{"type":"atis-latch","atis":"","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:33:58.980Z","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","content":"Review"} {"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:33:58.986Z","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"parentUuid":null,"isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":"Review"},"uuid":"a28c7141-b1e8-4528-af51-c56504711875","timestamp":"2026-10-30T05:33:58.990Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-shape","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","timestamp":"2026-10-30T05:33:59.004Z","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/RR0006\nDate: 2026-10-30\n\nYou are an independent scientific reviewer. In the current working directory, `TASK.md` describes a bounded scientific task and the directory `out/` contains the deliverables submitted by another assistant (you have not seen how they were produced and you must not look for their working transcript). There is no network access. Use `~/wp29/venv/bin/python` if you need to re-run or test code. Do not modify any file under `out/` except that you must create `out/review/review.json`.\n\nReview the deliverables against `TASK.md` only. Specifically check:\n1. Does `out/results.json` contain every required key with legitimately computed values? Re-run `out/analysis.py` in a scratch copy if needed and compare.\n2. Are the information-availability rules of `TASK.md` respected by the code (for example no use of future information, no use of forbidden inputs)? Read the code to verify; do not trust the report.\n3. Are the central claims in `out/report.md` and `out/claims.json` supported by the numbers in `out/results.json`, with appropriate uncertainty and caveats? Flag any claim that is stronger than the evidence.\n4. Are counts, exclusions, units, signs and magnitudes internally consistent? Are baseline comparisons present when the task requires them?\n5. Are limitations stated honestly? Is anything declared complete that is not?\n\nYou have no reference answers; do not guess what the \"right\" number is. Report only issues you can justify from the files. Write `out/review/review.json` as {\"verdict\": \"accept\"|\"revise\", \"issues\": [{\"id\": \"R1\", \"severity\": \"critical\"|\"major\"|\"minor\", \"location\": \"\", \"issue\": \"...\", \"suggested_fix\": \"...\"}], \"summary\": \"...\"}. Use \"revise\" if there is at least one critical or major issue. Be concise and specific. End with a one-paragraph plain-text summary.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"6d7ffc2f-8809-4573-b633-4eff30d01e38","timestamp":"2026-10-30T05:33:59.004Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":["99833769e4310fc124186eb9e97416cea64dc8ececb015cbe8928bf0c2bd9984","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ab8ee141a4d0c1f0565c9cfc18598bc9e33d8ac2188bd6f50ffb11da93ebc446"} {"parentUuid":"a28c7141-b1e8-4528-af51-c56504711875","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"1a1c6e6c-7238-45eb-883a-f3d01125ea64","timestamp":"2026-10-30T05:33:58.995Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"1a1c6e6c-7238-45eb-883a-f3d01125ea64","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"6f55818d-2703-4a50-bd5d-1025652636d3","timestamp":"2026-10-30T05:33:58.995Z","rendered":[{"content":"\nToday's date is 2026-10-30.\n"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"6f55818d-2703-4a50-bd5d-1025652636d3","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 ","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"b1d712fd-210c-4398-a7aa-1ce1cef91899","timestamp":"2026-10-30T05:33:58.996Z","rendered":[{"content":"\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 \n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"tools-used","tools":["Bash"],"sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"parentUuid":"b1d712fd-210c-4398-a7aa-1ce1cef91899","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsovJpaHbiWs27oo4Rj","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":716,"cache_read_input_tokens":1504,"output_tokens":144,"output_tokens_details":{"thinking_tokens":17},"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":105,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsov3wDyqLawQfjM4z1","requestRef":"6d7ffc2f-8809-4573-b633-4eff30d01e38","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"94cdfc04-e89b-4366-b2c0-9d32592ff086","timestamp":"2026-10-30T05:34:01.478Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"94cdfc04-e89b-4366-b2c0-9d32592ff086","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsovJpaHbiWs27oo4Rj","type":"message","role":"assistant","content":[{"type":"text","text":"I'll start by reading the task and the deliverables."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":716,"cache_read_input_tokens":1504,"output_tokens":144,"output_tokens_details":{"thinking_tokens":17},"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsov3wDyqLawQfjM4z1","requestRef":"6d7ffc2f-8809-4573-b633-4eff30d01e38","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8f19cc09-6cc8-43af-92bc-95fde9186890","timestamp":"2026-10-30T05:34:01.848Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"8f19cc09-6cc8-43af-92bc-95fde9186890","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsovJpaHbiWs27oo4Rj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01AM7zPFAyDPeRLPFwLj4RiT","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Show task, deliverables list, results and claims"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":716,"cache_read_input_tokens":1504,"output_tokens":144,"output_tokens_details":{"thinking_tokens":17},"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsov3wDyqLawQfjM4z1","requestRef":"6d7ffc2f-8809-4573-b633-4eff30d01e38","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"93024381-07fe-4f2a-8a55-508fbff11769","timestamp":"2026-10-30T05:34:02.625Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"93024381-07fe-4f2a-8a55-508fbff11769","isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01AM7zPFAyDPeRLPFwLj4RiT","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 208\ndrwxr-xr-x@ 11 simon-pierreboucher staff 352 oct. 30 01:33 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:31 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 8855 oct. 30 01:32 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 1831 oct. 30 01:33 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 621 oct. 30 01:32 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 67512 oct. 30 01:32 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 6889 oct. 30 01:33 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 2703 oct. 30 01:32 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:33 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 01:33 state\n-rw-r--r--@ 1 simon-pierreboucher staff 214 oct. 30 01:32 table1.csv\n{\n \"task_id\": \"F6-dev-01\",\n \"analysis_year\": 2023,\n \"n_excluded_missing\": 20,\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_ci_low\": 4.854257477179233,\n \"effect_ci_high\": 5.6800894267380775,\n \"conclusion\": \"positive_effect\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"wb_indicators.csv contains 44 regional/income/other aggregate entities mixed with countries/economies\",\n \"handling\": \"excluded via region == 'Aggregates' in wb_entities.csv\"\n },\n {\n \"issue\": \"20 countries/economies in 2023 lack an indicator (GDPpc missing: 20, LE missing: 0): ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM; mostly small territories and conflict/sanctioned economies, so missingness is not random\",\n \"handling\": \"excluded from the estimate, counted in n_excluded_missing; no imputation\"\n },\n {\n \"issue\": \"implausibly large year-to-year life-expectancy swings (>10 years) in: CAF (max |dLE|=38.6), SSD (max |dLE|=16.6), PSE (max |dLE|=11.5); e.g. CAF LE 18.8 in 2022 vs 57.4 in 2023; PSE 2023 LE 65.2 vs 76.7 in 2022 (plausibly war-related; not verified)\",\n \"handling\": \"only 2023 values enter the estimate; values kept as published (no editing); influence checked with leave-one-out slopes\"\n },\n {\n \"issue\": \"4 entity names in wb_entities.csv carry trailing whitespace\",\n \"handling\": \"cosmetic; joins use iso3 only\"\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 \"se_type\": \"HC3\",\n \"ci_method\": \"beta +/- 1.959964 * HC3 SE (normal approximation)\",\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 \"n_countries_in_year\": 217,\n \"n_aggregate_entities_excluded\": 44,\n \"effect_se_hc0\": 0.20736485591704354,\n \"effect_se_hc1\": 0.2084255526375312,\n \"effect_se_hc2\": 0.20901105806015902,\n \"effect_se_hc3\": 0.21067528691162227,\n \"effect_se_classical\": 0.22246758287864518,\n \"loo_slope_min\": 5.205387994234399,\n \"loo_slope_min_dropped\": \"TCD\",\n \"loo_slope_max\": 5.327563424394044,\n \"loo_slope_max_dropped\": \"GRL\",\n \"rmse_reduction_share\": 0.491977495120151,\n \"le_gain_per_doubling_gdp\": 3.650926427745336,\n \"mean_life_expectancy\": 73.47408158883249,\n \"mean_log_gdp_pc\": 9.664953946043608\n}[\n {\"id\":\"C1\",\"text\":\"The analysis year is 2023, the most recent year with at least 150 countries/economies having both indicators; 197 countries are analysed and 20 are excluded for missing GDP per capita.\",\"results_keys\":[\"analysis_year\",\"n_analysed\",\"n_excluded_missing\",\"complete_countries_by_year\"],\"status\":\"supported\",\"caveat\":\"Excluded economies are not missing at random.\"},\n {\"id\":\"C2\",\"text\":\"In 2023 the OLS slope of life expectancy on ln(GDP per capita) is about 5.27 years per log-point (about 3.65 years per doubling of income).\",\"results_keys\":[\"effect_estimate\",\"intercept\",\"le_gain_per_doubling_gdp\"],\"status\":\"supported\",\"caveat\":\"Descriptive linear projection, not a causal effect; equal country weights.\"},\n {\"id\":\"C3\",\"text\":\"The association is positive and statistically clear: the HC3-robust 95% CI [4.85, 5.68] excludes zero (conclusion positive_effect).\",\"results_keys\":[\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\",\"se_type\"],\"status\":\"supported\",\"caveat\":\"Assumes independent countries; ignores measurement error and selection from missing data.\"},\n {\"id\":\"C4\",\"text\":\"The relationship is strong: r = 0.86, R^2 = 0.74, and log income cuts the RMSE of life expectancy from 7.08 years (mean-only baseline) to 3.59 years.