spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:39:42.931Z","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:39:42.935Z","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}4{"parentUuid":null,"isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":"Begin"},"uuid":"72573e08-6bf2-4edd-945e-817fef38df39","timestamp":"2026-10-30T05:39:42.938Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","timestamp":"2026-10-30T05:39:42.947Z","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/RT0023\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":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"38844940-0611-4340-a267-a361d26689a2","timestamp":"2026-10-30T05:39:42.947Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"38ab50881248b5837c33c775a98e6d7f17933c9866bc63a22bfe93a83715d8e6"}8{"parentUuid":"72573e08-6bf2-4edd-945e-817fef38df39","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"166834bd-0a92-4671-87fc-1c33abd29f09","timestamp":"2026-10-30T05:39:42.942Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"166834bd-0a92-4671-87fc-1c33abd29f09","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"bd7c0ea2-fbf8-4ad9-86dd-d43c5a7682c7","timestamp":"2026-10-30T05:39:42.942Z","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/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"bd7c0ea2-fbf8-4ad9-86dd-d43c5a7682c7","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":"7106b7ec-9bcb-4361-a201-7326afd43d24","timestamp":"2026-10-30T05:39:42.942Z","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/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}12{"parentUuid":"7106b7ec-9bcb-4361-a201-7326afd43d24","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFHvH8X2ByvFnhoZE5","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":124,"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":480,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtFHeuZrDbV73mUBQQ1","requestRef":"38844940-0611-4340-a267-a361d26689a2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f16a9daa-13ee-4e55-bee3-07813e9a2a8a","timestamp":"2026-10-30T05:39:45.227Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"f16a9daa-13ee-4e55-bee3-07813e9a2a8a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFHvH8X2ByvFnhoZE5","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BaCL6yfZ1Rz48GXeYiDgXN","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data; ls -R out 2>/dev/null | head","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":124,"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_011CgXtFHeuZrDbV73mUBQQ1","requestRef":"38844940-0611-4340-a267-a361d26689a2","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6695be84-dc9d-4e17-b99f-1f26a4b308ff","timestamp":"2026-10-30T05:39:45.766Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"6695be84-dc9d-4e17-b99f-1f26a4b308ff","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BaCL6yfZ1Rz48GXeYiDgXN","type":"tool_result","content":"# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n  - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n  - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n  - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 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\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":false}]},"uuid":"a01394a9-32d1-4722-b487-d2b8b2d47345","timestamp":"2026-10-30T05:39:45.857Z","toolUseResult":{"stdout":"# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n  - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n  - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n  - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 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\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","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6695be84-dc9d-4e17-b99f-1f26a4b308ff","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"7b3fc96e7ade03729bf9ba5639915e16c65d27f51db4480950837beee420de84","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01BaCL6yfZ1Rz48GXeYiDgXN","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -la data; ls -R out 2>/dev/null | head","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"2e0ec277-bb00-4453-9e1e-0a9f00bc7aad","timestamp":"2026-10-30T05:39:45.861Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"38844940-0611-4340-a267-a361d26689a2","keep":2,"tail":["7b3fc96e7ade03729bf9ba5639915e16c65d27f51db4480950837beee420de84","aded96ec8eb849f0eb48b99bccb139a9f84ca527247f3bb75fa32c5668b66aba"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0b829b7722453ccf4fdd1a985aeeed699f6dcc1cb748205af3bcfc9dbefe9050"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a01394a9-32d1-4722-b487-d2b8b2d47345","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}18{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}19{"parentUuid":"a01394a9-32d1-4722-b487-d2b8b2d47345","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFRtVyo2tYeNiyVrwp","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TWNrBFoD1YQqJMLRB9xm1G","name":"Bash","input":{"command":"cat data/design.csv; cat data/README.md; cat gate_spec.json bundle.json; shasum -a 256 data/*","description":"Inspect design data and 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":3303,"cache_read_input_tokens":4107,"output_tokens":120,"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":3303},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtFRcdo66Pqbzd8T84P","requestRef":"2e0ec277-bb00-4453-9e1e-0a9f00bc7aad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6683792a-1cc2-4b93-9993-34257c3d8fe3","timestamp":"2026-10-30T05:39:47.505Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"6683792a-1cc2-4b93-9993-34257c3d8fe3","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TWNrBFoD1YQqJMLRB9xm1G","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":"4e5a2395-2665-4014-b8fa-1dc4dcdde5ba","timestamp":"2026-10-30T05:39:47.570Z","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":"6683792a-1cc2-4b93-9993-34257c3d8fe3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"f46d6689e244a911a7533a7a69fca8055cb6e007ac3250a836b59b850bf853f6","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01TWNrBFoD1YQqJMLRB9xm1G","name":"Bash","input":{"command":"cat data/design.csv; cat data/README.md; cat gate_spec.json bundle.json; shasum -a 256 data/*","description":"Inspect design data and gate spec"}}]}}22{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"9140dad4-f25b-4473-b828-ab774a4f6d1f","timestamp":"2026-10-30T05:39:47.573Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"2e0ec277-bb00-4453-9e1e-0a9f00bc7aad","keep":4,"tail":["f46d6689e244a911a7533a7a69fca8055cb6e007ac3250a836b59b850bf853f6","cdfadf6311a9596e90188b1b0663f365a79e72ffc089336af04d1fe8319f1dd7"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e04ca7285bf6afd9c81f39784bafb128271cfdc19635a1a7808dd54278157d00"}23{"parentUuid":"4e5a2395-2665-4014-b8fa-1dc4dcdde5ba","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFZDGnSb4DFriKuQVn","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":2276,"cache_read_input_tokens":7410,"output_tokens":1542,"output_tokens_details":{"thinking_tokens":383},"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":2276},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3320,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtFYwQyMkhRvhVbfjWt","requestRef":"9140dad4-f25b-4473-b828-ab774a4f6d1f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f0e0de49-5d4a-4288-a6bc-6ac9bfd469af","timestamp":"2026-10-30T05:39:53.161Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"f0e0de49-5d4a-4288-a6bc-6ac9bfd469af","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFZDGnSb4DFriKuQVn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BJ9wi4u84AnzfsL2MAnoDE","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 μ (estimated by the sample mean ȳ of N clustered obs)?\n\n**Estimands (per cell G∈{5,10,30} × ICC∈{0,0.2,0.5}, per procedure CR0/CR1/WCB):**\n(a) actual coverage of nominal 95% interval (fraction of R=2000 intervals containing μ=0);\n(b) for CR0, CR1: relative bias E[V̂]/Var(ȳ), Var(ȳ) exact = [ICC Σn_g² + (1−ICC)N]/N², E[V̂] by MC mean;\n(c) MC SE of coverage = sqrt(p(1−p)/R);\n(d) failure regimes: coverage < 0.90. Nominal-consistent: |p−0.95| ≤ 2 MC SE.\nAssumptions: DGP is Gaussian random-intercept as specified; estimands are meaningful for this DGP only.\n\n**Procedures** exactly as TASK.md: CR0 (z=1.96), CR1 (G/(G−1) factor, t_{G−1}), WCB (unrestricted Rademacher wild cluster bootstrap-t, B=399, q = 0.95 empirical quantile of |t*|, interval ȳ ± q√V̂_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 keys 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; do not change grid, R, B, seeds. Cell seed → numpy default_rng(seed).\n\n**Invalidity:** changing R/B/grid/seeds; inconsistent design rows (N ≠ Σn_g, len(sizes) ≠ G); non-deterministic output; runtime > 10 min.\nEOF\ncat > 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\necho \"- 2026-10-30: P0 passed (contract written).\" > log.md","description":"Write contract, phase ledger, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2276,"cache_read_input_tokens":7410,"output_tokens":1542,"output_tokens_details":{"thinking_tokens":383},"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":2276},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtFYwQyMkhRvhVbfjWt","requestRef":"9140dad4-f25b-4473-b828-ab774a4f6d1f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1ba7a335-4fc5-448f-8dda-47bda684b87d","timestamp":"2026-10-30T05:40:01.858Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"1ba7a335-4fc5-448f-8dda-47bda684b87d","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BJ9wi4u84AnzfsL2MAnoDE","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"a0b4edae-597e-443d-b30d-cd437f72ceaf","timestamp":"2026-10-30T05:40:01.876Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1ba7a335-4fc5-448f-8dda-47bda684b87d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"9dd3f14591aa4b847ed4c310af95aa608eecc69f5a1686871787b939b2adef51","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSwwsKEAgTGAI4AUIIdGhpbmtpbmcSDFMxct8w3adVrvbgGhoMDp6XKuTIydBMCBp9IjAzols9yAtIsHgW29eGFJymv2L9ucCUFFv4WeWa+1zEIAlYAQLfCzP5OkPJ5rr9Ry4q4ArpnHtcdtTS4Ldv93DCyh+7A2l6kKOhQVSQTaPNv/qjlNZ7VVu5o95LhobScVQtTJ8/lEL4O8tTEUp/znrdRAc08V4CrSG2xTBdTG9WxOtK1tVwNA4BXU/uFXeOuZhqPemh0c2rgGphQRwBr4nHyFV+A6YhtuBG+WUr9KhgH1YfhHWQQEzH4nF3tJFKhbLbvZao3gZx8rqmKfmXIwqqAPbFSZXxeelex2OPYy0z+5dIaWs83i95HBsAs2uy9Jh6DTEXHVRIiUzqGBwmFM3AmUyKPzVzUDm3QgL53z7qUPug8igsbYI7O3eoCYMTxYTWNTrnyU1raVixSy6m6jY1rPiXNZj7rGOiMFWcgYE3E323vYen8b0mqSzawXLlDPbkTL0YaoHmGX6RoGUzJbL/g1qwkZ8aeIW36jFgPsAzmihyZT0ZRLV+/X31aMrfsiXnzz3Si8Jp5Yo7JrbAUz3VSoa0NvIQ1rBuvXi9wy6vO/Btmkc58JbEjN4oyosjq1abVD17JnFCZgd7TXxh8k9mdWLmKkJEAf3Dn9xbStjvq4BEcNwjzhmWnJJXEfYyCagpMGBLPmHnPqsqkaFP5+/XwiOD0Dyx7jrx+V5THLseWOUJ6Y5cQidFQ8tpxYwdlzHAQDar5osQMlrl/o+wZxFMy+YROz4HO8mAySa2D1lInz0nf2s5Xpt1Jg/E1C/ix27mdo6UCo7q4PdJf+R68H4yMI6NLxu3q6mba+CsmpdkniS/+yFVlqmvwI+mDZMoBGz/0BbnY1iXV4EAtXJrVcXH0pc04vD0sWqAsTrZnqTclTJRBlyGpSFw+oUAcUUJqQdWNDEOfinHxAhM68Dy0DXNNsnHTsFCF7dcpjRP/21grVw5wjcfo2NE196arttD7h0pTfCyM9E9auXdx3/NhejkX2BnUCEEy4sOkLejSaG+sADAVkahLr04BwXS791xFRrOMC2+Dww+XzcAFJnwH3bEeRdMnNFSxtER7V6DhCOX86h2nLhdqFFcEOuGR7tAQ404psWpI6sqt6Io2fahhtSFnQiiQw8r2nCoBvx/Lyukap5PFMj7CjtZISrNfz7F+GzmoHiUtombnSucP8HpkwfM9pe73ewuzlmPhJ5xJ2+ugUvCgrj24APu7267LUJ6RFv5mcgvoJ2LkGnW9sQP+EF+EYZqhGYyYJkGXs1M+j4NiqWsZTk8B/CvJ8CbAdU9h1LUG/0ZOiIkKmTbi8oY3CvQVIkTdSiJ2MjgSQGStZGice/7Bdy+a1Kg7KUlo6K0wx8JdU3kJqqU/lQ5R6V+LILWwKKYArB6fxQ1KgmpE412KmP0Cv866fZcsAOhBSNFLd0lpdZ/GrRVWDxO4Bsy7Xuk+aYSjCLheSQfcSXgzh1A10KcUDqiPvosjVGK3LmIKsbhi4KAiIy+D8su8xwQH9ipCtYUT7+Zhu3ux6aESuDyxF5hgRgu2vyZNRw46UIzQyidKYfefXalNRw8PIesbAspeEqiCOxdm8gF06gcPQpC0Ml14d6ar2G0GidJ1jbNVkBW0G9dxLd7h4ycSV6qbzFWFzYx1AzWfTcBlcNCIjo1Pa88qciodVYo8q+k2fFgqRBI5dZZoOCRpqiPuobGeDBVQl3YHYmbIFpNT3FutdMW9G0Wf4GlCoP4VVJj78rx2xzl/jiUv0Xy/iMcWjVyXyyMSnzwqLF2xYBix+QiWD4vsIgdiUm1rbC3y2/Z/KRvpIsdw6HztekHryhkbrT/awZl4o499qkge8oQR1q7ASSKPeCLGKP5VSHPEywmm0Fn7u9QFx8N4HZgpNVftpk+q8Ox6RmNfM6QcgGTHFZK6XhAbTms4xgB"},{"type":"tool_use","id":"toolu_01BJ9wi4u84AnzfsL2MAnoDE","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 μ (estimated by the sample mean ȳ of N clustered obs)?\n\n**Estimands (per cell G∈{5,10,30} × ICC∈{0,0.2,0.5}, per procedure CR0/CR1/WCB):**\n(a) actual coverage of nominal 95% interval (fraction of R=2000 intervals containing μ=0);\n(b) for CR0, CR1: relative bias E[V̂]/Var(ȳ), Var(ȳ) exact = [ICC Σn_g² + (1−ICC)N]/N², E[V̂] by MC mean;\n(c) MC SE of coverage = sqrt(p(1−p)/R);\n(d) failure regimes: coverage < 0.90. Nominal-consistent: |p−0.95| ≤ 2 MC SE.\nAssumptions: DGP is Gaussian random-intercept as specified; estimands are meaningful for this DGP only.\n\n**Procedures** exactly as TASK.md: CR0 (z=1.96), CR1 (G/(G−1) factor, t_{G−1}), WCB (unrestricted Rademacher wild cluster bootstrap-t, B=399, q = 0.95 empirical quantile of |t*|, interval ȳ ± q√V̂_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 keys 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; do not change grid, R, B, seeds. Cell seed → numpy default_rng(seed).\n\n**Invalidity:** changing R/B/grid/seeds; inconsistent design rows (N ≠ Σn_g, len(sizes) ≠ G); non-deterministic output; runtime > 10 min.\nEOF\ncat > 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\necho \"- 2026-10-30: P0 passed (contract written).\" > log.md","description":"Write contract, phase ledger, log"}}]}}27{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"274ff21c-a77c-4866-9458-9987a3ca45c4","timestamp":"2026-10-30T05:40:01.879Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"9140dad4-f25b-4473-b828-ab774a4f6d1f","keep":6,"tail":["9dd3f14591aa4b847ed4c310af95aa608eecc69f5a1686871787b939b2adef51","9134e716a05b4420f76da1a29ddf3959e7bf3ab5840c3fb73ddee088dad0187a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2f8579b65cca8f1f3e1b4555e468e53f9de937a88eb32d1b313b04ddcbf36d8f"}28{"parentUuid":"a0b4edae-597e-443d-b30d-cd437f72ceaf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtGcMKjikc5x6SDeAt2","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":1557,"cache_read_input_tokens":9686,"output_tokens":276,"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":1557},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":361,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtGc6SrLEhuaFSPSRdW","requestRef":"274ff21c-a77c-4866-9458-9987a3ca45c4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"268601a4-6273-4ba2-8953-b6011f4c170a","timestamp":"2026-10-30T05:40:03.107Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"268601a4-6273-4ba2-8953-b6011f4c170a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtGcMKjikc5x6SDeAt2","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CtTkLDFWSx5QfpDM8tUdrH","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\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  s=[int(x) for x in r.cluster_sizes.split('|')]; print(r.cell_id,len(s)==r.G,sum(s)==r.N,sum(x*x for x in s))\n\"","description":"Audit design.csv consistency"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1557,"cache_read_input_tokens":9686,"output_tokens":276,"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":1557},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtGc6SrLEhuaFSPSRdW","requestRef":"274ff21c-a77c-4866-9458-9987a3ca45c4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3365025e-c507-4d35-a84e-273b5041e918","timestamp":"2026-10-30T05:40:04.521Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"3365025e-c507-4d35-a84e-273b5041e918","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","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_01CtTkLDFWSx5QfpDM8tUdrH"}]},"uuid":"080c4899-e2f0-4061-bfa0-02918aff0e31","timestamp":"2026-10-30T05:40:04.754Z","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":"3365025e-c507-4d35-a84e-273b5041e918","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"9438078c8ecf4c3e5e03c1f45e7f449029100dfc6a90edf9d10301a7aca73799","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01CtTkLDFWSx5QfpDM8tUdrH","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\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  