spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:30:53.651Z","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:30:53.657Z","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}4{"parentUuid":null,"isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":"Begin"},"uuid":"b6b89700-b910-4291-b06c-d78745963e16","timestamp":"2026-10-30T05:30:53.662Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","timestamp":"2026-10-30T05:30:53.676Z","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/RR0005\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\nSEPARATE REVIEW (additional)\n- After the gate passes, a separate reviewer session that has not seen your work in progress will examine `TASK.md` and everything under `out/` and may return a list of issues (file `out/review/review.json`). You will then be resumed once to address them: fix what is justified, explain in `out/report.md` (Limitations and open issues) what you disagree with, re-run the gate, and update `out/claims.json` and `out/state/phases.json`. The reviewer has no reference answers; its role is to challenge unsupported claims, violated information rules, unverified computations, and inconsistencies between your report and your results.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"f8da5d15-eff9-4fc1-b758-b03f310be56d","timestamp":"2026-10-30T05:30:53.676Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"53231b6c3b940cd83c6769ecfc557548c4b6a16275c4de1712e8242552d73270"}8{"parentUuid":"b6b89700-b910-4291-b06c-d78745963e16","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"70784a2d-551b-40e1-935a-cfe560c2d578","timestamp":"2026-10-30T05:30:53.667Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"70784a2d-551b-40e1-935a-cfe560c2d578","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"2f76a33a-a85c-4f84-afb3-424d65032079","timestamp":"2026-10-30T05:30:53.667Z","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/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"2f76a33a-a85c-4f84-afb3-424d65032079","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":"6c35eec5-7f18-4baf-b763-1d1be459634c","timestamp":"2026-10-30T05:30:53.668Z","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/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}12{"parentUuid":"6c35eec5-7f18-4baf-b763-1d1be459634c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsaHTQmnTJ3dYvC4aep","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":129,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":414,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsaHAJBsxDvqjcen6Qw","requestRef":"f8da5d15-eff9-4fc1-b758-b03f310be56d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0ceabfdc-6a92-41f6-91af-9d96f0f24642","timestamp":"2026-10-30T05:30:56.983Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"0ceabfdc-6a92-41f6-91af-9d96f0f24642","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsaHTQmnTJ3dYvC4aep","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016tPEPd6vCvcaGc7Zmg5Bp4","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":129,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsaHAJBsxDvqjcen6Qw","requestRef":"f8da5d15-eff9-4fc1-b758-b03f310be56d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a470b1f6-078c-4baa-9dbe-4e113b77a80a","timestamp":"2026-10-30T05:30:57.550Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"a470b1f6-078c-4baa-9dbe-4e113b77a80a","isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016tPEPd6vCvcaGc7Zmg5Bp4","type":"tool_result","content":"# F6-dev-01 — Income and life expectancy across countries: a bounded mini-project\n\n## Scientific question\nDoes the cross-country relationship between real income per capita and life expectancy (the \"Preston curve\") hold in the most recent year with usable World Bank data, and how strong is it? The estimand is the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies (one equally weighted observation per country) in the analysis year, where LE is life expectancy at birth (years) and GDPpc is GDP per capita in PPP constant 2021 international dollars, with heteroskedasticity-robust uncertainty. The task is a complete, bounded chain: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report. \"Effect\" is used here in the descriptive, associational sense: no causal claim is requested.\n\n## Inputs\n- `data/wb_indicators.csv` — observed data, World Bank World Development Indicators (retrieved 2026-10-30, CC BY 4.0; full provenance, URLs and SHA-256 in `data/README.md`). One row per entity-year, 2015–2023. Columns: `iso3`, `name`, `year`, `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international $; empty if not reported), `life_expectancy` (years; empty if not reported). The file is the API download for *all* World Bank entities, so it contains countries/economies as well as regional and income-group aggregates.\n- `data/wb_entities.csv` — World Bank entity metadata: `iso3`, `name`, `region` (the value `Aggregates` marks groupings that are not countries/economies), `income_level`, `lending_type`.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- The analysis population is countries/economies only: exclude every entity whose `region` is `Aggregates` in `wb_entities.csv`.\n- The analysis year is the most recent year (2015–2023) in which both indicators are observed for at least 150 countries/economies. Report it as `analysis_year`.\n- In the analysis year, countries/economies with either indicator missing are excluded from the estimate and counted in `n_excluded_missing`. No imputation.\n- Use the natural logarithm of GDP per capita. Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `analysis_year` | integer | year | year selected by the rule above |\n| `n_excluded_missing` | integer | countries | countries/economies present in `wb_indicators.csv` for the analysis year but dropped for a missing indicator |\n| `baseline_metric` | number | years | RMSE of the mean-only prediction of life expectancy, sqrt(mean((LE − mean LE)²)) over the analysed countries (the no-information baseline) |\n| `model_metric` | number | years | RMSE of the OLS residuals, sqrt(mean(e²)) |\n| `pearson_r` | number | — | Pearson correlation between ln(GDPpc) and LE |\n| `r_squared` | number | — | R² of the OLS regression |\n| `effect_estimate` | number | years per log-point | OLS slope β |\n| `intercept` | number | years | OLS intercept α |\n| `effect_se` | number | years per log-point | heteroskedasticity-robust standard error of β (HC0–HC3; state which in the report) |\n| `effect_ci_low`, `effect_ci_high` | number | years per log-point | 95% confidence interval for β based on `effect_se` |\n| `conclusion` | string | — | one of the codes below |\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 life expectancy against ln(GDP per capita) for the analysed countries with the fitted OLS line, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per World Bank income level present among the analysed countries, with columns `income_level`, `n_countries`, `mean_log_gdp_pc`, `mean_life_expectancy` (header row + 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 23:42 .\ndrwxr-xr-x  169 simon-pierreboucher  staff  5408 oct.  30 01:30 ..\n-rw-r--r--    1 simon-pierreboucher  staff   611 oct.  29 23:42 bundle.json\ndrwxr-xr-x    5 simon-pierreboucher  staff   160 oct.  29 23:27 data\n-rw-r--r--    1 simon-pierreboucher  staff  2284 oct.  29 23:35 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6165 oct.  29 23:35 TASK.md\ndata:\nREADME.md\nwb_entities.csv\nwb_indicators.csv","is_error":false}]},"uuid":"70dafa8d-be9e-4c90-8247-e1962ae44c4d","timestamp":"2026-10-30T05:30:57.664Z","toolUseResult":{"stdout":"# F6-dev-01 — Income and life expectancy across countries: a bounded mini-project\n\n## Scientific question\nDoes the cross-country relationship between real income per capita and life expectancy (the \"Preston curve\") hold in the most recent year with usable World Bank data, and how strong is it? The estimand is the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies (one equally weighted observation per country) in the analysis year, where LE is life expectancy at birth (years) and GDPpc is GDP per capita in PPP constant 2021 international dollars, with heteroskedasticity-robust uncertainty. The task is a complete, bounded chain: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report. \"Effect\" is used here in the descriptive, associational sense: no causal claim is requested.\n\n## Inputs\n- `data/wb_indicators.csv` — observed data, World Bank World Development Indicators (retrieved 2026-10-30, CC BY 4.0; full provenance, URLs and SHA-256 in `data/README.md`). One row per entity-year, 2015–2023. Columns: `iso3`, `name`, `year`, `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international $; empty if not reported), `life_expectancy` (years; empty if not reported). The file is the API download for *all* World Bank entities, so it contains countries/economies as well as regional and income-group aggregates.\n- `data/wb_entities.csv` — World Bank entity metadata: `iso3`, `name`, `region` (the value `Aggregates` marks groupings that are not countries/economies), `income_level`, `lending_type`.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- The analysis population is countries/economies only: exclude every entity whose `region` is `Aggregates` in `wb_entities.csv`.\n- The analysis year is the most recent year (2015–2023) in which both indicators are observed for at least 150 countries/economies. Report it as `analysis_year`.\n- In the analysis year, countries/economies with either indicator missing are excluded from the estimate and counted in `n_excluded_missing`. No imputation.\n- Use the natural logarithm of GDP per capita. Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `analysis_year` | integer | year | year selected by the rule above |\n| `n_excluded_missing` | integer | countries | countries/economies present in `wb_indicators.csv` for the analysis year but dropped for a missing indicator |\n| `baseline_metric` | number | years | RMSE of the mean-only prediction of life expectancy, sqrt(mean((LE − mean LE)²)) over the analysed countries (the no-information baseline) |\n| `model_metric` | number | years | RMSE of the OLS residuals, sqrt(mean(e²)) |\n| `pearson_r` | number | — | Pearson correlation between ln(GDPpc) and LE |\n| `r_squared` | number | — | R² of the OLS regression |\n| `effect_estimate` | number | years per log-point | OLS slope β |\n| `intercept` | number | years | OLS intercept α |\n| `effect_se` | number | years per log-point | heteroskedasticity-robust standard error of β (HC0–HC3; state which in the report) |\n| `effect_ci_low`, `effect_ci_high` | number | years per log-point | 95% confidence interval for β based on `effect_se` |\n| `conclusion` | string | — | one of the codes below |\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 life expectancy against ln(GDP per capita) for the analysed countries with the fitted OLS line, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per World Bank income level present among the analysed countries, with columns `income_level`, `n_countries`, `mean_log_gdp_pc`, `mean_life_expectancy` (header row + 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 23:42 .\ndrwxr-xr-x  169 simon-pierreboucher  staff  5408 oct.  30 01:30 ..\n-rw-r--r--    1 simon-pierreboucher  staff   611 oct.  29 23:42 bundle.json\ndrwxr-xr-x    5 simon-pierreboucher  staff   160 oct.  29 23:27 data\n-rw-r--r--    1 simon-pierreboucher  staff  2284 oct.  29 23:35 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6165 oct.  29 23:35 TASK.md\ndata:\nREADME.md\nwb_entities.csv\nwb_indicators.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a470b1f6-078c-4baa-9dbe-4e113b77a80a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}15{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"70dafa8d-be9e-4c90-8247-e1962ae44c4d","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}16{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}17{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"f88d603d138bde2469b3abe72b2b6e7dfc8b5b6eebd1aadc8cf8465f4a7784ad","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016tPEPd6vCvcaGc7Zmg5Bp4","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}18{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"bfc39c7d-c010-45ec-89a5-abdf6e1f4d8a","timestamp":"2026-10-30T05:30:57.669Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"f8da5d15-eff9-4fc1-b758-b03f310be56d","keep":2,"tail":["f88d603d138bde2469b3abe72b2b6e7dfc8b5b6eebd1aadc8cf8465f4a7784ad","7bcc1d864ba9de8116c1ad0b462013316be3a8914c6e52645223533aaf4fe0d4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"364f8624cfb51e128cfd15a83c4fd4a2add46f488843cb5433489e47761cddb3"}19{"parentUuid":"70dafa8d-be9e-4c90-8247-e1962ae44c4d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsaV6PzArYUJLCqRJDN","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RdNUqU1iaeFgAXfKpzU8R9","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json bundle.json; head -5 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data files and specs"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2644,"cache_read_input_tokens":4315,"output_tokens":131,"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":2644},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsaUpXgmUYN2ZqnYq5c","requestRef":"bfc39c7d-c010-45ec-89a5-abdf6e1f4d8a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"088f5835-5cba-40cf-9691-fd4dc7afb368","timestamp":"2026-10-30T05:30:59.411Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"088f5835-5cba-40cf-9691-fd4dc7afb368","isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01RdNUqU1iaeFgAXfKpzU8R9","type":"tool_result","content":"# Data provenance — F6-dev-01\n\nAll files are observed data from the World Bank World Development Indicators (WDI), retrieved by the task author with `curl` on 2026-10-30T03:23:28Z.\nLicense: World Bank open data, Creative Commons Attribution 4.0 (CC BY 4.0), https://datacatalog.worldbank.org/public-licenses#cc-by\n\n## `wb_indicators.csv` (2349 rows)\nLong table, one row per entity-year, years 2015–2023, built by merging two API responses on (ISO3 code, year):\n- `NY.GDP.PCAP.PP.KD` — GDP per capita, PPP (constant 2021 international $). URL: `https://api.worldbank.org/v2/country/all/indicator/NY.GDP.PCAP.PP.KD?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `742e87326d9748e0873cd996d9d4ebdf9464bec10ccd24a97d66b07e651789ec`)\n- `SP.DYN.LE00.IN` — Life expectancy at birth, total (years). URL: `https://api.worldbank.org/v2/country/all/indicator/SP.DYN.LE00.IN?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `6bb51828124409f555b5089900a507aa62a0a17523ec3608b4b51bb5c6928d04`)\n\nColumns: `iso3` (ISO-3166 alpha-3 code as returned by the API), `name` (entity name), `year` (integer), `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international dollars; empty = not reported), `life_expectancy` (years; empty = not reported).\nThe API endpoint `country/all` returns every entity in the World Bank database, i.e. countries/economies **and** regional, income-group and other aggregates. 45 records whose `countryiso3code` field was empty in the API response (a few income-group aggregates identified only by a 2-letter code) were dropped during preparation; nothing else was altered.\nSHA-256 of `wb_indicators.csv`: `6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0`\n\n## `wb_entities.csv` (296 rows)\nEntity metadata from `https://api.worldbank.org/v2/country?format=json&per_page=400` (raw response SHA-256 `c9acf3932785191a649cbc04c3056af4cf64a236e5c3b49d49be25ddb0440bce`).\nColumns: `iso3`, `name`, `region` (World Bank region; the value `Aggregates` marks entities that are regional, income or other groupings rather than countries/economies), `income_level`, `lending_type`.\nSHA-256 of `wb_entities.csv`: `06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d`\n{\n  \"task_id\": \"F6-dev-01\",\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    \"analysis_year\": {\n      \"type\": \"integer\",\n      \"nullable\": false\n    },\n    \"n_excluded_missing\": {\n      \"type\": \"integer\",\n      \"nullable\": false\n    },\n    \"baseline_metric\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"model_metric\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"pearson_r\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"r_squared\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_estimate\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"intercept\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_se\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_ci_low\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_ci_high\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"conclusion\": {\n      \"type\": \"string\",\n      \"nullable\": false\n    }\n  },\n  \"report_sections\": [\n    \"Question\",\n    \"Data and exclusions\",\n    \"Method\",\n    \"Results\",\n    \"Uncertainty\",\n    \"Limitations and open issues\"\n  ],\n  \"family_checks\": [\n    \"ci_contains_estimate\",\n    \"positive_se\",\n    \"claims_reference_existing_keys\",\n    \"phase_ledger_consistent\",\n    \"exclusion_ledger_sums\"\n  ],\n  \"ci_pairs\": [\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-dev-01\",\n  \"family\": \"F6\",\n  \"split\": \"dev\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T03:42:41.723569+00:00\",\n  \"files\": {\n    \"TASK.md\": \"6aa11fe5b23688a6084aeca7e83157ee4240169267dc7bc77d3da5e9fd8567e5\",\n    \"data/README.md\": \"76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a\",\n    \"data/wb_entities.csv\": \"06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d\",\n    \"data/wb_indicators.csv\": \"6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0\",\n    \"gate_spec.json\": \"2f6efaa4406577bd9a1133182ff2b15374cd250cad0229cf79c8e3f48ed6b3c3\"\n  }\n}==> data/wb_entities.csv <==\niso3,name,region,income_level,lending_type\nABW,Aruba,Latin America & Caribbean,High income,Not classified\nAFE,Africa Eastern and Southern,Aggregates,Aggregates,Aggregates\nAFG,Afghanistan,\"Middle East, North Africa, Afghanistan & Pakistan\",Low income,IDA\nAFR,Africa,Aggregates,Aggregates,Aggregates\n\n==> data/wb_indicators.csv <==\niso3,name,year,gdp_pc_ppp,life_expectancy\nABW,Aruba,2015,36753.404173,75.405000\nABW,Aruba,2016,36926.113069,75.540000\nABW,Aruba,2017,38213.289239,75.620000\nABW,Aruba,2018,39378.228411,75.880000\n     297 data/wb_entities.csv\n    2350 data/wb_indicators.csv\n    2647 total\n76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a  data/README.md\n06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d  data/wb_entities.csv\n6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0  data/wb_indicators.csv","is_error":false}]},"uuid":"ee410848-ca2b-4a17-9729-e7236d614801","timestamp":"2026-10-30T05:30:59.473Z","toolUseResult":{"stdout":"# Data provenance — F6-dev-01\n\nAll files are observed data from the World Bank World Development Indicators (WDI), retrieved by the task author with `curl` on 2026-10-30T03:23:28Z.