1{"type":"atis-latch","atis":"","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:42:58.935Z","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","content":"Review"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:42:58.943Z","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}4{"parentUuid":null,"isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":"Review"},"uuid":"1b4cc3d3-4f93-4911-aadb-087201738afe","timestamp":"2026-10-30T05:42:58.948Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","timestamp":"2026-10-30T05:42:58.964Z","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/RT0021\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\": \"<file or key>\", \"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}}]}}6{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"506e0560-7611-4f37-b859-3079090025a0","timestamp":"2026-10-30T05:42:58.964Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"bae76fbcd1a6371e3e77fbc1511fce2446266cb10db27120349b90bde22210c8"}8{"parentUuid":"1b4cc3d3-4f93-4911-aadb-087201738afe","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"781edd4e-92a5-4866-b78b-cd46287f065d","timestamp":"2026-10-30T05:42:58.954Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"781edd4e-92a5-4866-b78b-cd46287f065d","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"b2f3d992-1a71-4a49-bf84-f1384d9aca89","timestamp":"2026-10-30T05:42:58.954Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"b2f3d992-1a71-4a49-bf84-f1384d9aca89","isSidechain":false,"attachment":{"type":"remote_session_change","url":null,"commit":"Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>","pr":"🤖 Generated with [Claude Code](https://claude.com/claude-code)","sendUserFileHint":false,"managedCommit":false,"managedPr":false},"type":"attachment","uuid":"d0926ae3-d2ff-4d91-a7bf-695b30999c2e","timestamp":"2026-10-30T05:42:58.954Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}12{"parentUuid":"d0926ae3-d2ff-4d91-a7bf-695b30999c2e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVezBusvf99LeYy5JY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HVB5jUPPQH3MyiD9WKPo2B","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json"},"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":76,"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtVeia1gKURqAWK8veK","requestRef":"506e0560-7611-4f37-b859-3079090025a0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2697d1a6-6fb2-4802-955d-9a60b0ea833e","timestamp":"2026-10-30T05:43:00.633Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"2697d1a6-6fb2-4802-955d-9a60b0ea833e","isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HVB5jUPPQH3MyiD9WKPo2B","type":"tool_result","content":"# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 248\ndrwxr-xr-x 11 simon-pierreboucher staff 352 oct. 30 01:42 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:39 ..\n-rw-r--r-- 1 simon-pierreboucher staff 9059 oct. 30 01:41 analysis.py\n-rw-r--r-- 1 simon-pierreboucher staff 2076 oct. 30 01:42 claims.json\n-rw-r--r-- 1 simon-pierreboucher staff 186 oct. 30 01:41 exclusions.csv\n-rw-r--r-- 1 simon-pierreboucher staff 74523 oct. 30 01:41 figure1.png\n-rw-r--r-- 1 simon-pierreboucher staff 9785 oct. 30 01:42 report.md\n-rw-r--r-- 1 simon-pierreboucher staff 8197 oct. 30 01:41 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:42 review\ndrwxr-xr-x 8 simon-pierreboucher staff 256 oct. 30 01:41 state\n-rw-r--r-- 1 simon-pierreboucher staff 1620 oct. 30 01:41 table1.csv\n{\n \"task_id\": \"T2-simulation\",\n \"R\": 2000,\n \"B\": 399,\n \"n_cells\": 9,\n \"coverage\": {\n \"cr0_G5_icc0.0\": 0.797,\n \"cr1_G5_icc0.0\": 0.919,\n \"wcb_G5_icc0.0\": 0.869,\n \"cr0_G5_icc0.2\": 0.7195,\n \"cr1_G5_icc0.2\": 0.8815,\n \"wcb_G5_icc0.2\": 0.847,\n \"cr0_G5_icc0.5\": 0.7205,\n \"cr1_G5_icc0.5\": 0.8795,\n \"wcb_G5_icc0.5\": 0.8565,\n \"cr0_G10_icc0.0\": 0.8835,\n \"cr1_G10_icc0.0\": 0.9395,\n \"wcb_G10_icc0.0\": 0.926,\n \"cr0_G10_icc0.2\": 0.859,\n \"cr1_G10_icc0.2\": 0.9165,\n \"wcb_G10_icc0.2\": 0.939,\n \"cr0_G10_icc0.5\": 0.853,\n \"cr1_G10_icc0.5\": 0.917,\n \"wcb_G10_icc0.5\": 0.9365,\n \"cr0_G30_icc0.0\": 0.9305,\n \"cr1_G30_icc0.0\": 0.944,\n \"wcb_G30_icc0.0\": 0.946,\n \"cr0_G30_icc0.2\": 0.924,\n \"cr1_G30_icc0.2\": 0.94,\n \"wcb_G30_icc0.2\": 0.9515,\n \"cr0_G30_icc0.5\": 0.916,\n \"cr1_G30_icc0.5\": 0.929,\n \"wcb_G30_icc0.5\": 0.9415\n },\n \"mc_se_coverage\": {\n \"cr0_G5_icc0.0\": 0.008994192570764758,\n \"cr1_G5_icc0.0\": 0.006100778638829636,\n \"wcb_G5_icc0.0\": 0.00754450130890041,\n \"cr0_G5_icc0.2\": 0.01004539073406306,\n \"cr1_G5_icc0.2\": 0.007226954752867907,\n \"wcb_G5_icc0.2\": 0.008049565205649308,\n \"cr0_G5_icc0.5\": 0.010034434463386564,\n \"cr1_G5_icc0.5\": 0.007279414468211026,\n \"wcb_G5_icc0.5\": 0.007839252196478946,\n \"cr0_G10_icc0.0\": 0.007173832657652395,\n \"cr1_G10_icc0.0\": 0.005331029450303197,\n \"wcb_G10_icc0.0\": 0.005853375094763702,\n \"cr0_G10_icc0.2\": 0.007781998457979801,\n \"cr1_G10_icc0.2\": 0.006185780063985464,\n \"wcb_G10_icc0.2\": 0.005351588549206677,\n \"cr0_G10_icc0.5\": 0.007918049002121673,\n \"cr1_G10_icc0.5\": 0.006168914004912047,\n \"wcb_G10_icc0.5\": 0.005452877680637995,\n \"cr0_G30_icc0.0\": 0.005686376262612245,\n \"cr1_G30_icc0.0\": 0.005141206084179083,\n \"wcb_G30_icc0.0\": 0.005053909377897473,\n \"cr0_G30_icc0.2\": 0.005925537950262405,\n \"cr1_G30_icc0.2\": 0.005310367218940704,\n \"wcb_G30_icc0.2\": 0.004803527349771207,\n \"cr0_G30_icc0.5\": 0.006202580108309766,\n \"cr1_G30_icc0.5\": 0.005742778073371805,\n \"wcb_G30_icc0.5\": 0.0052477495176503994\n },\n \"rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.6531045734688924,\n \"cr1_G5_icc0.0\": 0.8163807168361153,\n \"cr0_G5_icc0.2\": 0.5073384003531096,\n \"cr1_G5_icc0.2\": 0.6341730004413871,\n \"cr0_G5_icc0.5\": 0.5054037231287982,\n \"cr1_G5_icc0.5\": 0.6317546539109978,\n \"cr0_G10_icc0.0\": 0.8457923977794889,\n \"cr1_G10_icc0.0\": 0.9397693308660987,\n \"cr0_G10_icc0.2\": 0.7595252021609881,\n \"cr1_G10_icc0.2\": 0.8439168912899868,\n \"cr0_G10_icc0.5\": 0.7668304455993856,\n \"cr1_G10_icc0.5\": 0.8520338284437619,\n \"cr0_G30_icc0.0\": 0.9349718907569042,\n \"cr1_G30_icc0.0\": 0.9672123007830045,\n \"cr0_G30_icc0.2\": 0.9185077380114064,\n \"cr1_G30_icc0.2\": 0.9501804186324896,\n \"cr0_G30_icc0.5\": 0.9153772013849211,\n \"cr1_G30_icc0.5\": 0.9469419324671597\n },\n \"failure_cells\": [\n \"cr0_G10_icc0.0\",\n \"cr0_G10_icc0.2\",\n \"cr0_G10_icc0.5\",\n \"cr0_G5_icc0.0\",\n \"cr0_G5_icc0.2\",\n \"cr0_G5_icc0.5\",\n \"cr1_G5_icc0.2\",\n \"cr1_G5_icc0.5\",\n \"wcb_G5_icc0.0\",\n \"wcb_G5_icc0.2\",\n \"wcb_G5_icc0.5\"\n ],\n \"n_failure_cells\": 11,\n \"nominal_cells\": [\n \"cr1_G10_icc0.0\",\n \"cr1_G30_icc0.0\",\n \"cr1_G30_icc0.2\",\n \"wcb_G30_icc0.0\",\n \"wcb_G30_icc0.2\",\n \"wcb_G30_icc0.5\"\n ],\n \"best_procedure_small_G\": \"cr1\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"\n }\n ],\n \"n_input_rows\": {\n \"design.csv\": 9\n },\n \"n_analysed\": 18000,\n \"random_seed\": 20261101,\n \"baseline_coverage_iid\": {\n \"iid_G5_icc0.0\": 0.944,\n \"iid_G5_icc0.2\": 0.465,\n \"iid_G5_icc0.5\": 0.296,\n \"iid_G10_icc0.0\": 0.95,\n \"iid_G10_icc0.2\": 0.4685,\n \"iid_G10_icc0.5\": 0.315,\n \"iid_G30_icc0.0\": 0.9555,\n \"iid_G30_icc0.2\": 0.482,\n \"iid_G30_icc0.5\": 0.298\n },\n \"mean_coverage_small_G\": {\n \"cr0\": 0.7456666666666667,\n \"cr1\": 0.8933333333333332,\n \"wcb\": 0.8574999999999999\n },\n \"mc_se_rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.012379922914024347,\n \"cr1_G5_icc0.0\": 0.015474903642530432,\n \"cr0_G5_icc0.2\": 0.012551876505571668,\n \"cr1_G5_icc0.2\": 0.015689845631964586,\n \"cr0_G5_icc0.5\": 0.012597853584309,\n \"cr1_G5_icc0.5\": 0.015747316980386252,\n \"cr0_G10_icc0.0\": 0.011335014984467255,\n \"cr1_G10_icc0.0\": 0.012594461093852507,\n \"cr0_G10_icc0.2\": 0.01321820179399827,\n \"cr1_G10_icc0.2\": 0.014686890882220303,\n \"cr0_G10_icc0.5\": 0.014357919526351126,\n \"cr1_G10_icc0.5\": 0.01595324391816792,\n \"cr0_G30_icc0.0\": 0.006800079998922955,\n \"cr1_G30_icc0.0\": 0.007034565516127195,\n \"cr0_G30_icc0.2\": 0.0085123734620183,\n \"cr1_G30_icc0.2\": 0.00880590358139824,\n \"cr0_G30_icc0.5\": 0.008257578831409366,\n \"cr1_G30_icc0.5\": 0.008542322929044171\n },\n \"mean_ci_halfwidth\": {\n \"cr0_G5_icc0.0\": 0.12921901485510345,\n \"cr1_G5_icc0.0\": 0.20465127376140263,\n \"wcb_G5_icc0.0\": 0.24438067367182634,\n \"cr0_G5_icc0.2\": 0.3363597922614171,\n \"cr1_G5_icc0.2\": 0.5327115363447698,\n \"wcb_G5_icc0.2\": 0.8814683692672445,\n \"cr0_G5_icc0.5\": 0.5098423713216832,\n \"cr1_G5_icc0.5\": 0.8074654556491971,\n \"wcb_G5_icc0.5\": 1.4186671197985352,\n \"cr0_G10_icc0.0\": 0.10653790084741674,\n \"cr1_G10_icc0.0\": 0.1296133046270418,\n \"wcb_G10_icc0.0\": 0.14460431575960167,\n \"cr0_G10_icc0.2\": 0.30019002401528055,\n \"cr1_G10_icc0.2\": 0.3652091952179194,\n \"wcb_G10_icc0.2\": 0.46849708469359214,\n \"cr0_G10_icc0.5\": 0.45866713816216975,\n \"cr1_G10_icc0.5\": 0.5580114027792793,\n \"wcb_G10_icc0.5\": 0.7171478891689117,\n \"cr0_G30_icc0.0\": 0.0636577759163469,\n \"cr1_G30_icc0.0\": 0.0675614709743341,\n \"wcb_G30_icc0.0\": 0.06989052905472656,\n \"cr0_G30_icc0.2\": 0.19481781032685644,\n \"cr1_G30_icc0.2\": 0.20676465126550664,\n \"wcb_G30_icc0.2\": 0.22177373668849737,\n \"cr0_G30_icc0.5\": 0.2981667448851098,\n \"cr1_G30_icc0.5\": 0.31645126758024267,\n \"wcb_G30_icc0.5\": 0.3408981681027193\n },\n \"exact_rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.6640625,\n \"cr1_G5_icc0.0\": 0.830078125,\n \"cr0_G5_icc0.2\": 0.49950132978723344,\n \"cr1_G5_icc0.2\": 0.6243766622340418,\n \"cr0_G5_icc0.5\": 0.48828125,\n \"cr1_G5_icc0.5\": 0.6103515625,\n \"cr0_G10_icc0.0\": 0.8393021120293873,\n \"cr1_G10_icc0.0\": 0.9325579022548748,\n \"cr0_G10_icc0.2\": 0.7598750380616052,\n \"cr1_G10_icc0.2\": 0.844305597846228,\n \"cr0_G10_icc0.5\": 0.7543877524211225,\n \"cr1_G10_icc0.5\": 0.8382086138012473,\n \"cr0_G30_icc0.0\": 0.9485596707818851,\n \"cr1_G30_icc0.0\": 0.9812686249467777,\n \"cr0_G30_icc0.2\": 0.9267376448823972,\n \"cr1_G30_icc0.2\": 0.9586941153955834,\n \"cr0_G30_icc0.5\": 0.9252970710455054,\n \"cr1_G30_icc0.5\": 0.9572038665987987\n },\n \"z_rel_bias_mc_vs_exact\": {\n \"cr0_G5_icc0.0\": -0.885136895213955,\n \"cr1_G5_icc0.0\": -0.8851368952139641,\n \"cr0_G5_icc0.2\": 0.6243744162394662,\n \"cr1_G5_icc0.2\": 0.6243744162394759,\n \"cr0_G5_icc0.5\": 1.3591579719679208,\n \"cr1_G5_icc0.5\": 1.359157971967924,\n \"cr0_G10_icc0.0\": 0.5725873110000674,\n \"cr1_G10_icc0.0\": 0.5725873110000634,\n \"cr0_G10_icc0.2\": -0.02646622483672057,\n \"cr1_G10_icc0.2\": -0.026466224836721407,\n \"cr0_G10_icc0.5\": 0.8666083658866433,\n \"cr1_G10_icc0.5\": 0.8666083658866424,\n \"cr0_G30_icc0.0\": -1.998179437173235,\n \"cr1_G30_icc0.0\": -1.9981794371732264,\n \"cr0_G30_icc0.2\": -0.9668169409756443,\n \"cr1_G30_icc0.2\": -0.9668169409756275,\n \"cr0_G30_icc0.5\": -1.2013048695160027,\n \"cr1_G30_icc0.5\": -1.2013048695160073\n },\n \"exact_var_ybar\": {\n \"G5_icc0.0\": 0.0078125,\n \"G5_icc0.2\": 0.0734375,\n \"G5_icc0.5\": 0.171875,\n \"G10_icc0.0\": 0.003787878787878788,\n \"G10_icc0.2\": 0.035169880624426074,\n \"G10_icc0.5\": 0.08224288337924701,\n \"G30_icc0.0\": 0.0011574074074074073,\n \"G30_icc0.2\": 0.011213991769547326,\n \"G30_icc0.5\": 0.0262988683127572\n }\n}[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G<=10 cells, CR1 at G=5 with ICC 0.2 and 0.5, WCB at all G=5 cells; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5 (icc0.2/0.5) and cr0_G10_icc0.0 lie only ~2.3-2.8 MC SE below 0.90.