1{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:37:56.625Z","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:37:56.629Z","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}4{"parentUuid":null,"isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":"Begin"},"uuid":"fff3156c-815b-4a90-98ab-69b4dbab3615","timestamp":"2026-10-30T05:37:56.632Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","timestamp":"2026-10-30T05:37:56.641Z","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/RT0020\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/<timestamp>.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n\nSEPARATE REVIEW (additional)\n- After the gate passes, a separate reviewer session that has not seen your work in progress will examine `TASK.md` and everything under `out/` and may return a list of issues (file `out/review/review.json`). You will then be resumed once to address them: fix what is justified, explain in `out/report.md` (Limitations and open issues) what you disagree with, re-run the gate, and update `out/claims.json` and `out/state/phases.json`. The reviewer has no reference answers; its role is to challenge unsupported claims, violated information rules, unverified computations, and inconsistencies between your report and your results.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"2c8dfccf-d2d0-4bfe-a832-6624d39e47ac","timestamp":"2026-10-30T05:37:56.641Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"ee14eb8d1c6700bca8da95e7a43fd9ea766b9ed4a60f35c774f32ea0c3248c49"}8{"parentUuid":"fff3156c-815b-4a90-98ab-69b4dbab3615","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"d42ec689-70ad-4dae-a220-018ce48610c0","timestamp":"2026-10-30T05:37:56.635Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"d42ec689-70ad-4dae-a220-018ce48610c0","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"fd59316a-9d26-40a0-95d7-3a6af5ff80ae","timestamp":"2026-10-30T05:37:56.635Z","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/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"fd59316a-9d26-40a0-95d7-3a6af5ff80ae","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":"94df4373-4113-466f-b5da-14e2d477a78b","timestamp":"2026-10-30T05:37:56.636Z","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/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}12{"parentUuid":"94df4373-4113-466f-b5da-14e2d477a78b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7PZdVFqeTZakWF2ih","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":136,"output_tokens_details":{"thinking_tokens":27},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":594,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt7PJWCsM7soYN6Gx5Z","requestRef":"2c8dfccf-d2d0-4bfe-a832-6624d39e47ac","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c8318a13-a7b6-4289-98bf-4d41e92642eb","timestamp":"2026-10-30T05:37:58.065Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"c8318a13-a7b6-4289-98bf-4d41e92642eb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7PZdVFqeTZakWF2ih","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01F3FXzH5LVqSmJ7Xq9FEhso","name":"Bash","input":{"command":"cat TASK.md; ls -R | head -50; cat out/state/log.md 2>/dev/null","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":136,"output_tokens_details":{"thinking_tokens":27},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt7PJWCsM7soYN6Gx5Z","requestRef":"2c8dfccf-d2d0-4bfe-a832-6624d39e47ac","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"beeac13c-e53f-4854-9206-c4c9b6538c2a","timestamp":"2026-10-30T05:37:58.620Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"beeac13c-e53f-4854-9206-c4c9b6538c2a","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\nbundle.json\ndata\ngate_spec.json\nTASK.md\n\n./data:\ndesign.csv\nREADME.md","is_error":true,"tool_use_id":"toolu_01F3FXzH5LVqSmJ7Xq9FEhso"}]},"uuid":"497cb372-432d-49de-8c41-be4750858d05","timestamp":"2026-10-30T05:37:58.687Z","toolUseResult":"Error: Exit code 1\n# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\nbundle.json\ndata\ngate_spec.json\nTASK.md\n\n./data:\ndesign.csv\nREADME.md","sandboxed":false,"sourceToolAssistantUUID":"beeac13c-e53f-4854-9206-c4c9b6538c2a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"07ae2f64484a87f8e88833f374c2935fd60a3413755e52a2b7ba5497ca84a12d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01F3FXzH5LVqSmJ7Xq9FEhso","name":"Bash","input":{"command":"cat TASK.md; ls -R | head -50; cat out/state/log.md 2>/dev/null","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"fdf44ce2-eac5-415b-be60-1a5829330886","timestamp":"2026-10-30T05:37:58.690Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"2c8dfccf-d2d0-4bfe-a832-6624d39e47ac","keep":2,"tail":["07ae2f64484a87f8e88833f374c2935fd60a3413755e52a2b7ba5497ca84a12d","3e0201e878e53d95a181bab5ad714921ccaf63fd80623c5918786654192d8f9a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"edc18686d9a341d177dc05216245c31f18ea10061fb1a2420acc3ff923330177"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"497cb372-432d-49de-8c41-be4750858d05","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}18{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}19{"parentUuid":"497cb372-432d-49de-8c41-be4750858d05","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7XBWh2PEyqZSdUYMS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Dg8pS5JdsdGK1yQ5uoGoAq","name":"Bash","input":{"command":"cat data/README.md; cat data/design.csv; cat gate_spec.json | head -80; shasum -a 256 data/*","description":"Inspect data, readme, gate spec"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2945,"cache_read_input_tokens":4315,"output_tokens":121,"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":2945},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt7WuPpep1NdWmvy9Fh","requestRef":"fdf44ce2-eac5-415b-be60-1a5829330886","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e997c7f0-e74c-4f6a-beb3-2aa7f4000b38","timestamp":"2026-10-30T05:38:00.172Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"e997c7f0-e74c-4f6a-beb3-2aa7f4000b38","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Dg8pS5JdsdGK1yQ5uoGoAq","type":"tool_result","content":"# 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.