s=[int(x) for x in r.cluster_sizes.split('|')]; print(r.cell_id,len(s)==r.G,sum(s)==r.N,sum(x*x for x in s))\n\"","description":"Audit design.csv consistency"}}]}}32{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"9eac79da-efb0-4b83-bde6-a2a9229bc6aa","timestamp":"2026-10-30T05:40:04.756Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"274ff21c-a77c-4866-9458-9987a3ca45c4","keep":8,"tail":["9438078c8ecf4c3e5e03c1f45e7f449029100dfc6a90edf9d10301a7aca73799","289c4955cc8947304e81f3b283c1cac3e766707098752ff448450efdbaebc402"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3fa37b544433887b05012a8fc02540c76f527c5717eb68dd5f32a1c0db9dc900"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"080c4899-e2f0-4061-bfa0-02918aff0e31","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}34{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}35{"parentUuid":"080c4899-e2f0-4061-bfa0-02918aff0e31","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtGphE7tFhMMZ9JfB6a","type":"message","role":"assistant","content":[{"type":"text","text":"The earlier `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":1011,"cache_read_input_tokens":11243,"output_tokens":312,"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":1011},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtGpQcnretS2X47WKhr","requestRef":"9eac79da-efb0-4b83-bde6-a2a9229bc6aa","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1df2a997-422d-4b95-bb7a-96e3210e13af","timestamp":"2026-10-30T05:40:05.664Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"1df2a997-422d-4b95-bb7a-96e3210e13af","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtGphE7tFhMMZ9JfB6a","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HbM4UrbDwQtJoQ4b93kwPs","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0023 && ~/wp29/venv/bin/python -c \"\nimport pandas as pd\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  s=[int(x) for x in r.cluster_sizes.split('|')]; print(r.cell_id,len(s)==r.G,sum(s)==r.N,sum(x*x for x in s))\n\"","description":"Audit design.csv consistency"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1011,"cache_read_input_tokens":11243,"output_tokens":312,"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":1011},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtGpQcnretS2X47WKhr","requestRef":"9eac79da-efb0-4b83-bde6-a2a9229bc6aa","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"69db5f5d-53f6-4d52-85d3-cb4655a4eb15","timestamp":"2026-10-30T05:40:07.386Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"69db5f5d-53f6-4d52-85d3-cb4655a4eb15","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HbM4UrbDwQtJoQ4b93kwPs","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\nC2 True True 5504\nC3 True True 5504\nC4 True True 11200\nC5 True True 11200\nC6 True True 11200\nC7 True True 38400\nC8 True True 38400\nC9 True True 38400","is_error":false}]},"uuid":"a1b08acc-ada5-49e5-a4dd-9a6a56f552a1","timestamp":"2026-10-30T05:40:07.610Z","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\nC2 True True 5504\nC3 True True 5504\nC4 True True 11200\nC5 True True 11200\nC6 True True 11200\nC7 True True 38400\nC8 True True 38400\nC9 True True 38400","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"69db5f5d-53f6-4d52-85d3-cb4655a4eb15","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"09135900cc311e578f8a38a605bda70ed966058b78502081a57240bbf0c23816","message":{"role":"assistant","content":[{"type":"text","text":"The earlier `cd` persisted; returning to the workspace root."},{"type":"tool_use","id":"toolu_01HbM4UrbDwQtJoQ4b93kwPs","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0023 && ~/wp29/venv/bin/python -c \"\nimport pandas as pd\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  s=[int(x) for x in r.cluster_sizes.split('|')]; print(r.cell_id,len(s)==r.G,sum(s)==r.N,sum(x*x for x in s))\n\"","description":"Audit design.csv consistency"}}]}}39{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"fc212346-39ba-4b25-92ed-011b3b74b560","timestamp":"2026-10-30T05:40:07.613Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"9eac79da-efb0-4b83-bde6-a2a9229bc6aa","keep":10,"tail":["09135900cc311e578f8a38a605bda70ed966058b78502081a57240bbf0c23816","fcad5d6323038fef3e8c65a15436869f7fda1ee0a023133a62c187ef054bd0bb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ea9c668acf0e59777b9c2c2001eb0151ea99b4b502f62c537539a4f8d1721403"}40{"parentUuid":"a1b08acc-ada5-49e5-a4dd-9a6a56f552a1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtH2uSbdxqHevaqsDp7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GVwTe5UBugAdxjNeBxfTcn","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0023/out && cat > state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 | rows | cols |\n|---|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 data rows | 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), B (int, 399 all), seed (int, 20261101..20261109), mu (0.0), total_variance (1.0), nominal_level (0.95). Units: y is unitless with total variance 1.\n\nMissing values: 0. Duplicate rows: 0. Duplicate cell_id: 0.\nConsistency: for every row len(cluster_sizes)==G and sum(cluster_sizes)==N (128, 264, 864). Σn_g² = 5504, 11200, 38400.\nDate ranges: none (synthetic design).\n\nAnomalies / notes:\n- Cluster sizes are unbalanced (8..64); pattern 8,16,32,64 repeated and truncated at G, so G=5 has two clusters of size 8 — as documented in README, not an error.\n- With G=5 and Rademacher weights there are only 2^5=32 distinct weight vectors (16 distinct |t*| values since w and −w give the same |t*|); the B=399 draws therefore sample with replacement from a tiny support and the 0.95 quantile is coarse. Not a data error; recorded as a data_issue / limitation, procedure kept exactly as specified.\n- No information-availability violations: the only input is the design file; no observed data. No exclusions are applied (exclusion ledger records a zero-removal step).\nEOF\ncat > exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep all design cells (no filtering; all rows consistent),9,9,0,All 9 design rows pass consistency checks (len(sizes)=G; sum(sizes)=N); unit = design cell\nEOF\ncd state && ~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 computed and matched bundle.json\",\"9 rows x 11 cols, 0 NA, 0 duplicates\",\"len(sizes)==G and sum(sizes)==N for all rows\",\"exclusions.csv written (0 removed)\"],\"notes\":\"G=5 Rademacher support limitation noted\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P1 passed (audit; no exclusions; G=5 Rademacher support noted).\" >> log.md","description":"Write data audit, exclusions, 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":559,"cache_read_input_tokens":12254,"output_tokens":1157,"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":559},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtH2daWQGVWVxmi13TA","requestRef":"fc212346-39ba-4b25-92ed-011b3b74b560","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"16d3f852-e262-4745-bf5c-d45aa6ea197e","timestamp":"2026-10-30T05:40:19.045Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"16d3f852-e262-4745-bf5c-d45aa6ea197e","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GVwTe5UBugAdxjNeBxfTcn","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"7f32e248-0594-4439-bed8-866de4895450","timestamp":"2026-10-30T05:40:19.114Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"16d3f852-e262-4745-bf5c-d45aa6ea197e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"823abdb63fcf00872a2d7962c132338801402fc10a60d8117c7b5702e3bf10b3","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01GVwTe5UBugAdxjNeBxfTcn","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0023/out && cat > state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 | rows | cols |\n|---|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 data rows | 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), B (int, 399 all), seed (int, 20261101..20261109), mu (0.0), total_variance (1.0), nominal_level (0.95). Units: y is unitless with total variance 1.\n\nMissing values: 0. Duplicate rows: 0. Duplicate cell_id: 0.\nConsistency: for every row len(cluster_sizes)==G and sum(cluster_sizes)==N (128, 264, 864). Σn_g² = 5504, 11200, 38400.\nDate ranges: none (synthetic design).\n\nAnomalies / notes:\n- Cluster sizes are unbalanced (8..64); pattern 8,16,32,64 repeated and truncated at G, so G=5 has two clusters of size 8 — as documented in README, not an error.\n- With G=5 and Rademacher weights there are only 2^5=32 distinct weight vectors (16 distinct |t*| values since w and −w give the same |t*|); the B=399 draws therefore sample with replacement from a tiny support and the 0.95 quantile is coarse. Not a data error; recorded as a data_issue / limitation, procedure kept exactly as specified.\n- No information-availability violations: the only input is the design file; no observed data. No exclusions are applied (exclusion ledger records a zero-removal step).\nEOF\ncat > exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_removed,rationale\n1,keep all design cells (no filtering; all rows consistent),9,9,0,All 9 design rows pass consistency checks (len(sizes)=G; sum(sizes)=N); unit = design cell\nEOF\ncd state && ~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 computed and matched bundle.json\",\"9 rows x 11 cols, 0 NA, 0 duplicates\",\"len(sizes)==G and sum(sizes)==N for all rows\",\"exclusions.csv written (0 removed)\"],\"notes\":\"G=5 Rademacher support limitation noted\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P1 passed (audit; no exclusions; G=5 Rademacher support noted).\" >> log.md","description":"Write data audit, exclusions, update ledger"}}]}}43{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"3bacb3a6-733c-4ed8-8fd8-e879811057c4","timestamp":"2026-10-30T05:40:19.116Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"fc212346-39ba-4b25-92ed-011b3b74b560","keep":12,"tail":["823abdb63fcf00872a2d7962c132338801402fc10a60d8117c7b5702e3bf10b3","9123128e08b3cf7828b7f7ee96bf1bb15070acb8304a65ca8d3e3703c3a385ae"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2c8cf776095dc724480db6456ccf1e9d25a42808e2443184f86fc3777c79755d"}44{"parentUuid":"7f32e248-0594-4439-bed8-866de4895450","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHtDb4RbNaxTwKfbAA","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":1172,"cache_read_input_tokens":12813,"output_tokens":5099,"output_tokens_details":{"thinking_tokens":736},"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":1172},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6918,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtHstz7FuJMGZv4kZMc","requestRef":"3bacb3a6-733c-4ed8-8fd8-e879811057c4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"29259a28-2fcb-4af2-9a66-d7a14748e589","timestamp":"2026-10-30T05:40:29.102Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"29259a28-2fcb-4af2-9a66-d7a14748e589","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHtDb4RbNaxTwKfbAA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0195J6BEnxVdQDEcoqG2cxNm","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0023/out && cat > 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.\nDeterministic: each cell uses numpy.random.default_rng(seed of that cell). Within a replication\nthe draw order is: u (G normals), e (N normals), then a B x G Rademacher weight matrix.\n\"\"\"\nimport json\nimport os\n\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\")\nEST = [\"cr0\", \"cr1\", \"wcb\"]\n\n\ndef key(est, G, icc):\n    return f\"{est}_G{int(G)}_icc{float(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, tv, level = float(row.mu), float(row.total_variance), float(row.nominal_level)\n    sizes = np.array([int(s) for s in str(row.cluster_sizes).split(\"|\")])\n    assert len(sizes) == G and sizes.sum() == N\n    cid = np.repeat(np.arange(G), sizes)\n    var_u, var_e = icc * tv, (1.0 - icc) * tv\n    var_ybar = (var_u * np.sum(sizes ** 2) + var_e * N) / N ** 2  # exact Var(ybar)\n    z = stats.norm.ppf(1 - (1 - level) / 2)\n    z = 1.96 if abs(z - 1.96) < 1e-3 else z  # TASK specifies 1.96\n    tcrit = stats.t.ppf(1 - (1 - level) / 2, G - 1)\n    cr1f = G / (G - 1)\n    rng = np.random.default_rng(int(row.seed))\n\n    out = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"v_iid\"]}\n    n_degenerate = 0\n    for r in range(R):\n        u = rng.normal(0.0, np.sqrt(var_u), G)\n        e = rng.normal(0.0, np.sqrt(var_e), N)\n        y = mu + u[cid] + e\n        ybar = y.mean()\n        res = y - ybar\n        S = np.bincount(cid, weights=res, minlength=G)  # cluster sums of residuals\n        v0 = np.sum(S ** 2) / N ** 2\n        v1 = cr1f * v0\n        # wild cluster bootstrap-t (unrestricted, Rademacher)\n        W = rng.choice(np.array([-1.0, 1.0]), size=(B, G))\n        delta = (W @ S) / N                              # ybar* - ybar\n        Sstar = W * S[None, :] - delta[:, None] * sizes[None, :]  # cluster sums of bootstrap residuals\n        v1s = cr1f * np.sum(Sstar ** 2, axis=1) / N ** 2\n        ok = v1s > 0\n        n_degenerate += int((~ok).sum())\n        tstar = np.abs(delta[ok]) / np.sqrt(v1s[ok])\n        q = np.quantile(tstar, level, method=\"inverted_cdf\")  # = ceil(0.95*B)-th order stat (380th of 399)\n        out[\"ybar\"][r], out[\"v0\"][r], out[\"v1\"][r], out[\"q\"][r] = ybar, v0, v1, q\n        out[\"v_iid\"][r] = np.sum(res ** 2) / (N - 1) / N  # naive iid variance (baseline only)\n\n    err = np.abs(out[\"ybar\"] - mu)\n    hw = {\n        \"cr0\": z * np.sqrt(out[\"v0\"]),\n        \"cr1\": tcrit * np.sqrt(out[\"v1\"]),\n        \"wcb\": out[\"q\"] * np.sqrt(out[\"v1\"]),\n        \"iid\": z * np.sqrt(out[\"v_iid\"]),\n    }\n    res = {}\n    for est, h in hw.items():\n        cov = float(np.mean(err <= h))\n        res[est] = dict(coverage=cov, mc_se=float(np.sqrt(cov * (1 - cov) / R)),\n                        mean_hw=float(np.mean(h)))\n    res[\"cr0\"][\"rel_bias\"] = float(np.mean(out[\"v0\"]) / var_ybar)\n    res[\"cr1\"][\"rel_bias\"] = float(np.mean(out[\"v1\"]) / var_ybar)\n    res[\"cr0\"][\"rel_bias_mcse\"] = float(np.std(out[\"v0\"], ddof=1) / np.sqrt(R) / var_ybar)\n    res[\"cr1\"][\"rel_bias_mcse\"] = float(np.std(out[\"v1\"], ddof=1) / np.sqrt(R) / var_ybar)\n    res[\"iid\"][\"rel_bias\"] = float(np.mean(out[\"v_iid\"]) / var_ybar)\n    res[\"meta\"] = dict(var_ybar=float(var_ybar), n_degenerate_boot=n_degenerate,\n                       mean_ybar=float(out[\"ybar\"].mean()),\n                       var_ybar_mc=float(np.var(out[\"ybar\"], ddof=1)),\n                       n_distinct_q_min=int(len(np.unique(np.round(out[\"q\"], 12)))))\n    return res\n\n\ndef main():\n    design = pd.read_csv(DATA)\n    R_all, B_all = design.R.unique(), design.B.unique()\n    assert len(R_all) == 1 and len(B_all) == 1\n    R, B = int(R_all[0]), int(B_all[0])\n\n    rows, cov, mcse, rb, extra = [], {}, {}, {}, {}\n    base_cov, base_mcse = {}, {}\n    n_degenerate = 0\n    for _, row in design.iterrows():\n        r = simulate_cell(row)\n        n_degenerate += r[\"meta\"][\"n_degenerate_boot\"]\n        for est in EST:\n            k = key(est, row.G, row.icc)\n            cov[k], mcse[k] = r[est][\"coverage\"], r[est][\"mc_se\"]\n            if est != \"wcb\":\n                rb[k] = r[est][\"rel_bias\"]\n                extra[k + \"_mcse\"] = r[est][\"rel_bias_mcse\"]\n            rows.append(dict(estimator=est, cell_id=row.cell_id, G=int(row.G), icc=float(row.icc),\n                             coverage=r[est][\"coverage\"], mc_se_coverage=r[est][\"mc_se\"],\n                             rel_bias_var=r[est].get(\"rel_bias\", np.nan) if est != \"wcb\" else np.nan,\n                             mean_ci_halfwidth=r[est][\"mean_hw\"], R=int(row.R)))\n        kb = f\"iid_G{int(row.G)}_icc{float(row.icc):.1f}\"\n        base_cov[kb], base_mcse[kb] = r[\"iid\"][\"coverage\"], r[\"iid\"][\"mc_se\"]\n        extra[f\"meta_{row.cell_id}\"] = r[\"meta\"]\n\n    table = pd.DataFrame(rows)\n    table.