\"},\n {\"id\":\"C2\",\"text\":\"Only 6 of 27 pairs are consistent with nominal 95% coverage (CR1 at G10/ICC0, G30/ICC0, G30/ICC0.2; WCB at all G=30 cells).\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE rule applied to 27 pairs without multiplicity correction.\"},\n {\"id\":\"C3\",\"text\":\"With G=5, CR1 has the highest average coverage (0.893) ahead of WCB (0.857) and CR0 (0.746).\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_small_G\"],\"status\":\"supported\",\"caveat\":\"Specific to unrestricted Rademacher WCB with symmetric bootstrap-t and B=399.\"},\n {\"id\":\"C4\",\"text\":\"At G=10 with ICC>0 and at G=30, WCB is closer to nominal than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences at G=30 are of the order of 1-3 MC SE; paired SEs not computed.\"},\n {\"id\":\"C5\",\"text\":\"CR0 and CR1 variance estimators are biased downward in every cell, strongly at G=5 (CR0 0.51-0.65, CR1 0.63-0.82), and Monte Carlo bias estimates agree with analytic expectations.\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\",\"exact_rel_bias_var\",\"z_rel_bias_mc_vs_exact\"],\"status\":\"supported\",\"caveat\":\"Bias depends on the unbalanced cluster-size pattern.\"},\n {\"id\":\"C6\",\"text\":\"At G=5 WCB intervals are wider on average than CR1 intervals yet cover less.\",\"results_keys\":[\"mean_ci_halfwidth\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Explanation (variable, discrete bootstrap critical value) is interpretive, not separately tested.\"},\n {\"id\":\"C7\",\"text\":\"The naive i.i.d. interval covers ~0.95 at ICC=0 but only 0.30-0.48 when ICC>0.\",\"results_keys\":[\"baseline_coverage_iid\"],\"status\":\"supported\",\"caveat\":\"Baseline not required by the task; included for context.\"}\n]","is_error":false}]},"uuid":"54c5675b-46a1-44f2-a233-3e9dbd168ebb","timestamp":"2026-10-30T05:43:00.750Z","toolUseResult":{"stdout":"# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 248\ndrwxr-xr-x 11 simon-pierreboucher staff 352 oct. 30 01:42 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:39 ..\n-rw-r--r-- 1 simon-pierreboucher staff 9059 oct. 30 01:41 analysis.py\n-rw-r--r-- 1 simon-pierreboucher staff 2076 oct. 30 01:42 claims.json\n-rw-r--r-- 1 simon-pierreboucher staff 186 oct. 30 01:41 exclusions.csv\n-rw-r--r-- 1 simon-pierreboucher staff 74523 oct. 30 01:41 figure1.png\n-rw-r--r-- 1 simon-pierreboucher staff 9785 oct. 30 01:42 report.md\n-rw-r--r-- 1 simon-pierreboucher staff 8197 oct. 30 01:41 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:42 review\ndrwxr-xr-x 8 simon-pierreboucher staff 256 oct. 30 01:41 state\n-rw-r--r-- 1 simon-pierreboucher staff 1620 oct. 30 01:41 table1.csv\n{\n \"task_id\": \"T2-simulation\",\n \"R\": 2000,\n \"B\": 399,\n \"n_cells\": 9,\n \"coverage\": {\n \"cr0_G5_icc0.0\": 0.797,\n \"cr1_G5_icc0.0\": 0.919,\n \"wcb_G5_icc0.0\": 0.869,\n \"cr0_G5_icc0.2\": 0.7195,\n \"cr1_G5_icc0.2\": 0.8815,\n \"wcb_G5_icc0.2\": 0.847,\n \"cr0_G5_icc0.5\": 0.7205,\n \"cr1_G5_icc0.5\": 0.8795,\n \"wcb_G5_icc0.5\": 0.8565,\n \"cr0_G10_icc0.0\": 0.8835,\n \"cr1_G10_icc0.0\": 0.9395,\n \"wcb_G10_icc0.0\": 0.926,\n \"cr0_G10_icc0.2\": 0.859,\n \"cr1_G10_icc0.2\": 0.9165,\n \"wcb_G10_icc0.2\": 0.939,\n \"cr0_G10_icc0.5\": 0.853,\n \"cr1_G10_icc0.5\": 0.917,\n \"wcb_G10_icc0.5\": 0.9365,\n \"cr0_G30_icc0.0\": 0.9305,\n \"cr1_G30_icc0.0\": 0.944,\n \"wcb_G30_icc0.0\": 0.946,\n \"cr0_G30_icc0.2\": 0.924,\n \"cr1_G30_icc0.2\": 0.94,\n \"wcb_G30_icc0.2\": 0.9515,\n \"cr0_G30_icc0.5\": 0.916,\n \"cr1_G30_icc0.5\": 0.929,\n \"wcb_G30_icc0.5\": 0.9415\n },\n \"mc_se_coverage\": {\n \"cr0_G5_icc0.0\": 0.008994192570764758,\n \"cr1_G5_icc0.0\": 0.006100778638829636,\n \"wcb_G5_icc0.0\": 0.00754450130890041,\n \"cr0_G5_icc0.2\": 0.01004539073406306,\n \"cr1_G5_icc0.2\": 0.007226954752867907,\n \"wcb_G5_icc0.2\": 0.008049565205649308,\n \"cr0_G5_icc0.5\": 0.010034434463386564,\n \"cr1_G5_icc0.5\": 0.007279414468211026,\n \"wcb_G5_icc0.5\": 0.007839252196478946,\n \"cr0_G10_icc0.0\": 0.007173832657652395,\n \"cr1_G10_icc0.0\": 0.005331029450303197,\n \"wcb_G10_icc0.0\": 0.005853375094763702,\n \"cr0_G10_icc0.2\": 0.007781998457979801,\n \"cr1_G10_icc0.2\": 0.006185780063985464,\n \"wcb_G10_icc0.2\": 0.005351588549206677,\n \"cr0_G10_icc0.5\": 0.007918049002121673,\n \"cr1_G10_icc0.5\": 0.006168914004912047,\n \"wcb_G10_icc0.5\": 0.005452877680637995,\n \"cr0_G30_icc0.0\": 0.005686376262612245,\n \"cr1_G30_icc0.0\": 0.005141206084179083,\n \"wcb_G30_icc0.0\": 0.005053909377897473,\n \"cr0_G30_icc0.2\": 0.005925537950262405,\n \"cr1_G30_icc0.2\": 0.005310367218940704,\n \"wcb_G30_icc0.2\": 0.004803527349771207,\n \"cr0_G30_icc0.5\": 0.006202580108309766,\n \"cr1_G30_icc0.5\": 0.005742778073371805,\n \"wcb_G30_icc0.5\": 0.0052477495176503994\n },\n \"rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.6531045734688924,\n \"cr1_G5_icc0.0\": 0.8163807168361153,\n \"cr0_G5_icc0.2\": 0.5073384003531096,\n \"cr1_G5_icc0.2\": 0.6341730004413871,\n \"cr0_G5_icc0.5\": 0.5054037231287982,\n \"cr1_G5_icc0.5\": 0.6317546539109978,\n \"cr0_G10_icc0.0\": 0.8457923977794889,\n \"cr1_G10_icc0.0\": 0.9397693308660987,\n \"cr0_G10_icc0.2\": 0.7595252021609881,\n \"cr1_G10_icc0.2\": 0.8439168912899868,\n \"cr0_G10_icc0.5\": 0.7668304455993856,\n \"cr1_G10_icc0.5\": 0.8520338284437619,\n \"cr0_G30_icc0.0\": 0.9349718907569042,\n \"cr1_G30_icc0.0\": 0.9672123007830045,\n \"cr0_G30_icc0.2\": 0.9185077380114064,\n \"cr1_G30_icc0.2\": 0.9501804186324896,\n \"cr0_G30_icc0.5\": 0.9153772013849211,\n \"cr1_G30_icc0.5\": 0.9469419324671597\n },\n \"failure_cells\": [\n \"cr0_G10_icc0.0\",\n \"cr0_G10_icc0.2\",\n \"cr0_G10_icc0.5\",\n \"cr0_G5_icc0.0\",\n \"cr0_G5_icc0.2\",\n \"cr0_G5_icc0.5\",\n \"cr1_G5_icc0.2\",\n \"cr1_G5_icc0.5\",\n \"wcb_G5_icc0.0\",\n \"wcb_G5_icc0.2\",\n \"wcb_G5_icc0.5\"\n ],\n \"n_failure_cells\": 11,\n \"nominal_cells\": [\n \"cr1_G10_icc0.0\",\n \"cr1_G30_icc0.0\",\n \"cr1_G30_icc0.2\",\n \"wcb_G30_icc0.0\",\n \"wcb_G30_icc0.2\",\n \"wcb_G30_icc0.5\"\n ],\n \"best_procedure_small_G\": \"cr1\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"\n }\n ],\n \"n_input_rows\": {\n \"design.csv\": 9\n },\n \"n_analysed\": 18000,\n \"random_seed\": 20261101,\n \"baseline_coverage_iid\": {\n \"iid_G5_icc0.0\": 0.944,\n \"iid_G5_icc0.2\": 0.465,\n \"iid_G5_icc0.5\": 0.296,\n \"iid_G10_icc0.0\": 0.95,\n \"iid_G10_icc0.2\": 0.4685,\n \"iid_G10_icc0.5\": 0.315,\n \"iid_G30_icc0.0\": 0.9555,\n \"iid_G30_icc0.2\": 0.482,\n \"iid_G30_icc0.5\": 0.298\n },\n \"mean_coverage_small_G\": {\n \"cr0\": 0.7456666666666667,\n \"cr1\": 0.8933333333333332,\n \"wcb\": 0.8574999999999999\n },\n \"mc_se_rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.012379922914024347,\n \"cr1_G5_icc0.0\": 0.015474903642530432,\n \"cr0_G5_icc0.2\": 0.012551876505571668,\n \"cr1_G5_icc0.2\": 0.015689845631964586,\n \"cr0_G5_icc0.5\": 0.012597853584309,\n \"cr1_G5_icc0.5\": 0.015747316980386252,\n \"cr0_G10_icc0.0\": 0.011335014984467255,\n \"cr1_G10_icc0.0\": 0.012594461093852507,\n \"cr0_G10_icc0.2\": 0.01321820179399827,\n \"cr1_G10_icc0.2\": 0.014686890882220303,\n \"cr0_G10_icc0.5\": 0.014357919526351126,\n \"cr1_G10_icc0.5\": 0.01595324391816792,\n \"cr0_G30_icc0.0\": 0.006800079998922955,\n \"cr1_G30_icc0.0\": 0.007034565516127195,\n \"cr0_G30_icc0.2\": 0.0085123734620183,\n \"cr1_G30_icc0.2\": 0.00880590358139824,\n \"cr0_G30_icc0.5\": 0.008257578831409366,\n \"cr1_G30_icc0.5\": 0.008542322929044171\n },\n \"mean_ci_halfwidth\": {\n \"cr0_G5_icc0.0\": 0.12921901485510345,\n \"cr1_G5_icc0.0\": 0.20465127376140263,\n \"wcb_G5_icc0.0\": 0.24438067367182634,\n \"cr0_G5_icc0.2\": 0.3363597922614171,\n \"cr1_G5_icc0.2\": 0.5327115363447698,\n \"wcb_G5_icc0.2\": 0.8814683692672445,\n \"cr0_G5_icc0.5\": 0.5098423713216832,\n \"cr1_G5_icc0.5\": 0.8074654556491971,\n \"wcb_G5_icc0.5\": 1.4186671197985352,\n \"cr0_G10_icc0.0\": 0.10653790084741674,\n \"cr1_G10_icc0.0\": 0.1296133046270418,\n \"wcb_G10_icc0.0\": 0.14460431575960167,\n \"cr0_G10_icc0.2\": 0.30019002401528055,\n \"cr1_G10_icc0.2\": 0.3652091952179194,\n \"wcb_G10_icc0.2\": 0.46849708469359214,\n \"cr0_G10_icc0.5\": 0.45866713816216975,\n \"cr1_G10_icc0.5\": 0.5580114027792793,\n \"wcb_G10_icc0.5\": 0.7171478891689117,\n \"cr0_G30_icc0.0\": 0.0636577759163469,\n \"cr1_G30_icc0.0\": 0.0675614709743341,\n \"wcb_G30_icc0.0\": 0.06989052905472656,\n \"cr0_G30_icc0.2\": 0.19481781032685644,\n \"cr1_G30_icc0.2\": 0.20676465126550664,\n \"wcb_G30_icc0.2\": 0.22177373668849737,\n \"cr0_G30_icc0.5\": 0.2981667448851098,\n \"cr1_G30_icc0.5\": 0.31645126758024267,\n \"wcb_G30_icc0.5\": 0.3408981681027193\n },\n \"exact_rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.6640625,\n \"cr1_G5_icc0.0\": 0.830078125,\n \"cr0_G5_icc0.2\": 0.49950132978723344,\n \"cr1_G5_icc0.2\": 0.6243766622340418,\n \"cr0_G5_icc0.5\": 0.48828125,\n \"cr1_G5_icc0.5\": 0.6103515625,\n \"cr0_G10_icc0.0\": 0.8393021120293873,\n \"cr1_G10_icc0.0\": 0.9325579022548748,\n \"cr0_G10_icc0.2\": 0.7598750380616052,\n \"cr1_G10_icc0.2\": 0.844305597846228,\n \"cr0_G10_icc0.5\": 0.7543877524211225,\n \"cr1_G10_icc0.5\": 0.8382086138012473,\n \"cr0_G30_icc0.0\": 0.9485596707818851,\n \"cr1_G30_icc0.0\": 0.9812686249467777,\n \"cr0_G30_icc0.2\": 0.9267376448823972,\n \"cr1_G30_icc0.2\": 0.9586941153955834,\n \"cr0_G30_icc0.5\": 0.9252970710455054,\n \"cr1_G30_icc0.5\": 0.9572038665987987\n },\n \"z_rel_bias_mc_vs_exact\": {\n \"cr0_G5_icc0.0\": -0.885136895213955,\n \"cr1_G5_icc0.0\": -0.8851368952139641,\n \"cr0_G5_icc0.2\": 0.6243744162394662,\n \"cr1_G5_icc0.2\": 0.6243744162394759,\n \"cr0_G5_icc0.5\": 1.3591579719679208,\n \"cr1_G5_icc0.5\": 1.359157971967924,\n \"cr0_G10_icc0.0\": 0.5725873110000674,\n \"cr1_G10_icc0.0\": 0.5725873110000634,\n \"cr0_G10_icc0.2\": -0.02646622483672057,\n \"cr1_G10_icc0.2\": -0.026466224836721407,\n \"cr0_G10_icc0.5\": 0.8666083658866433,\n \"cr1_G10_icc0.5\": 0.8666083658866424,\n \"cr0_G30_icc0.0\": -1.998179437173235,\n \"cr1_G30_icc0.0\": -1.9981794371732264,\n \"cr0_G30_icc0.2\": -0.9668169409756443,\n \"cr1_G30_icc0.2\": -0.9668169409756275,\n \"cr0_G30_icc0.5\": -1.2013048695160027,\n \"cr1_G30_icc0.5\": -1.2013048695160073\n },\n \"exact_var_ybar\": {\n \"G5_icc0.0\": 0.0078125,\n \"G5_icc0.2\": 0.0734375,\n \"G5_icc0.5\": 0.171875,\n \"G10_icc0.0\": 0.003787878787878788,\n \"G10_icc0.2\": 0.035169880624426074,\n \"G10_icc0.5\": 0.08224288337924701,\n \"G30_icc0.0\": 0.0011574074074074073,\n \"G30_icc0.2\": 0.011213991769547326,\n \"G30_icc0.5\": 0.0262988683127572\n }\n}[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G<=10 cells, CR1 at G=5 with ICC 0.2 and 0.5, WCB at all G=5 cells; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5 (icc0.2/0.5) and cr0_G10_icc0.0 lie only ~2.3-2.8 MC SE below 0.90.\"},\n {\"id\":\"C2\",\"text\":\"Only 6 of 27 pairs are consistent with nominal 95% coverage (CR1 at G10/ICC0, G30/ICC0, G30/ICC0.2; WCB at all G=30 cells).\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE rule applied to 27 pairs without multiplicity correction.