\",\"results_keys\":[\"pearson_r\",\"r_squared\",\"baseline_metric\",\"model_metric\",\"rmse_reduction_share\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; nonlinearity at high income not tested.\"},\n {\"id\":\"C5\",\"text\":\"The slope is robust to the choice of HC estimator and to dropping any single country (leave-one-out range 5.21 to 5.33).\",\"results_keys\":[\"effect_se_hc0\",\"effect_se_hc1\",\"effect_se_hc2\",\"effect_se_hc3\",\"effect_se_classical\",\"loo_slope_min\",\"loo_slope_max\"],\"status\":\"supported\",\"caveat\":\"Does not address joint influence of groups of countries or other years.\"}\n]","is_error":false}]},"uuid":"a23abc39-dbe1-4ea7-a23f-572800efd94c","timestamp":"2026-10-30T05:34:02.704Z","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 208\ndrwxr-xr-x@ 11 simon-pierreboucher staff 352 oct. 30 01:33 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:31 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 8855 oct. 30 01:32 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 1831 oct. 30 01:33 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 621 oct. 30 01:32 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 67512 oct. 30 01:32 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 6889 oct. 30 01:33 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 2703 oct. 30 01:32 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:33 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 01:33 state\n-rw-r--r--@ 1 simon-pierreboucher staff 214 oct. 30 01:32 table1.csv\n{\n \"task_id\": \"F6-dev-01\",\n \"analysis_year\": 2023,\n \"n_excluded_missing\": 20,\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_ci_low\": 4.854257477179233,\n \"effect_ci_high\": 5.6800894267380775,\n \"conclusion\": \"positive_effect\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"wb_indicators.csv contains 44 regional/income/other aggregate entities mixed with countries/economies\",\n \"handling\": \"excluded via region == 'Aggregates' in wb_entities.csv\"\n },\n {\n \"issue\": \"20 countries/economies in 2023 lack an indicator (GDPpc missing: 20, LE missing: 0): ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM; mostly small territories and conflict/sanctioned economies, so missingness is not random\",\n \"handling\": \"excluded from the estimate, counted in n_excluded_missing; no imputation\"\n },\n {\n \"issue\": \"implausibly large year-to-year life-expectancy swings (>10 years) in: CAF (max |dLE|=38.6), SSD (max |dLE|=16.6), PSE (max |dLE|=11.5); e.g. CAF LE 18.8 in 2022 vs 57.4 in 2023; PSE 2023 LE 65.2 vs 76.7 in 2022 (plausibly war-related; not verified)\",\n \"handling\": \"only 2023 values enter the estimate; values kept as published (no editing); influence checked with leave-one-out slopes\"\n },\n {\n \"issue\": \"4 entity names in wb_entities.csv carry trailing whitespace\",\n \"handling\": \"cosmetic; joins use iso3 only\"\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 \"se_type\": \"HC3\",\n \"ci_method\": \"beta +/- 1.959964 * HC3 SE (normal approximation)\",\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 \"n_countries_in_year\": 217,\n \"n_aggregate_entities_excluded\": 44,\n \"effect_se_hc0\": 0.20736485591704354,\n \"effect_se_hc1\": 0.2084255526375312,\n \"effect_se_hc2\": 0.20901105806015902,\n \"effect_se_hc3\": 0.21067528691162227,\n \"effect_se_classical\": 0.22246758287864518,\n \"loo_slope_min\": 5.205387994234399,\n \"loo_slope_min_dropped\": \"TCD\",\n \"loo_slope_max\": 5.327563424394044,\n \"loo_slope_max_dropped\": \"GRL\",\n \"rmse_reduction_share\": 0.491977495120151,\n \"le_gain_per_doubling_gdp\": 3.650926427745336,\n \"mean_life_expectancy\": 73.47408158883249,\n \"mean_log_gdp_pc\": 9.664953946043608\n}[\n {\"id\":\"C1\",\"text\":\"The analysis year is 2023, the most recent year with at least 150 countries/economies having both indicators; 197 countries are analysed and 20 are excluded for missing GDP per capita.\",\"results_keys\":[\"analysis_year\",\"n_analysed\",\"n_excluded_missing\",\"complete_countries_by_year\"],\"status\":\"supported\",\"caveat\":\"Excluded economies are not missing at random.\"},\n {\"id\":\"C2\",\"text\":\"In 2023 the OLS slope of life expectancy on ln(GDP per capita) is about 5.27 years per log-point (about 3.65 years per doubling of income).\",\"results_keys\":[\"effect_estimate\",\"intercept\",\"le_gain_per_doubling_gdp\"],\"status\":\"supported\",\"caveat\":\"Descriptive linear projection, not a causal effect; equal country weights.\"},\n {\"id\":\"C3\",\"text\":\"The association is positive and statistically clear: the HC3-robust 95% CI [4.85, 5.68] excludes zero (conclusion positive_effect).\",\"results_keys\":[\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\",\"se_type\"],\"status\":\"supported\",\"caveat\":\"Assumes independent countries; ignores measurement error and selection from missing data.\"},\n {\"id\":\"C4\",\"text\":\"The relationship is strong: r = 0.86, R^2 = 0.74, and log income cuts the RMSE of life expectancy from 7.08 years (mean-only baseline) to 3.59 years.\",\"results_keys\":[\"pearson_r\",\"r_squared\",\"baseline_metric\",\"model_metric\",\"rmse_reduction_share\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; nonlinearity at high income not tested.\"},\n {\"id\":\"C5\",\"text\":\"The slope is robust to the choice of HC estimator and to dropping any single country (leave-one-out range 5.21 to 5.33).\",\"results_keys\":[\"effect_se_hc0\",\"effect_se_hc1\",\"effect_se_hc2\",\"effect_se_hc3\",\"effect_se_classical\",\"loo_slope_min\",\"loo_slope_max\"],\"status\":\"supported\",\"caveat\":\"Does not address joint influence of groups of countries or other years.\"}\n]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"93024381-07fe-4f2a-8a55-508fbff11769","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"a52952476122352270dad23cff9248c9ae248e7f62cd2b1f854e43b1231ea6d9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"I'll start by reading the task and the deliverables."},{"type":"tool_use","id":"toolu_01AM7zPFAyDPeRLPFwLj4RiT","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Show task, deliverables list, results and claims"}}]}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"79f6a059-4dcd-4b6e-9021-190dc08e995e","timestamp":"2026-10-30T05:34:02.709Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":"6d7ffc2f-8809-4573-b633-4eff30d01e38","keep":2,"tail":["a52952476122352270dad23cff9248c9ae248e7f62cd2b1f854e43b1231ea6d9","17300427f375d457266ce784f3cfbce20ec8101b6c44f2a271160a943283d2f6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"23006c85162f7dce1cd1d18911f2dddc6d24c664b7b33f25bc3f8ac1ee4fa6b6"} {"type":"last-prompt","lastPrompt":"Review","leafUuid":"a23abc39-dbe1-4ea7-a23f-572800efd94c","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"type":"atis-latch","atis":"","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"parentUuid":"a23abc39-dbe1-4ea7-a23f-572800efd94c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsp831t38oR25yuZqQu","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013ofciXEi4RYMAjGxYRwnB6","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/table1.csv; cat out/exclusions.csv; ls out/state","description":"Show code, report, table, exclusions"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4899,"cache_read_input_tokens":2220,"output_tokens":123,"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":4899},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsp7me6vxdjDtNoFBPJ","requestRef":"79f6a059-4dcd-4b6e-9021-190dc08e995e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a4ea447c-6375-4648-a2bb-e237ad6d1699","timestamp":"2026-10-30T05:34:04.675Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"a4ea447c-6375-4648-a2bb-e237ad6d1699","isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013ofciXEi4RYMAjGxYRwnB6","type":"tool_result","content":"\"\"\"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 recorded as 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\nDATA, OUT = \"data\", \"out\"\nMIN_COUNTRIES = 150\nHC = \"HC3\"\nZ = 1.959963984540054 # 97.5% standard-normal quantile\n\nind = pd.read_csv(os.path.join(DATA, \"wb_indicators.csv\"), keep_default_na=False, na_values=[\"\"])\nent = pd.read_csv(os.path.join(DATA, \"wb_entities.csv\"), keep_default_na=False, na_values=[\"\"])\nn_input_rows = {\"wb_indicators.csv\": int(len(ind)), \"wb_entities.csv\": int(len(ent))}\ndata_issues = []\nexcl = []\n\ndef log_ex(step, rule, before, after, why):\n excl.append(dict(step=step, rule=rule, n_before=int(before), n_after=int(after),\n n_removed=int(before - after), rationale=why))\n\n# --- integrity checks ---\nassert not ind.duplicated([\"iso3\", \"year\"]).any(), \"duplicate iso3-year rows\"\nassert not ent.duplicated(\"iso3\").any(), \"duplicate entity rows\"\nunmatched = sorted(set(ind.iso3) - set(ent.iso3))\nif unmatched:\n data_issues.append({\"issue\": f\"{len(unmatched)} indicator iso3 codes absent from entity metadata: {unmatched}\",\n \"handling\": \"excluded (country status cannot be verified)\"})\nassert (ind.gdp_pc_ppp.dropna() > 0).all(), \"non-positive GDP per capita\"\n\nm = ind.merge(ent[[\"iso3\", \"region\", \"income_level\"]], on=\"iso3\", how=\"left\")\nn0 = len(m)\nm = m[m.region.notna()]\nlog_ex(1, \"drop indicator rows whose iso3 is not in wb_entities.csv\", n0, len(m),\n \"country/aggregate status cannot be established\")\nn1 = len(m)\nn_agg = m.loc[m.region == \"Aggregates\", \"iso3\"].nunique()\nc = m[m.region != \"Aggregates\"].copy()\nlog_ex(2, \"drop entities with region == 'Aggregates' (all years)\", n1, len(c),\n f\"information rule: countries/economies only ({n_agg} aggregate entities)\")\ndata_issues.append({\"issue\": f\"wb_indicators.csv contains {n_agg} regional/income/other aggregate entities \"\n \"mixed with countries/economies\",\n \"handling\": \"excluded via region == 'Aggregates' in wb_entities.csv\"})\n\n# --- analysis year selection ---\nc[\"complete\"] = c.gdp_pc_ppp.notna() & c.life_expectancy.notna()\ncounts = c.groupby(\"year\")[\"complete\"].sum().astype(int)\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\nn2 = len(c)\ny = c[c.year == year].copy()\nlog_ex(3, f\"keep analysis year {year} only\", n2, len(y),\n f\"most recent year with >= {MIN_COUNTRIES} countries having both indicators\")\nn3 = len(y)\nmiss = y[~y.complete]\nd = y[y.complete].copy()\nn_excluded_missing = int(len(miss))\nlog_ex(4, \"drop countries with GDPpc or LE missing in analysis year (no imputation)\", n3, len(d),\n \"information rule; missing: \" + \"; \".join(miss.iso3))\nmiss_g = int(miss.gdp_pc_ppp.isna().sum()); miss_l = int(miss.life_expectancy.isna().sum())\ndata_issues.append({\"issue\": f\"{n_excluded_missing} countries/economies in {year} lack an indicator \"\n f\"(GDPpc missing: {miss_g}, LE missing: {miss_l}): {', '.join(miss.iso3)}; \"\n \"mostly small territories and conflict/sanctioned economies, so missingness is not random\",\n \"handling\": \"excluded from the estimate, counted in n_excluded_missing; no imputation\"})\n\n# anomalies outside the analysis year (documented, not used)\nle_p = c.pivot(index=\"iso3\", columns=\"year\", values=\"life_expectancy\")\njumps = le_p.diff(axis=1).abs().max(axis=1)\nbig = jumps[jumps > 10].sort_values(ascending=False)\nif len(big):\n data_issues.append({\"issue\": \"implausibly large year-to-year life-expectancy swings (>10 years) in: \"\n + \", \".join(f\"{k} (max |dLE|={v:.1f})\" for k, v in big.items())\n + \"; e.g. CAF LE 18.8 in 2022 vs 57.4 in 2023; PSE 2023 LE 65.2 vs 76.7 in 2022 (plausibly war-related; not verified)\",\n \"handling\": f\"only {year} values enter the estimate; values kept as published (no editing); \"\n \"influence checked with leave-one-out slopes\"})\naggname = ent[ent.name != ent.name.str.strip()]\nif len(aggname):\n data_issues.append({\"issue\": f\"{len(aggname)} entity names in wb_entities.csv carry trailing whitespace\",\n \"handling\": \"cosmetic; joins use iso3 only\"})\n\n# --- estimation ---\nd[\"log_gdp_pc\"] = np.log(d.gdp_pc_ppp)\nx = d.log_gdp_pc.to_numpy(); le = d.life_expectancy.to_numpy()\nn = len(d)\nbaseline_rmse = float(np.sqrt(np.mean((le - le.mean()) ** 2)))\nX = sm.add_constant(x)\nfit = sm.OLS(le, X).fit(cov_type=HC)\nalpha, beta = (float(v) for v in fit.params)\nse = float(fit.bse[1])\nresid = le - (alpha + beta * x)\nmodel_rmse = float(np.sqrt(np.mean(resid ** 2)))\nr = float(np.corrcoef(x, le)[0, 1])\nr2 = float(fit.rsquared)\nlo, hi = beta - Z * se, beta + Z * se\nse_hc = {h: float(sm.OLS(le, X).fit(cov_type=h).bse[1]) for h in [\"HC0\", \"HC1\", \"HC2\", \"HC3\"]}\nse_classical = float(sm.OLS(le, X).fit().bse[1])\n\n# leave-one-out influence\nloo = []\nfor i in range(n):\n k = np.arange(n) != i\n b = np.polyfit(x[k], le[k], 1)[0]\n loo.append(b)\nloo = np.array(loo)\niso = d.iso3.to_numpy()\n\nif lo > 0:\n concl = \"positive_effect\"\nelif hi < 0:\n concl = \"negative_effect\"\nelse:\n concl = \"no_detectable_effect\"\n\nresults = {\n \"task_id\": \"F6-dev-01\",\n \"analysis_year\": year,\n \"n_excluded_missing\": n_excluded_missing,\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_ci_low\": float(lo),\n \"effect_ci_high\": float(hi),\n \"conclusion\": concl,\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 # supplementary diagnostics\n \"se_type\": HC,\n \"ci_method\": \"beta +/- 1.959964 * HC3 SE (normal approximation)\",\n \"complete_countries_by_year\": {str(k): int(v) for k, v in counts.items()},\n \"n_countries_in_year\": int(n3),\n \"n_aggregate_entities_excluded\": int(n_agg),\n \"effect_se_hc0\": se_hc[\"HC0\"], \"effect_se_hc1\": se_hc[\"HC1\"],\n \"effect_se_hc2\": se_hc[\"HC2\"], \"effect_se_hc3\": se_hc[\"HC3\"],\n \"effect_se_classical\": se_classical,\n \"loo_slope_min\": float(loo.min()), \"loo_slope_min_dropped\": str(iso[loo.argmin()]),\n \"loo_slope_max\": float(loo.max()), \"loo_slope_max_dropped\": str(iso[loo.argmax()]),\n \"rmse_reduction_share\": float(1 - model_rmse / baseline_rmse),\n \"le_gain_per_doubling_gdp\": float(beta * np.log(2)),\n \"mean_life_expectancy\": float(le.mean()),\n \"mean_log_gdp_pc\": float(x.mean()),\n}\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n# --- table ---\norder = [\"Low income\", \"Lower middle income\", \"Upper middle income\", \"High income\"]\nt = (d.groupby(\"income_level\")\n .agg(n_countries=(\"iso3\", \"size\"), mean_log_gdp_pc=(\"log_gdp_pc\", \"mean\"),\n mean_life_expectancy=(\"life_expectancy\", \"mean\"))\n .reset_index())\nt[\"k\"] = t.income_level.map({v: i for i, v in enumerate(order)}).fillna(99)\nt = t.sort_values([\"k\", \"income_level\"]).drop(columns=\"k\")\nassert t.n_countries.sum() == n\nt.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n# --- exclusions ledger ---\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\n os.path.join(OUT, \"exclusions.csv\"), index=False)\n\n# --- figure ---\nfig, ax = plt.subplots(figsize=(7.5, 5.2))\ncols = dict(zip(order, [\"#d7191c\", \"#fdae61\", \"#abd9e9\", \"#2c7bb6\"]))\nfor lvl in order:\n s = d[d.income_level == lvl]\n ax.scatter(s.log_gdp_pc, s.life_expectancy, s=18, alpha=0.8, color=cols[lvl], label=f\"{lvl} (n={len(s)})\")\nxx = np.linspace(x.min(), x.max(), 100)\nax.plot(xx, alpha + beta * xx, color=\"k\", lw=1.5,\n 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=8, loc=\"lower right\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(f\"year={year} n={n} excluded_missing={n_excluded_missing} beta={beta:.4f} se({HC})={se:.4f} \"\n f\"CI=[{lo:.4f},{hi:.4f}] r={r:.4f} R2={r2:.4f} RMSE base={baseline_rmse:.4f} model={model_rmse:.4f} -> {concl}\")\n# F6-dev-01 — Preston curve in the latest usable WDI year\n\n## Question\nDoes the cross-country relationship between real income per capita and life expectancy hold in the most recent year with usable World Bank data, and how strong is it? Estimand: the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i over countries/economies (equal weights) in the analysis year, with heteroskedasticity-robust uncertainty. The interpretation is descriptive (associational), not causal.\n\n## Data and exclusions\nInputs: `data/wb_indicators.csv` (2349 rows) and `data/wb_entities.csv` (296 rows) (`n_input_rows`); SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Exclusion ledger (`out/exclusions.csv`):\n\n1. Indicator rows with an iso3 absent from the entity file: 0 removed (all matched).\n2. Entities with region `Aggregates`: 44 aggregate entities × 9 years = 396 rows removed (`n_aggregate_entities_excluded`).\n3. Analysis-year restriction: the number of countries/economies with both indicators is 199 in every year 2015–2022 and 197 in 2023 (`complete_countries_by_year`), so the most recent year with ≥150 is **2023** (`analysis_year`); 1736 rows of other years removed, leaving 217 countries/economies (`n_countries_in_year`).\n4. Countries missing an indicator in 2023: 20 removed (`n_excluded_missing`), all because GDP per capita is missing (life expectancy is never missing): ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM. No imputation.\n\nAnalysed: 197 countries/economies (`n_analysed`); 2349 − 2152 removed = 197. Data issues found and how they were handled are listed in `data_issues`. They include implausibly large year-to-year life-expectancy swings outside 2023 (e.g. Central African Republic at 18.8 years in 2022), which do not enter the estimate, and a sharp 2023 drop for West Bank and Gaza (65.2 vs 76.7 in 2022), which does enter it and was kept as published.\n\n## Method\n- Baseline: predict every country's LE by the sample mean; the metric is the RMSE (`baseline_metric`).\n- Main model: OLS of LE on the natural log of GDP per capita (PPP, constant 2021 $), one equally weighted observation per country. Model fit is the residual RMSE (`model_metric`) computed with the same rule, plus R² (`r_squared`) and the Pearson correlation (`pearson_r`).\n- Uncertainty: **HC3** heteroskedasticity-robust SE for β (`effect_se`, `se_type`). The 95% CI is β ± 1.96·SE (normal approximation, `ci_method`). HC0/HC1/HC2 and classical SEs are reported for comparison. Leave-one-out slopes measure the influence of single countries.\n- Conclusion rule: `positive_effect` if the 95% CI lies above zero.\n- No randomness is used (`random_seed` = null). `out/analysis.py` regenerates `results.json`, `figure1.png`, `table1.csv` and `exclusions.csv` from `data/` alone.\n\n## Results\n- In 2023, across 197 countries, the OLS slope is **β = 5.27 years of life expectancy per log-point of GDP per capita** (`effect_estimate` = 5.267). The intercept is 22.57 years (`intercept`). One log-point is about a 2.72× income ratio. Doubling income goes with about 3.65 more years (`le_gain_per_doubling_gdp`).\n- Strength: Pearson r = 0.861 (`pearson_r`), R² = 0.742 (`r_squared`). The residual RMSE is 3.59 years (`model_metric`), against 7.08 years for the mean-only baseline (`baseline_metric`). That is a 49% reduction in RMSE (`rmse_reduction_share`).\n- Conclusion: `positive_effect` (`conclusion`). The Preston-curve association holds clearly in 2023.\n- Table 1 (`out/table1.csv`): mean LE rises steadily across income groups: Low income 63.2 years (n=20), Lower middle 67.8 (n=46), Upper middle 73.7 (n=58), High 79.7 (n=73). These figures are produced by `analysis.py` but are not keys in results.json; the group counts sum to `n_analysed`.\n- Figure 1 (`out/figure1.png`): scatter with the fitted line, coloured by income group.\n\n## Uncertainty\nHC3 SE = 0.211 (`effect_se`), giving a 95% CI of [4.85, 5.68] years per log-point (`effect_ci_low`, `effect_ci_high`). The choice of SE type matters little: HC0 0.207, HC1 0.208, HC2 0.209, classical 0.222 (`effect_se_hc0`, `effect_se_hc1`, `effect_se_hc2`, `effect_se_classical`). Dropping any single country moves β only within [5.21, 5.33] (`loo_slope_min`, dropping TCD; `loo_slope_max`, dropping GRL). This CI covers sampling-type variation only, under the assumption that countries are independent observations. It does not cover measurement error in the WDI series, model misspecification, or the selection effects described below.\n\n## Limitations and open issues\n- **Not causal.** β is a descriptive linear projection. Income is correlated with health systems, education, institutions and geography, and causality runs both ways (health also raises income). Nothing here identifies the effect of raising income.\n- **Non-random missingness.** The 20 excluded economies (`n_excluded_missing`) lack GDP data, not life expectancy. They are mostly small high-income territories (Monaco, Liechtenstein, Channel Islands, …) and conflict-affected or sanctioned economies (South Sudan, Syria, Yemen, Venezuela, DPRK, Eritrea, Cuba). The second group probably sits at low income or low LE. Leaving out both tails could bias β in either direction. I did not quantify this, because the rules forbid imputation.