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n    failure = [k for k, v in cov.items() if v < 0.90]\n    nominal = [k for k, v in cov.items() if abs(v - 0.95) <= 2 * mcse[k]]\n    g5 = {est: float(np.mean([cov[key(est, 5, i)] for i in sorted(design.icc.unique())])) for est in EST}\n    best = max(g5, key=lambda e: g5[e])\n\n    data_issues = [{\n        \"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct bootstrap weight vectors exist \"\n                 \"(16 distinct |t*| values), so the B=399 draws resample a tiny support and the WCB \"\n                 \"critical value is coarse and typically large.\",\n        \"handling\": \"Procedure kept exactly as specified (no Webb weights, no enumeration); flagged as a \"\n                    \"limitation in the report.\"}]\n    if n_degenerate:\n        data_issues.append({\"issue\": f\"{n_degenerate} bootstrap draws had V*_CR1 = 0\",\n                            \"handling\": \"dropped from that replication's |t*| set before taking the quantile\"})\n\n    results = {\n        \"task_id\": \"T2-simulation\",\n        \"R\": R, \"B\": B, \"n_cells\": int(len(design)),\n        \"coverage\": cov, \"mc_se_coverage\": mcse, \"rel_bias_var\": rb,\n        \"failure_cells\": failure, \"n_failure_cells\": len(failure),\n        \"nominal_cells\": nominal,\n        \"best_procedure_small_G\": best,\n        \"feasibility\": \"complete\", \"feasibility_reason\": None,\n        \"data_issues\": data_issues,\n        \"n_input_rows\": {\"design.csv\": int(len(design))},\n        \"n_analysed\": int(len(design) * R),\n        \"random_seed\": int(design.loc[design.cell_id == \"C1\", \"seed\"].iloc[0]),\n        \"mean_coverage_G5\": g5,\n        \"rel_bias_var_mcse\": {k.replace(\"_mcse\", \"\"): v for k, v in extra.items() if k.endswith(\"_mcse\")},\n        \"baseline_iid_coverage\": base_cov,\n        \"baseline_iid_mc_se_coverage\": base_mcse,\n        \"cell_diagnostics\": {k[5:]: v for k, v in extra.items() if k.startswith(\"meta_\")},\n        \"seeds\": {str(c): int(s) for c, s in zip(design.cell_id, design.seed)},\n        \"wcb_quantile_rule\": \"inverted_cdf 0.95 quantile of |t*| (380th order statistic of 399)\",\n    }\n    with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n        json.dump(results, f, indent=2)\n\n    # figure\n    iccs = sorted(design.icc.unique())\n    Gs = sorted(design.G.unique())\n    fig, axes = plt.subplots(1, len(iccs), figsize=(13, 4.2), sharey=True)\n    styles = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t (Rademacher)\")}\n    for ax, icc in zip(axes, iccs):\n        for est in EST:\n            p = np.array([cov[key(est, g, icc)] for g in Gs])\n            se = np.array([mcse[key(est, g, icc)] for g in Gs])\n            ax.errorbar(Gs, p, yerr=1.96 * se, fmt=styles[est][0], label=styles[est][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\")\n    axes[0].set_ylabel(\"coverage (±1.96 MC SE)\")\n    axes[0].legend(fontsize=8, loc=\"lower right\")\n    fig.suptitle(f\"Coverage of nominal 95% CIs for the mean (R={R}, B={B})\")\n    fig.tight_layout()\n    fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n    plt.close(fig)\n\n    print(table.to_string(index=False))\n    print(\"failure cells:\", failure)\n    print(\"best procedure at G=5:\", best, g5)\n\n\nif __name__ == \"__main__\":\n    main()\nEOF\ncd .. && time ~/wp29/venv/bin/python out/analysis.py","description":"Write and run simulation script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1172,"cache_read_input_tokens":12813,"output_tokens":5099,"output_tokens_details":{"thinking_tokens":736},"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":1172},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtHstz7FuJMGZv4kZMc","requestRef":"3bacb3a6-733c-4ed8-8fd8-e879811057c4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"075a29fb-dddb-42e7-98a2-70a0a304cf92","timestamp":"2026-10-30T05:41:00.256Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"075a29fb-dddb-42e7-98a2-70a0a304cf92","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0195J6BEnxVdQDEcoqG2cxNm","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      cr1      C1  5  0.0    0.9115        0.006351      0.827054           0.205387 2000\n      wcb      C1  5  0.0    0.8575        0.007816           NaN           0.250419 2000\n      cr0      C2  5  0.2    0.7210        0.010029      0.531396           0.342268 2000\n      cr1      C2  5  0.2    0.8845        0.007147      0.664245           0.542069 2000\n      wcb      C2  5  0.2    0.8545        0.007884           NaN           0.925496 2000\n      cr0      C3  5  0.5    0.7170        0.010073      0.483350           0.498894 2000\n      cr1      C3  5  0.5    0.8755        0.007382      0.604188           0.790125 2000\n      wcb      C3  5  0.5    0.8510        0.007962           NaN           1.386152 2000\n      cr0      C4 10  0.0    0.8965        0.006811      0.855805           0.106852 2000\n      cr1      C4 10  0.0    0.9435        0.005163      0.950894           0.129995 2000\n      wcb      C4 10  0.0    0.9375        0.005413           NaN           0.146598 2000\n      cr0      C5 10  0.2    0.8570        0.007828      0.762437           0.301309 2000\n      cr1      C5 10  0.2    0.9155        0.006219      0.847152           0.366571 2000\n      wcb      C5 10  0.2    0.9325        0.005610           NaN           0.465642 2000\n      cr0      C6 10  0.5    0.8530        0.007918      0.773743           0.461422 2000\n      cr1      C6 10  0.5    0.9065        0.006510      0.859715           0.561363 2000\n      wcb      C6 10  0.5    0.9350        0.005512           NaN           0.730597 2000\n      cr0      C7 30  0.0    0.9275        0.005798      0.943797           0.063969 2000\n      cr1      C7 30  0.0    0.9400        0.005310      0.976341           0.067892 2000\n      wcb      C7 30  0.0    0.9445        0.005120           NaN           0.070410 2000\n      cr0      C8 30  0.2    0.9210        0.006032      0.931367           0.196303 2000\n      cr1      C8 30  0.2    0.9350        0.005512      0.963483           0.208341 2000\n      wcb      C8 30  0.2    0.9470        0.005010           NaN           0.224426 2000\n      cr0      C9 30  0.5    0.9165        0.006186      0.925260           0.299237 2000\n      cr1      C9 30  0.5    0.9300        0.005705      0.957165           0.317587 2000\n      wcb      C9 30  0.5    0.9440        0.005141           NaN           0.341879 2000\nfailure cells: ['cr0_G5_icc0.0', 'wcb_G5_icc0.0', 'cr0_G5_icc0.2', 'cr1_G5_icc0.2', 'wcb_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.5', 'wcb_G5_icc0.5', 'cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_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  2,09s user 0,07s system 99% cpu 2,167 total","is_error":false}]},"uuid":"be48a9e0-65a3-4c47-ba33-fb69739bce8a","timestamp":"2026-10-30T05:41:02.462Z","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      cr1      C1  5  0.0    0.9115        0.006351      0.827054           0.205387 2000\n      wcb      C1  5  0.0    0.8575        0.007816           NaN           0.250419 2000\n      cr0      C2  5  0.2    0.7210        0.010029      0.531396           0.342268 2000\n      cr1      C2  5  0.2    0.8845        0.007147      0.664245           0.542069 2000\n      wcb      C2  5  0.2    0.8545        0.007884           NaN           0.925496 2000\n      cr0      C3  5  0.5    0.7170        0.010073      0.483350           0.498894 2000\n      cr1      C3  5  0.5    0.8755        0.007382      0.604188           0.790125 2000\n      wcb      C3  5  0.5    0.8510        0.007962           NaN           1.386152 2000\n      cr0      C4 10  0.0    0.8965        0.006811      0.855805           0.106852 2000\n      cr1      C4 10  0.0    0.9435        0.005163      0.950894           0.129995 2000\n      wcb      C4 10  0.0    0.9375        0.005413           NaN           0.146598 2000\n      cr0      C5 10  0.2    0.8570        0.007828      0.762437           0.301309 2000\n      cr1      C5 10  0.2    0.9155        0.006219      0.847152           0.366571 2000\n      wcb      C5 10  0.2    0.9325        0.005610           NaN           0.465642 2000\n      cr0      C6 10  0.5    0.8530        0.007918      0.773743           0.461422 2000\n      cr1      C6 10  0.5    0.9065        0.006510      0.859715           0.561363 2000\n      wcb      C6 10  0.5    0.9350        0.005512           NaN           0.730597 2000\n      cr0      C7 30  0.0    0.9275        0.005798      0.943797           0.063969 2000\n      cr1      C7 30  0.0    0.9400        0.005310      0.976341           0.067892 2000\n      wcb      C7 30  0.0    0.9445        0.005120           NaN           0.070410 2000\n      cr0      C8 30  0.2    0.9210        0.006032      0.931367           0.196303 2000\n      cr1      C8 30  0.2    0.9350        0.005512      0.963483           0.208341 2000\n      wcb      C8 30  0.2    0.9470        0.005010           NaN           0.224426 2000\n      cr0      C9 30  0.5    0.9165        0.006186      0.925260           0.299237 2000\n      cr1      C9 30  0.5    0.9300        0.005705      0.957165           0.317587 2000\n      wcb      C9 30  0.5    0.9440        0.005141           NaN           0.341879 2000\nfailure cells: ['cr0_G5_icc0.0', 'wcb_G5_icc0.0', 'cr0_G5_icc0.2', 'cr1_G5_icc0.2', 'wcb_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.5', 'wcb_G5_icc0.5', 'cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_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  2,09s user 0,07s system 99% cpu 2,167 total","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"075a29fb-dddb-42e7-98a2-70a0a304cf92","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}47{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"896c6fc368dbbbfa220d081d0b78a9b80a7b42c783e03dc1ebf8ea1871fd5d79","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_0195J6BEnxVdQDEcoqG2cxNm","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0023/out && cat > 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.\nDeterministic: each cell uses numpy.random.default_rng(seed of that cell). Within a replication\nthe draw order is: u (G normals), e (N normals), then a B x G Rademacher weight matrix.\n\"\"\"\nimport json\nimport os\n\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\")\nEST = [\"cr0\", \"cr1\", \"wcb\"]\n\n\ndef key(est, G, icc):\n    return f\"{est}_G{int(G)}_icc{float(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, tv, level = float(row.mu), float(row.total_variance), float(row.nominal_level)\n    sizes = np.array([int(s) for s in str(row.cluster_sizes).split(\"|\")])\n    assert len(sizes) == G and sizes.sum() == N\n    cid = np.repeat(np.arange(G), sizes)\n    var_u, var_e = icc * tv, (1.0 - icc) * tv\n    var_ybar = (var_u * np.sum(sizes ** 2) + var_e * N) / N ** 2  # exact Var(ybar)\n    z = stats.norm.ppf(1 - (1 - level) / 2)\n    z = 1.96 if abs(z - 1.96) < 1e-3 else z  # TASK specifies 1.96\n    tcrit = stats.t.ppf(1 - (1 - level) / 2, G - 1)\n    cr1f = G / (G - 1)\n    rng = np.random.default_rng(int(row.seed))\n\n    out = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"v_iid\"]}\n    n_degenerate = 0\n    for r in range(R):\n        u = rng.normal(0.0, np.sqrt(var_u), G)\n        e = rng.normal(0.0, np.sqrt(var_e), N)\n        y = mu + u[cid] + e\n        ybar = y.mean()\n        res = y - ybar\n        S = np.bincount(cid, weights=res, minlength=G)  # cluster sums of residuals\n        v0 = np.sum(S ** 2) / N ** 2\n        v1 = cr1f * v0\n        # wild cluster bootstrap-t (unrestricted, Rademacher)\n        W = rng.choice(np.array([-1.0, 1.0]), size=(B, G))\n        delta = (W @ S) / N                              # ybar* - ybar\n        Sstar = W * S[None, :] - delta[:, None] * sizes[None, :]  # cluster sums of bootstrap residuals\n        v1s = cr1f * np.sum(Sstar ** 2, axis=1) / N ** 2\n        ok = v1s > 0\n        n_degenerate += int((~ok).sum())\n        tstar = np.abs(delta[ok]) / np.sqrt(v1s[ok])\n        q = np.quantile(tstar, level, method=\"inverted_cdf\")  # = ceil(0.95*B)-th order stat (380th of 399)\n        out[\"ybar\"][r], out[\"v0\"][r], out[\"v1\"][r], out[\"q\"][r] = ybar, v0, v1, q\n        out[\"v_iid\"][r] = np.sum(res ** 2) / (N - 1) / N  # naive iid variance (baseline only)\n\n    err = np.abs(out[\"ybar\"] - mu)\n    hw = {\n        \"cr0\": z * np.sqrt(out[\"v0\"]),\n        \"cr1\": tcrit * np.sqrt(out[\"v1\"]),\n        \"wcb\": out[\"q\"] * np.sqrt(out[\"v1\"]),\n        \"iid\": z * np.sqrt(out[\"v_iid\"]),\n    }\n    res = {}\n    for est, h in hw.items():\n        cov = float(np.mean(err <= h))\n        res[est] = dict(coverage=cov, mc_se=float(np.sqrt(cov * (1 - cov) / R)),\n                        mean_hw=float(np.mean(h)))\n    res[\"cr0\"][\"rel_bias\"] = float(np.mean(out[\"v0\"]) / var_ybar)\n    res[\"cr1\"][\"rel_bias\"] = float(np.mean(out[\"v1\"]) / var_ybar)\n    res[\"cr0\"][\"rel_bias_mcse\"] = float(np.std(out[\"v0\"], ddof=1) / np.sqrt(R) / var_ybar)\n    res[\"cr1\"][\"rel_bias_mcse\"] = float(np.std(out[\"v1\"], ddof=1) / np.sqrt(R) / var_ybar)\n    res[\"iid\"][\"rel_bias\"] = float(np.mean(out[\"v_iid\"]) / var_ybar)\n    res[\"meta\"] = dict(var_ybar=float(var_ybar), n_degenerate_boot=n_degenerate,\n                       mean_ybar=float(out[\"ybar\"].mean()),\n                       var_ybar_mc=float(np.var(out[\"ybar\"], ddof=1)),\n                       n_distinct_q_min=int(len(np.unique(np.round(out[\"q\"], 12)))))\n    return res\n\n\ndef main():\n    design = pd.read_csv(DATA)\n    R_all, B_all = design.R.unique(), design.B.unique()\n    assert len(R_all) == 1 and len(B_all) == 1\n    R, B = int(R_all[0]), int(B_all[0])\n\n    rows, cov, mcse, rb, extra = [], {}, {}, {}, {}\n    base_cov, base_mcse = {}, {}\n    n_degenerate = 0\n    for _, row in design.iterrows():\n        r = simulate_cell(row)\n        n_degenerate += r[\"meta\"][\"n_degenerate_boot\"]\n        for est in EST:\n            k = key(est, row.G, row.icc)\n            cov[k], mcse[k] = r[est][\"coverage\"], r[est][\"mc_se\"]\n            if est != \"wcb\":\n                rb[k] = r[est][\"rel_bias\"]\n                extra[k + \"_mcse\"] = r[est][\"rel_bias_mcse\"]\n            rows.append(dict(estimator=est, cell_id=row.cell_id, G=int(row.G), icc=float(row.icc),\n                             coverage=r[est][\"coverage\"], mc_se_coverage=r[est][\"mc_se\"],\n                             rel_bias_var=r[est].get(\"rel_bias\", np.nan) if est != \"wcb\" else np.nan,\n                             mean_ci_halfwidth=r[est][\"mean_hw\"], R=int(row.R)))\n        kb = f\"iid_G{int(row.G)}_icc{float(row.icc):.1f}\"\n        base_cov[kb], base_mcse[kb] = r[\"iid\"][\"coverage\"], r[\"iid\"][\"mc_se\"]\n        extra[f\"meta_{row.cell_id}\"] = r[\"meta\"]\n\n    table = pd.DataFrame(rows)\n    table.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\n    failure = [k for k, v in cov.items() if v < 0.90]\n    nominal = [k for k, v in cov.items() if abs(v - 0.95) <= 2 * mcse[k]]\n    g5 = {est: float(np.mean([cov[key(est, 5, i)] for i in sorted(design.icc.unique())])) for est in EST}\n    best = max(g5, key=lambda e: g5[e])\n\n    data_issues = [{\n        \"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct bootstrap weight vectors exist \"\n                 \"(16 distinct |t*| values), so the B=399 draws resample a tiny support and the WCB \"\n                 \"critical value is coarse and typically large.\",\n        \"handling\": \"Procedure kept exactly as specified (no Webb weights, no enumeration); flagged as a \"\n                    \"limitation in the report.