\nLicense: World Bank open data, Creative Commons Attribution 4.0 (CC BY 4.0), https://datacatalog.worldbank.org/public-licenses#cc-by\n\n## `wb_indicators.csv` (2349 rows)\nLong table, one row per entity-year, years 2015–2023, built by merging two API responses on (ISO3 code, year):\n- `NY.GDP.PCAP.PP.KD` — GDP per capita, PPP (constant 2021 international $). URL: `https://api.worldbank.org/v2/country/all/indicator/NY.GDP.PCAP.PP.KD?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `742e87326d9748e0873cd996d9d4ebdf9464bec10ccd24a97d66b07e651789ec`)\n- `SP.DYN.LE00.IN` — Life expectancy at birth, total (years). URL: `https://api.worldbank.org/v2/country/all/indicator/SP.DYN.LE00.IN?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `6bb51828124409f555b5089900a507aa62a0a17523ec3608b4b51bb5c6928d04`)\n\nColumns: `iso3` (ISO-3166 alpha-3 code as returned by the API), `name` (entity name), `year` (integer), `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international dollars; empty = not reported), `life_expectancy` (years; empty = not reported).\nThe API endpoint `country/all` returns every entity in the World Bank database, i.e. countries/economies **and** regional, income-group and other aggregates. 45 records whose `countryiso3code` field was empty in the API response (a few income-group aggregates identified only by a 2-letter code) were dropped during preparation; nothing else was altered.\nSHA-256 of `wb_indicators.csv`: `6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0`\n\n## `wb_entities.csv` (296 rows)\nEntity metadata from `https://api.worldbank.org/v2/country?format=json&per_page=400` (raw response SHA-256 `c9acf3932785191a649cbc04c3056af4cf64a236e5c3b49d49be25ddb0440bce`).\nColumns: `iso3`, `name`, `region` (World Bank region; the value `Aggregates` marks entities that are regional, income or other groupings rather than countries/economies), `income_level`, `lending_type`.\nSHA-256 of `wb_entities.csv`: `06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d`\n{\n  \"task_id\": \"F6-dev-01\",\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    \"analysis_year\": {\n      \"type\": \"integer\",\n      \"nullable\": false\n    },\n    \"n_excluded_missing\": {\n      \"type\": \"integer\",\n      \"nullable\": false\n    },\n    \"baseline_metric\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"model_metric\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"pearson_r\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"r_squared\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_estimate\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"intercept\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_se\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_ci_low\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_ci_high\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"conclusion\": {\n      \"type\": \"string\",\n      \"nullable\": false\n    }\n  },\n  \"report_sections\": [\n    \"Question\",\n    \"Data and exclusions\",\n    \"Method\",\n    \"Results\",\n    \"Uncertainty\",\n    \"Limitations and open issues\"\n  ],\n  \"family_checks\": [\n    \"ci_contains_estimate\",\n    \"positive_se\",\n    \"claims_reference_existing_keys\",\n    \"phase_ledger_consistent\",\n    \"exclusion_ledger_sums\"\n  ],\n  \"ci_pairs\": [\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-dev-01\",\n  \"family\": \"F6\",\n  \"split\": \"dev\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T03:42:41.723569+00:00\",\n  \"files\": {\n    \"TASK.md\": \"6aa11fe5b23688a6084aeca7e83157ee4240169267dc7bc77d3da5e9fd8567e5\",\n    \"data/README.md\": \"76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a\",\n    \"data/wb_entities.csv\": \"06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d\",\n    \"data/wb_indicators.csv\": \"6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0\",\n    \"gate_spec.json\": \"2f6efaa4406577bd9a1133182ff2b15374cd250cad0229cf79c8e3f48ed6b3c3\"\n  }\n}==> data/wb_entities.csv <==\niso3,name,region,income_level,lending_type\nABW,Aruba,Latin America & Caribbean,High income,Not classified\nAFE,Africa Eastern and Southern,Aggregates,Aggregates,Aggregates\nAFG,Afghanistan,\"Middle East, North Africa, Afghanistan & Pakistan\",Low income,IDA\nAFR,Africa,Aggregates,Aggregates,Aggregates\n\n==> data/wb_indicators.csv <==\niso3,name,year,gdp_pc_ppp,life_expectancy\nABW,Aruba,2015,36753.404173,75.405000\nABW,Aruba,2016,36926.113069,75.540000\nABW,Aruba,2017,38213.289239,75.620000\nABW,Aruba,2018,39378.228411,75.880000\n     297 data/wb_entities.csv\n    2350 data/wb_indicators.csv\n    2647 total\n76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a  data/README.md\n06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d  data/wb_entities.csv\n6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0  data/wb_indicators.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"088f5835-5cba-40cf-9691-fd4dc7afb368","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"8876606d7e53394f9441eb741c2ad799f99bae170a4cd63ec33a868bb607c8e1","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01RdNUqU1iaeFgAXfKpzU8R9","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json bundle.json; head -5 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data files and specs"}}]}}22{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"30e072d0-0c04-46a3-87e7-9f2addc4fd2f","timestamp":"2026-10-30T05:30:59.476Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"bfc39c7d-c010-45ec-89a5-abdf6e1f4d8a","keep":4,"tail":["8876606d7e53394f9441eb741c2ad799f99bae170a4cd63ec33a868bb607c8e1","f90a7454af8c08dfed201cde685e00bf6786dacd33f97b1aa82ba1b1386cb5cc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e1a3a264f28cdca7144c6feb4d88f8513c34f22bbcb09dfc7a1f3fd6600ed900"}23{"parentUuid":"ee410848-ca2b-4a17-9729-e7236d614801","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsacoVxHfkzi4Q85Pah","type":"message","role":"assistant","content":[{"type":"text","text":"Hashes match. Now a quick audit."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2969,"cache_read_input_tokens":6959,"output_tokens":534,"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":2969},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsacVtAh8qXoYHC1PUz","requestRef":"30e072d0-0c04-46a3-87e7-9f2addc4fd2f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"41ae5ad2-4e4d-4747-bfa1-e6d7d87f8135","timestamp":"2026-10-30T05:31:00.650Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"41ae5ad2-4e4d-4747-bfa1-e6d7d87f8135","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsacoVxHfkzi4Q85Pah","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MzFiJeki8BZkhF42TNB6yy","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\ni=pd.read_csv('data/wb_indicators.csv',keep_default_na=False,na_values=['']); e=pd.read_csv('data/wb_entities.csv',keep_default_na=False,na_values=[''])\nprint(i.dtypes); print(e.dtypes); print(i.isna().sum()); print(e.isna().sum())\nprint('dup ind',i.duplicated(['iso3','year']).sum(),'dup ent',e.duplicated('iso3').sum())\nprint('not in ent',set(i.iso3)-set(e.iso3)); print(e.region.value_counts())\nprint(e[e.region.isna()|(e.region=='')])\nc=i.merge(e[['iso3','region','income_level']],on='iso3',how='left')\nc=c[c.region!='Aggregates']\nprint('countries',c.iso3.nunique())\nprint(c.groupby('year').apply(lambda d:pd.Series({'n':len(d),'both':(d.gdp_pc_ppp.notna()&d.life_expectancy.notna()).sum()})))\nprint(i.describe())\nprint(c.income_level.value_counts(dropna=False))\nprint(i.year.value_counts().sort_index())\n\"","description":"Audit data schema, missingness, year coverage"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2969,"cache_read_input_tokens":6959,"output_tokens":534,"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":2969},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsacVtAh8qXoYHC1PUz","requestRef":"30e072d0-0c04-46a3-87e7-9f2addc4fd2f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3cebd61c-d185-4774-9221-8537d66b151e","timestamp":"2026-10-30T05:31:04.430Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"3cebd61c-d185-4774-9221-8537d66b151e","isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MzFiJeki8BZkhF42TNB6yy","type":"tool_result","content":"<string>:11: FutureWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\niso3                object\nname                object\nyear                 int64\ngdp_pc_ppp         float64\nlife_expectancy    float64\ndtype: object\niso3            object\nname            object\nregion          object\nincome_level    object\nlending_type    object\ndtype: object\niso3                 0\nname                 0\nyear                 0\ngdp_pc_ppp         164\nlife_expectancy      0\ndtype: int64\niso3            0\nname            0\nregion          0\nincome_level    0\nlending_type    0\ndtype: int64\ndup ind 0 dup ent 0\nnot in ent set()\nregion\nAggregates                                           79\nEurope & Central Asia                                58\nSub-Saharan Africa                                   48\nLatin America & Caribbean                            42\nEast Asia & Pacific                                  37\nMiddle East, North Africa, Afghanistan & Pakistan    23\nSouth Asia                                            6\nNorth America                                         3\nName: count, dtype: int64\nEmpty DataFrame\nColumns: [iso3, name, region, income_level, lending_type]\nIndex: []\ncountries 217\n        n  both\nyear           \n2015  217   199\n2016  217   199\n2017  217   199\n2018  217   199\n2019  217   199\n2020  217   199\n2021  217   199\n2022  217   199\n2023  217   197\n              year     gdp_pc_ppp  life_expectancy\ncount  2349.000000    2185.000000      2349.000000\nmean   2019.000000   24483.044024        72.341773\nstd       2.582539   24511.848957         7.637494\nmin    2015.000000     992.285806        18.818000\n25%    2017.000000    6153.637902        66.940000\n50%    2019.000000   15831.584983        72.996000\n75%    2021.000000   35798.041275        77.814000\nmax    2023.000000  139541.157249        86.372000\nincome_level\nHigh income            774\nUpper middle income    531\nLower middle income    423\nLow income             225\nName: count, dtype: int64\nyear\n2015    261\n2016    261\n2017    261\n2018    261\n2019    261\n2020    261\n2021    261\n2022    261\n2023    261\nName: count, dtype: int64","is_error":false}]},"uuid":"85687fe9-9ba0-48f3-ba0c-de4c2e2a6afb","timestamp":"2026-10-30T05:31:04.763Z","toolUseResult":{"stdout":"<string>:11: FutureWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\niso3                object\nname                object\nyear                 int64\ngdp_pc_ppp         float64\nlife_expectancy    float64\ndtype: object\niso3            object\nname            object\nregion          object\nincome_level    object\nlending_type    object\ndtype: object\niso3                 0\nname                 0\nyear                 0\ngdp_pc_ppp         164\nlife_expectancy      0\ndtype: int64\niso3            0\nname            0\nregion          0\nincome_level    0\nlending_type    0\ndtype: int64\ndup ind 0 dup ent 0\nnot in ent set()\nregion\nAggregates                                           79\nEurope & Central Asia                                58\nSub-Saharan Africa                                   48\nLatin America & Caribbean                            42\nEast Asia & Pacific                                  37\nMiddle East, North Africa, Afghanistan & Pakistan    23\nSouth Asia                                            6\nNorth America                                         3\nName: count, dtype: int64\nEmpty DataFrame\nColumns: [iso3, name, region, income_level, lending_type]\nIndex: []\ncountries 217\n        n  both\nyear           \n2015  217   199\n2016  217   199\n2017  217   199\n2018  217   199\n2019  217   199\n2020  217   199\n2021  217   199\n2022  217   199\n2023  217   197\n              year     gdp_pc_ppp  life_expectancy\ncount  2349.000000    2185.000000      2349.000000\nmean   2019.000000   24483.044024        72.341773\nstd       2.582539   24511.848957         7.637494\nmin    2015.000000     992.285806        18.818000\n25%    2017.000000    6153.637902        66.940000\n50%    2019.000000   15831.584983        72.996000\n75%    2021.000000   35798.041275        77.814000\nmax    2023.000000  139541.157249        86.372000\nincome_level\nHigh income            774\nUpper middle income    531\nLower middle income    423\nLow income             225\nName: count, dtype: int64\nyear\n2015    261\n2016    261\n2017    261\n2018    261\n2019    261\n2020    261\n2021    261\n2022    261\n2023    261\nName: count, dtype: int64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3cebd61c-d185-4774-9221-8537d66b151e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"0ff75ae5f291739151d849620b74dfff62b99c67c52df63c66ec80e9ed358891","message":{"role":"assistant","content":[{"type":"text","text":"Hashes match. Now a quick audit."},{"type":"tool_use","id":"toolu_01MzFiJeki8BZkhF42TNB6yy","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\ni=pd.read_csv('data/wb_indicators.csv',keep_default_na=False,na_values=['']); e=pd.read_csv('data/wb_entities.csv',keep_default_na=False,na_values=[''])\nprint(i.dtypes); print(e.dtypes); print(i.isna().sum()); print(e.isna().sum())\nprint('dup ind',i.duplicated(['iso3','year']).sum(),'dup ent',e.duplicated('iso3').sum())\nprint('not in ent',set(i.iso3)-set(e.iso3)); print(e.region.value_counts())\nprint(e[e.region.isna()|(e.region=='')])\nc=i.merge(e[['iso3','region','income_level']],on='iso3',how='left')\nc=c[c.region!='Aggregates']\nprint('countries',c.iso3.nunique())\nprint(c.groupby('year').apply(lambda d:pd.Series({'n':len(d),'both':(d.gdp_pc_ppp.notna()&d.life_expectancy.notna()).sum()})))\nprint(i.describe())\nprint(c.income_level.value_counts(dropna=False))\nprint(i.year.value_counts().sort_index())\n\"","description":"Audit data schema, missingness, year coverage"}}]}}27{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"57ff422a-130d-4738-83e0-f694e31d7e6a","timestamp":"2026-10-30T05:31:04.766Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"30e072d0-0c04-46a3-87e7-9f2addc4fd2f","keep":6,"tail":["0ff75ae5f291739151d849620b74dfff62b99c67c52df63c66ec80e9ed358891","eacb6884facedf51d72884a18adc66ae0710e19960041d9f72b819147151955b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"667d22c9fff23594d05d13c7c2e93a41cd6c367688106560f70b8024dd5c1553"}28{"parentUuid":"85687fe9-9ba0-48f3-ba0c-de4c2e2a6afb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsb1WypZ9b41wH6yxVo","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":1348,"cache_read_input_tokens":9928,"output_tokens":730,"output_tokens_details":{"thinking_tokens":141},"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":1348},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1088,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsb18RV1vP9YVxNPFRb","requestRef":"57ff422a-130d-4738-83e0-f694e31d7e6a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e72dbfbf-f513-418e-9bd9-541168410785","timestamp":"2026-10-30T05:31:07.297Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"e72dbfbf-f513-418e-9bd9-541168410785","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsb1WypZ9b41wH6yxVo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HTRwUqs7LxozLwWxoUzikT","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\ni=pd.read_csv('data/wb_indicators.csv'); e=pd.read_csv('data/wb_entities.csv')\nc=i.merge(e,on='iso3',suffixes=('','_e')); c=c[c.region!='Aggregates']\nprint(c.sort_values('life_expectancy').head(12)[['iso3','name','year','gdp_pc_ppp','life_expectancy']])\nprint(c.sort_values('life_expectancy').tail(5)[['iso3','name','year','life_expectancy']])\nd=c[c.year==2023]; print(d[d.gdp_pc_ppp.isna()][['iso3','name','income_level']])\nprint(d.sort_values('gdp_pc_ppp').head(5)[['iso3','name','gdp_pc_ppp','life_expectancy']]);print(d.sort_values('gdp_pc_ppp').tail(5)[['iso3','name','gdp_pc_ppp','life_expectancy']])\nprint((c.name!=c.name_e).sum())\n# year-on-year jumps in LE\nc=c.sort_values(['iso3','year']); c['dle']=c.groupby('iso3').life_expectancy.diff(); print(c.loc[c.dle.abs()>5,['iso3','year','life_expectancy','dle']])\n# repeated identical values\nprint(c.groupby('iso3').life_expectancy.nunique().sort_values().head(10))\n\"","description":"Check anomalies in life expectancy and GDP"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1348,"cache_read_input_tokens":9928,"output_tokens":730,"output_tokens_details":{"thinking_tokens":141},"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":1348},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsb18RV1vP9YVxNPFRb","requestRef":"57ff422a-130d-4738-83e0-f694e31d7e6a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2dfb7d21-f82c-4103-b36a-0176ac9d5069","timestamp":"2026-10-30T05:31:11.500Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}30{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2dfb7d21-f82c-4103-b36a-0176ac9d5069","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}31{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}32{"parentUuid":"2dfb7d21-f82c-4103-b36a-0176ac9d5069","isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HTRwUqs7LxozLwWxoUzikT","type":"tool_result","content":"     iso3                      name  year   gdp_pc_ppp  life_expectancy\n313   CAF  Central African Republic  2022  1136.801711           18.818\n310   CAF  Central African Republic  2019  1145.095637           31.530\n1910  SSD               South Sudan  2017          NaN           35.351\n1909  SSD               South Sudan  2016          NaN           36.720\n1908  SSD               South Sudan  2015          NaN           39.757\n312   CAF  Central African Republic  2021  1128.552380           40.279\n308   CAF  Central African Republic  2017  1103.866093           45.231\n311   CAF  Central African Republic  2020  1136.570530           50.596\n307   CAF  Central African Republic  2016  1073.944777           50.999\n2025  TCD                      Chad  2015  2822.579299           51.320\n2026  TCD                      Chad  2016  2622.597808           51.603\n1233  LSO                   Lesotho  2015  2986.958667           51.830\n     iso3    name  year  life_expectancy\n1307  MCO  Monaco  2017           85.878\n1308  MCO  Monaco  2018           86.084\n1310  MCO  Monaco  2020           86.089\n1309  MCO  Monaco  2019           86.151\n1313  MCO  Monaco  2023           86.372\n     iso3                       name         income_level\n107   ASM             American Samoa          High income\n350   CHI            Channel Islands          High income\n458   CUB                       Cuba  Upper middle income\n629   ERI                    Eritrea           Low income\n764   GIB                  Gibraltar          High income\n845   GUM                       Guam          High income\n971   IMN                Isle of Man          High income\n1214  LIE              Liechtenstein          High income\n1295  MAF   St. Martin (French part)          High income\n1313  MCO                     Monaco          High income\n1448  MNP   Northern Mariana Islands          High income\n1520  NCL              New Caledonia          High income\n1709  PRK  Korea, Dem. People's Rep.           