spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:39:12.961Z","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:39:12.965Z","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}4{"parentUuid":null,"isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":"Begin"},"uuid":"d347e964-87eb-4c81-a3a4-dde893fcd3a7","timestamp":"2026-10-30T05:39:12.968Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","timestamp":"2026-10-30T05:39:12.977Z","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/RT0024\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/<timestamp>.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"9ca80da0-397b-4ea9-bb34-9ca85f3cba6d","timestamp":"2026-10-30T05:39:12.977Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0b7f7d5817d07a80f5501da1f79281bad07aaf6a4f55003ad884a5426958e66f"}8{"parentUuid":"d347e964-87eb-4c81-a3a4-dde893fcd3a7","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"c51717f8-45cf-4d63-85b6-e3ef943a66ed","timestamp":"2026-10-30T05:39:12.971Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"c51717f8-45cf-4d63-85b6-e3ef943a66ed","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"f713cd48-5e32-4bd7-a59a-3e9e2006e3c2","timestamp":"2026-10-30T05:39:12.972Z","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/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"f713cd48-5e32-4bd7-a59a-3e9e2006e3c2","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":"3a7911d9-e1c9-4939-b2b8-27dbc08d84fb","timestamp":"2026-10-30T05:39:12.972Z","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/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}12{"parentUuid":"3a7911d9-e1c9-4939-b2b8-27dbc08d84fb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtD1itNddTCeu6FjKqY","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":117,"output_tokens_details":{"thinking_tokens":15},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":360,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtD1S2aWmP7zTvQvGWH","requestRef":"9ca80da0-397b-4ea9-bb34-9ca85f3cba6d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c92bffb2-16ee-444a-9041-19716b2c01b4","timestamp":"2026-10-30T05:39:14.567Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"c92bffb2-16ee-444a-9041-19716b2c01b4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtD1itNddTCeu6FjKqY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01EPpCRGWzAafkxr7qoJ245b","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":117,"output_tokens_details":{"thinking_tokens":15},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtD1S2aWmP7zTvQvGWH","requestRef":"9ca80da0-397b-4ea9-bb34-9ca85f3cba6d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d8a6ff33-c66f-4381-8386-9b476dcdeb7d","timestamp":"2026-10-30T05:39:15.170Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"d8a6ff33-c66f-4381-8386-9b476dcdeb7d","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n# 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 32\ndrwxr-xr-x    6 simon-pierreboucher  staff   192 oct.  30 00:18 .\ndrwxr-xr-x  192 simon-pierreboucher  staff  6144 oct.  30 01:39 ..\n-rw-r--r--    1 simon-pierreboucher  staff   517 oct.  30 00:32 bundle.json\ndrwxr-xr-x    4 simon-pierreboucher  staff   128 oct.  30 00:12 data\n-rw-r--r--    1 simon-pierreboucher  staff  1545 oct.  30 00:12 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6628 oct.  30 00:12 TASK.md\ndata:\ntotal 16\ndrwxr-xr-x  4 simon-pierreboucher  staff   128 oct.  30 00:12 .\ndrwxr-xr-x  6 simon-pierreboucher  staff   192 oct.  30 00:18 ..\n-rw-r--r--  1 simon-pierreboucher  staff   849 oct.  30 00:12 design.csv\n-rw-r--r--  1 simon-pierreboucher  staff  1163 oct.  30 00:12 README.md","is_error":true,"tool_use_id":"toolu_01EPpCRGWzAafkxr7qoJ245b"}]},"uuid":"2aa03e5f-5bb6-47f2-b322-d039094d490e","timestamp":"2026-10-30T05:39:15.252Z","toolUseResult":"Error: Exit code 1\n# 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 32\ndrwxr-xr-x    6 simon-pierreboucher  staff   192 oct.  30 00:18 .\ndrwxr-xr-x  192 simon-pierreboucher  staff  6144 oct.  30 01:39 ..\n-rw-r--r--    1 simon-pierreboucher  staff   517 oct.  30 00:32 bundle.json\ndrwxr-xr-x    4 simon-pierreboucher  staff   128 oct.  30 00:12 data\n-rw-r--r--    1 simon-pierreboucher  staff  1545 oct.  30 00:12 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6628 oct.  30 00:12 TASK.md\ndata:\ntotal 16\ndrwxr-xr-x  4 simon-pierreboucher  staff   128 oct.  30 00:12 .\ndrwxr-xr-x  6 simon-pierreboucher  staff   192 oct.  30 00:18 ..\n-rw-r--r--  1 simon-pierreboucher  staff   849 oct.  30 00:12 design.csv\n-rw-r--r--  1 simon-pierreboucher  staff  1163 oct.  30 00:12 README.md","sandboxed":false,"sourceToolAssistantUUID":"d8a6ff33-c66f-4381-8386-9b476dcdeb7d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"9d846932bf9752a7a368de779b945460a73879534dc6fcfc129f5c3eac584ec9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01EPpCRGWzAafkxr7qoJ245b","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data out 2>/dev/null","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"8ec281d0-a19e-4e07-8c9e-d1c9f3d9324b","timestamp":"2026-10-30T05:39:15.256Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"9ca80da0-397b-4ea9-bb34-9ca85f3cba6d","keep":2,"tail":["9d846932bf9752a7a368de779b945460a73879534dc6fcfc129f5c3eac584ec9","f65d0f58b2830a6d6e6fda2bb52f020209184e0c822f977e09d262cee13931fd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d824782f6d7474ef8bea569e143c821ebb608644e8deac3416fcd738ae1f7730"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2aa03e5f-5bb6-47f2-b322-d039094d490e","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}18{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}19{"parentUuid":"2aa03e5f-5bb6-47f2-b322-d039094d490e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDAahC9bhweqbjykg8","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DSVBSV5q9ax4fKZrk8xvvH","name":"Bash","input":{"command":"cat data/design.csv data/README.md gate_spec.json bundle.json; shasum -a 256 data/*","description":"Show design, readme, gate spec"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3312,"cache_read_input_tokens":4107,"output_tokens":114,"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":3312},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtDAEMzJyufjQFwr85n","requestRef":"8ec281d0-a19e-4e07-8c9e-d1c9f3d9324b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5bf3a741-5f0e-4da1-8a71-7158953b4bfa","timestamp":"2026-10-30T05:39:17.043Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"5bf3a741-5f0e-4da1-8a71-7158953b4bfa","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DSVBSV5q9ax4fKZrk8xvvH","type":"tool_result","content":"cell_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\n# Data — T2-simulation\n\nThis project uses **no observed data**. The only input is `design.csv`, written by the task designer: the nine cells of the Monte Carlo design (one row per cell).\n\n| column | meaning |\n|---|---|\n| `cell_id` | C1 … C9 |\n| `G` | number of clusters (5, 10, 30) |\n| `icc` | intra-cluster correlation of the data-generating process (0.0, 0.2, 0.5) |\n| `cluster_sizes` | the G cluster sizes n_1, …, n_G, separated by `|` (the pattern 8, 16, 32, 64 repeated) |\n| `N` | total number of observations in a sample |\n| `R` | number of Monte Carlo replications per cell (2000) |\n| `B` | number of wild-bootstrap draws per replication (399) |\n| `seed` | the seed to use for the cell (numpy `default_rng(seed)` or equivalent) |\n| `mu` | population mean of y (0.0) |\n| `total_variance` | Var(y_ig) = Var(u_g) + Var(e_ig) = 1.0 |\n| `nominal_level` | nominal confidence level (0.95) |\n\nData-generating process for a cell: y_ig = mu + u_g + e_ig, g = 1..G, i = 1..n_g, with u_g ~ N(0, icc) independent across clusters and e_ig ~ N(0, 1 − icc) independent across observations and of u. All simulated data are synthetic; nothing here is observed data.\n{\n  \"task_id\": \"T2-simulation\",\n  \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/table1.csv\", \"out/figure1.png\"],\n  \"results_keys\": {\n    \"task_id\": {\"type\": \"string\", \"nullable\": false},\n    \"R\": {\"type\": \"integer\", \"nullable\": false},\n    \"B\": {\"type\": \"integer\", \"nullable\": false},\n    \"n_cells\": {\"type\": \"integer\", \"nullable\": false},\n    \"coverage\": {\"type\": \"object\", \"nullable\": false},\n    \"mc_se_coverage\": {\"type\": \"object\", \"nullable\": false},\n    \"rel_bias_var\": {\"type\": \"object\", \"nullable\": false},\n    \"failure_cells\": {\"type\": \"array\", \"nullable\": false},\n    \"n_failure_cells\": {\"type\": \"integer\", \"nullable\": false},\n    \"nominal_cells\": {\"type\": \"array\", \"nullable\": false},\n    \"best_procedure_small_G\": {\"type\": \"string\", \"nullable\": false},\n    \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n    \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n    \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n    \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n    \"n_analysed\": {\"type\": \"integer\", \"nullable\": true},\n    \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n  },\n  \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n  \"family_checks\": [\"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n  \"ci_pairs\": [],\n  \"positive_keys\": [],\n  \"chronology_pairs\": [],\n  \"analysis_timeout_s\": 600,\n  \"reproducibility_tolerance_rel\": 1e-6\n}\n{\n  \"task_id\": \"T2-simulation\",\n  \"family\": \"T2\",\n  \"split\": \"transfer\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T04:32:27.189577+00:00\",\n  \"files\": {\n    \"TASK.md\": \"22849122c96cf5f55a070b010b46d61fcd43177c89a6278a0e8dfc609113cb73\",\n    \"data/README.md\": \"73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67\",\n    \"data/design.csv\": \"f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50\",\n    \"gate_spec.json\": \"30f9d1aec40a303349e47e2a432ac95c1403984a0b951eefb117ace32d657e1e\"\n  }\n}f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50  data/design.csv\n73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67  data/README.md","is_error":false}]},"uuid":"822e303b-22cd-432e-bc53-3b46e8847480","timestamp":"2026-10-30T05:39:17.065Z","toolUseResult":{"stdout":"cell_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\n# Data — T2-simulation\n\nThis project uses **no observed data**. The only input is `design.csv`, written by the task designer: the nine cells of the Monte Carlo design (one row per cell).\n\n| column | meaning |\n|---|---|\n| `cell_id` | C1 … C9 |\n| `G` | number of clusters (5, 10, 30) |\n| `icc` | intra-cluster correlation of the data-generating process (0.0, 0.2, 0.5) |\n| `cluster_sizes` | the G cluster sizes n_1, …, n_G, separated by `|` (the pattern 8, 16, 32, 64 repeated) |\n| `N` | total number of observations in a sample |\n| `R` | number of Monte Carlo replications per cell (2000) |\n| `B` | number of wild-bootstrap draws per replication (399) |\n| `seed` | the seed to use for the cell (numpy `default_rng(seed)` or equivalent) |\n| `mu` | population mean of y (0.0) |\n| `total_variance` | Var(y_ig) = Var(u_g) + Var(e_ig) = 1.0 |\n| `nominal_level` | nominal confidence level (0.95) |\n\nData-generating process for a cell: y_ig = mu + u_g + e_ig, g = 1..G, i = 1..n_g, with u_g ~ N(0, icc) independent across clusters and e_ig ~ N(0, 1 − icc) independent across observations and of u. All simulated data are synthetic; nothing here is observed data.\n{\n  \"task_id\": \"T2-simulation\",\n  \"required_files\": [\"out/results.json\", \"out/report.md\", \"out/analysis.py\", \"out/claims.json\", \"out/table1.csv\", \"out/figure1.png\"],\n  \"results_keys\": {\n    \"task_id\": {\"type\": \"string\", \"nullable\": false},\n    \"R\": {\"type\": \"integer\", \"nullable\": false},\n    \"B\": {\"type\": \"integer\", \"nullable\": false},\n    \"n_cells\": {\"type\": \"integer\", \"nullable\": false},\n    \"coverage\": {\"type\": \"object\", \"nullable\": false},\n    \"mc_se_coverage\": {\"type\": \"object\", \"nullable\": false},\n    \"rel_bias_var\": {\"type\": \"object\", \"nullable\": false},\n    \"failure_cells\": {\"type\": \"array\", \"nullable\": false},\n    \"n_failure_cells\": {\"type\": \"integer\", \"nullable\": false},\n    \"nominal_cells\": {\"type\": \"array\", \"nullable\": false},\n    \"best_procedure_small_G\": {\"type\": \"string\", \"nullable\": false},\n    \"feasibility\": {\"type\": \"string\", \"nullable\": false},\n    \"feasibility_reason\": {\"type\": \"string\", \"nullable\": true},\n    \"data_issues\": {\"type\": \"array\", \"nullable\": false},\n    \"n_input_rows\": {\"type\": \"object\", \"nullable\": false},\n    \"n_analysed\": {\"type\": \"integer\", \"nullable\": true},\n    \"random_seed\": {\"type\": \"integer\", \"nullable\": true}\n  },\n  \"report_sections\": [\"Question\", \"Data and exclusions\", \"Method\", \"Results\", \"Uncertainty\", \"Limitations and open issues\"],\n  \"family_checks\": [\"claims_reference_existing_keys\", \"phase_ledger_consistent\", \"exclusion_ledger_sums\"],\n  \"ci_pairs\": [],\n  \"positive_keys\": [],\n  \"chronology_pairs\": [],\n  \"analysis_timeout_s\": 600,\n  \"reproducibility_tolerance_rel\": 1e-6\n}\n{\n  \"task_id\": \"T2-simulation\",\n  \"family\": \"T2\",\n  \"split\": \"transfer\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T04:32:27.189577+00:00\",\n  \"files\": {\n    \"TASK.md\": \"22849122c96cf5f55a070b010b46d61fcd43177c89a6278a0e8dfc609113cb73\",\n    \"data/README.md\": \"73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67\",\n    \"data/design.csv\": \"f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50\",\n    \"gate_spec.json\": \"30f9d1aec40a303349e47e2a432ac95c1403984a0b951eefb117ace32d657e1e\"\n  }\n}f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50  data/design.csv\n73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67  data/README.md","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5bf3a741-5f0e-4da1-8a71-7158953b4bfa","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"3647873bdffc72f21cfdd7c24a19871b2d92a1310646ccfac943d5f57d620f47","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01DSVBSV5q9ax4fKZrk8xvvH","name":"Bash","input":{"command":"cat data/design.csv data/README.md gate_spec.json bundle.json; shasum -a 256 data/*","description":"Show design, readme, gate spec"}}]}}22{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"2dd040e4-ce0c-4d26-bcbc-e9d8b45b37a9","timestamp":"2026-10-30T05:39:17.067Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"8ec281d0-a19e-4e07-8c9e-d1c9f3d9324b","keep":4,"tail":["3647873bdffc72f21cfdd7c24a19871b2d92a1310646ccfac943d5f57d620f47","37e19cfe0ddfbd40a42cb63d779a42611ed810779319b5147174fa02bba98577"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"428bb97df12a11cc40e3f34b1b58d4dddd6ccaf891d1dcf6e6bfeccdae15cdc5"}23{"parentUuid":"822e303b-22cd-432e-bc53-3b46e8847480","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDJDKuGJBZVNzHgTH1","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":2270,"cache_read_input_tokens":7419,"output_tokens":1801,"output_tokens_details":{"thinking_tokens":650},"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":2270},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6299,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtDHzvbv6xHVe6kVgiM","requestRef":"2dd040e4-ce0c-4d26-bcbc-e9d8b45b37a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"42b327e1-4e2a-46e4-a8dd-e3172f04be2b","timestamp":"2026-10-30T05:39:24.792Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"42b327e1-4e2a-46e4-a8dd-e3172f04be2b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDJDKuGJBZVNzHgTH1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016tJ2HxUjZTibceqEAJi9QM","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0)\n**Question.** With few clusters, how reliable are cluster-robust 95% CIs for a population mean? Monte Carlo study over 9 cells (G in {5,10,30} x ICC in {0,0.2,0.5}), unequal cluster sizes (pattern 8,16,32,64 repeated).\n\n**Estimands (per cell x procedure CR0, CR1, WCB):** (a) actual coverage of the nominal 95% CI for mu (=0); (b) for CR0/CR1, E[V_hat]/Var(ybar) with exact Var(ybar) = [ICC*sum n_g^2 + (1-ICC)N]/N^2; (c) MC SE sqrt(p(1-p)/R); (d) failure regimes: coverage < 0.90. Also \"nominal-consistent\": |p-0.95| <= 2 MCSE. Meaningful under the stated Gaussian random-effects DGP only.\n\n**Procedures exactly as specified:** CR0 with z=1.96; CR1 = G/(G-1) CR0 with t_{G-1}; WCB unrestricted Rademacher bootstrap-t with B=399, q = 0.95 empirical quantile of |t*|, interval ybar +- q sqrt(V_CR1).\n\n**Outputs:** out/table1.csv (27 rows: estimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var (empty for wcb),mean_ci_halfwidth,R); out/results.json (task_id,R,B,n_cells,coverage,mc_se_coverage,rel_bias_var,failure_cells,n_failure_cells,nominal_cells,best_procedure_small_G,feasibility,feasibility_reason,data_issues,n_input_rows,n_analysed,random_seed); out/figure1.png; out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues); out/analysis.py; out/claims.json.\n\n**Information rules:** use only data/design.csv; R=2000, B=399, per-cell seeds; do not change grid.\n\n**Invalidity:** changing R/B/grid/seeds, deviating from the procedure definitions, inconsistent design rows (sizes not summing to N, wrong G), non-deterministic script, runtime > 10 min.\nEOF\ncat > log.md <<'EOF'\n# Log\n- 2026-10-30 P0: read TASK.md, wrote contract.md. P0 passed.\nEOF\ncat > ../../out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\nls","description":"Write contract, log, phase ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2270,"cache_read_input_tokens":7419,"output_tokens":1801,"output_tokens_details":{"thinking_tokens":650},"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":2270},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtDHzvbv6xHVe6kVgiM","requestRef":"2dd040e4-ce0c-4d26-bcbc-e9d8b45b37a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"51b3ff4d-38bd-4392-a405-c9f769592859","timestamp":"2026-10-30T05:39:33.286Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"51b3ff4d-38bd-4392-a405-c9f769592859","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016tJ2HxUjZTibceqEAJi9QM","type":"tool_result","content":"contract.md\nlog.md\nphases.json","is_error":false}]},"uuid":"f6c9c475-41a7-46dc-9dab-a4b6ae5fa53a","timestamp":"2026-10-30T05:39:33.339Z","toolUseResult":{"stdout":"contract.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"51b3ff4d-38bd-4392-a405-c9f769592859","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"4ee72a7857c5cbdb3905d1125c24feca2d925f6e9c03501efb42c3362d335355","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016tJ2HxUjZTibceqEAJi9QM","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0)\n**Question.