adj.nobs),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_se\": float(naive.bse[\"training_hours\"]),\n \"naive_ci_low\": float(nci[0]), \"naive_ci_high\": float(nci[1]),\n \"baseline_metric\": rmse(naive),\n \"model_metric\": rmse(adj),\n \"effect_estimate\": float(adj.params[\"training_hours\"]),\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"skill_index_se\": float(adj.bse[\"skill_index\"]),\n \"se_type\": \"HC1 heteroskedasticity-robust; 95% CI = estimate +/- 1.96*SE (normal)\",\n \"conclusion\": conclusion,\n \"corr_skill_training\": float(d[[\"skill_index\", \"training_hours\"]].corr().iloc[0, 1]),\n \"robust_quadratic_skill_effect\": float(quad.params[\"training_hours\"]),\n \"robust_quadratic_skill_sq_pvalue\": float(quad.pvalues[\"I(skill_index ** 2)\"]),\n \"robust_interaction_coef\": float(inter.params[\"training_hours:skill_index\"]),\n \"robust_interaction_pvalue\": float(inter.pvalues[\"training_hours:skill_index\"]),\n \"sens_all_rows_naive_estimate\": float(naive_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_estimate\": float(adj_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_se\": float(adj_all.bse[\"training_hours\"]),\n \"n_excluded_negative_hours\": n_neg,\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\n# Figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.35, color=\"grey\", label=\"firms (n=%d)\" % len(d))\nxs = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(xs, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * xs, color=\"tab:red\",\n label=\"unadjusted OLS (slope %.3f)\" % naive.params[\"training_hours\"])\nsbar = d.skill_index.mean()\nax.plot(xs, adj.params[\"Intercept\"] + adj.params[\"skill_index\"] * sbar + adj.params[\"training_hours\"] * xs,\n color=\"tab:blue\", label=\"adjusted for skill_index, at mean skill (slope %.3f)\" % adj.params[\"training_hours\"])\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Training hours vs productivity growth (simulated data)\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(f\"n_raw={n_raw} n_analysed={res['n_analysed']}\")\nprint(f\"naive slope={res['naive_estimate']:.4f} [{res['naive_ci_low']:.4f}, {res['naive_ci_high']:.4f}]\")\nprint(f\"adjusted slope={res['effect_estimate']:.4f} (HC1 se {res['effect_se']:.4f}) [{lo:.4f}, {hi:.4f}] -> {conclusion}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/table1.csv out/exclusions.csv","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1114,"cache_read_input_tokens":10882,"output_tokens":3231,"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":1114},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmCtx2TNicxjaykyBi8","requestRef":"54579a68-e1e6-4601-a4b1-e3aab3ee2065","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"714950da-ec27-4d2e-93a4-cd3896708efb","timestamp":"2026-10-30T04:07:48.168Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"714950da-ec27-4d2e-93a4-cd3896708efb","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0020/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01GMaGjjxJiBzmS3b9eoohRJ"}]},"uuid":"e1982c63-fc91-4c13-a601-bf60b295f4db","timestamp":"2026-10-30T04:07:48.218Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0020/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"714950da-ec27-4d2e-93a4-cd3896708efb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}43{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"4972f060294f1d7969593dec575e417a328e448dadcdd234fda961b14b57e329","message":{"role":"assistant","content":[{"type":"text","text":"Now the analysis script."},{"type":"tool_use","id":"toolu_01GMaGjjxJiBzmS3b9eoohRJ","name":"Bash","input":{"command":"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\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nDeterministic: no randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA = \"data/firms.csv\"\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\n\nraw = pd.read_csv(DATA)\nn_raw = len(raw)\ncols = [\"firm_id\", \"skill_index\", \"training_hours\", \"productivity_growth\"]\nassert list(raw.columns) == cols\n\nexcl = []\ndata_issues = []\nd = raw.copy()\n\n# Step 1: missing values (none expected)\nnb = len(d); d = d.dropna(subset=cols); excl.append((\"1\", \"drop rows with missing values\", nb, len(d), \"required variables must be observed\"))\n# Step 2: duplicate firm_id (none expected)\nnb = len(d); d = d.drop_duplicates(subset=\"firm_id\"); excl.append((\"2\", \"drop duplicate firm_id\", nb, len(d), \"one row per firm\"))\n# Step 3: negative training hours (physically impossible)\nn_neg = int((d.training_hours < 0).sum())\nnb = len(d); d = d[d.training_hours >= 0]; excl.append((\"3\", \"drop training_hours < 0\", nb, len(d),\n \"hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.\"))\nif n_neg:\n data_issues.append({\"issue\": f\"{n_neg} rows have negative training_hours (min {raw.training_hours.min():.3f}), which is physically impossible\",\n \"handling\": \"excluded from the main analysis; sensitivity analysis re-estimates both models on all 1200 rows (keys sens_all_rows_*)\"})\ndata_issues.append({\"issue\": \"training_hours is strongly correlated with pre-programme skill_index (r = %.3f), and skill_index is strongly negatively related to productivity_growth: the unadjusted slope is confounded\" % raw[[\"skill_index\",\"training_hours\"]].corr().iloc[0,1],\n \"handling\": \"skill_index (measured before the programme) is included as a control in the model that targets the estimand\"})\n\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"rationale\"]).assign(\n n_removed=lambda x: x.n_before - x.n_after)[[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]].to_csv(\n os.path.join(OUT, \"exclusions.csv\"), index=False)\n\nCOV = \"HC1\" # heteroskedasticity-robust standard errors\ndef fit(formula, df):\n return smf.ols(formula, df).fit(cov_type=COV)\n\ndef rmse(m):\n return float(np.sqrt(np.mean(m.resid ** 2)))\n\nnaive = fit(\"productivity_growth ~ training_hours\", d)\nadj = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# robustness checks (not the main estimate)\nquad = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\ninter = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nnaive_all = fit(\"productivity_growth ~ training_hours\", raw)\nadj_all = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\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\ntable = pd.DataFrame([\n row(\"M1 unadjusted: growth ~ hours\", naive),\n row(\"M2 adjusted (main): growth ~ hours + skill_index\", adj),\n row(\"R1 adds skill_index^2\", quad),\n row(\"R2 adds hours x skill_index (effect at skill_index=0)\", inter),\n row(\"S1 unadjusted, all 1200 rows incl. negative hours\", naive_all),\n row(\"S2 adjusted, all 1200 rows incl. negative hours\", adj_all),\n])\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\nnci = naive.conf_int().loc[\"training_hours\"]; aci = adj.conf_int().loc[\"training_hours\"]\nlo, hi = float(aci[0]), float(aci[1])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nres = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(adj.nobs),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_se\": float(naive.bse[\"training_hours\"]),\n \"naive_ci_low\": float(nci[0]), \"naive_ci_high\": float(nci[1]),\n \"baseline_metric\": rmse(naive),\n \"model_metric\": rmse(adj),\n \"effect_estimate\": float(adj.params[\"training_hours\"]),\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"skill_index_se\": float(adj.bse[\"skill_index\"]),\n \"se_type\": \"HC1 heteroskedasticity-robust; 95% CI = estimate +/- 1.96*SE (normal)\",\n \"conclusion\": conclusion,\n \"corr_skill_training\": float(d[[\"skill_index\", \"training_hours\"]].corr().iloc[0, 1]),\n \"robust_quadratic_skill_effect\": float(quad.params[\"training_hours\"]),\n \"robust_quadratic_skill_sq_pvalue\": float(quad.pvalues[\"I(skill_index ** 2)\"]),\n \"robust_interaction_coef\": float(inter.params[\"training_hours:skill_index\"]),\n \"robust_interaction_pvalue\": float(inter.pvalues[\"training_hours:skill_index\"]),\n \"sens_all_rows_naive_estimate\": float(naive_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_estimate\": float(adj_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_se\": float(adj_all.bse[\"training_hours\"]),\n \"n_excluded_negative_hours\": n_neg,\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\n# Figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.35, color=\"grey\", label=\"firms (n=%d)\" % len(d))\nxs = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(xs, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * xs, color=\"tab:red\",\n label=\"unadjusted OLS (slope %.3f)\" % naive.params[\"training_hours\"])\nsbar = d.skill_index.mean()\nax.plot(xs, adj.params[\"Intercept\"] + adj.params[\"skill_index\"] * sbar + adj.params[\"training_hours\"] * xs,\n color=\"tab:blue\", label=\"adjusted for skill_index, at mean skill (slope %.3f)\" % adj.params[\"training_hours\"])\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Training hours vs productivity growth (simulated data)\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(f\"n_raw={n_raw} n_analysed={res['n_analysed']}\")\nprint(f\"naive slope={res['naive_estimate']:.4f} [{res['naive_ci_low']:.4f}, {res['naive_ci_high']:.4f}]\")\nprint(f\"adjusted slope={res['effect_estimate']:.4f} (HC1 se {res['effect_se']:.4f}) [{lo:.4f}, {hi:.4f}] -> {conclusion}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/table1.csv out/exclusions.csv","description":"Write and run analysis script"}}]}}44{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"bd30e270-3c5c-46ee-b184-d0f88f6a3bec","timestamp":"2026-10-30T04:07:48.221Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"54579a68-e1e6-4601-a4b1-e3aab3ee2065","keep":12,"tail":["4972f060294f1d7969593dec575e417a328e448dadcdd234fda961b14b57e329","efe4fd8e4ea3f2c7f0c677c74cfce88420794f49ea44fa27a55e48cf7ee6f6a3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1ef124f2ba1036ee7a6427aaa6b062307868ad45032b25e208c87b06d298d949"}45{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e1982c63-fc91-4c13-a601-bf60b295f4db","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}46{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}47{"parentUuid":"e1982c63-fc91-4c13-a601-bf60b295f4db","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEh4DRdtyzvUCmtbAL","type":"message","role":"assistant","content":[{"type":"text","text":"The previous `cd` persisted; rerunning from the workspace root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3393,"cache_read_input_tokens":11996,"output_tokens":134,"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":3393},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmEgnbzKg3pLzddR7MX","requestRef":"bd30e270-3c5c-46ee-b184-d0f88f6a3bec","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a87f7236-2f09-43bb-aa88-9310d2de4f99","timestamp":"2026-10-30T04:07:49.633Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"a87f7236-2f09-43bb-aa88-9310d2de4f99","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEh4DRdtyzvUCmtbAL","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019WED5fjC1PD9cZzqFRwqcx","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0020 && ls out out/state","description":"Return to workspace root and list out"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3393,"cache_read_input_tokens":11996,"output_tokens":134,"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":3393},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmEgnbzKg3pLzddR7MX","requestRef":"bd30e270-3c5c-46ee-b184-d0f88f6a3bec","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"60f61179-3734-4eec-b6dd-171d93df48e5","timestamp":"2026-10-30T04:07:50.257Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"60f61179-3734-4eec-b6dd-171d93df48e5","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019WED5fjC1PD9cZzqFRwqcx","type":"tool_result","content":"out:\nstate\n\nout/state:\ncontract.md\nlog.md\nphases.json","is_error":false}]},"uuid":"231870dd-6fff-42a1-bf61-366ad43c5b77","timestamp":"2026-10-30T04:07:50.284Z","toolUseResult":{"stdout":"out:\nstate\n\nout/state:\ncontract.