\n- **Data quality.** WDI life expectancy for 2023 comes largely from modelled UN WPP estimates rather than direct vital registration in many countries. The audit found implausible swings in some series (CAF, SSD, PSE; `data_issues`). Only PSE's 2023 value enters the estimate, and leave-one-out shows no single country drives β. PPP GDP for small or conflict-affected economies is also uncertain. Errors in ln(GDPpc) would attenuate β.\n- **Functional form.** One linear-in-log slope summarises a relationship that may flatten at high income. The figure shows several high-income economies well below the line. I did not test nonlinearity, piecewise slopes, or residual patterns by region. Robust SEs keep the inference valid for the linear projection, but β should not be read as a constant marginal gradient.\n- **Equal weighting.** Tiny economies count as much as China or India. A population-weighted estimand would answer a different question; it was not computed.\n- **Single cross-section.** Only 2023 is analysed. Stability across 2015–2022 (including the COVID-19 years) was not checked.\n- **Independence.** Countries within a region share shocks, so cross-sectional dependence could make the SEs too small. Clustered or spatial SEs were not computed.\n- What would invalidate the result: a systematic error in the 2023 WDI vintage, a mis-classification of aggregates as countries (checked: all 44 aggregate codes are excluded), or a different reading of the year-selection rule. Under the stated rule, 2023 qualifies (197 ≥ 150).\nincome_level,n_countries,mean_log_gdp_pc,mean_life_expectancy\nLow income,20,7.610046,63.188050\nLower middle income,46,8.689852,67.809452\nUpper middle income,58,9.689900,73.695373\nHigh income,73,10.822570,79.685845\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop indicator rows whose iso3 is not in wb_entities.csv,2349,2349,0,country/aggregate status cannot be established\n2,drop entities with region == 'Aggregates' (all years),2349,1953,396,information rule: countries/economies only (44 aggregate entities)\n3,keep analysis year 2023 only,1953,217,1736,most recent year with >= 150 countries having both indicators\n4,drop countries with GDPpc or LE missing in analysis year (no imputation),217,197,20,information rule; missing: ASM; CHI; CUB; ERI; GIB; GUM; IMN; LIE; MAF; MCO; MNP; NCL; PRK; PYF; SSD; SYR; VEN; VGB; VIR; YEM\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","is_error":false}]},"uuid":"e240490f-fe5d-4623-9daa-3c05c0e55a64","timestamp":"2026-10-30T05:34:04.708Z","toolUseResult":{"stdout":"\"\"\"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 recorded as 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\nDATA, OUT = \"data\", \"out\"\nMIN_COUNTRIES = 150\nHC = \"HC3\"\nZ = 1.959963984540054 # 97.5% standard-normal quantile\n\nind = pd.read_csv(os.path.join(DATA, \"wb_indicators.csv\"), keep_default_na=False, na_values=[\"\"])\nent = pd.read_csv(os.path.join(DATA, \"wb_entities.csv\"), keep_default_na=False, na_values=[\"\"])\nn_input_rows = {\"wb_indicators.csv\": int(len(ind)), \"wb_entities.csv\": int(len(ent))}\ndata_issues = []\nexcl = []\n\ndef log_ex(step, rule, before, after, why):\n excl.append(dict(step=step, rule=rule, n_before=int(before), n_after=int(after),\n n_removed=int(before - after), rationale=why))\n\n# --- integrity checks ---\nassert not ind.duplicated([\"iso3\", \"year\"]).any(), \"duplicate iso3-year rows\"\nassert not ent.duplicated(\"iso3\").any(), \"duplicate entity rows\"\nunmatched = sorted(set(ind.iso3) - set(ent.iso3))\nif unmatched:\n data_issues.append({\"issue\": f\"{len(unmatched)} indicator iso3 codes absent from entity metadata: {unmatched}\",\n \"handling\": \"excluded (country status cannot be verified)\"})\nassert (ind.gdp_pc_ppp.dropna() > 0).all(), \"non-positive GDP per capita\"\n\nm = ind.merge(ent[[\"iso3\", \"region\", \"income_level\"]], on=\"iso3\", how=\"left\")\nn0 = len(m)\nm = m[m.region.notna()]\nlog_ex(1, \"drop indicator rows whose iso3 is not in wb_entities.csv\", n0, len(m),\n \"country/aggregate status cannot be established\")\nn1 = len(m)\nn_agg = m.loc[m.region == \"Aggregates\", \"iso3\"].nunique()\nc = m[m.region != \"Aggregates\"].copy()\nlog_ex(2, \"drop entities with region == 'Aggregates' (all years)\", n1, len(c),\n f\"information rule: countries/economies only ({n_agg} aggregate entities)\")\ndata_issues.append({\"issue\": f\"wb_indicators.csv contains {n_agg} regional/income/other aggregate entities \"\n \"mixed with countries/economies\",\n \"handling\": \"excluded via region == 'Aggregates' in wb_entities.csv\"})\n\n# --- analysis year selection ---\nc[\"complete\"] = c.gdp_pc_ppp.notna() & c.life_expectancy.notna()\ncounts = c.groupby(\"year\")[\"complete\"].sum().astype(int)\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\nn2 = len(c)\ny = c[c.year == year].copy()\nlog_ex(3, f\"keep analysis year {year} only\", n2, len(y),\n f\"most recent year with >= {MIN_COUNTRIES} countries having both indicators\")\nn3 = len(y)\nmiss = y[~y.complete]\nd = y[y.complete].copy()\nn_excluded_missing = int(len(miss))\nlog_ex(4, \"drop countries with GDPpc or LE missing in analysis year (no imputation)\", n3, len(d),\n \"information rule; missing: \" + \"; \".join(miss.iso3))\nmiss_g = int(miss.gdp_pc_ppp.isna().sum()); miss_l = int(miss.life_expectancy.isna().sum())\ndata_issues.append({\"issue\": f\"{n_excluded_missing} countries/economies in {year} lack an indicator \"\n f\"(GDPpc missing: {miss_g}, LE missing: {miss_l}): {', '.join(miss.iso3)}; \"\n \"mostly small territories and conflict/sanctioned economies, so missingness is not random\",\n \"handling\": \"excluded from the estimate, counted in n_excluded_missing; no imputation\"})\n\n# anomalies outside the analysis year (documented, not used)\nle_p = c.pivot(index=\"iso3\", columns=\"year\", values=\"life_expectancy\")\njumps = le_p.diff(axis=1).abs().max(axis=1)\nbig = jumps[jumps > 10].sort_values(ascending=False)\nif len(big):\n data_issues.append({\"issue\": \"implausibly large year-to-year life-expectancy swings (>10 years) in: \"\n + \", \".join(f\"{k} (max |dLE|={v:.1f})\" for k, v in big.items())\n + \"; e.g. CAF LE 18.8 in 2022 vs 57.4 in 2023; PSE 2023 LE 65.2 vs 76.7 in 2022 (plausibly war-related; not verified)\",\n \"handling\": f\"only {year} values enter the estimate; values kept as published (no editing); \"\n \"influence checked with leave-one-out slopes\"})\naggname = ent[ent.name != ent.name.str.strip()]\nif len(aggname):\n data_issues.append({\"issue\": f\"{len(aggname)} entity names in wb_entities.csv carry trailing whitespace\",\n \"handling\": \"cosmetic; joins use iso3 only\"})\n\n# --- estimation ---\nd[\"log_gdp_pc\"] = np.log(d.gdp_pc_ppp)\nx = d.log_gdp_pc.to_numpy(); le = d.life_expectancy.to_numpy()\nn = len(d)\nbaseline_rmse = float(np.sqrt(np.mean((le - le.mean()) ** 2)))\nX = sm.add_constant(x)\nfit = sm.OLS(le, X).fit(cov_type=HC)\nalpha, beta = (float(v) for v in fit.params)\nse = float(fit.bse[1])\nresid = le - (alpha + beta * x)\nmodel_rmse = float(np.sqrt(np.mean(resid ** 2)))\nr = float(np.corrcoef(x, le)[0, 1])\nr2 = float(fit.rsquared)\nlo, hi = beta - Z * se, beta + Z * se\nse_hc = {h: float(sm.OLS(le, X).fit(cov_type=h).bse[1]) for h in [\"HC0\", \"HC1\", \"HC2\", \"HC3\"]}\nse_classical = float(sm.OLS(le, X).fit().bse[1])\n\n# leave-one-out influence\nloo = []\nfor i in range(n):\n k = np.arange(n) != i\n b = np.polyfit(x[k], le[k], 1)[0]\n loo.append(b)\nloo = np.array(loo)\niso = d.iso3.to_numpy()\n\nif lo > 0:\n concl = \"positive_effect\"\nelif hi < 0:\n concl = \"negative_effect\"\nelse:\n concl = \"no_detectable_effect\"\n\nresults = {\n \"task_id\": \"F6-dev-01\",\n \"analysis_year\": year,\n \"n_excluded_missing\": n_excluded_missing,\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_ci_low\": float(lo),\n \"effect_ci_high\": float(hi),\n \"conclusion\": concl,\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 # supplementary diagnostics\n \"se_type\": HC,\n \"ci_method\": \"beta +/- 1.959964 * HC3 SE (normal approximation)\",\n \"complete_countries_by_year\": {str(k): int(v) for k, v in counts.items()},\n \"n_countries_in_year\": int(n3),\n \"n_aggregate_entities_excluded\": int(n_agg),\n \"effect_se_hc0\": se_hc[\"HC0\"], \"effect_se_hc1\": se_hc[\"HC1\"],\n \"effect_se_hc2\": se_hc[\"HC2\"], \"effect_se_hc3\": se_hc[\"HC3\"],\n \"effect_se_classical\": se_classical,\n \"loo_slope_min\": float(loo.min()), \"loo_slope_min_dropped\": str(iso[loo.argmin()]),\n \"loo_slope_max\": float(loo.max()), \"loo_slope_max_dropped\": str(iso[loo.argmax()]),\n \"rmse_reduction_share\": float(1 - model_rmse / baseline_rmse),\n \"le_gain_per_doubling_gdp\": float(beta * np.log(2)),\n \"mean_life_expectancy\": float(le.mean()),\n \"mean_log_gdp_pc\": float(x.mean()),\n}\n\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n# --- table ---\norder = [\"Low income\", \"Lower middle income\", \"Upper middle income\", \"High income\"]\nt = (d.groupby(\"income_level\")\n .agg(n_countries=(\"iso3\", \"size\"), mean_log_gdp_pc=(\"log_gdp_pc\", \"mean\"),\n mean_life_expectancy=(\"life_expectancy\", \"mean\"))\n .reset_index())\nt[\"k\"] = t.income_level.map({v: i for i, v in enumerate(order)}).fillna(99)\nt = t.sort_values([\"k\", \"income_level\"]).drop(columns=\"k\")\nassert t.n_countries.sum() == n\nt.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n# --- exclusions ledger ---\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]).to_csv(\n os.path.join(OUT, \"exclusions.csv\"), index=False)\n\n# --- figure ---\nfig, ax = plt.subplots(figsize=(7.5, 5.2))\ncols = dict(zip(order, [\"#d7191c\", \"#fdae61\", \"#abd9e9\", \"#2c7bb6\"]))\nfor lvl in order:\n s = d[d.income_level == lvl]\n ax.scatter(s.log_gdp_pc, s.life_expectancy, s=18, alpha=0.8, color=cols[lvl], label=f\"{lvl} (n={len(s)})\")\nxx = np.linspace(x.min(), x.max(), 100)\nax.plot(xx, alpha + beta * xx, color=\"k\", lw=1.5,\n 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=8, loc=\"lower right\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n\nprint(f\"year={year} n={n} excluded_missing={n_excluded_missing} beta={beta:.4f} se({HC})={se:.4f} \"\n f\"CI=[{lo:.4f},{hi:.4f}] r={r:.4f} R2={r2:.4f} RMSE base={baseline_rmse:.4f} model={model_rmse:.4f} -> {concl}\")\n# F6-dev-01 — Preston curve in the latest usable WDI year\n\n## Question\nDoes the cross-country relationship between real income per capita and life expectancy hold in the most recent year with usable World Bank data, and how strong is it? Estimand: the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i over countries/economies (equal weights) in the analysis year, with heteroskedasticity-robust uncertainty. The interpretation is descriptive (associational), not causal.