** With few clusters, how reliable are cluster-robust 95% CIs for a population mean? Monte Carlo study over 9 cells (G in {5,10,30} x ICC in {0,0.2,0.5}), unequal cluster sizes (pattern 8,16,32,64 repeated).\n\n**Estimands (per cell x procedure CR0, CR1, WCB):** (a) actual coverage of the nominal 95% CI for mu (=0); (b) for CR0/CR1, E[V_hat]/Var(ybar) with exact Var(ybar) = [ICC*sum n_g^2 + (1-ICC)N]/N^2; (c) MC SE sqrt(p(1-p)/R); (d) failure regimes: coverage < 0.90. Also \"nominal-consistent\": |p-0.95| <= 2 MCSE. Meaningful under the stated Gaussian random-effects DGP only.\n\n**Procedures exactly as specified:** CR0 with z=1.96; CR1 = G/(G-1) CR0 with t_{G-1}; WCB unrestricted Rademacher bootstrap-t with B=399, q = 0.95 empirical quantile of |t*|, interval ybar +- q sqrt(V_CR1).\n\n**Outputs:** out/table1.csv (27 rows: estimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var (empty for wcb),mean_ci_halfwidth,R); out/results.json (task_id,R,B,n_cells,coverage,mc_se_coverage,rel_bias_var,failure_cells,n_failure_cells,nominal_cells,best_procedure_small_G,feasibility,feasibility_reason,data_issues,n_input_rows,n_analysed,random_seed); out/figure1.png; out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues); out/analysis.py; out/claims.json.\n\n**Information rules:** use only data/design.csv; R=2000, B=399, per-cell seeds; do not change grid.\n\n**Invalidity:** changing R/B/grid/seeds, deviating from the procedure definitions, inconsistent design rows (sizes not summing to N, wrong G), non-deterministic script, runtime > 10 min.\nEOF\ncat > log.md <<'EOF'\n# Log\n- 2026-10-30 P0: read TASK.md, wrote contract.md. P0 passed.\nEOF\ncat > ../../out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\nls","description":"Write contract, log, phase ledger"}}]}}27{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"9f23116f-a8a3-41fb-a33a-84611bea8265","timestamp":"2026-10-30T05:39:33.343Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"2dd040e4-ce0c-4d26-bcbc-e9d8b45b37a9","keep":6,"tail":["4ee72a7857c5cbdb3905d1125c24feca2d925f6e9c03501efb42c3362d335355","bb2b7a510905a8130f910c55d3eb65af0eeaac1cab27abd4dfe97ecdfb8eabf2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4d1efbee824e555965deca01d8904d161c77c6de12278661979eab72d6b73eb1"}28{"parentUuid":"f6c9c475-41a7-46dc-9dab-a4b6ae5fa53a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEVqMdKp4HaVG6sDcQ","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":1819,"cache_read_input_tokens":9689,"output_tokens":281,"output_tokens_details":{"thinking_tokens":11},"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":1819},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":318,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtEVZit2qL7sf1yNH6j","requestRef":"9f23116f-a8a3-41fb-a33a-84611bea8265","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ce1894c5-9305-4126-9d9c-2b5bb423ea96","timestamp":"2026-10-30T05:39:34.798Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"ce1894c5-9305-4126-9d9c-2b5bb423ea96","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEVqMdKp4HaVG6sDcQ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NAtiZ6Q7VsVYFiziktDw4L","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape,d.dtypes.to_dict());print(d.isna().sum().sum(),d.duplicated().sum(),d.cell_id.duplicated().sum())\nfor _,r in d.iterrows():\n  n=np.array([int(x) for x in r.cluster_sizes.split('|')]); print(r.cell_id,len(n)==r.G,n.sum()==r.N,(n**2).sum(),r.seed)\n\"","description":"Audit design file consistency"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1819,"cache_read_input_tokens":9689,"output_tokens":281,"output_tokens_details":{"thinking_tokens":11},"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":1819},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtEVZit2qL7sf1yNH6j","requestRef":"9f23116f-a8a3-41fb-a33a-84611bea8265","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7600d9b4-3bac-46e8-8a49-57057ca5e38d","timestamp":"2026-10-30T05:39:36.277Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"7600d9b4-3bac-46e8-8a49-57057ca5e38d","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nTraceback (most recent call last):\n  File \"<string>\", line 3, in <module>\n    d=pd.read_csv('data/design.csv');print(d.shape,d.dtypes.to_dict());print(d.isna().sum().sum(),d.duplicated().sum(),d.cell_id.duplicated().sum())\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n    return _read(filepath_or_buffer, kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n    parser = TextFileReader(filepath_or_buffer, **kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n    self._engine = self._make_engine(f, self.engine)\n                   ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n    self.handles = get_handle(\n                   ~~~~~~~~~~^\n        f,\n        ^^\n    ...<6 lines>...\n        storage_options=self.options.get(\"storage_options\", None),\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n    handle = open(\n        handle,\n    ...<3 lines>...\n        newline=\"\",\n    )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/design.csv'","is_error":true,"tool_use_id":"toolu_01NAtiZ6Q7VsVYFiziktDw4L"}]},"uuid":"3a20c4df-9750-4c7e-bc1d-2e4c02a4c35c","timestamp":"2026-10-30T05:39:36.499Z","toolUseResult":"Error: Exit code 1\nTraceback (most recent call last):\n  File \"<string>\", line 3, in <module>\n    d=pd.read_csv('data/design.csv');print(d.shape,d.dtypes.to_dict());print(d.isna().sum().sum(),d.duplicated().sum(),d.cell_id.duplicated().sum())\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1026, in read_csv\n    return _read(filepath_or_buffer, kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 620, in _read\n    parser = TextFileReader(filepath_or_buffer, **kwds)\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1620, in __init__\n    self._engine = self._make_engine(f, self.engine)\n                   ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/parsers/readers.py\", line 1880, in _make_engine\n    self.handles = get_handle(\n                   ~~~~~~~~~~^\n        f,\n        ^^\n    ...<6 lines>...\n        storage_options=self.options.get(\"storage_options\", None),\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n    )\n    ^\n  File \"/Users/simon-pierreboucher/wp29/venv/lib/python3.14/site-packages/pandas/io/common.py\", line 873, in get_handle\n    handle = open(\n        handle,\n    ...<3 lines>...\n        newline=\"\",\n    )\nFileNotFoundError: [Errno 2] No such file or directory: 'data/design.csv'","sandboxed":false,"sourceToolAssistantUUID":"7600d9b4-3bac-46e8-8a49-57057ca5e38d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"99e05733baeccbb2855f0c476068a7b062c91169be08f58400792cebe459c4bf","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01NAtiZ6Q7VsVYFiziktDw4L","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape,d.dtypes.to_dict());print(d.isna().sum().sum(),d.duplicated().sum(),d.cell_id.duplicated().sum())\nfor _,r in d.iterrows():\n  n=np.array([int(x) for x in r.cluster_sizes.split('|')]); print(r.cell_id,len(n)==r.G,n.sum()==r.N,(n**2).sum(),r.seed)\n\"","description":"Audit design file consistency"}}]}}32{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"c6af75e4-4764-4342-a51f-48dfbfea0046","timestamp":"2026-10-30T05:39:36.502Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"9f23116f-a8a3-41fb-a33a-84611bea8265","keep":8,"tail":["99e05733baeccbb2855f0c476068a7b062c91169be08f58400792cebe459c4bf","97ea1a05f01075e041bc2c365f848bf2f163ee8c71d0c69c0da359ec828f39c1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c2107e52d5e91ea57fc8ddd6f8cbaf9581992a2a663f2f8f6fdeea98e47ef09a"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3a20c4df-9750-4c7e-bc1d-2e4c02a4c35c","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}34{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}35{"parentUuid":"3a20c4df-9750-4c7e-bc1d-2e4c02a4c35c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEjNgvF75PoYceSN6Z","type":"message","role":"assistant","content":[{"type":"text","text":"The previous `cd` persisted; returning to the workspace root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1015,"cache_read_input_tokens":11508,"output_tokens":320,"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":1015},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtEj65Y7NxVJeDddLYj","requestRef":"c6af75e4-4764-4342-a51f-48dfbfea0046","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3fbc86eb-7659-45f2-9485-a3fa4fa69cbc","timestamp":"2026-10-30T05:39:38.822Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"3fbc86eb-7659-45f2-9485-a3fa4fa69cbc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEjNgvF75PoYceSN6Z","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UoYTEk61myN3vZYjiLNVcg","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0024 && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape,d.dtypes.to_dict());print(d.isna().sum().sum(),d.duplicated().sum(),d.cell_id.duplicated().sum())\nfor _,r in d.iterrows():\n  n=np.array([int(x) for x in r.cluster_sizes.split('|')]); print(r.cell_id,len(n)==r.G,n.sum()==r.N,(n**2).sum(),r.seed)\n\"","description":"Audit design file consistency"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1015,"cache_read_input_tokens":11508,"output_tokens":320,"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":1015},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtEj65Y7NxVJeDddLYj","requestRef":"c6af75e4-4764-4342-a51f-48dfbfea0046","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6ce914e9-9e68-4b8f-b5a6-cfd240ec46af","timestamp":"2026-10-30T05:39:40.610Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"6ce914e9-9e68-4b8f-b5a6-cfd240ec46af","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UoYTEk61myN3vZYjiLNVcg","type":"tool_result","content":"(9, 11) {'cell_id': dtype('O'), 'G': dtype('int64'), 'icc': dtype('float64'), 'cluster_sizes': dtype('O'), 'N': dtype('int64'), 'R': dtype('int64'), 'B': dtype('int64'), 'seed': dtype('int64'), 'mu': dtype('float64'), 'total_variance': dtype('float64'), 'nominal_level': dtype('float64')}\n0 0 0\nC1 True True 5504 20261101\nC2 True True 5504 20261102\nC3 True True 5504 20261103\nC4 True True 11200 20261104\nC5 True True 11200 20261105\nC6 True True 11200 20261106\nC7 True True 38400 20261107\nC8 True True 38400 20261108\nC9 True True 38400 20261109","is_error":false}]},"uuid":"a78c15d3-ba81-4d0a-963c-f0bed22a193e","timestamp":"2026-10-30T05:39:40.791Z","toolUseResult":{"stdout":"(9, 11) {'cell_id': dtype('O'), 'G': dtype('int64'), 'icc': dtype('float64'), 'cluster_sizes': dtype('O'), 'N': dtype('int64'), 'R': dtype('int64'), 'B': dtype('int64'), 'seed': dtype('int64'), 'mu': dtype('float64'), 'total_variance': dtype('float64'), 'nominal_level': dtype('float64')}\n0 0 0\nC1 True True 5504 20261101\nC2 True True 5504 20261102\nC3 True True 5504 20261103\nC4 True True 11200 20261104\nC5 True True 11200 20261105\nC6 True True 11200 20261106\nC7 True True 38400 20261107\nC8 True True 38400 20261108\nC9 True True 38400 20261109","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6ce914e9-9e68-4b8f-b5a6-cfd240ec46af","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"151db77c5a1049dea74d1dd7a9b22a1d3e7a2f5fe8114f21c3a1bc41ff182c41","message":{"role":"assistant","content":[{"type":"text","text":"The previous `cd` persisted; returning to the workspace root."},{"type":"tool_use","id":"toolu_01UoYTEk61myN3vZYjiLNVcg","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0024 && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape,d.dtypes.to_dict());print(d.isna().sum().sum(),d.duplicated().sum(),d.cell_id.duplicated().sum())\nfor _,r in d.iterrows():\n  n=np.array([int(x) for x in r.cluster_sizes.split('|')]); print(r.cell_id,len(n)==r.G,n.sum()==r.N,(n**2).sum(),r.seed)\n\"","description":"Audit design file consistency"}}]}}39{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"7c17a1e7-dcbd-4c1b-a89c-cc557da1394f","timestamp":"2026-10-30T05:39:40.793Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"c6af75e4-4764-4342-a51f-48dfbfea0046","keep":10,"tail":["151db77c5a1049dea74d1dd7a9b22a1d3e7a2f5fe8114f21c3a1bc41ff182c41","f1c37994376be7d261a7d8191bc4787be830c39dcb161ab5b89d79773f0f61a5"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3bc6006970eac490dc02489d248418af6946dff685cb6504fc8d754b49bef77c"}40{"parentUuid":"a78c15d3-ba81-4d0a-963c-f0bed22a193e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtF3jFLYAH3nFGoMS65","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":603,"cache_read_input_tokens":12523,"output_tokens":1271,"output_tokens_details":{"thinking_tokens":247},"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":603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2169,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtF3S8RrokDk1PExA3Y","requestRef":"7c17a1e7-dcbd-4c1b-a89c-cc557da1394f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"16273a21-82e4-4adc-a3c3-729e5dad2355","timestamp":"2026-10-30T05:39:44.378Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"16273a21-82e4-4adc-a3c3-729e5dad2355","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtF3jFLYAH3nFGoMS65","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013JNAGb7mxiLLaaaGyjxJ3W","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | sha256 | rows x cols |\n|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 x 11 |\n| data/README.md | 73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 | (text) |\n\nHashes match bundle.json.\n\nSchema: cell_id (str C1..C9), G (int 5/10/30), icc (float 0.0/0.2/0.5), cluster_sizes (str, '|'-separated ints), N (int), R (int, 2000 all rows), B (int, 399 all rows), seed (int 20261101..20261109), mu (0.0), total_variance (1.0), nominal_level (0.95). Units: dimensionless (y has unit variance).\n\nChecks: no missing values; no duplicate rows or cell_ids; for every row len(cluster_sizes)==G and sum(cluster_sizes)==N (128, 264, 864). Sum n_g^2 = 5504 / 11200 / 38400. Grid is the full 3x3 factorial. No dates (simulation design), so no temporal availability issues; no input violates the information rules.\n\nAnomalies / design notes (not errors):\n- ICC=0.0 cells: u_g ~ N(0,0) is degenerate (u_g = 0); implemented as 0*standard normal draw so the RNG stream structure is identical across ICC.\n- G=5: Rademacher weights have only 2^5 = 32 distinct vectors, and |t*| is invariant to w -> -w, so at most 16 distinct |t*| values; the WCB critical value is coarse. Kept as specified (no change to procedure), reported in data_issues.\n- The cluster-size patterns are unbalanced (G=5 repeats size 8; G=10 and 30 are truncated repetitions), as documented in README.\n\nExclusions: none (all 9 cells simulated). See out/exclusions.csv.\nEOF\ncat > out/exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep all design cells (none fail consistency checks),9,9,0,all rows have len(cluster_sizes)=G and sum=N; no exclusion needed\nEOF\necho \"- 2026-10-30 P1: audited design.csv (9 rows, consistent); no exclusions. Decision: WCB quantile = ceil((B+1)*0.95)=380th order statistic of |t*| (standard for B=399). P1 passed.\" >> out/state/log.md","description":"Write data audit and exclusion ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":603,"cache_read_input_tokens":12523,"output_tokens":1271,"output_tokens_details":{"thinking_tokens":247},"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":603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtF3S8RrokDk1PExA3Y","requestRef":"7c17a1e7-dcbd-4c1b-a89c-cc557da1394f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1868f9ad-b215-4d74-8ab7-e7e069903a02","timestamp":"2026-10-30T05:39:54.011Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"1868f9ad-b215-4d74-8ab7-e7e069903a02","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013JNAGb7mxiLLaaaGyjxJ3W","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"20588b84-b7f8-4d5c-8603-ed61ae6e0d67","timestamp":"2026-10-30T05:39:54.050Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1868f9ad-b215-4d74-8ab7-e7e069903a02","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}43{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"fd0422407e17f130634b19e722965aa5e20400bdbeee440126939a1b24301e4e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_013JNAGb7mxiLLaaaGyjxJ3W","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | sha256 | rows x cols |\n|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 x 11 |\n| data/README.md | 73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 | (text) |\n\nHashes match bundle.json.\n\nSchema: cell_id (str C1..C9), G (int 5/10/30), icc (float 0.0/0.2/0.5), cluster_sizes (str, '|'-separated ints), N (int), R (int, 2000 all rows), B (int, 399 all rows), seed (int 20261101..20261109), mu (0.0), total_variance (1.0), nominal_level (0.95). Units: dimensionless (y has unit variance).\n\nChecks: no missing values; no duplicate rows or cell_ids; for every row len(cluster_sizes)==G and sum(cluster_sizes)==N (128, 264, 864). Sum n_g^2 = 5504 / 11200 / 38400. Grid is the full 3x3 factorial. No dates (simulation design), so no temporal availability issues; no input violates the information rules.\n\nAnomalies / design notes (not errors):\n- ICC=0.0 cells: u_g ~ N(0,0) is degenerate (u_g = 0); implemented as 0*standard normal draw so the RNG stream structure is identical across ICC.\n- G=5: Rademacher weights have only 2^5 = 32 distinct vectors, and |t*| is invariant to w -> -w, so at most 16 distinct |t*| values; the WCB critical value is coarse. Kept as specified (no change to procedure), reported in data_issues.\n- The cluster-size patterns are unbalanced (G=5 repeats size 8; G=10 and 30 are truncated repetitions), as documented in README.\n\nExclusions: none (all 9 cells simulated). See out/exclusions.csv.\nEOF\ncat > out/exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep all design cells (none fail consistency checks),9,9,0,all rows have len(cluster_sizes)=G and sum=N; no exclusion needed\nEOF\necho \"- 2026-10-30 P1: audited design.csv (9 rows, consistent); no exclusions. Decision: WCB quantile = ceil((B+1)*0.95)=380th order statistic of |t*| (standard for B=399). P1 passed.