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"60f61179-3734-4eec-b6dd-171d93df48e5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"bc10241a2e1672f1e570847c4305272af6d540ed1f47bd599e9f31ec8703c125","message":{"role":"assistant","content":[{"type":"text","text":"The previous `cd` persisted; rerunning from the workspace root."},{"type":"tool_use","id":"toolu_019WED5fjC1PD9cZzqFRwqcx","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0020 && ls out out/state","description":"Return to workspace root and list out"}}]}}51{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"7d077b67-c50b-4bbb-a322-80ca6b88c8bf","timestamp":"2026-10-30T04:07:50.287Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"bd30e270-3c5c-46ee-b184-d0f88f6a3bec","keep":14,"tail":["bc10241a2e1672f1e570847c4305272af6d540ed1f47bd599e9f31ec8703c125","b1f77fb77aaa2f79112e6c979ed8b570d9dc507468e12fee52e692fc6c757876"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"192fe310222edafddce73173bd9b9e31c0dc4e08e957b7b512ecc1746a7db4e1"}52{"parentUuid":"231870dd-6fff-42a1-bf61-366ad43c5b77","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEqtnSYz69Em7sgfoa","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":162,"cache_read_input_tokens":15389,"output_tokens":3283,"output_tokens_details":{"thinking_tokens":29},"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":162},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":313,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmEqdA3Qni82zEAKbNR","requestRef":"7d077b67-c50b-4bbb-a322-80ca6b88c8bf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4a705c9c-8a15-469e-b51c-ba257b582352","timestamp":"2026-10-30T04:07:51.685Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"4a705c9c-8a15-469e-b51c-ba257b582352","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEqtnSYz69Em7sgfoa","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Qjvzyqm2Z7vRYFejwJU1wb","name":"Bash","input":{"command":"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\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nDeterministic: no randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA = \"data/firms.csv\"\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\n\nraw = pd.read_csv(DATA)\nn_raw = len(raw)\ncols = [\"firm_id\", \"skill_index\", \"training_hours\", \"productivity_growth\"]\nassert list(raw.columns) == cols\n\nexcl = []\ndata_issues = []\nd = raw.copy()\n\n# Step 1: missing values (none expected)\nnb = len(d); d = d.dropna(subset=cols); excl.append((\"1\", \"drop rows with missing values\", nb, len(d), \"required variables must be observed\"))\n# Step 2: duplicate firm_id (none expected)\nnb = len(d); d = d.drop_duplicates(subset=\"firm_id\"); excl.append((\"2\", \"drop duplicate firm_id\", nb, len(d), \"one row per firm\"))\n# Step 3: negative training hours (physically impossible)\nn_neg = int((d.training_hours < 0).sum())\nnb = len(d); d = d[d.training_hours >= 0]; excl.append((\"3\", \"drop training_hours < 0\", nb, len(d),\n \"hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.\"))\nif n_neg:\n data_issues.append({\"issue\": f\"{n_neg} rows have negative training_hours (min {raw.training_hours.min():.3f}), which is physically impossible\",\n \"handling\": \"excluded from the main analysis; sensitivity analysis re-estimates both models on all 1200 rows (keys sens_all_rows_*)\"})\ndata_issues.append({\"issue\": \"training_hours is strongly correlated with pre-programme skill_index (r = %.3f), and skill_index is strongly negatively related to productivity_growth: the unadjusted slope is confounded\" % raw[[\"skill_index\",\"training_hours\"]].corr().iloc[0,1],\n \"handling\": \"skill_index (measured before the programme) is included as a control in the model that targets the estimand\"})\n\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"rationale\"]).assign(\n n_removed=lambda x: x.n_before - x.n_after)[[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]].to_csv(\n os.path.join(OUT, \"exclusions.csv\"), index=False)\n\nCOV = \"HC1\" # heteroskedasticity-robust standard errors\ndef fit(formula, df):\n return smf.ols(formula, df).fit(cov_type=COV)\n\ndef rmse(m):\n return float(np.sqrt(np.mean(m.resid ** 2)))\n\nnaive = fit(\"productivity_growth ~ training_hours\", d)\nadj = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# robustness checks (not the main estimate)\nquad = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\ninter = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nnaive_all = fit(\"productivity_growth ~ training_hours\", raw)\nadj_all = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\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\ntable = pd.DataFrame([\n row(\"M1 unadjusted: growth ~ hours\", naive),\n row(\"M2 adjusted (main): growth ~ hours + skill_index\", adj),\n row(\"R1 adds skill_index^2\", quad),\n row(\"R2 adds hours x skill_index (effect at skill_index=0)\", inter),\n row(\"S1 unadjusted, all 1200 rows incl. negative hours\", naive_all),\n row(\"S2 adjusted, all 1200 rows incl. negative hours\", adj_all),\n])\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\nnci = naive.conf_int().loc[\"training_hours\"]; aci = adj.conf_int().loc[\"training_hours\"]\nlo, hi = float(aci[0]), float(aci[1])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nres = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(adj.nobs),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_se\": float(naive.bse[\"training_hours\"]),\n \"naive_ci_low\": float(nci[0]), \"naive_ci_high\": float(nci[1]),\n \"baseline_metric\": rmse(naive),\n \"model_metric\": rmse(adj),\n \"effect_estimate\": float(adj.params[\"training_hours\"]),\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"skill_index_se\": float(adj.bse[\"skill_index\"]),\n \"se_type\": \"HC1 heteroskedasticity-robust; 95% CI = estimate +/- 1.96*SE (normal)\",\n \"conclusion\": conclusion,\n \"corr_skill_training\": float(d[[\"skill_index\", \"training_hours\"]].corr().iloc[0, 1]),\n \"robust_quadratic_skill_effect\": float(quad.params[\"training_hours\"]),\n \"robust_quadratic_skill_sq_pvalue\": float(quad.pvalues[\"I(skill_index ** 2)\"]),\n \"robust_interaction_coef\": float(inter.params[\"training_hours:skill_index\"]),\n \"robust_interaction_pvalue\": float(inter.pvalues[\"training_hours:skill_index\"]),\n \"sens_all_rows_naive_estimate\": float(naive_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_estimate\": float(adj_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_se\": float(adj_all.bse[\"training_hours\"]),\n \"n_excluded_negative_hours\": n_neg,\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\n# Figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.35, color=\"grey\", label=\"firms (n=%d)\" % len(d))\nxs = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(xs, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * xs, color=\"tab:red\",\n label=\"unadjusted OLS (slope %.3f)\" % naive.params[\"training_hours\"])\nsbar = d.skill_index.mean()\nax.plot(xs, adj.params[\"Intercept\"] + adj.params[\"skill_index\"] * sbar + adj.params[\"training_hours\"] * xs,\n color=\"tab:blue\", label=\"adjusted for skill_index, at mean skill (slope %.3f)\" % adj.params[\"training_hours\"])\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Training hours vs productivity growth (simulated data)\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(f\"n_raw={n_raw} n_analysed={res['n_analysed']}\")\nprint(f\"naive slope={res['naive_estimate']:.4f} [{res['naive_ci_low']:.4f}, {res['naive_ci_high']:.4f}]\")\nprint(f\"adjusted slope={res['effect_estimate']:.4f} (HC1 se {res['effect_se']:.4f}) [{lo:.4f}, {hi:.4f}] -> {conclusion}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/table1.csv out/exclusions.csv","description":"Write and run analysis script from root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":162,"cache_read_input_tokens":15389,"output_tokens":3283,"output_tokens_details":{"thinking_tokens":29},"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":162},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmEqdA3Qni82zEAKbNR","requestRef":"7d077b67-c50b-4bbb-a322-80ca6b88c8bf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6a95d61d-dc09-406a-af1d-d719210e0f17","timestamp":"2026-10-30T04:08:11.728Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"6a95d61d-dc09-406a-af1d-d719210e0f17","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Qjvzyqm2Z7vRYFejwJU1wb","type":"tool_result","content":"n_raw=1200 n_analysed=1188\nnaive slope=-0.1317 [-0.1604, -0.1030]\nadjusted slope=0.2535 (HC1 se 0.0098) [0.2343, 0.2728] -> positive_effect\n{\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 rows have negative training_hours (min -7.585), which is physically impossible\",\n \"handling\": \"excluded from the main analysis; sensitivity analysis re-estimates both models on all 1200 rows (keys sens_all_rows_*)\"\n },\n {\n \"issue\": \"training_hours is strongly correlated with pre-programme skill_index (r = 0.694), and skill_index is strongly negatively related to productivity_growth: the unadjusted slope is confounded\",\n \"handling\": \"skill_index (measured before the programme) is included as a control in the model that targets the estimand\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null,\n \"naive_estimate\": -0.13169790632300882,\n \"naive_se\": 0.014619618827634278,\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 \"skill_index_se\": 0.07816357249116873,\n \"se_type\": \"HC1 heteroskedasticity-robust; 95% CI = estimate +/- 1.96*SE (normal)\",\n \"conclusion\": \"positive_effect\",\n \"corr_skill_training\": 0.677572028059802,\n \"robust_quadratic_skill_effect\": 0.25383792381516485,\n \"robust_quadratic_skill_sq_pvalue\": 0.5689381094023501,\n \"robust_interaction_coef\": -0.00032835690944043455,\n \"robust_interaction_pvalue\": 0.9564572077696775,\n \"sens_all_rows_naive_estimate\": -0.13518960504279864,\n \"sens_all_rows_effect_estimate\": 0.25222449623309495,\n \"sens_all_rows_effect_se\": 0.00947885217664965,\n \"n_excluded_negative_hours\": 12\n}model,estimate,se,ci_low,ci_high\nM1 unadjusted: growth ~ hours,-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\nM2 adjusted (main): growth ~ hours + skill_index,0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\nR1 adds skill_index^2,0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293\nR2 adds hours x skill_index (effect at skill_index=0),0.2535986940513955,0.009917283395566277,0.23416117577160853,0.2730362123311825\n\"S1 unadjusted, all 1200 rows incl. negative hours\",-0.13518960504279864,0.013896968221774055,-0.16242716225177342,-0.10795204783382387\n\"S2 adjusted, all 1200 rows incl. negative hours\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values,1200,1200,0,required variables must be observed\n2,drop duplicate firm_id,1200,1200,0,one row per firm\n3,drop training_hours < 0,1200,1188,12,hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.","is_error":false}]},"uuid":"2b830b58-4512-4e7e-9bc2-600e0f02c498","timestamp":"2026-10-30T04:08:12.602Z","toolUseResult":{"stdout":"n_raw=1200 n_analysed=1188\nnaive slope=-0.1317 [-0.1604, -0.1030]\nadjusted slope=0.2535 (HC1 se 0.0098) [0.2343, 0.2728] -> positive_effect\n{\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 rows have negative training_hours (min -7.585), which is physically impossible\",\n \"handling\": \"excluded from the main analysis; sensitivity analysis re-estimates both models on all 1200 rows (keys sens_all_rows_*)\"\n },\n {\n \"issue\": \"training_hours is strongly correlated with pre-programme skill_index (r = 0.694), and skill_index is strongly negatively related to productivity_growth: the unadjusted slope is confounded\",\n \"handling\": \"skill_index (measured before the programme) is included as a control in the model that targets the estimand\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null,\n \"naive_estimate\": -0.13169790632300882,\n \"naive_se\": 0.014619618827634278,\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 \"skill_index_se\": 0.07816357249116873,\n \"se_type\": \"HC1 heteroskedasticity-robust; 95% CI = estimate +/- 1.96*SE (normal)\",\n \"conclusion\": \"positive_effect\",\n \"corr_skill_training\": 0.677572028059802,\n \"robust_quadratic_skill_effect\": 0.25383792381516485,\n \"robust_quadratic_skill_sq_pvalue\": 0.5689381094023501,\n \"robust_interaction_coef\": -0.00032835690944043455,\n \"robust_interaction_pvalue\": 0.9564572077696775,\n \"sens_all_rows_naive_estimate\": -0.13518960504279864,\n \"sens_all_rows_effect_estimate\": 0.25222449623309495,\n \"sens_all_rows_effect_se\": 0.00947885217664965,\n \"n_excluded_negative_hours\": 12\n}model,estimate,se,ci_low,ci_high\nM1 unadjusted: growth ~ hours,-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\nM2 adjusted (main): growth ~ hours + skill_index,0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\nR1 adds skill_index^2,0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293\nR2 adds hours x skill_index (effect at skill_index=0),0.2535986940513955,0.009917283395566277,0.23416117577160853,0.2730362123311825\n\"S1 unadjusted, all 1200 rows incl. negative hours\",-0.13518960504279864,0.013896968221774055,-0.16242716225177342,-0.10795204783382387\n\"S2 adjusted, all 1200 rows incl. negative hours\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values,1200,1200,0,required variables must be observed\n2,drop duplicate firm_id,1200,1200,0,one row per firm\n3,drop training_hours < 0,1200,1188,12,hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6a95d61d-dc09-406a-af1d-d719210e0f17","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}55{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"798ab01a159d170ce1f6c59933396102ee396de2e758decb11c27e98bcf286b5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSwgYKEAgTGAI4AUIIdGhpbmtpbmcSDCAvMUjfX5cKC5rdLRoMSz9nhBKqWR5HV3GnIjD04oBp4EdWFrcTs+WFhzbGcoBikmTdUSYChhWO6Cykdas7I4Wq51WkOOiPJU2Cy1Iq3wXkp/Xz4wL12N19rCcsaaMM6l7f3uFfduZva1WMqmj6hYn/8+xgls8B/zyHbXuGd/5p8d+ZioxCofdNeV2FdobDZDmk0BukSkoZxDcveo/ifBYbrTJhP4a0YDtGmlhtT4mEeuoUjtZockyt1oKAKo9gQwskgVvRIuxB8e4/ENfCM9knH+vG4AnSx7r1Z785XyGxy4ikLDkbCr4oVAII4k4rDE0d3+JU97GjfOLzhVX3Wcg0nZ6YhnDxWjuXY/QJqb2ISkjgIqzQyB8NAJwxC1pWoh+3U1Mxc77IY+Et/KgjCxdxR1zXbhel/eZPgxzufarD+A2Fw79T6BiM+ZFmqbVEXxz5jqWl6kqBrDMzG/HRIar24tFBEmsow3SJp2HeRv2x1MxPYyXp5yPHpXabvOjadDEVz0+llL0BBssUT6xJ0N5qujqL2Dy5RuKr3DUQhj/9Ihayhj1MTnyXKEgsKeKlYTdrv1PixSniCv67bVpitoLqYE0AoSnjXMJjYbmoYzKEluwUfo3dSLOZHGTgiPtDdiJUYrztVAMVSM+dZ9tt6awfg2+qEhMPPhCviA5pPSW+R7iEm4wckkhhbafJd1bWH1l5xDQAS5LT3igGirKAsvFIRbbqKQbPMUsHXHnzVjOmVW4IQXv4fdB8l2FLMbosE1lyAEJZMW3MyWpgC5Lm8yDAu9OyidSBe64pR86gQ63ZeSMGgTp+abKeTSBiyNVwVtN5iqJh0Q7QT+3o6x+FLVFmc+qc23CIQoWY97yudgwcrlwDaZCIpCSpRLSG2qy8x8hVmj1oY/RaCcurZNNPqVfVVSFm+qfHuFAJVXULklE0xIwdFS0iUilL4tRDPIbh2Dfxz0RyWKoeoK/tU1NB5E3uGIGHVvmWHWTBDQZbnFwkroYF18djdC7Nm+tlHNOT6GMYaQM/0t1bSVamAAVdEHRtPd721Syami/MumY3HizvfoN56kJNBN7oMYTkegYYAQ=="},{"type":"tool_use","id":"toolu_01Qjvzyqm2Z7vRYFejwJU1wb","name":"Bash","input":{"command":"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\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nDeterministic: no randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA = \"data/firms.csv\"\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\n\nraw = pd.read_csv(DATA)\nn_raw = len(raw)\ncols = [\"firm_id\", \"skill_index\", \"training_hours\", \"productivity_growth\"]\nassert list(raw.columns) == cols\n\nexcl = []\ndata_issues = []\nd = raw.copy()\n\n# Step 1: missing values (none expected)\nnb = len(d); d = d.dropna(subset=cols); excl.append((\"1\", \"drop rows with missing values\", nb, len(d), \"required variables must be observed\"))\n# Step 2: duplicate firm_id (none expected)\nnb = len(d); d = d.drop_duplicates(subset=\"firm_id\"); excl.append((\"2\", \"drop duplicate firm_id\", nb, len(d), \"one row per firm\"))\n# Step 3: negative training hours (physically impossible)\nn_neg = int((d.training_hours < 0).sum())\nnb = len(d); d = d[d.training_hours >= 0]; excl.append((\"3\", \"drop training_hours < 0\", nb, len(d),\n \"hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.\"))\nif n_neg:\n data_issues.append({\"issue\": f\"{n_neg} rows have negative training_hours (min {raw.training_hours.min():.3f}), which is physically impossible\",\n \"handling\": \"excluded from the main analysis; sensitivity analysis re-estimates both models on all 1200 rows (keys sens_all_rows_*)\"})\ndata_issues.append({\"issue\": \"training_hours is strongly correlated with pre-programme skill_index (r = %.3f), and skill_index is strongly negatively related to productivity_growth: the unadjusted slope is confounded\" % raw[[\"skill_index\",\"training_hours\"]].corr().iloc[0,1],\n \"handling\": \"skill_index (measured before the programme) is included as a control in the model that targets the estimand\"})\n\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"rationale\"]).assign(\n n_removed=lambda x: x.n_before - x.n_after)[[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]].to_csv(\n os.path.join(OUT, \"exclusions.csv\"), index=False)\n\nCOV = \"HC1\" # heteroskedasticity-robust standard errors\ndef fit(formula, df):\n return smf.ols(formula, df).fit(cov_type=COV)\n\ndef rmse(m):\n return float(np.sqrt(np.mean(m.resid ** 2)))\n\nnaive = fit(\"productivity_growth ~ training_hours\", d)\nadj = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# robustness checks (not the main estimate)\nquad = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\ninter = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nnaive_all = fit(\"productivity_growth ~ training_hours\", raw)\nadj_all = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\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\ntable = pd.DataFrame([\n row(\"M1 unadjusted: growth ~ hours\", naive),\n row(\"M2 adjusted (main): growth ~ hours + skill_index\", adj),\n row(\"R1 adds skill_index^2\", quad),\n row(\"R2 adds hours x skill_index (effect at skill_index=0)\", inter),\n row(\"S1 unadjusted, all 1200 rows incl. negative hours\", naive_all),\n row(\"S2 adjusted, all 1200 rows incl. negative hours\", adj_all),\n])\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\nnci = naive.conf_int().loc[\"training_hours\"]; aci = adj.conf_int().loc[\"training_hours\"]\nlo, hi = float(aci[0]), float(aci[1])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nres = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(adj.nobs),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_se\": float(naive.bse[\"training_hours\"]),\n \"naive_ci_low\": float(nci[0]), \"naive_ci_high\": float(nci[1]),\n \"baseline_metric\": rmse(naive),\n \"model_metric\": rmse(adj),\n \"effect_estimate\": float(adj.params[\"training_hours\"]),\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo, \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"skill_index_se\": float(adj.bse[\"skill_index\"]),\n \"se_type\": \"HC1 heteroskedasticity-robust; 95% CI = estimate +/- 1.96*SE (normal)\",\n \"conclusion\": conclusion,\n \"corr_skill_training\": float(d[[\"skill_index\", \"training_hours\"]].corr().iloc[0, 1]),\n \"robust_quadratic_skill_effect\": float(quad.params[\"training_hours\"]),\n \"robust_quadratic_skill_sq_pvalue\": float(quad.pvalues[\"I(skill_index ** 2)\"]),\n \"robust_interaction_coef\": float(inter.params[\"training_hours:skill_index\"]),\n \"robust_interaction_pvalue\": float(inter.pvalues[\"training_hours:skill_index\"]),\n \"sens_all_rows_naive_estimate\": float(naive_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_estimate\": float(adj_all.params[\"training_hours\"]),\n \"sens_all_rows_effect_se\": float(adj_all.bse[\"training_hours\"]),\n \"n_excluded_negative_hours\": n_neg,\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(res, f, indent=2)\n\n# Figure\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.35, color=\"grey\", label=\"firms (n=%d)\" % len(d))\nxs = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(xs, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * xs, color=\"tab:red\",\n label=\"unadjusted OLS (slope %.3f)\" % naive.params[\"training_hours\"])\nsbar = d.skill_index.mean()\nax.plot(xs, adj.params[\"Intercept\"] + adj.params[\"skill_index\"] * sbar + adj.params[\"training_hours\"] * xs,\n color=\"tab:blue\", label=\"adjusted for skill_index, at mean skill (slope %.3f)\" % adj.params[\"training_hours\"])\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Training