\"},\n {\"id\":\"C3\",\"text\":\"With G=5, CR1 has the highest average coverage (0.893) ahead of WCB (0.857) and CR0 (0.746).\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_small_G\"],\"status\":\"supported\",\"caveat\":\"Specific to unrestricted Rademacher WCB with symmetric bootstrap-t and B=399.\"},\n {\"id\":\"C4\",\"text\":\"At G=10 with ICC>0 and at G=30, WCB is closer to nominal than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences at G=30 are of the order of 1-3 MC SE; paired SEs not computed.\"},\n {\"id\":\"C5\",\"text\":\"CR0 and CR1 variance estimators are biased downward in every cell, strongly at G=5 (CR0 0.51-0.65, CR1 0.63-0.82), and Monte Carlo bias estimates agree with analytic expectations.\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\",\"exact_rel_bias_var\",\"z_rel_bias_mc_vs_exact\"],\"status\":\"supported\",\"caveat\":\"Bias depends on the unbalanced cluster-size pattern.\"},\n {\"id\":\"C6\",\"text\":\"At G=5 WCB intervals are wider on average than CR1 intervals yet cover less.\",\"results_keys\":[\"mean_ci_halfwidth\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Explanation (variable, discrete bootstrap critical value) is interpretive, not separately tested.\"},\n {\"id\":\"C7\",\"text\":\"The naive i.i.d. interval covers ~0.95 at ICC=0 but only 0.30-0.48 when ICC>0.\",\"results_keys\":[\"baseline_coverage_iid\"],\"status\":\"supported\",\"caveat\":\"Baseline not required by the task; included for context.\"}\n]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2697d1a6-6fb2-4802-955d-9a60b0ea833e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}14{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"b33c424d53571c0fabed47712f3b771b4006607301b0adf79478a7f1beffd9c6","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01HVB5jUPPQH3MyiD9WKPo2B","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json"}}]}}15{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"dcab3bdf-66a0-4009-a242-fc187b1d5be5","timestamp":"2026-10-30T05:43:00.755Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"506e0560-7611-4f37-b859-3079090025a0","keep":2,"tail":["b33c424d53571c0fabed47712f3b771b4006607301b0adf79478a7f1beffd9c6","8d7d5a82579bd29186951b3fc9123d9c2b68e27af3fb214e8db8c743432e5e7c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5b949130cb8c908bc7509ee9c470b1852e0d45e11eff74810d2534770a8b7952"}16{"type":"last-prompt","lastPrompt":"Review","leafUuid":"54c5675b-46a1-44f2-a233-3e9dbd168ebb","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}17{"type":"atis-latch","atis":"","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}18{"parentUuid":"54c5675b-46a1-44f2-a233-3e9dbd168ebb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVnaLNh7NEXUw12Wxe","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Erahy1NrTrYPCRMjtBNKvU","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/exclusions.csv; cat data/design.csv; ls out/state"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":9329,"cache_read_input_tokens":2220,"output_tokens":90,"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":9329},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtVnKhuMw39sjcgb2ET","requestRef":"dcab3bdf-66a0-4009-a242-fc187b1d5be5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a24413ce-89eb-4d74-acb2-197b3ad2e398","timestamp":"2026-10-30T05:43:02.413Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}19{"parentUuid":"a24413ce-89eb-4d74-acb2-197b3ad2e398","isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Erahy1NrTrYPCRMjtBNKvU","type":"tool_result","content":"\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild cluster bootstrap-t CIs for a mean.\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nRandom numbers: per cell numpy default_rng(seed from design.csv); draw order per cell:\n u = sqrt(icc)*N(0,1) of shape (R,G); e = sqrt(1-icc)*N(0,1) of shape (R,N);\n Rademacher weights W = 2*integers(0,2,(R,B,G))-1.\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nOUT = os.path.join(ROOT, \"out\")\ndesign = pd.read_csv(os.path.join(ROOT, \"data\", \"design.csv\"))\nn_raw = len(design)\n\n# ---------------- design audit ----------------\ndata_issues = []\ncells = []\nfor _, row in design.iterrows():\n sizes = np.array([int(s) for s in str(row[\"cluster_sizes\"]).split(\"|\")])\n assert len(sizes) == row[\"G\"], f\"{row.cell_id}: len(cluster_sizes) != G\"\n assert sizes.sum() == row[\"N\"], f\"{row.cell_id}: sum(cluster_sizes) != N\"\n assert int(row[\"R\"]) == 2000 and int(row[\"B\"]) == 399\n cells.append(dict(cell_id=row[\"cell_id\"], G=int(row[\"G\"]), icc=float(row[\"icc\"]), sizes=sizes,\n N=int(row[\"N\"]), R=int(row[\"R\"]), B=int(row[\"B\"]), seed=int(row[\"seed\"]),\n mu=float(row[\"mu\"]), level=float(row[\"nominal_level\"])))\nassert design[\"cell_id\"].is_unique and not design.isna().any().any()\nif (design[\"G\"] == 5).any():\n data_issues.append({\n \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"})\n\n# exclusion ledger: nothing is excluded\npd.DataFrame([{\"step\": 1, \"rule\": \"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",\n \"n_before\": n_raw, \"n_after\": n_raw, \"n_removed\": 0,\n \"rationale\": \"all 9 cells consistent; no filtering\"}]).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\ndef key(est, c):\n return f\"{est}_G{c['G']}_icc{c['icc']:.1f}\"\n\nCHUNK = 250\nrows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nrelbias_se = {}\nfor c in cells:\n G, N, R, B, icc, mu, sizes = c[\"G\"], c[\"N\"], c[\"R\"], c[\"B\"], c[\"icc\"], c[\"mu\"], c[\"sizes\"]\n rng = np.random.default_rng(c[\"seed\"])\n gid = np.repeat(np.arange(G), sizes)\n u = np.sqrt(icc) * rng.standard_normal((R, G))\n e = np.sqrt(1 - icc) * rng.standard_normal((R, N))\n W = 2 * rng.integers(0, 2, size=(R, B, G)) - 1\n y = mu + u[:, gid] + e\n ybar = y.mean(axis=1)\n resid = y - ybar[:, None]\n S = np.zeros((R, G))\n for g in range(G):\n S[:, g] = resid[:, gid == g].sum(axis=1) # cluster residual sums\n V0 = (S ** 2).sum(axis=1) / N ** 2\n V1 = G / (G - 1) * V0\n var_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n z = 1.96 # as specified in TASK.md\n tcrit = stats.t.ppf(0.5 + c[\"level\"] / 2, G - 1)\n # wild cluster bootstrap-t: y* = ybar + w_g * resid; cluster sums of y*-ybar* are w_g S_g - n_g D\n q = np.empty(R)\n for s in range(0, R, CHUNK):\n Wc, Sc = W[s:s + CHUNK].astype(float), S[s:s + CHUNK]\n WS = Wc * Sc[:, None, :] # (r,B,G)\n D = WS.sum(axis=2) / N # ybar* - ybar\n Sstar = WS - sizes[None, None, :] * D[:, :, None]\n V1s = G / (G - 1) * (Sstar ** 2).sum(axis=2) / N ** 2\n with np.errstate(divide=\"ignore\", invalid=\"ignore\"):\n tstar = np.abs(D / np.sqrt(V1s))\n tstar = np.where(np.isfinite(tstar), tstar, 0.0) # guard only (0/0 does not occur with continuous data)\n # 0.95 empirical quantile = inverted-CDF definition: the ceil(0.95*B)=380th order statistic\n q[s:s + CHUNK] = np.quantile(tstar, c[\"level\"], axis=1, method=\"inverted_cdf\")\n # naive i.i.d. baseline (ignores clustering)\n s2 = resid.var(axis=1, ddof=1)\n Viid = s2 / N\n hw = {\"cr0\": z * np.sqrt(V0), \"cr1\": tcrit * np.sqrt(V1), \"wcb\": q * np.sqrt(V1),\n \"iid\": z * np.sqrt(Viid)}\n err = np.abs(ybar - mu)\n for est in [\"cr0\", \"cr1\", \"wcb\", \"iid\"]:\n p = float(np.mean(err <= hw[est]))\n se = float(np.sqrt(p * (1 - p) / R))\n if est == \"iid\":\n base_cov[key(\"iid\", c)] = p\n continue\n k = key(est, c)\n coverage[k], mcse[k] = p, se\n rb = None\n if est in (\"cr0\", \"cr1\"):\n rb = float(np.mean(V0 if est == \"cr0\" else V1) / var_exact)\n relbias[k] = rb\n Vk = V0 if est == \"cr0\" else V1\n relbias_se[k] = float(Vk.std(ddof=1) / np.sqrt(R) / var_exact)\n rows.append(dict(estimator=est, cell_id=c[\"cell_id\"], G=G, icc=icc, coverage=p, mc_se_coverage=se,\n rel_bias_var=rb, mean_ci_halfwidth=float(hw[est].mean()), R=R))\n print(f\"{c['cell_id']} G={G} icc={icc}: \" + \", \".join(f\"{k2}={coverage[key(k2, c)]:.4f}\" for k2 in [\"cr0\", \"cr1\", \"wcb\"])\n + f\", iid={base_cov[key('iid', c)]:.4f}\")\n\ntable = pd.DataFrame(rows)\ntable[\"_o\"] = table[\"estimator\"].map({\"cr0\": 0, \"cr1\": 1, \"wcb\": 2})\ntable = table.sort_values([\"_o\", \"G\", \"icc\"]).drop(columns=\"_o\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n# analytic E[V_CR0]/Var(ybar) (verification of the Monte Carlo bias estimates):\n# S = A y with A = C - n 1'/N (C: G x N cluster indicator); E[S'S] = tr(A Sigma A'),\n# Sigma = icc * C'C + (1-icc) I.\nexact_rb = {}\nfor c in cells:\n G, N, icc, sizes = c[\"G\"], c[\"N\"], c[\"icc\"], c[\"sizes\"]\n C = (np.repeat(np.arange(G), sizes)[None, :] == np.arange(G)[:, None]).astype(float)\n A = C - np.outer(sizes, np.ones(N)) / N\n Sigma = icc * C.T @ C + (1 - icc) * np.eye(N)\n v_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n ev0 = np.trace(A @ Sigma @ A.T) / N ** 2 / v_exact\n exact_rb[key(\"cr0\", c)] = float(ev0)\n exact_rb[key(\"cr1\", c)] = float(G / (G - 1) * ev0)\n\nfailure = sorted(k for k, p in coverage.items() if p < 0.90)\nnominal = sorted(k for k, p in coverage.items() if abs(p - 0.95) <= 2 * mcse[k])\nsmall = {est: float(np.mean([coverage[key(est, c)] for c in cells if c[\"G\"] == 5])) for est in [\"cr0\", \"cr1\", \"wcb\"]}\nbest_small = max(small, key=small.get)\n\nresults = {\n \"task_id\": \"T2-simulation\",\n \"R\": int(cells[0][\"R\"]), \"B\": int(cells[0][\"B\"]), \"n_cells\": len(cells),\n \"coverage\": coverage, \"mc_se_coverage\": mcse, \"rel_bias_var\": relbias,\n \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n \"best_procedure_small_G\": best_small,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": {\"design.csv\": n_raw},\n \"n_analysed\": int(sum(c[\"R\"] for c in cells)),\n \"random_seed\": int(cells[0][\"seed\"]),\n \"baseline_coverage_iid\": base_cov,\n \"mean_coverage_small_G\": small,\n \"mc_se_rel_bias_var\": relbias_se,\n \"mean_ci_halfwidth\": {f\"{r['estimator']}_G{r['G']}_icc{r['icc']:.1f}\": r[\"mean_ci_halfwidth\"] for r in rows},\n \"exact_rel_bias_var\": exact_rb,\n \"z_rel_bias_mc_vs_exact\": {k: float((relbias[k] - exact_rb[k]) / relbias_se[k]) for k in relbias},\n \"exact_var_ybar\": {f\"G{c['G']}_icc{c['icc']:.1f}\": float((c['icc'] * (c['sizes'] ** 2).sum() + (1 - c['icc']) * c['N']) / c['N'] ** 2) for c in cells},\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\nGs = sorted({c[\"G\"] for c in cells})\nfor ax, icc in zip(axes, [0.0, 0.2, 0.5]):\n for est, mk in [(\"cr0\", \"o\"), (\"cr1\", \"s\"), (\"wcb\", \"^\"), (\"iid\", \"x\")]:\n src = base_cov if est == \"iid\" else coverage\n p = np.array([src[f\"{est}_G{G}_icc{icc:.1f}\"] for G in Gs])\n se = np.sqrt(p * (1 - p) / 2000)\n ax.errorbar(Gs, p, yerr=2 * se, marker=mk, capsize=3,\n label=est.upper() + (\" (naive baseline)\" if est == \"iid\" else \"\"),\n linestyle=\":\" if est == \"iid\" else \"-\")\n ax.axhline(0.95, color=\"k\", lw=1, label=\"nominal 0.95\")\n ax.axhline(0.90, color=\"r\", lw=1, ls=\"--\", label=\"failure line 0.90\")\n ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels(Gs); ax.minorticks_off()\n ax.set_title(f\"ICC = {icc}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±2 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(\"Coverage of nominal 95% intervals for the mean (R=2000 per cell)\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best_small)\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap intervals for a mean with few clusters\n\nTechnical note for T2-simulation. To reproduce everything: `~/wp29/venv/bin/python out/analysis.py` (about 2 s). It reads only `data/design.csv` and writes `out/results.json`, `out/table1.csv`, `out/figure1.png` and `out/exclusions.csv`. Below, keys in `code` refer to `out/results.json`. Pairs are named `<estimator>_G<G>_icc<icc>`.