\" >> out/state/log.md","description":"Write data audit and exclusion ledger"}}]}}44{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"c8210cde-9079-4b06-90ce-fd1c5f35e7f8","timestamp":"2026-10-30T05:39:54.052Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"7c17a1e7-dcbd-4c1b-a89c-cc557da1394f","keep":12,"tail":["fd0422407e17f130634b19e722965aa5e20400bdbeee440126939a1b24301e4e","53710b6d1f90fa75244f876e6ba1557e2b06330f06d3211014b286d93806a252"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"dfd8404d51215b83d9e0c6c1f3e4244c8e4b18e62b729020818733dcc72382dc"}45{"parentUuid":"20588b84-b7f8-4d5c-8603-ed61ae6e0d67","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtG2V7SxiG42XgJ8Gra","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSrggKEAgTGAI4AUIIdGhpbmtpbmcSDIg4N7UQkCdGGGWemhoM0CEqE7pyD1Um52f2IjBSh/hKusxo4Cn/+o43vpSwJcdqRhTAp7FGwo/nvpFhqOCNkNfvsOo3xAWLuTve1tQqywcTlK9j3K8kahDWWlDRSbUiOdrRHxmuMbJM6nSv0MeZQ8TAuN6X7IVPTZOIxPqJ7Q1fkVkgwPtMx2lqEBclOQ/0XqjMWT2bwbol81gsxjjrsRqq2sgXzYaNOTOPuAxf7L+Cq2usnoxaGawN9DbRRV04D408zQgXy4NMmPYEODahJQVr3PD9TTUGim4UhuaRCULIc5/BuokY4JMUkRQJjby19b7TvwlIj5HDeos4KsxqdBF3bDMd7nnm0hUWNAg4vAJvFp3EUiisjUkQqjl6RknwXcxaWKxJ5I03g944jx+ktM6NhXEu5WWGyIHTqNb/2vQNFs7v0o/+mfUCatsHvEdtpuyiaRd5SZ3LryZZHH4rkmwVJOnhmkBuaH/SDa45NNunIBpOcHFtXeSt+YIpQIzq4jTnlnK9az/yX1AssGq9iGGFexIsz2BuOw8XuOpkckpUnnShM3tIh29I5dc2ircDYK227MEqQlrkmoDxsjwELGr280gqDrREgUXlfc1k8tFG6W+/0VxUQl4piO/Lo4AIzuzv/3txr521h85aqCp5lhj99CVAFALE0pz5zddzlJRrG8CK9pP9a2Ek6UpS7FVXGAXLs6XiHySYJHP/grcx/se4/DPheYEJmoN9SxplIIAG8L1KfbESJGlHNeARtyz4pjzl+7PXetLqmL6qdTbGZ9XVNWuZtfNH/36olS7fcuKvD5e4AZ5kgsCQF1skr6bdxPma8bmIe8v+GN91KG8jK53JSNjs3EAamI4aF5URMCuamgt5PUsJ1jSFcudYXQDftOodukEc8pCRnCP0LPUO2BYhGlLEfG/ovRB3ySVhENbdc6sVo4KEY37dTt6BSnCRtghU/x2KAOUkabDm/m0tTH30kb/MbyDRvxiPGI6OVsE6A6AMLJE3PtGM7lBM/72gsqM5BwO8BXVyy5nzw1wxQkLPQBXtwE88e+U0HXeTRu1B+n+tqpD/M3Ru7oyprjsyavFo/TckBocdUIM6PbBmV3/+jtN2LVoAxdwyodRA9ZlRCqZ0DC90OP7qy21LXChzBNlrWlBvsnfbO64kf1HswF5mVDXcVFer0x4w7fOEoO882aYgSaVm0r82KoHSFkz+0zRZuoRg7zUB6lxi+/UHt8JSqopVw5MXEPps1qvj/gi6t5hM18ZdskzR1WwJvVDIW2frh5SRW1mb6uJB0XOB6SsDIWXCLoAT175OJ/ZK/fVvPS3GcrjLKaDmhIgM/rralU01ssqkAG/VBR3lhUYfUcf7DgM8If/7u0c/Qme6+hIqbzZxVF6qLlptRhgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1257,"cache_read_input_tokens":13126,"output_tokens":4104,"output_tokens_details":{"thinking_tokens":134},"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":1257},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":832,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtG28XTmhnAgHBQp1YE","requestRef":"c8210cde-9079-4b06-90ce-fd1c5f35e7f8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5a2a97ee-5d56-4688-8270-2bf92a26b1e6","timestamp":"2026-10-30T05:39:56.552Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"5a2a97ee-5d56-4688-8270-2bf92a26b1e6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtG2V7SxiG42XgJ8Gra","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016Dvv11TytC5Fyi5TFaZSj3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t CIs for a mean.\n\nRun from the workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png.\n\nRNG: for each cell, rng = numpy.random.default_rng(cell seed). Per replication the draw order is\n  u = rng.standard_normal(G); e = rng.standard_normal(N); W = rng.integers(0, 2, (B, G))*2-1.\nBaseline (P2): naive i.i.d. interval ybar +- 1.96*s/sqrt(N), ignoring clustering (baseline_* keys).\n\"\"\"\nimport json\nimport 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__)))\nDATA = os.path.join(ROOT, \"data\", \"design.csv\")\nOUT = os.path.join(ROOT, \"out\")\n\ndesign = pd.read_csv(DATA)\ndata_issues = []\n\n\ndef key(est, G, icc):\n    return f\"{est}_G{int(G)}_icc{icc:.1f}\"\n\n\ndef simulate_cell(row):\n    G, icc, N, R, B = int(row.G), float(row.icc), int(row.N), int(row.R), int(row.B)\n    mu = float(row.mu)\n    n = np.array([int(x) for x in str(row.cluster_sizes).split(\"|\")])\n    assert len(n) == G and n.sum() == N, f\"inconsistent design row {row.cell_id}\"\n    gid = np.repeat(np.arange(G), n)\n    var_exact = (icc * np.sum(n ** 2) + (1 - icc) * N) / N ** 2\n    z = 1.96\n    tcrit = stats.t.ppf(0.975, G - 1)\n    cfac = G / (G - 1)\n    qidx = int(np.ceil((B + 1) * 0.95)) - 1  # 0-based index of the 380th order statistic for B=399\n    rng = np.random.default_rng(int(row.seed))\n    rec = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"s2\"]}\n    n_zero_vstar = 0\n    for r in range(R):\n        u = rng.standard_normal(G) * np.sqrt(icc)\n        e = rng.standard_normal(N) * np.sqrt(1 - icc)\n        W = rng.integers(0, 2, size=(B, G)) * 2 - 1\n        y = mu + u[gid] + e\n        ybar = y.mean()\n        ehat = y - ybar\n        S = np.bincount(gid, weights=ehat, minlength=G)  # cluster residual sums\n        v0 = np.sum(S ** 2) / N ** 2\n        v1 = cfac * v0\n        # wild cluster bootstrap: y* = ybar + w_g ehat_ig\n        d = (W @ S) / N                               # ybar* - ybar, shape (B,)\n        Sstar = W * S[None, :] - d[:, None] * n[None, :]  # cluster sums of bootstrap residuals\n        vstar = cfac * np.sum(Sstar ** 2, axis=1) / N ** 2\n        n_zero_vstar += int(np.sum(vstar <= 0))\n        tabs = np.abs(d) / np.sqrt(vstar)\n        q = np.sort(tabs)[qidx]\n        rec[\"ybar\"][r], rec[\"v0\"][r], rec[\"v1\"][r], rec[\"q\"][r] = ybar, v0, v1, q\n        rec[\"s2\"][r] = ehat.var(ddof=1)\n    ybar, v0, v1, q = rec[\"ybar\"], rec[\"v0\"], rec[\"v1\"], rec[\"q\"]\n    hw = {\"cr0\": z * np.sqrt(v0), \"cr1\": tcrit * np.sqrt(v1), \"wcb\": q * np.sqrt(v1),\n          \"iid\": z * np.sqrt(rec[\"s2\"] / N)}\n    out = {}\n    for est, h in hw.items():\n        cov = float(np.mean(np.abs(ybar - mu) <= h))\n        out[est] = {\"coverage\": cov, \"mc_se\": float(np.sqrt(cov * (1 - cov) / R)),\n                    \"hw\": float(np.mean(h))}\n    out[\"cr0\"][\"rel_bias\"] = float(np.mean(v0) / var_exact)\n    out[\"cr1\"][\"rel_bias\"] = float(np.mean(v1) / var_exact)\n    out[\"meta\"] = {\"var_exact\": float(var_exact), \"mc_var_ybar\": float(np.var(ybar, ddof=1)),\n                   \"n_zero_vstar\": n_zero_vstar, \"n_distinct_q\": int(len(np.unique(np.round(q, 12))))}\n    return out\n\n\nests = [\"cr0\", \"cr1\", \"wcb\"]\nrows, coverage, mcse, relbias = [], {}, {}, {}\nbase_cov, base_se, meta = {}, {}, {}\nfor _, row in design.iterrows():\n    res = simulate_cell(row)\n    G, icc = int(row.G), float(row.icc)\n    for est in ests:\n        k = key(est, G, icc)\n        coverage[k] = res[est][\"coverage\"]\n        mcse[k] = res[est][\"mc_se\"]\n        rb = res[est].get(\"rel_bias\")\n        if rb is not None:\n            relbias[k] = rb\n        rows.append({\"estimator\": est, \"cell_id\": row.cell_id, \"G\": G, \"icc\": icc,\n                     \"coverage\": res[est][\"coverage\"], \"mc_se_coverage\": res[est][\"mc_se\"],\n                     \"rel_bias_var\": rb, \"mean_ci_halfwidth\": res[est][\"hw\"], \"R\": int(row.R)})\n    bk = f\"G{G}_icc{icc:.1f}\"\n    base_cov[bk] = res[\"iid\"][\"coverage\"]\n    base_se[bk] = res[\"iid\"][\"mc_se\"]\n    meta[row.cell_id] = res[\"meta\"]\n    if res[\"meta\"][\"n_zero_vstar\"] > 0:\n        data_issues.append({\"issue\": f\"{row.cell_id}: {res['meta']['n_zero_vstar']} bootstrap draws with zero V*\",\n                            \"handling\": \"t* set to inf/nan by numpy; kept as is\"})\n\ntable = pd.DataFrame(rows)\ntable[\"est_order\"] = table.estimator.map({e: i for i, e in enumerate(ests)})\ntable = table.sort_values([\"est_order\", \"cell_id\"]).drop(columns=\"est_order\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nfailure = sorted([k for k, v in coverage.items() if v < 0.90])\nnominal = sorted([k for k, v in coverage.items() if abs(v - 0.95) <= 2 * mcse[k]])\nsmallG = {e: float(np.mean([coverage[key(e, 5, i)] for i in [0.0, 0.2, 0.5]])) for e in ests}\nbest = max(smallG, key=smallG.get)\n\nif (design.G == 5).any():\n    data_issues.append({\"issue\": \"G=5 cells: Rademacher weights give only 2^5=32 distinct weight vectors (16 distinct |t*| values), \"\n                                 \"so the WCB critical value takes few distinct values and B=399 draws mostly repeat them\",\n                        \"handling\": \"procedure kept exactly as specified (no Webb weights / enumeration); reported as a limitation\"})\ndata_issues.append({\"issue\": \"ICC=0.0 cells: cluster effect variance is zero (degenerate N(0,0))\",\n                    \"handling\": \"u_g drawn as sqrt(0)*N(0,1)=0 so the RNG stream structure is the same in every cell\"})\n\nR = int(design.R.iloc[0]); B = int(design.B.iloc[0])\nresults = {\n    \"task_id\": \"T2-simulation\",\n    \"R\": R, \"B\": B, \"n_cells\": int(len(design)),\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,\n    \"mean_coverage_G5\": smallG,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": {\"design.csv\": int(len(design))},\n    \"n_analysed\": int(design.R.sum()),\n    \"random_seed\": int(design.loc[design.cell_id == \"C1\", \"seed\"].iloc[0]),\n    \"baseline_iid_coverage\": base_cov, \"baseline_iid_mc_se\": base_se,\n    \"wcb_quantile_rule\": \"380th order statistic of B=399 |t*| values (ceil((B+1)*0.95))\",\n    \"cell_diagnostics\": meta,\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(design.G.unique())\nstyle = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t (Rademacher)\")}\nfor ax, icc in zip(axes, sorted(design.icc.unique())):\n    for e in ests:\n        c = np.array([coverage[key(e, g, icc)] for g in Gs])\n        s = np.array([mcse[key(e, g, icc)] for g in Gs])\n        ax.errorbar(Gs, c, yerr=1.96 * s, fmt=style[e][0], label=style[e][1], capsize=3)\n    ax.axhline(0.95, color=\"k\", ls=\"--\", lw=1, label=\"nominal 0.95\")\n    ax.axhline(0.90, color=\"r\", ls=\":\", lw=1, label=\"failure line 0.90\")\n    ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels([str(g) for g in Gs])\n    ax.set_title(f\"ICC = {icc:.1f}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±1.96 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(f\"Coverage of nominal 95% cluster-robust CIs for the mean (R={R}, B={B})\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n\nprint(table.to_string(index=False))\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best, smallG)\nEOF\ntime ~/wp29/venv/bin/python out/analysis.py","description":"Write and run simulation script","timeout":600000},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1257,"cache_read_input_tokens":13126,"output_tokens":4104,"output_tokens_details":{"thinking_tokens":134},"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":1257},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtG28XTmhnAgHBQp1YE","requestRef":"c8210cde-9079-4b06-90ce-fd1c5f35e7f8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dd7d246d-e28a-4bcc-bc06-b6f5e5e3151d","timestamp":"2026-10-30T05:40:25.298Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}47{"parentUuid":"dd7d246d-e28a-4bcc-bc06-b6f5e5e3151d","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016Dvv11TytC5Fyi5TFaZSj3","type":"tool_result","content":"estimator cell_id  G  icc  coverage  mc_se_coverage  rel_bias_var  mean_ci_halfwidth    R\n      cr0      C1  5  0.0    0.7805        0.009255      0.661643           0.129684 2000\n      cr0      C2  5  0.2    0.7210        0.010029      0.531396           0.342268 2000\n      cr0      C3  5  0.5    0.7170        0.010073      0.483350           0.498894 2000\n      cr0      C4 10  0.0    0.8965        0.006811      0.855805           0.106852 2000\n      cr0      C5 10  0.2    0.8570        0.007828      0.762437           0.301309 2000\n      cr0      C6 10  0.5    0.8530        0.007918      0.773743           0.461422 2000\n      cr0      C7 30  0.0    0.9275        0.005798      0.943797           0.063969 2000\n      cr0      C8 30  0.2    0.9210        0.006032      0.931367           0.196303 2000\n      cr0      C9 30  0.5    0.9165        0.006186      0.925260           0.299237 2000\n      cr1      C1  5  0.0    0.9115        0.006351      0.827054           0.205387 2000\n      cr1      C2  5  0.2    0.8845        0.007147      0.664245           0.542069 2000\n      cr1      C3  5  0.5    0.8755        0.007382      0.604188           0.790125 2000\n      cr1      C4 10  0.0    0.9435        0.005163      0.950894           0.129995 2000\n      cr1      C5 10  0.2    0.9155        0.006219      0.847152           0.366571 2000\n      cr1      C6 10  0.5    0.9065        0.006510      0.859715           0.561363 2000\n      cr1      C7 30  0.0    0.9400        0.005310      0.976341           0.067892 2000\n      cr1      C8 30  0.2    0.9350        0.005512      0.963483           0.208341 2000\n      cr1      C9 30  0.5    0.9300        0.005705      0.957165           0.317587 2000\n      wcb      C1  5  0.0    0.8575        0.007816           NaN           0.250419 2000\n      wcb      C2  5  0.2    0.8545        0.007884           NaN           0.925496 2000\n      wcb      C3  5  0.5    0.8510        0.007962           NaN           1.386152 2000\n      wcb      C4 10  0.0    0.9375        0.005413           NaN           0.146598 2000\n      wcb      C5 10  0.2    0.9325        0.005610           NaN           0.465642 2000\n      wcb      C6 10  0.5    0.9350        0.005512           NaN           0.730597 2000\n      wcb      C7 30  0.0    0.9445        0.005120           NaN           0.070410 2000\n      wcb      C8 30  0.2    0.9470        0.005010           NaN           0.224426 2000\n      wcb      C9 30  0.5    0.9440        0.005141           NaN           0.341879 2000\nfailure cells: ['cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5', 'cr0_G5_icc0.0', 'cr0_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.2', 'cr1_G5_icc0.5', 'wcb_G5_icc0.0', 'wcb_G5_icc0.2', 'wcb_G5_icc0.5']\nbest procedure at G=5: cr1 {'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}\n~/wp29/venv/bin/python out/analysis.py  1,92s user 0,06s system 99% cpu 1,985 total","is_error":false}]},"uuid":"3553dbb8-1e5d-4a12-9e02-ad76a70d3fcd","timestamp":"2026-10-30T05:40:27.316Z","toolUseResult":{"stdout":"estimator cell_id  G  icc  coverage  mc_se_coverage  rel_bias_var  mean_ci_halfwidth    R\n      cr0      C1  5  0.0    0.7805        0.009255      0.661643           0.129684 2000\n      cr0      C2  5  0.2    0.7210        0.010029      0.531396           0.342268 2000\n      cr0      C3  5  0.5    0.7170        0.010073      0.483350           0.498894 2000\n      cr0      C4 10  0.0    0.8965        0.006811      0.855805           0.106852 2000\n      cr0      C5 10  0.2    0.8570        0.007828      0.762437           0.301309 2000\n      cr0      C6 10  0.5    0.8530        0.007918      0.773743           0.461422 2000\n      cr0      C7 30  0.0    0.9275        0.005798      0.943797           0.063969 2000\n      cr0      C8 30  0.2    0.9210        0.006032      0.931367           0.196303 2000\n      cr0      C9 30  0.5    0.9165        0.006186      0.925260           0.299237 2000\n      cr1      C1  5  0.0    0.9115        0.006351      0.827054           0.205387 2000\n      cr1      C2  5  0.2    0.8845        0.007147      0.664245           0.542069 2000\n      cr1      C3  5  0.5    0.8755        0.007382      0.604188           0.790125 2000\n      cr1      C4 10  0.0    0.9435        0.005163      0.950894           0.129995 2000\n      cr1      C5 10  0.2    0.9155        0.006219      0.847152           0.366571 2000\n      cr1      C6 10  0.5    0.9065        0.006510      0.859715           0.561363 2000\n      cr1      C7 30  0.0    0.9400        0.005310      0.976341           0.067892 2000\n      cr1      C8 30  0.2    0.9350        0.005512      0.963483           0.208341 2000\n      cr1      C9 30  0.5    0.9300        0.005705      0.957165           0.317587 2000\n      wcb      C1  5  0.0    0.8575        0.007816           NaN           0.250419 2000\n      wcb      C2  5  0.2    0.8545        0.007884           NaN           0.925496 2000\n      wcb      C3  5  0.5    0.8510        0.007962           NaN           1.386152 2000\n      wcb      C4 10  0.0    0.9375        0.005413           NaN           0.146598 2000\n      wcb      C5 10  0.2    0.9325        0.005610           NaN           0.465642 2000\n      wcb      C6 10  0.5    0.9350        0.005512           NaN           0.730597 2000\n      wcb      C7 30  0.0    0.9445        0.005120           NaN           0.070410 2000\n      wcb      C8 30  0.2    0.9470        0.005010           NaN           0.224426 2000\n      wcb      C9 30  0.5    0.9440        0.005141           NaN           0.341879 2000\nfailure cells: ['cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5', 'cr0_G5_icc0.0', 'cr0_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.2', 'cr1_G5_icc0.5', 'wcb_G5_icc0.0', 'wcb_G5_icc0.2', 'wcb_G5_icc0.5']\nbest procedure at G=5: cr1 {'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}\n~/wp29/venv/bin/python out/analysis.py  1,92s user 0,06s system 99% cpu 1,985 total","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"dd7d246d-e28a-4bcc-bc06-b6f5e5e3151d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}48{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"d4bdb8cbdec25ac93a4520661ed4877bab60fcbf48956be506ff84a40424844d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSrggKEAgTGAI4AUIIdGhpbmtpbmcSDIg4N7UQkCdGGGWemhoM0CEqE7pyD1Um52f2IjBSh/hKusxo4Cn/+o43vpSwJcdqRhTAp7FGwo/nvpFhqOCNkNfvsOo3xAWLuTve1tQqywcTlK9j3K8kahDWWlDRSbUiOdrRHxmuMbJM6nSv0MeZQ8TAuN6X7IVPTZOIxPqJ7Q1fkVkgwPtMx2lqEBclOQ/0XqjMWT2bwbol81gsxjjrsRqq2sgXzYaNOTOPuAxf7L+Cq2usnoxaGawN9DbRRV04D408zQgXy4NMmPYEODahJQVr3PD9TTUGim4UhuaRCULIc5/BuokY4JMUkRQJjby19b7TvwlIj5HDeos4KsxqdBF3bDMd7nnm0hUWNAg4vAJvFp3EUiisjUkQqjl6RknwXcxaWKxJ5I03g944jx+ktM6NhXEu5WWGyIHTqNb/2vQNFs7v0o/+mfUCatsHvEdtpuyiaRd5SZ3LryZZHH4rkmwVJOnhmkBuaH/SDa45NNunIBpOcHFtXeSt+YIpQIzq4jTnlnK9az/yX1AssGq9iGGFexIsz2BuOw8XuOpkckpUnnShM3tIh29I5dc2ircDYK227MEqQlrkmoDxsjwELGr280gqDrREgUXlfc1k8tFG6W+/0VxUQl4piO/Lo4AIzuzv/3txr521h85aqCp5lhj99CVAFALE0pz5zddzlJRrG8CK9pP9a2Ek6UpS7FVXGAXLs6XiHySYJHP/grcx/se4/DPheYEJmoN9SxplIIAG8L1KfbESJGlHNeARtyz4pjzl+7PXetLqmL6qdTbGZ9XVNWuZtfNH/36olS7fcuKvD5e4AZ5kgsCQF1skr6bdxPma8bmIe8v+GN91KG8jK53JSNjs3EAamI4aF5URMCuamgt5PUsJ1jSFcudYXQDftOodukEc8pCRnCP0LPUO2BYhGlLEfG/ovRB3ySVhENbdc6sVo4KEY37dTt6BSnCRtghU/x2KAOUkabDm/m0tTH30kb/MbyDRvxiPGI6OVsE6A6AMLJE3PtGM7lBM/72gsqM5BwO8BXVyy5nzw1wxQkLPQBXtwE88e+U0HXeTRu1B+n+tqpD/M3Ru7oyprjsyavFo/TckBocdUIM6PbBmV3/+jtN2LVoAxdwyodRA9ZlRCqZ0DC90OP7qy21LXChzBNlrWlBvsnfbO64kf1HswF5mVDXcVFer0x4w7fOEoO882aYgSaVm0r82KoHSFkz+0zRZuoRg7zUB6lxi+/UHt8JSqopVw5MXEPps1qvj/gi6t5hM18ZdskzR1WwJvVDIW2frh5SRW1mb6uJB0XOB6SsDIWXCLoAT175OJ/ZK/fVvPS3GcrjLKaDmhIgM/rralU01ssqkAG/VBR3lhUYfUcf7DgM8If/7u0c/Qme6+hIqbzZxVF6qLlptRhgB"},{"type":"tool_use","id":"toolu_016Dvv11TytC5Fyi5TFaZSj3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t CIs for a mean.\n\nRun from the workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png.\n\nRNG: for each cell, rng = numpy.random.default_rng(cell seed). Per replication the draw order is\n  u = rng.standard_normal(G); e = rng.standard_normal(N); W = rng.integers(0, 2, (B, G))*2-1.\nBaseline (P2): naive i.i.d. interval ybar +- 1.96*s/sqrt(N), ignoring clustering (baseline_* keys).