Low income\n1763  PYF           French Polynesia          High income\n1916  SSD                South Sudan           Low income\n2015  SYR       Syrian Arab Republic           Low income\n2249  VEN              Venezuela, RB  Lower middle income\n2258  VGB     British Virgin Islands          High income\n2267  VIR      Virgin Islands (U.S.)          High income\n2321  YEM                Yemen, Rep.           Low income\n     iso3                      name   gdp_pc_ppp  life_expectancy\n152   BDI                   Burundi  1033.009373           63.651\n314   CAF  Central African Republic  1132.676434           57.408\n1889  SOM        Somalia, Fed. Rep.  1401.647352           58.816\n1457  MOZ                Mozambique  1512.667296           63.611\n395   COD          Congo, Dem. Rep.  1559.338065           61.895\n     iso3                    name  gdp_pc_ppp  life_expectancy\n2015  SYR    Syrian Arab Republic         NaN        72.120000\n2249  VEN           Venezuela, RB         NaN        72.514000\n2258  VGB  British Virgin Islands         NaN        77.276000\n2267  VIR   Virgin Islands (U.S.)         NaN        80.519512\n2321  YEM             Yemen, Rep.         NaN        69.295000\n0\n     iso3  year  life_expectancy     dle\n25    AFG  2022           65.617   5.200\n259   BOL  2022           67.434   6.007\n304   BWA  2022           68.749   5.446\n308   CAF  2017           45.231  -5.768\n309   CAF  2018           52.297   7.066\n310   CAF  2019           31.530 -20.767\n311   CAF  2020           50.596  19.066\n312   CAF  2021           40.279 -10.317\n313   CAF  2022           18.818 -21.461\n314   CAF  2023           57.408  38.590\n599   ECU  2020           72.004  -5.282\n853   GUY  2022           69.888   5.565\n1178  LBY  2023           69.339  -5.123\n1645  PER  2022           76.834   5.238\n1736  PSE  2023           65.170 -11.492\n1911  SSD  2018           51.905  16.554\n1912  SSD  2019           58.129   6.224\niso3\nCHI    6\nBHR    8\nROU    8\nPRT    8\nKOR    8\nGRC    8\nUSA    8\nDEU    8\nSVK    8\nAUS    8\nName: life_expectancy, dtype: int64","is_error":false}]},"uuid":"051f92d3-82d6-43e4-a3f5-6b321ad29cf7","timestamp":"2026-10-30T05:31:11.785Z","toolUseResult":{"stdout":"     iso3                      name  year   gdp_pc_ppp  life_expectancy\n313   CAF  Central African Republic  2022  1136.801711           18.818\n310   CAF  Central African Republic  2019  1145.095637           31.530\n1910  SSD               South Sudan  2017          NaN           35.351\n1909  SSD               South Sudan  2016          NaN           36.720\n1908  SSD               South Sudan  2015          NaN           39.757\n312   CAF  Central African Republic  2021  1128.552380           40.279\n308   CAF  Central African Republic  2017  1103.866093           45.231\n311   CAF  Central African Republic  2020  1136.570530           50.596\n307   CAF  Central African Republic  2016  1073.944777           50.999\n2025  TCD                      Chad  2015  2822.579299           51.320\n2026  TCD                      Chad  2016  2622.597808           51.603\n1233  LSO                   Lesotho  2015  2986.958667           51.830\n     iso3    name  year  life_expectancy\n1307  MCO  Monaco  2017           85.878\n1308  MCO  Monaco  2018           86.084\n1310  MCO  Monaco  2020           86.089\n1309  MCO  Monaco  2019           86.151\n1313  MCO  Monaco  2023           86.372\n     iso3                       name         income_level\n107   ASM             American Samoa          High income\n350   CHI            Channel Islands          High income\n458   CUB                       Cuba  Upper middle income\n629   ERI                    Eritrea           Low income\n764   GIB                  Gibraltar          High income\n845   GUM                       Guam          High income\n971   IMN                Isle of Man          High income\n1214  LIE              Liechtenstein          High income\n1295  MAF   St. Martin (French part)          High income\n1313  MCO                     Monaco          High income\n1448  MNP   Northern Mariana Islands          High income\n1520  NCL              New Caledonia          High income\n1709  PRK  Korea, Dem. People's Rep.           Low income\n1763  PYF           French Polynesia          High income\n1916  SSD                South Sudan           Low income\n2015  SYR       Syrian Arab Republic           Low income\n2249  VEN              Venezuela, RB  Lower middle income\n2258  VGB     British Virgin Islands          High income\n2267  VIR      Virgin Islands (U.S.)          High income\n2321  YEM                Yemen, Rep.           Low income\n     iso3                      name   gdp_pc_ppp  life_expectancy\n152   BDI                   Burundi  1033.009373           63.651\n314   CAF  Central African Republic  1132.676434           57.408\n1889  SOM        Somalia, Fed. Rep.  1401.647352           58.816\n1457  MOZ                Mozambique  1512.667296           63.611\n395   COD          Congo, Dem. Rep.  1559.338065           61.895\n     iso3                    name  gdp_pc_ppp  life_expectancy\n2015  SYR    Syrian Arab Republic         NaN        72.120000\n2249  VEN           Venezuela, RB         NaN        72.514000\n2258  VGB  British Virgin Islands         NaN        77.276000\n2267  VIR   Virgin Islands (U.S.)         NaN        80.519512\n2321  YEM             Yemen, Rep.         NaN        69.295000\n0\n     iso3  year  life_expectancy     dle\n25    AFG  2022           65.617   5.200\n259   BOL  2022           67.434   6.007\n304   BWA  2022           68.749   5.446\n308   CAF  2017           45.231  -5.768\n309   CAF  2018           52.297   7.066\n310   CAF  2019           31.530 -20.767\n311   CAF  2020           50.596  19.066\n312   CAF  2021           40.279 -10.317\n313   CAF  2022           18.818 -21.461\n314   CAF  2023           57.408  38.590\n599   ECU  2020           72.004  -5.282\n853   GUY  2022           69.888   5.565\n1178  LBY  2023           69.339  -5.123\n1645  PER  2022           76.834   5.238\n1736  PSE  2023           65.170 -11.492\n1911  SSD  2018           51.905  16.554\n1912  SSD  2019           58.129   6.224\niso3\nCHI    6\nBHR    8\nROU    8\nPRT    8\nKOR    8\nGRC    8\nUSA    8\nDEU    8\nSVK    8\nAUS    8\nName: life_expectancy, dtype: int64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2dfb7d21-f82c-4103-b36a-0176ac9d5069","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"3cb0953f9241ea2caff531ace31cf749f4bedc52b7be4c75e2d139282ff0786d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01HTRwUqs7LxozLwWxoUzikT","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\ni=pd.read_csv('data/wb_indicators.csv'); e=pd.read_csv('data/wb_entities.csv')\nc=i.merge(e,on='iso3',suffixes=('','_e')); c=c[c.region!='Aggregates']\nprint(c.sort_values('life_expectancy').head(12)[['iso3','name','year','gdp_pc_ppp','life_expectancy']])\nprint(c.sort_values('life_expectancy').tail(5)[['iso3','name','year','life_expectancy']])\nd=c[c.year==2023]; print(d[d.gdp_pc_ppp.isna()][['iso3','name','income_level']])\nprint(d.sort_values('gdp_pc_ppp').head(5)[['iso3','name','gdp_pc_ppp','life_expectancy']]);print(d.sort_values('gdp_pc_ppp').tail(5)[['iso3','name','gdp_pc_ppp','life_expectancy']])\nprint((c.name!=c.name_e).sum())\n# year-on-year jumps in LE\nc=c.sort_values(['iso3','year']); c['dle']=c.groupby('iso3').life_expectancy.diff(); print(c.loc[c.dle.abs()>5,['iso3','year','life_expectancy','dle']])\n# repeated identical values\nprint(c.groupby('iso3').life_expectancy.nunique().sort_values().head(10))\n\"","description":"Check anomalies in life expectancy and GDP"}}]}}34{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"87fa8310-248d-40de-baaa-5c9b8e035e42","timestamp":"2026-10-30T05:31:11.789Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"57ff422a-130d-4738-83e0-f694e31d7e6a","keep":8,"tail":["3cb0953f9241ea2caff531ace31cf749f4bedc52b7be4c75e2d139282ff0786d","c2bf31dcbe99c013b04343b50f4700e4eb7976a0c8f716b694d2307bba1565fb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"19276471160b848dc9f55d80d94e40d4f7a63c19126e25110bb126e3f8114d3f"}35{"parentUuid":"051f92d3-82d6-43e4-a3f5-6b321ad29cf7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsbXSJeNsAomAsZepoy","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":2277,"cache_read_input_tokens":11276,"output_tokens":1566,"output_tokens_details":{"thinking_tokens":292},"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":2277},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2773,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsbXAh3f9uNggLFAM2K","requestRef":"87fa8310-248d-40de-baaa-5c9b8e035e42","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"65fd8006-6b44-459e-b9e0-4966e563522d","timestamp":"2026-10-30T05:31:15.892Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005/out/state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"65fd8006-6b44-459e-b9e0-4966e563522d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsbXSJeNsAomAsZepoy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SyJEjJEm1htr3Lsi6H6hjS","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — F6-dev-01\n\n**Question.** Does the cross-country Preston curve (life expectancy rising with log income) hold in the most recent year with usable WDI data, and how strong is it?\n\n**Estimand.** β in the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies (equal weights, one obs per country) in the analysis year. LE = life expectancy at birth (years); GDPpc = GDP per capita PPP, constant 2021 intl $. β is a descriptive best-linear-predictor slope (years per log-point), meaningful without causal assumptions; inference via heteroskedasticity-robust SE treats countries as independent draws (the \"population\" is essentially the full set of countries, so the SE is a superpopulation/model-based notion). Also: α, Pearson r, R², RMSE of mean-only baseline vs OLS residual RMSE.\n\n**Outputs.** out/results.json with keys analysis_year, n_excluded_missing, baseline_metric, model_metric, pearson_r, r_squared, effect_estimate, intercept, effect_se, effect_ci_low, effect_ci_high, conclusion (positive_effect/negative_effect/no_detectable_effect/premise_invalid), task_id (\"F6-dev-01\"), feasibility, feasibility_reason, data_issues [{issue,handling}], n_input_rows {file:int}, n_analysed, random_seed. Also out/figure1.png (scatter + OLS line), out/table1.csv (income_level, n_countries, mean_log_gdp_pc, mean_life_expectancy), out/report.md (six sections in order), out/analysis.py (Agg, deterministic, data/ only), out/claims.json, plus exclusions.csv and state files.\n\n**Information rules.** Exclude region==\"Aggregates\". Analysis year = latest year 2015–2023 with both indicators observed for ≥150 countries/economies. Countries with a missing indicator in that year are dropped and counted (n_excluded_missing); no imputation. Natural log. Only the listed files.\n\n**Invalidity / impossibility.** No year reaching 150 complete countries; inability to identify aggregates; non-positive GDP (log undefined); duplicated entity-years; data not matching provenance hashes. Any of these would make the estimand inestimable or contaminated (→ premise_invalid / null values).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\",\"data hashes match bundle.json/README\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30: P0 passed (contract written, hashes verified).\" > 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":2277,"cache_read_input_tokens":11276,"output_tokens":1566,"output_tokens_details":{"thinking_tokens":292},"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":2277},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsbXAh3f9uNggLFAM2K","requestRef":"87fa8310-248d-40de-baaa-5c9b8e035e42","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2eb0c17f-8dc8-46e3-84a2-71c82c1b1eab","timestamp":"2026-10-30T05:31:25.449Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005/out/state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"2eb0c17f-8dc8-46e3-84a2-71c82c1b1eab","isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SyJEjJEm1htr3Lsi6H6hjS","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"661dfd0e-1f4b-4953-a65d-a5f0c7e4cd75","timestamp":"2026-10-30T05:31:25.499Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2eb0c17f-8dc8-46e3-84a2-71c82c1b1eab","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005/out/state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}38{"parentUuid":"661dfd0e-1f4b-4953-a65d-a5f0c7e4cd75","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsbXSJeNsAomAsZepoy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01P13YvMsaRwfD7JRjUxVS11","name":"Bash","input":{"command":"cat ~/wp29/gates/pgar_gate.py | head -400 | grep -n -i -E \"exclusion|phases|receipt|status|claims\" | head -60","description":"Inspect gate expectations"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2277,"cache_read_input_tokens":11276,"output_tokens":1566,"output_tokens_details":{"thinking_tokens":292},"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":2277},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsbXAh3f9uNggLFAM2K","requestRef":"87fa8310-248d-40de-baaa-5c9b8e035e42","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8fc65670-a028-4b19-96f2-e67405c803eb","timestamp":"2026-10-30T05:31:26.281Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005/out/state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}39{"parentUuid":"8fc65670-a028-4b19-96f2-e67405c803eb","isSidechain":false,"promptId":"ff5c8311-b853-4900-a265-437bd4edc24f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01P13YvMsaRwfD7JRjUxVS11","type":"tool_result","content":"7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n106:    # 4. claims\n107:    claims, cerr = _load_json(os.path.join(ws, \"out\", \"claims.json\"))\n108:    if \"claims_reference_existing_keys\" in fam or os.path.exists(os.path.join(ws, \"out\", \"claims.json\")):\n109:        if not isinstance(claims, list) or not claims:\n110:            add(\"claims_json\", False, f\"out/claims.json {cerr or 'must be a non-empty list'}\")\n113:            for i, c in enumerate(claims):\n114:                if not isinstance(c, dict) or not all(k in c for k in (\"id\", \"text\", \"results_keys\", \"status\")):\n116:                if c[\"status\"] not in (\"supported\", \"unsupported\", \"not_evaluated\"):\n117:                    bad.append(f\"{c.get('id')}: bad status {c['status']!r}\")\n121:            add(\"claims_json\", not bad, \"; \".join(bad) if bad else f\"{len(claims)} claims, all keys resolve\")\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n131:                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n132:                    bad.append(f\"{pid}: invalid status\"); continue\n133:                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n135:            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n137:                bad.append(f\"phases not terminal: {not_done}\")\n139:    # 6. exclusion ledger\n140:    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n141:    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n153:            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n155:            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n215:    receipt = {\"gate_version\": GATE_VERSION, \"workspace\": ws, \"utc\": datetime.datetime.now(datetime.timezone.utc).isoformat(),\n218:        d = os.path.join(ws, \"out\", \"state\", \"gate_receipts\"); os.makedirs(d, exist_ok=True)\n221:            json.dump(receipt, fh, indent=1)\n222:        receipt[\"receipt_path\"] = path\n223:        receipt[\"receipt_sha256\"] = hashlib.sha256(open(path, \"rb\").read()).hexdigest()\n225:        receipt[\"receipt_path\"] = None; receipt[\"receipt_error\"] = str(e)\n226:    return receipt\n245:        print(f\"receipt: {r.get('receipt_path')}\")","is_error":false}]},"uuid":"15a805bf-bb98-4c26-a61d-a087c4797e33","timestamp":"2026-10-30T05:31:26.325Z","toolUseResult":{"stdout":"7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n106:    # 4. claims\n107:    claims, cerr = _load_json(os.path.join(ws, \"out\", \"claims.json\"))\n108:    if \"claims_reference_existing_keys\" in fam or os.path.exists(os.path.join(ws, \"out\", \"claims.json\")):\n109:        if not isinstance(claims, list) or not claims:\n110:            add(\"claims_json\", False, f\"out/claims.json {cerr or 'must be a non-empty list'}\")\n113:            for i, c in enumerate(claims):\n114:                if not isinstance(c, dict) or not all(k in c for k in (\"id\", \"text\", \"results_keys\", \"status\")):\n116:                if c[\"status\"] not in (\"supported\", \"unsupported\", \"not_evaluated\"):\n117:                    bad.append(f\"{c.get('id')}: bad status {c['status']!r}\")\n121:            add(\"claims_json\", not bad, \"; \".join(bad) if bad else f\"{len(claims)} claims, all keys resolve\")\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n131:                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n132:                    bad.append(f\"{pid}: invalid status\"); continue\n133:                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n135:            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n137:                bad.append(f\"phases not terminal: {not_done}\")\n139:    # 6. exclusion ledger\n140:    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n141:    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n153:            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n155:            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n215:    receipt = {\"gate_version\": GATE_VERSION, \"workspace\": ws, \"utc\": datetime.datetime.now(datetime.timezone.utc).isoformat(),\n218:        d = os.path.join(ws, \"out\", \"state\", \"gate_receipts\"); os.makedirs(d, exist_ok=True)\n221:            json.dump(receipt, fh, indent=1)\n222:        receipt[\"receipt_path\"] = path\n223:        receipt[\"receipt_sha256\"] = hashlib.sha256(open(path, \"rb\").read()).hexdigest()\n225:        receipt[\"receipt_path\"] = None; receipt[\"receipt_error\"] = str(e)\n226:    return receipt\n245:        print(f\"receipt: {r.get('receipt_path')}\")","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8fc65670-a028-4b19-96f2-e67405c803eb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005/out/state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}40{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"d00cf2bbadec7d69dda80c4f5d565671e75f7aadfa6e46533d955c651839e901","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSkQsKEAgTGAI4AUIIdGhpbmtpbmcSDCekvxSEHezpOtYBRxoMHpj2vYZB1lHAxCjPIjBk95m+T8u1DWg9vBI38Egue16e54QjsGc3gUwJCiHFPEOIykyXXSTV56/ksSHbkYwqrgqg1E2UoiO/vpYfuX4Wp0Rh+UCOveevsNNIDu7caaBKCT50jtDdXVZFOtdejbcgtpRLnyHLkqLgpxvwlhOoYPDvzKA2dxd199rTrLbu0nlAcUAdFs/0ABBng3jnEzvUajBtVm7lmGfZXWctQvMWeTX98YRgOczf0zcwPHBIwLSAhq2m1oR/lu7lQD/7tC1cbaiWBBJ5EJyhxEP+9hPexyDvnI5FqQFmclpQ1aOg9lSqlcnZFvDl2E1M/TiyJIjdkaRuWby0Jb/N2ZEb4Majipm1RP898OZJ7XUD3jIXlSSh89ceA6g58NU7Fegji1ihAYE728QLIVOyGOueqR+/V8d6jEKPI9ey/G531tehfcmDnj1HTyfYBmisTeM7TvIInLvDt6gpVyu6+Ji9XTptCKjhci0lmkRpOMAeH5xP/Pfg6A5wsYwLbOWe7kxOM7B0HwMcWtIo9jVmd/WrZ4llx57v62MNAsKmkMc2ZZVceJebBtKcboWG+VnWaZOY9l40/ydL3HJXp3hkkj1FUMR+FlSUlTP2UAd0eDBkrMipFuOLEfKtroWa+bt+EzwfL98/WnLoDtvWvkqO8+6TdyKHeBJMTLDawZjrqZYbFf5PSbbJIaJ2E7WznWTKwZrNGikip5k5QAypfnrPWY0vllDus/chfSxCtn1RIlfR8MTtQZwN6nY/PNFPdcxkp1aDGrg2lsoqPQina4yUfoSpTid6sircenWkJ/7x06tXQ1fDQpqgGAqdsYX71xsvxOBdl8wZqsCANy+oBGkfSMBItz73LBszlYM/22ROWJdJb91dKjrO0MOEateXiZpbZ0prmxMIkQ9IBieE7e6PzBkAMdZ8TPEU/G30AloFFgKigFr596Ga9WNjB2FxJF1qxIJYYHBPdSXSG3I73ZiXW7dt1agNyOKWXyVhMA/b1LhNfbxqycnduyQb4DKcKcmxNirPzRp+pm33GqaFp2YBj0qlJ02LrGERtUuKTMHBMZu7mCgp0Qwb6xgd3MLhbI/sZ3z66d1+re+LH9cF9YYMpidD+G5SvyyNsUokYLvd1pi+jjfWUbyJZgpNtIy8TyQ2NQqgN7Uh1LHhiYABKmy1WaHMYg56LKN91GlPsLphsXoSQr6u9Z309+ZXqj9bDONRULlCJsbcuBGtdmnwUoeO5Hrr1jfDY7giG1OzrzlMGB3zji8d0GESnJKAuoiiqutzEAQylZrKLfWCVDW7SRZhF26jskdnjd1nOyylsEj5QqDPJ8CRDKm+owoQXNoWeeGG65RRc6t9fRZIwRc9eQ4COeVyFqbByoHhGATF3RwXy3aPUfpEweyHF1GHOD8WNIR373NTDn5W25ulesoUe6is9DtNaEJPHVxTKaE/yxOFEM9SAj0msJbeugOYCDZ4IrVG4jtZNYBJ2Y+MtKo0IrhXgOzol0OSLiHzTQ1DCjCUKEAnorm1VS0tiKDyItxgp/rSAttI8xR76AzjIZprBOOOSFnkZ5YofbHYNICqPaEdUuqsTe1BsPqS+MgW0RB5SoY3OC/9nEdCMAXzaJReEvKAxHZXLWHsaIyJHGRCB5nC6zi13R4d2dCNJM0M0Q8zfhVX4nCVB60dKJ0tw9inEdUohO4cjEptIQe5b3UYTppZHmWxxDJ4Hk7x8NmUUBqClBCbusEGcoITSVsK+94Qao50mpjXcTStBM4tllSyevhNBsi1LkMCHOctEQ9PpodgbYF43NTkuvojNLGjO2fn/FZmgRdUSCf0qEOZJJrfw7jdnhyjtwko9ZQYAQ=="},{"type":"tool_use","id":"toolu_01SyJEjJEm1htr3Lsi6H6hjS","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — F6-dev-01\n\n**Question.