\n\n## Question\nWhen the data are grouped in only a few, unequal-sized clusters, how close to the nominal 95% do three standard cluster-robust intervals for a population mean μ actually cover? The three intervals are CR0 with a normal critical value, CR1 with a t(G−1) critical value, and the wild cluster bootstrap-t with Rademacher weights (WCB). Which (procedure, design) pairs fall below 90% coverage (the \"failure regimes\")? How biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ)?\n\n## Data and exclusions\nNo observed data are used. The only input is the design file `data/design.csv`: 9 rows (`n_input_rows`), one per cell of G ∈ {5, 10, 30} × ICC ∈ {0, 0.2, 0.5}. Each row gives unequal cluster sizes (8, 16, 32, 64 repeated, so N = 128, 264 and 864), R = 2000, B = 399 and one seed per cell. The SHA-256 hashes match the bundle manifest. In every row the number of listed cluster sizes equals G and their sum equals N; the script asserts both. Nothing was excluded (`out/exclusions.csv`: 9 → 9 cells). We simulated 9 × 2000 = 18 000 replications (`n_analysed`, `R`, `B`, `n_cells`). C1 used seed 20261101 (`random_seed`); the other cells use their own seeds from the design file. One issue is recorded in `data_issues`: with G = 5 the Rademacher weights have only 32 sign patterns, so the WCB reference distribution is coarse.\n\n## Method\n- **DGP.** y_ig = μ + u_g + e_ig, with u_g ~ N(0, ICC) and e_ig ~ N(0, 1−ICC), and μ = 0. Each cell uses `numpy.random.default_rng(seed)`. Draws are made in a fixed order: u (R×G), then e (R×N), then the Rademacher weights (R×B×G).\n- **Exact variance.** Var(ȳ) = [ICC Σ n_g² + (1−ICC) N] / N² (`exact_var_ybar`).\n- **CR0.** V̂ = Σ_g (Σ_i ê_ig)² / N², with interval ȳ ± 1.96 √V̂ (1.96 used literally, as specified).\n- **CR1.** V̂ = G/(G−1) · V̂_CR0, with interval ȳ ± t_{0.975, G−1} √V̂.\n- **WCB.** The bootstrap is vectorised. Write S_g for the cluster sums of the residuals. Then ȳ* − ȳ = D = Σ w_g S_g / N, and the bootstrap residuals have cluster sums w_g S_g − n_g D. These give V̂*_CR1 and |t*_b| = |D| / √V̂*_CR1. The critical value q is the 0.95 empirical quantile of the 399 values of |t*|, using the inverted-CDF definition: the ⌈0.95·399⌉ = 380th order statistic, the usual (B+1)(1−α) choice. The interval is ȳ ± q √V̂_CR1. A plain loop implementation gave the same q (max difference 4e−15; see `out/state/checks.md`).\n- **Evaluation.** Coverage is the share of the R intervals that contain μ (`coverage`), with MC SE √(p̂(1−p̂)/R) (`mc_se_coverage`). The variance relative bias is mean(V̂)/Var(ȳ) (`rel_bias_var`). A pair is a failure when coverage < 0.90 (`failure_cells`). It is \"consistent with nominal\" when |p̂ − 0.95| ≤ 2·SE (`nominal_cells`).\n- **Baseline (P2).** A naive i.i.d. interval, ȳ ± 1.96·s/√N, which ignores clustering, evaluated on the same replications (`baseline_coverage_iid`).\n- **Verification.** E[V̂_CR0] is a quadratic form, so it was computed analytically: tr(AΣA′)/N² with A = C − n1′/N (`exact_rel_bias_var`). This was compared with the Monte Carlo means (`z_rel_bias_mc_vs_exact`).\n\n## Results\nTable 1 (`out/table1.csv`) and Figure 1 (`out/figure1.png`) give all 27 pairs. Coverage (`coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive iid (baseline) |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.797 | 0.919 | 0.869 | 0.944 |\n| 5 | 0.2 | 0.720 | 0.882 | 0.847 | 0.465 |\n| 5 | 0.5 | 0.721 | 0.880 | 0.857 | 0.296 |\n| 10 | 0.0 | 0.884 | 0.940 | 0.926 | 0.950 |\n| 10 | 0.2 | 0.859 | 0.917 | 0.939 | 0.469 |\n| 10 | 0.5 | 0.853 | 0.917 | 0.937 | 0.315 |\n| 30 | 0.0 | 0.931 | 0.944 | 0.946 | 0.956 |\n| 30 | 0.2 | 0.924 | 0.940 | 0.952 | 0.482 |\n| 30 | 0.5 | 0.916 | 0.929 | 0.942 | 0.298 |\n\n1. **Failure regimes** (`failure_cells`, `n_failure_cells` = 11):\n - CR0 fails in all six cells with G ≤ 10.\n - CR1 fails at G = 5 when ICC = 0.2 or 0.5; at ICC = 0 its coverage is 0.919.\n - WCB fails in all three G = 5 cells.\n - No procedure fails at G = 30.\n2. **Consistent with nominal 0.95** (`nominal_cells`): only 6 of the 27 pairs. These are cr1_G10_icc0.0, cr1_G30_icc0.0, cr1_G30_icc0.2 and WCB in all three G = 30 cells. Every other pair under-covers by more than 2 MC SE. Even at G = 30, CR0 (0.916–0.931) and CR1 at ICC = 0.5 (0.929) are significantly below nominal.\n3. **Best procedure at G = 5** (`best_procedure_small_G` = cr1). Mean coverage over the three G = 5 cells is 0.893 for CR1, 0.857 for WCB and 0.746 for CR0 (`mean_coverage_small_G`). At G = 10 with ICC > 0, WCB covers better than CR1 (0.939/0.937 vs 0.917/0.917). At G = 30, WCB is the closest to nominal.\n4. **WCB at G = 5: wider but covers less.** WCB intervals are on average much wider than CR1 (mean half-width 0.88 vs 0.53 at ICC = 0.2; `mean_ci_halfwidth`), yet they cover less. The bootstrap critical value is very variable: when one large cluster dominates, |t*| takes few distinct values. The result is very wide intervals in some replications and too-narrow ones in others.\n5. **Variance bias** (`rel_bias_var`). Both sandwich estimators are biased downward in every cell, and the bias is worst with few clusters:\n - CR0: E[V̂]/Var(ȳ) ≈ 0.51–0.65 at G = 5, 0.76–0.85 at G = 10 and 0.92–0.94 at G = 30.\n - CR1: 0.63–0.82, 0.84–0.94 and 0.95–0.97 at the same G.\n \n The downward bias comes from estimating μ by ȳ, which removes variability that a single dominant cluster carries. It is larger when ICC > 0 than when ICC = 0, because the large clusters then contribute more to Var(ȳ). The analytic values (`exact_rel_bias_var`) agree.\n6. **Baseline.** Ignoring clustering (`baseline_coverage_iid`) is fine at ICC = 0 (0.94–0.96) but disastrous at ICC > 0 (0.30–0.48), at every G. All three cluster-robust procedures are a large improvement, but none reaches nominal coverage reliably with 5 clusters.\n\n## Uncertainty\n- **Coverage.** With R = 2000, the MC SE of a coverage estimate is about 0.0049 near 0.95 and at most 0.010 (CR0 at G = 5) (`mc_se_coverage`). So ±2 SE ≈ ±0.01–0.02.\n- **Classifications.** Classifying a pair as a failure is robust when its coverage is far from 0.90. The cases nearest the threshold are:\n - cr1_G5_icc0.2 (0.8815, SE 0.0072) and cr1_G5_icc0.5 (0.8795, SE 0.0073): about 2.6–2.8 SE below 0.90.\n - cr0_G10_icc0.0 (0.8835, SE 0.0072): about 2.3 SE below.\n - cr1_G5_icc0.0 (0.919, SE 0.0061): about 3.1 SE above.\n \n Other seeds could plausibly move these by a few hundredths. The \"nominal\" set rests on a 2-SE rule applied to 27 pairs, so a borderline pair could be misclassified by chance (multiple comparisons; no correction was applied, as the task specifies the rule).\n- **Variance bias.** The MC SE of the relative bias is 0.007–0.016 (`mc_se_rel_bias_var`). The Monte Carlo means agree with the analytic expectations (`exact_rel_bias_var`): z-scores range from −2.0 to 1.36 over the 9 independent cells (`z_rel_bias_mc_vs_exact`). This is consistent with pure MC noise and confirms the implementation.\n- **Bootstrap error.** The WCB coverage also includes bootstrap randomness (B = 399), which is part of the procedure as specified. It is absorbed into the binomial MC SE.\n- **Comparisons between procedures.** All procedures in a cell use the same replications, so their differences are positively correlated. The marginal SEs are therefore conservative for those differences. We did not compute paired SEs separately. The G = 5 gap between CR1 and WCB (0.036 on average) is several times the marginal SE of each mean (≈0.004).\n\n## Limitations and open issues\n- **Distribution.** Only Gaussian random intercepts and Gaussian errors. Skewed or heavy-tailed u_g or e_ig, which usually hurt few-cluster inference more, are not covered.\n- **Heterogeneity.** Within-cluster variance and ICC are the same in every cluster. Cluster sizes follow one fixed unbalanced pattern (8/16/32/64) and are not random or informative about the outcome. Balanced designs, or designs even more dominated by one cluster, may behave differently. At G = 5, half of the sample is in one cluster, which drives much of the small-G behaviour.\n- **Regressors.** The estimand is a simple mean, so there are no regressors and no leverage from covariates. Results for regression coefficients, fixed effects, or treatment indicators that vary only at the cluster level can differ substantially.\n- **Other methods and weights.** We did not study:\n - CR2/CR3 (bias-reduced linearisation) or Bell–McCaffrey/Satterthwaite degrees of freedom;\n - the restricted (null-imposed) WCB or the WCB p-value inversion;\n - Webb six-point or Mammen weights;\n - full enumeration of the 32 Rademacher patterns at G = 5;\n - the equal-tailed rather than symmetric bootstrap-t.\n \n The WCB results apply only to the unrestricted, symmetric, Rademacher version with B = 399.\n- **Specification choices.**\n - The \"0.95 empirical quantile\" was implemented as the inverted-CDF (380th of 399) order statistic. Interpolated quantile definitions would change q slightly.\n - CR0 uses the literal 1.96 as specified.\n- **Design coverage.** Only the 9 cells and R = 2000 required by the task were run. No other G values or ICC values were explored.\n- **Feasibility.** The task was completed as specified (`feasibility` = \"complete\").\nstep,rule,n_before,n_after,n_removed,rationale\n1,\"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",9,9,0,all 9 cells consistent; no filtering\ncell_id,G,icc,cluster_sizes,N,R,B,seed,mu,total_variance,nominal_level\r\nC1,5,0.0,8|16|32|64|8,128,2000,399,20261101,0.0,1.0,0.95\r\nC2,5,0.2,8|16|32|64|8,128,2000,399,20261102,0.0,1.0,0.95\r\nC3,5,0.5,8|16|32|64|8,128,2000,399,20261103,0.0,1.0,0.95\r\nC4,10,0.0,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261104,0.0,1.0,0.95\r\nC5,10,0.2,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261105,0.0,1.0,0.95\r\nC6,10,0.5,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261106,0.0,1.0,0.95\r\nC7,30,0.0,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261107,0.0,1.0,0.95\r\nC8,30,0.2,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261108,0.0,1.0,0.95\r\nC9,30,0.5,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261109,0.0,1.0,0.95\r\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","is_error":false}]},"uuid":"96e795ef-9b85-470a-9c4c-edfa9cd5bf68","timestamp":"2026-10-30T05:43:02.464Z","toolUseResult":{"stdout":"\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild cluster bootstrap-t CIs for a mean.\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nRandom numbers: per cell numpy default_rng(seed from design.csv); draw order per cell:\n u = sqrt(icc)*N(0,1) of shape (R,G); e = sqrt(1-icc)*N(0,1) of shape (R,N);\n Rademacher weights W = 2*integers(0,2,(R,B,G))-1.