\n\n## Data and exclusions\nInputs: `data/wb_indicators.csv` (2349 rows) and `data/wb_entities.csv` (296 rows) (`n_input_rows`); SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Exclusion ledger (`out/exclusions.csv`):\n\n1. Indicator rows with an iso3 absent from the entity file: 0 removed (all matched).\n2. Entities with region `Aggregates`: 44 aggregate entities × 9 years = 396 rows removed (`n_aggregate_entities_excluded`).\n3. Analysis-year restriction: the number of countries/economies with both indicators is 199 in every year 2015–2022 and 197 in 2023 (`complete_countries_by_year`), so the most recent year with ≥150 is **2023** (`analysis_year`); 1736 rows of other years removed, leaving 217 countries/economies (`n_countries_in_year`).\n4. Countries missing an indicator in 2023: 20 removed (`n_excluded_missing`), all because GDP per capita is missing (life expectancy is never missing): ASM, CHI, CUB, ERI, GIB, GUM, IMN, LIE, MAF, MCO, MNP, NCL, PRK, PYF, SSD, SYR, VEN, VGB, VIR, YEM. No imputation.\n\nAnalysed: 197 countries/economies (`n_analysed`); 2349 − 2152 removed = 197. Data issues found and how they were handled are listed in `data_issues`. They include implausibly large year-to-year life-expectancy swings outside 2023 (e.g. Central African Republic at 18.8 years in 2022), which do not enter the estimate, and a sharp 2023 drop for West Bank and Gaza (65.2 vs 76.7 in 2022), which does enter it and was kept as published.\n\n## Method\n- Baseline: predict every country's LE by the sample mean; the metric is the RMSE (`baseline_metric`).\n- Main model: OLS of LE on the natural log of GDP per capita (PPP, constant 2021 $), one equally weighted observation per country. Model fit is the residual RMSE (`model_metric`) computed with the same rule, plus R² (`r_squared`) and the Pearson correlation (`pearson_r`).\n- Uncertainty: **HC3** heteroskedasticity-robust SE for β (`effect_se`, `se_type`). The 95% CI is β ± 1.96·SE (normal approximation, `ci_method`). HC0/HC1/HC2 and classical SEs are reported for comparison. Leave-one-out slopes measure the influence of single countries.\n- Conclusion rule: `positive_effect` if the 95% CI lies above zero.\n- No randomness is used (`random_seed` = null). `out/analysis.py` regenerates `results.json`, `figure1.png`, `table1.csv` and `exclusions.csv` from `data/` alone.\n\n## Results\n- In 2023, across 197 countries, the OLS slope is **β = 5.27 years of life expectancy per log-point of GDP per capita** (`effect_estimate` = 5.267). The intercept is 22.57 years (`intercept`). One log-point is about a 2.72× income ratio. Doubling income goes with about 3.65 more years (`le_gain_per_doubling_gdp`).\n- Strength: Pearson r = 0.861 (`pearson_r`), R² = 0.742 (`r_squared`). The residual RMSE is 3.59 years (`model_metric`), against 7.08 years for the mean-only baseline (`baseline_metric`). That is a 49% reduction in RMSE (`rmse_reduction_share`).\n- Conclusion: `positive_effect` (`conclusion`). The Preston-curve association holds clearly in 2023.\n- Table 1 (`out/table1.csv`): mean LE rises steadily across income groups: Low income 63.2 years (n=20), Lower middle 67.8 (n=46), Upper middle 73.7 (n=58), High 79.7 (n=73). These figures are produced by `analysis.py` but are not keys in results.json; the group counts sum to `n_analysed`.\n- Figure 1 (`out/figure1.png`): scatter with the fitted line, coloured by income group.\n\n## Uncertainty\nHC3 SE = 0.211 (`effect_se`), giving a 95% CI of [4.85, 5.68] years per log-point (`effect_ci_low`, `effect_ci_high`). The choice of SE type matters little: HC0 0.207, HC1 0.208, HC2 0.209, classical 0.222 (`effect_se_hc0`, `effect_se_hc1`, `effect_se_hc2`, `effect_se_classical`). Dropping any single country moves β only within [5.21, 5.33] (`loo_slope_min`, dropping TCD; `loo_slope_max`, dropping GRL). This CI covers sampling-type variation only, under the assumption that countries are independent observations. It does not cover measurement error in the WDI series, model misspecification, or the selection effects described below.\n\n## Limitations and open issues\n- **Not causal.** β is a descriptive linear projection. Income is correlated with health systems, education, institutions and geography, and causality runs both ways (health also raises income). Nothing here identifies the effect of raising income.\n- **Non-random missingness.** The 20 excluded economies (`n_excluded_missing`) lack GDP data, not life expectancy. They are mostly small high-income territories (Monaco, Liechtenstein, Channel Islands, …) and conflict-affected or sanctioned economies (South Sudan, Syria, Yemen, Venezuela, DPRK, Eritrea, Cuba). The second group probably sits at low income or low LE. Leaving out both tails could bias β in either direction. I did not quantify this, because the rules forbid imputation.\n- **Data quality.** WDI life expectancy for 2023 comes largely from modelled UN WPP estimates rather than direct vital registration in many countries. The audit found implausible swings in some series (CAF, SSD, PSE; `data_issues`). Only PSE's 2023 value enters the estimate, and leave-one-out shows no single country drives β. PPP GDP for small or conflict-affected economies is also uncertain. Errors in ln(GDPpc) would attenuate β.\n- **Functional form.** One linear-in-log slope summarises a relationship that may flatten at high income. The figure shows several high-income economies well below the line. I did not test nonlinearity, piecewise slopes, or residual patterns by region. Robust SEs keep the inference valid for the linear projection, but β should not be read as a constant marginal gradient.\n- **Equal weighting.** Tiny economies count as much as China or India. A population-weighted estimand would answer a different question; it was not computed.\n- **Single cross-section.** Only 2023 is analysed. Stability across 2015–2022 (including the COVID-19 years) was not checked.\n- **Independence.** Countries within a region share shocks, so cross-sectional dependence could make the SEs too small. Clustered or spatial SEs were not computed.\n- What would invalidate the result: a systematic error in the 2023 WDI vintage, a mis-classification of aggregates as countries (checked: all 44 aggregate codes are excluded), or a different reading of the year-selection rule. Under the stated rule, 2023 qualifies (197 ≥ 150).\nincome_level,n_countries,mean_log_gdp_pc,mean_life_expectancy\nLow income,20,7.610046,63.188050\nLower middle income,46,8.689852,67.809452\nUpper middle income,58,9.689900,73.695373\nHigh income,73,10.822570,79.685845\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop indicator rows whose iso3 is not in wb_entities.csv,2349,2349,0,country/aggregate status cannot be established\n2,drop entities with region == 'Aggregates' (all years),2349,1953,396,information rule: countries/economies only (44 aggregate entities)\n3,keep analysis year 2023 only,1953,217,1736,most recent year with >= 150 countries having both indicators\n4,drop countries with GDPpc or LE missing in analysis year (no imputation),217,197,20,information rule; missing: ASM; CHI; CUB; ERI; GIB; GUM; IMN; LIE; MAF; MCO; MNP; NCL; PRK; PYF; SSD; SYR; VEN; VGB; VIR; YEM\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a4ea447c-6375-4648-a2bb-e237ad6d1699","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"3d1a46c6da4a3b316eed6f90f3a748273f60940788860daf0c49243a7ab5f25d","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_013ofciXEi4RYMAjGxYRwnB6","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/table1.csv; cat out/exclusions.csv; ls out/state","description":"Show code, report, table, exclusions"}}]}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"5f23f1b3-2a36-4ebf-8b8f-e774a6d3f337","timestamp":"2026-10-30T05:34:04.712Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":"79f6a059-4dcd-4b6e-9021-190dc08e995e","keep":4,"tail":["3d1a46c6da4a3b316eed6f90f3a748273f60940788860daf0c49243a7ab5f25d","45cb96485af3c04734e2e9763c939f564c572abc71faa6c600c1a5b32211522e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"313b1e79fa2a8f094083206e3188a16d6f3a6bc4f1caa0a3227963bfeb9d6503"} {"type":"last-prompt","lastPrompt":"Review","leafUuid":"e240490f-fe5d-4623-9daa-3c05c0e55a64","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"type":"atis-latch","atis":"","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"parentUuid":"e240490f-fe5d-4623-9daa-3c05c0e55a64","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspGcwMqdyKAeERRbMX","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":7464,"cache_read_input_tokens":7119,"output_tokens":523,"output_tokens_details":{"thinking_tokens":195},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":7464},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1825,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXspGM5BM9YFPPWMQ96F","requestRef":"5f23f1b3-2a36-4ebf-8b8f-e774a6d3f337","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"73192bc7-310d-46a4-86d7-73b177c877a9","timestamp":"2026-10-30T05:34:08.004Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"73192bc7-310d-46a4-86d7-73b177c877a9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspGcwMqdyKAeERRbMX","type":"message","role":"assistant","content":[{"type":"text","text":"Now I'll re-run the analysis in a scratch copy and check the data on my own."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7464,"cache_read_input_tokens":7119,"output_tokens":523,"output_tokens_details":{"thinking_tokens":195},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":7464},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXspGM5BM9YFPPWMQ96F","requestRef":"5f23f1b3-2a36-4ebf-8b8f-e774a6d3f337","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5161ccaf-57c2-4b09-9bd4-24200f77f8cc","timestamp":"2026-10-30T05:34:08.004Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"5161ccaf-57c2-4b09-9bd4-24200f77f8cc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspGcwMqdyKAeERRbMX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0192YgsvYtqnHbnBt1bQtb6J","name":"Bash","input":{"command":"S=$(mktemp -d); cp -r data $S/; mkdir $S/out; cp out/analysis.py $S/out/; cd $S && ~/wp29/venv/bin/python out/analysis.py && ~/wp29/venv/bin/python -c \"\nimport json\na=json.load(open('out/results.json'));b=json.load(open('$OLDPWD/out/results.json'))\nprint([k for k in set(a)|set(b) if a.get(k)!