** Does the cross-country Preston curve (life expectancy rising with log income) hold in the most recent year with usable WDI data, and how strong is it?\n\n**Estimand.** β in the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies (equal weights, one obs per country) in the analysis year. LE = life expectancy at birth (years); GDPpc = GDP per capita PPP, constant 2021 intl $. β is a descriptive best-linear-predictor slope (years per log-point), meaningful without causal assumptions; inference via heteroskedasticity-robust SE treats countries as independent draws (the \"population\" is essentially the full set of countries, so the SE is a superpopulation/model-based notion). Also: α, Pearson r, R², RMSE of mean-only baseline vs OLS residual RMSE.\n\n**Outputs.** out/results.json with keys analysis_year, n_excluded_missing, baseline_metric, model_metric, pearson_r, r_squared, effect_estimate, intercept, effect_se, effect_ci_low, effect_ci_high, conclusion (positive_effect/negative_effect/no_detectable_effect/premise_invalid), task_id (\"F6-dev-01\"), feasibility, feasibility_reason, data_issues [{issue,handling}], n_input_rows {file:int}, n_analysed, random_seed. Also out/figure1.png (scatter + OLS line), out/table1.csv (income_level, n_countries, mean_log_gdp_pc, mean_life_expectancy), out/report.md (six sections in order), out/analysis.py (Agg, deterministic, data/ only), out/claims.json, plus exclusions.csv and state files.\n\n**Information rules.** Exclude region==\"Aggregates\". Analysis year = latest year 2015–2023 with both indicators observed for ≥150 countries/economies. Countries with a missing indicator in that year are dropped and counted (n_excluded_missing); no imputation. Natural log. Only the listed files.\n\n**Invalidity / impossibility.** No year reaching 150 complete countries; inability to identify aggregates; non-positive GDP (log undefined); duplicated entity-years; data not matching provenance hashes. Any of these would make the estimand inestimable or contaminated (→ premise_invalid / null values).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\",\"data hashes match bundle.json/README\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\necho \"- 2026-10-30: P0 passed (contract written, hashes verified).\" > log.md","description":"Write contract, phase ledger, log"}},{"type":"tool_use","id":"toolu_01P13YvMsaRwfD7JRjUxVS11","name":"Bash","input":{"command":"cat ~/wp29/gates/pgar_gate.py | head -400 | grep -n -i -E \"exclusion|phases|receipt|status|claims\" | head -60","description":"Inspect gate expectations"}}]}}41{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"f2481c257ffac8889fdc5b0b7ffc2ee6e9f9ec99b1d93624e762c47d81f43d49","message":{"role":"user","content":[{"tool_use_id":"toolu_01SyJEjJEm1htr3Lsi6H6hjS","type":"tool_result","content":"(Bash completed with no output)","is_error":false},{"tool_use_id":"toolu_01P13YvMsaRwfD7JRjUxVS11","type":"tool_result","content":"7:Writes a receipt to <workspace_dir>/out/state/gate_receipts/<utc>.json and exits 0 if passed, 1 otherwise.\n106:    # 4. claims\n107:    claims, cerr = _load_json(os.path.join(ws, \"out\", \"claims.json\"))\n108:    if \"claims_reference_existing_keys\" in fam or os.path.exists(os.path.join(ws, \"out\", \"claims.json\")):\n109:        if not isinstance(claims, list) or not claims:\n110:            add(\"claims_json\", False, f\"out/claims.json {cerr or 'must be a non-empty list'}\")\n113:            for i, c in enumerate(claims):\n114:                if not isinstance(c, dict) or not all(k in c for k in (\"id\", \"text\", \"results_keys\", \"status\")):\n116:                if c[\"status\"] not in (\"supported\", \"unsupported\", \"not_evaluated\"):\n117:                    bad.append(f\"{c.get('id')}: bad status {c['status']!r}\")\n121:            add(\"claims_json\", not bad, \"; \".join(bad) if bad else f\"{len(claims)} claims, all keys resolve\")\n123:    pl_path = os.path.join(ws, \"out\", \"state\", \"phases.json\")\n127:            add(\"phase_ledger\", False, f\"phases.json {perr or 'not an object'}\")\n131:                if not isinstance(st, dict) or st.get(\"status\") not in (\"pending\", \"running\", \"passed\", \"failed\", \"blocked\", \"stale\", \"skipped_optional\"):\n132:                    bad.append(f\"{pid}: invalid status\"); continue\n133:                if st.get(\"status\") == \"passed\" and not st.get(\"checks\"):\n135:            not_done = [pid for pid, st in pl.items() if isinstance(st, dict) and st.get(\"status\") not in (\"passed\", \"skipped_optional\", \"blocked\")]\n137:                bad.append(f\"phases not terminal: {not_done}\")\n139:    # 6. exclusion ledger\n140:    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n141:    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n153:            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n155:            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n215:    receipt = {\"gate_version\": GATE_VERSION, \"workspace\": ws, \"utc\": datetime.datetime.now(datetime.timezone.utc).isoformat(),\n218:        d = os.path.join(ws, \"out\", \"state\", \"gate_receipts\"); os.makedirs(d, exist_ok=True)\n221:            json.dump(receipt, fh, indent=1)\n222:        receipt[\"receipt_path\"] = path\n223:        receipt[\"receipt_sha256\"] = hashlib.sha256(open(path, \"rb\").read()).hexdigest()\n225:        receipt[\"receipt_path\"] = None; receipt[\"receipt_error\"] = str(e)\n226:    return receipt\n245:        print(f\"receipt: {r.get('receipt_path')}\")","is_error":false}]}}42{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"075bfb47-672e-41b3-9bf3-5e35c6ea2db5","timestamp":"2026-10-30T05:31:26.329Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"87fa8310-248d-40de-baaa-5c9b8e035e42","keep":10,"tail":["d00cf2bbadec7d69dda80c4f5d565671e75f7aadfa6e46533d955c651839e901","f2481c257ffac8889fdc5b0b7ffc2ee6e9f9ec99b1d93624e762c47d81f43d49"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"0181907876768c5ab02c97106866ec4435f494c7aa32f160f9840060889c0f1b"}43{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"15a805bf-bb98-4c26-a61d-a087c4797e33","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}44{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}45{"type":"cost-state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","totalCostUSD":0.1288894,"totalAPIDuration":31851,"totalAPIDurationWithoutRetries":31846,"totalToolDuration":841,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":32849,"startTime":1793338253501,"modelUsage":{"claude-opus-5-5":{"inputTokens":12,"outputTokens":3090,"thinkingTokens":456,"cacheReadInputTokens":33982,"cacheCreationInputTokens":12049,"cacheCreationEphemeral5mInputTokens":12049,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.1288894}},"hasUnknownModelCost":false}46{"type":"tools-used","tools":["Bash"],"sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}47{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:31:27.754Z","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","content":"Your"}48{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:31:27.755Z","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}49{"parentUuid":"15a805bf-bb98-4c26-a61d-a087c4797e33","isSidechain":false,"type":"assistant","uuid":"037b55e6-c467-4935-b9db-7b222f4f3c17","timestamp":"2026-10-30T05:31:27.738Z","message":{"diagnostics":null,"id":"d557ad08-3d85-4090-b256-6838f663a3d0","container":null,"model":"<synthetic>","role":"assistant","stop_details":null,"stop_reason":"stop_sequence","stop_sequence":"","type":"message","usage":{"output_tokens_details":null,"input_tokens":0,"output_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":null,"cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":null,"iterations":null,"speed":null,"fallback_credit":null},"content":[{"type":"text","text":"No response requested."}],"context_management":null},"isApiErrorMessage":false,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"d7592816a22ce1cecc3749565908ab41138ebded503e449dc1add192fb8dcca3","message":{"role":"user","content":[{"type":"text","text":"Your"}]}}51{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"b3356c63-fc0a-43c8-89e2-1bb3a3bdf2e6","timestamp":"2026-10-30T05:31:27.776Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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","f88d603d138bde2469b3abe72b2b6e7dfc8b5b6eebd1aadc8cf8465f4a7784ad","7bcc1d864ba9de8116c1ad0b462013316be3a8914c6e52645223533aaf4fe0d4","8876606d7e53394f9441eb741c2ad799f99bae170a4cd63ec33a868bb607c8e1","f90a7454af8c08dfed201cde685e00bf6786dacd33f97b1aa82ba1b1386cb5cc","0ff75ae5f291739151d849620b74dfff62b99c67c52df63c66ec80e9ed358891","eacb6884facedf51d72884a18adc66ae0710e19960041d9f72b819147151955b","3cb0953f9241ea2caff531ace31cf749f4bedc52b7be4c75e2d139282ff0786d","c2bf31dcbe99c013b04343b50f4700e4eb7976a0c8f716b694d2307bba1565fb","d00cf2bbadec7d69dda80c4f5d565671e75f7aadfa6e46533d955c651839e901","f2481c257ffac8889fdc5b0b7ffc2ee6e9f9ec99b1d93624e762c47d81f43d49","c5d33e5a837fcfbd74c4136d69de118287b5d28538b032c28ee879f5747d6cea","d7592816a22ce1cecc3749565908ab41138ebded503e449dc1add192fb8dcca3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"13eaddd65e27a98f3b6365483cfcb4cdcd88f91e347e7c40062f89b8ecff44d2"}52{"parentUuid":"037b55e6-c467-4935-b9db-7b222f4f3c17","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":"Your"},"uuid":"91ee5450-a6f7-478b-9fbb-a153a983e07c","timestamp":"2026-10-30T05:31:27.760Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":2},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"91ee5450-a6f7-478b-9fbb-a153a983e07c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXscjwB4yPEeYSt6HfW7","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSrQYKEAgTGAI4AUIIdGhpbmtpbmcSDEN05CDAq+0CO2BRxxoMv1rKiZZCQj8X3moKIjBRoBYdwGvnyWj4V29Gtx0yeBek9nRkQhBrEllyoNog1lLxbWaZ2oImiWtApAiWeAkqygVs6z7aT+jrvHLnryEeQjnTe8Tc4J2t1cuyVFfZKuYRZH+0CTDEp+4cENcuGUXJlu6SnBUvru+ZpgJyO7GXIvbnx1yZIMnIaGtCRSh1WhaDnb4YiTnWnGc8aR+0g1d4yCY1fCva8rhtRCtT+cVh8thFtsO2Q6Frtrkn7lqP99OnIKp9j1x1wRjmI1hqFnm7Qa59C0S44YAUndeVVE343HDetTZKN2aDyarSl+zgbpg9Zw9IX3JhgJvMRwtygOPxqIyJzvLwFrJRzN2Vds632EGb8pi6MkBZHWf4CVEhGrY+3fkgNFn7zvZtqcJbNnlI5BuAya7FNtcOhHjRw0aHgKGdo6dn5nd7u/Li8KAUC5lJDYRvP34pr5ZorYAoKicpRZvgchgVntnhAIoWXJr40ZUH8/p4Cx0ig7GjVsI5KvhB+FmOLl7yWLaavuoSU9mmVaUmmQ99oOPT2ejwWCQu4utKQoKb3HDRmkUe6b2UvSFrDVVN4we9il+1F1MSS+HrhcU6TEH/XFjIHDOttp9MwhpCgjiAAETuiKJvRjNEaz0ZS9naN0NdqKznpqVpBtUR0MfiCS8bv8CvQ6PyKRzADMM/iDmZmv6xFE6+FhNwf2XCma8u6u8TI+JlwQLQwGqJ9JgwRJc7+1w4L4G+R0Zim1nviURQ6aBLw08lzHu8D6y86+lX6HLqr0+cW5QBXN2FAb8rgqyFRpbCzYn0ff+ivKTn9Ael/gYMqDs2tkhQ5ltp74qDQa1Fpwkl4jUZulrAxInQJWKpxQzHbrki5ErstgfMg0PKtVaKY3FE8jX/Gaa4QZe+HVySBlpIs5nmR8K/9rkSpYaRynBxyCSzmWpa1IukUDs3DxjGz+PxEIkpqAwYu3dxzMtzMlW/+yvlib7gwNAJwuhzKfKRt6o9Kaj7NusRS0P6lQK6taYMt/MyQgD3XMvOGfiGf01q25EYAQ=="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2693,"cache_read_input_tokens":13553,"output_tokens":124,"output_tokens_details":{"thinking_tokens":20},"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":2693},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":541,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXscjeJiHPufQvBqYp6b","requestRef":"b3356c63-fc0a-43c8-89e2-1bb3a3bdf2e6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aa300170-141f-41df-94b6-a47d82589f2a","timestamp":"2026-10-30T05:31:29.829Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"aa300170-141f-41df-94b6-a47d82589f2a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXscjwB4yPEeYSt6HfW7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014n38FJENvpMQ3yGDRRpJRY","name":"Bash","input":{"command":"sed -n 139,156p ~/wp29/gates/pgar_gate.py","description":"Read exclusion ledger check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2693,"cache_read_input_tokens":13553,"output_tokens":124,"output_tokens_details":{"thinking_tokens":20},"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":2693},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXscjeJiHPufQvBqYp6b","requestRef":"b3356c63-fc0a-43c8-89e2-1bb3a3bdf2e6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d1e9fd45-b0f1-43da-a4ac-268657b84a70","timestamp":"2026-10-30T05:31:30.438Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}55{"parentUuid":"d1e9fd45-b0f1-43da-a4ac-268657b84a70","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014n38FJENvpMQ3yGDRRpJRY","type":"tool_result","content":"    # 6. exclusion ledger\n    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n        try:\n            rows = list(csv.DictReader(open(ex_path, newline=\"\")))\n            bad = []\n            prev_after = None\n            for i, r in enumerate(rows):\n                nb, na, nr = int(float(r[\"n_before\"])), int(float(r[\"n_after\"])), int(float(r[\"n_removed\"]))\n                if nb - nr != na:\n                    bad.append(f\"row {i}: n_before - n_removed != n_after\")\n                if prev_after is not None and nb != prev_after:\n                    bad.append(f\"row {i}: n_before != previous n_after\")\n                prev_after = na\n            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n        except Exception as e:  # noqa: BLE001\n            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n    # 7. numeric sanity checks","is_error":false}]},"uuid":"5ee988d6-7dec-41c1-8d93-9340f7d64888","timestamp":"2026-10-30T05:31:30.546Z","toolUseResult":{"stdout":"    # 6. exclusion ledger\n    ex_path = os.path.join(ws, \"out\", \"exclusions.csv\")\n    if \"exclusion_ledger_sums\" in fam and os.path.exists(ex_path):\n        try:\n            rows = list(csv.DictReader(open(ex_path, newline=\"\")))\n            bad = []\n            prev_after = None\n            for i, r in enumerate(rows):\n                nb, na, nr = int(float(r[\"n_before\"])), int(float(r[\"n_after\"])), int(float(r[\"n_removed\"]))\n                if nb - nr != na:\n                    bad.append(f\"row {i}: n_before - n_removed != n_after\")\n                if prev_after is not None and nb != prev_after:\n                    bad.append(f\"row {i}: n_before != previous n_after\")\n                prev_after = na\n            add(\"exclusion_ledger\", not bad, \"; \".join(bad) if bad else f\"{len(rows)} steps consistent\")\n        except Exception as e:  # noqa: BLE001\n            add(\"exclusion_ledger\", False, f\"unreadable: {e}\")\n    # 7. numeric sanity checks","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d1e9fd45-b0f1-43da-a4ac-268657b84a70","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}56{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"522924e7d362ee88603de836677c4ad304cd7f5699961832050a7ea5f1bbdf87","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_014n38FJENvpMQ3yGDRRpJRY","name":"Bash","input":{"command":"sed -n 139,156p ~/wp29/gates/pgar_gate.py","description":"Read exclusion ledger check"}}]}}57{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"972caabb-ac1a-4d2c-918a-c29d51e64e0a","timestamp":"2026-10-30T05:31:30.551Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"b3356c63-fc0a-43c8-89e2-1bb3a3bdf2e6","keep":14,"tail":["522924e7d362ee88603de836677c4ad304cd7f5699961832050a7ea5f1bbdf87","1af9f471dbdd76f6fbcc0b9bac2153f34761c4548b2c39bdd5ba04381d78c09d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a7b6499e76ea6f8f78bd766f365767f26c3b42cff019181de9f6a3158e471c40"}58{"parentUuid":"5ee988d6-7dec-41c1-8d93-9340f7d64888","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXscue5WKJANjAGUtDw1","type":"message","role":"assistant","content":[{"type":"text","text":"Now the data audit and the analysis script."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":505,"cache_read_input_tokens":16246,"output_tokens":1248,"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":505},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXscuNhADWwJVNNpDm4h","requestRef":"972caabb-ac1a-4d2c-918a-c29d51e64e0a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"50ca6bed-1100-40cb-9752-98112179dd13","timestamp":"2026-10-30T05:31:35.053Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}59{"parentUuid":"50ca6bed-1100-40cb-9752-98112179dd13","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXscue5WKJANjAGUtDw1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01D27Ev2PxvaxkiAA5sr6ev7","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\n| file | SHA-256 | data rows | cols |\n|---|---|---|---|\n| data/wb_indicators.csv | 6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0 (matches README & bundle.json) | 2349 | 5 |\n| data/wb_entities.csv | 06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d (matches) | 296 | 5 |\n| data/README.md | 76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a (matches bundle.json) | – | – |\n\n**wb_indicators.csv**: iso3 (str), name (str), year (int, 2015–2023, 261 entities × 9 years, balanced), gdp_pc_ppp (float, constant 2021 PPP $, 164 missing, range 992–139,541, all > 0), life_expectancy (float, years, 0 missing, range 18.8–86.4). No duplicated (iso3, year). Every iso3 appears in wb_entities.csv; names agree.