\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nOUT = os.path.join(ROOT, \"out\")\ndesign = pd.read_csv(os.path.join(ROOT, \"data\", \"design.csv\"))\nn_raw = len(design)\n\n# ---------------- design audit ----------------\ndata_issues = []\ncells = []\nfor _, row in design.iterrows():\n sizes = np.array([int(s) for s in str(row[\"cluster_sizes\"]).split(\"|\")])\n assert len(sizes) == row[\"G\"], f\"{row.cell_id}: len(cluster_sizes) != G\"\n assert sizes.sum() == row[\"N\"], f\"{row.cell_id}: sum(cluster_sizes) != N\"\n assert int(row[\"R\"]) == 2000 and int(row[\"B\"]) == 399\n cells.append(dict(cell_id=row[\"cell_id\"], G=int(row[\"G\"]), icc=float(row[\"icc\"]), sizes=sizes,\n N=int(row[\"N\"]), R=int(row[\"R\"]), B=int(row[\"B\"]), seed=int(row[\"seed\"]),\n mu=float(row[\"mu\"]), level=float(row[\"nominal_level\"])))\nassert design[\"cell_id\"].is_unique and not design.isna().any().any()\nif (design[\"G\"] == 5).any():\n data_issues.append({\n \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"})\n\n# exclusion ledger: nothing is excluded\npd.DataFrame([{\"step\": 1, \"rule\": \"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",\n \"n_before\": n_raw, \"n_after\": n_raw, \"n_removed\": 0,\n \"rationale\": \"all 9 cells consistent; no filtering\"}]).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\ndef key(est, c):\n return f\"{est}_G{c['G']}_icc{c['icc']:.1f}\"\n\nCHUNK = 250\nrows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nrelbias_se = {}\nfor c in cells:\n G, N, R, B, icc, mu, sizes = c[\"G\"], c[\"N\"], c[\"R\"], c[\"B\"], c[\"icc\"], c[\"mu\"], c[\"sizes\"]\n rng = np.random.default_rng(c[\"seed\"])\n gid = np.repeat(np.arange(G), sizes)\n u = np.sqrt(icc) * rng.standard_normal((R, G))\n e = np.sqrt(1 - icc) * rng.standard_normal((R, N))\n W = 2 * rng.integers(0, 2, size=(R, B, G)) - 1\n y = mu + u[:, gid] + e\n ybar = y.mean(axis=1)\n resid = y - ybar[:, None]\n S = np.zeros((R, G))\n for g in range(G):\n S[:, g] = resid[:, gid == g].sum(axis=1) # cluster residual sums\n V0 = (S ** 2).sum(axis=1) / N ** 2\n V1 = G / (G - 1) * V0\n var_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n z = 1.96 # as specified in TASK.md\n tcrit = stats.t.ppf(0.5 + c[\"level\"] / 2, G - 1)\n # wild cluster bootstrap-t: y* = ybar + w_g * resid; cluster sums of y*-ybar* are w_g S_g - n_g D\n q = np.empty(R)\n for s in range(0, R, CHUNK):\n Wc, Sc = W[s:s + CHUNK].astype(float), S[s:s + CHUNK]\n WS = Wc * Sc[:, None, :] # (r,B,G)\n D = WS.sum(axis=2) / N # ybar* - ybar\n Sstar = WS - sizes[None, None, :] * D[:, :, None]\n V1s = G / (G - 1) * (Sstar ** 2).sum(axis=2) / N ** 2\n with np.errstate(divide=\"ignore\", invalid=\"ignore\"):\n tstar = np.abs(D / np.sqrt(V1s))\n tstar = np.where(np.isfinite(tstar), tstar, 0.0) # guard only (0/0 does not occur with continuous data)\n # 0.95 empirical quantile = inverted-CDF definition: the ceil(0.95*B)=380th order statistic\n q[s:s + CHUNK] = np.quantile(tstar, c[\"level\"], axis=1, method=\"inverted_cdf\")\n # naive i.i.d. baseline (ignores clustering)\n s2 = resid.var(axis=1, ddof=1)\n Viid = s2 / N\n hw = {\"cr0\": z * np.sqrt(V0), \"cr1\": tcrit * np.sqrt(V1), \"wcb\": q * np.sqrt(V1),\n \"iid\": z * np.sqrt(Viid)}\n err = np.abs(ybar - mu)\n for est in [\"cr0\", \"cr1\", \"wcb\", \"iid\"]:\n p = float(np.mean(err <= hw[est]))\n se = float(np.sqrt(p * (1 - p) / R))\n if est == \"iid\":\n base_cov[key(\"iid\", c)] = p\n continue\n k = key(est, c)\n coverage[k], mcse[k] = p, se\n rb = None\n if est in (\"cr0\", \"cr1\"):\n rb = float(np.mean(V0 if est == \"cr0\" else V1) / var_exact)\n relbias[k] = rb\n Vk = V0 if est == \"cr0\" else V1\n relbias_se[k] = float(Vk.std(ddof=1) / np.sqrt(R) / var_exact)\n rows.append(dict(estimator=est, cell_id=c[\"cell_id\"], G=G, icc=icc, coverage=p, mc_se_coverage=se,\n rel_bias_var=rb, mean_ci_halfwidth=float(hw[est].mean()), R=R))\n print(f\"{c['cell_id']} G={G} icc={icc}: \" + \", \".join(f\"{k2}={coverage[key(k2, c)]:.4f}\" for k2 in [\"cr0\", \"cr1\", \"wcb\"])\n + f\", iid={base_cov[key('iid', c)]:.4f}\")\n\ntable = pd.DataFrame(rows)\ntable[\"_o\"] = table[\"estimator\"].map({\"cr0\": 0, \"cr1\": 1, \"wcb\": 2})\ntable = table.sort_values([\"_o\", \"G\", \"icc\"]).drop(columns=\"_o\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n# analytic E[V_CR0]/Var(ybar) (verification of the Monte Carlo bias estimates):\n# S = A y with A = C - n 1'/N (C: G x N cluster indicator); E[S'S] = tr(A Sigma A'),\n# Sigma = icc * C'C + (1-icc) I.\nexact_rb = {}\nfor c in cells:\n G, N, icc, sizes = c[\"G\"], c[\"N\"], c[\"icc\"], c[\"sizes\"]\n C = (np.repeat(np.arange(G), sizes)[None, :] == np.arange(G)[:, None]).astype(float)\n A = C - np.outer(sizes, np.ones(N)) / N\n Sigma = icc * C.T @ C + (1 - icc) * np.eye(N)\n v_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n ev0 = np.trace(A @ Sigma @ A.T) / N ** 2 / v_exact\n exact_rb[key(\"cr0\", c)] = float(ev0)\n exact_rb[key(\"cr1\", c)] = float(G / (G - 1) * ev0)\n\nfailure = sorted(k for k, p in coverage.items() if p < 0.90)\nnominal = sorted(k for k, p in coverage.items() if abs(p - 0.95) <= 2 * mcse[k])\nsmall = {est: float(np.mean([coverage[key(est, c)] for c in cells if c[\"G\"] == 5])) for est in [\"cr0\", \"cr1\", \"wcb\"]}\nbest_small = max(small, key=small.get)\n\nresults = {\n \"task_id\": \"T2-simulation\",\n \"R\": int(cells[0][\"R\"]), \"B\": int(cells[0][\"B\"]), \"n_cells\": len(cells),\n \"coverage\": coverage, \"mc_se_coverage\": mcse, \"rel_bias_var\": relbias,\n \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n \"best_procedure_small_G\": best_small,\n \"feasibility\": \"complete\", \"feasibility_reason\": None,\n \"data_issues\": data_issues,\n \"n_input_rows\": {\"design.csv\": n_raw},\n \"n_analysed\": int(sum(c[\"R\"] for c in cells)),\n \"random_seed\": int(cells[0][\"seed\"]),\n \"baseline_coverage_iid\": base_cov,\n \"mean_coverage_small_G\": small,\n \"mc_se_rel_bias_var\": relbias_se,\n \"mean_ci_halfwidth\": {f\"{r['estimator']}_G{r['G']}_icc{r['icc']:.1f}\": r[\"mean_ci_halfwidth\"] for r in rows},\n \"exact_rel_bias_var\": exact_rb,\n \"z_rel_bias_mc_vs_exact\": {k: float((relbias[k] - exact_rb[k]) / relbias_se[k]) for k in relbias},\n \"exact_var_ybar\": {f\"G{c['G']}_icc{c['icc']:.1f}\": float((c['icc'] * (c['sizes'] ** 2).sum() + (1 - c['icc']) * c['N']) / c['N'] ** 2) for c in cells},\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\nGs = sorted({c[\"G\"] for c in cells})\nfor ax, icc in zip(axes, [0.0, 0.2, 0.5]):\n for est, mk in [(\"cr0\", \"o\"), (\"cr1\", \"s\"), (\"wcb\", \"^\"), (\"iid\", \"x\")]:\n src = base_cov if est == \"iid\" else coverage\n p = np.array([src[f\"{est}_G{G}_icc{icc:.1f}\"] for G in Gs])\n se = np.sqrt(p * (1 - p) / 2000)\n ax.errorbar(Gs, p, yerr=2 * se, marker=mk, capsize=3,\n label=est.upper() + (\" (naive baseline)\" if est == \"iid\" else \"\"),\n linestyle=\":\" if est == \"iid\" else \"-\")\n ax.axhline(0.95, color=\"k\", lw=1, label=\"nominal 0.95\")\n ax.axhline(0.90, color=\"r\", lw=1, ls=\"--\", label=\"failure line 0.90\")\n ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels(Gs); ax.minorticks_off()\n ax.set_title(f\"ICC = {icc}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±2 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(\"Coverage of nominal 95% intervals for the mean (R=2000 per cell)\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best_small)\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap intervals for a mean with few clusters\n\nTechnical note for T2-simulation. To reproduce everything: `~/wp29/venv/bin/python out/analysis.py` (about 2 s). It reads only `data/design.csv` and writes `out/results.json`, `out/table1.csv`, `out/figure1.png` and `out/exclusions.csv`. Below, keys in `code` refer to `out/results.json`. Pairs are named `<estimator>_G<G>_icc<icc>`.\n\n## Question\nWhen the data are grouped in only a few, unequal-sized clusters, how close to the nominal 95% do three standard cluster-robust intervals for a population mean μ actually cover? The three intervals are CR0 with a normal critical value, CR1 with a t(G−1) critical value, and the wild cluster bootstrap-t with Rademacher weights (WCB). Which (procedure, design) pairs fall below 90% coverage (the \"failure regimes\")? How biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ)?\n\n## Data and exclusions\nNo observed data are used. The only input is the design file `data/design.csv`: 9 rows (`n_input_rows`), one per cell of G ∈ {5, 10, 30} × ICC ∈ {0, 0.2, 0.5}. Each row gives unequal cluster sizes (8, 16, 32, 64 repeated, so N = 128, 264 and 864), R = 2000, B = 399 and one seed per cell. The SHA-256 hashes match the bundle manifest. In every row the number of listed cluster sizes equals G and their sum equals N; the script asserts both. Nothing was excluded (`out/exclusions.csv`: 9 → 9 cells). We simulated 9 × 2000 = 18 000 replications (`n_analysed`, `R`, `B`, `n_cells`). C1 used seed 20261101 (`random_seed`); the other cells use their own seeds from the design file. One issue is recorded in `data_issues`: with G = 5 the Rademacher weights have only 32 sign patterns, so the WCB reference distribution is coarse.\n\n## Method\n- **DGP.** y_ig = μ + u_g + e_ig, with u_g ~ N(0, ICC) and e_ig ~ N(0, 1−ICC), and μ = 0. Each cell uses `numpy.random.default_rng(seed)`. Draws are made in a fixed order: u (R×G), then e (R×N), then the Rademacher weights (R×B×G).\n- **Exact variance.** Var(ȳ) = [ICC Σ n_g² + (1−ICC) N] / N² (`exact_var_ybar`).\n- **CR0.** V̂ = Σ_g (Σ_i ê_ig)² / N², with interval ȳ ± 1.96 √V̂ (1.96 used literally, as specified).\n- **CR1.** V̂ = G/(G−1) · V̂_CR0, with interval ȳ ± t_{0.975, G−1} √V̂.\n- **WCB.** The bootstrap is vectorised. Write S_g for the cluster sums of the residuals. Then ȳ* − ȳ = D = Σ w_g S_g / N, and the bootstrap residuals have cluster sums w_g S_g − n_g D. These give V̂*_CR1 and |t*_b| = |D| / √V̂*_CR1. The critical value q is the 0.95 empirical quantile of the 399 values of |t*|, using the inverted-CDF definition: the ⌈0.95·399⌉ = 380th order statistic, the usual (B+1)(1−α) choice. The interval is ȳ ± q √V̂_CR1. A plain loop implementation gave the same q (max difference 4e−15; see `out/state/checks.md`).\n- **Evaluation.** Coverage is the share of the R intervals that contain μ (`coverage`), with MC SE √(p̂(1−p̂)/R) (`mc_se_coverage`). The variance relative bias is mean(V̂)/Var(ȳ) (`rel_bias_var`). A pair is a failure when coverage < 0.90 (`failure_cells`). It is \"consistent with nominal\" when |p̂ − 0.95| ≤ 2·SE (`nominal_cells`).\n- **Baseline (P2).** A naive i.i.d. interval, ȳ ± 1.96·s/√N, which ignores clustering, evaluated on the same replications (`baseline_coverage_iid`).\n- **Verification.** E[V̂_CR0] is a quadratic form, so it was computed analytically: tr(AΣA′)/N² with A = C − n1′/N (`exact_rel_bias_var`). This was compared with the Monte Carlo means (`z_rel_bias_mc_vs_exact`).\n\n## Results\nTable 1 (`out/table1.csv`) and Figure 1 (`out/figure1.png`) give all 27 pairs. Coverage (`coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive iid (baseline) |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.797 | 0.919 | 0.869 | 0.944 |\n| 5 | 0.2 | 0.720 | 0.882 | 0.847 | 0.465 |\n| 5 | 0.5 | 0.721 | 0.880 | 0.857 | 0.296 |\n| 10 | 0.0 | 0.884 | 0.940 | 0.926 | 0.950 |\n| 10 | 0.2 | 0.859 | 0.917 | 0.939 | 0.469 |\n| 10 | 0.5 | 0.853 | 0.917 | 0.937 | 0.315 |\n| 30 | 0.0 | 0.931 | 0.944 | 0.946 | 0.956 |\n| 30 | 0.2 | 0.924 | 0.940 | 0.952 | 0.482 |\n| 30 | 0.5 | 0.916 | 0.929 | 0.942 | 0.298 |\n\n1. **Failure regimes** (`failure_cells`, `n_failure_cells` = 11):\n - CR0 fails in all six cells with G ≤ 10.