hours vs productivity growth (simulated data)\")\nax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(f\"n_raw={n_raw} n_analysed={res['n_analysed']}\")\nprint(f\"naive slope={res['naive_estimate']:.4f} [{res['naive_ci_low']:.4f}, {res['naive_ci_high']:.4f}]\")\nprint(f\"adjusted slope={res['effect_estimate']:.4f} (HC1 se {res['effect_se']:.4f}) [{lo:.4f}, {hi:.4f}] -> {conclusion}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/table1.csv out/exclusions.csv","description":"Write and run analysis script from root"}}]}}56{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"88167041-5b97-48ae-8ed2-36c19810b9cf","timestamp":"2026-10-30T04:08:12.605Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"7d077b67-c50b-4bbb-a322-80ca6b88c8bf","keep":16,"tail":["798ab01a159d170ce1f6c59933396102ee396de2e758decb11c27e98bcf286b5","0d16e2f3143cf543a7f72c5e7ca8c2b103834b7ff62abeaa8b9e614d6e75d2e0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"10cc6eeceb3f807c95c46d32bde9c878e251b123f85999083a4b96f994af9af3"}57{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2b830b58-4512-4e7e-9bc2-600e0f02c498","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}58{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}59{"parentUuid":"2b830b58-4512-4e7e-9bc2-600e0f02c498","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmGVMZrpjNVfmFpgZ7L","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":4684,"cache_read_input_tokens":15551,"output_tokens":357,"output_tokens_details":{"thinking_tokens":84},"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":4684},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":761,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmGV3U6XQpmrNBrHHPF","requestRef":"88167041-5b97-48ae-8ed2-36c19810b9cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6ac60262-d64c-4807-b00b-ff2380aab0e4","timestamp":"2026-10-30T04:08:14.774Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}60{"parentUuid":"6ac60262-d64c-4807-b00b-ff2380aab0e4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmGVMZrpjNVfmFpgZ7L","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Abnn6kZmTtg7p8DRkYNAps","name":"Bash","input":{"command":"sed -i '' 's/(r = %.3f), and skill_index/(r = %.3f in all 1200 rows), and skill_index/' out/analysis.py && rm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r1.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; ls out","description":"Patch label, clean rerun twice, compare"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4684,"cache_read_input_tokens":15551,"output_tokens":357,"output_tokens_details":{"thinking_tokens":84},"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":4684},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmGV3U6XQpmrNBrHHPF","requestRef":"88167041-5b97-48ae-8ed2-36c19810b9cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"79333f32-1dab-4e72-9d06-d496576c884a","timestamp":"2026-10-30T04:08:16.714Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"79333f32-1dab-4e72-9d06-d496576c884a","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Abnn6kZmTtg7p8DRkYNAps","type":"tool_result","content":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv","is_error":false}]},"uuid":"dd77755d-deb1-4e2e-bae9-eb9defd14264","timestamp":"2026-10-30T04:08:18.467Z","toolUseResult":{"stdout":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"79333f32-1dab-4e72-9d06-d496576c884a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}62{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"413952a3ca8281d75696962408219e37698947e6f86d180cf824167b7f491dfa","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Abnn6kZmTtg7p8DRkYNAps","name":"Bash","input":{"command":"sed -i '' 's/(r = %.3f), and skill_index/(r = %.3f in all 1200 rows), and skill_index/' out/analysis.py && rm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r1.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; ls out","description":"Patch label, clean rerun twice, compare"}}]}}63{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"05062433-e32d-4de0-b631-8461c92d81d1","timestamp":"2026-10-30T04:08:18.470Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"88167041-5b97-48ae-8ed2-36c19810b9cf","keep":18,"tail":["413952a3ca8281d75696962408219e37698947e6f86d180cf824167b7f491dfa","431a26883e7c47606a8c4288fc21839585f0857d225b6b7043c984f1ae47aa9a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7c8c067edd21522be0b28f29069fc140200b7d7ac65745890d6494325ad59245"}64{"type":"tools-used","tools":["Bash","Read"],"sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}65{"parentUuid":"dd77755d-deb1-4e2e-bae9-eb9defd14264","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmGvRh6KTrm7rdgiQSf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018i6hAZ1gKRb9hT747mvbWg","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0020/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":401,"cache_read_input_tokens":20235,"output_tokens":80,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":401},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmGv7qGYXvQXU2JNg97","requestRef":"05062433-e32d-4de0-b631-8461c92d81d1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aea7fea4-1acf-41d8-af2d-effdc557409b","timestamp":"2026-10-30T04:08:19.940Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}66{"parentUuid":"aea7fea4-1acf-41d8-af2d-effdc557409b","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018i6hAZ1gKRb9hT747mvbWg","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"e0849330-1322-4e70-9be9-c3ad3c5faa91","timestamp":"2026-10-30T04:08:19.957Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":91692,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"aea7fea4-1acf-41d8-af2d-effdc557409b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}67{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"cc2da29c08089cf798869b8abc604b54639b8e162832ac489b5afa0da4d22a7f","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_018i6hAZ1gKRb9hT747mvbWg","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0020/out/figure1.png"}}]}}68{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"dbae72ca-4ec5-4934-a4a1-9599e0c4e46c","timestamp":"2026-10-30T04:08:19.965Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"05062433-e32d-4de0-b631-8461c92d81d1","keep":20,"tail":["cc2da29c08089cf798869b8abc604b54639b8e162832ac489b5afa0da4d22a7f","5261de521213efeabc164236f807f200c3a0d0de6fd1f73136588b3a4f700992"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"00343eaa8af144c53cbc67f18978920adf3f2fd3020d324bb64b0eabdb783496"}69{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e0849330-1322-4e70-9be9-c3ad3c5faa91","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}70{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}71{"parentUuid":"e0849330-1322-4e70-9be9-c3ad3c5faa91","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmH2rexdvFa6QRDNyWF","type":"message","role":"assistant","content":[{"type":"text","text":"Figure is fine. Now audit, checks, and the gate."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":759,"cache_read_input_tokens":20636,"output_tokens":1437,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":759},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmH2W4h6yLkbKzrLzmg","requestRef":"dbae72ca-4ec5-4934-a4a1-9599e0c4e46c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5b6b2b90-0392-4de9-80d1-afdc04a135cb","timestamp":"2026-10-30T04:08:21.379Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}72{"parentUuid":"5b6b2b90-0392-4de9-80d1-afdc04a135cb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmH2rexdvFa6QRDNyWF","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_012unrdUzu8EFvwLGToK69C9","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\nFile: `data/firms.csv`, SHA-256 `34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df` (matches bundle.json).\n- 1200 rows (header excluded), 4 columns: firm_id (int64, 1001–2200, all unique), skill_index (float, standardised, mean -0.001, sd 0.99, range -3.83..2.96, measured pre-programme), training_hours (float, hours/employee in programme year, mean 19.9, sd 8.2, range -7.585..51.77), productivity_growth (float, % change in following year, mean 7.08, sd 4.02, range -4.04..19.39).\n- No dates in file (timing only via variable definitions: skill pre, hours during, growth after → no availability violation; skill_index is a valid pre-treatment control).\n- Missing values: 0 in every column. Duplicate rows: 0. Duplicate firm_id: 0.\n- **Anomaly:** 12 rows with training_hours < 0 (impossible). All have low skill_index (-3.0..-1.0). Decision: exclude from main analysis (exclusion ledger step 3); sensitivity on all 1200 rows reported.\n- Negative productivity growth values are plausible (productivity can fall) → kept.\n- Correlations (all rows): skill–hours 0.694, skill–growth -0.787, hours–growth -0.277 → strong confounding by skill_index expected.\n- No input violates the information-availability rules.\nEOF\ncat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| check | outcome |\n|---|---|\n| Clean re-run (deleted outputs, ran twice) gives byte-identical results.json | PASS (cmp identical) |\n| Exclusion ledger: 1200 − 0 − 0 − 12 = 1188 = n_analysed | PASS |\n| n_input_rows firms.csv = 1200 = wc -l − 1 | PASS |\n| SEs positive (naive_se 0.0146, effect_se 0.0098, skill_index_se 0.078) | PASS |\n| CIs contain estimates (naive, effect) | PASS |\n| CI = est ± 1.96·SE (HC1, normal) | PASS (0.2535 ± 0.0192 = [0.2343, 0.2728]) |\n| RMSE positive; model_metric (1.98) < baseline_metric (3.86), expected since adjusted model nests unadjusted | PASS |\n| conclusion consistent with CI (lo>0 → positive_effect) | PASS |\n| Magnitude vs baseline: sign flip from −0.132 to +0.254 explained by positive skill–hours correlation and negative skill–growth coefficient (omitted-variable bias formula: bias = β_skill·cov(h,s)/var(h) < 0) | PASS (consistent) |\n| Robustness: skill² term (p=0.57) and hours×skill interaction (p=0.96) not significant; effect unchanged (0.2538, 0.2536) | PASS |\n| Sensitivity incl. 12 negative-hour rows: effect 0.2522 | PASS (conclusion unchanged) |\n| Information rules: only data/firms.csv read; control is pre-treatment | PASS |\nEOF\n~/wp29/venv/bin/python -c \"\nimport json,pandas as pd;r=json.load(open('out/results.json'));d=pd.read_csv('data/firms.csv')\nh=d[d.training_hours>=0];import numpy as np\nb=np.polyfit(h.skill_index,h.training_hours,1)[0]\nprint('OVB check', r['effect_estimate']+r['skill_index_coefficient']*np.cov(h.training_hours,h.skill_index)[0,1]/h.training_hours.var(), r['naive_estimate'])\"","description":"Write audit and checks; verify OVB identity"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":759,"cache_read_input_tokens":20636,"output_tokens":1437,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":759},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmH2W4h6yLkbKzrLzmg","requestRef":"dbae72ca-4ec5-4934-a4a1-9599e0c4e46c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"da01b003-92bf-48d9-8567-fe26f9fc2ea1","timestamp":"2026-10-30T04:08:33.193Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}73{"parentUuid":"da01b003-92bf-48d9-8567-fe26f9fc2ea1","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_012unrdUzu8EFvwLGToK69C9","type":"tool_result","content":"OVB check -0.13169790632300893 -0.13169790632300882","is_error":false}]},"uuid":"69195faf-59be-492c-82e2-8553ff8bc6e4","timestamp":"2026-10-30T04:08:33.438Z","toolUseResult":{"stdout":"OVB check -0.13169790632300893 -0.13169790632300882","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"da01b003-92bf-48d9-8567-fe26f9fc2ea1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}74{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"ec5bfd4cb0f2d28aecf13e07d07c6f7d5ef120f898df2ed0cbb6a46fd9869db0","message":{"role":"assistant","content":[{"type":"text","text":"Figure is fine. Now audit, checks, and the gate."