\"}]\n    if n_degenerate:\n        data_issues.append({\"issue\": f\"{n_degenerate} bootstrap draws had V*_CR1 = 0\",\n                            \"handling\": \"dropped from that replication's |t*| set before taking the quantile\"})\n\n    results = {\n        \"task_id\": \"T2-simulation\",\n        \"R\": R, \"B\": B, \"n_cells\": int(len(design)),\n        \"coverage\": cov, \"mc_se_coverage\": mcse, \"rel_bias_var\": rb,\n        \"failure_cells\": failure, \"n_failure_cells\": len(failure),\n        \"nominal_cells\": nominal,\n        \"best_procedure_small_G\": best,\n        \"feasibility\": \"complete\", \"feasibility_reason\": None,\n        \"data_issues\": data_issues,\n        \"n_input_rows\": {\"design.csv\": int(len(design))},\n        \"n_analysed\": int(len(design) * R),\n        \"random_seed\": int(design.loc[design.cell_id == \"C1\", \"seed\"].iloc[0]),\n        \"mean_coverage_G5\": g5,\n        \"rel_bias_var_mcse\": {k.replace(\"_mcse\", \"\"): v for k, v in extra.items() if k.endswith(\"_mcse\")},\n        \"baseline_iid_coverage\": base_cov,\n        \"baseline_iid_mc_se_coverage\": base_mcse,\n        \"cell_diagnostics\": {k[5:]: v for k, v in extra.items() if k.startswith(\"meta_\")},\n        \"seeds\": {str(c): int(s) for c, s in zip(design.cell_id, design.seed)},\n        \"wcb_quantile_rule\": \"inverted_cdf 0.95 quantile of |t*| (380th order statistic of 399)\",\n    }\n    with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n        json.dump(results, f, indent=2)\n\n    # figure\n    iccs = sorted(design.icc.unique())\n    Gs = sorted(design.G.unique())\n    fig, axes = plt.subplots(1, len(iccs), figsize=(13, 4.2), sharey=True)\n    styles = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t (Rademacher)\")}\n    for ax, icc in zip(axes, iccs):\n        for est in EST:\n            p = np.array([cov[key(est, g, icc)] for g in Gs])\n            se = np.array([mcse[key(est, g, icc)] for g in Gs])\n            ax.errorbar(Gs, p, yerr=1.96 * se, fmt=styles[est][0], label=styles[est][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\")\n    axes[0].set_ylabel(\"coverage (±1.96 MC SE)\")\n    axes[0].legend(fontsize=8, loc=\"lower right\")\n    fig.suptitle(f\"Coverage of nominal 95% CIs for the mean (R={R}, B={B})\")\n    fig.tight_layout()\n    fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=120)\n    plt.close(fig)\n\n    print(table.to_string(index=False))\n    print(\"failure cells:\", failure)\n    print(\"best procedure at G=5:\", best, g5)\n\n\nif __name__ == \"__main__\":\n    main()\nEOF\ncd .. && time ~/wp29/venv/bin/python out/analysis.py","description":"Write and run simulation script"}}]}}48{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"aa2d4805-fcad-4154-a4a1-79a8ce223e2d","timestamp":"2026-10-30T05:41:02.464Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"3bacb3a6-733c-4ed8-8fd8-e879811057c4","keep":14,"tail":["896c6fc368dbbbfa220d081d0b78a9b80a7b42c783e03dc1ebf8ea1871fd5d79","66201a1ec4d65a4df00c8b7582b08415ffd730457d0fb71a8883f7a8907bf37e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e077021213d2aff38d330ea3cc7947b600b943e2974b9978ad886443808a2e62"}49{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"be48a9e0-65a3-4c47-ba33-fb69739bce8a","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}50{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}51{"parentUuid":"be48a9e0-65a3-4c47-ba33-fb69739bce8a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtM5T6fST4hnm2aJn56","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":6411,"cache_read_input_tokens":13985,"output_tokens":1045,"output_tokens_details":{"thinking_tokens":424},"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":6411},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4124,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtM5Ayr7zfa4Ws1NR4W","requestRef":"aa2d4805-fcad-4154-a4a1-79a8ce223e2d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7636b0c4-9bab-48fe-8b9f-ed8a4cc9c5f2","timestamp":"2026-10-30T05:41:07.777Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}52{"parentUuid":"7636b0c4-9bab-48fe-8b9f-ed8a4cc9c5f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtM5T6fST4hnm2aJn56","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019ZCdDmwxzmubbTa9LLzny6","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,numpy as np\nr=json.load(open('out/results.json'))\nfor c,m in r['cell_diagnostics'].items(): print(c, m['var_ybar'], m['var_ybar_mc'], m['var_ybar_mc']/m['var_ybar'], m['mean_ybar'], m['n_degenerate_boot'])\nprint(r['baseline_iid_coverage'])\n# brute-force check of vectorised bootstrap\nrng=np.random.default_rng(1); sizes=np.array([8,16,32,64,8]); G=5; N=128; cid=np.repeat(np.arange(G),sizes)\ny=rng.normal(size=N)+np.repeat(rng.normal(size=G)*0.6,sizes); yb=y.mean(); e=y-yb\nS=np.bincount(cid,e); W=rng.choice([-1.,1.],size=(20,G))\nd=W@S/N; Ss=W*S-d[:,None]*sizes; v=G/(G-1)*np.sum(Ss**2,1)/N**2\nfor b in range(20):\n  ys=yb+W[b][cid]*e; m=ys.mean(); vv=G/(G-1)*np.sum(np.bincount(cid,ys-m)**2)/N**2\n  assert abs(m-yb-d[b])<1e-12 and abs(vv-v[b])<1e-14\nprint(\"brute-force bootstrap check OK\")\nEOF","description":"Sanity-check variance and bootstrap implementation"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":6411,"cache_read_input_tokens":13985,"output_tokens":1045,"output_tokens_details":{"thinking_tokens":424},"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":6411},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtM5Ayr7zfa4Ws1NR4W","requestRef":"aa2d4805-fcad-4154-a4a1-79a8ce223e2d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"eba80b04-1e6b-4e13-a660-e55569897690","timestamp":"2026-10-30T05:41:12.284Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"eba80b04-1e6b-4e13-a660-e55569897690","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019ZCdDmwxzmubbTa9LLzny6","type":"tool_result","content":"C1 0.0078125 0.008088486730047813 1.03532630144612 0.00028867307788429486 0\nC2 0.0734375 0.07818095367838697 1.0645917096631416 0.010497786660162045 0\nC3 0.171875 0.16265026991742373 0.9463288431559199 -0.005763243574855418 0\nC4 0.003787878787878788 0.0035362244420084166 0.9335632526902219 -8.481537588492616e-05 0\nC5 0.035169880624426074 0.03406304358390313 0.9685288371506661 0.004033474563745705 0\nC6 0.08224288337924701 0.080563566169808 0.979581002751385 -0.0013932598375193423 0\nC7 0.0011574074074074073 0.0011557426105430798 0.9985616155092211 -0.000782799084647925 0\nC8 0.011213991769547326 0.010533848298136778 0.9393486739255914 0.0021016344076126483 0\nC9 0.0262988683127572 0.027362497147835698 1.0404439013279725 -0.0024768417619560603 0\n{'iid_G5_icc0.0': 0.9405, 'iid_G5_icc0.2': 0.46, 'iid_G5_icc0.5': 0.2865, 'iid_G10_icc0.0': 0.957, 'iid_G10_icc0.2': 0.488, 'iid_G10_icc0.5': 0.3125, 'iid_G30_icc0.0': 0.9515, 'iid_G30_icc0.2': 0.485, 'iid_G30_icc0.5': 0.2985}\nbrute-force bootstrap check OK","is_error":false}]},"uuid":"0335f64c-0919-46cc-918a-a9f04a084c4f","timestamp":"2026-10-30T05:41:12.387Z","toolUseResult":{"stdout":"C1 0.0078125 0.008088486730047813 1.03532630144612 0.00028867307788429486 0\nC2 0.0734375 0.07818095367838697 1.0645917096631416 0.010497786660162045 0\nC3 0.171875 0.16265026991742373 0.9463288431559199 -0.005763243574855418 0\nC4 0.003787878787878788 0.0035362244420084166 0.9335632526902219 -8.481537588492616e-05 0\nC5 0.035169880624426074 0.03406304358390313 0.9685288371506661 0.004033474563745705 0\nC6 0.08224288337924701 0.080563566169808 0.979581002751385 -0.0013932598375193423 0\nC7 0.0011574074074074073 0.0011557426105430798 0.9985616155092211 -0.000782799084647925 0\nC8 0.011213991769547326 0.010533848298136778 0.9393486739255914 0.0021016344076126483 0\nC9 0.0262988683127572 0.027362497147835698 1.0404439013279725 -0.0024768417619560603 0\n{'iid_G5_icc0.0': 0.9405, 'iid_G5_icc0.2': 0.46, 'iid_G5_icc0.5': 0.2865, 'iid_G10_icc0.0': 0.957, 'iid_G10_icc0.2': 0.488, 'iid_G10_icc0.5': 0.3125, 'iid_G30_icc0.0': 0.9515, 'iid_G30_icc0.2': 0.485, 'iid_G30_icc0.5': 0.2985}\nbrute-force bootstrap check OK","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"eba80b04-1e6b-4e13-a660-e55569897690","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}54{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"bc0c2ed4e9b54d5027eb81d69f35e76164b057457884d1ddea439d8335e24cbe","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019ZCdDmwxzmubbTa9LLzny6","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,numpy as np\nr=json.load(open('out/results.json'))\nfor c,m in r['cell_diagnostics'].items(): print(c, m['var_ybar'], m['var_ybar_mc'], m['var_ybar_mc']/m['var_ybar'], m['mean_ybar'], m['n_degenerate_boot'])\nprint(r['baseline_iid_coverage'])\n# brute-force check of vectorised bootstrap\nrng=np.random.default_rng(1); sizes=np.array([8,16,32,64,8]); G=5; N=128; cid=np.repeat(np.arange(G),sizes)\ny=rng.normal(size=N)+np.repeat(rng.normal(size=G)*0.6,sizes); yb=y.mean(); e=y-yb\nS=np.bincount(cid,e); W=rng.choice([-1.,1.],size=(20,G))\nd=W@S/N; Ss=W*S-d[:,None]*sizes; v=G/(G-1)*np.sum(Ss**2,1)/N**2\nfor b in range(20):\n  ys=yb+W[b][cid]*e; m=ys.mean(); vv=G/(G-1)*np.sum(np.bincount(cid,ys-m)**2)/N**2\n  assert abs(m-yb-d[b])<1e-12 and abs(vv-v[b])<1e-14\nprint(\"brute-force bootstrap check OK\")\nEOF","description":"Sanity-check variance and bootstrap implementation"}}]}}55{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"f6ef1262-a018-424e-b3e0-10612f4c0dad","timestamp":"2026-10-30T05:41:12.390Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"aa2d4805-fcad-4154-a4a1-79a8ce223e2d","keep":16,"tail":["bc0c2ed4e9b54d5027eb81d69f35e76164b057457884d1ddea439d8335e24cbe","3a56337ba45a5df918049e8dbfb031fa6e38d69ef7cc1d51b1bebe902449c257"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9d4e3c6245eb2c2ecf84f46fccfbce43785c675babe032d6422f7d394cd8074b"}56{"parentUuid":"0335f64c-0919-46cc-918a-a9f04a084c4f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMorkgbJ5GCcr8b6CP","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSggkKEAgTGAI4AUIIdGhpbmtpbmcSDPN0ac5xOONxE31XGhoMDrnhubpj522QGZTDIjBytGt0UFrz9RWu8GoVFBx3vJ6IIjZeRLLXJ/7KFxDZz28yHUzvPgzHYc0gprMnOn0qnwjMAk92f5t3oxHcphCcMu945a4HUeAtPbIrTxf/Bw8SdeRemLeM4C4aQ4zbmLB9fFkibVOyRAKRyVqNw4TTlQShO0tuOTs145L4XlI9hkP7I+LA2cfr4J+xxq565fYQmXH40nUKcH2Owt57N4YpTGKn/m1hxCMTDJJyG2mEZE60Ikf2pU3qOvW7lleX/U8q3YFQPEX2EZGxF96lbTZ24lZWjuCu3NvOR0hnmQtdsoU5+8v7Wm5fzDgVbYhz1yHgVLToEFYiDVSm+3Ct9U0VtE653v/ndAz/Gq0kObitC5HAjunvBjzhACCayrJaQ7o+CbJmlCdAZtL52Di5hBQViQ3N8nQUcQ7rexuaP5AWttbGiJDFkvmACXBeG3+6RX1jMWMfiMEHs5hOaMYhXvz23u/Z3w+QDx/It8QIuosNTyzdecazW/BJUCH5Z+DSTThrLHUaM0Apgjw50BznEGozPiLFIycZzauihl42qnyS7Y3W69SdWvHuFdl4SMjXV8YXkxaMSs8lrEaHfP4wiyizbDjb/Fuu3yAb4nDZCAu0z0D7Kq2J9WaAk5UmbO+IdrMueeMJrDBiQpxllBLR6HObTK+UdOy5in41H1OF8LaO+lGHWQ3EpmOoMKk3vShFZNWvzpDX1IC+HElxuqgFglUR5jDsP/TONzVaAsoISsiJnFIUlk3lmpkuYH9dGFmkmkDI4YOISVo7t5aQPlzWpJ+gmff9JUHo8DzN97RAkuVeMQ6eKUhK+tco4vwVKAmY1Oo+JmM8or8sf+GzUgB6G5oWDnTCmgcDWpORqHuyLV2lJd/GIljh6euUhpcNUrjNI4+XW2t6ciKTjVkDn7ht3rTtMOzI0q14G4PMXT7gOmAUkijlq+05GgXLNPyQQImvjSrXZgoYXeWLctT/G7fyx5ZYV/O0JoPU0k6NP4ARTnh9b2aaHBk71TWDuLaEPDA3/sCEYtATvax2ai3VfrzNiq8VjkziqVyv4kke0+8crqPUTq6U1UiYHrc5heKJL2w884XMW9JhOyCC9kQhpsgl1H1LybIiRlS+yXa73BlrVasNJJlAGPRhaV9iLDIIBYwX6nlcWIdD+wLo17CP8ONoaefqXNRbL1PCf8di0ioodoOu1UnPJp6r+WwymvlIkeGViAFboBmCUKbTKqaXl22GnKabzF2XpgrUHr2z8O9Jdxi1PJT2NtxmjCYNTYRgpmCUy8jPqVuybdwlNhYFYu8nl1yxINjW1zTP5EuP5esEH+3Y2HF2r3Fpd2sx4zjMfPA9uE5Lk1jzEb6UQBaHiQY8Izq7IQ1gNb1dmSZAWKzr/79mnJ0MSu715ZMuzqteSW/UpJV9gKFR03xcS8JlYP2WAoJvajZyON3yzvEeU003WrtRA/4dr0gVK2TwonxRFwo1ooKazxgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1579,"cache_read_input_tokens":20396,"output_tokens":675,"output_tokens_details":{"thinking_tokens":196},"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":1579},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1761,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtMoZtdcyxiqT1hSdiD","requestRef":"f6ef1262-a018-424e-b3e0-10612f4c0dad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6bce3a86-90af-4aac-9a6d-134de691d5c3","timestamp":"2026-10-30T05:41:15.254Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}57{"parentUuid":"6bce3a86-90af-4aac-9a6d-134de691d5c3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMorkgbJ5GCcr8b6CP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VLzG3DpuAC2yDchL7oS2gZ","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,numpy as np\nr=json.load(open('out/results.json'))\nfor G,s in [(5,[8,16,32,64,8]),(10,[8,16,32,64]*2+[8,16]),(30,[8,16,32,64]*7+[8,16])]:\n  s=np.array(s);N=s.sum();cid=np.repeat(np.arange(G),s)\n  for icc in [0.0,0.2,0.5]:\n    Sig=icc*(cid[:,None]==cid[None,:])+(1-icc)*np.eye(N); M=np.eye(N)-1/N\n    A=np.zeros((G,N));A[cid,np.arange(N)]=1\n    EV=np.trace(A@M@Sig@M@A.T)/N**2; V=(icc*np.sum(s**2)+(1-icc)*N)/N**2\n    k=f\"G{G}_icc{icc:.1f}\"; print(k, round(EV/V,4), round(r['rel_bias_var']['cr0_'+k],4), round(r['rel_bias_var_mcse']['cr0_'+k],4))\nEOF","description":"Compare MC relative bias to exact analytic value"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1579,"cache_read_input_tokens":20396,"output_tokens":675,"output_tokens_details":{"thinking_tokens":196},"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":1579},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtMoZtdcyxiqT1hSdiD","requestRef":"f6ef1262-a018-424e-b3e0-10612f4c0dad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5d7191ad-20a4-44e2-ab43-68d8da709ba6","timestamp":"2026-10-30T05:41:18.502Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"5d7191ad-20a4-44e2-ab43-68d8da709ba6","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VLzG3DpuAC2yDchL7oS2gZ","type":"tool_result","content":"G5_icc0.0 0.6641 0.6616 0.013\nG5_icc0.2 0.4995 0.5314 0.013\nG5_icc0.5 0.4883 0.4834 0.0119\nG10_icc0.0 0.8393 0.8558 0.0118\nG10_icc0.2 0.7599 0.7624 0.0129\nG10_icc0.5 0.7544 0.7737 0.0141\nG30_icc0.0 0.9486 0.9438 0.0068\nG30_icc0.2 0.9267 0.9314 0.0085\nG30_icc0.5 0.9253 0.9253 0.0087","is_error":false}]},"uuid":"a50f07bb-1f7f-47ca-9b2c-174c4ede394d","timestamp":"2026-10-30T05:41:18.603Z","toolUseResult":{"stdout":"G5_icc0.0 0.6641 0.6616 0.013\nG5_icc0.2 0.4995 0.5314 0.013\nG5_icc0.5 0.4883 0.4834 0.0119\nG10_icc0.0 0.8393 0.8558 0.0118\nG10_icc0.2 0.7599 0.7624 0.0129\nG10_icc0.5 0.7544 0.7737 0.0141\nG30_icc0.0 0.9486 0.9438 0.0068\nG30_icc0.2 0.9267 0.9314 0.0085\nG30_icc0.5 0.9253 0.9253 0.0087","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5d7191ad-20a4-44e2-ab43-68d8da709ba6","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}59{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"272cac2f686d9ec44a8ef7351e01d98a88b17b9d035b08bfeb9ac1b88580326b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01VLzG3DpuAC2yDchL7oS2gZ","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,numpy as np\nr=json.load(open('out/results.json'))\nfor G,s in [(5,[8,16,32,64,8]),(10,[8,16,32,64]*2+[8,16]),(30,[8,16,32,64]*7+[8,16])]:\n  s=np.array(s);N=s.sum();cid=np.repeat(np.arange(G),s)\n  for icc in [0.0,0.2,0.5]:\n    Sig=icc*(cid[:,None]==cid[None,:])+(1-icc)*np.eye(N); M=np.eye(N)-1/N\n    A=np.zeros((G,N));A[cid,np.arange(N)]=1\n    EV=np.trace(A@M@Sig@M@A.T)/N**2; V=(icc*np.sum(s**2)+(1-icc)*N)/N**2\n    k=f\"G{G}_icc{icc:.1f}\"; print(k, round(EV/V,4), round(r['rel_bias_var']['cr0_'+k],4), round(r['rel_bias_var_mcse']['cr0_'+k],4))\nEOF","description":"Compare MC relative bias to exact analytic value"}}]}}60{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"58a73c66-5bbc-44db-9db1-98a18ad9c931","timestamp":"2026-10-30T05:41:18.606Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"f6ef1262-a018-424e-b3e0-10612f4c0dad","keep":18,"tail":["272cac2f686d9ec44a8ef7351e01d98a88b17b9d035b08bfeb9ac1b88580326b","b1537ab51a4245f325ae8e083520aea5a05515a477d545587df36f717c785083"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ec4102140b0d2d1a17f0f9474f1bb806557ff48afc4fa5c8b7607e81ee0d9a6f"}61{"parentUuid":"a50f07bb-1f7f-47ca-9b2c-174c4ede394d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNGSBByiu8zY8puW3g","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":893,"cache_read_input_tokens":21975,"output_tokens":900,"output_tokens_details":{"thinking_tokens":165},"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":893},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1359,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtNG9JeGHgLrU6NGQry","requestRef":"58a73c66-5bbc-44db-9db1-98a18ad9c931","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"df928653-2906-4cdf-8610-d57524273147","timestamp":"2026-10-30T05:41:21.040Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"df928653-2906-4cdf-8610-d57524273147","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNGSBByiu8zY8puW3g","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016Jewzq75oQJGKznkysCcdC","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py';s=open(p).read()\ns=s.replace('''    