\n\"\"\"\nimport json\nimport 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__)))\nDATA = os.path.join(ROOT, \"data\", \"design.csv\")\nOUT = os.path.join(ROOT, \"out\")\n\ndesign = pd.read_csv(DATA)\ndata_issues = []\n\n\ndef key(est, G, icc):\n    return f\"{est}_G{int(G)}_icc{icc:.1f}\"\n\n\ndef simulate_cell(row):\n    G, icc, N, R, B = int(row.G), float(row.icc), int(row.N), int(row.R), int(row.B)\n    mu = float(row.mu)\n    n = np.array([int(x) for x in str(row.cluster_sizes).split(\"|\")])\n    assert len(n) == G and n.sum() == N, f\"inconsistent design row {row.cell_id}\"\n    gid = np.repeat(np.arange(G), n)\n    var_exact = (icc * np.sum(n ** 2) + (1 - icc) * N) / N ** 2\n    z = 1.96\n    tcrit = stats.t.ppf(0.975, G - 1)\n    cfac = G / (G - 1)\n    qidx = int(np.ceil((B + 1) * 0.95)) - 1  # 0-based index of the 380th order statistic for B=399\n    rng = np.random.default_rng(int(row.seed))\n    rec = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"s2\"]}\n    n_zero_vstar = 0\n    for r in range(R):\n        u = rng.standard_normal(G) * np.sqrt(icc)\n        e = rng.standard_normal(N) * np.sqrt(1 - icc)\n        W = rng.integers(0, 2, size=(B, G)) * 2 - 1\n        y = mu + u[gid] + e\n        ybar = y.mean()\n        ehat = y - ybar\n        S = np.bincount(gid, weights=ehat, minlength=G)  # cluster residual sums\n        v0 = np.sum(S ** 2) / N ** 2\n        v1 = cfac * v0\n        # wild cluster bootstrap: y* = ybar + w_g ehat_ig\n        d = (W @ S) / N                               # ybar* - ybar, shape (B,)\n        Sstar = W * S[None, :] - d[:, None] * n[None, :]  # cluster sums of bootstrap residuals\n        vstar = cfac * np.sum(Sstar ** 2, axis=1) / N ** 2\n        n_zero_vstar += int(np.sum(vstar <= 0))\n        tabs = np.abs(d) / np.sqrt(vstar)\n        q = np.sort(tabs)[qidx]\n        rec[\"ybar\"][r], rec[\"v0\"][r], rec[\"v1\"][r], rec[\"q\"][r] = ybar, v0, v1, q\n        rec[\"s2\"][r] = ehat.var(ddof=1)\n    ybar, v0, v1, q = rec[\"ybar\"], rec[\"v0\"], rec[\"v1\"], rec[\"q\"]\n    hw = {\"cr0\": z * np.sqrt(v0), \"cr1\": tcrit * np.sqrt(v1), \"wcb\": q * np.sqrt(v1),\n          \"iid\": z * np.sqrt(rec[\"s2\"] / N)}\n    out = {}\n    for est, h in hw.items():\n        cov = float(np.mean(np.abs(ybar - mu) <= h))\n        out[est] = {\"coverage\": cov, \"mc_se\": float(np.sqrt(cov * (1 - cov) / R)),\n                    \"hw\": float(np.mean(h))}\n    out[\"cr0\"][\"rel_bias\"] = float(np.mean(v0) / var_exact)\n    out[\"cr1\"][\"rel_bias\"] = float(np.mean(v1) / var_exact)\n    out[\"meta\"] = {\"var_exact\": float(var_exact), \"mc_var_ybar\": float(np.var(ybar, ddof=1)),\n                   \"n_zero_vstar\": n_zero_vstar, \"n_distinct_q\": int(len(np.unique(np.round(q, 12))))}\n    return out\n\n\nests = [\"cr0\", \"cr1\", \"wcb\"]\nrows, coverage, mcse, relbias = [], {}, {}, {}\nbase_cov, base_se, meta = {}, {}, {}\nfor _, row in design.iterrows():\n    res = simulate_cell(row)\n    G, icc = int(row.G), float(row.icc)\n    for est in ests:\n        k = key(est, G, icc)\n        coverage[k] = res[est][\"coverage\"]\n        mcse[k] = res[est][\"mc_se\"]\n        rb = res[est].get(\"rel_bias\")\n        if rb is not None:\n            relbias[k] = rb\n        rows.append({\"estimator\": est, \"cell_id\": row.cell_id, \"G\": G, \"icc\": icc,\n                     \"coverage\": res[est][\"coverage\"], \"mc_se_coverage\": res[est][\"mc_se\"],\n                     \"rel_bias_var\": rb, \"mean_ci_halfwidth\": res[est][\"hw\"], \"R\": int(row.R)})\n    bk = f\"G{G}_icc{icc:.1f}\"\n    base_cov[bk] = res[\"iid\"][\"coverage\"]\n    base_se[bk] = res[\"iid\"][\"mc_se\"]\n    meta[row.cell_id] = res[\"meta\"]\n    if res[\"meta\"][\"n_zero_vstar\"] > 0:\n        data_issues.append({\"issue\": f\"{row.cell_id}: {res['meta']['n_zero_vstar']} bootstrap draws with zero V*\",\n                            \"handling\": \"t* set to inf/nan by numpy; kept as is\"})\n\ntable = pd.DataFrame(rows)\ntable[\"est_order\"] = table.estimator.map({e: i for i, e in enumerate(ests)})\ntable = table.sort_values([\"est_order\", \"cell_id\"]).drop(columns=\"est_order\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nfailure = sorted([k for k, v in coverage.items() if v < 0.90])\nnominal = sorted([k for k, v in coverage.items() if abs(v - 0.95) <= 2 * mcse[k]])\nsmallG = {e: float(np.mean([coverage[key(e, 5, i)] for i in [0.0, 0.2, 0.5]])) for e in ests}\nbest = max(smallG, key=smallG.get)\n\nif (design.G == 5).any():\n    data_issues.append({\"issue\": \"G=5 cells: Rademacher weights give only 2^5=32 distinct weight vectors (16 distinct |t*| values), \"\n                                 \"so the WCB critical value takes few distinct values and B=399 draws mostly repeat them\",\n                        \"handling\": \"procedure kept exactly as specified (no Webb weights / enumeration); reported as a limitation\"})\ndata_issues.append({\"issue\": \"ICC=0.0 cells: cluster effect variance is zero (degenerate N(0,0))\",\n                    \"handling\": \"u_g drawn as sqrt(0)*N(0,1)=0 so the RNG stream structure is the same in every cell\"})\n\nR = int(design.R.iloc[0]); B = int(design.B.iloc[0])\nresults = {\n    \"task_id\": \"T2-simulation\",\n    \"R\": R, \"B\": B, \"n_cells\": int(len(design)),\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,\n    \"mean_coverage_G5\": smallG,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": {\"design.csv\": int(len(design))},\n    \"n_analysed\": int(design.R.sum()),\n    \"random_seed\": int(design.loc[design.cell_id == \"C1\", \"seed\"].iloc[0]),\n    \"baseline_iid_coverage\": base_cov, \"baseline_iid_mc_se\": base_se,\n    \"wcb_quantile_rule\": \"380th order statistic of B=399 |t*| values (ceil((B+1)*0.95))\",\n    \"cell_diagnostics\": meta,\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(design.G.unique())\nstyle = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t (Rademacher)\")}\nfor ax, icc in zip(axes, sorted(design.icc.unique())):\n    for e in ests:\n        c = np.array([coverage[key(e, g, icc)] for g in Gs])\n        s = np.array([mcse[key(e, g, icc)] for g in Gs])\n        ax.errorbar(Gs, c, yerr=1.96 * s, fmt=style[e][0], label=style[e][1], capsize=3)\n    ax.axhline(0.95, color=\"k\", ls=\"--\", lw=1, label=\"nominal 0.95\")\n    ax.axhline(0.90, color=\"r\", ls=\":\", lw=1, label=\"failure line 0.90\")\n    ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels([str(g) for g in Gs])\n    ax.set_title(f\"ICC = {icc:.1f}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±1.96 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(f\"Coverage of nominal 95% cluster-robust CIs for the mean (R={R}, B={B})\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n\nprint(table.to_string(index=False))\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best, smallG)\nEOF\ntime ~/wp29/venv/bin/python out/analysis.py","description":"Write and run simulation script","timeout":600000}}]}}49{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"234dfe20-6d7a-4194-bbd5-4f20c0f5ec68","timestamp":"2026-10-30T05:40:27.319Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"c8210cde-9079-4b06-90ce-fd1c5f35e7f8","keep":14,"tail":["d4bdb8cbdec25ac93a4520661ed4877bab60fcbf48956be506ff84a40424844d","c6909d8b47d29ac0f8a94a620ad1bb553d9cf045b4c7423551993a1a5a31a0e4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d84f020eae594728ec3bba3199c679ab692160edb3a7533dc70f86ff5eefec60"}50{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3553dbb8-1e5d-4a12-9e02-ad76a70d3fcd","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}51{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}52{"parentUuid":"3553dbb8-1e5d-4a12-9e02-ad76a70d3fcd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtJUfGyG9zoa79Tp4tM","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":5416,"cache_read_input_tokens":14383,"output_tokens":983,"output_tokens_details":{"thinking_tokens":274},"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":5416},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2373,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtJUMfrPycLjuyDhmBJ","requestRef":"234dfe20-6d7a-4194-bbd5-4f20c0f5ec68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"677e5c6c-f3e1-4ef9-8737-0a017690ccd0","timestamp":"2026-10-30T05:40:31.473Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"677e5c6c-f3e1-4ef9-8737-0a017690ccd0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtJUfGyG9zoa79Tp4tM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KHTdnTbxmbme3uxinoUGSe","name":"Bash","input":{"command":"mkdir -p out/state/verify && cat > out/state/verify/check_wcb.py <<'EOF'\n# Verification: brute-force WCB on explicit y* vs vectorised formula; MC var vs exact var.\nimport json, numpy as np\nrng = np.random.default_rng(1)\nn = np.array([8,16,32,64,8]); G=len(n); N=n.sum(); gid=np.repeat(np.arange(G), n)\ny = rng.standard_normal(G)[gid]*np.sqrt(.5) + rng.standard_normal(N)*np.sqrt(.5)\nyb=y.mean(); eh=y-yb; S=np.bincount(gid,weights=eh); W=rng.integers(0,2,(399,G))*2-1\nd=(W@S)/N; Ss=W*S-d[:,None]*n; vs=G/(G-1)*np.sum(Ss**2,1)/N**2; t1=np.abs(d)/np.sqrt(vs)\nt2=[]\nfor w in W:\n    ys=yb+w[gid]*eh; m=ys.mean(); r=ys-m; v=G/(G-1)*np.sum(np.bincount(gid,weights=r)**2)/N**2; t2.append(abs(m-yb)/np.sqrt(v))\nprint(\"max abs diff t* vectorised vs brute force:\", np.max(np.abs(t1-np.array(t2))))\nres=json.load(open(\"out/results.json\"))\nfor c,m in res[\"cell_diagnostics\"].items():\n    print(c, \"MC var/exact var = %.4f\"%(m[\"mc_var_ybar\"]/m[\"var_exact\"]), \"distinct q:\", m[\"n_distinct_q\"], \"zero V*:\", m[\"n_zero_vstar\"])\nEOF\n~/wp29/venv/bin/python out/state/verify/check_wcb.py","description":"Verify bootstrap formula and variance"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5416,"cache_read_input_tokens":14383,"output_tokens":983,"output_tokens_details":{"thinking_tokens":274},"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":5416},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtJUMfrPycLjuyDhmBJ","requestRef":"234dfe20-6d7a-4194-bbd5-4f20c0f5ec68","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"47d73c19-4119-4507-bd10-1c39fe6115fb","timestamp":"2026-10-30T05:40:36.704Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"47d73c19-4119-4507-bd10-1c39fe6115fb","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KHTdnTbxmbme3uxinoUGSe","type":"tool_result","content":"max abs diff t* vectorised vs brute force: 1.0658141036401503e-14\nC1 MC var/exact var = 1.0353 distinct q: 2000 zero V*: 0\nC2 MC var/exact var = 1.0646 distinct q: 2000 zero V*: 0\nC3 MC var/exact var = 0.9463 distinct q: 2000 zero V*: 0\nC4 MC var/exact var = 0.9336 distinct q: 2000 zero V*: 0\nC5 MC var/exact var = 0.9685 distinct q: 2000 zero V*: 0\nC6 MC var/exact var = 0.9796 distinct q: 2000 zero V*: 0\nC7 MC var/exact var = 0.9986 distinct q: 2000 zero V*: 0\nC8 MC var/exact var = 0.9393 distinct q: 2000 zero V*: 0\nC9 MC var/exact var = 1.0404 distinct q: 2000 zero V*: 0","is_error":false}]},"uuid":"877def0e-99ee-48eb-85dc-62b4c0cc5bc3","timestamp":"2026-10-30T05:40:36.814Z","toolUseResult":{"stdout":"max abs diff t* vectorised vs brute force: 1.0658141036401503e-14\nC1 MC var/exact var = 1.0353 distinct q: 2000 zero V*: 0\nC2 MC var/exact var = 1.0646 distinct q: 2000 zero V*: 0\nC3 MC var/exact var = 0.9463 distinct q: 2000 zero V*: 0\nC4 MC var/exact var = 0.9336 distinct q: 2000 zero V*: 0\nC5 MC var/exact var = 0.9685 distinct q: 2000 zero V*: 0\nC6 MC var/exact var = 0.9796 distinct q: 2000 zero V*: 0\nC7 MC var/exact var = 0.9986 distinct q: 2000 zero V*: 0\nC8 MC var/exact var = 0.9393 distinct q: 2000 zero V*: 0\nC9 MC var/exact var = 1.0404 distinct q: 2000 zero V*: 0","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"47d73c19-4119-4507-bd10-1c39fe6115fb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}55{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"a544528941bad9c21647ea5a7c216f5da90344569679db0d834c926464cf551c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KHTdnTbxmbme3uxinoUGSe","name":"Bash","input":{"command":"mkdir -p out/state/verify && cat > out/state/verify/check_wcb.py <<'EOF'\n# Verification: brute-force WCB on explicit y* vs vectorised formula; MC var vs exact var.\nimport json, numpy as np\nrng = np.random.default_rng(1)\nn = np.array([8,16,32,64,8]); G=len(n); N=n.sum(); gid=np.repeat(np.arange(G), n)\ny = rng.standard_normal(G)[gid]*np.sqrt(.5) + rng.standard_normal(N)*np.sqrt(.5)\nyb=y.mean(); eh=y-yb; S=np.bincount(gid,weights=eh); W=rng.integers(0,2,(399,G))*2-1\nd=(W@S)/N; Ss=W*S-d[:,None]*n; vs=G/(G-1)*np.sum(Ss**2,1)/N**2; t1=np.abs(d)/np.sqrt(vs)\nt2=[]\nfor w in W:\n    ys=yb+w[gid]*eh; m=ys.mean(); r=ys-m; v=G/(G-1)*np.sum(np.bincount(gid,weights=r)**2)/N**2; t2.append(abs(m-yb)/np.sqrt(v))\nprint(\"max abs diff t* vectorised vs brute force:\", np.max(np.abs(t1-np.array(t2))))\nres=json.load(open(\"out/results.json\"))\nfor c,m in res[\"cell_diagnostics\"].items():\n    print(c, \"MC var/exact var = %.4f\"%(m[\"mc_var_ybar\"]/m[\"var_exact\"]), \"distinct q:\", m[\"n_distinct_q\"], \"zero V*:\", m[\"n_zero_vstar\"])\nEOF\n~/wp29/venv/bin/python out/state/verify/check_wcb.py","description":"Verify bootstrap formula and variance"}}]}}56{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"89b03d6a-c20e-4db7-a92b-ded8fa85ba9a","timestamp":"2026-10-30T05:40:36.816Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"234dfe20-6d7a-4194-bbd5-4f20c0f5ec68","keep":16,"tail":["a544528941bad9c21647ea5a7c216f5da90344569679db0d834c926464cf551c","f66e433cbf805d9a487c169ae16c1e666d774f3bb4ab962af57177aea846f208"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"dd01ab5496bb700ef1149be99569bfa1a5087faf113d37ef9792670b9b4546d5"}57{"parentUuid":"877def0e-99ee-48eb-85dc-62b4c0cc5bc3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtKBEJvomCMrm4bvxMn","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":1323,"cache_read_input_tokens":19799,"output_tokens":1415,"output_tokens_details":{"thinking_tokens":257},"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":1323},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2145,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtKAxBNhKeccLN6Wk52","requestRef":"89b03d6a-c20e-4db7-a92b-ded8fa85ba9a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d69cbb72-e110-445b-ba88-aa113cd0ac41","timestamp":"2026-10-30T05:40:40.610Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"d69cbb72-e110-445b-ba88-aa113cd0ac41","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtKBEJvomCMrm4bvxMn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VQ2XZaZGAxh4Cox2an9yeB","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace('''rec = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"s2\"]}''','''rec = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"s2\", \"qalt\"]}''')\ns=s.replace('''        q = np.sort(tabs)[qidx]\n''','''        q = np.sort(tabs)[qidx]\n        rec[\"qalt\"][r] = np.quantile(tabs, 0.95)  # sensitivity: numpy linear-interpolation quantile\n''')\ns=s.replace('''          \"iid\": z * np.sqrt(rec[\"s2\"] / N)}''','''          \"iid\": z * np.sqrt(rec[\"s2\"] / N), \"wcb_alt\": rec[\"qalt\"] * np.sqrt(v1)}''')\ns=s.replace('''    out[\"cr1\"][\"rel_bias\"] = float(np.mean(v1) / var_exact)\n''','''    out[\"cr1\"][\"rel_bias\"] = float(np.mean(v1) / var_exact)\n    out[\"cr0\"][\"rel_bias_se\"] = float(np.std(v0, ddof=1) / np.sqrt(R) / var_exact)\n    out[\"cr1\"][\"rel_bias_se\"] = float(np.std(v1, ddof=1) / np.sqrt(R) / var_exact)\n''')\ns=s.replace('''base_cov, base_se, meta = {}, {}, {}''','''base_cov, base_se, meta, rb_se, wcb_alt = {}, {}, {}, {}, {}''')\ns=s.replace('''            relbias[k] = rb\n''','''            relbias[k] = rb\n            rb_se[k] = res[est][\"rel_bias_se\"]\n''')\ns=s.replace('''    base_se[bk] = res[\"iid\"][\"mc_se\"]\n''','''    base_se[bk] = res[\"iid\"][\"mc_se\"]\n    wcb_alt[key(\"wcb\", G, icc)] = res[\"wcb_alt\"][\"coverage\"]\n''')\ns=s.replace('''\"rel_bias_var\": relbias,\n''','''\"rel_bias_var\": relbias,\n    \"mc_se_rel_bias_var\": rb_se,\n''')\ns=s.replace('''    \"wcb_quantile_rule\"''','''    \"sensitivity_wcb_coverage_numpy_quantile\": wcb_alt,\n    \"wcb_quantile_rule\"''')\ns=s.replace('''print(\"best procedure''','''print(\"baseline iid coverage:\", base_cov)\nprint(\"WCB coverage, numpy-quantile sensitivity:\", wcb_alt)\nprint(\"best procedure''')\nopen('analysis.py','w').write(s)\nEOF\ncd .. && ~/wp29/venv/bin/python out/analysis.py | tail -4 && ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));print(r['mc_se_rel_bias_var']);print(r['nominal_cells'])\"","description":"Add bias MC SE and quantile sensitivity, rerun"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1323,"cache_read_input_tokens":19799,"output_tokens":1415,"output_tokens_details":{"thinking_tokens":257},"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":1323},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtKAxBNhKeccLN6Wk52","requestRef":"89b03d6a-c20e-4db7-a92b-ded8fa85ba9a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"43e19abf-05f8-4ee8-a7a6-7845a6d157db","timestamp":"2026-10-30T05:40:48.267Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}59{"parentUuid":"43e19abf-05f8-4ee8-a7a6-7845a6d157db","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VQ2XZaZGAxh4Cox2an9yeB","type":"tool_result","content":"failure cells: ['cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5', 'cr0_G5_icc0.0', 'cr0_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.2', 'cr1_G5_icc0.5', 'wcb_G5_icc0.0', 'wcb_G5_icc0.2', 'wcb_G5_icc0.5']\nbaseline iid coverage: {'G5_icc0.0': 0.9405, 'G5_icc0.2': 0.46, 'G5_icc0.5': 0.2865, 'G10_icc0.0': 0.957, 'G10_icc0.2': 0.488, 'G10_icc0.5': 0.3125, 'G30_icc0.0': 0.9515, 'G30_icc0.2': 0.485, 'G30_icc0.5': 0.2985}\nWCB coverage, numpy-quantile sensitivity: {'wcb_G5_icc0.0': 0.855, 'wcb_G5_icc0.2': 0.854, 'wcb_G5_icc0.5': 0.849, 'wcb_G10_icc0.0': 0.936, 'wcb_G10_icc0.2': 0.9295, 'wcb_G10_icc0.5': 0.9325, 'wcb_G30_icc0.0': 0.943, 'wcb_G30_icc0.2': 0.946, 'wcb_G30_icc0.5': 0.9425}\nbest procedure at G=5: cr1 {'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}\n{'cr0_G5_icc0.0': 0.012963511182344976, 'cr1_G5_icc0.0': 0.01620438897793122, 'cr0_G5_icc0.2': 0.012975387163286884, 'cr1_G5_icc0.2': 0.016219233954108608, 'cr0_G5_icc0.5': 0.011854909267984598, 'cr1_G5_icc0.5': 0.01481863658498075, 'cr0_G10_icc0.0': 0.011793478824212352, 'cr1_G10_icc0.0': 0.013103865360235948, 'cr0_G10_icc0.2': 0.012887411160981703, 'cr1_G10_icc0.2': 0.014319345734424112, 'cr0_G10_icc0.5': 0.014100595197540216, 'cr1_G10_icc0.5': 0.015667327997266903, 'cr0_G30_icc0.0': 0.006765949452231232, 'cr1_G30_icc0.0': 0.006999258054032309, 'cr0_G30_icc0.2': 0.00853308139600021, 'cr1_G30_icc0.2': 0.008827325582069187, 'cr0_G30_icc0.5': 0.008700682520806436, 'cr1_G30_icc0.5': 0.009000706056006657}\n['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5']","is_error":false}]},"uuid":"9a924665-c9e7-428d-81f9-05e32f36e99d","timestamp":"2026-10-30T05:40:50.669Z","toolUseResult":{"stdout":"failure cells: ['cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5', 'cr0_G5_icc0.0', 'cr0_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.2', 'cr1_G5_icc0.5', 'wcb_G5_icc0.0', 