},{"type":"tool_use","id":"toolu_012unrdUzu8EFvwLGToK69C9","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\nFile: `data/firms.csv`, SHA-256 `34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df` (matches bundle.json).\n- 1200 rows (header excluded), 4 columns: firm_id (int64, 1001–2200, all unique), skill_index (float, standardised, mean -0.001, sd 0.99, range -3.83..2.96, measured pre-programme), training_hours (float, hours/employee in programme year, mean 19.9, sd 8.2, range -7.585..51.77), productivity_growth (float, % change in following year, mean 7.08, sd 4.02, range -4.04..19.39).\n- No dates in file (timing only via variable definitions: skill pre, hours during, growth after → no availability violation; skill_index is a valid pre-treatment control).\n- Missing values: 0 in every column. Duplicate rows: 0. Duplicate firm_id: 0.\n- **Anomaly:** 12 rows with training_hours < 0 (impossible). All have low skill_index (-3.0..-1.0). Decision: exclude from main analysis (exclusion ledger step 3); sensitivity on all 1200 rows reported.\n- Negative productivity growth values are plausible (productivity can fall) → kept.\n- Correlations (all rows): skill–hours 0.694, skill–growth -0.787, hours–growth -0.277 → strong confounding by skill_index expected.\n- No input violates the information-availability rules.\nEOF\ncat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| check | outcome |\n|---|---|\n| Clean re-run (deleted outputs, ran twice) gives byte-identical results.json | PASS (cmp identical) |\n| Exclusion ledger: 1200 − 0 − 0 − 12 = 1188 = n_analysed | PASS |\n| n_input_rows firms.csv = 1200 = wc -l − 1 | PASS |\n| SEs positive (naive_se 0.0146, effect_se 0.0098, skill_index_se 0.078) | PASS |\n| CIs contain estimates (naive, effect) | PASS |\n| CI = est ± 1.96·SE (HC1, normal) | PASS (0.2535 ± 0.0192 = [0.2343, 0.2728]) |\n| RMSE positive; model_metric (1.98) < baseline_metric (3.86), expected since adjusted model nests unadjusted | PASS |\n| conclusion consistent with CI (lo>0 → positive_effect) | PASS |\n| Magnitude vs baseline: sign flip from −0.132 to +0.254 explained by positive skill–hours correlation and negative skill–growth coefficient (omitted-variable bias formula: bias = β_skill·cov(h,s)/var(h) < 0) | PASS (consistent) |\n| Robustness: skill² term (p=0.57) and hours×skill interaction (p=0.96) not significant; effect unchanged (0.2538, 0.2536) | PASS |\n| Sensitivity incl. 12 negative-hour rows: effect 0.2522 | PASS (conclusion unchanged) |\n| Information rules: only data/firms.csv read; control is pre-treatment | PASS |\nEOF\n~/wp29/venv/bin/python -c \"\nimport json,pandas as pd;r=json.load(open('out/results.json'));d=pd.read_csv('data/firms.csv')\nh=d[d.training_hours>=0];import numpy as np\nb=np.polyfit(h.skill_index,h.training_hours,1)[0]\nprint('OVB check', r['effect_estimate']+r['skill_index_coefficient']*np.cov(h.training_hours,h.skill_index)[0,1]/h.training_hours.var(), r['naive_estimate'])\"","description":"Write audit and checks; verify OVB identity"}}]}}75{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"d94776a2-a027-4260-8f5d-44dcf06d2305","timestamp":"2026-10-30T04:08:33.441Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"dbae72ca-4ec5-4934-a4a1-9599e0c4e46c","keep":22,"tail":["ec5bfd4cb0f2d28aecf13e07d07c6f7d5ef120f898df2ed0cbb6a46fd9869db0","e6c4c7a075265c02e5f12c4bf474bdd4f0a89224f263700917c2a7c0e9e31317"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7828c6ba7d82641c5f02b40e7c84c4860c2a38e1146e6a09bc124295e7ccaba0"}76{"parentUuid":"69195faf-59be-492c-82e2-8553ff8bc6e4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmJ2Qtj4oF6zwuaZu1q","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":1465,"cache_read_input_tokens":21395,"output_tokens":770,"output_tokens_details":{"thinking_tokens":28},"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":1465},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":299,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmJ28XQn6QmvnkJnPiL","requestRef":"d94776a2-a027-4260-8f5d-44dcf06d2305","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a005c33a-0f68-41b1-9b47-fcdad2b7850e","timestamp":"2026-10-30T04:08:35.170Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}77{"parentUuid":"a005c33a-0f68-41b1-9b47-fcdad2b7850e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmJ2Qtj4oF6zwuaZu1q","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WEuQkASixzWUx2T6VEaXhb","name":"Bash","input":{"command":"echo '| OVB identity: effect + β_skill·cov(h,s)/var(h) = naive slope (−0.131698 both) | PASS (exact to 1e-15) |' >> out/state/checks.md\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 matches bundle.json\",\"schema/missing/duplicates checked: none\",\"12 negative training_hours found and excluded (ledger step 3)\",\"exclusions.csv sums: 1200-12=1188\"],\"notes\":\"see data_audit.md\"},\n \"P2\":{\"status\":\"passed\",\"checks\":[\"unadjusted OLS slope -0.1317 HC1 CI [-0.160,-0.103], RMSE 3.86 recorded\"],\"notes\":\"\"},\n \"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png; no randomness (seed null)\",\"adjusted OLS with skill_index: 0.2535 (HC1 SE 0.0098)\"],\"notes\":\"\"},\n \"P4\":{\"status\":\"running\",\"checks\":[\"clean rerun byte-identical\",\"internal consistency checks in checks.md all PASS\",\"OVB identity exact\"],\"notes\":\"\"},\n \"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: 12 negative training_hours rows excluded (decision: impossible values; sensitivity kept).\n- 2026-10-30 P2 passed: baseline unadjusted OLS on analysed sample.\n- 2026-10-30 P3 passed: main model OLS hours + skill_index, HC1 SEs.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Update ledger and run gate (P4)"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1465,"cache_read_input_tokens":21395,"output_tokens":770,"output_tokens_details":{"thinking_tokens":28},"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":1465},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmJ28XQn6QmvnkJnPiL","requestRef":"d94776a2-a027-4260-8f5d-44dcf06d2305","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d21da247-1837-4373-ae9f-5b37b9b6900c","timestamp":"2026-10-30T04:08:40.363Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"d21da247-1837-4373-ae9f-5b37b9b6900c","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 40 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:naive_estimate: ok\n [ok] key:naive_ci_low: ok\n [ok] key:naive_ci_high: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:effect_se: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:skill_index_coefficient: ok\n [ok] key:conclusion: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 3 steps consistent\n [ok] ci:naive_estimate: -0.1603518326928757 <= -0.13169790632300882 <= -0.10304397995314195\n [ok] ci:effect_estimate: 0.2343066231767153 <= 0.25353820594501253 <= 0.27276978871330976\n [ok] positive:effect_se: 0.009812212326345536\n [ok] positive:baseline_metric: 3.8601022336733584\n [ok] positive:model_metric: 1.9758571828823268\n [ok] reproducibility: regenerated in 0.8s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0020/out/state/gate_receipts/20261030T040841.270048Z.json","is_error":true,"tool_use_id":"toolu_01WEuQkASixzWUx2T6VEaXhb"}]},"uuid":"2b4b78e1-c30c-4f99-a408-4a3e47fe42c9","timestamp":"2026-10-30T04:08:41.276Z","toolUseResult":"Error: Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 40 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:naive_estimate: ok\n [ok] key:naive_ci_low: ok\n [ok] key:naive_ci_high: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:effect_se: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:skill_index_coefficient: ok\n [ok] key:conclusion: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 3 steps consistent\n [ok] ci:naive_estimate: -0.1603518326928757 <= -0.13169790632300882 <= -0.10304397995314195\n [ok] ci:effect_estimate: 0.2343066231767153 <= 0.25353820594501253 <= 0.27276978871330976\n [ok] positive:effect_se: 0.009812212326345536\n [ok] positive:baseline_metric: 3.8601022336733584\n [ok] positive:model_metric: 1.9758571828823268\n [ok] reproducibility: regenerated in 0.8s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0020/out/state/gate_receipts/20261030T040841.270048Z.json","sandboxed":false,"sourceToolAssistantUUID":"d21da247-1837-4373-ae9f-5b37b9b6900c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}79{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"ed11259576d7eb338c5cfb236fc21fe806b982d6264850abc268fb7f396eb986","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WEuQkASixzWUx2T6VEaXhb","name":"Bash","input":{"command":"echo '| OVB identity: effect + β_skill·cov(h,s)/var(h) = naive slope (−0.131698 both) | PASS (exact to 1e-15) |' >> out/state/checks.md\ncat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 matches bundle.json\",\"schema/missing/duplicates checked: none\",\"12 negative training_hours found and excluded (ledger step 3)\",\"exclusions.csv sums: 1200-12=1188\"],\"notes\":\"see data_audit.md\"},\n \"P2\":{\"status\":\"passed\",\"checks\":[\"unadjusted OLS slope -0.1317 HC1 CI [-0.160,-0.103], RMSE 3.86 recorded\"],\"notes\":\"\"},\n \"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png; no randomness (seed null)\",\"adjusted OLS with skill_index: 0.2535 (HC1 SE 0.0098)\"],\"notes\":\"\"},\n \"P4\":{\"status\":\"running\",\"checks\":[\"clean rerun byte-identical\",\"internal consistency checks in checks.md all PASS\",\"OVB identity exact\"],\"notes\":\"\"},\n \"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed: 12 negative training_hours rows excluded (decision: impossible values; sensitivity kept).\n- 2026-10-30 P2 passed: baseline unadjusted OLS on analysed sample.\n- 2026-10-30 P3 passed: main model OLS hours + skill_index, HC1 SEs.