res[\"meta\"] = dict(''','''    # exact E[V_CR0]/Var(ybar) (analytic check of the Monte Carlo bias estimate)\n    Mm = np.eye(N) - 1.0 / N\n    Sig = var_u * (cid[:, None] == cid[None, :]) + var_e * np.eye(N)\n    A = np.zeros((G, N)); A[cid, np.arange(N)] = 1.0\n    ev0 = float(np.trace(A @ Mm @ Sig @ Mm @ A.T) / N ** 2)\n    res[\"cr0\"][\"rel_bias_exact\"] = ev0 / var_ybar\n    res[\"cr1\"][\"rel_bias_exact\"] = cr1f * ev0 / var_ybar\n    res[\"meta\"] = dict(''')\ns=s.replace('''                extra[k + \"_mcse\"] = r[est][\"rel_bias_mcse\"]''','''                extra[k + \"_mcse\"] = r[est][\"rel_bias_mcse\"]\n                extra[k + \"_exact\"] = r[est][\"rel_bias_exact\"]''')\ns=s.replace('''        \"baseline_iid_coverage\"''','''        \"rel_bias_var_exact\": {k.replace(\"_exact\", \"\"): v for k, v in extra.items() if k.endswith(\"_exact\")},\n        \"baseline_iid_coverage\"''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && python3 -c \"\nimport json;r=json.load(open('out/results.json'));print(r['rel_bias_var_exact']);print(r['nominal_cells']);print(r['mean_coverage_G5'])\"","description":"Add analytic bias check and rerun"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":893,"cache_read_input_tokens":21975,"output_tokens":900,"output_tokens_details":{"thinking_tokens":165},"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":893},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtNG9JeGHgLrU6NGQry","requestRef":"58a73c66-5bbc-44db-9db1-98a18ad9c931","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d208ae8d-87d8-4524-a918-8e49eafef4cc","timestamp":"2026-10-30T05:41:25.904Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}63{"parentUuid":"d208ae8d-87d8-4524-a918-8e49eafef4cc","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016Jewzq75oQJGKznkysCcdC","type":"tool_result","content":"{'cr0_G5_icc0.0': 0.6640625, 'cr1_G5_icc0.0': 0.830078125, 'cr0_G5_icc0.2': 0.4995013297872341, 'cr1_G5_icc0.2': 0.6243766622340426, 'cr0_G5_icc0.5': 0.48828125, 'cr1_G5_icc0.5': 0.6103515625, 'cr0_G10_icc0.0': 0.8393021120293876, 'cr1_G10_icc0.0': 0.9325579022548752, 'cr0_G10_icc0.2': 0.7598750380616044, 'cr1_G10_icc0.2': 0.8443055978462272, 'cr0_G10_icc0.5': 0.7543877524211221, 'cr1_G10_icc0.5': 0.8382086138012469, 'cr0_G30_icc0.0': 0.9485596707818842, 'cr1_G30_icc0.0': 0.9812686249467768, 'cr0_G30_icc0.2': 0.9267376448823956, 'cr1_G30_icc0.2': 0.9586941153955817, 'cr0_G30_icc0.5': 0.9252970710455035, 'cr1_G30_icc0.5': 0.9572038665987969}\n['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5']\n{'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}","is_error":false}]},"uuid":"89822ccb-1875-4def-a5ea-3921f7b9dd71","timestamp":"2026-10-30T05:41:28.159Z","toolUseResult":{"stdout":"{'cr0_G5_icc0.0': 0.6640625, 'cr1_G5_icc0.0': 0.830078125, 'cr0_G5_icc0.2': 0.4995013297872341, 'cr1_G5_icc0.2': 0.6243766622340426, 'cr0_G5_icc0.5': 0.48828125, 'cr1_G5_icc0.5': 0.6103515625, 'cr0_G10_icc0.0': 0.8393021120293876, 'cr1_G10_icc0.0': 0.9325579022548752, 'cr0_G10_icc0.2': 0.7598750380616044, 'cr1_G10_icc0.2': 0.8443055978462272, 'cr0_G10_icc0.5': 0.7543877524211221, 'cr1_G10_icc0.5': 0.8382086138012469, 'cr0_G30_icc0.0': 0.9485596707818842, 'cr1_G30_icc0.0': 0.9812686249467768, 'cr0_G30_icc0.2': 0.9267376448823956, 'cr1_G30_icc0.2': 0.9586941153955817, 'cr0_G30_icc0.5': 0.9252970710455035, 'cr1_G30_icc0.5': 0.9572038665987969}\n['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5']\n{'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8543333333333334}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d208ae8d-87d8-4524-a918-8e49eafef4cc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}64{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"ff7970314b9662fe4c416504edb5e3668091f3e92b4af893a4cf2a83f62249b6","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016Jewzq75oQJGKznkysCcdC","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py';s=open(p).read()\ns=s.replace('''    res[\"meta\"] = dict(''','''    # exact E[V_CR0]/Var(ybar) (analytic check of the Monte Carlo bias estimate)\n    Mm = np.eye(N) - 1.0 / N\n    Sig = var_u * (cid[:, None] == cid[None, :]) + var_e * np.eye(N)\n    A = np.zeros((G, N)); A[cid, np.arange(N)] = 1.0\n    ev0 = float(np.trace(A @ Mm @ Sig @ Mm @ A.T) / N ** 2)\n    res[\"cr0\"][\"rel_bias_exact\"] = ev0 / var_ybar\n    res[\"cr1\"][\"rel_bias_exact\"] = cr1f * ev0 / var_ybar\n    res[\"meta\"] = dict(''')\ns=s.replace('''                extra[k + \"_mcse\"] = r[est][\"rel_bias_mcse\"]''','''                extra[k + \"_mcse\"] = r[est][\"rel_bias_mcse\"]\n                extra[k + \"_exact\"] = r[est][\"rel_bias_exact\"]''')\ns=s.replace('''        \"baseline_iid_coverage\"''','''        \"rel_bias_var_exact\": {k.replace(\"_exact\", \"\"): v for k, v in extra.items() if k.endswith(\"_exact\")},\n        \"baseline_iid_coverage\"''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && python3 -c \"\nimport json;r=json.load(open('out/results.json'));print(r['rel_bias_var_exact']);print(r['nominal_cells']);print(r['mean_coverage_G5'])\"","description":"Add analytic bias check and rerun"}}]}}65{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"1c9d5182-ca31-4cee-9737-46c15823d38d","timestamp":"2026-10-30T05:41:28.161Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"58a73c66-5bbc-44db-9db1-98a18ad9c931","keep":20,"tail":["ff7970314b9662fe4c416504edb5e3668091f3e92b4af893a4cf2a83f62249b6","571a4220d30806cedbd8a642bde5963b113e297aabe5acd918f35546f6021cfd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d5c4c4800d032c85cf8cf8bf81a7ccc42c6cd3e69af40f0b927642ce09cdeb9b"}66{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"89822ccb-1875-4def-a5ea-3921f7b9dd71","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}67{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}68{"parentUuid":"89822ccb-1875-4def-a5ea-3921f7b9dd71","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNyHKKoRThianxtaiM","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":1430,"cache_read_input_tokens":22868,"output_tokens":1773,"output_tokens_details":{"thinking_tokens":90},"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":1430},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":557,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtNxzToXpdm1fWCH1Jw","requestRef":"1c9d5182-ca31-4cee-9737-46c15823d38d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1982d6db-630f-45d3-935d-80d457459abe","timestamp":"2026-10-30T05:41:29.799Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}69{"parentUuid":"1982d6db-630f-45d3-935d-80d457459abe","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNyHKKoRThianxtaiM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PePHdkVtwnqs8vMSz3fscs","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && md5 -q out/table1.csv > /tmp/t1 && 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 && echo IDENTICAL && [ \"$(md5 -q out/table1.csv)\" = \"$(cat /tmp/t1)\" ] && echo TABLE_IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,math,pandas as pd\nr=json.load(open('out/results.json'));t=pd.read_csv('out/table1.csv')\nc=[]\nc.append((\"27 coverage keys / 27 mcse keys / 18 rel_bias keys\", len(r['coverage'])==27 and len(r['mc_se_coverage'])==27 and len(r['rel_bias_var'])==18))\nc.append((\"table1 has 27 rows, wcb rel_bias empty\", len(t)==27 and t[t.estimator=='wcb'].rel_bias_var.isna().all() and t[t.estimator!='wcb'].rel_bias_var.notna().all()))\nc.append((\"coverages in [0,1], mc se >0 and = sqrt(p(1-p)/R)\", all(0<=v<=1 for v in r['coverage'].values()) and all(r['mc_se_coverage'][k]>0 and abs(r['mc_se_coverage'][k]-math.sqrt(v*(1-v)/2000))<1e-12 for k,v in r['coverage'].items())))\nc.append((\"n_failure_cells == len(failure_cells) and failure set matches rule\", r['n_failure_cells']==len(r['failure_cells']) and set(r['failure_cells'])=={k for k,v in r['coverage'].items() if v<0.9}))\nc.append((\"nominal set matches rule\", set(r['nominal_cells'])=={k for k,v in r['coverage'].items() if abs(v-.95)<=2*r['mc_se_coverage'][k]}))\nc.append((\"n_analysed = 9*2000\", r['n_analysed']==18000))\nc.append((\"cr1 rel bias = G/(G-1)*cr0 rel bias\", all(abs(r['rel_bias_var']['cr1'+k[3:]]-int(k.split('_G')[1].split('_')[0])/(int(k.split('_G')[1].split('_')[0])-1)*v)<1e-9 for k,v in r['rel_bias_var'].items() if k.startswith('cr0'))))\nz=[abs(r['rel_bias_var'][k]-r['rel_bias_var_exact'][k])/r['rel_bias_var_mcse'][k] for k in r['rel_bias_var']]\nc.append((f\"MC rel bias vs exact analytic: max |z| = {max(z):.2f} (<3)\", max(z)<3))\nc.append((\"cr1 halfwidth > cr0 halfwidth in every cell\", all(t[(t.estimator=='cr1')].mean_ci_halfwidth.values>t[(t.estimator=='cr0')].mean_ci_halfwidth.values)))\nc.append((\"cr1 coverage >= cr0 coverage in every cell (nested intervals)\", all(r['coverage']['cr1'+k[3:]]>=v for k,v in r['coverage'].items() if k.startswith('cr0'))))\nc.append((\"best_procedure_small_G is argmax of mean_coverage_G5\", r['best_procedure_small_G']==max(r['mean_coverage_G5'],key=r['mean_coverage_G5'].get)))\nc.append((\"no degenerate bootstrap draws\", all(m['n_degenerate_boot']==0 for m in r['cell_diagnostics'].values())))\nopen('out/state/checks.md','w').write(\"# Verification checks (P4)\\n\\n- Clean re-run (deleted results.json/table1.csv/figure1.png, re-ran analysis.py): results.json byte-identical, table1.csv identical — PASS\\n- Brute-force check of vectorised bootstrap (explicit y* construction, 20 draws) matched to 1e-12 — PASS\\n- MC Var(ybar)/exact Var(ybar) in 0.93–1.06 across cells (cell_diagnostics), consistent with MC error (~3% SE for R=2000) — PASS\\n\"+\"\".join(f\"- {n} — {'PASS' if ok else 'FAIL'}\\n\" for n,ok in c))\nfor n,ok in c: print(ok,n)\nEOF","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":1430,"cache_read_input_tokens":22868,"output_tokens":1773,"output_tokens_details":{"thinking_tokens":90},"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":1430},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtNxzToXpdm1fWCH1Jw","requestRef":"1c9d5182-ca31-4cee-9737-46c15823d38d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"32c1c327-0593-4824-8845-2ccca7527e00","timestamp":"2026-10-30T05:41:41.738Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}70{"parentUuid":"32c1c327-0593-4824-8845-2ccca7527e00","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PePHdkVtwnqs8vMSz3fscs","type":"tool_result","content":"IDENTICAL\nTABLE_IDENTICAL\nTrue 27 coverage keys / 27 mcse keys / 18 rel_bias keys\nTrue table1 has 27 rows, wcb rel_bias empty\nTrue coverages in [0,1], mc se >0 and = sqrt(p(1-p)/R)\nTrue n_failure_cells == len(failure_cells) and failure set matches rule\nTrue nominal set matches rule\nTrue n_analysed = 9*2000\nTrue cr1 rel bias = G/(G-1)*cr0 rel bias\nTrue MC rel bias vs exact analytic: max |z| = 2.46 (<3)\nTrue cr1 halfwidth > cr0 halfwidth in every cell\nTrue cr1 coverage >= cr0 coverage in every cell (nested intervals)\nTrue best_procedure_small_G is argmax of mean_coverage_G5\nTrue no degenerate bootstrap draws","is_error":false}]},"uuid":"d38f379a-e713-4e9d-bd2f-c4478027cd09","timestamp":"2026-10-30T05:41:44.130Z","toolUseResult":{"stdout":"IDENTICAL\nTABLE_IDENTICAL\nTrue 27 coverage keys / 27 mcse keys / 18 rel_bias keys\nTrue table1 has 27 rows, wcb rel_bias empty\nTrue coverages in [0,1], mc se >0 and = sqrt(p(1-p)/R)\nTrue n_failure_cells == len(failure_cells) and failure set matches rule\nTrue nominal set matches rule\nTrue n_analysed = 9*2000\nTrue cr1 rel bias = G/(G-1)*cr0 rel bias\nTrue MC rel bias vs exact analytic: max |z| = 2.46 (<3)\nTrue cr1 halfwidth > cr0 halfwidth in every cell\nTrue cr1 coverage >= cr0 coverage in every cell (nested intervals)\nTrue best_procedure_small_G is argmax of mean_coverage_G5\nTrue no degenerate bootstrap draws","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"32c1c327-0593-4824-8845-2ccca7527e00","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}71{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"28d7791693f41f5fa0ee37d408fb6d4a58e5ef389c0a45a66b007f0e67dafdff","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01PePHdkVtwnqs8vMSz3fscs","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && md5 -q out/table1.csv > /tmp/t1 && 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 && echo IDENTICAL && [ \"$(md5 -q out/table1.csv)\" = \"$(cat /tmp/t1)\" ] && echo TABLE_IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,math,pandas as pd\nr=json.load(open('out/results.json'));t=pd.read_csv('out/table1.csv')\nc=[]\nc.append((\"27 coverage keys / 27 mcse keys / 18 rel_bias keys\", len(r['coverage'])==27 and len(r['mc_se_coverage'])==27 and len(r['rel_bias_var'])==18))\nc.append((\"table1 has 27 rows, wcb rel_bias empty\", len(t)==27 and t[t.estimator=='wcb'].rel_bias_var.isna().all() and t[t.estimator!='wcb'].rel_bias_var.notna().all()))\nc.append((\"coverages in [0,1], mc se >0 and = sqrt(p(1-p)/R)\", all(0<=v<=1 for v in r['coverage'].values()) and all(r['mc_se_coverage'][k]>0 and abs(r['mc_se_coverage'][k]-math.sqrt(v*(1-v)/2000))<1e-12 for k,v in r['coverage'].items())))\nc.append((\"n_failure_cells == len(failure_cells) and failure set matches rule\", r['n_failure_cells']==len(r['failure_cells']) and set(r['failure_cells'])=={k for k,v in r['coverage'].items() if v<0.9}))\nc.append((\"nominal set matches rule\", set(r['nominal_cells'])=={k for k,v in r['coverage'].items() if abs(v-.95)<=2*r['mc_se_coverage'][k]}))\nc.append((\"n_analysed = 9*2000\", r['n_analysed']==18000))\nc.append((\"cr1 rel bias = G/(G-1)*cr0 rel bias\", all(abs(r['rel_bias_var']['cr1'+k[3:]]-int(k.split('_G')[1].split('_')[0])/(int(k.split('_G')[1].split('_')[0])-1)*v)<1e-9 for k,v in r['rel_bias_var'].items() if k.startswith('cr0'))))\nz=[abs(r['rel_bias_var'][k]-r['rel_bias_var_exact'][k])/r['rel_bias_var_mcse'][k] for k in r['rel_bias_var']]\nc.append((f\"MC rel bias vs exact analytic: max |z| = {max(z):.2f} (<3)\", max(z)<3))\nc.append((\"cr1 halfwidth > cr0 halfwidth in every cell\", all(t[(t.estimator=='cr1')].mean_ci_halfwidth.values>t[(t.estimator=='cr0')].mean_ci_halfwidth.values)))\nc.append((\"cr1 coverage >= cr0 coverage in every cell (nested intervals)\", all(r['coverage']['cr1'+k[3:]]>=v for k,v in r['coverage'].items() if k.startswith('cr0'))))\nc.append((\"best_procedure_small_G is argmax of mean_coverage_G5\", r['best_procedure_small_G']==max(r['mean_coverage_G5'],key=r['mean_coverage_G5'].get)))\nc.append((\"no degenerate bootstrap draws\", all(m['n_degenerate_boot']==0 for m in r['cell_diagnostics'].values())))\nopen('out/state/checks.md','w').write(\"# Verification checks (P4)\\n\\n- Clean re-run (deleted results.json/table1.csv/figure1.png, re-ran analysis.py): results.json byte-identical, table1.csv identical — PASS\\n- Brute-force check of vectorised bootstrap (explicit y* construction, 20 draws) matched to 1e-12 — PASS\\n- MC Var(ybar)/exact Var(ybar) in 0.93–1.06 across cells (cell_diagnostics), consistent with MC error (~3% SE for R=2000) — PASS\\n\"+\"\".join(f\"- {n} — {'PASS' if ok else 'FAIL'}\\n\" for n,ok in c))\nfor n,ok in c: print(ok,n)\nEOF","description":"Reproducibility and consistency