=b.get(k)])\n\"; diff out/table1.csv $OLDPWD/out/table1.csv && echo tableok; cat $OLDPWD/data/README.md | head -60","description":"Re-run analysis in scratch dir and compare outputs"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7464,"cache_read_input_tokens":7119,"output_tokens":523,"output_tokens_details":{"thinking_tokens":195},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":7464},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXspGM5BM9YFPPWMQ96F","requestRef":"5f23f1b3-2a36-4ebf-8b8f-e774a6d3f337","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d146e1f3-934c-4915-9776-d2fa0ea9d44a","timestamp":"2026-10-30T05:34:10.043Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"d146e1f3-934c-4915-9776-d2fa0ea9d44a","isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0192YgsvYtqnHbnBt1bQtb6J","type":"tool_result","content":"year=2023 n=197 excluded_missing=20 beta=5.2672 se(HC3)=0.2107 CI=[4.8543,5.6801] r=0.8613 R2=0.7419 RMSE base=7.0765 model=3.5950 -> positive_effect\n[]\ntableok\n# 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`\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RR0006","is_error":false}]},"uuid":"146ca8f2-3f2b-49f5-8a96-c14ed6b9a7f5","timestamp":"2026-10-30T05:34:11.350Z","toolUseResult":{"stdout":"year=2023 n=197 excluded_missing=20 beta=5.2672 se(HC3)=0.2107 CI=[4.8543,5.6801] r=0.8613 R2=0.7419 RMSE base=7.0765 model=3.5950 -> positive_effect\n[]\ntableok\n# 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`","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RR0006","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d146e1f3-934c-4915-9776-d2fa0ea9d44a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"851c1614137b8fd23d817385b57f4b85d8226127b29d6e6d6beb93046b40eb06","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSkwkKEAgTGAI4AUIIdGhpbmtpbmcSDOtsFzaDwQ3RoOdjlxoM0DgSHMiAMXySdNn+IjB3esv+Me76FYhQVIePCoHfIw4ZVm/6PVmR3Zo0JCK+4igbLrVRvJNGJapDW1/muYsqsAgARPnNBJobPGQIo0ctiDHnNMTzwHVjddcbRfiuFkgWJIv6omgkmfOPuCAEN6yWTK0qYjiV5TPyq0jSfzgwSrv6NfIL4PouAt3az0LDIMVQ2osHSUG/yo2FrqOgcxTK7FEEsfME3DtD448P8xQk6v5DOyeyHqxIf6Kr3Iap1jKRmGWKLD76+7kclT3YqIzRdBELvVXn7fas9w9/Kw9A+eyv6TQgpsXMowZRDmkTS8CeOv5kKWIGx/Ry+ujlPE8HOcwcrndDvUN9HIWk7wKVYPqZTXela0XZLhTQH6eKAYwB/cjauHLj5j3tsAfszdQkOYN6eFec6Ch36sIj3Rs9EOfiWpIm5b1PG3C6vrYsG56/Hwz3uXvF3XcQLdrOVKuD7WtASWC+/7UttP7RdostNE4YKW162ke9Lt/h6s3iPUGC9Q2dMOG6gPZU3nAv213r5uu9AcSnYl/HkhShGDaYBLfUVbRaxLa9Oa7uWY3y0YxrcnfGUzLismmLQdmRCN07vvvoEI30k9Vb34JxHNQqALle2+6c1G4YZmvyWT3Dk0L+0C8y1dV7M6Jho+e5sZRlNRSAR002EQettVoKA34IQbpk0QKLDav9/UNlSknfcoXGXhhKYV/JcINlg0YD+YWInTswpVi+cz52OLNfc/LjzTuJVQGk7IgvdH6A3pbjAoAu9LFcn/m12iDkeKRT8O5JkP8l993lk6M0XgNxKC3DtgEfby64QhowdsBKYCIj1HtlRLRayse8pTF9GYsfuALZaHoUncVwnoP9qxxPTUGeTog5fwKWQyM8BB1XGqBWP0AkC14uR2klhUHee5bJX3aODD8EeW1R5s06bHwvZRZ/0dq7s9AeN//FzxMo/7yyINSXz8aBqaNjiYLcyqm1TfKNsVmrN4lzgG7vv2lL/Pdm0WYiATdS2yi/tkv/ehi+rXqxDO3SYV1X84Gr8iMRTYGdxS6oadAIiS5KQwlrjQZ4A0fzC086nqIrMdMCuRSL1EDoCzIQ4RNhFBF5POokH0cXQX25YGBI95Glvv+h7dzv3Ipc2Qn5OT8KaOtgQBNzGE+kE7bOa/vLhovdpwXEMuYuFT6TldvtEYbEm1T1oyZsodwfNbC0+nDYttsnUx7qulkTyYiMvLHYmHAMBfPKyNCc6XWf9BxO0e/mUKGukIqh7reH1GMZS8HUy26+cleRHAoSMMYrGUQ8a7e8p0t8EJNqbQXR5tLV8CmBVQPieIXifuIaZxxzu445JHLubRRFeHAYyQPr6Y1c0axQE0RXaN7nI7ikzv00NDvdLgf2YkmJA/57YLosBcsKg9MgqOINGqEk/RXRXT6YlmeESF/+Fa5fxfOzLOj8Yg4E47wvrh+/II91t+a/VGAlJO9Mbmnjya47PLzs6I4H4ehPTkPuzuP9IRlxfPTRp+mQnsaT7hcItLO9GAE="},{"type":"text","text":"Now I'll re-run the analysis in a scratch copy and check the data on my own."},{"type":"tool_use","id":"toolu_0192YgsvYtqnHbnBt1bQtb6J","name":"Bash","input":{"command":"S=$(mktemp -d); cp -r data $S/; mkdir $S/out; cp out/analysis.py $S/out/; cd $S && ~/wp29/venv/bin/python out/analysis.py && ~/wp29/venv/bin/python -c \"\nimport json\na=json.load(open('out/results.json'));b=json.load(open('$OLDPWD/out/results.json'))\nprint([k for k in set(a)|set(b) if a.get(k)!=b.get(k)])\n\"; diff out/table1.csv $OLDPWD/out/table1.csv && echo tableok; cat $OLDPWD/data/README.md | head -60","description":"Re-run analysis in scratch dir and compare outputs"}}]}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"82c90c5a-24f8-4b2e-972f-a016c79ae1e0","timestamp":"2026-10-30T05:34:11.353Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":"5f23f1b3-2a36-4ebf-8b8f-e774a6d3f337","keep":6,"tail":["851c1614137b8fd23d817385b57f4b85d8226127b29d6e6d6beb93046b40eb06","878678fee0f9aa983e3747539ed64c4492f6fc9d084e03dcd7a516cc22375004"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a507c15456c432b811fef2ee806672497a2055b418fb24416ed425ce0b69d8bf"} {"parentUuid":"146ca8f2-3f2b-49f5-8a96-c14ed6b9a7f5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspm1VdUhTXZ7ev3c4D","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSmwcKEAgTGAI4AUIIdGhpbmtpbmcSDBLMjunr2sIpbHFujBoMj+9CxWlDwZIDuNG7IjDtXJjhIC5QXGlll3GJ8edo/vW70GkOH4MDS5LWZ+12NyLgYxFMSkPIkBQVn/eWTnoquAZICVGF2wMG1rqBXwlPJDLPfzyr2PF6oWkx1le5Pz2XJTZ53IDJgEubh9S18l8ifynJB28Ha2HUT9jC3EHjn5rA0s5t5JN6OB32UkVQOSsQZmPD3TGPRFDXc4cxilDegD1wszK4AiNSsmwTMgk+L0My4DBLClOt2bSysUxWYWzGvgYDrUTjAP9LrjO4DySIy2nLHIc2tXS4avbNYDqWd014SMNPEoSfMfjXEI8C8TlHNpHF+ToUBXPc6QIZo0/Lb51Wug3PV1F08sgKgs9LrJ2Qrl8Qpgz4xnhUhNIX0R2JNQnfIjo4s4MZxb1QEkENY0vn/qpGD0BiEo3adx8KLWA6jO9K6/8NQDtkR2Mf/AvBRf8HxYiRBuvif8i4rakxPz+KELjEtGpNXIarqkZIKp3zUHJsqR7mKGC15yEzhVGQqyaiRpggZd0P+Mva2Qm+9Ptuz6q7db8oDO6sNKGbPlokyOMOJUl/NnYL77rt6ks+M2b8SGtjd3qSxv85Ow/85banLAV4gSo6EqKj4o6X9m2RG0Ugt6ZtlBSaRoKHfYmRb8FGNtiwf/8CPJYh/MgrjGoyCTxPESwsx48jIrV08SwGm+Ta7J+n6HeZqwXdtPw2sBkWjFq32yzeAyMx3a9ZurhK/BuEedClnlDQ3Qtzl9Y2sYX3HsNp9wRLAfErv2bX3j/c5XS5jhAHlwXqh8ZTVH6vS5sxDt2s1kjw9AUXosNF/eeoVCLPbzRywHlJG964xo/ftGAz2zC1QdAPF+xZiSB34LRClHnWtj1qryCtr/J7nvtfUdP4ecsN3MTe0FzcXPrYEeLrla+7Jf50xNy+AM4LZ0SWD8kaQ7Q9NTf7XpwwJToicubw5e0pm+fTR7JHBgDPEvUnm2kriOE0/Fc1njmEChPPzDmKHBPWuWAeTCjDnNNUftoVQxQOne0AuahyVzEdUUbiIPZ5748kaMIT5q07LZi3jjDeQej3XsnsgyGbv02SC4z1/6MH0tLwEi91fLlCjtpIN9kN+Vq3rC6FV5ZWF7ZzwwX9MeVGPAnAcBPbcAbxuL2Izna3bdFGmXHnFhwOXxuil1kIyd7T6b14MwVjAcMFGc+BGRgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1679,"cache_read_input_tokens":14583,"output_tokens":793,"output_tokens_details":{"thinking_tokens":74},"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":1679},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":857,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXspkjNnX5rqShCBRs51","requestRef":"82c90c5a-24f8-4b2e-972f-a016c79ae1e0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5d4f50e9-26ae-4955-9d27-e8e1557e7c1b","timestamp":"2026-10-30T05:34:13.538Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"5d4f50e9-26ae-4955-9d27-e8e1557e7c1b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspm1VdUhTXZ7ev3c4D","type":"message","role":"assistant","content":[{"type":"text","text":"The re-run matches exactly. Next I'll check edge cases in the raw data on my own."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1679,"cache_read_input_tokens":14583,"output_tokens":793,"output_tokens_details":{"thinking_tokens":74},"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":1679},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXspkjNnX5rqShCBRs51","requestRef":"82c90c5a-24f8-4b2e-972f-a016c79ae1e0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9d1dcec3-ece2-4b04-b4f3-a3f7f267574d","timestamp":"2026-10-30T05:34:13.539Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"9d1dcec3-ece2-4b04-b4f3-a3f7f267574d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspm1VdUhTXZ7ev3c4D","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JiR8z5GscyxnkZUEMkj2Tb","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd, numpy as np\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(e.region.value_counts(dropna=False).to_string())\nprint(e.income_level.value_counts(dropna=False).to_string())\nprint(sorted(set(i.iso3)-set(e.iso3)), len(set(e.iso3)-set(i.iso3)))\nm=i.merge(e,on='iso3');c=m[m.region!='Aggregates']\nprint(c.groupby('year').size().to_string())\nd=c[(c.year==2023)].dropna(subset=['gdp_pc_ppp','life_expectancy'])\nprint(d.income_level.value_counts().to_string())\nprint(d.sort_values('life_expectancy').head(5)[['iso3','gdp_pc_ppp','life_expectancy']])\nprint(d.sort_values('gdp_pc_ppp').head(3)[['iso3','gdp_pc_ppp','life_expectancy']]); print(d.sort_values('gdp_pc_ppp').tail(3)[['iso3','gdp_pc_ppp','life_expectancy']])\nprint(c[c.iso3.isin(['CAF','PSE','SSD'])].pivot(index='iso3',columns='year',values='life_expectancy').round(1).to_string())\nprint(i.dtypes)\nimport statsmodels.api as sm\nX=sm.add_constant(np.log(d.gdp_pc_ppp));f=sm.OLS(d.life_expectancy,X).fit(cov_type='HC3');print(f.params.values,f.bse.values)\n\"","description":"Independent data checks and re-estimation"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1679,"cache_read_input_tokens":14583,"output_tokens":793,"output_tokens_details":{"thinking_tokens":74},"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":1679},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXspkjNnX5rqShCBRs51","requestRef":"82c90c5a-24f8-4b2e-972f-a016c79ae1e0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7b0a5c0d-58ca-4a86-85cc-e7e7462b50bb","timestamp":"2026-10-30T05:34:18.160Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"7b0a5c0d-58ca-4a86-85cc-e7e7462b50bb","isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JiR8z5GscyxnkZUEMkj2Tb","type":"tool_result","content":"region\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\nincome_level\nHigh income 86\nAggregates 79\nUpper middle income 59\nLower middle income 47\nLow income 25\n[] 35\nyear\n2015 217\n2016 217\n2017 217\n2018 217\n2019 217\n2020 217\n2021 217\n2022 217\n2023 217\nincome_level\nHigh income 73\nUpper middle income 58\nLower middle income 46\nLow income 20\n iso3 gdp_pc_ppp life_expectancy\n1538 NGA 7843.003990 54.462\n2033 TCD 2433.533310 55.069\n1241 LSO 2592.457013 57.375\n314 CAF 1132.676434 57.408\n1889 SOM 1401.647352 58.816\n iso3 gdp_pc_ppp life_expectancy\n152 BDI 1033.009373 63.651\n314 CAF 1132.676434 57.408\n1889 SOM 1401.647352 58.816\n iso3 gdp_pc_ppp life_expectancy\n989 IRL 117659.728594 82.807317\n1268 LUX 130048.922273 83.309756\n1844 SGP 