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Update ledger and run gate (P4)"}}]}}80{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"3b6c0f61-ca8c-4711-a128-77f7709ae952","timestamp":"2026-10-30T04:08:41.279Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"d94776a2-a027-4260-8f5d-44dcf06d2305","keep":24,"tail":["ed11259576d7eb338c5cfb236fc21fe806b982d6264850abc268fb7f396eb986","11fd351b565e6e96e8019380d4f898362609719d2f890748741839052d9e863b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"413e89297ce333adf3b898025fd21b3b4b705db4de69b0eef782246b334c655d"}81{"parentUuid":"2b4b78e1-c30c-4f99-a408-4a3e47fe42c9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmJbrJMpdDCxrqwL4Sk","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":1690,"cache_read_input_tokens":22860,"output_tokens":3357,"output_tokens_details":{"thinking_tokens":136},"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":1690},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1585,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmJbf9EFmBZhHiFh5cQ","requestRef":"3b6c0f61-ca8c-4711-a128-77f7709ae952","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c5793ccf-935a-407c-a1e4-efca3f17a714","timestamp":"2026-10-30T04:08:44.890Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}82{"parentUuid":"c5793ccf-935a-407c-a1e4-efca3f17a714","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmJbrJMpdDCxrqwL4Sk","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"The P4 gate passes all results, reproducibility, and ledger checks; only the unwritten P5 report, claims, and unmarked terminal phases fail. I'm writing the report and claims next.\n\n","signature":"CAQS7wcKEQgTGAI4AUIJbmFycmF0aW9uEgyUlix7UA3rLEtLPh8aDPHe+aJsAlu5/qHGzSIwhmOjUv4b/pSyy8CKAD511+ohuFYME+veLOad9wVy/TpME1xlJDdEq6z8RJ93mt9aKosHsrsw5gWkhWkp7HFyygT2IZ+7uREuKm4DgF2PLmQSKLFCKVvac9xt3GSKXQjGiAowHlnDiNUivLyIVkVI/SRH6FfDVxF8Waq7CsdS9IC4LEMFSQVLJOThtLXVZ7FeNSPF98qkXCTgRg4LDLMVPPTTLFWu+7wqcDq661aEVwtSMHz9IAxnQDWI5yZn+1oTEJlExd/o8LzR3GiZ/7/gxQ0SqU2ofBwm6R6sq5DHV7WJQl1GbyJ38GdXMH468LYX9MVs17jzNii9aUdQubCpFR7OMVfwlJk2FP9sb8MOlbZsHAuxk9k+Pio55Q8LA8ju1ugiC9ByfdjzALtABcKPyF3oDe0YJyV2leNoXPU1NTmpunmSzcu37LlV9m+tzMucjRyU9iMy1H7xS9k1JCH/HiDMoQzgBBjX37GXDwuvjlHZvQKTROX9tVUy1M7+grScFjyvOPPpXYdOc56JKRfYy+o/GMjZWrqq8DSmh3fK33DCWVJ90jIZ7bf3aWLCy8Kr8KjkxstLpWEe6R0KMzJe83tWnR85FbL/19y27I8IwwDnV8dpBKdzyYd8a87zMVDSJkDuaaF+VrhrcbV8ikqAEeS/lNJ07otEWVGZrItZ3JsyVc4gjC9sSSTZqRU0R6If9mgGU5oNHV3xp19OziOf/jgOJE5dZA5m5TmgyX1kDoI3yVC3T03hxLkQFfTbOr+ID+YHGcy+qtav8UUOVz+1wSUaRK8Dfegb2T9kYdQQpC1DjNpCVRDEFrjwiz4Sc4b8kpfc388+C2E5iGdAqsWFspKycqZsxXrY8giB9VxngVD7ignYSmZg/nOSErFKBsURvFDGr35yhx9XnFghZqHqvhPSzeFYHEzc6mAyHbmuzm5Fk41ESpTP8f/2Em13W9u6IvWiDDHaOklPCc7YQf+xFc4dqaNx8VVUy9Or2OTegbRdKfmN64wmOvHZMrrVRNdRsQK24mG/G4oAct4iRAt5PwMqNRR8nLFB4Ozuu+EwpZMdwNHZXe8WMEgR9fuynNlghav6HWRWiZgXtbAqZw7iB6GGTnHA0CO29buabwDP5NEy3GwIui9OK+hjoAEdsIhzUDWh1Ix26pzkxnK24b+yrj4yw54TfCJPYcB1idaoyKO7iu68EsDPlUj5Q3ZUNK4KB/xL3j8Sha4fSxM28ERzkF0exRCKgz94GfH9ByjLOTQf6VUzeo+P/MHwH0Gn5BgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1690,"cache_read_input_tokens":22860,"output_tokens":3357,"output_tokens_details":{"thinking_tokens":136},"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":1690},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2,"thinkingDisplay":"updates","apiBlockIndex":1,"requestId":"req_011CgXmJbf9EFmBZhHiFh5cQ","requestRef":"3b6c0f61-ca8c-4711-a128-77f7709ae952","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"335a5dd9-9334-4624-b5b5-fe131ac1a5c3","timestamp":"2026-10-30T04:08:44.892Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}83{"parentUuid":"335a5dd9-9334-4624-b5b5-fe131ac1a5c3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmJbrJMpdDCxrqwL4Sk","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RvG1L23uyoHkoHXuK5awhZ","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Training hours and productivity growth: task F6-conf-04 (simulated data)\n\n## Question\nWhat is the causal effect of one more training hour per employee during the programme year on productivity growth in the following year, measured in percentage points (pp) per hour? This is identified only under 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. As a baseline, I also report the unadjusted association.\n\n## Data and exclusions\n`data/firms.csv` (simulated) has 1200 rows (`n_input_rows`) and 4 columns. There are no missing values, no duplicate rows and no duplicate `firm_id`s. The full audit is in `out/state/data_audit.md`.\n- **Exclusion:** 12 firms (`n_excluded_negative_hours`) have negative `training_hours`, with a minimum of −7.585. Negative hours are impossible, so I dropped these rows from the main analysis. That leaves 1188 firms (`n_analysed`). The ledger is in `out/exclusions.csv`: 1200 − 0 − 0 − 12 = 1188. A sensitivity analysis that keeps the 12 rows is reported below.\n- **Confounding:** `skill_index` is measured before the programme, so including it cannot introduce post-treatment bias. It is strongly correlated with training hours (r = 0.678 in the analysed sample, `corr_skill_training`) and strongly negatively associated with growth. Both issues are listed in `data_issues`.\n\n## Method\n- **Baseline (M1):** OLS of `productivity_growth` on `training_hours` with an intercept.\n- **Main model (M2):** OLS of `productivity_growth` on `training_hours` and `skill_index`. Under the stated assumption, `skill_index` is the only observed confounder, so conditioning on it linearly targets the estimand. No other variables exist.\n- **Standard errors:** HC1 heteroskedasticity-robust. 95% CIs use the normal approximation, ±1.96·SE (`se_type`).\n- **Fit metric:** in-sample residual RMSE.\n- **Robustness:** R1 adds skill²; R2 adds an hours×skill interaction.\n- **Sensitivity:** S1 and S2 re-estimate M1 and M2 on all 1200 rows.\n- **Randomness:** none is used (`random_seed` = null).\n- **Outputs:** Table 1 is `out/table1.csv` and Figure 1 is `out/figure1.png`. Both are produced by `out/analysis.py`.\n\n## Results\n- **Unadjusted slope:** −0.132 pp/hour (`naive_estimate`), 95% CI [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`). Firms that trained more grew *less*.\n- **Adjusted for `skill_index`:** the sign reverses. The effect is +0.254 pp per hour (`effect_estimate`), 95% CI [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`). The coefficient on `skill_index` is −4.62 pp per index unit (`skill_index_coefficient`).\n- **Conclusion:** `positive_effect` (`conclusion`).\n- **Fit:** residual RMSE falls from 3.86 pp in the unadjusted model (`baseline_metric`) to 1.98 pp in the adjusted model (`model_metric`).\n- **Why the sign reverses:** firms with higher baseline skill trained more but grew less. Omitting skill therefore biases the slope downward. The omitted-variable identity reproduces the naive slope exactly from the adjusted coefficients (`out/state/checks.md`).\n- **Robustness:** the effect barely moves when adding skill² (0.2538, `robust_quadratic_skill_effect`; p for skill² = 0.57, `robust_quadratic_skill_sq_pvalue`). An hours×skill interaction is negligible (−0.0003, p = 0.96; `robust_interaction_coef`, `robust_interaction_pvalue`).\n- **Sensitivity:** keeping the 12 negative-hour rows gives 0.252 (`sens_all_rows_effect_estimate`) against −0.135 unadjusted (`sens_all_rows_naive_estimate`).\n\n## Uncertainty\n- The main effect has an HC1 SE of 0.0098 pp/hour (`effect_se`), so the 95% CI spans about ±0.019 around 0.254 and is far from zero. The unadjusted slope's SE is 0.0146 (`naive_se`).\n- These intervals cover sampling uncertainty only, given the model. They do not cover model or identification uncertainty, which is likely much larger: the gap between the naive and adjusted estimates (0.39 pp/hour) is about 40 times the SE.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n - **Unobserved confounding.** Anything that drives both training and later growth and is not captured by `skill_index` would bias the estimate. Examples are management quality, sector shocks, or expected growth, if firms anticipating a slowdown trained more. Adjustment flipped the sign, which shows that the estimate depends heavily on which confounders are controlled for. Another omitted confounder could move it substantially in either direction.\n - **Measurement error in `skill_index`.** A noisy index would only partly control for confounding. Here the confounding pushes the slope downward, so residual confounding would likely bias the estimate downward too. That direction is a reasoned guess, not tested.\n - **Mis-specification.** Linearity and homogeneity are assumptions. Only the simple skill² and interaction checks were run.\n- **What was not checked:**\n - No formal sensitivity analysis for unobserved confounding (e.g. E-values or Oster bounds).\n - No non-parametric adjustment (matching or weighting), and no formal overlap diagnostics beyond the observed spread.\n - Nonlinearity in training hours (e.g. diminishing returns) was not tested.\n - No out-of-sample evaluation: the RMSEs are in-sample and describe fit, not causal validity.\n- **Data issue:** the 12 negative training-hour values are unexplained. They could be coding errors, or the result of a generating process that does not respect the zero bound. Excluding them changes the effect only slightly (0.254 vs 0.252), and they are concentrated among low-skill firms.\n- **External validity:** the data are simulated. The numbers say nothing about real training programmes.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The unadjusted OLS slope of productivity growth on training hours is negative (-0.132 pp/hour, 95% CI [-0.160,-0.103]).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by skill_index.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one extra training hour raises next-year productivity growth by about 0.254 pp (95% HC1 CI [0.234,0.273]); conclusion positive_effect.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal interpretation requires selection on observables given skill_index alone, linearity and homogeneity; untestable.\"},\n {\"id\":\"C3\",\"text\":\"The sign reversal is explained by confounding: skill_index is positively correlated with training and has a strongly negative coefficient on growth (-4.62 pp per unit).\",\"results_keys\":[\"skill_index_coefficient\",\"corr_skill_training\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"OVB identity verified numerically; does not rule out other confounders.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits much better: residual RMSE 1.98 pp vs 3.86 pp unadjusted.\",\"results_keys\":[\"model_metric\",\"baseline_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; not evidence of causal validity.\"},\n {\"id\":\"C5\",\"text\":\"The effect estimate is robust to adding skill^2, an hours x skill interaction, and to retaining the 12 negative-hour rows.