checks"}}]}}72{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"738c4f1b-b5a9-4eb2-b92f-eb5886356531","timestamp":"2026-10-30T05:41:44.132Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"1c9d5182-ca31-4cee-9737-46c15823d38d","keep":22,"tail":["28d7791693f41f5fa0ee37d408fb6d4a58e5ef389c0a45a66b007f0e67dafdff","44e604a9343bb5b091fc900421616212ce49b98c37d227b2d31dfc68ceff8164"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a13143d328b8e1e06a3071d57003f7a34fbd059a6cada6bfc5a445d224806690"}73{"parentUuid":"d38f379a-e713-4e9d-bd2f-c4478027cd09","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQ9Zz5Lgnq1Dzwy4iM","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":2053,"cache_read_input_tokens":24298,"output_tokens":579,"output_tokens_details":{"thinking_tokens":64},"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":2053},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":437,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtQ9JMrzZw7WvyY7Wzk","requestRef":"738c4f1b-b5a9-4eb2-b92f-eb5886356531","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1069948c-280b-4375-ae71-518f9b062f8c","timestamp":"2026-10-30T05:41:45.595Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}74{"parentUuid":"1069948c-280b-4375-ae71-518f9b062f8c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQ9Zz5Lgnq1Dzwy4iM","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GiXjsLq3ACA6cmKNWNbk53","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"baseline naive iid-SE z-interval coverage computed on the same replications (results.json baseline_iid_coverage)\",\"iid coverage ~0.94-0.96 at ICC=0 and 0.29-0.49 at ICC>0, as expected\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/design.csv, seeds per cell via default_rng(seed)\",\"runtime ~2s\",\"brute-force check of vectorised WCB passed\"],\"notes\":\"WCB quantile rule: inverted_cdf (380th order stat of 399)\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json and table1.csv\",\"12 consistency checks in checks.md all PASS\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P2, P3 passed; P4 checks pass; running gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .; ls out/state/gate_receipts","description":"Update ledger 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":2053,"cache_read_input_tokens":24298,"output_tokens":579,"output_tokens_details":{"thinking_tokens":64},"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":2053},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtQ9JMrzZw7WvyY7Wzk","requestRef":"738c4f1b-b5a9-4eb2-b92f-eb5886356531","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"78e8e045-9e7c-4e1b-8cd5-5753cc6ccd0b","timestamp":"2026-10-30T05:41:48.982Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}75{"parentUuid":"78e8e045-9e7c-4e1b-8cd5-5753cc6ccd0b","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GiXjsLq3ACA6cmKNWNbk53","type":"tool_result","content":"PGAR 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 2.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0023/out/state/gate_receipts/20261030T054151.239822Z.json\n20261030T054151.239822Z.json","is_error":false}]},"uuid":"98397abd-b821-49ba-8c19-438bff963d38","timestamp":"2026-10-30T05:41:51.247Z","toolUseResult":{"stdout":"PGAR 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 2.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0023/out/state/gate_receipts/20261030T054151.239822Z.json\n20261030T054151.239822Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"78e8e045-9e7c-4e1b-8cd5-5753cc6ccd0b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}76{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"bb1cd74083e4fe5984879e0ef7b377917792a79fb119c721131df1a5c9b84e7a","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01GiXjsLq3ACA6cmKNWNbk53","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"baseline naive iid-SE z-interval coverage computed on the same replications (results.json baseline_iid_coverage)\",\"iid coverage ~0.94-0.96 at ICC=0 and 0.29-0.49 at ICC>0, as expected\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/design.csv, seeds per cell via default_rng(seed)\",\"runtime ~2s\",\"brute-force check of vectorised WCB passed\"],\"notes\":\"WCB quantile rule: inverted_cdf (380th order stat of 399)\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json and table1.csv\",\"12 consistency checks in checks.md all PASS\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P2, P3 passed; P4 checks pass; running gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .; ls out/state/gate_receipts","description":"Update ledger and run gate"}}]}}77{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"82cc8c66-adfb-47c9-b098-025490f877ba","timestamp":"2026-10-30T05:41:51.249Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"738c4f1b-b5a9-4eb2-b92f-eb5886356531","keep":24,"tail":["bb1cd74083e4fe5984879e0ef7b377917792a79fb119c721131df1a5c9b84e7a","2cbf80113f7c0e391b5c494befbe9a71b7e80abba461affbd25ab4f1eb1ffafd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"25b84787e7687dac3ed26104d143b02f96864e8314ba509a65b1b91c7e161156"}78{"type":"tools-used","tools":["Bash","Read"],"sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}79{"parentUuid":"98397abd-b821-49ba-8c19-438bff963d38","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQg536pbXKsJ1zw8Me","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":1304,"cache_read_input_tokens":26351,"output_tokens":149,"output_tokens_details":{"thinking_tokens":68},"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":1304},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":480,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtQfnRUEvfwRRQUEekh","requestRef":"82cc8c66-adfb-47c9-b098-025490f877ba","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5ad27789-b16a-40de-b1ac-7be0a06300a1","timestamp":"2026-10-30T05:41:52.739Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}80{"parentUuid":"5ad27789-b16a-40de-b1ac-7be0a06300a1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQg536pbXKsJ1zw8Me","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01U94kVfGN8mchQYk5HRsuLe","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0023/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":1304,"cache_read_input_tokens":26351,"output_tokens":149,"output_tokens_details":{"thinking_tokens":68},"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":1304},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtQfnRUEvfwRRQUEekh","requestRef":"82cc8c66-adfb-47c9-b098-025490f877ba","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"68eb01b0-45db-4e4c-8e66-af67cce62802","timestamp":"2026-10-30T05:41:53.047Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}81{"parentUuid":"68eb01b0-45db-4e4c-8e66-af67cce62802","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01U94kVfGN8mchQYk5HRsuLe","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"bbf3e35c-1b13-4e27-8104-423966eca830","timestamp":"2026-10-30T05:41:53.081Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":75537,"dimensions":{"originalWidth":1560,"originalHeight":504,"displayWidth":1560,"displayHeight":504}}},"sourceToolAssistantUUID":"68eb01b0-45db-4e4c-8e66-af67cce62802","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}82{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"a986225694ead0f7dbbe828862a343214cf616dfb7cb723f62e7dec6fcd3ade3","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01U94kVfGN8mchQYk5HRsuLe","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0023/out/figure1.png"}}]}}83{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"7cb2fce3-b31a-4244-9cc9-109d09cef60e","timestamp":"2026-10-30T05:41:53.089Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"82cc8c66-adfb-47c9-b098-025490f877ba","keep":26,"tail":["a986225694ead0f7dbbe828862a343214cf616dfb7cb723f62e7dec6fcd3ade3","eb198b40ad066c3a9174cd140ad96cbf209b2791fafedd065cd279cdf1ae90ae"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d1d748a64ed23a6fcc397744303100203d3a817b071159f59e5d0c271191f131"}84{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"bbf3e35c-1b13-4e27-8104-423966eca830","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}85{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}86{"parentUuid":"bbf3e35c-1b13-4e27-8104-423966eca830","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQopcTYBjxb68MYvRK","type":"message","role":"assistant","content":[{"type":"text","text":"Fix the stray minor tick labels on the log axis."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1176,"cache_read_input_tokens":27655,"output_tokens":744,"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":1176},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtQoaj4S5EcfRZaCaqY","requestRef":"7cb2fce3-b31a-4244-9cc9-109d09cef60e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fde6c5f8-670a-4be0-9f16-2251c937a8fd","timestamp":"2026-10-30T05:41:54.790Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}87{"parentUuid":"fde6c5f8-670a-4be0-9f16-2251c937a8fd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQopcTYBjxb68MYvRK","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016SeMurS3zWta6QciP2Nvyy","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py';s=open(p).read()\ns=s.replace('ax.set_xticklabels([str(g) for g in Gs])','ax.set_xticklabels([str(g) for g in Gs])\\n        ax.xaxis.set_minor_formatter(matplotlib.ticker.NullFormatter())')\ns=s.replace('import matplotlib.pyplot as plt','import matplotlib.pyplot as plt\\nimport matplotlib.ticker')\nopen(p,'w').write(s)\nEOF\n~/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;p=json.load(open('out/state/phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json and table1.csv\",\"12 consistency checks in checks.md all PASS (incl. MC vs analytic rel-bias, max |z|=2.46)\",\"gate run 20261030T054151.239822Z: all results-key and reproducibility checks ok; only failures = P5 deliverables not yet written (report, claims, sections, non-terminal ledger)\",\"figure tick-label cosmetic fix; results.json unchanged (cmp)\"],\"notes\":\"gate_receipts: out/state/gate_receipts/20261030T054151.239822Z.json\",\"gate_receipts\":[\"out/state/gate_receipts/20261030T054151.239822Z.json\"]}\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 run 1: only P5 items missing). Starting P5.\" >> out/state/log.md","description":"Fix figure ticks, rerun, 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":1176,"cache_read_input_tokens":27655,"output_tokens":744,"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":1176},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtQoaj4S5EcfRZaCaqY","requestRef":"7cb2fce3-b31a-4244-9cc9-109d09cef60e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b97d7496-8a15-4c28-b5cc-efa8de1b556f","timestamp":"2026-10-30T05:41:59.793Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}88{"parentUuid":"b97d7496-8a15-4c28-b5cc-efa8de1b556f","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016SeMurS3zWta6QciP2Nvyy","type":"tool_result","content":"SAME","is_error":false}]},"uuid":"bf065001-680c-477f-ad76-4a65d165f7f9","timestamp":"2026-10-30T05:42:02.001Z","toolUseResult":{"stdout":"SAME","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b97d7496-8a15-4c28-b5cc-efa8de1b556f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}89{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"1eb0d94062456309eb3030881ee6b1f5ea09112b6d372d547d39df2261fb3908","message":{"role":"assistant","content":[{"type":"text","text":"Fix the stray minor tick labels on the log axis."},{"type":"tool_use","id":"toolu_016SeMurS3zWta6QciP2Nvyy","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py';s=open(p).read()\ns=s.replace('ax.set_xticklabels([str(g) for g in Gs])','ax.set_xticklabels([str(g) for g in Gs])\\n        ax.xaxis.set_minor_formatter(matplotlib.ticker.NullFormatter())')\ns=s.replace('import matplotlib.pyplot as plt','import matplotlib.pyplot as plt\\nimport matplotlib.ticker')\nopen(p,'w').write(s)\nEOF\n~/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;p=json.load(open('out/state/phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json and table1.csv\",\"12 consistency checks in checks.md all PASS (incl. MC vs analytic rel-bias, max |z|=2.46)\",\"gate run 20261030T054151.239822Z: all results-key and reproducibility checks ok; only failures = P5 deliverables not yet written (report, claims, sections, non-terminal ledger)\",\"figure tick-label cosmetic fix; results.json unchanged (cmp)\"],\"notes\":\"gate_receipts: out/state/gate_receipts/20261030T054151.239822Z.json\",\"gate_receipts\":[\"out/state/gate_receipts/20261030T054151.239822Z.json\"]}\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 run 1: only P5 items missing). Starting P5.\" >> out/state/log.md","description":"Fix figure ticks, rerun, update ledger"}}]}}90{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"2bc0db13-6287-4d06-bec1-eeccbb72e411","timestamp":"2026-10-30T05:42:02.004Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"7cb2fce3-b31a-4244-9cc9-109d09cef60e","keep":28,"tail":["1eb0d94062456309eb3030881ee6b1f5ea09112b6d372d547d39df2261fb3908","ed5e869083c98da9d3f0ab7c573d7c807bdc4e3733acb94c47e76ec0733d08ad"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"32f8d926a2ce493df80061f9d7328c9581a9a24cf29c78c31cbae195a8cd16c4"}91{"parentUuid":"bf065001-680c-477f-ad76-4a65d165f7f9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRTxYfSVfGBKq2CCpL","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":752,"cache_read_input_tokens":28831,"output_tokens":4961,"output_tokens_details":{"thinking_tokens":57},"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":752},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":442,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtRTgBT6MxvnSTpwqVN","requestRef":"2bc0db13-6287-4d06-bec1-eeccbb72e411","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"86367f73-a3d3-417a-b1ee-3d35b2875656","timestamp":"2026-10-30T05:42:03.542Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}92{"parentUuid":"86367f73-a3d3-417a-b1ee-3d35b2875656","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRTxYfSVfGBKq2CCpL","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Xv5NPByMWkjQzExKqHWEsg","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 (T2-simulation)\n\n## Question\nWhen N observations come from a small number G of unequal-size clusters, how close to 95% is the actual coverage of three cluster-robust intervals for the population mean μ, using the sample mean ȳ as estimator? For each of nine cells (G ∈ {5, 10, 30} × ICC ∈ {0.0, 0.2, 0.5}) we estimate coverage (`coverage`), its Monte Carlo SE (`mc_se_coverage`), the relative bias E[V̂]/Var(ȳ) of the CR0 and CR1 variance estimators (`rel_bias_var`), and the failure regimes where coverage is below 0.90 (`failure_cells`).\n\n## Data and exclusions\nThere is no observed data. The only input is `data/design.csv` (9 rows, `n_input_rows`; SHA-256 f4ff004e…c50, see `out/state/data_audit.md`). Every row passed the consistency checks (number of sizes = G, sum of sizes = N). No exclusions were applied (`out/exclusions.csv`: 9 → 9 cells). In each cell R = 2000 replications (`R`) and B = 399 bootstrap draws (`B`) were used, giving 18,000 simulated samples (`n_analysed`). Cell seeds are 20261101–20261109; C1's seed is 20261101 (`random_seed`, all seeds under `seeds`). Cluster sizes follow 8, 16, 32, 64 repeated, so with G = 5 the 64-observation cluster contains half the sample. One design-related issue is recorded in `data_issues`: with G = 5, Rademacher weights can produce only 32 distinct weight vectors. No bootstrap draw had a zero variance (`cell_diagnostics.*.n_degenerate_boot` = 0).\n\n## Method\nEach replication draws y_ig = μ + u_g + e_ig, with u_g ~ N(0, ICC) and e_ig ~ N(0, 1−ICC), using `numpy.random.default_rng(cell seed)`. Within each replication the draws are made in this order: u, e, then the B×G Rademacher matrix. The exact variance is Var(ȳ) = [ICC·Σn_g² + (1−ICC)N]/N².\n- **CR0**: V̂ = Σ_g S_g²/N², where S_g is the sum of residuals y − ȳ in cluster g; 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**: unrestricted wild cluster bootstrap-t with Rademacher weights. This is vectorised: ȳ* − ȳ = Σ w_g S_g/N, and the bootstrap cluster residual sums are w_g S_g − n_g(ȳ* − ȳ). These give V̂*_CR1 and |t*_b|. The critical value q is the 0.95 empirical quantile of the 399 |t*| values. I took this to be the `inverted_cdf` quantile, which is the 380th order statistic (`wcb_quantile_rule`). The interval is ȳ ± q√V̂_CR1. A brute-force check that builds y* explicitly matched the vectorised version to 1e-12 (`out/state/checks.md`).