\n\n**wb_entities.csv**: 296 entities, no duplicates, no blanks; 79 have region == \"Aggregates\" (217 countries/economies). Note: \"NA\" (Namibia's ISO2) is not an issue because codes are ISO3; pandas default NA parsing is nevertheless disabled for string columns in the script for safety (keep_default_na=False) — no entity has a code/name that would be mis-parsed anyway.\n\n**Countries/economies, both indicators observed, by year**: 199 in each year 2015–2022, 197 in 2023. Rule (≥150, latest) ⇒ analysis year **2023**. In 2023, 217 countries present, 20 lack GDP (ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM); 0 lack LE ⇒ n_excluded_missing = 20, n_analysed = 197.\n\n**Anomalies**\n- Central African Republic LE is erratic across years (2019 31.5, 2021 40.3, 2022 18.8, 2023 57.4). The 2023 value (57.4) is within the plausible range for CAF and is kept; earlier years are not used. Flagged in data_issues; a leave-out sensitivity is not required, but CAF's leverage is noted.\n- West Bank & Gaza (PSE) LE drops 11.5 years in 2023 (conflict); kept as reported.\n- Missing GDP is non-random: mostly small high-income territories and conflict/sanctioned states (possible selection bias). Handled by exclusion per rules, discussed in report.\n- 2023 LE values for some countries may be WB estimates/projections rather than vital-registration measurements (not verifiable from the files).\n\n**Information-availability**: no input violates the rules; aggregates are removed via region == \"Aggregates\". No other files used.\nEOF\necho \"- 2026-10-30: P1 audit written; analysis year 2023 (197 complete, 20 missing GDP). Decision: HC3 robust SE, t(n-2) CI.\" >> out/state/log.md","description":"Write data audit"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":505,"cache_read_input_tokens":16246,"output_tokens":1248,"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":505},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXscuNhADWwJVNNpDm4h","requestRef":"972caabb-ac1a-4d2c-918a-c29d51e64e0a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"08410d56-ad79-4222-82aa-209c29b3165f","timestamp":"2026-10-30T05:31:47.198Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}60{"parentUuid":"08410d56-ad79-4222-82aa-209c29b3165f","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01D27Ev2PxvaxkiAA5sr6ev7","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"e667a468-c132-48a4-8023-51d8358d3941","timestamp":"2026-10-30T05:31:47.252Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"08410d56-ad79-4222-82aa-209c29b3165f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}61{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"f779db248191c6a3712478338d304a0c1532ffd2fdedeae94c16386ce8fe0206","message":{"role":"assistant","content":[{"type":"text","text":"Now the data audit and the analysis script."},{"type":"tool_use","id":"toolu_01D27Ev2PxvaxkiAA5sr6ev7","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\n| file | SHA-256 | data rows | cols |\n|---|---|---|---|\n| data/wb_indicators.csv | 6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0 (matches README & bundle.json) | 2349 | 5 |\n| data/wb_entities.csv | 06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d (matches) | 296 | 5 |\n| data/README.md | 76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a (matches bundle.json) | – | – |\n\n**wb_indicators.csv**: iso3 (str), name (str), year (int, 2015–2023, 261 entities × 9 years, balanced), gdp_pc_ppp (float, constant 2021 PPP $, 164 missing, range 992–139,541, all > 0), life_expectancy (float, years, 0 missing, range 18.8–86.4). No duplicated (iso3, year). Every iso3 appears in wb_entities.csv; names agree.\n\n**wb_entities.csv**: 296 entities, no duplicates, no blanks; 79 have region == \"Aggregates\" (217 countries/economies). Note: \"NA\" (Namibia's ISO2) is not an issue because codes are ISO3; pandas default NA parsing is nevertheless disabled for string columns in the script for safety (keep_default_na=False) — no entity has a code/name that would be mis-parsed anyway.\n\n**Countries/economies, both indicators observed, by year**: 199 in each year 2015–2022, 197 in 2023. Rule (≥150, latest) ⇒ analysis year **2023**. In 2023, 217 countries present, 20 lack GDP (ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM); 0 lack LE ⇒ n_excluded_missing = 20, n_analysed = 197.\n\n**Anomalies**\n- Central African Republic LE is erratic across years (2019 31.5, 2021 40.3, 2022 18.8, 2023 57.4). The 2023 value (57.4) is within the plausible range for CAF and is kept; earlier years are not used. Flagged in data_issues; a leave-out sensitivity is not required, but CAF's leverage is noted.\n- West Bank & Gaza (PSE) LE drops 11.5 years in 2023 (conflict); kept as reported.\n- Missing GDP is non-random: mostly small high-income territories and conflict/sanctioned states (possible selection bias). Handled by exclusion per rules, discussed in report.\n- 2023 LE values for some countries may be WB estimates/projections rather than vital-registration measurements (not verifiable from the files).\n\n**Information-availability**: no input violates the rules; aggregates are removed via region == \"Aggregates\". No other files used.\nEOF\necho \"- 2026-10-30: P1 audit written; analysis year 2023 (197 complete, 20 missing GDP). Decision: HC3 robust SE, t(n-2) CI.\" >> out/state/log.md","description":"Write data audit"}}]}}62{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"013c8e5d-60be-4a40-b39e-3244e1182b1b","timestamp":"2026-10-30T05:31:47.256Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"972caabb-ac1a-4d2c-918a-c29d51e64e0a","keep":16,"tail":["f779db248191c6a3712478338d304a0c1532ffd2fdedeae94c16386ce8fe0206","5413b2050f97c1ae31a8b315d290c3eaffa3bcc52799026de01ece118c10de44"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"6ae1524160409c955e5ea9879ed862c3c9e0b6f5947b0c7ce229b4db2e3b5b99"}63{"parentUuid":"e667a468-c132-48a4-8023-51d8358d3941","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXse93zhWxx5iE11PL6k","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018kYVFS8uEp8LKNSAyP3vdR","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-dev-01 (Preston curve, WDI).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/figure1.png, out/table1.csv, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nTASK_ID = \"F6-dev-01\"\nMIN_COUNTRIES = 150\n\nind = pd.read_csv(\"data/wb_indicators.csv\", keep_default_na=False, na_values=[\"\"],\n                  dtype={\"iso3\": str, \"name\": str})\nent = pd.read_csv(\"data/wb_entities.csv\", keep_default_na=False, na_values=[\"\"], dtype=str)\nn_input_rows = {\"wb_indicators.csv\": int(len(ind)), \"wb_entities.csv\": int(len(ent))}\n\nassert not ind.duplicated([\"iso3\", \"year\"]).any()\nassert not ent.duplicated(\"iso3\").any()\nassert set(ind.iso3) <= set(ent.iso3)\n\nex = []\ndef log_ex(step, rule, nb, na, why):\n    ex.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\n# Step 1: remove aggregates (entity-year rows)\ndf = ind.merge(ent[[\"iso3\", \"region\", \"income_level\"]], on=\"iso3\", how=\"left\")\nn0 = len(df)\ndf = df[df.region != \"Aggregates\"].copy()\nlog_ex(1, \"drop region == 'Aggregates'\", n0, len(df), \"analysis population is countries/economies only (TASK info rule)\")\n\n# Analysis year: latest with both indicators for >= 150 countries\ncomplete = df.gdp_pc_ppp.notna() & df.life_expectancy.notna()\ncounts = df[complete].groupby(\"year\").size()\neligible = counts[counts >= MIN_COUNTRIES]\nif eligible.empty:\n    raise SystemExit(\"No year with >=150 complete countries: premise invalid\")\nyear = int(eligible.index.max())\n\n# Step 2: keep analysis year\nn1 = len(df)\nd = df[df.year == year].copy()\nlog_ex(2, f\"keep year == {year}\", n1, len(d), \"latest year 2015-2023 with both indicators for >=150 countries/economies\")\nn_year = len(d)\n\n# Step 3: drop missing indicator\nd = d[d.gdp_pc_ppp.notna() & d.life_expectancy.notna()].copy()\nn_excl_missing = n_year - len(d)\nlog_ex(3, \"drop rows with missing gdp_pc_ppp or life_expectancy\", n_year, len(d), \"no imputation (TASK info rule)\")\nmissing_iso = sorted(set(df[df.year == year].iso3) - set(d.iso3))\npd.DataFrame(ex).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\nassert (d.gdp_pc_ppp > 0).all()\nd[\"log_gdp\"] = np.log(d.gdp_pc_ppp)\ny = d.life_expectancy.to_numpy(); x = d.log_gdp.to_numpy(); n = len(d)\n\n# Baseline: mean-only prediction\nbaseline_rmse = float(np.sqrt(np.mean((y - y.mean()) ** 2)))\n\n# OLS with HC3 robust SE (primary); t(n-2) critical value for 95% CI\nX = sm.add_constant(x)\nfit = sm.OLS(y, X).fit(cov_type=\"HC3\")\nbeta, alpha = float(fit.params[1]), float(fit.params[0])\nse = float(fit.bse[1])\nci = fit.conf_int(alpha=0.05)[1]  # uses t(n-2) since use_t defaults True for OLS with cov_type? enforce below\nfrom scipy import stats\ntcrit = float(stats.t.ppf(0.975, n - 2))\nci_low, ci_high = beta - tcrit * se, beta + tcrit * se\nresid = fit.resid\nmodel_rmse = float(np.sqrt(np.mean(resid ** 2)))\nr = float(np.corrcoef(x, y)[0, 1])\nr2 = float(fit.rsquared)\n\n# Sensitivity: other HC variants and classical SE\nse_alt = {f\"sensitivity_se_{k.lower()}\": float(sm.OLS(y, X).fit(cov_type=k).bse[1]) for k in (\"HC0\", \"HC1\", \"HC2\")}\nse_alt[\"sensitivity_se_classical\"] = float(sm.OLS(y, X).fit().bse[1])\n# Sensitivity: drop the 5 largest |residual| observations (influence check, descriptive only)\norder = np.argsort(-np.abs(resid))\nkeep = np.ones(n, bool); keep[order[:5]] = False\nfit_trim = sm.OLS(y[keep], X[keep]).fit(cov_type=\"HC3\")\ntop_resid = d.iloc[order[:5]].iso3.tolist()\n\nif ci_low > 0:\n    conclusion = \"positive_effect\"\nelif ci_high < 0:\n    conclusion = \"negative_effect\"\nelse:\n    conclusion = \"no_detectable_effect\"\n\n# Table 1\nlvl_order = [\"Low income\", \"Lower middle income\", \"Upper middle income\", \"High income\"]\nt1 = (d.groupby(\"income_level\")\n        .agg(n_countries=(\"iso3\", \"size\"), mean_log_gdp_pc=(\"log_gdp\", \"mean\"), mean_life_expectancy=(\"life_expectancy\", \"mean\"))\n        .reset_index())\nt1[\"_o\"] = t1.income_level.map({k: i for i, k in enumerate(lvl_order)}).fillna(99)\nt1 = t1.sort_values([\"_o\", \"income_level\"]).drop(columns=\"_o\")\nt1.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.4f\")\n\n# Figure 1\nfig, ax = plt.subplots(figsize=(7, 5))\ncolors = {\"Low income\": \"tab:red\", \"Lower middle income\": \"tab:orange\", \"Upper middle income\": \"tab:green\", \"High income\": \"tab:blue\"}\nfor lvl in lvl_order + sorted(set(d.income_level) - set(lvl_order)):\n    s = d[d.income_level == lvl]\n    if len(s):\n        ax.scatter(s.log_gdp, s.life_expectancy, s=14, alpha=0.75, color=colors.get(lvl, \"gray\"), label=f\"{lvl} (n={len(s)})\")\nxx = np.linspace(x.min(), x.max(), 100)\nax.plot(xx, alpha + beta * xx, \"k-\", lw=1.5, label=f\"OLS: LE = {alpha:.1f} + {beta:.2f} ln(GDPpc), R² = {r2:.2f}\")\nax.set_xlabel(\"ln(GDP per capita, PPP, constant 2021 int'l $)\")\nax.set_ylabel(\"Life expectancy at birth (years)\")\nax.set_title(f\"Preston curve, {year} ({n} countries/economies, WDI)\")\nax.legend(fontsize=7, loc=\"lower right\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=150)\nplt.close(fig)\n\ncaf = d[d.iso3 == \"CAF\"]\ndata_issues = [\n    {\"issue\": \"wb_indicators.csv contains regional/income-group aggregates (79 entities with region 'Aggregates')\",\n     \"handling\": \"Excluded via wb_entities.csv region == 'Aggregates' before choosing the analysis year.\"},\n    {\"issue\": f\"{n_excl_missing} countries/economies lack GDP per capita PPP in {year} (\" + \", \".join(missing_iso) + \"); missingness is non-random (small territories, conflict/sanctioned states)\",\n     \"handling\": \"Excluded without imputation as required; counted in n_excluded_missing; possible selection bias discussed in report.\"},\n    {\"issue\": \"Central African Republic life expectancy is erratic across 2015-2022 (e.g. 18.8 in 2022, 31.5 in 2019)\",\n     \"handling\": f\"Only the analysis-year value is used ({float(caf.life_expectancy.iloc[0]) if len(caf) else 'n/a'} in {year}), which is plausible; kept. Influence assessed by the drop-5-largest-residuals sensitivity.\"},\n    {\"issue\": \"West Bank and Gaza life expectancy falls ~11.5 years in 2023 (conflict)\",\n     \"handling\": \"Kept as reported; real data feature, covered by the residual-trimming sensitivity if influential.\"},\n    {\"issue\": \"Recent-year WDI values may be modelled estimates/projections rather than measurements\",\n     \"handling\": \"Not verifiable from the provided files; noted as a limitation.\"},\n]\n\nres = {\n    \"task_id\": TASK_ID,\n    \"feasibility\": \"complete\",\n    \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": n_input_rows,\n    \"n_analysed\": int(n),\n    \"random_seed\": None,\n    \"analysis_year\": year,\n    \"n_countries_in_year\": int(n_year),\n    \"n_excluded_missing\": int(n_excl_missing),\n    \"complete_countries_by_year\": {str(k): int(v) for k, v in counts.items()},\n    \"baseline_metric\": baseline_rmse,\n    \"model_metric\": model_rmse,\n    \"pearson_r\": r,\n    \"r_squared\": r2,\n    \"effect_estimate\": beta,\n    \"intercept\": alpha,\n    \"effect_se\": se,\n    \"effect_se_type\": \"HC3\",\n    \"effect_ci_low\": float(ci_low),\n    \"effect_ci_high\": float(ci_high),\n    \"ci_critical_value_t\": tcrit,\n    \"effect_t_stat\": beta / se,\n    \"conclusion\": conclusion,\n    **se_alt,\n    \"sensitivity_trim5_effect\": float(fit_trim.params[1]),\n    \"sensitivity_trim5_se_hc3\": float(fit_trim.bse[1]),\n    \"sensitivity_trim5_dropped_iso3\": top_resid,\n    \"mean_life_expectancy\": float(y.mean()),\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=2)\nprint(f\"year={year} n={n} excluded_missing={n_excl_missing} beta={beta:.4f} se_HC3={se:.4f} \"\n      f\"CI=[{ci_low:.4f},{ci_high:.4f}] R2={r2:.4f} rmse_base={baseline_rmse:.4f} rmse_ols={model_rmse:.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":1263,"cache_read_input_tokens":16751,"output_tokens":3980,"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":1263},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXse8o8BifcYbAT9Uzej","requestRef":"013c8e5d-60be-4a40-b39e-3244e1182b1b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"faf8d5d5-67e1-479a-baea-55718665abd0","timestamp":"2026-10-30T05:32:17.961Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}64{"type":"last-prompt","lastPrompt":"Your","leafUuid":"faf8d5d5-67e1-479a-baea-55718665abd0","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}65{"type":"mode","mode":"normal","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}66{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}67{"parentUuid":"faf8d5d5-67e1-479a-baea-55718665abd0","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018kYVFS8uEp8LKNSAyP3vdR","type":"tool_result","content":"year=2023 n=197 excluded_missing=20 beta=5.2672 se_HC3=0.2107 CI=[4.8517,5.6827] R2=0.7419 rmse_base=7.0765 rmse_ols=3.5950 -> positive_effect\n{\n  \"task_id\": \"F6-dev-01\",\n  \"feasibility\": \"complete\",\n  \"feasibility_reason\": null,\n  \"data_issues\": [\n    {\n      \"issue\": \"wb_indicators.csv contains regional/income-group aggregates (79 entities with region 'Aggregates')\",\n      \"handling\": \"Excluded via wb_entities.csv region == 'Aggregates' before choosing the analysis year.\"\n    },\n    {\n      \"issue\": \"20 countries/economies lack GDP per capita PPP in 2023 (ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM); missingness is non-random (small territories, conflict/sanctioned states)\",\n      \"handling\": \"Excluded without imputation as required; counted in n_excluded_missing; possible selection bias discussed in report.\"\n    },\n    {\n      \"issue\": \"Central African Republic life expectancy is erratic across 2015-2022 (e.g. 18.8 in 2022, 31.5 in 2019)\",\n      \"handling\": \"Only the analysis-year value is used (57.408 in 2023), which is plausible; kept. Influence assessed by the drop-5-largest-residuals sensitivity.\"\n    },\n    {\n      \"issue\": \"West Bank and Gaza life expectancy falls ~11.5 years in 2023 (conflict)\",\n      \"handling\": \"Kept as reported; real data feature, covered by the residual-trimming sensitivity if influential.\"\n    },\n    {\n      \"issue\": \"Recent-year WDI values may be modelled estimates/projections rather than measurements\",\n      \"handling\": \"Not verifiable from the provided files; noted as a limitation.\"\n    }\n  ],\n  \"n_input_rows\": {\n    \"wb_indicators.csv\": 2349,\n    \"wb_entities.csv\": 296\n  },\n  \"n_analysed\": 197,\n  \"random_seed\": null,\n  \"analysis_year\": 2023,\n  \"n_countries_in_year\": 217,\n  \"n_excluded_missing\": 20,\n  \"complete_countries_by_year\": {\n    \"2015\": 199,\n    \"2016\": 199,\n    \"2017\": 199,\n    \"2018\": 199,\n    \"2019\": 199,\n    \"2020\": 199,\n    \"2021\": 199,\n    \"2022\": 199,\n    \"2023\": 197\n  },\n  \"baseline_metric\": 7.07645404460588,\n  \"model_metric\": 3.5949979094078177,\n  \"pearson_r\": 0.8613437957840087,\n  \"r_squared\": 0.7419131345356038,\n  \"effect_estimate\": 5.267173451958655,\n  \"intercept\": 22.56709274982858,\n  \"effect_se\": 0.21067528691162227,\n  \"effect_se_type\": \"HC3\",\n  \"effect_ci_low\": 4.851678797609962,\n  \"effect_ci_high\": 5.682668106307348,\n  \"ci_critical_value_t\": 1.9722040512658325,\n  \"effect_t_stat\": 25.00138259770459,\n  \"conclusion\": \"positive_effect\",\n  \"sensitivity_se_hc0\": 0.20736485591704354,\n  \"sensitivity_se_hc1\": 0.2084255526375312,\n  \"sensitivity_se_hc2\": 0.20901105806015902,\n  \"sensitivity_se_classical\": 0.22246758287864518,\n  \"sensitivity_trim5_effect\": 5.317276954719264,\n  \"sensitivity_trim5_se_hc3\": 0.19476985624358756,\n  \"sensitivity_trim5_dropped_iso3\": [\n    \"NGA\",\n    \"GRL\",\n    \"NRU\",\n    \"GNQ\",\n    \"GUY\"\n  ],\n  \"mean_life_expectancy\": 73.47408158883249\n}income_level,n_countries,mean_log_gdp_pc,mean_life_expectancy\nLow income,20,7.6100,63.1880\nLower middle income,46,8.6899,67.8095\nUpper middle income,58,9.6899,73.6954\nHigh income,73,10.8226,79.6858\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop region == 'Aggregates',2349,1953,396,analysis population is countries/economies only (TASK info rule)\n2,keep year == 2023,1953,217,1736,latest year 2015-2023 with both indicators for >=150 countries/economies\n3,drop rows with missing gdp_pc_ppp or life_expectancy,217,197,20,no imputation (TASK info rule)","is_error":false}]},"uuid":"6cbb5fd5-588d-435a-acb6-9419a052c5be","timestamp":"2026-10-30T05:32:19.277Z","toolUseResult":{"stdout":"year=2023 n=197 excluded_missing=20 beta=5.2672 se_HC3=0.2107 CI=[4.8517,5.6827] R2=0.7419 rmse_base=7.0765 rmse_ols=3.5950 -> positive_effect\n{\n  \"task_id\": \"F6-dev-01\",\n  \"feasibility\": \"complete\",\n  \"feasibility_reason\": null,\n  \"data_issues\": [\n    {\n      \"issue\": \"wb_indicators.csv contains regional/income-group aggregates (79 entities with region 'Aggregates')\",\n      \"handling\": \"Excluded via wb_entities.csv region == 'Aggregates' before choosing the analysis year.