'wcb_G5_icc0.2', 'wcb_G5_icc0.5']\nbaseline iid coverage: {'G5_icc0.0': 0.9405, 'G5_icc0.2': 0.46, 'G5_icc0.5': 0.2865, 'G10_icc0.0': 0.957, 'G10_icc0.2': 0.488, 'G10_icc0.5': 0.3125, 'G30_icc0.0': 0.9515, 'G30_icc0.2': 0.485, 'G30_icc0.5': 0.2985}\nWCB coverage, numpy-quantile sensitivity: {'wcb_G5_icc0.0': 0.855, 'wcb_G5_icc0.2': 0.854, 'wcb_G5_icc0.5': 0.849, 'wcb_G10_icc0.0': 0.936, 'wcb_G10_icc0.2': 0.9295, 'wcb_G10_icc0.5': 0.9325, 'wcb_G30_icc0.0': 0.943, 'wcb_G30_icc0.2': 0.946, 'wcb_G30_icc0.5': 0.9425}\nbest procedure at G=5: cr1 {'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}\n{'cr0_G5_icc0.0': 0.012963511182344976, 'cr1_G5_icc0.0': 0.01620438897793122, 'cr0_G5_icc0.2': 0.012975387163286884, 'cr1_G5_icc0.2': 0.016219233954108608, 'cr0_G5_icc0.5': 0.011854909267984598, 'cr1_G5_icc0.5': 0.01481863658498075, 'cr0_G10_icc0.0': 0.011793478824212352, 'cr1_G10_icc0.0': 0.013103865360235948, 'cr0_G10_icc0.2': 0.012887411160981703, 'cr1_G10_icc0.2': 0.014319345734424112, 'cr0_G10_icc0.5': 0.014100595197540216, 'cr1_G10_icc0.5': 0.015667327997266903, 'cr0_G30_icc0.0': 0.006765949452231232, 'cr1_G30_icc0.0': 0.006999258054032309, 'cr0_G30_icc0.2': 0.00853308139600021, 'cr1_G30_icc0.2': 0.008827325582069187, 'cr0_G30_icc0.5': 0.008700682520806436, 'cr1_G30_icc0.5': 0.009000706056006657}\n['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5']","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"43e19abf-05f8-4ee8-a7a6-7845a6d157db","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}60{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"b25f4e903e3b07b25daf2399a1e76e23c6d5dfcb41d6e289a05cdc4b8867c1fc","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01VQ2XZaZGAxh4Cox2an9yeB","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace('''rec = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"s2\"]}''','''rec = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"s2\", \"qalt\"]}''')\ns=s.replace('''        q = np.sort(tabs)[qidx]\n''','''        q = np.sort(tabs)[qidx]\n        rec[\"qalt\"][r] = np.quantile(tabs, 0.95)  # sensitivity: numpy linear-interpolation quantile\n''')\ns=s.replace('''          \"iid\": z * np.sqrt(rec[\"s2\"] / N)}''','''          \"iid\": z * np.sqrt(rec[\"s2\"] / N), \"wcb_alt\": rec[\"qalt\"] * np.sqrt(v1)}''')\ns=s.replace('''    out[\"cr1\"][\"rel_bias\"] = float(np.mean(v1) / var_exact)\n''','''    out[\"cr1\"][\"rel_bias\"] = float(np.mean(v1) / var_exact)\n    out[\"cr0\"][\"rel_bias_se\"] = float(np.std(v0, ddof=1) / np.sqrt(R) / var_exact)\n    out[\"cr1\"][\"rel_bias_se\"] = float(np.std(v1, ddof=1) / np.sqrt(R) / var_exact)\n''')\ns=s.replace('''base_cov, base_se, meta = {}, {}, {}''','''base_cov, base_se, meta, rb_se, wcb_alt = {}, {}, {}, {}, {}''')\ns=s.replace('''            relbias[k] = rb\n''','''            relbias[k] = rb\n            rb_se[k] = res[est][\"rel_bias_se\"]\n''')\ns=s.replace('''    base_se[bk] = res[\"iid\"][\"mc_se\"]\n''','''    base_se[bk] = res[\"iid\"][\"mc_se\"]\n    wcb_alt[key(\"wcb\", G, icc)] = res[\"wcb_alt\"][\"coverage\"]\n''')\ns=s.replace('''\"rel_bias_var\": relbias,\n''','''\"rel_bias_var\": relbias,\n    \"mc_se_rel_bias_var\": rb_se,\n''')\ns=s.replace('''    \"wcb_quantile_rule\"''','''    \"sensitivity_wcb_coverage_numpy_quantile\": wcb_alt,\n    \"wcb_quantile_rule\"''')\ns=s.replace('''print(\"best procedure''','''print(\"baseline iid coverage:\", base_cov)\nprint(\"WCB coverage, numpy-quantile sensitivity:\", wcb_alt)\nprint(\"best procedure''')\nopen('analysis.py','w').write(s)\nEOF\ncd .. && ~/wp29/venv/bin/python out/analysis.py | tail -4 && ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));print(r['mc_se_rel_bias_var']);print(r['nominal_cells'])\"","description":"Add bias MC SE and quantile sensitivity, rerun"}}]}}61{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"3f30a56e-b09c-4d6e-a2f6-e972af9c8ccb","timestamp":"2026-10-30T05:40:50.671Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"89b03d6a-c20e-4db7-a92b-ded8fa85ba9a","keep":18,"tail":["b25f4e903e3b07b25daf2399a1e76e23c6d5dfcb41d6e289a05cdc4b8867c1fc","615c22ec5ddb18d4837ee8d112a011e65b58a8ea33d773ec115aa7f868f45530"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"42cdefc6fa5711a156a579a7d2c481c7d718c8d7c5bf34a71e894fcdd5ea6fe1"}62{"parentUuid":"9a924665-c9e7-428d-81f9-05e32f36e99d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtLCUVT92okJKFuxW7N","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":2533,"cache_read_input_tokens":21122,"output_tokens":708,"output_tokens_details":{"thinking_tokens":142},"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":2533},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1397,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtLCD7LKEMLaa6Eo4SP","requestRef":"3f30a56e-b09c-4d6e-a2f6-e972af9c8ccb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"56f95883-d31a-4f68-a732-a01c7f0f7a73","timestamp":"2026-10-30T05:40:53.681Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}63{"parentUuid":"56f95883-d31a-4f68-a732-a01c7f0f7a73","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtLCUVT92okJKFuxW7N","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Gzr9yVgi4aA5Sp6NSiPCrA","name":"Bash","input":{"command":"cat > out/state/verify/check_bias.py <<'EOF'\n# Exact E[V_CR0]/Var(ybar) under the DGP vs Monte Carlo estimate (z-score with MC SE)\nimport json, numpy as np, pandas as pd\nres=json.load(open(\"out/results.json\")); d=pd.read_csv(\"data/design.csv\")\nfor _,r in d.iterrows():\n    n=np.array([int(x) for x in r.cluster_sizes.split(\"|\")]); G=len(n); N=n.sum(); icc=r.icc\n    gid=np.repeat(np.arange(G),n); Z=(gid[:,None]==np.arange(G)).astype(float)\n    Sig=icc*Z@Z.T+(1-icc)*np.eye(N); A=Z.T-np.outer(n,np.ones(N))/N\n    ev0=np.trace(A@Sig@A.T)/N**2; var=(icc*np.sum(n**2)+(1-icc)*N)/N**2\n    k=f\"cr0_G{G}_icc{icc:.1f}\"; mc=res[\"rel_bias_var\"][k]; se=res[\"mc_se_rel_bias_var\"][k]\n    print(k, \"exact %.4f  MC %.4f  z=%.2f\"%(ev0/var, mc, (mc-ev0/var)/se))\nEOF\n~/wp29/venv/bin/python out/state/verify/check_bias.py","description":"Compare MC bias to exact expectation"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2533,"cache_read_input_tokens":21122,"output_tokens":708,"output_tokens_details":{"thinking_tokens":142},"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":2533},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtLCD7LKEMLaa6Eo4SP","requestRef":"3f30a56e-b09c-4d6e-a2f6-e972af9c8ccb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0dff0b0b-c24f-4510-b92c-79805f1ba9c2","timestamp":"2026-10-30T05:40:57.547Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}64{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"0dff0b0b-c24f-4510-b92c-79805f1ba9c2","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}65{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}66{"parentUuid":"0dff0b0b-c24f-4510-b92c-79805f1ba9c2","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Gzr9yVgi4aA5Sp6NSiPCrA","type":"tool_result","content":"cr0_G5_icc0.0 exact 0.6641  MC 0.6616  z=-0.19\ncr0_G5_icc0.2 exact 0.4995  MC 0.5314  z=2.46\ncr0_G5_icc0.5 exact 0.4883  MC 0.4834  z=-0.42\ncr0_G10_icc0.0 exact 0.8393  MC 0.8558  z=1.40\ncr0_G10_icc0.2 exact 0.7599  MC 0.7624  z=0.20\ncr0_G10_icc0.5 exact 0.7544  MC 0.7737  z=1.37\ncr0_G30_icc0.0 exact 0.9486  MC 0.9438  z=-0.70\ncr0_G30_icc0.2 exact 0.9267  MC 0.9314  z=0.54\ncr0_G30_icc0.5 exact 0.9253  MC 0.9253  z=-0.00","is_error":false}]},"uuid":"1a05bf4c-0b80-4f94-88f8-781876c7e1f7","timestamp":"2026-10-30T05:40:57.776Z","toolUseResult":{"stdout":"cr0_G5_icc0.0 exact 0.6641  MC 0.6616  z=-0.19\ncr0_G5_icc0.2 exact 0.4995  MC 0.5314  z=2.46\ncr0_G5_icc0.5 exact 0.4883  MC 0.4834  z=-0.42\ncr0_G10_icc0.0 exact 0.8393  MC 0.8558  z=1.40\ncr0_G10_icc0.2 exact 0.7599  MC 0.7624  z=0.20\ncr0_G10_icc0.5 exact 0.7544  MC 0.7737  z=1.37\ncr0_G30_icc0.0 exact 0.9486  MC 0.9438  z=-0.70\ncr0_G30_icc0.2 exact 0.9267  MC 0.9314  z=0.54\ncr0_G30_icc0.5 exact 0.9253  MC 0.9253  z=-0.00","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"0dff0b0b-c24f-4510-b92c-79805f1ba9c2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}67{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"6a1a23296197ceca4c35d09438411730aa3c051b2a76fa32f85b79b6096cf9ba","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Gzr9yVgi4aA5Sp6NSiPCrA","name":"Bash","input":{"command":"cat > out/state/verify/check_bias.py <<'EOF'\n# Exact E[V_CR0]/Var(ybar) under the DGP vs Monte Carlo estimate (z-score with MC SE)\nimport json, numpy as np, pandas as pd\nres=json.load(open(\"out/results.json\")); d=pd.read_csv(\"data/design.csv\")\nfor _,r in d.iterrows():\n    n=np.array([int(x) for x in r.cluster_sizes.split(\"|\")]); G=len(n); N=n.sum(); icc=r.icc\n    gid=np.repeat(np.arange(G),n); Z=(gid[:,None]==np.arange(G)).astype(float)\n    Sig=icc*Z@Z.T+(1-icc)*np.eye(N); A=Z.T-np.outer(n,np.ones(N))/N\n    ev0=np.trace(A@Sig@A.T)/N**2; var=(icc*np.sum(n**2)+(1-icc)*N)/N**2\n    k=f\"cr0_G{G}_icc{icc:.1f}\"; mc=res[\"rel_bias_var\"][k]; se=res[\"mc_se_rel_bias_var\"][k]\n    print(k, \"exact %.4f  MC %.4f  z=%.2f\"%(ev0/var, mc, (mc-ev0/var)/se))\nEOF\n~/wp29/venv/bin/python out/state/verify/check_bias.py","description":"Compare MC bias to exact expectation"}}]}}68{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"bc49bf61-a11c-4030-9088-14247049b118","timestamp":"2026-10-30T05:40:57.778Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"3f30a56e-b09c-4d6e-a2f6-e972af9c8ccb","keep":20,"tail":["6a1a23296197ceca4c35d09438411730aa3c051b2a76fa32f85b79b6096cf9ba","6d47133b70008085ce97d69421f084a8499f1ef7daca668f0c0f8ffad92631ca"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b388892470da7dae4d73c37cd4a83bee02d4a5ed116e21fe11a8bc207e64d6e6"}69{"parentUuid":"1a05bf4c-0b80-4f94-88f8-781876c7e1f7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtLj7VAic3idxQ6XkZP","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":1031,"cache_read_input_tokens":23655,"output_tokens":833,"output_tokens_details":{"thinking_tokens":125},"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":1031},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":752,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtLibUmXUkAJaaSw9WS","requestRef":"bc49bf61-a11c-4030-9088-14247049b118","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1cc69938-10a8-42be-854a-fc75c1d024b9","timestamp":"2026-10-30T05:41:01.310Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}70{"parentUuid":"1cc69938-10a8-42be-854a-fc75c1d024b9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtLj7VAic3idxQ6XkZP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MBNFtybdEcaLF485bfWhjC","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && cp out/table1.csv /tmp/t1.csv && rm out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && cmp out/table1.csv /tmp/t1.csv && echo IDENTICAL; ~/wp29/venv/bin/python -c \"\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json'));t=pd.read_csv('out/table1.csv')\nprint(len(t),t.estimator.value_counts().to_dict(),len(r['coverage']),len(r['mc_se_coverage']),len(r['rel_bias_var']))\nprint('se>0',all(v>0 for v in r['mc_se_coverage'].values()),'cov in [0,1]',all(0<=v<=1 for v in r['coverage'].values()))\nprint('nfail',r['n_failure_cells']==len(r['failure_cells']),'n_analysed',r['n_analysed']==9*2000)\nprint('wcb rel_bias empty',t[t.estimator=='wcb'].rel_bias_var.isna().all())\nprint('fail recompute',sorted(k for k,v in r['coverage'].items() if v<0.9)==sorted(r['failure_cells']))\nprint('cr1/cr0 relbias ratio', set(np.round([r['rel_bias_var']['cr1'+k[3:]]/r['rel_bias_var'][k] for k in r['rel_bias_var'] if k.startswith('cr0')],6)))\nprint('hw cr1>cr0', all(t[t.estimator=='cr1'].mean_ci_halfwidth.values>t[t.estimator=='cr0'].mean_ci_halfwidth.values))\n\"","description":"Reproducibility and consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1031,"cache_read_input_tokens":23655,"output_tokens":833,"output_tokens_details":{"thinking_tokens":125},"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":1031},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtLibUmXUkAJaaSw9WS","requestRef":"bc49bf61-a11c-4030-9088-14247049b118","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"875f5dde-01c9-4148-b4cf-25d06abf1d6d","timestamp":"2026-10-30T05:41:06.358Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}71{"parentUuid":"875f5dde-01c9-4148-b4cf-25d06abf1d6d","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MBNFtybdEcaLF485bfWhjC","type":"tool_result","content":"IDENTICAL\n27 {'cr0': 9, 'cr1': 9, 'wcb': 9} 27 27 18\nse>0 True cov in [0,1] True\nnfail True n_analysed True\nwcb rel_bias empty True\nfail recompute True\ncr1/cr0 relbias ratio {np.float64(1.25), np.float64(1.034483), np.float64(1.111111)}\nhw cr1>cr0 True","is_error":false}]},"uuid":"22545fc1-e0f7-46d5-9190-e8f39cfeb33d","timestamp":"2026-10-30T05:41:08.966Z","toolUseResult":{"stdout":"IDENTICAL\n27 {'cr0': 9, 'cr1': 9, 'wcb': 9} 27 27 18\nse>0 True cov in [0,1] True\nnfail True n_analysed True\nwcb rel_bias empty True\nfail recompute True\ncr1/cr0 relbias ratio {np.float64(1.25), np.float64(1.034483), np.float64(1.111111)}\nhw cr1>cr0 True","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"875f5dde-01c9-4148-b4cf-25d06abf1d6d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}72{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"44698f07a5d4160ac20471c2a26eeb9457578559892f7a649f8dfe839b18d69c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01MBNFtybdEcaLF485bfWhjC","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && cp out/table1.csv /tmp/t1.csv && rm out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && cmp out/table1.csv /tmp/t1.csv && echo IDENTICAL; ~/wp29/venv/bin/python -c \"\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json'));t=pd.read_csv('out/table1.csv')\nprint(len(t),t.estimator.value_counts().to_dict(),len(r['coverage']),len(r['mc_se_coverage']),len(r['rel_bias_var']))\nprint('se>0',all(v>0 for v in r['mc_se_coverage'].values()),'cov in [0,1]',all(0<=v<=1 for v in r['coverage'].values()))\nprint('nfail',r['n_failure_cells']==len(r['failure_cells']),'n_analysed',r['n_analysed']==9*2000)\nprint('wcb rel_bias empty',t[t.estimator=='wcb'].rel_bias_var.isna().all())\nprint('fail recompute',sorted(k for k,v in r['coverage'].items() if v<0.9)==sorted(r['failure_cells']))\nprint('cr1/cr0 relbias ratio', set(np.round([r['rel_bias_var']['cr1'+k[3:]]/r['rel_bias_var'][k] for k in r['rel_bias_var'] if k.startswith('cr0')],6)))\nprint('hw cr1>cr0', all(t[t.estimator=='cr1'].mean_ci_halfwidth.values>t[t.estimator=='cr0'].mean_ci_halfwidth.values))\n\"","description":"Reproducibility and consistency checks"}}]}}73{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"817e72bb-3d45-48ba-9bea-bc5d7213d2c8","timestamp":"2026-10-30T05:41:08.969Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"bc49bf61-a11c-4030-9088-14247049b118","keep":22,"tail":["44698f07a5d4160ac20471c2a26eeb9457578559892f7a649f8dfe839b18d69c","3159a2d901f97e81763dd3f612683759b9510e0256c7a8e441109f92c13abf66"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1bad6695d1d8381e4c48abcffb5238bdc7d7e8d32a6005c0dd389d5bc17206e2"}74{"parentUuid":"22545fc1-e0f7-46d5-9190-e8f39cfeb33d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMYkQuyMmDRBXEJtX4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PhBcvMVsXEzW3gdkpCPyqc","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run of out/analysis.py (results.json, table1.csv, figure1.png deleted first) reproduces byte-identical results.json and table1.csv | PASS |\n| 2 | Runtime | ~2 s for full grid (limit 600 s) — PASS |\n| 3 | table1.csv has 27 rows (9 per estimator); coverage/mc_se objects have 27 keys; rel_bias_var 18 keys; wcb rel_bias_var empty | PASS |\n| 4 | All MC SEs > 0; all coverages in [0,1] | PASS |\n| 5 | n_failure_cells == len(failure_cells); failure set recomputed from coverage < 0.90 matches | PASS |\n| 6 | n_analysed = 9 x 2000 = 18000; exclusion ledger 9 - 0 = 9 cells | PASS |\n| 7 | rel_bias(CR1)/rel_bias(CR0) = G/(G-1) exactly (1.25, 1.1111, 1.0345) | PASS |\n| 8 | CR1 mean half-width > CR0 in every cell | PASS |\n| 9 | Vectorised wild-bootstrap t* vs brute-force construction of y* (out/state/verify/check_wcb.py): max abs diff 1.1e-14 | PASS |\n| 10 | MC Var(ybar)/exact Var(ybar) per cell: 0.934–1.065 (sampling SE of ratio ≈ 0.032 for R=2000) — consistent with DGP, largest deviations ≈ 2 SE (C4 0.934, C2 1.065) | PASS (noted) |\n| 11 | MC rel_bias(CR0) vs exact analytic E[V_CR0]/Var(ybar) (check_bias.py): |z| ≤ 1.4 in 8/9 cells; C2 z = 2.46 (MC 0.531 vs exact 0.500) | PASS with note: one 2.5-SE deviation among 9 cells, consistent with C2's above-average realised Var(ybar); MC estimates otherwise match theory |\n| 12 | Baseline (naive iid CI) coverage ≈ 0.94–0.96 at ICC=0 and 0.29–0.49 at ICC>0, as expected; all cluster-robust procedures improve on it when ICC>0 | PASS |\n| 13 | WCB quantile-rule sensitivity (numpy linear quantile vs 380th order statistic): coverage changes ≤ 0.003; failure set unchanged | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 recorded and matched bundle.json\",\"schema/missing/duplicates checked\",\"len(cluster_sizes)==G and sum==N for all rows\",\"exclusions.csv written (0 removed)\"],\"notes\":\"no availability violations\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive iid CI baseline computed under same coverage rule -> baseline_iid_coverage, baseline_iid_mc_se\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/design.csv\",\"per-cell seeds from design.csv, draw order documented\",\"writes results.json, table1.csv, figure1.png\"],\"notes\":\"WCB critical value = 380th order statistic of 399 |t*|\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean rerun byte-identical (checks.md #1)\",\"internal consistency checks #2-#13 in checks.md\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2/P3 passed: baseline iid CI + full simulation in analysis.py (2 s). P4 checks recorded in checks.md.