\",\"results_keys\":[\"robust_quadratic_skill_effect\",\"robust_quadratic_skill_sq_pvalue\",\"robust_interaction_coef\",\"robust_interaction_pvalue\",\"sens_all_rows_effect_estimate\"],\"status\":\"supported\",\"caveat\":\"Only these specific alternatives were checked.\"},\n {\"id\":\"C6\",\"text\":\"12 rows with negative training hours were excluded, leaving 1188 of 1200 firms.\",\"results_keys\":[\"n_excluded_negative_hours\",\"n_analysed\",\"n_input_rows\"],\"status\":\"supported\",\"caveat\":\"Origin of negative values unknown.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\nr=json.load(open('out/results.json'));c=json.load(open('out/claims.json'))\nprint([k for x in c for k in x['results_keys'] if k not in r])\nEOF","description":"Write report and claims; validate claim keys"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1690,"cache_read_input_tokens":22860,"output_tokens":3357,"output_tokens_details":{"thinking_tokens":136},"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":1690},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXmJbf9EFmBZhHiFh5cQ","requestRef":"3b6c0f61-ca8c-4711-a128-77f7709ae952","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"07271cc5-b96e-44d6-a966-7fc99938cd4c","timestamp":"2026-10-30T04:09:10.636Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}84{"parentUuid":"07271cc5-b96e-44d6-a966-7fc99938cd4c","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01RvG1L23uyoHkoHXuK5awhZ","type":"tool_result","content":"[]","is_error":false}]},"uuid":"ac9555d4-9a46-4935-8615-987bf101b533","timestamp":"2026-10-30T04:09:10.694Z","toolUseResult":{"stdout":"[]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"07271cc5-b96e-44d6-a966-7fc99938cd4c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}85{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"9533417d754db2e7f2cf828e782a93f2edbd170ac6dd36f234763830e6272fbe","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"thinking","thinking":"The P4 gate passes all results, reproducibility, and ledger checks; only the unwritten P5 report, claims, and unmarked terminal phases fail. I'm writing the report and claims next.\n\n","signature":"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"},{"type":"tool_use","id":"toolu_01RvG1L23uyoHkoHXuK5awhZ","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Training hours and productivity growth: task F6-conf-04 (simulated data)\n\n## Question\nWhat is the causal effect of one more training hour per employee during the programme year on productivity growth in the following year, measured in percentage points (pp) per hour? This is identified only under 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. As a baseline, I also report the unadjusted association.\n\n## Data and exclusions\n`data/firms.csv` (simulated) has 1200 rows (`n_input_rows`) and 4 columns. There are no missing values, no duplicate rows and no duplicate `firm_id`s. The full audit is in `out/state/data_audit.md`.\n- **Exclusion:** 12 firms (`n_excluded_negative_hours`) have negative `training_hours`, with a minimum of −7.585. Negative hours are impossible, so I dropped these rows from the main analysis. That leaves 1188 firms (`n_analysed`). The ledger is in `out/exclusions.csv`: 1200 − 0 − 0 − 12 = 1188. A sensitivity analysis that keeps the 12 rows is reported below.\n- **Confounding:** `skill_index` is measured before the programme, so including it cannot introduce post-treatment bias. It is strongly correlated with training hours (r = 0.678 in the analysed sample, `corr_skill_training`) and strongly negatively associated with growth. Both issues are listed in `data_issues`.\n\n## Method\n- **Baseline (M1):** OLS of `productivity_growth` on `training_hours` with an intercept.\n- **Main model (M2):** OLS of `productivity_growth` on `training_hours` and `skill_index`. Under the stated assumption, `skill_index` is the only observed confounder, so conditioning on it linearly targets the estimand. No other variables exist.\n- **Standard errors:** HC1 heteroskedasticity-robust. 95% CIs use the normal approximation, ±1.96·SE (`se_type`).\n- **Fit metric:** in-sample residual RMSE.\n- **Robustness:** R1 adds skill²; R2 adds an hours×skill interaction.\n- **Sensitivity:** S1 and S2 re-estimate M1 and M2 on all 1200 rows.\n- **Randomness:** none is used (`random_seed` = null).\n- **Outputs:** Table 1 is `out/table1.csv` and Figure 1 is `out/figure1.png`. Both are produced by `out/analysis.py`.\n\n## Results\n- **Unadjusted slope:** −0.132 pp/hour (`naive_estimate`), 95% CI [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`). Firms that trained more grew *less*.\n- **Adjusted for `skill_index`:** the sign reverses. The effect is +0.254 pp per hour (`effect_estimate`), 95% CI [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`). The coefficient on `skill_index` is −4.62 pp per index unit (`skill_index_coefficient`).\n- **Conclusion:** `positive_effect` (`conclusion`).\n- **Fit:** residual RMSE falls from 3.86 pp in the unadjusted model (`baseline_metric`) to 1.98 pp in the adjusted model (`model_metric`).\n- **Why the sign reverses:** firms with higher baseline skill trained more but grew less. Omitting skill therefore biases the slope downward. The omitted-variable identity reproduces the naive slope exactly from the adjusted coefficients (`out/state/checks.md`).\n- **Robustness:** the effect barely moves when adding skill² (0.2538, `robust_quadratic_skill_effect`; p for skill² = 0.57, `robust_quadratic_skill_sq_pvalue`). An hours×skill interaction is negligible (−0.0003, p = 0.96; `robust_interaction_coef`, `robust_interaction_pvalue`).\n- **Sensitivity:** keeping the 12 negative-hour rows gives 0.252 (`sens_all_rows_effect_estimate`) against −0.135 unadjusted (`sens_all_rows_naive_estimate`).\n\n## Uncertainty\n- The main effect has an HC1 SE of 0.0098 pp/hour (`effect_se`), so the 95% CI spans about ±0.019 around 0.254 and is far from zero. The unadjusted slope's SE is 0.0146 (`naive_se`).\n- These intervals cover sampling uncertainty only, given the model. They do not cover model or identification uncertainty, which is likely much larger: the gap between the naive and adjusted estimates (0.39 pp/hour) is about 40 times the SE.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n - **Unobserved confounding.** Anything that drives both training and later growth and is not captured by `skill_index` would bias the estimate. Examples are management quality, sector shocks, or expected growth, if firms anticipating a slowdown trained more. Adjustment flipped the sign, which shows that the estimate depends heavily on which confounders are controlled for. Another omitted confounder could move it substantially in either direction.\n - **Measurement error in `skill_index`.** A noisy index would only partly control for confounding. Here the confounding pushes the slope downward, so residual confounding would likely bias the estimate downward too. That direction is a reasoned guess, not tested.\n - **Mis-specification.** Linearity and homogeneity are assumptions. Only the simple skill² and interaction checks were run.\n- **What was not checked:**\n - No formal sensitivity analysis for unobserved confounding (e.g. E-values or Oster bounds).\n - No non-parametric adjustment (matching or weighting), and no formal overlap diagnostics beyond the observed spread.\n - Nonlinearity in training hours (e.g. diminishing returns) was not tested.\n - No out-of-sample evaluation: the RMSEs are in-sample and describe fit, not causal validity.\n- **Data issue:** the 12 negative training-hour values are unexplained. They could be coding errors, or the result of a generating process that does not respect the zero bound. Excluding them changes the effect only slightly (0.254 vs 0.252), and they are concentrated among low-skill firms.\n- **External validity:** the data are simulated. The numbers say nothing about real training programmes.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The unadjusted OLS slope of productivity growth on training hours is negative (-0.132 pp/hour, 95% CI [-0.160,-0.103]).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by skill_index.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one extra training hour raises next-year productivity growth by about 0.254 pp (95% HC1 CI [0.234,0.273]); conclusion positive_effect.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal interpretation requires selection on observables given skill_index alone, linearity and homogeneity; untestable.\"},\n {\"id\":\"C3\",\"text\":\"The sign reversal is explained by confounding: skill_index is positively correlated with training and has a strongly negative coefficient on growth (-4.62 pp per unit).\",\"results_keys\":[\"skill_index_coefficient\",\"corr_skill_training\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"OVB identity verified numerically; does not rule out other confounders.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits much better: residual RMSE 1.98 pp vs 3.86 pp unadjusted.\",\"results_keys\":[\"model_metric\",\"baseline_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; not evidence of causal validity.\"},\n {\"id\":\"C5\",\"text\":\"The effect estimate is robust to adding skill^2, an hours x skill interaction, and to retaining the 12 negative-hour rows.\",\"results_keys\":[\"robust_quadratic_skill_effect\",\"robust_quadratic_skill_sq_pvalue\",\"robust_interaction_coef\",\"robust_interaction_pvalue\",\"sens_all_rows_effect_estimate\"],\"status\":\"supported\",\"caveat\":\"Only these specific alternatives were checked.\"},\n {\"id\":\"C6\",\"text\":\"12 rows with negative training hours were excluded, leaving 1188 of 1200 firms.\",\"results_keys\":[\"n_excluded_negative_hours\",\"n_analysed\",\"n_input_rows\"],\"status\":\"supported\",\"caveat\":\"Origin of negative values unknown.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\nr=json.load(open('out/results.json'));c=json.load(open('out/claims.json'))\nprint([k for x in c for k in x['results_keys'] if k not in r])\nEOF","description":"Write report and claims; validate claim keys"}}]}}86{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"01d2d833-6867-447d-8adc-709a1c58d417","timestamp":"2026-10-30T04:09:10.697Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"3b6c0f61-ca8c-4711-a128-77f7709ae952","keep":26,"tail":["9533417d754db2e7f2cf828e782a93f2edbd170ac6dd36f234763830e6272fbe","56a75c96c34824bb59f00573e8620337bef8f818ddf4ccd05fab911949f013a3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"14b9057ddeae260a6632973b9cf822513f67bb2c2ead262409cb1575fea5af7e"}87{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"ac9555d4-9a46-4935-8615-987bf101b533","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}88{"type":"atis-latch","atis":"","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}89{"parentUuid":"ac9555d4-9a46-4935-8615-987bf101b533","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmLmpddFsyeL7hYGDqH","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015hbWKiaLw5FDrYmsfeoHJM","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']['status']='passed'; p['P4']['checks'].append('gate run 1 receipt out/state/gate_receipts/20261030T040841.270048Z.json: all P4 contract/repro/CI/ledger checks ok; only failures were not-yet-written P5 files (report, claims) and non-terminal P4/P5')\np['P5']['status']='passed'; p['P5']['checks']+=['report.md written with 6 sections, each number cites a results key','claims.json: 6 claims, all keys exist in results.json','final gate run (see gate_receipts, latest)']\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P4 passed (gate run 1, P5 files pending). P5: report and claims written; final gate run.