\"\n    },\n    {\n      \"issue\": \"20 countries/economies lack GDP per capita PPP in 2023 (ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM); missingness is non-random (small territories, conflict/sanctioned states)\",\n      \"handling\": \"Excluded without imputation as required; counted in n_excluded_missing; possible selection bias discussed in report.\"\n    },\n    {\n      \"issue\": \"Central African Republic life expectancy is erratic across 2015-2022 (e.g. 18.8 in 2022, 31.5 in 2019)\",\n      \"handling\": \"Only the analysis-year value is used (57.408 in 2023), which is plausible; kept. Influence assessed by the drop-5-largest-residuals sensitivity.\"\n    },\n    {\n      \"issue\": \"West Bank and Gaza life expectancy falls ~11.5 years in 2023 (conflict)\",\n      \"handling\": \"Kept as reported; real data feature, covered by the residual-trimming sensitivity if influential.\"\n    },\n    {\n      \"issue\": \"Recent-year WDI values may be modelled estimates/projections rather than measurements\",\n      \"handling\": \"Not verifiable from the provided files; noted as a limitation.\"\n    }\n  ],\n  \"n_input_rows\": {\n    \"wb_indicators.csv\": 2349,\n    \"wb_entities.csv\": 296\n  },\n  \"n_analysed\": 197,\n  \"random_seed\": null,\n  \"analysis_year\": 2023,\n  \"n_countries_in_year\": 217,\n  \"n_excluded_missing\": 20,\n  \"complete_countries_by_year\": {\n    \"2015\": 199,\n    \"2016\": 199,\n    \"2017\": 199,\n    \"2018\": 199,\n    \"2019\": 199,\n    \"2020\": 199,\n    \"2021\": 199,\n    \"2022\": 199,\n    \"2023\": 197\n  },\n  \"baseline_metric\": 7.07645404460588,\n  \"model_metric\": 3.5949979094078177,\n  \"pearson_r\": 0.8613437957840087,\n  \"r_squared\": 0.7419131345356038,\n  \"effect_estimate\": 5.267173451958655,\n  \"intercept\": 22.56709274982858,\n  \"effect_se\": 0.21067528691162227,\n  \"effect_se_type\": \"HC3\",\n  \"effect_ci_low\": 4.851678797609962,\n  \"effect_ci_high\": 5.682668106307348,\n  \"ci_critical_value_t\": 1.9722040512658325,\n  \"effect_t_stat\": 25.00138259770459,\n  \"conclusion\": \"positive_effect\",\n  \"sensitivity_se_hc0\": 0.20736485591704354,\n  \"sensitivity_se_hc1\": 0.2084255526375312,\n  \"sensitivity_se_hc2\": 0.20901105806015902,\n  \"sensitivity_se_classical\": 0.22246758287864518,\n  \"sensitivity_trim5_effect\": 5.317276954719264,\n  \"sensitivity_trim5_se_hc3\": 0.19476985624358756,\n  \"sensitivity_trim5_dropped_iso3\": [\n    \"NGA\",\n    \"GRL\",\n    \"NRU\",\n    \"GNQ\",\n    \"GUY\"\n  ],\n  \"mean_life_expectancy\": 73.47408158883249\n}income_level,n_countries,mean_log_gdp_pc,mean_life_expectancy\nLow income,20,7.6100,63.1880\nLower middle income,46,8.6899,67.8095\nUpper middle income,58,9.6899,73.6954\nHigh income,73,10.8226,79.6858\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop region == 'Aggregates',2349,1953,396,analysis population is countries/economies only (TASK info rule)\n2,keep year == 2023,1953,217,1736,latest year 2015-2023 with both indicators for >=150 countries/economies\n3,drop rows with missing gdp_pc_ppp or life_expectancy,217,197,20,no imputation (TASK info rule)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"faf8d5d5-67e1-479a-baea-55718665abd0","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}68{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"6bac121ed1a0a19b8c29549263d4505421cbdbd0502a1626b64e67d8c1dc6b2f","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_018kYVFS8uEp8LKNSAyP3vdR","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-dev-01 (Preston curve, WDI).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/figure1.png, out/table1.csv, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nTASK_ID = \"F6-dev-01\"\nMIN_COUNTRIES = 150\n\nind = pd.read_csv(\"data/wb_indicators.csv\", keep_default_na=False, na_values=[\"\"],\n                  dtype={\"iso3\": str, \"name\": str})\nent = pd.read_csv(\"data/wb_entities.csv\", keep_default_na=False, na_values=[\"\"], dtype=str)\nn_input_rows = {\"wb_indicators.csv\": int(len(ind)), \"wb_entities.csv\": int(len(ent))}\n\nassert not ind.duplicated([\"iso3\", \"year\"]).any()\nassert not ent.duplicated(\"iso3\").any()\nassert set(ind.iso3) <= set(ent.iso3)\n\nex = []\ndef log_ex(step, rule, nb, na, why):\n    ex.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\n# Step 1: remove aggregates (entity-year rows)\ndf = ind.merge(ent[[\"iso3\", \"region\", \"income_level\"]], on=\"iso3\", how=\"left\")\nn0 = len(df)\ndf = df[df.region != \"Aggregates\"].copy()\nlog_ex(1, \"drop region == 'Aggregates'\", n0, len(df), \"analysis population is countries/economies only (TASK info rule)\")\n\n# Analysis year: latest with both indicators for >= 150 countries\ncomplete = df.gdp_pc_ppp.notna() & df.life_expectancy.notna()\ncounts = df[complete].groupby(\"year\").size()\neligible = counts[counts >= MIN_COUNTRIES]\nif eligible.empty:\n    raise SystemExit(\"No year with >=150 complete countries: premise invalid\")\nyear = int(eligible.index.max())\n\n# Step 2: keep analysis year\nn1 = len(df)\nd = df[df.year == year].copy()\nlog_ex(2, f\"keep year == {year}\", n1, len(d), \"latest year 2015-2023 with both indicators for >=150 countries/economies\")\nn_year = len(d)\n\n# Step 3: drop missing indicator\nd = d[d.gdp_pc_ppp.notna() & d.life_expectancy.notna()].copy()\nn_excl_missing = n_year - len(d)\nlog_ex(3, \"drop rows with missing gdp_pc_ppp or life_expectancy\", n_year, len(d), \"no imputation (TASK info rule)\")\nmissing_iso = sorted(set(df[df.year == year].iso3) - set(d.iso3))\npd.DataFrame(ex).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\nassert (d.gdp_pc_ppp > 0).all()\nd[\"log_gdp\"] = np.log(d.gdp_pc_ppp)\ny = d.life_expectancy.to_numpy(); x = d.log_gdp.to_numpy(); n = len(d)\n\n# Baseline: mean-only prediction\nbaseline_rmse = float(np.sqrt(np.mean((y - y.mean()) ** 2)))\n\n# OLS with HC3 robust SE (primary); t(n-2) critical value for 95% CI\nX = sm.add_constant(x)\nfit = sm.OLS(y, X).fit(cov_type=\"HC3\")\nbeta, alpha = float(fit.params[1]), float(fit.params[0])\nse = float(fit.bse[1])\nci = fit.conf_int(alpha=0.05)[1]  # uses t(n-2) since use_t defaults True for OLS with cov_type? enforce below\nfrom scipy import stats\ntcrit = float(stats.t.ppf(0.975, n - 2))\nci_low, ci_high = beta - tcrit * se, beta + tcrit * se\nresid = fit.resid\nmodel_rmse = float(np.sqrt(np.mean(resid ** 2)))\nr = float(np.corrcoef(x, y)[0, 1])\nr2 = float(fit.rsquared)\n\n# Sensitivity: other HC variants and classical SE\nse_alt = {f\"sensitivity_se_{k.lower()}\": float(sm.OLS(y, X).fit(cov_type=k).bse[1]) for k in (\"HC0\", \"HC1\", \"HC2\")}\nse_alt[\"sensitivity_se_classical\"] = float(sm.OLS(y, X).fit().bse[1])\n# Sensitivity: drop the 5 largest |residual| observations (influence check, descriptive only)\norder = np.argsort(-np.abs(resid))\nkeep = np.ones(n, bool); keep[order[:5]] = False\nfit_trim = sm.OLS(y[keep], X[keep]).fit(cov_type=\"HC3\")\ntop_resid = d.iloc[order[:5]].iso3.tolist()\n\nif ci_low > 0:\n    conclusion = \"positive_effect\"\nelif ci_high < 0:\n    conclusion = \"negative_effect\"\nelse:\n    conclusion = \"no_detectable_effect\"\n\n# Table 1\nlvl_order = [\"Low income\", \"Lower middle income\", \"Upper middle income\", \"High income\"]\nt1 = (d.groupby(\"income_level\")\n        .agg(n_countries=(\"iso3\", \"size\"), mean_log_gdp_pc=(\"log_gdp\", \"mean\"), mean_life_expectancy=(\"life_expectancy\", \"mean\"))\n        .reset_index())\nt1[\"_o\"] = t1.income_level.map({k: i for i, k in enumerate(lvl_order)}).fillna(99)\nt1 = t1.sort_values([\"_o\", \"income_level\"]).drop(columns=\"_o\")\nt1.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.4f\")\n\n# Figure 1\nfig, ax = plt.subplots(figsize=(7, 5))\ncolors = {\"Low income\": \"tab:red\", \"Lower middle income\": \"tab:orange\", \"Upper middle income\": \"tab:green\", \"High income\": \"tab:blue\"}\nfor lvl in lvl_order + sorted(set(d.income_level) - set(lvl_order)):\n    s = d[d.income_level == lvl]\n    if len(s):\n        ax.scatter(s.log_gdp, s.life_expectancy, s=14, alpha=0.75, color=colors.get(lvl, \"gray\"), label=f\"{lvl} (n={len(s)})\")\nxx = np.linspace(x.min(), x.max(), 100)\nax.plot(xx, alpha + beta * xx, \"k-\", lw=1.5, label=f\"OLS: LE = {alpha:.1f} + {beta:.2f} ln(GDPpc), R² = {r2:.2f}\")\nax.set_xlabel(\"ln(GDP per capita, PPP, constant 2021 int'l $)\")\nax.set_ylabel(\"Life expectancy at birth (years)\")\nax.set_title(f\"Preston curve, {year} ({n} countries/economies, WDI)\")\nax.legend(fontsize=7, loc=\"lower right\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=150)\nplt.close(fig)\n\ncaf = d[d.iso3 == \"CAF\"]\ndata_issues = [\n    {\"issue\": \"wb_indicators.csv contains regional/income-group aggregates (79 entities with region 'Aggregates')\",\n     \"handling\": \"Excluded via wb_entities.csv region == 'Aggregates' before choosing the analysis year.\"},\n    {\"issue\": f\"{n_excl_missing} countries/economies lack GDP per capita PPP in {year} (\" + \", \".join(missing_iso) + \"); missingness is non-random (small territories, conflict/sanctioned states)\",\n     \"handling\": \"Excluded without imputation as required; counted in n_excluded_missing; possible selection bias discussed in report.\"},\n    {\"issue\": \"Central African Republic life expectancy is erratic across 2015-2022 (e.g. 18.8 in 2022, 31.5 in 2019)\",\n     \"handling\": f\"Only the analysis-year value is used ({float(caf.life_expectancy.iloc[0]) if len(caf) else 'n/a'} in {year}), which is plausible; kept. Influence assessed by the drop-5-largest-residuals sensitivity.\"},\n    {\"issue\": \"West Bank and Gaza life expectancy falls ~11.5 years in 2023 (conflict)\",\n     \"handling\": \"Kept as reported; real data feature, covered by the residual-trimming sensitivity if influential.\"},\n    {\"issue\": \"Recent-year WDI values may be modelled estimates/projections rather than measurements\",\n     \"handling\": \"Not verifiable from the provided files; noted as a limitation.\"},\n]\n\nres = {\n    \"task_id\": TASK_ID,\n    \"feasibility\": \"complete\",\n    \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": n_input_rows,\n    \"n_analysed\": int(n),\n    \"random_seed\": None,\n    \"analysis_year\": year,\n    \"n_countries_in_year\": int(n_year),\n    \"n_excluded_missing\": int(n_excl_missing),\n    \"complete_countries_by_year\": {str(k): int(v) for k, v in counts.items()},\n    \"baseline_metric\": baseline_rmse,\n    \"model_metric\": model_rmse,\n    \"pearson_r\": r,\n    \"r_squared\": r2,\n    \"effect_estimate\": beta,\n    \"intercept\": alpha,\n    \"effect_se\": se,\n    \"effect_se_type\": \"HC3\",\n    \"effect_ci_low\": float(ci_low),\n    \"effect_ci_high\": float(ci_high),\n    \"ci_critical_value_t\": tcrit,\n    \"effect_t_stat\": beta / se,\n    \"conclusion\": conclusion,\n    **se_alt,\n    \"sensitivity_trim5_effect\": float(fit_trim.params[1]),\n    \"sensitivity_trim5_se_hc3\": float(fit_trim.bse[1]),\n    \"sensitivity_trim5_dropped_iso3\": top_resid,\n    \"mean_life_expectancy\": float(y.mean()),\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n    json.dump(res, fh, indent=2)\nprint(f\"year={year} n={n} excluded_missing={n_excl_missing} beta={beta:.4f} se_HC3={se:.4f} \"\n      f\"CI=[{ci_low:.4f},{ci_high:.4f}] R2={r2:.4f} rmse_base={baseline_rmse:.4f} rmse_ols={model_rmse:.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"}}]}}69{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"684db01a-a61e-4bc9-ade7-5297a78a17b0","timestamp":"2026-10-30T05:32:19.281Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"013c8e5d-60be-4a40-b39e-3244e1182b1b","keep":18,"tail":["6bac121ed1a0a19b8c29549263d4505421cbdbd0502a1626b64e67d8c1dc6b2f","948872f0fe2c0650ff8347a27541629d4a58f44f87e58c4c398ef94e155324d1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2c086800eb968ed4d0e95de503c62f197865c116768d0f717a706deafd9870c2"}70{"parentUuid":"6cbb5fd5-588d-435a-acb6-9419a052c5be","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsgVye7Hpz5cbR7wnPz","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":5617,"cache_read_input_tokens":18014,"output_tokens":853,"output_tokens_details":{"thinking_tokens":87},"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":5617},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":955,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsgViGevV6kMd4FN9tY","requestRef":"684db01a-a61e-4bc9-ade7-5297a78a17b0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c029b13d-a1ab-424e-91e0-e536d021e8d4","timestamp":"2026-10-30T05:32:22.656Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}71{"parentUuid":"c029b13d-a1ab-424e-91e0-e536d021e8d4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsgVye7Hpz5cbR7wnPz","type":"message","role":"assistant","content":[{"type":"text","text":"Remove a dead line, then verify independently."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5617,"cache_read_input_tokens":18014,"output_tokens":853,"output_tokens_details":{"thinking_tokens":87},"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":5617},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsgViGevV6kMd4FN9tY","requestRef":"684db01a-a61e-4bc9-ade7-5297a78a17b0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5b68bdac-775d-42c4-a740-435b42b8f5b6","timestamp":"2026-10-30T05:32:22.656Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}72{"parentUuid":"5b68bdac-775d-42c4-a740-435b42b8f5b6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsgVye7Hpz5cbR7wnPz","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WwWaaYdPP2z42m6T1T5nmV","name":"Bash","input":{"command":"sed -i '' '/^ci = fit.conf_int/d' out/analysis.py && cp out/results.json /tmp/r1.json && rm -f out/results.json out/figure1.png out/table1.csv out/exclusions.csv && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL\n~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np,json\nr=json.load(open('out/results.json'))\ni=pd.read_csv('data/wb_indicators.csv');e=pd.read_csv('data/wb_entities.csv',keep_default_na=False)\nagg=set(e[e.region=='Aggregates'].iso3); d=i[(i.year==2023)&~i.iso3.isin(agg)].dropna()\nx=np.log(d.gdp_pc_ppp.values);y=d.life_expectancy.values;n=len(y)\nX=np.c_[np.ones(n),x];b=np.linalg.solve(X.T@X,X.T@y);e_=y-X@b\nXtXi=np.linalg.inv(X.T@X);h=np.einsum('ij,jk,ik->i',X,XtXi,X)\nV=XtXi@(X.T*(e_**2/(1-h)**2))@X@XtXi\nprint(n,b,np.sqrt(V[1,1]),np.sqrt(np.mean(e_**2)),np.std(y),1-np.mean(e_**2)/np.var(y))\nprint(abs(b[1]-r['effect_estimate'])<1e-9,abs(np.sqrt(V[1,1])-r['effect_se'])<1e-9, abs(r['pearson_r']**2-r['r_squared'])<1e-12)\nprint('rmse identity', abs(r['model_metric']-r['baseline_metric']*np.sqrt(1-r['r_squared']))<1e-9)\n\"","description":"Re-run cleanly and verify with manual computation"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5617,"cache_read_input_tokens":18014,"output_tokens":853,"output_tokens_details":{"thinking_tokens":87},"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":5617},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsgViGevV6kMd4FN9tY","requestRef":"684db01a-a61e-4bc9-ade7-5297a78a17b0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a094aef9-e63a-4742-9f37-5adc6ef08963","timestamp":"2026-10-30T05:32:27.956Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}73{"parentUuid":"a094aef9-e63a-4742-9f37-5adc6ef08963","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WwWaaYdPP2z42m6T1T5nmV","type":"tool_result","content":"IDENTICAL\n197 [22.56709275  5.26717345] 0.2106752869116229 3.594997909407818 7.07645404460588 0.7419131345356038\nTrue True True\nrmse identity True","is_error":false}]},"uuid":"23556ad6-dceb-467d-b654-5dbeabec82b0","timestamp":"2026-10-30T05:32:29.499Z","toolUseResult":{"stdout":"IDENTICAL\n197 [22.56709275  5.26717345] 0.2106752869116229 3.594997909407818 7.07645404460588 0.7419131345356038\nTrue True True\nrmse identity True","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a094aef9-e63a-4742-9f37-5adc6ef08963","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}74{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"79c8c63a39f9cd1ee747556f9b83906b0413332823c03591c7830e6aed48972e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Remove a dead line, then verify independently."},{"type":"tool_use","id":"toolu_01WwWaaYdPP2z42m6T1T5nmV","name":"Bash","input":{"command":"sed -i '' '/^ci = fit.conf_int/d' out/analysis.py && cp out/results.json /tmp/r1.json && rm -f out/results.json out/figure1.png out/table1.csv out/exclusions.csv && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL\n~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np,json\nr=json.load(open('out/results.json'))\ni=pd.read_csv('data/wb_indicators.csv');e=pd.read_csv('data/wb_entities.csv',keep_default_na=False)\nagg=set(e[e.region=='Aggregates'].iso3); d=i[(i.year==2023)&~i.iso3.isin(agg)].dropna()\nx=np.log(d.gdp_pc_ppp.values);y=d.life_expectancy.values;n=len(y)\nX=np.c_[np.ones(n),x];b=np.linalg.solve(X.T@X,X.T@y);e_=y-X@b\nXtXi=np.linalg.inv(X.T@X);h=np.einsum('ij,jk,ik->i',X,XtXi,X)\nV=XtXi@(X.T*(e_**2/(1-h)**2))@X@XtXi\nprint(n,b,np.sqrt(V[1,1]),np.sqrt(np.mean(e_**2)),np.std(y),1-np.mean(e_**2)/np.var(y))\nprint(abs(b[1]-r['effect_estimate'])<1e-9,abs(np.sqrt(V[1,1])-r['effect_se'])<1e-9, abs(r['pearson_r']**2-r['r_squared'])<1e-12)\nprint('rmse identity', abs(r['model_metric']-r['baseline_metric']*np.sqrt(1-r['r_squared']))<1e-9)\n\"","description":"Re-run cleanly and verify with manual computation"}}]}}75{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"f327f1a0-047a-4866-b598-3d8a9900243b","timestamp":"2026-10-30T05:32:29.502Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"684db01a-a61e-4bc9-ade7-5297a78a17b0","keep":20,"tail":["79c8c63a39f9cd1ee747556f9b83906b0413332823c03591c7830e6aed48972e","945ee8b28a18a34661fda0a7aad8aba55858240f34480b808c0255752e99caa2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5dcb02c0a7bc0c0cfd349832507ce989935b359cb1ea6ce2c36da7ba555984c2"}76{"type":"tools-used","tools":["Bash","Read"],"sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}77{"parentUuid":"23556ad6-dceb-467d-b654-5dbeabec82b0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXshFfwhK9Ra3Zt8VzCw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NbdR2y4qumcB8BhPe4HcXG","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RR0005/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":926,"cache_read_input_tokens":23631,"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":926},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXshFParyXaQ9eTnBuzM","requestRef":"f327f1a0-047a-4866-b598-3d8a9900243b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c6792102-6ef3-485e-b5b7-ab650f4c1f3d","timestamp":"2026-10-30T05:32:30.992Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"c6792102-6ef3-485e-b5b7-ab650f4c1f3d","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01NbdR2y4qumcB8BhPe4HcXG","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"dc2ab7e5-de20-4d1b-af43-ab6014fa80e4","timestamp":"2026-10-30T05:32:30.998Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":89115,"dimensions":{"originalWidth":1050,"originalHeight":750,"displayWidth":1050,"displayHeight":750}}},"sourceToolAssistantUUID":"c6792102-6ef3-485e-b5b7-ab650f4c1f3d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}79{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"7e21ab8749c7e4e1a8e1b6a94d821b8435034eab41d91e8565f284dcdb7c4125","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01NbdR2y4qumcB8BhPe4HcXG","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RR0005/out/figure1.png"}}]}}80{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"5f746925-71d1-4800-9e0a-345a21a75f6e","timestamp":"2026-10-30T05:32:31.002Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"f327f1a0-047a-4866-b598-3d8a9900243b","keep":22,"tail":["7e21ab8749c7e4e1a8e1b6a94d821b8435034eab41d91e8565f284dcdb7c4125","a30b0142bcf5f2b3f857aeb25baa4b489a4e86c1f9229c435e6e9199c11bec32"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"382a57178f68e0e027433789b32f3448e5d8b5c69169cd8124e54ed5ae558aa1"}81{"type":"last-prompt","lastPrompt":"Your","leafUuid":"dc2ab7e5-de20-4d1b-af43-ab6014fa80e4","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}82{"type":"mode","mode":"normal","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}83{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}84{"parentUuid":"dc2ab7e5-de20-4d1b-af43-ab6014fa80e4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXshN79tn87hJTQJYzUv","type":"message","role":"assistant","content":[{"type":"text","text":"Good. Write checks, update ledger, run the gate (P4)."