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Record checks and run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":984,"cache_read_input_tokens":24686,"output_tokens":1496,"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":984},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtMYS4VMiqpW6FRQNAY","requestRef":"817e72bb-3d45-48ba-9bea-bc5d7213d2c8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"56b494fd-11c9-4839-9f3b-53501e123c99","timestamp":"2026-10-30T05:41:22.423Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}75{"parentUuid":"56b494fd-11c9-4839-9f3b-53501e123c99","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 34 checks failed)\n  [ok] file:out/results.json: present\n  [FAIL] file:out/report.md: missing or empty\n  [ok] file:out/analysis.py: present\n  [FAIL] file:out/claims.json: missing or empty\n  [ok] file:out/table1.csv: present\n  [ok] file:out/figure1.png: present\n  [ok] results_json: parsed\n  [ok] key:task_id: ok\n  [ok] key:R: ok\n  [ok] key:B: ok\n  [ok] key:n_cells: ok\n  [ok] key:coverage: ok\n  [ok] key:mc_se_coverage: ok\n  [ok] key:rel_bias_var: ok\n  [ok] key:failure_cells: ok\n  [ok] key:n_failure_cells: ok\n  [ok] key:nominal_cells: ok\n  [ok] key:best_procedure_small_G: ok\n  [ok] key:feasibility: ok\n  [ok] key:feasibility_reason: ok\n  [ok] key:data_issues: ok\n  [ok] key:n_input_rows: ok\n  [ok] key:n_analysed: ok\n  [ok] key:random_seed: ok\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n  [ok] exclusion_ledger: 1 steps consistent\n  [ok] reproducibility: regenerated in 2.4s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0024/out/state/gate_receipts/20261030T054124.839175Z.json","is_error":true,"tool_use_id":"toolu_01PhBcvMVsXEzW3gdkpCPyqc"}]},"uuid":"ba51685a-eed5-46d7-ba4d-f587d49b77ed","timestamp":"2026-10-30T05:41:24.844Z","toolUseResult":"Error: Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 34 checks failed)\n  [ok] file:out/results.json: present\n  [FAIL] file:out/report.md: missing or empty\n  [ok] file:out/analysis.py: present\n  [FAIL] file:out/claims.json: missing or empty\n  [ok] file:out/table1.csv: present\n  [ok] file:out/figure1.png: present\n  [ok] results_json: parsed\n  [ok] key:task_id: ok\n  [ok] key:R: ok\n  [ok] key:B: ok\n  [ok] key:n_cells: ok\n  [ok] key:coverage: ok\n  [ok] key:mc_se_coverage: ok\n  [ok] key:rel_bias_var: ok\n  [ok] key:failure_cells: ok\n  [ok] key:n_failure_cells: ok\n  [ok] key:nominal_cells: ok\n  [ok] key:best_procedure_small_G: ok\n  [ok] key:feasibility: ok\n  [ok] key:feasibility_reason: ok\n  [ok] key:data_issues: ok\n  [ok] key:n_input_rows: ok\n  [ok] key:n_analysed: ok\n  [ok] key:random_seed: ok\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n  [ok] exclusion_ledger: 1 steps consistent\n  [ok] reproducibility: regenerated in 2.4s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0024/out/state/gate_receipts/20261030T054124.839175Z.json","sandboxed":false,"sourceToolAssistantUUID":"56b494fd-11c9-4839-9f3b-53501e123c99","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}76{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"6106cdb5ac89fea4099f9758db374353b5bbd339df7a7a17bdf797c685b0c567","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01PhBcvMVsXEzW3gdkpCPyqc","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run of out/analysis.py (results.json, table1.csv, figure1.png deleted first) reproduces byte-identical results.json and table1.csv | PASS |\n| 2 | Runtime | ~2 s for full grid (limit 600 s) — PASS |\n| 3 | table1.csv has 27 rows (9 per estimator); coverage/mc_se objects have 27 keys; rel_bias_var 18 keys; wcb rel_bias_var empty | PASS |\n| 4 | All MC SEs > 0; all coverages in [0,1] | PASS |\n| 5 | n_failure_cells == len(failure_cells); failure set recomputed from coverage < 0.90 matches | PASS |\n| 6 | n_analysed = 9 x 2000 = 18000; exclusion ledger 9 - 0 = 9 cells | PASS |\n| 7 | rel_bias(CR1)/rel_bias(CR0) = G/(G-1) exactly (1.25, 1.1111, 1.0345) | PASS |\n| 8 | CR1 mean half-width > CR0 in every cell | PASS |\n| 9 | Vectorised wild-bootstrap t* vs brute-force construction of y* (out/state/verify/check_wcb.py): max abs diff 1.1e-14 | PASS |\n| 10 | MC Var(ybar)/exact Var(ybar) per cell: 0.934–1.065 (sampling SE of ratio ≈ 0.032 for R=2000) — consistent with DGP, largest deviations ≈ 2 SE (C4 0.934, C2 1.065) | PASS (noted) |\n| 11 | MC rel_bias(CR0) vs exact analytic E[V_CR0]/Var(ybar) (check_bias.py): |z| ≤ 1.4 in 8/9 cells; C2 z = 2.46 (MC 0.531 vs exact 0.500) | PASS with note: one 2.5-SE deviation among 9 cells, consistent with C2's above-average realised Var(ybar); MC estimates otherwise match theory |\n| 12 | Baseline (naive iid CI) coverage ≈ 0.94–0.96 at ICC=0 and 0.29–0.49 at ICC>0, as expected; all cluster-robust procedures improve on it when ICC>0 | PASS |\n| 13 | WCB quantile-rule sensitivity (numpy linear quantile vs 380th order statistic): coverage changes ≤ 0.003; failure set unchanged | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 recorded and matched bundle.json\",\"schema/missing/duplicates checked\",\"len(cluster_sizes)==G and sum==N for all rows\",\"exclusions.csv written (0 removed)\"],\"notes\":\"no availability violations\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive iid CI baseline computed under same coverage rule -> baseline_iid_coverage, baseline_iid_mc_se\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/design.csv\",\"per-cell seeds from design.csv, draw order documented\",\"writes results.json, table1.csv, figure1.png\"],\"notes\":\"WCB critical value = 380th order statistic of 399 |t*|\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean rerun byte-identical (checks.md #1)\",\"internal consistency checks #2-#13 in checks.md\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2/P3 passed: baseline iid CI + full simulation in analysis.py (2 s). P4 checks recorded in checks.md.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Record checks and run gate"}}]}}77{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"6ef86ace-b368-4c15-b37f-09efc8cb4d09","timestamp":"2026-10-30T05:41:24.847Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"817e72bb-3d45-48ba-9bea-bc5d7213d2c8","keep":24,"tail":["6106cdb5ac89fea4099f9758db374353b5bbd339df7a7a17bdf797c685b0c567","27ebb020d34c7df951b36e433d151e76048cec1d7087a772cf148733b0f79976"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"173c7ea49622af121001c8e5ae15fe40f4f794fa24b94d093b83dc2765cb169b"}78{"type":"tools-used","tools":["Bash","Read"],"sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}79{"parentUuid":"ba51685a-eed5-46d7-ba4d-f587d49b77ed","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNib3GPJYYVvJ4W6Sj","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":2220,"cache_read_input_tokens":25670,"output_tokens":155,"output_tokens_details":{"thinking_tokens":74},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2220},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":490,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtNiJfmx6jZj2ELNpQ3","requestRef":"6ef86ace-b368-4c15-b37f-09efc8cb4d09","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"78669f7c-cefc-4a56-92d9-71da1cbef39a","timestamp":"2026-10-30T05:41:26.964Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}80{"parentUuid":"78669f7c-cefc-4a56-92d9-71da1cbef39a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNib3GPJYYVvJ4W6Sj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016XD3yKGxeCBGiLWh8zS2gK","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0024/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":2220,"cache_read_input_tokens":25670,"output_tokens":155,"output_tokens_details":{"thinking_tokens":74},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2220},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtNiJfmx6jZj2ELNpQ3","requestRef":"6ef86ace-b368-4c15-b37f-09efc8cb4d09","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"27a0e45b-89bf-444e-ab13-4c2e90c28bfb","timestamp":"2026-10-30T05:41:27.411Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}81{"parentUuid":"27a0e45b-89bf-444e-ab13-4c2e90c28bfb","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016XD3yKGxeCBGiLWh8zS2gK","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"c7064f12-9cc7-4a5c-ae44-ab17f70a8952","timestamp":"2026-10-30T05:41:27.437Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":85467,"dimensions":{"originalWidth":1690,"originalHeight":546,"displayWidth":1690,"displayHeight":546}}},"sourceToolAssistantUUID":"27a0e45b-89bf-444e-ab13-4c2e90c28bfb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}82{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"a3fb81c34d61ca9c80c099c8d2951ffbf3c49683d6dbcd39755d90b928571158","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016XD3yKGxeCBGiLWh8zS2gK","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0024/out/figure1.png"}}]}}83{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"e6050c7f-fe45-416f-95cb-3b7d4b251f49","timestamp":"2026-10-30T05:41:27.445Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"6ef86ace-b368-4c15-b37f-09efc8cb4d09","keep":26,"tail":["a3fb81c34d61ca9c80c099c8d2951ffbf3c49683d6dbcd39755d90b928571158","298656261c5c1b9cf7179cb00e7f98a7ebe406ce735bcbf1d63435ba05e93a8e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8ee64259402bac31129cf727360fc317c6081e40b66bbdd27ed7123df959b000"}84{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"c7064f12-9cc7-4a5c-ae44-ab17f70a8952","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}85{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}86{"parentUuid":"c7064f12-9cc7-4a5c-ae44-ab17f70a8952","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNui21f6zALFSy5LD3","type":"message","role":"assistant","content":[{"type":"text","text":"Minor fix: suppress minor log ticks."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1394,"cache_read_input_tokens":27890,"output_tokens":569,"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":1394},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtNuSQ2AZNdFp8GSs7j","requestRef":"e6050c7f-fe45-416f-95cb-3b7d4b251f49","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c594c791-c047-4bd9-a7a0-c0bb29e9bb2f","timestamp":"2026-10-30T05:41:29.150Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}87{"parentUuid":"c594c791-c047-4bd9-a7a0-c0bb29e9bb2f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNui21f6zALFSy5LD3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01W4jLVb2iwPA8QnY6EDRYao","name":"Bash","input":{"command":"sed -i '' 's/ax.set_xscale(\"log\"); ax.set_xticks(Gs)/ax.set_xscale(\"log\"); ax.minorticks_off(); ax.set_xticks(Gs)/' out/analysis.py && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo same\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"clean rerun byte-identical (checks.md #1)\",\"internal consistency checks #2-#13 in checks.md all PASS\",\"gate run receipt out/state/gate_receipts/20261030T054124.839175Z.json: all results-key, exclusion-ledger and reproducibility checks ok; remaining failures are P5 deliverables (report.md, claims.json, terminal phases)\"],\"notes\":\"figure tick cosmetic fix after gate; results.json unchanged (cmp)\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P4 passed (gate receipt 20261030T054124; only P5-owned items failing). Starting P5.\" >> out/state/log.md","description":"Fix ticks, confirm results unchanged, update ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1394,"cache_read_input_tokens":27890,"output_tokens":569,"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":1394},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtNuSQ2AZNdFp8GSs7j","requestRef":"e6050c7f-fe45-416f-95cb-3b7d4b251f49","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"366097a3-7526-4f51-a1bf-c138fcbc9142","timestamp":"2026-10-30T05:41:33.267Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}88{"parentUuid":"366097a3-7526-4f51-a1bf-c138fcbc9142","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01W4jLVb2iwPA8QnY6EDRYao","type":"tool_result","content":"same","is_error":false}]},"uuid":"7ecb165e-c043-44b4-9e7b-5d2956b6b3de","timestamp":"2026-10-30T05:41:35.603Z","toolUseResult":{"stdout":"same","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"366097a3-7526-4f51-a1bf-c138fcbc9142","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}89{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"e9d5265e3299c453892b1ca334ca87b006d037ec310e18a162080e5029688f4f","message":{"role":"assistant","content":[{"type":"text","text":"Minor fix: suppress minor log ticks."},{"type":"tool_use","id":"toolu_01W4jLVb2iwPA8QnY6EDRYao","name":"Bash","input":{"command":"sed -i '' 's/ax.set_xscale(\"log\"); ax.set_xticks(Gs)/ax.set_xscale(\"log\"); ax.minorticks_off(); ax.set_xticks(Gs)/' out/analysis.py && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo same\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"clean rerun byte-identical (checks.md #1)\",\"internal consistency checks #2-#13 in checks.md all PASS\",\"gate run receipt out/state/gate_receipts/20261030T054124.839175Z.json: all results-key, exclusion-ledger and reproducibility checks ok; remaining failures are P5 deliverables (report.md, claims.json, terminal phases)\"],\"notes\":\"figure tick cosmetic fix after gate; results.json unchanged (cmp)\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P4 passed (gate receipt 20261030T054124; only P5-owned items failing). Starting P5.\" >> out/state/log.md","description":"Fix ticks, confirm results unchanged, update ledger"}}]}}90{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"6e9462ea-34d0-42c1-9fce-f52099fd96d1","timestamp":"2026-10-30T05:41:35.606Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"e6050c7f-fe45-416f-95cb-3b7d4b251f49","keep":28,"tail":["e9d5265e3299c453892b1ca334ca87b006d037ec310e18a162080e5029688f4f","2259e154c56b1fa9813695124427aefd390e46da675d8c1db37151a908a9d28c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"54a59ad62c7cb71e9f8ebfd4bbfaa45ca77ea0e36ea4b58b124cefd6e578e97e"}91{"parentUuid":"7ecb165e-c043-44b4-9e7b-5d2956b6b3de","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPWbVeMNdffnL65tdf","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":575,"cache_read_input_tokens":29284,"output_tokens":5257,"output_tokens_details":{"thinking_tokens":31},"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":575},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":411,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtPWK8NwMVE3ECCikre","requestRef":"6e9462ea-34d0-42c1-9fce-f52099fd96d1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e389924d-19fb-4d3b-a5e9-41219a83db49","timestamp":"2026-10-30T05:41:38.069Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}92{"parentUuid":"e389924d-19fb-4d3b-a5e9-41219a83db49","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPWbVeMNdffnL65tdf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ANrJ1jMCAMdvA3dD3EWPja","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t intervals for a mean with few clusters\n\nExecutable note: every number below is produced by `~/wp29/venv/bin/python out/analysis.py` (≈2 s), which writes `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only. Keys of `out/results.json` are cited in brackets.\n\n## Question\nWith N observations in G clusters (G ∈ {5, 10, 30}) and intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}, how close to 95% is the actual coverage of three cluster-robust intervals for the population mean μ (estimated by ȳ): CR0 with a normal critical value, CR1 with a t(G−1) critical value, and the unrestricted Rademacher wild cluster bootstrap-t (WCB)? We also estimate the relative bias E[V̂]/Var(ȳ) of the CR0/CR1 variance estimators, the Monte Carlo (MC) SE of each coverage, and the failure regimes (coverage < 0.90).\n\n## Data and exclusions\nNo observed data. The only input is `data/design.csv` (9 rows [`n_input_rows`], SHA-256 f4ff004e…; audit in `out/state/data_audit.md`): one row per cell with the cluster sizes (pattern 8, 16, 32, 64 repeated; N = 128, 264, 864), R = 2000 [`R`], B = 399 [`B`], and a per-cell seed (C1 seed 20261101 [`random_seed`]). All rows passed consistency checks (G sizes listed, sizes summing to N), so no cell was excluded (`out/exclusions.csv`: 9 → 9). 9 cells [`n_cells`] × 2000 replications = 18000 simulated samples [`n_analysed`]. The design issues found [`data_issues`]: (i) at G = 5 Rademacher weights have only 32 distinct vectors (16 distinct |t*| values), so the WCB critical value is coarse; (ii) at ICC = 0 the cluster effect is degenerate (zero variance). Neither changed the procedures. Feasibility: complete [`feasibility`].\n\n## Method\nDGP per replication: y_ig = μ + u_g + e_ig, u_g ~ N(0, ICC), e_ig ~ N(0, 1−ICC), μ = 0. Exact Var(ȳ) = [ICC·Σn_g² + (1−ICC)N]/N². For each cell, `numpy.random.default_rng(seed)`; per replication draws in the order u (G), e (N), Rademacher weight matrix (B × G).\n- CR0: V̂ = Σ_g(Σ_i ê_ig)²/N², interval ȳ ± 1.96√V̂.\n- CR1: V̂_CR1 = G/(G−1)·V̂_CR0, interval ȳ ± t_{0.975,G−1}√V̂_CR1.\n- WCB: y* = ȳ + w_g ê_ig, t*_b = (ȳ* − ȳ)/√V̂*_CR1 (V̂* recomputed on the bootstrap sample), q = 0.95 empirical quantile of |t*|, interval ȳ ± q√V̂_CR1. Vectorised via cluster residual sums; checked against a brute-force construction of y* (max difference 1e-14). Empirical-quantile convention: the ⌈(B+1)·0.95⌉ = 380th order statistic of the 399 |t*| values (the standard convention for B = 399); the numpy linear-interpolation quantile is reported as a sensitivity [`sensitivity_wcb_coverage_numpy_quantile`].\n- Coverage = share of R intervals containing μ; MC SE = √(p̂(1−p̂)/R); relative bias = mean(V̂)/exact Var(ȳ), with MC SE sd(V̂)/(√R·Var(ȳ)) [`mc_se_rel_bias_var`].\n- Baseline (P2): the naive i.i.d. interval ȳ ± 1.96·s/√N that ignores clustering [`baseline_iid_coverage`].\n\n## Results\nFull table: `out/table1.csv`; figure: `out/figure1.png` (coverage vs G, one panel per ICC, ±1.96 MC SE bars, lines at 0.95 and 0.90).\n\nCoverage [`coverage`] (MC SE ≈ 0.005–0.010 [`mc_se_coverage`]):\n\n| G | ICC | CR0 | CR1 | WCB | naive iid baseline |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.781 | 0.912 | 0.858 | 0.941 |\n| 5 | 0.2 | 0.721 | 0.885 | 0.855 | 0.460 |\n| 5 | 0.5 | 0.717 | 0.876 | 0.851 | 0.287 |\n| 10 | 0.0 | 0.897 | 0.944 | 0.938 | 0.957 |\n| 10 | 0.2 | 0.857 | 0.916 | 0.933 | 0.488 |\n| 10 | 0.5 | 0.853 | 0.907 | 0.935 | 0.313 |\n| 30 | 0.0 | 0.928 | 0.940 | 0.945 | 0.952 |\n| 30 | 0.2 | 0.921 | 0.935 | 0.947 | 0.485 |\n| 30 | 0.5 | 0.917 | 0.930 | 0.944 | 0.299 |\n\n1. **Baseline.** Ignoring clustering gives near-nominal coverage only at ICC = 0 and coverage of 0.29–0.49 when ICC > 0 [`baseline_iid_coverage`]; all three cluster-robust intervals do much better whenever ICC > 0.\n2. **Failure regimes.** 11 of 27 pairs have coverage < 0.90 [`n_failure_cells`, `failure_cells`]: CR0 at G = 5 and G = 10 (all ICC; 0.717–0.897), CR1 at G = 5 with ICC = 0.2 and 0.5 (0.885, 0.876), and WCB at G = 5 (all ICC; 0.851–0.858). No pair fails at G = 30.\n3. **Variance bias.** CR0 underestimates Var(ȳ) strongly with few clusters: E[V̂]/Var(ȳ) = 0.48–0.66 at G = 5, 0.76–0.86 at G = 10, 0.93–0.94 at G = 30 [`rel_bias_var`]. The G/(G−1) factor of CR1 reduces but does not remove the bias at G = 5 (0.60–0.83); at G = 30 CR1 is within 0.96–0.98. The downward bias is larger with ICC > 0, because the unequal cluster sizes make the large cluster (n = 64) carry much of the variance and its residual sum is shrunk most by centring on ȳ.\n4. **Comparison of procedures.** At G = 5, CR1 has the highest average coverage (0.891 vs WCB 0.854 and CR0 0.740) [`best_procedure_small_G`, `mean_coverage_G5`]. At G = 10 and 30 with ICC > 0, WCB is closest to nominal (0.933–0.947). WCB intervals at G = 5 are much wider on average than CR1 (`mean_ci_halfwidth` in table1.csv, e.g. 1.39 vs 0.79 at ICC = 0.5) yet cover less often, which points to an unstable, data-dependent critical value when only 16 distinct |t*| values exist.