\n - CR1 fails at G = 5 when ICC = 0.2 or 0.5; at ICC = 0 its coverage is 0.919.\n - WCB fails in all three G = 5 cells.\n - No procedure fails at G = 30.\n2. **Consistent with nominal 0.95** (`nominal_cells`): only 6 of the 27 pairs. These are cr1_G10_icc0.0, cr1_G30_icc0.0, cr1_G30_icc0.2 and WCB in all three G = 30 cells. Every other pair under-covers by more than 2 MC SE. Even at G = 30, CR0 (0.916–0.931) and CR1 at ICC = 0.5 (0.929) are significantly below nominal.\n3. **Best procedure at G = 5** (`best_procedure_small_G` = cr1). Mean coverage over the three G = 5 cells is 0.893 for CR1, 0.857 for WCB and 0.746 for CR0 (`mean_coverage_small_G`). At G = 10 with ICC > 0, WCB covers better than CR1 (0.939/0.937 vs 0.917/0.917). At G = 30, WCB is the closest to nominal.\n4. **WCB at G = 5: wider but covers less.** WCB intervals are on average much wider than CR1 (mean half-width 0.88 vs 0.53 at ICC = 0.2; `mean_ci_halfwidth`), yet they cover less. The bootstrap critical value is very variable: when one large cluster dominates, |t*| takes few distinct values. The result is very wide intervals in some replications and too-narrow ones in others.\n5. **Variance bias** (`rel_bias_var`). Both sandwich estimators are biased downward in every cell, and the bias is worst with few clusters:\n - CR0: E[V̂]/Var(ȳ) ≈ 0.51–0.65 at G = 5, 0.76–0.85 at G = 10 and 0.92–0.94 at G = 30.\n - CR1: 0.63–0.82, 0.84–0.94 and 0.95–0.97 at the same G.\n \n The downward bias comes from estimating μ by ȳ, which removes variability that a single dominant cluster carries. It is larger when ICC > 0 than when ICC = 0, because the large clusters then contribute more to Var(ȳ). The analytic values (`exact_rel_bias_var`) agree.\n6. **Baseline.** Ignoring clustering (`baseline_coverage_iid`) is fine at ICC = 0 (0.94–0.96) but disastrous at ICC > 0 (0.30–0.48), at every G. All three cluster-robust procedures are a large improvement, but none reaches nominal coverage reliably with 5 clusters.\n\n## Uncertainty\n- **Coverage.** With R = 2000, the MC SE of a coverage estimate is about 0.0049 near 0.95 and at most 0.010 (CR0 at G = 5) (`mc_se_coverage`). So ±2 SE ≈ ±0.01–0.02.\n- **Classifications.** Classifying a pair as a failure is robust when its coverage is far from 0.90. The cases nearest the threshold are:\n - cr1_G5_icc0.2 (0.8815, SE 0.0072) and cr1_G5_icc0.5 (0.8795, SE 0.0073): about 2.6–2.8 SE below 0.90.\n - cr0_G10_icc0.0 (0.8835, SE 0.0072): about 2.3 SE below.\n - cr1_G5_icc0.0 (0.919, SE 0.0061): about 3.1 SE above.\n \n Other seeds could plausibly move these by a few hundredths. The \"nominal\" set rests on a 2-SE rule applied to 27 pairs, so a borderline pair could be misclassified by chance (multiple comparisons; no correction was applied, as the task specifies the rule).\n- **Variance bias.** The MC SE of the relative bias is 0.007–0.016 (`mc_se_rel_bias_var`). The Monte Carlo means agree with the analytic expectations (`exact_rel_bias_var`): z-scores range from −2.0 to 1.36 over the 9 independent cells (`z_rel_bias_mc_vs_exact`). This is consistent with pure MC noise and confirms the implementation.\n- **Bootstrap error.** The WCB coverage also includes bootstrap randomness (B = 399), which is part of the procedure as specified. It is absorbed into the binomial MC SE.\n- **Comparisons between procedures.** All procedures in a cell use the same replications, so their differences are positively correlated. The marginal SEs are therefore conservative for those differences. We did not compute paired SEs separately. The G = 5 gap between CR1 and WCB (0.036 on average) is several times the marginal SE of each mean (≈0.004).\n\n## Limitations and open issues\n- **Distribution.** Only Gaussian random intercepts and Gaussian errors. Skewed or heavy-tailed u_g or e_ig, which usually hurt few-cluster inference more, are not covered.\n- **Heterogeneity.** Within-cluster variance and ICC are the same in every cluster. Cluster sizes follow one fixed unbalanced pattern (8/16/32/64) and are not random or informative about the outcome. Balanced designs, or designs even more dominated by one cluster, may behave differently. At G = 5, half of the sample is in one cluster, which drives much of the small-G behaviour.\n- **Regressors.** The estimand is a simple mean, so there are no regressors and no leverage from covariates. Results for regression coefficients, fixed effects, or treatment indicators that vary only at the cluster level can differ substantially.\n- **Other methods and weights.** We did not study:\n - CR2/CR3 (bias-reduced linearisation) or Bell–McCaffrey/Satterthwaite degrees of freedom;\n - the restricted (null-imposed) WCB or the WCB p-value inversion;\n - Webb six-point or Mammen weights;\n - full enumeration of the 32 Rademacher patterns at G = 5;\n - the equal-tailed rather than symmetric bootstrap-t.\n \n The WCB results apply only to the unrestricted, symmetric, Rademacher version with B = 399.\n- **Specification choices.**\n - The \"0.95 empirical quantile\" was implemented as the inverted-CDF (380th of 399) order statistic. Interpolated quantile definitions would change q slightly.\n - CR0 uses the literal 1.96 as specified.\n- **Design coverage.** Only the 9 cells and R = 2000 required by the task were run. No other G values or ICC values were explored.\n- **Feasibility.** The task was completed as specified (`feasibility` = \"complete\").\nstep,rule,n_before,n_after,n_removed,rationale\n1,\"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",9,9,0,all 9 cells consistent; no filtering\ncell_id,G,icc,cluster_sizes,N,R,B,seed,mu,total_variance,nominal_level\r\nC1,5,0.0,8|16|32|64|8,128,2000,399,20261101,0.0,1.0,0.95\r\nC2,5,0.2,8|16|32|64|8,128,2000,399,20261102,0.0,1.0,0.95\r\nC3,5,0.5,8|16|32|64|8,128,2000,399,20261103,0.0,1.0,0.95\r\nC4,10,0.0,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261104,0.0,1.0,0.95\r\nC5,10,0.2,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261105,0.0,1.0,0.95\r\nC6,10,0.5,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261106,0.0,1.0,0.95\r\nC7,30,0.0,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261107,0.0,1.0,0.95\r\nC8,30,0.2,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261108,0.0,1.0,0.95\r\nC9,30,0.5,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261109,0.0,1.0,0.95\r\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a24413ce-89eb-4d74-acb2-197b3ad2e398","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}20{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"38ed95aa2356411cf26134e5551a23753c6ec94f0706a26774e5336bfe712f94","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Erahy1NrTrYPCRMjtBNKvU","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/exclusions.csv; cat data/design.csv; ls out/state"}}]}}21{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"44524447-9f25-4d56-9d8e-792e92f34c3d","timestamp":"2026-10-30T05:43:02.469Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"dcab3bdf-66a0-4009-a242-fc187b1d5be5","keep":4,"tail":["38ed95aa2356411cf26134e5551a23753c6ec94f0706a26774e5336bfe712f94","3f65cdecc025989019d36685f5ff7636c64162e284e162b2c55fc1005bdd667b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"52647a05aa589701311cd6287d76f10798cb4d446d4fbfc64a9cbc45c0918471"}22{"type":"last-prompt","lastPrompt":"Review","leafUuid":"96e795ef-9b85-470a-9c4c-edfa9cd5bf68","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}23{"type":"atis-latch","atis":"","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}24{"parentUuid":"96e795ef-9b85-470a-9c4c-edfa9cd5bf68","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVuuNMBT8GqvPKycqf","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":9865,"cache_read_input_tokens":11549,"output_tokens":1197,"output_tokens_details":{"thinking_tokens":825},"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":9865},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":7501,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtVudVvoVv4DoGMZUPn","requestRef":"44524447-9f25-4d56-9d8e-792e92f34c3d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8921b085-3145-4d01-a123-32a99c97886a","timestamp":"2026-10-30T05:43:19.316Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"8921b085-3145-4d01-a123-32a99c97886a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVuuNMBT8GqvPKycqf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VgCPoD8wspXuhedL9xSywb","name":"Bash","input":{"command":"rm -rf /tmp/rt21 && mkdir -p /tmp/rt21/out && cp -r data /tmp/rt21/ && cp out/analysis.py /tmp/rt21/out/ && cd /tmp/rt21 && time ~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;a=json.load(open('/tmp/rt21/out/results.json'));b=json.load(open('$PWD/out/results.json'.replace('/tmp/rt21','/Users/simon-pierreboucher/wp29/runs/RT0021')))\nprint(a==b)\n\" ; diff /tmp/rt21/out/table1.csv /Users/simon-pierreboucher/wp29/runs/RT0021/out/table1.csv && echo tableok; head -3 /tmp/rt21/out/table1.csv; wc -l /tmp/rt21/out/table1.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":9865,"cache_read_input_tokens":11549,"output_tokens":1197,"output_tokens_details":{"thinking_tokens":825},"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":9865},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtVudVvoVv4DoGMZUPn","requestRef":"44524447-9f25-4d56-9d8e-792e92f34c3d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8a50967b-c07b-4d34-a2ab-b204a8943722","timestamp":"2026-10-30T05:43:22.109Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"8a50967b-c07b-4d34-a2ab-b204a8943722","isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VgCPoD8wspXuhedL9xSywb","type":"tool_result","content":"~/wp29/venv/bin/python out/analysis.py > /dev/null 1,69s user 0,16s system 99% cpu 1,850 total\nTrue\ntableok\nestimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.000000,0.797000,0.008994,0.653105,0.129219,2000\ncr0,C2,5,0.200000,0.719500,0.010045,0.507338,0.336360,2000\n 28 /tmp/rt21/out/table1.csv\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0021","is_error":false}]},"uuid":"9f49bac2-c02e-4223-a6e8-045cbe69758e","timestamp":"2026-10-30T05:43:24.080Z","toolUseResult":{"stdout":"~/wp29/venv/bin/python out/analysis.py > /dev/null 1,69s user 0,16s system 99% cpu 1,850 total\nTrue\ntableok\nestimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.000000,0.797000,0.008994,0.653105,0.129219,2000\ncr0,C2,5,0.200000,0.719500,0.010045,0.507338,0.336360,2000\n 28 /tmp/rt21/out/table1.csv","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0021","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8a50967b-c07b-4d34-a2ab-b204a8943722","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}27{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"4b8b8080a202d26c0e6e04e86485f48cdc46549930da8d29c32903f53399c620","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01VgCPoD8wspXuhedL9xSywb","name":"Bash","input":{"command":"rm -rf /tmp/rt21 && mkdir -p /tmp/rt21/out && cp -r data /tmp/rt21/ && cp out/analysis.py /tmp/rt21/out/ && cd /tmp/rt21 && time ~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;a=json.load(open('/tmp/rt21/out/results.json'));b=json.load(open('$PWD/out/results.json'.replace('/tmp/rt21','/Users/simon-pierreboucher/wp29/runs/RT0021')))\nprint(a==b)\n\" ; diff /tmp/rt21/out/table1.csv /Users/simon-pierreboucher/wp29/runs/RT0021/out/table1.csv && echo tableok; head -3 /tmp/rt21/out/table1.csv; wc -l /tmp/rt21/out/table1.csv"}}]}}28{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"c22b9a21-ca9d-4c33-9c38-85c1fd7faba0","timestamp":"2026-10-30T05:43:24.083Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"44524447-9f25-4d56-9d8e-792e92f34c3d","keep":6,"tail":["4b8b8080a202d26c0e6e04e86485f48cdc46549930da8d29c32903f53399c620","5c1e09331c8cd78b13ad2aea503022491634212ef7be655eb35b3d7fca2057e0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1fd6307307535ab29e186db247f659f6e92061854c1557a3e02a61031e55baee"}29{"parentUuid":"9f49bac2-c02e-4223-a6e8-045cbe69758e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtXWHcPF16gDkXDZdkC","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":1437,"cache_read_input_tokens":21414,"output_tokens":646,"output_tokens_details":{"thinking_tokens":101},"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":1437},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":873,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtXW2jHrWKJjBjxNABh","requestRef":"c22b9a21-ca9d-4c33-9c38-85c1fd7faba0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1a712423-b37f-4b92-a0ca-66af880fde7d","timestamp":"2026-10-30T05:43:26.271Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"1a712423-b37f-4b92-a0ca-66af880fde7d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtXWHcPF16gDkXDZdkC","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Tt8oJfWWrWv3wVcGE2DGVY","name":"Bash","input":{"command":"cd /tmp && ~/wp29/venv/bin/python -c \"\nimport numpy as np\nfrom scipy import stats\nrng=np.random.default_rng(1)\nsizes=np.array([8,16,32,64,8]);G=5;N=128;icc=0.2;B=399\ngid=np.repeat(np.arange(G),sizes)\ndef v1(y):\n yb=y.mean();e=y-yb;S=np.bincount(gid,e,minlength=G);return yb,G/(G-1)*(S**2).sum()/N**2\nc=np.zeros(3);R=1500\nfor r in range(R):\n y=np.sqrt(icc)*rng.standard_normal(G)[gid]+np.sqrt(1-icc)*rng.standard_normal(N)\n yb,V1=v1(y);V0=V1*(G-1)/G;e=y-yb\n ts=[]\n for b in range(B):\n w=rng.choice([-1,1],G);ys=yb+w[gid]*e;ybs,V1s=v1(ys);ts.append(abs(ybs-yb)/np.sqrt(V1s) if V1s>0 else 0)\n q=np.sort(ts)[379]\n c+= [abs(yb)<=1.96*np.sqrt(V0), abs(yb)<=stats.t.ppf(.975,G-1)*np.sqrt(V1), abs(yb)<=q*np.sqrt(V1)]\nprint(c/R)\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1437,"cache_read_input_tokens":21414,"output_tokens":646,"output_tokens_details":{"thinking_tokens":101},"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":1437},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtXW2jHrWKJjBjxNABh","requestRef":"c22b9a21-ca9d-4c33-9c38-85c1fd7faba0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fe2355da-ea3c-4c81-b9f2-d6b922efae88","timestamp":"2026-10-30T05:43:29.995Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"fe2355da-ea3c-4c81-b9f2-d6b922efae88","isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Tt8oJfWWrWv3wVcGE2DGVY","type":"tool_result","content":"[0.72466667 0.88333333 0.85266667]\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0021","is_error":false}]},"uuid":"c3c6ddde-2cf2-41ee-9820-c45db79c71e0","timestamp":"2026-10-30T05:43:36.501Z","toolUseResult":{"stdout":"[0.72466667 0.88333333 0.85266667]","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0021","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fe2355da-ea3c-4c81-b9f2-d6b922efae88","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}32{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"c30e056a1a0459d091e2ab71e19d8e4cfa33fb43af8bc550e0e47344efa8d78f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Tt8oJfWWrWv3wVcGE2DGVY","name":"Bash","input":{"command":"cd /tmp && ~/wp29/venv/bin/python -c \"\nimport numpy as np\nfrom scipy import stats\nrng=np.random.default_rng(1)\nsizes=np.array([8,16,32,64,8]);G=5;N=128;icc=0.2;B=399\ngid=np.repeat(np.arange(G),sizes)\ndef v1(y):\n yb=y.mean();e=y-yb;S=np.bincount(gid,e,minlength=G);return yb,G/(G-1)*(S**2).sum()/N**2\nc=np.zeros(3);R=1500\nfor r in range(R):\n y=np.sqrt(icc)*rng.standard_normal(G)[gid]+np.sqrt(1-icc)*rng.standard_normal(N)\n yb,V1=v1(y);V0=V1*(G-1)/G;e=y-yb\n ts=[]\n for b in range(B):\n w=rng.choice([-1,1],G);ys=yb+w[gid]*e;ybs,V1s=v1(ys);ts.append(abs(ybs-yb)/np.sqrt(V1s) if V1s>0 else 0)\n q=np.sort(ts)[379]\n c+= [abs(yb)<=1.96*np.sqrt(V0), abs(yb)<=stats.t.ppf(.975,G-1)*np.sqrt(V1), abs(yb)<=q*np.sqrt(V1)]\nprint(c/R)\n\""}}]}}33{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"e7ec33e0-e850-431e-97ee-f8b74f234f65","timestamp":"2026-10-30T05:43:36.504Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"c22b9a21-ca9d-4c33-9c38-85c1fd7faba0","keep":8,"tail":["c30e056a1a0459d091e2ab71e19d8e4cfa33fb43af8bc550e0e47344efa8d78f","2ef6577d190f9b595797508cd9f5e2ef01454c573c25ff4d04162e70f9aab1c8"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"be716a9d53083a718b04ee4bb89997072b50641fac95d4a39955cf1cdc67b5cf"}34{"type":"tools-used","tools":["Bash","Read"],"sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}35{"parentUuid":"c3c6ddde-2cf2-41ee-9820-c45db79c71e0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtYRRSi2mpiCNyEaEWZ","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":706,"cache_read_input_tokens":22851,"output_tokens":114,"output_tokens_details":{"thinking_tokens":33},"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":706},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":216,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtYR8q4cLM4NdVnC52S","requestRef":"e7ec33e0-e850-431e-97ee-f8b74f234f65","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2bb483d0-662a-4620-9053-f150476c054c","timestamp":"2026-10-30T05:43:37.989Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"2bb483d0-662a-4620-9053-f150476c054c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtYRRSi2mpiCNyEaEWZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0193roy5sbKdCH8rCBAbkLnq","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0021/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":706,"cache_read_input_tokens":22851,"output_tokens":114,"output_tokens_details":{"thinking_tokens":33},"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":706},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtYR8q4cLM4NdVnC52S","requestRef":"e7ec33e0-e850-431e-97ee-f8b74f234f65","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"05dcd1cc-2273-4db2-b0a2-4546fd5bd45e","timestamp":"2026-10-30T05:43:38.263Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"05dcd1cc-2273-4db2-b0a2-4546fd5bd45e","isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0193roy5sbKdCH8rCBAbkLnq","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"ae3c50b9-328c-499a-8769-e14a608541db","timestamp":"2026-10-30T05:43:38.272Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":74523,"dimensions":{"originalWidth":1690,"originalHeight":546,"displayWidth":1690,"displayHeight":546}}},"sourceToolAssistantUUID":"05dcd1cc-2273-4db2-b0a2-4546fd5bd45e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"64a9c83d41ba84418626cc5b2c23d33655f83fa16e1f37bb3762ae194cefba7b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_0193roy5sbKdCH8rCBAbkLnq","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/figure1.png"}}]}}39{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"d149b436-b1d4-4d56-b478-cf6e23d43536","timestamp":"2026-10-30T05:43:38.277Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"e7ec33e0-e850-431e-97ee-f8b74f234f65","keep":10,"tail":["64a9c83d41ba84418626cc5b2c23d33655f83fa16e1f37bb3762ae194cefba7b","1f9b0e81cedeb2e956bc205d403e1f9e7a356e08f12e453f980e3b009483a5b0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"af5d9d7b6eb63313ca66fc73565bb35aae2908b34ae213844c9f5c79c757274f"}40{"type":"last-prompt","lastPrompt":"Review","leafUuid":"ae3c50b9-328c-499a-8769-e14a608541db","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}41{"type":"atis-latch","atis":"","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}42{"parentUuid":"ae3c50b9-328c-499a-8769-e14a608541db","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtYZ267zFbbwWTFRE6x","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":1353,"cache_read_input_tokens":23557,"output_tokens":1417,"output_tokens_details":{"thinking_tokens":186},"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":1353},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1727,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtYYkDqD6GxbaNbVxXt","requestRef":"d149b436-b1d4-4d56-b478-cf6e23d43536","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"24d3e698-13a0-4250-b10d-74545a3af2b6","timestamp":"2026-10-30T05:43:41.737Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}43{"parentUuid":"24d3e698-13a0-4250-b10d-74545a3af2b6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtYZ267zFbbwWTFRE6x","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01K7mjFqBtnGWk27Eg3ExvpX","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\"id\": \"R1\", \"severity\": \"minor\", \"location\": \"claims.json C4; report.md Results item 3\", \"issue\": \"C4 says WCB is closer to nominal than CR1 at every G=30 cell. At G30/ICC0 the two are 0.946 and 0.944, a gap of 0.002, which is about 0.4 MC SE. The caveat says the G=30 differences are '1-3 MC SE', which is wrong for this cell. In that cell the ordering cannot be told apart from noise.\", \"suggested_fix\": \"Narrow C4 to G=10 with ICC>0 and G30/ICC0.2 and 0.5, or say WCB and CR1 cannot be distinguished at G30/ICC0. Compute paired SEs of the coverage differences, which are cheap because both use the same replications.\"},\n {\"id\": \"R2\", \"severity\": \"minor\", \"location\": \"report.md Results item 4\", \"issue\": \"The report explains WCB's lower coverage at G=5 despite wider mean intervals by a variable, discrete bootstrap critical value. This is stated as fact, but the distribution of q was never examined. C6 does carry an 'interpretive' caveat; the report text does not.\", \"suggested_fix\": \"Report the distribution of q across replications (e.g. quantiles) at G=5, or mark the explanation as a hypothesis in the report.\"},\n {\"id\": \"R3\", \"severity\": \"minor\", \"location\": \"report.md Data and exclusions\", \"issue\": \"'The SHA-256 hashes match the bundle manifest' cannot be checked from the deliverables. No hash or manifest is reproduced.\", \"suggested_fix\": \"Give the hash values or remove the statement.\"},\n {\"id\": \"R4\", \"severity\": \"minor\", \"location\": \"figure1.png\", \"issue\": \"The naive i.i.d. baseline and the 0.90 failure line are both drawn in red. At ICC=0 the baseline curve sits near the reference lines, which makes the panel harder to read.\", \"suggested_fix\": \"Use a different colour for the baseline.