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1125,"cache_read_input_tokens":24557,"output_tokens":1142,"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":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXshMqX94j65zSDZp2r3","requestRef":"5f746925-71d1-4800-9e0a-345a21a75f6e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"898bac6e-e98b-4bf4-927e-c96358f18e5a","timestamp":"2026-10-30T05:32:33.583Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}85{"parentUuid":"898bac6e-e98b-4bf4-927e-c96358f18e5a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXshN79tn87hJTQJYzUv","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TwVrQz1gegyUWqST4TCiLU","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n\n| check | outcome |\n|---|---|\n| Clean re-run (deleted results/figure/table/exclusions, re-ran analysis.py): results.json byte-identical (`cmp`) | PASS |\n| Independent numpy re-implementation (OLS + manual HC3 sandwich): β, α, SE, RMSEs, R² match to <1e-9 | PASS |\n| r² = pearson_r² | PASS (diff < 1e-12) |\n| model_metric = baseline_metric·sqrt(1−R²) (OLS-with-intercept identity) | PASS |\n| model_metric (3.59) < baseline_metric (7.08) | PASS |\n| effect_se > 0; CI [4.85, 5.68] contains β = 5.27 | PASS |\n| Exclusion ledger: 2349 −396 −1736 −20 = 197 = n_analysed; n_excluded_missing = 20 = 217−197 | PASS |\n| table1 n_countries sums to 20+46+58+73 = 197 = n_analysed | PASS |\n| Analysis year rule: complete counts 199 (2015–2022), 197 (2023) ≥150 ⇒ 2023 latest | PASS |\n| All GDP > 0 before log (assert in script) | PASS |\n| SE robustness: HC0 0.207, HC1 0.208, HC2 0.209, HC3 0.211, classical 0.222 — conclusion unchanged | PASS |\n| Trim-5 largest residuals: β = 5.32 (vs 5.27) | PASS (stable) |\n| Figure visually inspected: scatter + fitted line, 197 points, labels correct | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 computed and matched README\",\"schema/missing/duplicates/ranges audited (data_audit.md)\",\"exclusions.csv sums to n_analysed\",\"no info-rule violations\"],\"notes\":\"\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"baseline_metric = mean-only RMSE 7.076 computed over the 197 analysed countries\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, Agg backend, no randomness (random_seed null)\",\"writes results.json, figure1.png, table1.csv, exclusions.csv\"],\"notes\":\"HC3 SE, t(n-2) CI\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean re-run byte-identical\",\"independent numpy recomputation matches\",\"identities in checks.md all PASS\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P1-P3 passed; P4 checks all PASS; running gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Record checks and run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1125,"cache_read_input_tokens":24557,"output_tokens":1142,"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":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXshMqX94j65zSDZp2r3","requestRef":"5f746925-71d1-4800-9e0a-345a21a75f6e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"312cbda2-0a52-47e0-be8c-cbbd870d5851","timestamp":"2026-10-30T05:32:42.109Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"312cbda2-0a52-47e0-be8c-cbbd870d5851","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","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:analysis_year: ok\n  [ok] key:n_excluded_missing: ok\n  [ok] key:baseline_metric: ok\n  [ok] key:model_metric: ok\n  [ok] key:pearson_r: ok\n  [ok] key:r_squared: ok\n  [ok] key:effect_estimate: ok\n  [ok] key:intercept: ok\n  [ok] key:effect_se: ok\n  [ok] key:effect_ci_low: ok\n  [ok] key:effect_ci_high: 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:effect_estimate: 4.851678797609962 <= 5.267173451958655 <= 5.682668106307348\n  [ok] positive:effect_se: 0.21067528691162227\n  [ok] positive:baseline_metric: 7.07645404460588\n  [ok] positive:model_metric: 3.5949979094078177\n  [ok] reproducibility: regenerated in 1.3s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RR0005/out/state/gate_receipts/20261030T053243.502455Z.json","is_error":true,"tool_use_id":"toolu_01TwVrQz1gegyUWqST4TCiLU"}]},"uuid":"dc49ad6c-3d8b-4493-aea8-b3ad92022a38","timestamp":"2026-10-30T05:32:43.510Z","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:analysis_year: ok\n  [ok] key:n_excluded_missing: ok\n  [ok] key:baseline_metric: ok\n  [ok] key:model_metric: ok\n  [ok] key:pearson_r: ok\n  [ok] key:r_squared: ok\n  [ok] key:effect_estimate: ok\n  [ok] key:intercept: ok\n  [ok] key:effect_se: ok\n  [ok] key:effect_ci_low: ok\n  [ok] key:effect_ci_high: 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:effect_estimate: 4.851678797609962 <= 5.267173451958655 <= 5.682668106307348\n  [ok] positive:effect_se: 0.21067528691162227\n  [ok] positive:baseline_metric: 7.07645404460588\n  [ok] positive:model_metric: 3.5949979094078177\n  [ok] reproducibility: regenerated in 1.3s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RR0005/out/state/gate_receipts/20261030T053243.502455Z.json","sandboxed":false,"sourceToolAssistantUUID":"312cbda2-0a52-47e0-be8c-cbbd870d5851","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}87{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"6b745a96fa0c526097f8286aa48548ba03c064843bd134241c6f857a2116bb11","message":{"role":"assistant","content":[{"type":"text","text":"Good. Write checks, update ledger, run the gate (P4)."},{"type":"tool_use","id":"toolu_01TwVrQz1gegyUWqST4TCiLU","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n\n| check | outcome |\n|---|---|\n| Clean re-run (deleted results/figure/table/exclusions, re-ran analysis.py): results.json byte-identical (`cmp`) | PASS |\n| Independent numpy re-implementation (OLS + manual HC3 sandwich): β, α, SE, RMSEs, R² match to <1e-9 | PASS |\n| r² = pearson_r² | PASS (diff < 1e-12) |\n| model_metric = baseline_metric·sqrt(1−R²) (OLS-with-intercept identity) | PASS |\n| model_metric (3.59) < baseline_metric (7.08) | PASS |\n| effect_se > 0; CI [4.85, 5.68] contains β = 5.27 | PASS |\n| Exclusion ledger: 2349 −396 −1736 −20 = 197 = n_analysed; n_excluded_missing = 20 = 217−197 | PASS |\n| table1 n_countries sums to 20+46+58+73 = 197 = n_analysed | PASS |\n| Analysis year rule: complete counts 199 (2015–2022), 197 (2023) ≥150 ⇒ 2023 latest | PASS |\n| All GDP > 0 before log (assert in script) | PASS |\n| SE robustness: HC0 0.207, HC1 0.208, HC2 0.209, HC3 0.211, classical 0.222 — conclusion unchanged | PASS |\n| Trim-5 largest residuals: β = 5.32 (vs 5.27) | PASS (stable) |\n| Figure visually inspected: scatter + fitted line, 197 points, labels correct | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 computed and matched README\",\"schema/missing/duplicates/ranges audited (data_audit.md)\",\"exclusions.csv sums to n_analysed\",\"no info-rule violations\"],\"notes\":\"\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"baseline_metric = mean-only RMSE 7.076 computed over the 197 analysed countries\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, Agg backend, no randomness (random_seed null)\",\"writes results.json, figure1.png, table1.csv, exclusions.csv\"],\"notes\":\"HC3 SE, t(n-2) CI\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean re-run byte-identical\",\"independent numpy recomputation matches\",\"identities in checks.md all PASS\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P1-P3 passed; P4 checks all PASS; running gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Record checks and run gate"}}]}}88{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"982543ee-887a-4b4e-9cf4-c74f4a34756c","timestamp":"2026-10-30T05:32:43.514Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"5f746925-71d1-4800-9e0a-345a21a75f6e","keep":24,"tail":["6b745a96fa0c526097f8286aa48548ba03c064843bd134241c6f857a2116bb11","31f173a20975fb97c24319e59ca194243de3266bcb064847c41f0778bac61bb9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"293745bf94644119d234cc227c9a07b7c21367af5adc8d24ec244809c4b84f0c"}89{"parentUuid":"dc49ad6c-3d8b-4493-aea8-b3ad92022a38","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsiHapGy7ufebFF6LBB","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":2016,"cache_read_input_tokens":25682,"output_tokens":3852,"output_tokens_details":{"thinking_tokens":133},"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":2016},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1499,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsiHKCVfpRAwn41a5B9","requestRef":"982543ee-887a-4b4e-9cf4-c74f4a34756c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"38dedf1e-7e65-4c11-8116-d28cacf25552","timestamp":"2026-10-30T05:32:46.536Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}90{"parentUuid":"38dedf1e-7e65-4c11-8116-d28cacf25552","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsiHapGy7ufebFF6LBB","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"The remaining gate failures are all P5 deliverables not yet written, while the P4 checks pass. I'm writing the report and claims ledger next.\n\n","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":2016,"cache_read_input_tokens":25682,"output_tokens":3852,"output_tokens_details":{"thinking_tokens":133},"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":2016},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1,"thinkingDisplay":"updates","apiBlockIndex":1,"requestId":"req_011CgXsiHKCVfpRAwn41a5B9","requestRef":"982543ee-887a-4b4e-9cf4-c74f4a34756c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f8fc98b9-90da-4e90-935c-d1fa56866746","timestamp":"2026-10-30T05:32:46.537Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}91{"parentUuid":"f8fc98b9-90da-4e90-935c-d1fa56866746","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsiHapGy7ufebFF6LBB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01XALnxLrHGMpgngZYXARcfc","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-dev-01 — Preston curve in World Bank WDI data\n\n## Question\nDoes the cross-country relationship between real income per capita and life expectancy (the Preston curve) hold in the most recent usable year, and how strong is it? The estimand is the slope β of the equal-weighted linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies. LE is life expectancy at birth in years; GDPpc is GDP per capita in PPP constant 2021 international $. β is descriptive (associational), not causal.\n\n## Data and exclusions\nInputs: `data/wb_indicators.csv` (2,349 entity-year rows) and `data/wb_entities.csv` (296 entities) (`n_input_rows`). The SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Exclusion ledger (`out/exclusions.csv`):\n1. Dropped the 79 entities with region `Aggregates`, i.e. 396 rows. That leaves 1,953 rows covering 217 countries/economies.\n2. Kept the analysis year. The number of countries/economies with both indicators is 199 in every year 2015–2022 and 197 in 2023 (`complete_countries_by_year`). The latest year with ≥150 is therefore **2023** (`analysis_year`), which has 217 countries/economies (`n_countries_in_year`).\n3. Dropped the **20** countries/economies with a missing indicator (`n_excluded_missing`). All 20 are missing GDP, none is missing LE. There is no imputation. This leaves **197** analysed countries (`n_analysed`).\n\nThe data problems found and how each was handled are listed in `data_issues`:\n- Aggregates mixed into the indicator file.\n- GDP missingness is non-random. The excluded economies are mostly small high-income territories plus conflict or sanctioned states (CUB, ERI, PRK, SSD, SYR, VEN, YEM).\n- The Central African Republic's LE series is erratic before 2023 (18.8 years in 2022). Its 2023 value of 57.4 is plausible and is kept.\n- LE in West Bank & Gaza fell by about 11.5 years in 2023. Kept as reported.\n\n## Method\n- **Baseline:** predict every country's LE by the sample mean. Its RMSE is `baseline_metric`.\n- **Main model:** OLS of LE on ln(GDPpc), one equally weighted observation per country. I report the in-sample residual RMSE (`model_metric`), R² (`r_squared`) and Pearson r (`pearson_r`).\n- **Uncertainty:** heteroskedasticity-robust standard error, **HC3** (`effect_se_type`). I chose HC3 because it is the most conservative of the HC variants at this sample size. The 95% CI is β ± t₀.₉₇₅(n−2)·SE (`ci_critical_value_t`).\n- **Decision rule:** the conclusion code follows from whether the CI excludes zero.\n- **Sensitivity:** SEs under HC0, HC1, HC2 and the classical formula, and a re-fit after dropping the 5 largest absolute residuals.\n- **Implementation:** `out/analysis.py` reads only `data/`, uses no randomness (`random_seed` = null), and generates `figure1.png` and `table1.csv`.\n\n## Results\n- **Fit:** LE = 22.57 (`intercept`) + 5.267 (`effect_estimate`) × ln(GDPpc), with n = 197 (`n_analysed`).\n- **What the slope means:** a 1-log-point difference in GDP per capita (about 2.7×) goes with 5.27 more years of life expectancy. A doubling goes with about 5.267 × ln 2 ≈ 3.65 years (arithmetic on `effect_estimate`).\n- **Strength:** Pearson r = 0.861 (`pearson_r`) and R² = 0.742 (`r_squared`).\n- **Against the baseline:** residual RMSE is 3.59 years (`model_metric`), versus 7.08 years for the mean-only baseline (`baseline_metric`). That is roughly half the prediction error. The mean LE is 73.5 years (`mean_life_expectancy`).\n- **Conclusion:** `positive_effect` (`conclusion`). The Preston-curve association holds clearly in 2023.\n- **Table 1** (`out/table1.csv`) shows mean LE rising steadily with income group:\n\n| Income group | Countries | Mean LE (years) |\n|---|---|---|\n| Low income | 20 | 63.2 |\n| Lower middle income | 46 | 67.8 |\n| Upper middle income | 58 | 73.7 |\n| High income | 73 | 79.7 |\n\n- **Figure 1** (`out/figure1.png`) shows the scatter with the fitted line.\n\n## Uncertainty\n- **Main interval:** HC3 SE = 0.211 (`effect_se`); 95% CI [4.85, 5.68] (`effect_ci_low`, `effect_ci_high`); t ≈ 25 (`effect_t_stat`).\n- **Other SE formulas:** HC0 0.207 (`sensitivity_se_hc0`), HC1 0.208 (`sensitivity_se_hc1`), HC2 0.209 (`sensitivity_se_hc2`), classical 0.222 (`sensitivity_se_classical`). None of these changes the conclusion.\n- **Influence of outliers:** dropping the 5 largest residuals (NGA, GRL, NRU, GNQ, GUY; `sensitivity_trim5_dropped_iso3`) gives β = 5.32 (`sensitivity_trim5_effect`), well inside the main CI.\n- **What the CI means:** the sample is nearly the whole population of economies. The interval therefore describes sampling uncertainty under a superpopulation view of countries, not uncertainty about which countries are included.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n  - The 2023 values may be revised later, or may be WDI model-based estimates/projections rather than measurements. This is not verifiable from the files.\n  - Missingness may be non-random. The 20 excluded economies include rich microstates (e.g. Monaco, Liechtenstein) and low-LE conflict states (South Sudan, Yemen). Including them could move β in either direction; I did not quantify this.\n  - The definition of the aggregates could be wrong. I relied on the `Aggregates` flag.\n- **Specification threats:**\n  - The linear-in-log form is a summary. The curve visibly flattens and spreads at high income, where several rich economies sit well below the line.\n  - β is an equal-weighted cross-country association. It is neither population-weighted nor causal. Confounders such as health systems, disease environment and institutions, and reverse causality from health to income, are not addressed.\n  - Countries are not independent (regional clustering, spatial correlation). The robust SE does not account for this, so the CI may be too narrow.\n- **Not checked:**\n  - Other years. The year is fixed by the rule; I estimated no other year.\n  - Nonlinear or regional specifications.\n  - Measurement error in PPP GDP, which would attenuate β.\n  - Leverage diagnostics beyond the trim-5 refit.\n- **Data quirks:** the Central African Republic's erratic pre-2023 LE series and the West Bank & Gaza 2023 drop indicate data-quality and shock issues. In 2023 they affect single observations only.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The analysis year is 2023, with 197 countries/economies analysed and 20 excluded for a missing indicator (all missing GDP).\",\"results_keys\":[\"analysis_year\",\"n_analysed\",\"n_excluded_missing\",\"complete_countries_by_year\"],\"status\":\"supported\",\"caveat\":\"Year determined mechanically by the >=150 rule.\"},\n {\"id\":\"C2\",\"text\":\"Life expectancy rises by about 5.27 years per log-point of GDP per capita (OLS slope, intercept 22.57).\",\"results_keys\":[\"effect_estimate\",\"intercept\"],\"status\":\"supported\",\"caveat\":\"Descriptive, equal-weighted association; not causal.\"},\n {\"id\":\"C3\",\"text\":\"The 95% HC3-robust CI [4.85, 5.68] lies entirely above zero, so the conclusion is positive_effect.\",\"results_keys\":[\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\",\"effect_se_type\"],\"status\":\"supported\",\"caveat\":\"Assumes independent countries; spatial/regional dependence not addressed.\"},\n {\"id\":\"C4\",\"text\":\"The relationship is strong: r = 0.86, R^2 = 0.74, and log income roughly halves prediction error relative to the mean-only baseline (RMSE 3.59 vs 7.08 years).\",\"results_keys\":[\"pearson_r\",\"r_squared\",\"model_metric\",\"baseline_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; no out-of-sample evaluation.\"},\n {\"id\":\"C5\",\"text\":\"The inference is robust to the choice of SE estimator (HC0-HC3, classical) and to dropping the 5 largest residuals (slope 5.32).