\n- Coverage is the share of replications with |ȳ − μ| ≤ half-width. MC SE = √(p̂(1−p̂)/R). Relative bias is the mean of V̂ over replications divided by the exact Var(ȳ).\n- **Baseline (P2)**: a naive i.i.d.-SE z-interval computed on the same replications (`baseline_iid_coverage`).\n- Running `out/analysis.py` regenerates `results.json`, `table1.csv` and `figure1.png` in about 2 s. A clean re-run gave byte-identical output.\n\n## Results\nFull numbers are in `out/table1.csv` and `out/figure1.png`.\n- **Naive baseline**: ignoring clustering gives coverage of about 0.29–0.49 whenever ICC > 0 (e.g. `baseline_iid_coverage.iid_G30_icc0.5` = 0.2985). At ICC = 0 it gives about 0.94–0.96. Some cluster correction is therefore necessary.\n- **CR0** under-covers in every cell:\n  - G = 5: 0.7805 / 0.7210 / 0.7170 for ICC 0 / 0.2 / 0.5 (`coverage.cr0_G5_icc0.0`, `cr0_G5_icc0.2`, `cr0_G5_icc0.5`);\n  - G = 10: 0.8965 / 0.8570 / 0.8530 (`coverage.cr0_G10_*`);\n  - G = 30: still only 0.9275 / 0.9210 / 0.9165 (`coverage.cr0_G30_*`).\n- **CR0 variance bias**: E[V̂_CR0]/Var(ȳ) is 0.66 / 0.53 / 0.48 at G = 5 (`rel_bias_var.cr0_G5_*`), 0.86 / 0.76 / 0.77 at G = 10 and 0.94 / 0.93 / 0.93 at G = 30. These Monte Carlo values agree with the analytic expectation (`rel_bias_var_exact`) within 2.5 MC SE in all 18 cases.\n- **CR1** removes only part of the variance bias: 0.83 / 0.66 / 0.60 at G = 5 (`rel_bias_var.cr1_G5_*`) and 0.95–0.98 at G = 30. Its t critical value adds more width.\n  - Coverage at G = 5: 0.9115 / 0.8845 / 0.8755 (`coverage.cr1_G5_*`).\n  - Coverage at G = 10: 0.9435 / 0.9155 / 0.9065.\n  - Coverage at G = 30: 0.9400 / 0.9350 / 0.9300.\n- **WCB** has the best coverage at G = 10 and G = 30 when ICC > 0 (0.9325 and 0.9350 at G = 10, `coverage.wcb_G10_icc0.2`, `wcb_G10_icc0.5`; 0.9445–0.9470 at G = 30). At G = 5 it fails: 0.8575 / 0.8545 / 0.8510 (`coverage.wcb_G5_*`). This happens even though its mean half-width there is the largest of the three procedures (`table1.csv`, `mean_ci_halfwidth`).\n- **Failure regimes** (coverage < 0.90): 11 of the 27 pairs (`n_failure_cells`, `failure_cells`):\n  - all three CR0 cells at G = 5 and all three at G = 10;\n  - all three WCB cells at G = 5;\n  - CR1 at G = 5 with ICC 0.2 and 0.5.\n- **Best procedure at G = 5**: CR1 has the highest average coverage over the G = 5 cells (0.8905 vs WCB 0.8543 and CR0 0.7395; `best_procedure_small_G`, `mean_coverage_G5`).\n- **Consistent with nominal 95%** (|p̂ − 0.95| ≤ 2 MC SE): only 5 pairs (`nominal_cells`): CR1 at G = 10 and G = 30 with ICC = 0, and WCB at G = 30 for all three ICC values.\n\n## Uncertainty\nEach coverage estimate is a binomial proportion based on R = 2000 replications. Its MC SE (`mc_se_coverage`) runs from 0.0050 (near 0.95) to 0.0101 (near 0.72). A ±2 SE band near the nominal level is therefore about ±0.010–0.011, and differences between procedures smaller than about 0.015 within a cell should not be over-interpreted. However, all procedures in a cell share the same replications, so paired comparisons are more precise than independent SEs suggest. That pairing was not separately quantified.\n\nThe MC SE of the relative-bias estimates (`rel_bias_var_mcse`) is about 0.012–0.014 at G = 5–10 and 0.007–0.009 at G = 30. The largest MC-vs-analytic discrepancy is 2.46 SE (`out/state/checks.md`).\n\nThe \"nominal\" classification uses a 2-SE rule applied separately to 27 pairs, with no multiplicity adjustment. Pairs close to the boundary (e.g. WCB at G = 10, 0.9325–0.9375) could change class under another seed. Similarly, failure classifications near 0.90 (CR0 at G = 10/ICC 0, 0.8965; CR1 at G = 10/ICC 0.5, 0.9065) are within one MC SE of the threshold.\n\nThe WCB critical value has its own Monte Carlo noise from B = 399. That noise is included in the coverage estimate but not separated from it.\n\n## Limitations and open issues\n- **Distributions**: only Gaussian random effects and errors were simulated. Skewed or heavy-tailed u_g or e_ig, which are known to hurt few-cluster inference, are not covered.\n- **Heterogeneity**: the ICC is common to all clusters, and errors are homoskedastic within and across clusters. Heterogeneity tied to cluster size, and informative cluster sizes, are not covered.\n- **Cluster-size design**: only one unbalanced pattern (8, 16, 32, 64) was used. With G = 5 a single cluster holds 50% of N, which drives the CR0/CR1 downward bias (high leverage). Balanced designs, or other degrees of imbalance, could give different rankings.\n- **Regressors**: the estimand is a plain mean (intercept-only model). Regression coefficients, especially for treatments that vary only at the cluster level or are given to few clusters, are not covered.\n- **Other weights and variants**:\n  - Only Rademacher weights were used, in the unrestricted (WCU) form. Webb six-point weights, Mammen weights, restricted (null-imposed, WCR) bootstrap and full enumeration of the 2^5 weight vectors at G = 5 were not studied.\n  - With G = 5, Rademacher weights give only 16 distinct |t*| values (`data_issues`). Under-coverage of WCB at G = 5 is therefore at least partly a property of this weight choice.\n  - CR2/CR3 (Bell–McCaffrey) corrections and other degrees-of-freedom rules were not studied.\n- **Quantile convention**: the WCB quantile rule (380th of 399 order statistics) is my choice for the unspecified \"empirical quantile\". Other interpolation rules would change q slightly.\n- **Grid**: only G ∈ {5, 10, 30} and three ICC values were simulated. The G at which each procedure reaches nominal coverage is not pinned down.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"CR0 under-covers in every design cell, failing (<0.90) in all G=5 and G=10 cells and reaching only 0.9165-0.9275 at G=30.\",\"results_keys\":[\"coverage\",\"failure_cells\"],\"status\":\"supported\",\"caveat\":\"CR0 at G=10, ICC=0 (0.8965) is within one MC SE of the 0.90 threshold.\"},\n {\"id\":\"C2\",\"text\":\"The CR0 variance estimator is biased downward, with E[V_CR0]/Var(ybar) of about 0.48-0.66 at G=5 and 0.93-0.94 at G=30; the Monte Carlo estimates agree with the analytic expectation within 2.5 MC SE.\",\"results_keys\":[\"rel_bias_var\",\"rel_bias_var_exact\",\"rel_bias_var_mcse\"],\"status\":\"supported\",\"caveat\":\"Specific to the 8/16/32/64 unbalanced design and Gaussian DGP.\"},\n {\"id\":\"C3\",\"text\":\"CR1 (G/(G-1) scaling with t_{G-1}) has the highest average coverage at G=5 (0.8905) but still fails for ICC 0.2 and 0.5 at G=5.\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_G5\",\"coverage\",\"failure_cells\"],\"status\":\"supported\",\"caveat\":\"CR1 vs WCB difference at G=5 ICC=0.5 (0.8755 vs 0.8510) is a few MC SE; paired precision not separately quantified.\"},\n {\"id\":\"C4\",\"text\":\"The Rademacher wild cluster bootstrap-t fails at G=5 (coverage 0.851-0.858) despite having the widest mean intervals, but is consistent with nominal 95% at G=30 for all ICC values and closest to nominal at G=10 for ICC>0.\",\"results_keys\":[\"coverage\",\"nominal_cells\",\"failure_cells\",\"data_issues\"],\"status\":\"supported\",\"caveat\":\"At G=5 Rademacher weights yield only 16 distinct |t*| values; other weights (Webb) or enumeration not studied. Mean half-width comes from table1.csv.\"},\n {\"id\":\"C5\",\"text\":\"11 of 27 (procedure, cell) pairs are failure regimes and only 5 are consistent with nominal coverage under the 2-MC-SE rule.\",\"results_keys\":[\"n_failure_cells\",\"failure_cells\",\"nominal_cells\"],\"status\":\"supported\",\"caveat\":\"Classification uses per-pair 2-SE rule without multiplicity adjustment; borderline pairs could change class under another seed.\"},\n {\"id\":\"C6\",\"text\":\"Ignoring clustering (naive iid SE) gives coverage of only about 0.29-0.49 whenever ICC>0.\",\"results_keys\":[\"baseline_iid_coverage\"],\"status\":\"supported\",\"caveat\":\"Baseline only; not one of the three studied procedures.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'));print('ok')\"","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":752,"cache_read_input_tokens":28831,"output_tokens":4961,"output_tokens_details":{"thinking_tokens":57},"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":752},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtRTgBT6MxvnSTpwqVN","requestRef":"2bc0db13-6287-4d06-bec1-eeccbb72e411","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9a814140-749c-47f0-ae5d-1867b8b44524","timestamp":"2026-10-30T05:42:44.710Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}93{"parentUuid":"9a814140-749c-47f0-ae5d-1867b8b44524","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Xv5NPByMWkjQzExKqHWEsg","type":"tool_result","content":"ok","is_error":false}]},"uuid":"b0c7d3d3-ae70-4cdb-b3ef-72de4f815eaf","timestamp":"2026-10-30T05:42:44.787Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"9a814140-749c-47f0-ae5d-1867b8b44524","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}94{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"53c9a27480e00a46f4f43131a49f47964d542b445f89b783e745fb96ea1ad6b7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Xv5NPByMWkjQzExKqHWEsg","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 (T2-simulation)\n\n## Question\nWhen N observations come from a small number G of unequal-size clusters, how close to 95% is the actual coverage of three cluster-robust intervals for the population mean μ, using the sample mean ȳ as estimator? For each of nine cells (G ∈ {5, 10, 30} × ICC ∈ {0.0, 0.2, 0.5}) we estimate coverage (`coverage`), its Monte Carlo SE (`mc_se_coverage`), the relative bias E[V̂]/Var(ȳ) of the CR0 and CR1 variance estimators (`rel_bias_var`), and the failure regimes where coverage is below 0.90 (`failure_cells`).\n\n## Data and exclusions\nThere is no observed data. The only input is `data/design.csv` (9 rows, `n_input_rows`; SHA-256 f4ff004e…c50, see `out/state/data_audit.md`). Every row passed the consistency checks (number of sizes = G, sum of sizes = N). No exclusions were applied (`out/exclusions.csv`: 9 → 9 cells). In each cell R = 2000 replications (`R`) and B = 399 bootstrap draws (`B`) were used, giving 18,000 simulated samples (`n_analysed`). Cell seeds are 20261101–20261109; C1's seed is 20261101 (`random_seed`, all seeds under `seeds`). Cluster sizes follow 8, 16, 32, 64 repeated, so with G = 5 the 64-observation cluster contains half the sample. One design-related issue is recorded in `data_issues`: with G = 5, Rademacher weights can produce only 32 distinct weight vectors. No bootstrap draw had a zero variance (`cell_diagnostics.*.n_degenerate_boot` = 0).\n\n## Method\nEach replication draws y_ig = μ + u_g + e_ig, with u_g ~ N(0, ICC) and e_ig ~ N(0, 1−ICC), using `numpy.random.default_rng(cell seed)`. Within each replication the draws are made in this order: u, e, then the B×G Rademacher matrix. The exact variance is Var(ȳ) = [ICC·Σn_g² + (1−ICC)N]/N².\n- **CR0**: V̂ = Σ_g S_g²/N², where S_g is the sum of residuals y − ȳ in cluster g; 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**: unrestricted wild cluster bootstrap-t with Rademacher weights. This is vectorised: ȳ* − ȳ = Σ w_g S_g/N, and the bootstrap cluster residual sums are w_g S_g − n_g(ȳ* − ȳ). These give V̂*_CR1 and |t*_b|. The critical value q is the 0.95 empirical quantile of the 399 |t*| values. I took this to be the `inverted_cdf` quantile, which is the 380th order statistic (`wcb_quantile_rule`). The interval is ȳ ± q√V̂_CR1. A brute-force check that builds y* explicitly matched the vectorised version to 1e-12 (`out/state/checks.md`).\n- Coverage is the share of replications with |ȳ − μ| ≤ half-width. MC SE = √(p̂(1−p̂)/R). Relative bias is the mean of V̂ over replications divided by the exact Var(ȳ).\n- **Baseline (P2)**: a naive i.i.d.-SE z-interval computed on the same replications (`baseline_iid_coverage`).\n- Running `out/analysis.py` regenerates `results.json`, `table1.csv` and `figure1.png` in about 2 s. A clean re-run gave byte-identical output.\n\n## Results\nFull numbers are in `out/table1.csv` and `out/figure1.png`.\n- **Naive baseline**: ignoring clustering gives coverage of about 0.29–0.49 whenever ICC > 0 (e.g. `baseline_iid_coverage.iid_G30_icc0.5` = 0.2985). At ICC = 0 it gives about 0.94–0.96. Some cluster correction is therefore necessary.\n- **CR0** under-covers in every cell:\n  - G = 5: 0.7805 / 0.7210 / 0.7170 for ICC 0 / 0.2 / 0.5 (`coverage.cr0_G5_icc0.0`, `cr0_G5_icc0.2`, `cr0_G5_icc0.5`);\n  - G = 10: 0.8965 / 0.8570 / 0.8530 (`coverage.cr0_G10_*`);\n  - G = 30: still only 0.9275 / 0.9210 / 0.9165 (`coverage.cr0_G30_*`).\n- **CR0 variance bias**: E[V̂_CR0]/Var(ȳ) is 0.66 / 0.53 / 0.48 at G = 5 (`rel_bias_var.cr0_G5_*`), 0.86 / 0.76 / 0.77 at G = 10 and 0.94 / 0.93 / 0.93 at G = 30. These Monte Carlo values agree with the analytic expectation (`rel_bias_var_exact`) within 2.5 MC SE in all 18 cases.\n- **CR1** removes only part of the variance bias: 0.83 / 0.66 / 0.60 at G = 5 (`rel_bias_var.cr1_G5_*`) and 0.95–0.98 at G = 30. Its t critical value adds more width.\n  - Coverage at G = 5: 0.9115 / 0.8845 / 0.8755 (`coverage.cr1_G5_*`).\n  - Coverage at G = 10: 0.9435 / 0.9155 / 0.9065.\n  - Coverage at G = 30: 0.9400 / 0.9350 / 0.9300.\n- **WCB** has the best coverage at G = 10 and G = 30 when ICC > 0 (0.9325 and 0.9350 at G = 10, `coverage.wcb_G10_icc0.2`, `wcb_G10_icc0.5`; 0.9445–0.9470 at G = 30). At G = 5 it fails: 0.8575 / 0.8545 / 0.8510 (`coverage.wcb_G5_*`). This happens even though its mean half-width there is the largest of the three procedures (`table1.csv`, `mean_ci_halfwidth`).\n- **Failure regimes** (coverage < 0.90): 11 of the 27 pairs (`n_failure_cells`, `failure_cells`):\n  - all three CR0 cells at G = 5 and all three at G = 10;\n  - all three WCB cells at G = 5;\n  - CR1 at G = 5 with ICC 0.2 and 0.5.\n- **Best procedure at G = 5**: CR1 has the highest average coverage over the G = 5 cells (0.8905 vs WCB 0.8543 and CR0 0.7395; `best_procedure_small_G`, `mean_coverage_G5`).\n- **Consistent with nominal 95%** (|p̂ − 0.95| ≤ 2 MC SE): only 5 pairs (`nominal_cells`): CR1 at G = 10 and G = 30 with ICC = 0, and WCB at G = 30 for all three ICC values.\n\n## Uncertainty\nEach coverage estimate is a binomial proportion based on R = 2000 replications. Its MC SE (`mc_se_coverage`) runs from 0.0050 (near 0.95) to 0.0101 (near 0.72). A ±2 SE band near the nominal level is therefore about ±0.010–0.011, and differences between procedures smaller than about 0.015 within a cell should not be over-interpreted. However, all procedures in a cell share the same replications, so paired comparisons are more precise than independent SEs suggest. That pairing was not separately quantified.\n\nThe MC SE of the relative-bias estimates (`rel_bias_var_mcse`) is about 0.012–0.014 at G = 5–10 and 0.007–0.009 at G = 30. The largest MC-vs-analytic discrepancy is 2.46 SE (`out/state/checks.md`).\n\nThe \"nominal\" classification uses a 2-SE rule applied separately to 27 pairs, with no multiplicity adjustment. Pairs close to the boundary (e.g. WCB at G = 10, 0.9325–0.9375) could change class under another seed. Similarly, failure classifications near 0.90 (CR0 at G = 10/ICC 0, 0.8965; CR1 at G = 10/ICC 0.5, 0.9065) are within one MC SE of the threshold.\n\nThe WCB critical value has its own Monte Carlo noise from B = 399. That noise is included in the coverage estimate but not separated from it.\n\n## Limitations and open issues\n- **Distributions**: only Gaussian random effects and errors were simulated. Skewed or heavy-tailed u_g or e_ig, which are known to hurt few-cluster inference, are not covered.\n- **Heterogeneity**: the ICC is common to all clusters, and errors are homoskedastic within and across clusters. Heterogeneity tied to cluster size, and informative cluster sizes, are not covered.\n- **Cluster-size design**: only one unbalanced pattern (8, 16, 32, 64) was used. With G = 5 a single cluster holds 50% of N, which drives the CR0/CR1 downward bias (high leverage). Balanced designs, or other degrees of imbalance, could give different rankings.