130296.843789 83.097561\nyear 2015 2016 2017 2018 2019 2020 2021 2022 2023\niso3 \nCAF 51.9 51.0 45.2 52.3 31.5 50.6 40.3 18.8 57.4\nPSE 74.6 74.9 75.2 75.4 75.8 75.0 73.9 76.7 65.2\nSSD 39.8 36.7 35.4 51.9 58.1 57.6 57.0 57.2 57.6\niso3 object\nname object\nyear int64\ngdp_pc_ppp float64\nlife_expectancy float64\ndtype: object\n[22.56709275 5.26717345] [2.10228623 0.21067529]","is_error":false}]},"uuid":"4b3a9eb6-97b9-4ce3-b724-f2632588573a","timestamp":"2026-10-30T05:34:19.247Z","toolUseResult":{"stdout":"region\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\nincome_level\nHigh income 86\nAggregates 79\nUpper middle income 59\nLower middle income 47\nLow income 25\n[] 35\nyear\n2015 217\n2016 217\n2017 217\n2018 217\n2019 217\n2020 217\n2021 217\n2022 217\n2023 217\nincome_level\nHigh income 73\nUpper middle income 58\nLower middle income 46\nLow income 20\n iso3 gdp_pc_ppp life_expectancy\n1538 NGA 7843.003990 54.462\n2033 TCD 2433.533310 55.069\n1241 LSO 2592.457013 57.375\n314 CAF 1132.676434 57.408\n1889 SOM 1401.647352 58.816\n iso3 gdp_pc_ppp life_expectancy\n152 BDI 1033.009373 63.651\n314 CAF 1132.676434 57.408\n1889 SOM 1401.647352 58.816\n iso3 gdp_pc_ppp life_expectancy\n989 IRL 117659.728594 82.807317\n1268 LUX 130048.922273 83.309756\n1844 SGP 130296.843789 83.097561\nyear 2015 2016 2017 2018 2019 2020 2021 2022 2023\niso3 \nCAF 51.9 51.0 45.2 52.3 31.5 50.6 40.3 18.8 57.4\nPSE 74.6 74.9 75.2 75.4 75.8 75.0 73.9 76.7 65.2\nSSD 39.8 36.7 35.4 51.9 58.1 57.6 57.0 57.2 57.6\niso3 object\nname object\nyear int64\ngdp_pc_ppp float64\nlife_expectancy float64\ndtype: object\n[22.56709275 5.26717345] [2.10228623 0.21067529]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7b0a5c0d-58ca-4a86-85cc-e7e7462b50bb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"c6b7a7cade5f8d4b312e704218d98beff56c2868b3893f7a7916ff183753c003","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"The re-run matches exactly. Next I'll check edge cases in the raw data on my own."},{"type":"tool_use","id":"toolu_01JiR8z5GscyxnkZUEMkj2Tb","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd, numpy as np\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(e.region.value_counts(dropna=False).to_string())\nprint(e.income_level.value_counts(dropna=False).to_string())\nprint(sorted(set(i.iso3)-set(e.iso3)), len(set(e.iso3)-set(i.iso3)))\nm=i.merge(e,on='iso3');c=m[m.region!='Aggregates']\nprint(c.groupby('year').size().to_string())\nd=c[(c.year==2023)].dropna(subset=['gdp_pc_ppp','life_expectancy'])\nprint(d.income_level.value_counts().to_string())\nprint(d.sort_values('life_expectancy').head(5)[['iso3','gdp_pc_ppp','life_expectancy']])\nprint(d.sort_values('gdp_pc_ppp').head(3)[['iso3','gdp_pc_ppp','life_expectancy']]); print(d.sort_values('gdp_pc_ppp').tail(3)[['iso3','gdp_pc_ppp','life_expectancy']])\nprint(c[c.iso3.isin(['CAF','PSE','SSD'])].pivot(index='iso3',columns='year',values='life_expectancy').round(1).to_string())\nprint(i.dtypes)\nimport statsmodels.api as sm\nX=sm.add_constant(np.log(d.gdp_pc_ppp));f=sm.OLS(d.life_expectancy,X).fit(cov_type='HC3');print(f.params.values,f.bse.values)\n\"","description":"Independent data checks and re-estimation"}}]}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"487ac779-0803-48d9-bc91-20f1ce58db62","timestamp":"2026-10-30T05:34:19.251Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":"82c90c5a-24f8-4b2e-972f-a016c79ae1e0","keep":8,"tail":["c6b7a7cade5f8d4b312e704218d98beff56c2868b3893f7a7916ff183753c003","cef5ee711a570d4dca6a30071c2bca46c112e6ed8cc365f44c05554049373657"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"bb13f1d03eb51a510da66e51cc2559d92a425013f5da2f915feb4b0f137e2567"} {"type":"tools-used","tools":["Bash","Read"],"sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"parentUuid":"4b3a9eb6-97b9-4ce3-b724-f2632588573a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqLmW21K3qX6Zpa4wA","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":1518,"cache_read_input_tokens":16262,"output_tokens":679,"output_tokens_details":{"thinking_tokens":578},"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":1518},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":5526,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsqLVP2VXDo6bRzwYQJ","requestRef":"487ac779-0803-48d9-bc91-20f1ce58db62","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"86983fbd-5a06-48b0-aa31-eb7ac555cec0","timestamp":"2026-10-30T05:34:26.101Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"86983fbd-5a06-48b0-aa31-eb7ac555cec0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqLmW21K3qX6Zpa4wA","type":"message","role":"assistant","content":[{"type":"text","text":"Everything reproduces. Last, I'll look at the figure."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1518,"cache_read_input_tokens":16262,"output_tokens":679,"output_tokens_details":{"thinking_tokens":578},"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":1518},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsqLVP2VXDo6bRzwYQJ","requestRef":"487ac779-0803-48d9-bc91-20f1ce58db62","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e9510b8c-f53a-4abc-a0aa-ce9757ff278e","timestamp":"2026-10-30T05:34:26.101Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e9510b8c-f53a-4abc-a0aa-ce9757ff278e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqLmW21K3qX6Zpa4wA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SCcigdCUkF4BZU8cHsKq5g","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RR0006/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":1518,"cache_read_input_tokens":16262,"output_tokens":679,"output_tokens_details":{"thinking_tokens":578},"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":1518},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsqLVP2VXDo6bRzwYQJ","requestRef":"487ac779-0803-48d9-bc91-20f1ce58db62","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5f8bddbc-364a-45ad-93db-6708d5caa223","timestamp":"2026-10-30T05:34:26.489Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"5f8bddbc-364a-45ad-93db-6708d5caa223","isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SCcigdCUkF4BZU8cHsKq5g","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"019f2e6d-23f8-4cb1-98d9-6526c1b8659a","timestamp":"2026-10-30T05:34:26.498Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":67512,"dimensions":{"originalWidth":900,"originalHeight":624,"displayWidth":900,"displayHeight":624}}},"sourceToolAssistantUUID":"5f8bddbc-364a-45ad-93db-6708d5caa223","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"c3900da38d1973d503e3e6e6b4235703f6d746a8422c713f9a35377b6fc61b34","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Everything reproduces. Last, I'll look at the figure."},{"type":"tool_use","id":"toolu_01SCcigdCUkF4BZU8cHsKq5g","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RR0006/out/figure1.png"}}]}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"85cf81ff-9da8-4187-81e5-2923ca245d9c","timestamp":"2026-10-30T05:34:26.503Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":"487ac779-0803-48d9-bc91-20f1ce58db62","keep":10,"tail":["c3900da38d1973d503e3e6e6b4235703f6d746a8422c713f9a35377b6fc61b34","361102ec29db9e4c9e1082701e853c7695d6d183d783ca4312870e356f377398"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b383f9811d12977b2fa10740b091c47eab6b753d41f1d2177202dfbc7cc95bcd"} {"type":"last-prompt","lastPrompt":"Review","leafUuid":"019f2e6d-23f8-4cb1-98d9-6526c1b8659a","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"type":"atis-latch","atis":"","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"parentUuid":"019f2e6d-23f8-4cb1-98d9-6526c1b8659a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqsgNBYRcoBJZPRC4i","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":1457,"cache_read_input_tokens":17780,"output_tokens":1189,"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":1457},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":372,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsqsVwnVW4sHDdPVvX2","requestRef":"85cf81ff-9da8-4187-81e5-2923ca245d9c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4dc2446a-fd09-42eb-aa73-6c871444acd5","timestamp":"2026-10-30T05:34:28.002Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"4dc2446a-fd09-42eb-aa73-6c871444acd5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqsgNBYRcoBJZPRC4i","type":"message","role":"assistant","content":[{"type":"text","text":"Everything checks out except some minor wording issues. Writing the review."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1457,"cache_read_input_tokens":17780,"output_tokens":1189,"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":1457},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsqsVwnVW4sHDdPVvX2","requestRef":"85cf81ff-9da8-4187-81e5-2923ca245d9c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a323fda4-76d5-4b36-84bd-def232bc01b5","timestamp":"2026-10-30T05:34:28.002Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"a323fda4-76d5-4b36-84bd-def232bc01b5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsqsgNBYRcoBJZPRC4i","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WJM6tqCEYZ52iFvoVX9TCo","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"out/report.md (Data and exclusions; Limitations, 'Data quality' bullet)\",\n \"issue\": \"The report says the implausible life-expectancy swings are 'outside 2023' and that 'Only PSE's 2023 value enters the estimate'. In fact CAF's 2023 value (57.4) is also in the estimate. It ends a very erratic series (31.5, 50.6, 40.3, 18.8, 57.4 for 2019-2023) with a 38.6-year jump into 2023. Leave-one-out covers its influence on beta, but the wording understates which suspect values enter the analysis.\",\n \"suggested_fix\": \"Say that CAF's 2023 value enters the estimate and is part of an erratic series, and give the slope when CAF is dropped (and when PSE is dropped).\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"out/claims.json C5\",\n \"issue\": \"The claim says 'The slope is robust to the choice of HC estimator'. The HC choice changes the SE, not the slope, so the wording is loose. The numbers themselves are correct (SE 0.207-0.222; LOO slope 5.21-5.33).\",\n \"suggested_fix\": \"Reword: 'The SE varies little across HC0-HC3 and classical estimators, and the slope stays within [5.21, 5.33] when any single country is dropped.'