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v '\\[ok\\]'","description":"Finalize phases and run final gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3364,"cache_read_input_tokens":24550,"output_tokens":448,"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":3364},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmLmXWkc1pNc89ycArs","requestRef":"01d2d833-6867-447d-8adc-709a1c58d417","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ef958adf-936f-4bf3-88ff-4cf7fd5c4045","timestamp":"2026-10-30T04:09:15.132Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}90{"parentUuid":"ef958adf-936f-4bf3-88ff-4cf7fd5c4045","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015hbWKiaLw5FDrYmsfeoHJM","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0020/out/state/gate_receipts/20261030T040916.082070Z.json","is_error":false}]},"uuid":"854afec1-298a-4a44-b051-ee6d1968b47f","timestamp":"2026-10-30T04:09:16.089Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0020/out/state/gate_receipts/20261030T040916.082070Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ef958adf-936f-4bf3-88ff-4cf7fd5c4045","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}91{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"f1ae2bf0eff11287f7b30f32bab2010cbde1e4dbddb55e75a53dde7d6680a105","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_015hbWKiaLw5FDrYmsfeoHJM","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']['status']='passed'; p['P4']['checks'].append('gate run 1 receipt out/state/gate_receipts/20261030T040841.270048Z.json: all P4 contract/repro/CI/ledger checks ok; only failures were not-yet-written P5 files (report, claims) and non-terminal P4/P5')\np['P5']['status']='passed'; p['P5']['checks']+=['report.md written with 6 sections, each number cites a results key','claims.json: 6 claims, all keys exist in results.json','final gate run (see gate_receipts, latest)']\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P4 passed (gate run 1, P5 files pending). P5: report and claims written; final gate run.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v '\\[ok\\]'","description":"Finalize phases and run final gate"}}]}}92{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"5156810f-be33-4b3a-be9a-902fc6b8c4f3","timestamp":"2026-10-30T04:09:16.091Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"01d2d833-6867-447d-8adc-709a1c58d417","keep":28,"tail":["f1ae2bf0eff11287f7b30f32bab2010cbde1e4dbddb55e75a53dde7d6680a105","273793529963bb0f71fe1c43dcde6edab5ea1725bae5178617e3b07c7d3a3adf"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d9e7a3a4935643bfa942046414958f2be896c936c41dc9234eeeb5eebbde6028"}93{"parentUuid":"854afec1-298a-4a44-b051-ee6d1968b47f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmMAozvMWMaoC1dTzeP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MZ2ULYf4rn11a3drKG7P1v","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'][-1]='final gate run PASSED 0/40 failed, receipt out/state/gate_receipts/20261030T040916.082070Z.json'\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate PASSED (20261030T040916.082070Z). Task complete.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record receipt and confirm gate still passes"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":543,"cache_read_input_tokens":27914,"output_tokens":298,"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":543},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmMAXd5kFdbRFEWCCrc","requestRef":"5156810f-be33-4b3a-be9a-902fc6b8c4f3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"65f61dcc-6405-4e63-b7e5-e81047bbc235","timestamp":"2026-10-30T04:09:19.256Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}94{"parentUuid":"65f61dcc-6405-4e63-b7e5-e81047bbc235","isSidechain":false,"promptId":"92081ec0-8662-47e1-932c-0ac897303cb2","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MZ2ULYf4rn11a3drKG7P1v","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","is_error":false}]},"uuid":"e0fb2c21-8249-4439-8ddf-52b0085885ec","timestamp":"2026-10-30T04:09:20.202Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"65f61dcc-6405-4e63-b7e5-e81047bbc235","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}95{"type":"api-request-blob","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","hash":"57968f01319fb4dc24a9bdce5ff029d4a89039c051b4ada4b7203e2397d3bd61","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MZ2ULYf4rn11a3drKG7P1v","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'][-1]='final gate run PASSED 0/40 failed, receipt out/state/gate_receipts/20261030T040916.082070Z.json'\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate PASSED (20261030T040916.082070Z). Task complete.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record receipt and confirm gate still passes"}}]}}96{"type":"api-request","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","id":"575b9a60-63fc-49fa-96c7-d9e819e6dbea","timestamp":"2026-10-30T04:09:20.205Z","version":"2.1.314","querySource":"sdk","shapeHash":"f4896ed7d9da06bd532b00fa3204900bca1f02e4e10722327efe5077ea72c4bf","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":"5156810f-be33-4b3a-be9a-902fc6b8c4f3","keep":30,"tail":["57968f01319fb4dc24a9bdce5ff029d4a89039c051b4ada4b7203e2397d3bd61","b1e404a8b163ddf0a4f23c72d64043c05df08a688cc4fa2b475759a2dbfd00c2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"06f12ccfec41d643dc8f25737acc0aa8687738c267542f8700410ce7b23f00ce"}97{"parentUuid":"e0fb2c21-8249-4439-8ddf-52b0085885ec","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmMURtZpFZzC5Wb1jpU","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":338,"cache_read_input_tokens":28457,"output_tokens":829,"output_tokens_details":{"thinking_tokens":15},"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":338},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6436,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmMU9H38CpZYXgS4paY","requestRef":"575b9a60-63fc-49fa-96c7-d9e819e6dbea","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1b6b4f1c-aaa1-4e45-b6eb-2965a315e5a0","timestamp":"2026-10-30T04:09:27.935Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}98{"parentUuid":"1b6b4f1c-aaa1-4e45-b6eb-2965a315e5a0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmMURtZpFZzC5Wb1jpU","type":"message","role":"assistant","content":[{"type":"text","text":"After controlling for baseline skill, one extra training hour per employee raises next-year productivity growth by about **+0.254 percentage points** (robust standard error 0.0098, 95% CI [0.234, 0.273]), so the conclusion is `positive_effect`. All deliverables are written and the final gate run passed (0 of 40 checks failed).\n\n**The unadjusted association points the other way.** Without controls, the slope is **−0.132 pp per hour** (95% CI [−0.160, −0.103]). Firms with more skilled workforces trained more (correlation 0.68) but grew much less (−4.62 pp per skill-index unit), and leaving skill out drags the slope below zero. A standard decomposition of this bias recovers the unadjusted slope exactly from the adjusted model. Adding skill also cuts the residual error from 3.86 to 1.98 pp.\n\n**Data and robustness:**\n- **Dropped rows:** 12 of the 1200 firms report negative training hours, which is impossible, so the main analysis uses 1188. Keeping them gives 0.252, almost the same.\n- **Robustness:** adding a squared skill term (0.2538) or a training × skill interaction (which is about zero) leaves the estimate essentially unchanged.\n- **Reproducibility:** no randomness is involved, and a clean re-run of `out/analysis.py` gives identical `results.json`.\n\n**Limitations:**\n- **Causal interpretation:** it holds only if skill is the sole confounder. Anything unmeasured that affects both training and growth (management quality, expected slowdowns) could shift the estimate a lot. The sign flip shows how much the answer depends on what is controlled for.\n- **Width of the interval:** the confidence interval covers sampling error only, not whether the model is right.\n- **Not done:**\n - no formal test of how strong an unobserved confounder would need to be to overturn the result;\n - no matching or weighting as an alternative to regression;\n - no test of diminishing returns to training hours.\n- **Unexplained values:** I don't know where the negative training-hour values came from.\n- **Simulated data:** the results say nothing about real training programmes.\n\nFiles are in `out/`:\n- `results.json`\n- `report.md`\n- `claims.json`\n- `analysis.py`\n- `figure1.png`\n- `table1.csv`\n- `exclusions.csv`\n- `state/` (audit, checks, phase ledger, log, gate receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":338,"cache_read_input_tokens":28457,"output_tokens":829,"output_tokens_details":{"thinking_tokens":15},"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":338},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmMU9H38CpZYXgS4paY","requestRef":"575b9a60-63fc-49fa-96c7-d9e819e6dbea","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"43a75337-390e-4762-ae02-ef3700c45bdd","timestamp":"2026-10-30T04:09:28.760Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0020","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","version":"2.1.314","gitBranch":"HEAD"}99{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"43a75337-390e-4762-ae02-ef3700c45bdd","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357"}100{"type":"cost-state","sessionId":"e6478e8c-3158-42fb-aabd-e882de7c5357","totalCostUSD":0.5137922,"totalAPIDuration":141960,"totalAPIDurationWithoutRetries":141955,"totalToolDuration":6649,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":148744,"startTime":1793333220034,"modelUsage":{"claude-opus-5-5":{"inputTokens":34,"outputTokens":16357,"thinkingTokens":613,"cacheReadInputTokens":250306,"cacheCreationInputTokens":27291,"cacheCreationEphemeral5mInputTokens":27291,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.5137922}},"hasUnknownModelCost":false}101