\"}\n ],\n \"summary\": \"The deliverables are complete, reproducible and correctly implemented. A re-run of analysis.py in a scratch copy reproduced results.json and table1.csv exactly (about 2 s). The DGP, CR0 (literal 1.96), CR1 (t with G−1 df), WCB (unrestricted Rademacher bootstrap-t, B=399, 380th order statistic) and the seeds all follow TASK.md. The vectorised WCB uses the identity that the cluster sums of the bootstrap residuals equal w_g·S_g − n_g·D, which is correct. A separate brute-force loop implementation (different RNG) of cell G5/ICC0.2 gave coverages of 0.725/0.883/0.853 against 0.720/0.882/0.847, consistent within MC error. Every required key is present. The failure set, nominal set, best procedure and counts are consistent with the coverage and MC SE values. The Monte Carlo relative bias agrees with analytic expectations (|z| ≤ 2). A naive i.i.d. baseline is included and the limitations are stated honestly. The only issues are minor: one over-stated comparison at G30/ICC0, an untested causal explanation, a hash claim that cannot be verified, and the figure colours.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1353,"cache_read_input_tokens":23557,"output_tokens":1417,"output_tokens_details":{"thinking_tokens":186},"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":1353},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtYYkDqD6GxbaNbVxXt","requestRef":"d149b436-b1d4-4d56-b478-cf6e23d43536","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"be496df9-ed51-456d-a54c-f4d770e09224","timestamp":"2026-10-30T05:43:52.091Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}44{"parentUuid":"be496df9-ed51-456d-a54c-f4d770e09224","isSidechain":false,"promptId":"1adbe700-6c7f-4072-9c16-3cb319892c9d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01K7mjFqBtnGWk27Eg3ExvpX","type":"tool_result","content":"ok","is_error":false}]},"uuid":"d26a4df6-ff4e-4130-9f23-bfd8eaa5a74f","timestamp":"2026-10-30T05:43:52.176Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"be496df9-ed51-456d-a54c-f4d770e09224","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}45{"type":"api-request-blob","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","hash":"3d7f823bfad82771b51a63cff1bb2487098d6e6810eff9c27e006b26c3c28781","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01K7mjFqBtnGWk27Eg3ExvpX","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\"id\": \"R1\", \"severity\": \"minor\", \"location\": \"claims.json C4; report.md Results item 3\", \"issue\": \"C4 says WCB is closer to nominal than CR1 at every G=30 cell. At G30/ICC0 the two are 0.946 and 0.944, a gap of 0.002, which is about 0.4 MC SE. The caveat says the G=30 differences are '1-3 MC SE', which is wrong for this cell. In that cell the ordering cannot be told apart from noise.\", \"suggested_fix\": \"Narrow C4 to G=10 with ICC>0 and G30/ICC0.2 and 0.5, or say WCB and CR1 cannot be distinguished at G30/ICC0. Compute paired SEs of the coverage differences, which are cheap because both use the same replications.\"},\n {\"id\": \"R2\", \"severity\": \"minor\", \"location\": \"report.md Results item 4\", \"issue\": \"The report explains WCB's lower coverage at G=5 despite wider mean intervals by a variable, discrete bootstrap critical value. This is stated as fact, but the distribution of q was never examined. C6 does carry an 'interpretive' caveat; the report text does not.\", \"suggested_fix\": \"Report the distribution of q across replications (e.g. quantiles) at G=5, or mark the explanation as a hypothesis in the report.\"},\n {\"id\": \"R3\", \"severity\": \"minor\", \"location\": \"report.md Data and exclusions\", \"issue\": \"'The SHA-256 hashes match the bundle manifest' cannot be checked from the deliverables. No hash or manifest is reproduced.\", \"suggested_fix\": \"Give the hash values or remove the statement.\"},\n {\"id\": \"R4\", \"severity\": \"minor\", \"location\": \"figure1.png\", \"issue\": \"The naive i.i.d. baseline and the 0.90 failure line are both drawn in red. At ICC=0 the baseline curve sits near the reference lines, which makes the panel harder to read.\", \"suggested_fix\": \"Use a different colour for the baseline.\"}\n ],\n \"summary\": \"The deliverables are complete, reproducible and correctly implemented. A re-run of analysis.py in a scratch copy reproduced results.json and table1.csv exactly (about 2 s). The DGP, CR0 (literal 1.96), CR1 (t with G−1 df), WCB (unrestricted Rademacher bootstrap-t, B=399, 380th order statistic) and the seeds all follow TASK.md. The vectorised WCB uses the identity that the cluster sums of the bootstrap residuals equal w_g·S_g − n_g·D, which is correct. A separate brute-force loop implementation (different RNG) of cell G5/ICC0.2 gave coverages of 0.725/0.883/0.853 against 0.720/0.882/0.847, consistent within MC error. Every required key is present. The failure set, nominal set, best procedure and counts are consistent with the coverage and MC SE values. The Monte Carlo relative bias agrees with analytic expectations (|z| ≤ 2). A naive i.i.d. baseline is included and the limitations are stated honestly. The only issues are minor: one over-stated comparison at G30/ICC0, an untested causal explanation, a hash claim that cannot be verified, and the figure colours.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok"}}]}}46{"type":"api-request","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","id":"f3b2efab-9c07-4bf8-ab70-8ee89989d607","timestamp":"2026-10-30T05:43:52.180Z","version":"2.1.314","querySource":"sdk","shapeHash":"67c0ba72388570fc8745bf49f8a33cb8093eb584d7bf427a8d44694cc05e57e9","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":"d149b436-b1d4-4d56-b478-cf6e23d43536","keep":12,"tail":["3d7f823bfad82771b51a63cff1bb2487098d6e6810eff9c27e006b26c3c28781","b48623fb8c87808c290514778f4ec8dc1c2224d0dd2300913b416606a4ce2077"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2d48a9dc2cc89ff50bf2efa67f04288a6ba580526548f1acc4803072cc290e07"}47{"parentUuid":"d26a4df6-ff4e-4130-9f23-bfd8eaa5a74f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtZaTCgTH7ANxPiXMHL","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS8QUKEAgTGAI4AUIIdGhpbmtpbmcSDF9Q93b7EvCOidC9shoMr9SoUHarn9bYE75bIjB2KVyJkD7rZpo6s3Tg6T5n4hZQyXUTlDT3D3Ns1UjyQXzZPq2zROMW0zNFhkWzWIAqjgW9/G0zX/DWlvKiK8djr5ytODkWswE2dbC4qtyESemjc8nXpbjss1POui+oGFIqFVPfu6j2/yjb2Xek1rhpnwCA2pQXZPjHks5ZVJMwgABK33J8zUcRDVyU6dydwN4wU1vwaCUnSgdRJf8+gvh1NB7J7E2gBncWbacPsfvPF1/CqKRK9Nuf3RV0Ji7c6P8DlGYMKuZRWcvTcCozq3lukzuhJjRAOji3l0Wax1SOVuuobaQ0gb9X1hGfZCyGaqpTfU98IgVbGXqZjrTvVcb962gTBtnXo9t+nmk7ltnupZGZlpapAxrol2dQhJRkSHXObrTIRPidLTczakF3/pLIYoJoXt8i+FfKtMu91TMDN+z2ehcIeGERzona7wbG80dveyUG6koZMCNNmCnl0ngFSiX31OIeR4e7+pyrHIaeFTW7KuLdtZxc+ThmXDNnI1K017U5QlkqgFKg6VZPdw4l3w9zUacWjl/4oi9a3LeGIgzSle5M4mKuwTVPtPAAjNfhz+f2XCQRLAdpgO2FxY2x81BJZtZIbHEANY8CIbuGXHeeRTa5LRbLPBAhY66fByBCsGOiP/pqbak1y1OTZRLFyUXHstGmlU+rNRMMsP2Uki/0f4ZRHfoilSZh/pf7GoisQoeZSeh0vIc1LBn+VlngAN+SvLVaA75FsPq8DS2xq2mEh1TVNx7wt+lSIP8gONDOVFW6LOlWc/PZh7Io64/wMbOhj7EvnoWclEfrLu10JFx/x7ZYEmIVcBSh3QpShxu8uDSXbGUiD1wBexc9UawOXj356HXNpJZw9NYSeTPlFlndkr2OYE2i7anHCqn1Ui1g0LODosaNDZsj30t3HeVR5MUNNQadvvX1g6SYlWTwBvUYAQ=="}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1424,"cache_read_input_tokens":24910,"output_tokens":899,"output_tokens_details":{"thinking_tokens":5},"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":1424},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6633,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtZaB5HjftiaowyNR3C","requestRef":"f3b2efab-9c07-4bf8-ab70-8ee89989d607","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bde0f460-8614-44a4-a8ff-1f002fa17df1","timestamp":"2026-10-30T05:44:00.099Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"bde0f460-8614-44a4-a8ff-1f002fa17df1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtZaTCgTH7ANxPiXMHL","type":"message","role":"assistant","content":[{"type":"text","text":"My verdict is **accept**: the work is correct and reproducible, with four minor issues. The review is saved to `out/review/review.json`.\n\n**How I checked it:**\n- **Reproducibility:** I ran `out/analysis.py` in a scratch copy. It finished in about 2 seconds and produced `results.json` and `table1.csv` identical to the submitted ones.\n- **Code against `TASK.md`:** the code follows the task as specified:\n - the data-generating process and exact variance formula match the task;\n - CR0 uses the literal 1.96, and CR1 uses a t critical value with G−1 degrees of freedom;\n - the bootstrap is the unrestricted Rademacher version with B=399, and its critical value is the 380th of the 399 sorted values;\n - each cell uses its seed from `design.csv`, and the only input read is `data/design.csv`.\n- **Bootstrap shortcut:** the fast version of the bootstrap rests on an algebraic shortcut, and the shortcut is correct.\n- **Independent check:** I wrote a slow loop version with a different random generator and ran it on the G=5, ICC=0.2 cell. It gave coverages of 0.725 / 0.883 / 0.853 for CR0 / CR1 / bootstrap. The submission has 0.720 / 0.882 / 0.847, so they agree within simulation error.\n- **Results file:** every required key is there. The failure list, the near-nominal list, the best procedure at G=5 and all counts follow from the coverage values and their standard errors. The simulated variance bias matches exact calculated values (z-scores all within ±2), and a baseline that ignores clustering is included.\n- **Report:** the limitations section is honest and covers what the task asks for.\n\n**Minor issues:**\n- **R1:** Claim C4 says the bootstrap is closer to 95% than CR1 at every G=30 cell. At G=30 with ICC=0 the two coverages are 0.946 and 0.944, a gap of about 0.4 standard errors, so that ordering is just noise. The caveat's \"1–3 standard errors\" is wrong for this cell.\n- **R2:** At G=5 the bootstrap intervals are wider on average but cover less. The report states the cause (a variable, coarse bootstrap critical value) as fact, but never tested it. The claims file marks it as interpretive; the report text does not.\n- **R3:** The report says the input file hashes match a manifest, but neither the hashes nor the manifest are included, so this can't be checked.\n- **R4:** In `figure1.png` the clustering-blind baseline and the 0.90 failure line are both red, which makes the ICC=0 panel harder to read."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1424,"cache_read_input_tokens":24910,"output_tokens":899,"output_tokens_details":{"thinking_tokens":5},"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":1424},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtZaB5HjftiaowyNR3C","requestRef":"f3b2efab-9c07-4bf8-ab70-8ee89989d607","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ae9db584-bd0e-48f8-bb75-3fd2d0a81361","timestamp":"2026-10-30T05:44:01.509Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","version":"2.1.314","gitBranch":"HEAD"}49{"type":"last-prompt","lastPrompt":"Review","leafUuid":"ae9db584-bd0e-48f8-bb75-3fd2d0a81361","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc"}50{"type":"cost-state","sessionId":"25dbca72-b30b-4afc-ba23-dbaed21022fc","totalCostUSD":0.23459500000000003,"totalAPIDuration":53871,"totalAPIDurationWithoutRetries":53866,"totalToolDuration":8664,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":62734,"startTime":1793338978782,"modelUsage":{"claude-opus-5-5":{"inputTokens":16,"outputTokens":4439,"thinkingTokens":1150,"cacheReadInputTokens":108005,"cacheCreationInputTokens":24830,"cacheCreationEphemeral5mInputTokens":24830,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.23459500000000003}},"hasUnknownModelCost":false}51