\n5. **Consistent with nominal** (|p̂ − 0.95| ≤ 2 MC SE): only 5 of 27 pairs [`nominal_cells`]: CR1 at (G=10, ICC=0) and (G=30, ICC=0), and WCB at G = 30 for every ICC. CR0 is never consistent with nominal, not even at G = 30.\n\n## Uncertainty\nEach coverage estimate is a binomial proportion with R = 2000; its MC SE [`mc_se_coverage`] ranges from about 0.005 (coverage near 0.95) to 0.010 (coverage near 0.72), so a 95% MC interval is about ±0.01–0.02. Pairs near the 0.90 threshold are therefore classified with limited confidence: CR0 at (G=10, ICC=0) = 0.8965 (SE 0.0068), CR1 at (G=5, ICC=0) = 0.9115 (SE 0.0064) and CR1 at (G=5, ICC=0.2) = 0.8845 (SE 0.0071) all lie within 2 MC SE of 0.90, so their failure/non-failure label could flip with another seed. The \"nominal-consistent\" label is a 2-SE screen applied to 27 pairs without multiplicity adjustment, so it is not a formal test. Classifications far from the boundaries (CR0 at G = 5, WCB at G = 5, everything at G = 30 vs 0.90) are robust. The relative-bias estimates have MC SEs of 0.007–0.016 [`mc_se_rel_bias_var`]. As a check, the MC relative bias of CR0 was compared with its exact analytic expectation (verification script in `out/state/verify/`): |z| ≤ 1.4 in 8 of 9 cells and z = 2.46 in C2 (G=5, ICC=0.2: MC 0.531 vs exact 0.500), a deviation that fits the somewhat large realised variance of ȳ in that cell; the conclusions about bias do not depend on it. The WCB critical value carries its own bootstrap noise (B = 399), which is part of the procedure's coverage. Switching to numpy's interpolated quantile changes WCB coverage by at most 0.003 and leaves the failure set unchanged [`sensitivity_wcb_coverage_numpy_quantile`]. Seeds are fixed, so re-running gives identical numbers; a different seed would give MC variation of the size of these SEs.\n\n## Limitations and open issues\n- **Distributions:** only Gaussian cluster effects and errors. Skewed or heavy-tailed u_g/e_ig, which usually hurt few-cluster inference more, are not covered.\n- **Heterogeneity:** only one fixed unequal size pattern (8/16/32/64) and homoskedastic, equal ICC across clusters. Cluster-size-dependent effects, heteroskedasticity across clusters and informative cluster sizes are not studied. Results may depend on the size pattern (e.g. the dominant 64-observation cluster at G = 5).\n- **Regressors:** only the mean (intercept-only model) is studied. Regression slopes, leverage from treated clusters and few treated clusters are outside the design.\n- **Other weights / variants:** only Rademacher weights with the unrestricted (non-null-imposed) WCB-t were studied. Webb six-point or Mammen weights, the restricted WCR bootstrap, full enumeration of the 32 sign vectors at G = 5, CR2/CR3 (bias-reduced linearisation) and Satterthwaite/Bell–McCaffrey degrees of freedom were not evaluated. The G = 5 WCB results should not be generalised to those variants.\n- The grid covers only G ∈ {5, 10, 30} and ICC ∈ {0, 0.2, 0.5}; the transition between G = 10 and 30 is not resolved.\n- Interval length was summarised only by the mean half-width; the WCB half-width distribution at G = 5 (which seems heavy-tailed) was not analysed further.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"11 of 27 (procedure, cell) pairs have coverage below 0.90: CR0 at G=5 and G=10 for all ICC, CR1 at G=5 with ICC 0.2 and 0.5, and WCB at G=5 for all ICC; no pair fails at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"CR0 (G=10, ICC=0), CR1 (G=5, ICC=0) and CR1 (G=5, ICC=0.2) are within 2 MC SE of the 0.90 threshold; their labels are not robust to MC error.\"},\n {\"id\":\"C2\",\"text\":\"CR0 underestimates Var(ybar) with few clusters (E[V]/Var = 0.48-0.66 at G=5, 0.76-0.86 at G=10, 0.93-0.94 at G=30); the CR1 correction reduces but does not remove the bias at G=5.\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\"],\"status\":\"supported\",\"caveat\":\"MC SE 0.007-0.016; confirmed against exact analytic expectation except one 2.5-SE deviation (C2).\"},\n {\"id\":\"C3\",\"text\":\"At G=5, CR1 has the highest average coverage (0.891) ahead of WCB (0.854) and CR0 (0.740).\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_G5\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Specific to Rademacher unrestricted WCB-t and this cluster-size pattern.\"},\n {\"id\":\"C4\",\"text\":\"For G=10 and G=30 with ICC>0, WCB coverage (0.933-0.947) is closest to nominal; WCB is consistent with nominal coverage at G=30 for every ICC.\",\"results_keys\":[\"coverage\",\"nominal_cells\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Nominal-consistency is a 2-SE screen without multiplicity adjustment.\"},\n {\"id\":\"C5\",\"text\":\"Only 5 of 27 pairs are consistent with nominal 95% coverage; CR0 is never consistent with nominal, even at G=30.\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE screen with R=2000.\"},\n {\"id\":\"C6\",\"text\":\"The naive iid interval that ignores clustering covers only 0.29-0.49 when ICC>0, far below all cluster-robust procedures.\",\"results_keys\":[\"baseline_iid_coverage\",\"baseline_iid_mc_se\"],\"status\":\"supported\",\"caveat\":\"Baseline only; not a required estimand.\"},\n {\"id\":\"C7\",\"text\":\"WCB coverage is insensitive to the empirical-quantile convention (changes of at most 0.003, failure set unchanged).\",\"results_keys\":[\"sensitivity_wcb_coverage_numpy_quantile\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Only two quantile conventions compared.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;r=json.load(open('out/results.json'));print(r['mean_coverage_G5'])\"","description":"Write report and claims ledger"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":575,"cache_read_input_tokens":29284,"output_tokens":5257,"output_tokens_details":{"thinking_tokens":31},"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":575},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtPWK8NwMVE3ECCikre","requestRef":"6e9462ea-34d0-42c1-9fce-f52099fd96d1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5db8ac6b-aac5-4a93-bea9-b9d8b95b8096","timestamp":"2026-10-30T05:42:18.610Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}93{"parentUuid":"5db8ac6b-aac5-4a93-bea9-b9d8b95b8096","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ANrJ1jMCAMdvA3dD3EWPja","type":"tool_result","content":"{'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}","is_error":false}]},"uuid":"33194799-c869-4f93-ba2c-32dbb27ad639","timestamp":"2026-10-30T05:42:18.684Z","toolUseResult":{"stdout":"{'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5db8ac6b-aac5-4a93-bea9-b9d8b95b8096","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}94{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"17dab7ee3b9a97f53fc656f7d8e40d70d06f8087ca933e597e77194826cd9fbe","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01ANrJ1jMCAMdvA3dD3EWPja","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t intervals for a mean with few clusters\n\nExecutable note: every number below is produced by `~/wp29/venv/bin/python out/analysis.py` (≈2 s), which writes `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only. Keys of `out/results.json` are cited in brackets.\n\n## Question\nWith N observations in G clusters (G ∈ {5, 10, 30}) and intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}, how close to 95% is the actual coverage of three cluster-robust intervals for the population mean μ (estimated by ȳ): CR0 with a normal critical value, CR1 with a t(G−1) critical value, and the unrestricted Rademacher wild cluster bootstrap-t (WCB)? We also estimate the relative bias E[V̂]/Var(ȳ) of the CR0/CR1 variance estimators, the Monte Carlo (MC) SE of each coverage, and the failure regimes (coverage < 0.90).\n\n## Data and exclusions\nNo observed data. The only input is `data/design.csv` (9 rows [`n_input_rows`], SHA-256 f4ff004e…; audit in `out/state/data_audit.md`): one row per cell with the cluster sizes (pattern 8, 16, 32, 64 repeated; N = 128, 264, 864), R = 2000 [`R`], B = 399 [`B`], and a per-cell seed (C1 seed 20261101 [`random_seed`]). All rows passed consistency checks (G sizes listed, sizes summing to N), so no cell was excluded (`out/exclusions.csv`: 9 → 9). 9 cells [`n_cells`] × 2000 replications = 18000 simulated samples [`n_analysed`]. The design issues found [`data_issues`]: (i) at G = 5 Rademacher weights have only 32 distinct vectors (16 distinct |t*| values), so the WCB critical value is coarse; (ii) at ICC = 0 the cluster effect is degenerate (zero variance). Neither changed the procedures. Feasibility: complete [`feasibility`].\n\n## Method\nDGP per replication: y_ig = μ + u_g + e_ig, u_g ~ N(0, ICC), e_ig ~ N(0, 1−ICC), μ = 0. Exact Var(ȳ) = [ICC·Σn_g² + (1−ICC)N]/N². For each cell, `numpy.random.default_rng(seed)`; per replication draws in the order u (G), e (N), Rademacher weight matrix (B × G).\n- CR0: V̂ = Σ_g(Σ_i ê_ig)²/N², interval ȳ ± 1.96√V̂.\n- CR1: V̂_CR1 = G/(G−1)·V̂_CR0, interval ȳ ± t_{0.975,G−1}√V̂_CR1.\n- WCB: y* = ȳ + w_g ê_ig, t*_b = (ȳ* − ȳ)/√V̂*_CR1 (V̂* recomputed on the bootstrap sample), q = 0.95 empirical quantile of |t*|, interval ȳ ± q√V̂_CR1. Vectorised via cluster residual sums; checked against a brute-force construction of y* (max difference 1e-14). Empirical-quantile convention: the ⌈(B+1)·0.95⌉ = 380th order statistic of the 399 |t*| values (the standard convention for B = 399); the numpy linear-interpolation quantile is reported as a sensitivity [`sensitivity_wcb_coverage_numpy_quantile`].\n- Coverage = share of R intervals containing μ; MC SE = √(p̂(1−p̂)/R); relative bias = mean(V̂)/exact Var(ȳ), with MC SE sd(V̂)/(√R·Var(ȳ)) [`mc_se_rel_bias_var`].\n- Baseline (P2): the naive i.i.d. interval ȳ ± 1.96·s/√N that ignores clustering [`baseline_iid_coverage`].\n\n## Results\nFull table: `out/table1.csv`; figure: `out/figure1.png` (coverage vs G, one panel per ICC, ±1.96 MC SE bars, lines at 0.95 and 0.90).\n\nCoverage [`coverage`] (MC SE ≈ 0.005–0.010 [`mc_se_coverage`]):\n\n| G | ICC | CR0 | CR1 | WCB | naive iid baseline |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.781 | 0.912 | 0.858 | 0.941 |\n| 5 | 0.2 | 0.721 | 0.885 | 0.855 | 0.460 |\n| 5 | 0.5 | 0.717 | 0.876 | 0.851 | 0.287 |\n| 10 | 0.0 | 0.897 | 0.944 | 0.938 | 0.957 |\n| 10 | 0.2 | 0.857 | 0.916 | 0.933 | 0.488 |\n| 10 | 0.5 | 0.853 | 0.907 | 0.935 | 0.313 |\n| 30 | 0.0 | 0.928 | 0.940 | 0.945 | 0.952 |\n| 30 | 0.2 | 0.921 | 0.935 | 0.947 | 0.485 |\n| 30 | 0.5 | 0.917 | 0.930 | 0.944 | 0.299 |\n\n1. **Baseline.** Ignoring clustering gives near-nominal coverage only at ICC = 0 and coverage of 0.29–0.49 when ICC > 0 [`baseline_iid_coverage`]; all three cluster-robust intervals do much better whenever ICC > 0.\n2. **Failure regimes.** 11 of 27 pairs have coverage < 0.90 [`n_failure_cells`, `failure_cells`]: CR0 at G = 5 and G = 10 (all ICC; 0.717–0.897), CR1 at G = 5 with ICC = 0.2 and 0.5 (0.885, 0.876), and WCB at G = 5 (all ICC; 0.851–0.858). No pair fails at G = 30.\n3. **Variance bias.** CR0 underestimates Var(ȳ) strongly with few clusters: E[V̂]/Var(ȳ) = 0.48–0.66 at G = 5, 0.76–0.86 at G = 10, 0.93–0.94 at G = 30 [`rel_bias_var`]. The G/(G−1) factor of CR1 reduces but does not remove the bias at G = 5 (0.60–0.83); at G = 30 CR1 is within 0.96–0.98. The downward bias is larger with ICC > 0, because the unequal cluster sizes make the large cluster (n = 64) carry much of the variance and its residual sum is shrunk most by centring on ȳ.\n4. **Comparison of procedures.** At G = 5, CR1 has the highest average coverage (0.891 vs WCB 0.854 and CR0 0.740) [`best_procedure_small_G`, `mean_coverage_G5`]. At G = 10 and 30 with ICC > 0, WCB is closest to nominal (0.933–0.947). WCB intervals at G = 5 are much wider on average than CR1 (`mean_ci_halfwidth` in table1.csv, e.g. 1.39 vs 0.79 at ICC = 0.5) yet cover less often, which points to an unstable, data-dependent critical value when only 16 distinct |t*| values exist.\n5. **Consistent with nominal** (|p̂ − 0.95| ≤ 2 MC SE): only 5 of 27 pairs [`nominal_cells`]: CR1 at (G=10, ICC=0) and (G=30, ICC=0), and WCB at G = 30 for every ICC. CR0 is never consistent with nominal, not even at G = 30.\n\n## Uncertainty\nEach coverage estimate is a binomial proportion with R = 2000; its MC SE [`mc_se_coverage`] ranges from about 0.005 (coverage near 0.95) to 0.010 (coverage near 0.72), so a 95% MC interval is about ±0.01–0.02. Pairs near the 0.90 threshold are therefore classified with limited confidence: CR0 at (G=10, ICC=0) = 0.8965 (SE 0.0068), CR1 at (G=5, ICC=0) = 0.9115 (SE 0.0064) and CR1 at (G=5, ICC=0.2) = 0.8845 (SE 0.0071) all lie within 2 MC SE of 0.90, so their failure/non-failure label could flip with another seed. The \"nominal-consistent\" label is a 2-SE screen applied to 27 pairs without multiplicity adjustment, so it is not a formal test. Classifications far from the boundaries (CR0 at G = 5, WCB at G = 5, everything at G = 30 vs 0.90) are robust. The relative-bias estimates have MC SEs of 0.007–0.016 [`mc_se_rel_bias_var`]. As a check, the MC relative bias of CR0 was compared with its exact analytic expectation (verification script in `out/state/verify/`): |z| ≤ 1.4 in 8 of 9 cells and z = 2.46 in C2 (G=5, ICC=0.2: MC 0.531 vs exact 0.500), a deviation that fits the somewhat large realised variance of ȳ in that cell; the conclusions about bias do not depend on it. The WCB critical value carries its own bootstrap noise (B = 399), which is part of the procedure's coverage. Switching to numpy's interpolated quantile changes WCB coverage by at most 0.003 and leaves the failure set unchanged [`sensitivity_wcb_coverage_numpy_quantile`]. Seeds are fixed, so re-running gives identical numbers; a different seed would give MC variation of the size of these SEs.\n\n## Limitations and open issues\n- **Distributions:** only Gaussian cluster effects and errors. Skewed or heavy-tailed u_g/e_ig, which usually hurt few-cluster inference more, are not covered.\n- **Heterogeneity:** only one fixed unequal size pattern (8/16/32/64) and homoskedastic, equal ICC across clusters. Cluster-size-dependent effects, heteroskedasticity across clusters and informative cluster sizes are not studied. Results may depend on the size pattern (e.g. the dominant 64-observation cluster at G = 5).\n- **Regressors:** only the mean (intercept-only model) is studied. Regression slopes, leverage from treated clusters and few treated clusters are outside the design.\n- **Other weights / variants:** only Rademacher weights with the unrestricted (non-null-imposed) WCB-t were studied. Webb six-point or Mammen weights, the restricted WCR bootstrap, full enumeration of the 32 sign vectors at G = 5, CR2/CR3 (bias-reduced linearisation) and Satterthwaite/Bell–McCaffrey degrees of freedom were not evaluated. The G = 5 WCB results should not be generalised to those variants.\n- The grid covers only G ∈ {5, 10, 30} and ICC ∈ {0, 0.2, 0.5}; the transition between G = 10 and 30 is not resolved.\n- Interval length was summarised only by the mean half-width; the WCB half-width distribution at G = 5 (which seems heavy-tailed) was not analysed further.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"11 of 27 (procedure, cell) pairs have coverage below 0.90: CR0 at G=5 and G=10 for all ICC, CR1 at G=5 with ICC 0.2 and 0.5, and WCB at G=5 for all ICC; no pair fails at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"CR0 (G=10, ICC=0), CR1 (G=5, ICC=0) and CR1 (G=5, ICC=0.2) are within 2 MC SE of the 0.90 threshold; their labels are not robust to MC error.\"},\n {\"id\":\"C2\",\"text\":\"CR0 underestimates Var(ybar) with few clusters (E[V]/Var = 0.48-0.66 at G=5, 0.76-0.86 at G=10, 0.93-0.94 at G=30); the CR1 correction reduces but does not remove the bias at G=5.\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\"],\"status\":\"supported\",\"caveat\":\"MC SE 0.007-0.016; confirmed against exact analytic expectation except one 2.5-SE deviation (C2).\"},\n {\"id\":\"C3\",\"text\":\"At G=5, CR1 has the highest average coverage (0.891) ahead of WCB (0.854) and CR0 (0.740).\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_G5\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Specific to Rademacher unrestricted WCB-t and this cluster-size pattern.\"},\n {\"id\":\"C4\",\"text\":\"For G=10 and G=30 with ICC>0, WCB coverage (0.933-0.947) is closest to nominal; WCB is consistent with nominal coverage at G=30 for every ICC.\",\"results_keys\":[\"coverage\",\"nominal_cells\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Nominal-consistency is a 2-SE screen without multiplicity adjustment.\"},\n {\"id\":\"C5\",\"text\":\"Only 5 of 27 pairs are consistent with nominal 95% coverage; CR0 is never consistent with nominal, even at G=30.\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE screen with R=2000.\"},\n {\"id\":\"C6\",\"text\":\"The naive iid interval that ignores clustering covers only 0.29-0.49 when ICC>0, far below all cluster-robust procedures.\",\"results_keys\":[\"baseline_iid_coverage\",\"baseline_iid_mc_se\"],\"status\":\"supported\",\"caveat\":\"Baseline only; not a required estimand.\"},\n {\"id\":\"C7\",\"text\":\"WCB coverage is insensitive to the empirical-quantile convention (changes of at most 0.003, failure set unchanged).\",\"results_keys\":[\"sensitivity_wcb_coverage_numpy_quantile\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Only two quantile conventions compared.