\n- **Regressors**: the estimand is a plain mean (intercept-only model). Regression coefficients, especially for treatments that vary only at the cluster level or are given to few clusters, are not covered.\n- **Other weights and variants**:\n  - Only Rademacher weights were used, in the unrestricted (WCU) form. Webb six-point weights, Mammen weights, restricted (null-imposed, WCR) bootstrap and full enumeration of the 2^5 weight vectors at G = 5 were not studied.\n  - With G = 5, Rademacher weights give only 16 distinct |t*| values (`data_issues`). Under-coverage of WCB at G = 5 is therefore at least partly a property of this weight choice.\n  - CR2/CR3 (Bell–McCaffrey) corrections and other degrees-of-freedom rules were not studied.\n- **Quantile convention**: the WCB quantile rule (380th of 399 order statistics) is my choice for the unspecified \"empirical quantile\". Other interpolation rules would change q slightly.\n- **Grid**: only G ∈ {5, 10, 30} and three ICC values were simulated. The G at which each procedure reaches nominal coverage is not pinned down.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"CR0 under-covers in every design cell, failing (<0.90) in all G=5 and G=10 cells and reaching only 0.9165-0.9275 at G=30.\",\"results_keys\":[\"coverage\",\"failure_cells\"],\"status\":\"supported\",\"caveat\":\"CR0 at G=10, ICC=0 (0.8965) is within one MC SE of the 0.90 threshold.\"},\n {\"id\":\"C2\",\"text\":\"The CR0 variance estimator is biased downward, with E[V_CR0]/Var(ybar) of about 0.48-0.66 at G=5 and 0.93-0.94 at G=30; the Monte Carlo estimates agree with the analytic expectation within 2.5 MC SE.\",\"results_keys\":[\"rel_bias_var\",\"rel_bias_var_exact\",\"rel_bias_var_mcse\"],\"status\":\"supported\",\"caveat\":\"Specific to the 8/16/32/64 unbalanced design and Gaussian DGP.\"},\n {\"id\":\"C3\",\"text\":\"CR1 (G/(G-1) scaling with t_{G-1}) has the highest average coverage at G=5 (0.8905) but still fails for ICC 0.2 and 0.5 at G=5.\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_G5\",\"coverage\",\"failure_cells\"],\"status\":\"supported\",\"caveat\":\"CR1 vs WCB difference at G=5 ICC=0.5 (0.8755 vs 0.8510) is a few MC SE; paired precision not separately quantified.\"},\n {\"id\":\"C4\",\"text\":\"The Rademacher wild cluster bootstrap-t fails at G=5 (coverage 0.851-0.858) despite having the widest mean intervals, but is consistent with nominal 95% at G=30 for all ICC values and closest to nominal at G=10 for ICC>0.\",\"results_keys\":[\"coverage\",\"nominal_cells\",\"failure_cells\",\"data_issues\"],\"status\":\"supported\",\"caveat\":\"At G=5 Rademacher weights yield only 16 distinct |t*| values; other weights (Webb) or enumeration not studied. Mean half-width comes from table1.csv.\"},\n {\"id\":\"C5\",\"text\":\"11 of 27 (procedure, cell) pairs are failure regimes and only 5 are consistent with nominal coverage under the 2-MC-SE rule.\",\"results_keys\":[\"n_failure_cells\",\"failure_cells\",\"nominal_cells\"],\"status\":\"supported\",\"caveat\":\"Classification uses per-pair 2-SE rule without multiplicity adjustment; borderline pairs could change class under another seed.\"},\n {\"id\":\"C6\",\"text\":\"Ignoring clustering (naive iid SE) gives coverage of only about 0.29-0.49 whenever ICC>0.\",\"results_keys\":[\"baseline_iid_coverage\"],\"status\":\"supported\",\"caveat\":\"Baseline only; not one of the three studied procedures.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'));print('ok')\"","description":"Write report and claims ledger"}}]}}95{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"325cb4d3-3380-48b5-8593-8792d483a9ea","timestamp":"2026-10-30T05:42:44.790Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"2bc0db13-6287-4d06-bec1-eeccbb72e411","keep":30,"tail":["53c9a27480e00a46f4f43131a49f47964d542b445f89b783e745fb96ea1ad6b7","1105397ba4b116d862a653215b76ad9ad8bc9d1dd8e9886fc8f39eae9abdc382"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f64c2106e582a182e129ce144f2305d154d36ca02c0dca4cffd75aa6a8293d1d"}96{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b0c7d3d3-ae70-4cdb-b3ef-72de4f815eaf","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}97{"type":"atis-latch","atis":"","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}98{"parentUuid":"b0c7d3d3-ae70-4cdb-b3ef-72de4f815eaf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtUcttpkEqHbgcnvcrR","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":4968,"cache_read_input_tokens":29583,"output_tokens":738,"output_tokens_details":{"thinking_tokens":358},"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":4968},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2683,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtUccYAnJiLoCUfkB5r","requestRef":"325cb4d3-3380-48b5-8593-8792d483a9ea","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6c48df48-8f1a-4c60-8102-7af11dc6c703","timestamp":"2026-10-30T05:42:48.657Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}99{"parentUuid":"6c48df48-8f1a-4c60-8102-7af11dc6c703","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtUcttpkEqHbgcnvcrR","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01A8Q4TPQXbGRbVSyPCQNiHp","name":"Bash","input":{"command":"sed -i '' 's/and 0.95–0.98 at G = 30/and 0.96–0.98 at G = 30/' out/report.md && grep -c \"0.96–0.98\" out/report.md\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 required sections, numbers cite results.json keys\",\"claims.json 6 claims, all keys exist in results.json\",\"numbers in report cross-checked against table1.csv/results.json\",\"final gate run (see gate_receipts)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"; ls out/state/gate_receipts","description":"Finalize ledger 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":4968,"cache_read_input_tokens":29583,"output_tokens":738,"output_tokens_details":{"thinking_tokens":358},"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":4968},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtUccYAnJiLoCUfkB5r","requestRef":"325cb4d3-3380-48b5-8593-8792d483a9ea","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8855a8c7-f99d-4ca2-a370-3eb5be413c3f","timestamp":"2026-10-30T05:42:51.104Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}100{"parentUuid":"8855a8c7-f99d-4ca2-a370-3eb5be413c3f","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01A8Q4TPQXbGRbVSyPCQNiHp","type":"tool_result","content":"1\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0023/out/state/gate_receipts/20261030T054253.336612Z.json\n20261030T054151.239822Z.json\n20261030T054253.336612Z.json","is_error":false}]},"uuid":"1de3001f-5dd6-4da5-8de3-accf55caf63b","timestamp":"2026-10-30T05:42:53.343Z","toolUseResult":{"stdout":"1\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0023/out/state/gate_receipts/20261030T054253.336612Z.json\n20261030T054151.239822Z.json\n20261030T054253.336612Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8855a8c7-f99d-4ca2-a370-3eb5be413c3f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}101{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"1079be42206d4fe57aa59880625fd415c37dae6771509bf5c3fe2802a91bf4ef","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01A8Q4TPQXbGRbVSyPCQNiHp","name":"Bash","input":{"command":"sed -i '' 's/and 0.95–0.98 at G = 30/and 0.96–0.98 at G = 30/' out/report.md && grep -c \"0.96–0.98\" out/report.md\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 required sections, numbers cite results.json keys\",\"claims.json 6 claims, all keys exist in results.json\",\"numbers in report cross-checked against table1.csv/results.json\",\"final gate run (see gate_receipts)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"; ls out/state/gate_receipts","description":"Finalize ledger and run gate"}}]}}102{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"83bbf705-5226-4d7a-a5ed-12f61156ae36","timestamp":"2026-10-30T05:42:53.346Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"325cb4d3-3380-48b5-8593-8792d483a9ea","keep":32,"tail":["1079be42206d4fe57aa59880625fd415c37dae6771509bf5c3fe2802a91bf4ef","d0c893647828199b2d9074c96d91cd2825d97509e465c4efcbadfd6aaf1fb2d4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f2faba0da332abf5beb01eaea86ddafb5058fe1641dc461042a3609604bccfbb"}103{"parentUuid":"1de3001f-5dd6-4da5-8de3-accf55caf63b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVFTaHdjSrwchbFcNZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011VhP9jXNYnwKy9yRP53F6N","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']['checks'][-1]=\"final gate run 20261030T054253.336612Z: PASSED (0 of 34 failed)\"\np['P5']['gate_receipts']=[\"out/state/gate_receipts/20261030T054253.336612Z.json\"]\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P5 passed; final gate PASSED (receipt 20261030T054253.336612Z). Task complete.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record receipt and confirm gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":863,"cache_read_input_tokens":34551,"output_tokens":334,"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":863},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtVFBU6vUso74cmgJZv","requestRef":"83bbf705-5226-4d7a-a5ed-12f61156ae36","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3a7675c5-6bc3-4e3e-8a50-e2811e3238f9","timestamp":"2026-10-30T05:42:56.227Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}104{"parentUuid":"3a7675c5-6bc3-4e3e-8a50-e2811e3238f9","isSidechain":false,"promptId":"ab3a76f6-a537-4ec0-b223-f09d2131888d","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011VhP9jXNYnwKy9yRP53F6N","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)","is_error":false}]},"uuid":"9beedaec-dcca-4728-ad3f-0301ec0036c8","timestamp":"2026-10-30T05:42:58.478Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3a7675c5-6bc3-4e3e-8a50-e2811e3238f9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}105{"type":"api-request-blob","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","hash":"71cceece954d9c229d0c80f4abbe97a8fcb3e79ba28fd04e08a94bfdff135547","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_011VhP9jXNYnwKy9yRP53F6N","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('out/state/phases.json'))\np['P5']['checks'][-1]=\"final gate run 20261030T054253.336612Z: PASSED (0 of 34 failed)\"\np['P5']['gate_receipts']=[\"out/state/gate_receipts/20261030T054253.336612Z.json\"]\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P5 passed; final gate PASSED (receipt 20261030T054253.336612Z). Task complete.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record receipt and confirm gate"}}]}}106{"type":"api-request","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","id":"989b21b0-94bb-48a8-b4ae-631cc06aeca4","timestamp":"2026-10-30T05:42:58.481Z","version":"2.1.314","querySource":"sdk","shapeHash":"30995343cfede10727ba1e2f3099b58c1000f9a1cdd562b9fbc66669800e4667","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":"83bbf705-5226-4d7a-a5ed-12f61156ae36","keep":34,"tail":["71cceece954d9c229d0c80f4abbe97a8fcb3e79ba28fd04e08a94bfdff135547","04cbb55394772939de64f0bad0a7e705e585613c6c6f34228bca5c3614d3ff41"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8480ee739d7c9fd7efe5bd7e2d3762a7c57204da129eb7bad5923ac21b50e030"}107{"parentUuid":"9beedaec-dcca-4728-ad3f-0301ec0036c8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVdZrzhWPH2VXRCzER","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":374,"cache_read_input_tokens":35414,"output_tokens":1005,"output_tokens_details":{"thinking_tokens":18},"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":374},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6435,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtVdB3cFNaa5j4DpVxU","requestRef":"989b21b0-94bb-48a8-b4ae-631cc06aeca4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4493473e-f32d-47eb-aac0-b85c33ee020c","timestamp":"2026-10-30T05:43:05.748Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}108{"parentUuid":"4493473e-f32d-47eb-aac0-b85c33ee020c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtVdZrzhWPH2VXRCzER","type":"message","role":"assistant","content":[{"type":"text","text":"I ran the full simulation as specified: 9 cells, 2,000 replications each (18,000 samples in total), 399 bootstrap draws per replication, using the seeds in `design.csv`. All deliverables are written and the final gate passed with 0 of 34 checks failing.\n\n**Main findings:**\n- **CR0** under-covers in every cell. Coverage at 5 clusters is 0.72–0.78, and even at 30 clusters it is only 0.92–0.93. Its variance estimate averages 48–66% of the true variance at 5 clusters. Those simulated values agree with the exact theoretical expectation to within 2.5 Monte Carlo standard errors.\n- **CR1** has the highest average coverage at 5 clusters (0.8905), but still falls below 0.90 when the intra-cluster correlation is 0.2 or 0.5.\n- **The wild cluster bootstrap** fails at 5 clusters (coverage 0.851–0.858) even though its intervals are the widest there. At 30 clusters it is consistent with 95% at every correlation level.\n- **Failures:** 11 of the 27 procedure–cell pairs have coverage below 0.90. Only 5 pairs are consistent with 95% (within 2 Monte Carlo standard errors).\n- **Naive baseline:** an interval that ignores clustering covers only about 0.29–0.49 whenever the intra-cluster correlation is above zero.\n\n**Checks:**\n- Re-running `out/analysis.py` from a clean state reproduces identical results.\n- A brute-force version of the bootstrap matched the fast one to 1e-12.\n- Coverage estimates have Monte Carlo standard errors of about 0.005–0.010.\n- All 12 consistency checks are recorded in `out/state/checks.md`.\n\n**Limitations:**\n- **Quantile rule:** the task doesn't say how to compute the 0.95 empirical quantile, so I used the 380th of the 399 sorted values. A different rule would shift the bootstrap critical value slightly.\n- **Bootstrap at 5 clusters:** with 5 clusters and ±1 weights there are only 32 possible weight patterns (16 distinct values of the statistic). The bootstrap's failure there is at least partly due to this weight choice.\n- **Borderline cases:** a few pairs sit within one standard error of the 0.90 or 95% thresholds and could change category under another seed. The classification is not adjusted for testing 27 pairs.\n- **What the design doesn't cover:** non-normal distributions, heterogeneity across clusters, regressors, other bootstrap weights or variants, and other cluster-size patterns. In this design one cluster holds half the sample when there are 5 clusters, which drives much of the downward variance bias.\n\nFiles are in `./out/`:\n- results.json\n- table1.csv\n- figure1.png\n- analysis.py\n- report.md\n- claims.json\n- exclusions.csv\n- state/ (working records)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":374,"cache_read_input_tokens":35414,"output_tokens":1005,"output_tokens_details":{"thinking_tokens":18},"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":374},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtVdB3cFNaa5j4DpVxU","requestRef":"989b21b0-94bb-48a8-b4ae-631cc06aeca4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"76fd9052-16c4-4357-9ecd-5fb6b703a08b","timestamp":"2026-10-30T05:43:07.547Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0023","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","version":"2.1.314","gitBranch":"HEAD"}109{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"76fd9052-16c4-4357-9ecd-5fb6b703a08b","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c"}110{"type":"cost-state","sessionId":"28887c64-53d2-4818-845a-2f1d1c88ab5c","totalCostUSD":0.6712168000000001,"totalAPIDuration":188067,"totalAPIDurationWithoutRetries":188060,"totalToolDuration":16548,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":204745,"startTime":1793338782829,"modelUsage":{"claude-opus-5-5":{"inputTokens":38,"outputTokens":21533,"thinkingTokens":2589,"cacheReadInputTokens":344924,"cacheCreationInputTokens":34284,"cacheCreationEphemeral5mInputTokens":34284,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.6712168000000001}},"hasUnknownModelCost":false}111