\",\"results_keys\":[\"sensitivity_se_hc0\",\"sensitivity_se_hc1\",\"sensitivity_se_hc2\",\"sensitivity_se_classical\",\"sensitivity_trim5_effect\",\"sensitivity_trim5_dropped_iso3\"],\"status\":\"supported\",\"caveat\":\"Does not address bias from non-random missingness of the 20 excluded economies.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json,glob,os\nr=sorted(glob.glob('out/state/gate_receipts/*.json'))\np=json.load(open('out/state/phases.json'))\np['P4']['status']='passed'; p['P4']['checks'].append(f\"gate run {os.path.basename(r[-1])}: reproducibility/CI/SE/exclusion checks ok; remaining failures were P5 artifacts not yet written\")\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, every number cites a results key\",\"claims.json written, keys resolve\",\"final gate run (see receipts)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P4 passed (gate receipt recorded); P5 report+claims written; running final gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"","description":"Write report and claims, 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":2016,"cache_read_input_tokens":25682,"output_tokens":3852,"output_tokens_details":{"thinking_tokens":133},"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":2016},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsiHKCVfpRAwn41a5B9","requestRef":"982543ee-887a-4b4e-9cf4-c74f4a34756c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d88ed677-eff7-49f2-804a-3f0abcfaa5f5","timestamp":"2026-10-30T05:33:16.691Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}92{"parentUuid":"d88ed677-eff7-49f2-804a-3f0abcfaa5f5","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01XALnxLrHGMpgngZYXARcfc","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RR0005/out/state/gate_receipts/20261030T053318.119818Z.json","is_error":false}]},"uuid":"7aa19420-3d57-473b-9b1a-958be6dfa45a","timestamp":"2026-10-30T05:33:18.129Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RR0005/out/state/gate_receipts/20261030T053318.119818Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d88ed677-eff7-49f2-804a-3f0abcfaa5f5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}93{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"428f1d8c2b7383ad9deee970f019b24ac18ed0eefd8beda9b541c37adfede60b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"thinking","thinking":"The remaining gate failures are all P5 deliverables not yet written, while the P4 checks pass. I'm writing the report and claims ledger next.\n\n","signature":"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"},{"type":"tool_use","id":"toolu_01XALnxLrHGMpgngZYXARcfc","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-dev-01 — Preston curve in World Bank WDI data\n\n## Question\nDoes the cross-country relationship between real income per capita and life expectancy (the Preston curve) hold in the most recent usable year, and how strong is it? The estimand is the slope β of the equal-weighted linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies. LE is life expectancy at birth in years; GDPpc is GDP per capita in PPP constant 2021 international $. β is descriptive (associational), not causal.\n\n## Data and exclusions\nInputs: `data/wb_indicators.csv` (2,349 entity-year rows) and `data/wb_entities.csv` (296 entities) (`n_input_rows`). The SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Exclusion ledger (`out/exclusions.csv`):\n1. Dropped the 79 entities with region `Aggregates`, i.e. 396 rows. That leaves 1,953 rows covering 217 countries/economies.\n2. Kept the analysis year. The number of countries/economies with both indicators is 199 in every year 2015–2022 and 197 in 2023 (`complete_countries_by_year`). The latest year with ≥150 is therefore **2023** (`analysis_year`), which has 217 countries/economies (`n_countries_in_year`).\n3. Dropped the **20** countries/economies with a missing indicator (`n_excluded_missing`). All 20 are missing GDP, none is missing LE. There is no imputation. This leaves **197** analysed countries (`n_analysed`).\n\nThe data problems found and how each was handled are listed in `data_issues`:\n- Aggregates mixed into the indicator file.\n- GDP missingness is non-random. The excluded economies are mostly small high-income territories plus conflict or sanctioned states (CUB, ERI, PRK, SSD, SYR, VEN, YEM).\n- The Central African Republic's LE series is erratic before 2023 (18.8 years in 2022). Its 2023 value of 57.4 is plausible and is kept.\n- LE in West Bank & Gaza fell by about 11.5 years in 2023. Kept as reported.\n\n## Method\n- **Baseline:** predict every country's LE by the sample mean. Its RMSE is `baseline_metric`.\n- **Main model:** OLS of LE on ln(GDPpc), one equally weighted observation per country. I report the in-sample residual RMSE (`model_metric`), R² (`r_squared`) and Pearson r (`pearson_r`).\n- **Uncertainty:** heteroskedasticity-robust standard error, **HC3** (`effect_se_type`). I chose HC3 because it is the most conservative of the HC variants at this sample size. The 95% CI is β ± t₀.₉₇₅(n−2)·SE (`ci_critical_value_t`).\n- **Decision rule:** the conclusion code follows from whether the CI excludes zero.\n- **Sensitivity:** SEs under HC0, HC1, HC2 and the classical formula, and a re-fit after dropping the 5 largest absolute residuals.\n- **Implementation:** `out/analysis.py` reads only `data/`, uses no randomness (`random_seed` = null), and generates `figure1.png` and `table1.csv`.\n\n## Results\n- **Fit:** LE = 22.57 (`intercept`) + 5.267 (`effect_estimate`) × ln(GDPpc), with n = 197 (`n_analysed`).\n- **What the slope means:** a 1-log-point difference in GDP per capita (about 2.7×) goes with 5.27 more years of life expectancy. A doubling goes with about 5.267 × ln 2 ≈ 3.65 years (arithmetic on `effect_estimate`).\n- **Strength:** Pearson r = 0.861 (`pearson_r`) and R² = 0.742 (`r_squared`).\n- **Against the baseline:** residual RMSE is 3.59 years (`model_metric`), versus 7.08 years for the mean-only baseline (`baseline_metric`). That is roughly half the prediction error. The mean LE is 73.5 years (`mean_life_expectancy`).\n- **Conclusion:** `positive_effect` (`conclusion`). The Preston-curve association holds clearly in 2023.\n- **Table 1** (`out/table1.csv`) shows mean LE rising steadily with income group:\n\n| Income group | Countries | Mean LE (years) |\n|---|---|---|\n| Low income | 20 | 63.2 |\n| Lower middle income | 46 | 67.8 |\n| Upper middle income | 58 | 73.7 |\n| High income | 73 | 79.7 |\n\n- **Figure 1** (`out/figure1.png`) shows the scatter with the fitted line.\n\n## Uncertainty\n- **Main interval:** HC3 SE = 0.211 (`effect_se`); 95% CI [4.85, 5.68] (`effect_ci_low`, `effect_ci_high`); t ≈ 25 (`effect_t_stat`).\n- **Other SE formulas:** HC0 0.207 (`sensitivity_se_hc0`), HC1 0.208 (`sensitivity_se_hc1`), HC2 0.209 (`sensitivity_se_hc2`), classical 0.222 (`sensitivity_se_classical`). None of these changes the conclusion.\n- **Influence of outliers:** dropping the 5 largest residuals (NGA, GRL, NRU, GNQ, GUY; `sensitivity_trim5_dropped_iso3`) gives β = 5.32 (`sensitivity_trim5_effect`), well inside the main CI.\n- **What the CI means:** the sample is nearly the whole population of economies. The interval therefore describes sampling uncertainty under a superpopulation view of countries, not uncertainty about which countries are included.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n  - The 2023 values may be revised later, or may be WDI model-based estimates/projections rather than measurements. This is not verifiable from the files.\n  - Missingness may be non-random. The 20 excluded economies include rich microstates (e.g. Monaco, Liechtenstein) and low-LE conflict states (South Sudan, Yemen). Including them could move β in either direction; I did not quantify this.\n  - The definition of the aggregates could be wrong. I relied on the `Aggregates` flag.\n- **Specification threats:**\n  - The linear-in-log form is a summary. The curve visibly flattens and spreads at high income, where several rich economies sit well below the line.\n  - β is an equal-weighted cross-country association. It is neither population-weighted nor causal. Confounders such as health systems, disease environment and institutions, and reverse causality from health to income, are not addressed.\n  - Countries are not independent (regional clustering, spatial correlation). The robust SE does not account for this, so the CI may be too narrow.\n- **Not checked:**\n  - Other years. The year is fixed by the rule; I estimated no other year.\n  - Nonlinear or regional specifications.\n  - Measurement error in PPP GDP, which would attenuate β.\n  - Leverage diagnostics beyond the trim-5 refit.\n- **Data quirks:** the Central African Republic's erratic pre-2023 LE series and the West Bank & Gaza 2023 drop indicate data-quality and shock issues. In 2023 they affect single observations only.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The analysis year is 2023, with 197 countries/economies analysed and 20 excluded for a missing indicator (all missing GDP).\",\"results_keys\":[\"analysis_year\",\"n_analysed\",\"n_excluded_missing\",\"complete_countries_by_year\"],\"status\":\"supported\",\"caveat\":\"Year determined mechanically by the >=150 rule.\"},\n {\"id\":\"C2\",\"text\":\"Life expectancy rises by about 5.27 years per log-point of GDP per capita (OLS slope, intercept 22.57).\",\"results_keys\":[\"effect_estimate\",\"intercept\"],\"status\":\"supported\",\"caveat\":\"Descriptive, equal-weighted association; not causal.\"},\n {\"id\":\"C3\",\"text\":\"The 95% HC3-robust CI [4.85, 5.68] lies entirely above zero, so the conclusion is positive_effect.\",\"results_keys\":[\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\",\"effect_se_type\"],\"status\":\"supported\",\"caveat\":\"Assumes independent countries; spatial/regional dependence not addressed.\"},\n {\"id\":\"C4\",\"text\":\"The relationship is strong: r = 0.86, R^2 = 0.74, and log income roughly halves prediction error relative to the mean-only baseline (RMSE 3.59 vs 7.08 years).\",\"results_keys\":[\"pearson_r\",\"r_squared\",\"model_metric\",\"baseline_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; no out-of-sample evaluation.\"},\n {\"id\":\"C5\",\"text\":\"The inference is robust to the choice of SE estimator (HC0-HC3, classical) and to dropping the 5 largest residuals (slope 5.32).\",\"results_keys\":[\"sensitivity_se_hc0\",\"sensitivity_se_hc1\",\"sensitivity_se_hc2\",\"sensitivity_se_classical\",\"sensitivity_trim5_effect\",\"sensitivity_trim5_dropped_iso3\"],\"status\":\"supported\",\"caveat\":\"Does not address bias from non-random missingness of the 20 excluded economies.\"}\n]\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json,glob,os\nr=sorted(glob.glob('out/state/gate_receipts/*.json'))\np=json.load(open('out/state/phases.json'))\np['P4']['status']='passed'; p['P4']['checks'].append(f\"gate run {os.path.basename(r[-1])}: reproducibility/CI/SE/exclusion checks ok; remaining failures were P5 artifacts not yet written\")\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, every number cites a results key\",\"claims.json written, keys resolve\",\"final gate run (see receipts)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P4 passed (gate receipt recorded); P5 report+claims written; running final gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"","description":"Write report and claims, run final gate"}}]}}94{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"77c6ef82-5779-4594-aaed-9ea32b23ebcb","timestamp":"2026-10-30T05:33:18.132Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"982543ee-887a-4b4e-9cf4-c74f4a34756c","keep":26,"tail":["428f1d8c2b7383ad9deee970f019b24ac18ed0eefd8beda9b541c37adfede60b","0c45bee7495536738f0eb1de490f7ddf562263b8216877c1b659e3a544fa6f55"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b1c3687d36026d524f5e7e7f7b56ee8a5ac359c0108588c3f2b8b134c46a39d9"}95{"type":"last-prompt","lastPrompt":"Your","leafUuid":"7aa19420-3d57-473b-9b1a-958be6dfa45a","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}96{"type":"mode","mode":"normal","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}97{"type":"atis-latch","atis":"","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}98{"parentUuid":"7aa19420-3d57-473b-9b1a-958be6dfa45a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXskqdSrpCkKAvntwPZZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013mVtKKLtTyVyTUM4tQaStY","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 20261030T053318.119818Z.json: PASSED 0/40 failed\"\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: final gate PASSED (20261030T053318.119818Z). Task complete pending review.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record final receipt and re-confirm gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3947,"cache_read_input_tokens":27698,"output_tokens":287,"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":3947},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXskqLLRRfaKUX5gfJ3m","requestRef":"77c6ef82-5779-4594-aaed-9ea32b23ebcb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"01c10c76-45f1-4269-bcc4-701e6328b964","timestamp":"2026-10-30T05:33:21.303Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}99{"parentUuid":"01c10c76-45f1-4269-bcc4-701e6328b964","isSidechain":false,"promptId":"8cf9c76d-cc8f-4a3c-ada1-82155060e425","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013mVtKKLtTyVyTUM4tQaStY","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","is_error":false}]},"uuid":"87f1a6dd-a7d3-4fbd-8097-54ff6e88a0d2","timestamp":"2026-10-30T05:33:22.578Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"01c10c76-45f1-4269-bcc4-701e6328b964","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}100{"type":"api-request-blob","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","hash":"5b6cfa27f2d9729311e8525a013860c17e1bdb5810a0d30a256e8a0e0bd5864a","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_013mVtKKLtTyVyTUM4tQaStY","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 20261030T053318.119818Z.json: PASSED 0/40 failed\"\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: final gate PASSED (20261030T053318.119818Z). Task complete pending review.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record final receipt and re-confirm gate"}}]}}101{"type":"api-request","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","id":"2c096e28-4b1d-4047-88c3-8804716a7555","timestamp":"2026-10-30T05:33:22.581Z","version":"2.1.314","querySource":"sdk","shapeHash":"43321f9204cce4cb417874a8c0ce8f99cacb9ae4499fa6951140d245a4da2c2e","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":"77c6ef82-5779-4594-aaed-9ea32b23ebcb","keep":28,"tail":["5b6cfa27f2d9729311e8525a013860c17e1bdb5810a0d30a256e8a0e0bd5864a","69c800d27095b4af07975d11729c2ff0ebf5aa45deb6d979dcf7985f18297249"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9df1d90896005cac8f71ebdd30b98fc107a9358d57f737c1a22db0fc3dccda61"}102{"parentUuid":"87f1a6dd-a7d3-4fbd-8097-54ff6e88a0d2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmAeSosQYG5jfAWn8a","type":"message","role":"assistant","content":[{"type":"text","text":"I've finished the analysis: the Preston curve holds clearly in the 2023 World Bank data, with life expectancy rising by about 5.27 years per log-point of GDP per capita. The final gate check passes with 0 of 40 failures, and re-running `out/analysis.py` from scratch gives byte-identical results.\n\n**How the sample was built:** 2023 is the most recent year with both indicators for at least 150 countries or economies (it has 197). After removing regional and income-group aggregates, I excluded 20 more because they have no GDP figure for 2023. That leaves 197 in the estimate, with no imputation.\n\n**Results (OLS fit):**\n- **Fitted line:** life expectancy = 22.57 + 5.267 × ln(GDP per capita). A doubling of income goes with about 3.65 more years of life expectancy.\n- **Uncertainty:** the robust standard error (HC3) is 0.211, giving a 95% confidence interval of [4.85, 5.68]. It lies entirely above zero, so the conclusion code is `positive_effect`.\n- **Strength:** the correlation is 0.861 and R² is 0.742.\n- **Against the baseline:** prediction error falls from 7.08 years (predicting everyone at the average) to 3.59 years with log income.\n- **Robustness:** the conclusion holds under the other standard-error formulas (HC0–HC2 and classical: 0.207–0.222). Dropping the five largest outliers moves the slope only to 5.32.\n- **I checked the numbers twice:** a separate hand-written numpy calculation matches the main results to within 1e-9.\n\n**Limitations (discussed in the report):**\n- **Missing countries may bias the slope:** the 20 excluded economies are mostly small rich territories and conflict or sanctioned states. Including them could move the estimate either way, and I didn't measure how much.\n- **The interval may be too narrow:** it assumes countries are independent, which ignores regional clustering.\n- **Recent figures may not be measurements:** 2023 values may be World Bank estimates or projections rather than recorded data, and could be revised.\n- **The straight line is a simplification:** the curve visibly flattens and spreads out at high incomes.\n- **Data quirks:** the Central African Republic's life-expectancy series is erratic before 2023 (18.8 years in 2022), though its 2023 value of 57.4 is plausible and kept. West Bank & Gaza fell by about 11.5 years in 2023, kept as reported.\n- **Descriptive only:** this is an association across countries, not a causal effect.\n\nEverything is in `out/`. The main files are:\n- `results.json`\n- `report.md`\n- `analysis.py`\n- `claims.json`\n- `figure1.png`\n- `table1.csv`\n\nThe working records (data audit, checks, log and gate receipts) are in `out/state/`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":327,"cache_read_input_tokens":31645,"output_tokens":952,"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":327},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsmAMpMfhnRR4AxWrUL","requestRef":"2c096e28-4b1d-4047-88c3-8804716a7555","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5bbad7a2-7e3b-471c-b0cc-c53359d7d917","timestamp":"2026-10-30T05:33:32.034Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0005","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","version":"2.1.314","gitBranch":"HEAD"}103{"type":"last-prompt","lastPrompt":"Your","leafUuid":"5bbad7a2-7e3b-471c-b0cc-c53359d7d917","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d"}104{"type":"cost-state","sessionId":"70279af9-39a8-4800-87a6-70f5188d6a6d","totalCostUSD":0.5109798,"totalAPIDuration":149048,"totalAPIDurationWithoutRetries":149036,"totalToolDuration":7893,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":157149,"startTime":1793338253501,"modelUsage":{"claude-opus-5-5":{"inputTokens":32,"outputTokens":15608,"thinkingTokens":696,"cacheReadInputTokens":231759,"cacheCreationInputTokens":30468,"cacheCreationEphemeral5mInputTokens":30468,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.5109798}},"hasUnknownModelCost":false}105