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;r=json.load(open('out/results.json'));print(r['mean_coverage_G5'])\"","description":"Write report and claims ledger"}}]}}95{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"5f8d8c17-b4f2-456a-a9a3-6e3254af042a","timestamp":"2026-10-30T05:42:18.687Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"6e9462ea-34d0-42c1-9fce-f52099fd96d1","keep":30,"tail":["17dab7ee3b9a97f53fc656f7d8e40d70d06f8087ca933e597e77194826cd9fbe","a3c5d78354b380e0fe1c346bfa7594281d1013347c2851225ba1d8154a8e1a55"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"25f2ea498ce8893d0e330e4c9034b78b2876e88b2552bd5d6d1fd9fa80c48325"}96{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"33194799-c869-4f93-ba2c-32dbb27ad639","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}97{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}98{"parentUuid":"33194799-c869-4f93-ba2c-32dbb27ad639","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtSgnk4otFLCF1vdzA3","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":5302,"cache_read_input_tokens":29859,"output_tokens":732,"output_tokens_details":{"thinking_tokens":281},"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":5302},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2553,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtSgWNe3JD291H9rxKX","requestRef":"5f8d8c17-b4f2-456a-a9a3-6e3254af042a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c21f3f17-fa98-4f34-895b-823f9ea9b210","timestamp":"2026-10-30T05:42:23.298Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}99{"parentUuid":"c21f3f17-fa98-4f34-895b-823f9ea9b210","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtSgnk4otFLCF1vdzA3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019DKcHsMaS6JcDpu1GvR1Sz","name":"Bash","input":{"command":"sed -i '' 's/(0.891 vs WCB 0.854 and CR0 0.740)/(0.8905 vs WCB 0.854 and CR0 0.740)/; s/The downward bias is larger with ICC > 0, because/The downward bias is larger with ICC > 0, plausibly because/' out/report.md\nsed -i '' 's/(0.891) ahead of/(0.8905) ahead of/' out/claims.json\ngrep -n \"0.891\\|plausibly\" out/report.md out/claims.json\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 required sections, quantitative statements cite results keys\",\"claims.json with 7 claims referencing existing keys\",\"final gate run (receipt recorded below)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | tail -8","description":"Fix rounding, finalize ledger, run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5302,"cache_read_input_tokens":29859,"output_tokens":732,"output_tokens_details":{"thinking_tokens":281},"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":5302},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtSgWNe3JD291H9rxKX","requestRef":"5f8d8c17-b4f2-456a-a9a3-6e3254af042a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ffaf28c8-db6c-4554-b58e-456cb773a51a","timestamp":"2026-10-30T05:42:26.308Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}100{"parentUuid":"ffaf28c8-db6c-4554-b58e-456cb773a51a","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019DKcHsMaS6JcDpu1GvR1Sz","type":"tool_result","content":"out/report.md:38:3. **Variance bias.** CR0 underestimates Var(ȳ) strongly with few clusters: E[V̂]/Var(ȳ) = 0.48–0.66 at G = 5, 0.76–0.86 at G = 10, 0.93–0.94 at G = 30 [`rel_bias_var`]. The G/(G−1) factor of CR1 reduces but does not remove the bias at G = 5 (0.60–0.83); at G = 30 CR1 is within 0.96–0.98. The downward bias is larger with ICC > 0, plausibly because the unequal cluster sizes make the large cluster (n = 64) carry much of the variance and its residual sum is shrunk most by centring on ȳ.\n  [ok] section:Results: present\n  [ok] section:Uncertainty: present\n  [ok] section:Limitations and open issues: present\n  [ok] claims_json: 7 claims, all keys resolve\n  [ok] phase_ledger: consistent\n  [ok] exclusion_ledger: 1 steps consistent\n  [ok] reproducibility: regenerated in 2.3s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0024/out/state/gate_receipts/20261030T054228.663481Z.json","is_error":false}]},"uuid":"342c586e-4692-4ab5-aae7-dd8f8c22a272","timestamp":"2026-10-30T05:42:28.668Z","toolUseResult":{"stdout":"out/report.md:38:3. **Variance bias.** CR0 underestimates Var(ȳ) strongly with few clusters: E[V̂]/Var(ȳ) = 0.48–0.66 at G = 5, 0.76–0.86 at G = 10, 0.93–0.94 at G = 30 [`rel_bias_var`]. The G/(G−1) factor of CR1 reduces but does not remove the bias at G = 5 (0.60–0.83); at G = 30 CR1 is within 0.96–0.98. The downward bias is larger with ICC > 0, plausibly because the unequal cluster sizes make the large cluster (n = 64) carry much of the variance and its residual sum is shrunk most by centring on ȳ.\n  [ok] section:Results: present\n  [ok] section:Uncertainty: present\n  [ok] section:Limitations and open issues: present\n  [ok] claims_json: 7 claims, all keys resolve\n  [ok] phase_ledger: consistent\n  [ok] exclusion_ledger: 1 steps consistent\n  [ok] reproducibility: regenerated in 2.3s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0024/out/state/gate_receipts/20261030T054228.663481Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ffaf28c8-db6c-4554-b58e-456cb773a51a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}101{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"ed0b5b209744dd60d59cd744e6b0142e2846439c9340e23965552625a3aa04d0","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019DKcHsMaS6JcDpu1GvR1Sz","name":"Bash","input":{"command":"sed -i '' 's/(0.891 vs WCB 0.854 and CR0 0.740)/(0.8905 vs WCB 0.854 and CR0 0.740)/; s/The downward bias is larger with ICC > 0, because/The downward bias is larger with ICC > 0, plausibly because/' out/report.md\nsed -i '' 's/(0.891) ahead of/(0.8905) ahead of/' out/claims.json\ngrep -n \"0.891\\|plausibly\" out/report.md out/claims.json\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 required sections, quantitative statements cite results keys\",\"claims.json with 7 claims referencing existing keys\",\"final gate run (receipt recorded below)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | tail -8","description":"Fix rounding, finalize ledger, run gate"}}]}}102{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"b049a6f0-e878-42f5-920d-e695de0960a3","timestamp":"2026-10-30T05:42:28.671Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"5f8d8c17-b4f2-456a-a9a3-6e3254af042a","keep":32,"tail":["ed0b5b209744dd60d59cd744e6b0142e2846439c9340e23965552625a3aa04d0","d8c4258053d3f40eb4971fdf8f93a0dec2e0556a1e36b59393c9c6f23280f001"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d3205b8a8ea3ea0640c105a2a1f0e7faea50394c3940ff66939412b33d036b9d"}103{"parentUuid":"342c586e-4692-4ab5-aae7-dd8f8c22a272","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtTRu5bX7j6mrXJ6i4D","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PeBVDR8fLcdDKowGADCh4R","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1; ls out/state/gate_receipts; ~/wp29/venv/bin/python - <<'EOF'\nimport json,glob\np=json.load(open('out/state/phases.json'))\nlast=sorted(glob.glob('out/state/gate_receipts/*.json'))[-1]\np['P5']['checks'].append(f\"final gate receipt {last}: passed={json.load(open(last)).get('passed')}\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nprint(p['P5'])\nEOF\necho \"- 2026-10-30 P5 passed: report.md, claims.json written; final gate PASSED. Task complete.\" >> out/state/log.md","description":"Confirm gate pass and record receipt"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1179,"cache_read_input_tokens":35161,"output_tokens":344,"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":1179},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtTRDPyfUX66AMrHZW2","requestRef":"b049a6f0-e878-42f5-920d-e695de0960a3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"11dbc9bf-4b49-4472-a801-3c55a1c0e809","timestamp":"2026-10-30T05:42:32.541Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}104{"parentUuid":"11dbc9bf-4b49-4472-a801-3c55a1c0e809","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PeBVDR8fLcdDKowGADCh4R","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\n20261030T054124.839175Z.json\n20261030T054228.663481Z.json\n20261030T054234.856651Z.json\n{'status': 'passed', 'checks': ['report.md with 6 required sections, quantitative statements cite results keys', 'claims.json with 7 claims referencing existing keys', 'final gate run (receipt recorded below)', 'final gate receipt out/state/gate_receipts/20261030T054234.856651Z.json: passed=True'], 'notes': ''}","is_error":false}]},"uuid":"3b94e400-be08-437e-9e36-afd6f69e24d3","timestamp":"2026-10-30T05:42:34.880Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\n20261030T054124.839175Z.json\n20261030T054228.663481Z.json\n20261030T054234.856651Z.json\n{'status': 'passed', 'checks': ['report.md with 6 required sections, quantitative statements cite results keys', 'claims.json with 7 claims referencing existing keys', 'final gate run (receipt recorded below)', 'final gate receipt out/state/gate_receipts/20261030T054234.856651Z.json: passed=True'], 'notes': ''}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"11dbc9bf-4b49-4472-a801-3c55a1c0e809","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}105{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"ca5ce2c8101197179e7a110d63f5f43fe749147c5ee92fc2d94db6ee949bd107","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01PeBVDR8fLcdDKowGADCh4R","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1; ls out/state/gate_receipts; ~/wp29/venv/bin/python - <<'EOF'\nimport json,glob\np=json.load(open('out/state/phases.json'))\nlast=sorted(glob.glob('out/state/gate_receipts/*.json'))[-1]\np['P5']['checks'].append(f\"final gate receipt {last}: passed={json.load(open(last)).get('passed')}\")\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nprint(p['P5'])\nEOF\necho \"- 2026-10-30 P5 passed: report.md, claims.json written; final gate PASSED. Task complete.\" >> out/state/log.md","description":"Confirm gate pass and record receipt"}}]}}106{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"875808b3-dc77-4372-baec-e3f711aa3d4f","timestamp":"2026-10-30T05:42:34.882Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"b049a6f0-e878-42f5-920d-e695de0960a3","keep":34,"tail":["ca5ce2c8101197179e7a110d63f5f43fe749147c5ee92fc2d94db6ee949bd107","b59939dd18bda1de74b29df47cc8c443905b32358c899205e8c6a10c9106d283"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"426a177af18f88a1d038dcdc637c6c5121ca75c56455e38add2282d5a41ad9da"}107{"parentUuid":"3b94e400-be08-437e-9e36-afd6f69e24d3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtTt5g2Ufch5DJdm2Gn","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSggcKEAgTGAI4AUIIdGhpbmtpbmcSDFFDelRVpBC17l+SixoM0OlmACZywsM8aziiIjAf08pG+cvhVuxWFJQ8SgtTYur6TUXlB12+PZ80wy0yivnMTeBN5Go/3Gpy1eg+Y0oqnwYE2YZZvV7Z701BZtU3VxsqjtVYGgGVRQ4mtw3bYNXWsaW+gBciawmnna9eAJhuEKZ0ML9fc/LNQpnkc58vXanv8dltnFLgeV8LUEhgMVmdgFOfTZQ3KPqPVYjzIn6eJ/vMMLUNiavkYBT2cFyUb2th7fOniYtzZH9zBtOehAns+oaM8E3J6M7AA55Opvh1s1J8Rbissmi2g2Q1KQroR5rHSSLvKeN0qAmARWW1/y1TGQurizXFtw3rEm3xxWGG+nmVxdGS9N1dDAJPSZv0uLX+SieudP7f6HtYvSJ9dLoGpdgNWJ5/zhMrto2N/xv1itihkbV45KBVGSrjWtngyT9XIRByfNAh0nxsfwoQrSnvn7T5jtc8UWK0Vu3J/5WZZ4ceW+/MiLdW/ESBBDYc+vrmNq2CVbCRn0KDovi5BGDw8NlBLGQAD/uKTVDCDzLx08vZNTYlj4ixr+aH9WvUDqn1EY5sU/qjwODTWXbBPrp4C4NROVrZbSWuF0zNWQ0d+bXSDtbwNILaHcMG39prlZuLW1/1qjexAqscD14OpraxuYfNgg30R7waFPRsUgyuEqYdCoXCbA8ZLDiFXDDtnbUsNhhTen6vo1sVUKfsFRT4Eyw0TITM5JnlRjgRNycqx9294NG2UKswAYzrjPAlVhLX5yTb1/22YYg+cuLhMR9SU6mlJXeSrvnwScBl3E0Xst2aQLXpn5DRPuXNrK9IsvXzh+0+Vu/3vrI5T0aB8hW8OT2f8OSooZtjseiNpE4KJSo2MQpRTysT2Z/WVN1/pwawNVKqPFptvp1El4Ez6lg1A0s/tVQcicu/qBAXMx+108RaOY97NNmc7s793eTQ187rVwIRWvwQal6YYbbi5eQCi7VM2Yub1x4MUHBE9nDsp17oidrssVxyMUIxYEtWNjPx/ri4CUXeyI1P4iFAJxe8H0j2axMp8d3LwsU6CRf/fd6G2JlYxonEq3mPbgFTAKdLxSChNVA7qtRT6RpGpewx3ztxtJKTfQnBSVkbyDEYHFE081hJIflEeKx1v+r0bsXMCr4/JHG7RVU3DC/dISXMGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":549,"cache_read_input_tokens":36340,"output_tokens":153,"output_tokens_details":{"thinking_tokens":38},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":549},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":347,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtTsnKhrpW25PfPjJK3","requestRef":"875808b3-dc77-4372-baec-e3f711aa3d4f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1ba76501-b119-4578-98de-058f059a1c4d","timestamp":"2026-10-30T05:42:36.985Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}108{"parentUuid":"1ba76501-b119-4578-98de-058f059a1c4d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtTt5g2Ufch5DJdm2Gn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JqY3qXh9fLHej88XbAZGuD","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Re-run gate after ledger edit"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":549,"cache_read_input_tokens":36340,"output_tokens":153,"output_tokens_details":{"thinking_tokens":38},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":549},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtTsnKhrpW25PfPjJK3","requestRef":"875808b3-dc77-4372-baec-e3f711aa3d4f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b71c5f54-71e2-4e55-b158-54655f64edaf","timestamp":"2026-10-30T05:42:37.480Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}109{"parentUuid":"b71c5f54-71e2-4e55-b158-54655f64edaf","isSidechain":false,"promptId":"5ea7d4b6-38be-4281-893d-ecc195e4c05c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JqY3qXh9fLHej88XbAZGuD","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)","is_error":false}]},"uuid":"d66d6bb5-9f98-4986-ada0-780a6c6fad90","timestamp":"2026-10-30T05:42:39.826Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b71c5f54-71e2-4e55-b158-54655f64edaf","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}110{"type":"api-request-blob","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","hash":"05f4b19314fb0ec6912fe1a21f212d5203fa5af02e1dfb6e1a6d2edbadedad0b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JqY3qXh9fLHej88XbAZGuD","name":"Bash","input":{"command":"~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Re-run gate after ledger edit"}}]}}111{"type":"api-request","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","id":"fcbb4630-ca9e-4ce9-b630-165180d3e8be","timestamp":"2026-10-30T05:42:39.828Z","version":"2.1.314","querySource":"sdk","shapeHash":"ac1b9be7af77be1645f17e76e613db4decfc91a37dddd2104e7bfe30f3fffe69","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":"875808b3-dc77-4372-baec-e3f711aa3d4f","keep":36,"tail":["05f4b19314fb0ec6912fe1a21f212d5203fa5af02e1dfb6e1a6d2edbadedad0b","cc22281077a2912a427e9a1e30dec65a6e71b4849cb2a565084f8a30229e117e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",37,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2564931c3738ed1e6eaeb4b9791512088946c2883aaf46fef0ac4a92ad4fe8cf"}112{"parentUuid":"d66d6bb5-9f98-4986-ada0-780a6c6fad90","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtUF9SkvKMszX5ubVxD","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":193,"cache_read_input_tokens":36889,"output_tokens":1252,"output_tokens_details":{"thinking_tokens":10},"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":193},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":7449,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtUEtZhZpEF3noX5YoS","requestRef":"fcbb4630-ca9e-4ce9-b630-165180d3e8be","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2a13c217-20db-4e88-972a-9884b02c4778","timestamp":"2026-10-30T05:42:48.796Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}113{"parentUuid":"2a13c217-20db-4e88-972a-9884b02c4778","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtUF9SkvKMszX5ubVxD","type":"message","role":"assistant","content":[{"type":"text","text":"I ran the full simulation: all 9 cells, R = 2000 replications per cell and B = 399 bootstrap draws, using the seeds in `design.csv`. That is 18,000 samples, and nothing was excluded. Every phase from P0 to P5 is marked passed, and the final gate run passes all 34 checks. The gate also confirmed that `out/analysis.py` regenerates identical results; the full grid runs in about 2 seconds.\n\n**Findings:**\n- **Failures (coverage below 0.90):** 11 of the 27 procedure-cell pairs fail.\n  - CR0 fails at G = 5 and G = 10 for every ICC, with coverage from 0.717 to 0.897.\n  - CR1 fails at G = 5 when ICC is 0.2 or 0.5 (0.885 and 0.876).\n  - The wild cluster bootstrap fails at G = 5 for every ICC (0.851 to 0.858).\n  - Nothing fails at G = 30.\n- **Variance bias:** CR0 underestimates the variance of the mean by a lot when clusters are few. Its ratio to the true variance is 0.48 to 0.66 at G = 5, 0.76 to 0.86 at G = 10 and 0.93 to 0.94 at G = 30. CR1's correction factor reduces this bias but doesn't remove it at G = 5 (0.60 to 0.83).\n- **Best procedure at G = 5:** CR1, with average coverage 0.8905, against 0.854 for the bootstrap and 0.740 for CR0. At G = 10 and 30 with ICC above zero, the bootstrap comes closest to 95% (0.933 to 0.947).\n- **Coverage close to 95%:** only 5 pairs are within 2 Monte Carlo standard errors of 0.95: CR1 at ICC = 0 with G = 10 and G = 30, and the bootstrap at G = 30 for every ICC. CR0 never is.\n- **Comparison point:** an ordinary interval that ignores clustering covers only 0.29 to 0.49 when ICC is above zero.\n\n**Checks:** I tested the fast bootstrap code against a slow direct version, and they agree to about 1e-14. The simulated CR0 bias matches its exact theoretical value within 1.4 standard errors in 8 of the 9 cells. The exception is G = 5, ICC = 0.2, which is off by 2.5 standard errors; the report says so.\n\n**Limitations and choices:**\n- Three pairs sit within 2 standard errors of the 0.90 cut-off, so their pass/fail label could flip with different seeds: CR0 at G = 10, ICC = 0, and CR1 at G = 5 with ICC = 0 and 0.2.\n- With G = 5 and ±1 weights, the bootstrap has only 32 possible weight patterns (16 distinct absolute t-values), so its critical value is coarse. I kept the procedure exactly as the task specifies and recorded this as a data issue.\n- For the bootstrap's 95% critical value I used the 380th of the 399 sorted values, a standard rule. Switching to numpy's interpolated quantile changes coverage by at most 0.003 and leaves the set of failures unchanged.\n- The design covers only normal errors, one cluster-size pattern, an intercept-only model and ±1 bootstrap weights. Other distributions, varying effects across clusters, regressors and other weight schemes or variants are not studied.\n\nEverything is in `out/`. Open `report.md` first; `table1.csv` and `figure1.png` show the results, `claims.json` lists the 7 claims and their supporting results, and `state/` holds the audit, checks and gate receipts."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":193,"cache_read_input_tokens":36889,"output_tokens":1252,"output_tokens_details":{"thinking_tokens":10},"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":193},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtUEtZhZpEF3noX5YoS","requestRef":"fcbb4630-ca9e-4ce9-b630-165180d3e8be","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"04e42583-b4a3-477d-a080-d2f084772d41","timestamp":"2026-10-30T05:42:51.772Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0024","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","version":"2.1.314","gitBranch":"HEAD"}114{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"04e42583-b4a3-477d-a080-d2f084772d41","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}115{"type":"atis-latch","atis":"","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f"}116{"type":"cost-state","sessionId":"26f3a2bd-1e41-40e9-81fe-450bf2eae17f","totalCostUSD":0.6930728000000002,"totalAPIDuration":199207,"totalAPIDurationWithoutRetries":199195,"totalToolDuration":19592,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":218934,"startTime":1793338752864,"modelUsage":{"claude-opus-5-5":{"inputTokens":40,"outputTokens":21905,"thinkingTokens":2289,"cacheReadInputTokens":384614,"cacheCreationInputTokens":35578,"cacheCreationEphemeral5mInputTokens":35578,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.6930728000000002}},"hasUnknownModelCost":false}117