\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"out/analysis.py (data_issues construction)\",\n \"issue\": \"The text of the life-expectancy-swing issue hard-codes example values (CAF 18.8/57.4, PSE 65.2/76.7) instead of reading them from the data. They are correct for these data, but they would go stale if the inputs changed.\",\n \"suggested_fix\": \"Format the example values from the le_p pivot.\"\n }\n ],\n \"summary\": \"I re-ran out/analysis.py in a scratch copy and got a results.json identical to the submitted one in every key, plus an identical table1.csv. An independent estimate gave the same numbers (beta 5.267, HC3 SE 0.2107). The code follows the information rules: aggregates are dropped via region=='Aggregates', the year rule uses complete-case counts (199 in 2015-2022, 197 in 2023, so 2023 is selected), there is no imputation, 20 exclusions are counted (all for missing GDP), the natural log is used, and only data/ is read. All required keys are present and correctly typed. The conclusion code matches the CI. The baseline RMSE (7.08) is compared with the model RMSE (3.59). The counts reconcile (2349-396-1736-20=197; table rows sum to 197). The report has the six required sections, states that HC3 is used, and gives an honest discussion of limitations and failure modes. Only minor wording and hard-coding issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write and validate review JSON"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1457,"cache_read_input_tokens":17780,"output_tokens":1189,"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":1457},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsqsVwnVW4sHDdPVvX2","requestRef":"85cf81ff-9da8-4187-81e5-2923ca245d9c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e7c0d5ef-8a49-4633-b52d-f61441428179","timestamp":"2026-10-30T05:34:37.669Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"e7c0d5ef-8a49-4633-b52d-f61441428179","isSidechain":false,"promptId":"237a1d72-7c5d-4ce8-8d93-c67163ea96f5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WJM6tqCEYZ52iFvoVX9TCo","type":"tool_result","content":"ok","is_error":false}]},"uuid":"faf67af0-1c70-4c49-a4da-270cb86b7b79","timestamp":"2026-10-30T05:34:37.731Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e7c0d5ef-8a49-4633-b52d-f61441428179","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"api-request-blob","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","hash":"2dbafe3b77fb19370a175a7e4475bb1fc6239ba652f1fa4fcab22e456348516f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Everything checks out except some minor wording issues. Writing the review."},{"type":"tool_use","id":"toolu_01WJM6tqCEYZ52iFvoVX9TCo","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"out/report.md (Data and exclusions; Limitations, 'Data quality' bullet)\",\n \"issue\": \"The report says the implausible life-expectancy swings are 'outside 2023' and that 'Only PSE's 2023 value enters the estimate'. In fact CAF's 2023 value (57.4) is also in the estimate. It ends a very erratic series (31.5, 50.6, 40.3, 18.8, 57.4 for 2019-2023) with a 38.6-year jump into 2023. Leave-one-out covers its influence on beta, but the wording understates which suspect values enter the analysis.\",\n \"suggested_fix\": \"Say that CAF's 2023 value enters the estimate and is part of an erratic series, and give the slope when CAF is dropped (and when PSE is dropped).\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"out/claims.json C5\",\n \"issue\": \"The claim says 'The slope is robust to the choice of HC estimator'. The HC choice changes the SE, not the slope, so the wording is loose. The numbers themselves are correct (SE 0.207-0.222; LOO slope 5.21-5.33).\",\n \"suggested_fix\": \"Reword: 'The SE varies little across HC0-HC3 and classical estimators, and the slope stays within [5.21, 5.33] when any single country is dropped.'\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"out/analysis.py (data_issues construction)\",\n \"issue\": \"The text of the life-expectancy-swing issue hard-codes example values (CAF 18.8/57.4, PSE 65.2/76.7) instead of reading them from the data. They are correct for these data, but they would go stale if the inputs changed.\",\n \"suggested_fix\": \"Format the example values from the le_p pivot.\"\n }\n ],\n \"summary\": \"I re-ran out/analysis.py in a scratch copy and got a results.json identical to the submitted one in every key, plus an identical table1.csv. An independent estimate gave the same numbers (beta 5.267, HC3 SE 0.2107). The code follows the information rules: aggregates are dropped via region=='Aggregates', the year rule uses complete-case counts (199 in 2015-2022, 197 in 2023, so 2023 is selected), there is no imputation, 20 exclusions are counted (all for missing GDP), the natural log is used, and only data/ is read. All required keys are present and correctly typed. The conclusion code matches the CI. The baseline RMSE (7.08) is compared with the model RMSE (3.59). The counts reconcile (2349-396-1736-20=197; table rows sum to 197). The report has the six required sections, states that HC3 is used, and gives an honest discussion of limitations and failure modes. Only minor wording and hard-coding issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write and validate review JSON"}}]}} {"type":"api-request","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","id":"5a7c6ba6-471a-476e-84fb-b71b578ac63c","timestamp":"2026-10-30T05:34:37.735Z","version":"2.1.314","querySource":"sdk","shapeHash":"887ab2260c5fbcb7944250f6d9ef695851c4eb985a471bbbe6f6a0bd6627fc39","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":"85cf81ff-9da8-4187-81e5-2923ca245d9c","keep":12,"tail":["2dbafe3b77fb19370a175a7e4475bb1fc6239ba652f1fa4fcab22e456348516f","fa66569bb8d9b670bd2967d18a5e832e6654d01c210d0071d1d177223f78e4bd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"57b6b94ce07760a9969655287597202a128cefe2be9b063cf84eec92882913c2"} {"parentUuid":"faf67af0-1c70-4c49-a4da-270cb86b7b79","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsrho4uj87nHQ53xW7k","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1196,"cache_read_input_tokens":19237,"output_tokens":816,"output_tokens_details":{"thinking_tokens":13},"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":1196},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6231,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsrhXwsqXE7BNNrVJAL","requestRef":"5a7c6ba6-471a-476e-84fb-b71b578ac63c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3dc49278-c613-4bc8-b0ee-b983077571b9","timestamp":"2026-10-30T05:34:45.216Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"parentUuid":"3dc49278-c613-4bc8-b0ee-b983077571b9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsrho4uj87nHQ53xW7k","type":"message","role":"assistant","content":[{"type":"text","text":"My verdict is **accept**, with three minor issues. The review is saved at `out/review/review.json`.\n\n**What I checked:**\n- **Reproducibility:** I re-ran `out/analysis.py` in a scratch copy. It produced a `results.json` identical to the submitted one in every key, and an identical `table1.csv`. A separate fit I wrote myself gave the same slope (5.267) and robust standard error (0.2107).\n- **Rules in `TASK.md`:** The code follows them all:\n - It drops every entity marked `Aggregates` (44 in the indicator file).\n - It picks the analysis year from countries with both indicators: 199 in each year 2015–2022 and 197 in 2023, so 2023 is selected.\n - It excludes the 20 countries missing an indicator without imputing anything; all 20 are missing GDP.\n - It uses the natural log of GDP and reads only `data/`.\n- **Required outputs:** Every required key is present with the right type.\n - The conclusion (`positive_effect`) matches the 95% interval, [4.85, 5.68].\n - The required baseline comparison is there: prediction error of 7.08 years for the mean-only baseline against 3.59 years for the regression.\n - The counts add up: 2349 − 396 − 1736 − 20 = 197 countries analysed, and the four income-group rows in `table1.csv` also sum to 197.\n - The figure is correct, and the report has the six required sections in order.\n - The report names the robust error type (HC3) and gives an honest discussion of what could invalidate the result.\n\n**Minor issues:**\n1. **Central African Republic data:** The report says the implausible life-expectancy swings fall outside 2023, and that only West Bank and Gaza's 2023 value enters the estimate. In fact the Central African Republic's 2023 value (57.4) is also used, and it ends a very erratic series (18.8 in 2022, a 38.6-year jump). The leave-one-out check limits how much one country can move the slope, but the report should say this value is included.\n2. **Wording of claim C5:** It says the slope is robust to the choice of error estimator. The estimator choice changes the standard error, not the slope; the numbers themselves are right.\n3. **Hard-coded values:** `analysis.py` writes the example values in the data-issue text by hand instead of reading them from the data. They are correct now but would go out of date if the inputs changed."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1196,"cache_read_input_tokens":19237,"output_tokens":816,"output_tokens_details":{"thinking_tokens":13},"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":1196},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsrhXwsqXE7BNNrVJAL","requestRef":"5a7c6ba6-471a-476e-84fb-b71b578ac63c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"47c22f76-2e58-4abd-a09b-f19505c9acfe","timestamp":"2026-10-30T05:34:45.973Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RR0006","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","version":"2.1.314","gitBranch":"HEAD"} {"type":"last-prompt","lastPrompt":"Review","leafUuid":"47c22f76-2e58-4abd-a09b-f19505c9acfe","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8"} {"type":"cost-state","sessionId":"061c3629-43cf-4c81-b9f5-330814e44df8","totalCostUSD":0.19579,"totalAPIDuration":44421,"totalAPIDurationWithoutRetries":44416,"totalToolDuration":2537,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":47145,"startTime":1793338438836,"modelUsage":{"claude-opus-5-5":{"inputTokens":16,"outputTokens":4267,"thinkingTokens":897,"cacheReadInputTokens":78705,"cacheCreationInputTokens":18929,"cacheCreationEphemeral5mInputTokens":18929,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.19579}},"hasUnknownModelCost":false}