\ncell_id,G,icc,cluster_sizes,N,R,B,seed,mu,total_variance,nominal_level\r\nC1,5,0.0,8|16|32|64|8,128,2000,399,20261101,0.0,1.0,0.95\r\nC2,5,0.2,8|16|32|64|8,128,2000,399,20261102,0.0,1.0,0.95\r\nC3,5,0.5,8|16|32|64|8,128,2000,399,20261103,0.0,1.0,0.95\r\nC4,10,0.0,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261104,0.0,1.0,0.95\r\nC5,10,0.2,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261105,0.0,1.0,0.95\r\nC6,10,0.5,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261106,0.0,1.0,0.95\r\nC7,30,0.0,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261107,0.0,1.0,0.95\r\nC8,30,0.2,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261108,0.0,1.0,0.95\r\nC9,30,0.5,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261109,0.0,1.0,0.95\r\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}\nf4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 data/design.csv\n73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 data/README.md","is_error":false}]},"uuid":"732a98ea-af9f-47a2-bc80-9a1284adbb17","timestamp":"2026-10-30T05:38:00.217Z","toolUseResult":{"stdout":"# 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.\ncell_id,G,icc,cluster_sizes,N,R,B,seed,mu,total_variance,nominal_level\r\nC1,5,0.0,8|16|32|64|8,128,2000,399,20261101,0.0,1.0,0.95\r\nC2,5,0.2,8|16|32|64|8,128,2000,399,20261102,0.0,1.0,0.95\r\nC3,5,0.5,8|16|32|64|8,128,2000,399,20261103,0.0,1.0,0.95\r\nC4,10,0.0,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261104,0.0,1.0,0.95\r\nC5,10,0.2,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261105,0.0,1.0,0.95\r\nC6,10,0.5,8|16|32|64|8|16|32|64|8|16,264,2000,399,20261106,0.0,1.0,0.95\r\nC7,30,0.0,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261107,0.0,1.0,0.95\r\nC8,30,0.2,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261108,0.0,1.0,0.95\r\nC9,30,0.5,8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16|32|64|8|16,864,2000,399,20261109,0.0,1.0,0.95\r\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}\nf4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 data/design.csv\n73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 data/README.md","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e997c7f0-e74c-4f6a-beb3-2aa7f4000b38","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"52af8120b4176390646af860cd4096e3efe8b6cc6fa79088e606d2d9b636ca87","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Dg8pS5JdsdGK1yQ5uoGoAq","name":"Bash","input":{"command":"cat data/README.md; cat data/design.csv; cat gate_spec.json | head -80; shasum -a 256 data/*","description":"Inspect data, readme, gate spec"}}]}}22{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"0a1d9b38-342b-4a7c-8080-e6e512430325","timestamp":"2026-10-30T05:38:00.219Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"fdf44ce2-eac5-415b-be60-1a5829330886","keep":4,"tail":["52af8120b4176390646af860cd4096e3efe8b6cc6fa79088e606d2d9b636ca87","6efc8f7e3f87a4f03c96bbe0c75c4ebd1be12b07d4e3ef163c1c5c6622b01002"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8ca7f08d307967e189e99982d7ac599c6027330d030a7c16e99803cead899f15"}23{"parentUuid":"732a98ea-af9f-47a2-bc80-9a1284adbb17","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7du5zGTgpTTtiEfCW","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":1985,"cache_read_input_tokens":7260,"output_tokens":1421,"output_tokens_details":{"thinking_tokens":348},"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":1985},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3080,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt7diBA33gpdTRPN41g","requestRef":"0a1d9b38-342b-4a7c-8080-e6e512430325","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0509c6f7-8a1b-404f-9d99-3cef8f8e1649","timestamp":"2026-10-30T05:38:04.270Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"0509c6f7-8a1b-404f-9d99-3cef8f8e1649","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt7du5zGTgpTTtiEfCW","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BCFz42ncAgDxwphvbdb6w7","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?\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 the nominal 95% interval (fraction of R=2000 intervals containing μ=0);\n(b) for CR0/CR1: relative bias E[V̂]/Var(ȳ), Var(ȳ) = [ICC Σ n_g² + (1−ICC) N]/N² (exact under the DGP), E[V̂] by Monte Carlo mean;\n(c) MC SE of coverage √(p̂(1−p̂)/R);\n(d) failure regimes: coverage < 0.90; \"nominal-consistent\": |p̂−0.95| ≤ 2 MC SE.\nMeaningful under the stated Gaussian random-intercept DGP with given unbalanced cluster sizes; results are Monte Carlo estimates with MC error.\n\n**Outputs:** out/table1.csv (27 rows: estimator, cell_id, G, icc, coverage, mc_se_coverage, rel_bias_var [empty for wcb], mean_ci_halfwidth, R); out/results.json (task_id, R, B, n_cells, coverage, mc_se_coverage, rel_bias_var, failure_cells, n_failure_cells, nominal_cells, best_procedure_small_G, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues); out/analysis.py; out/claims.json; plus protocol files (state/, exclusions.csv).\n\n**Information rules:** use only data/design.csv; DGP and procedures exactly as specified; R=2000, B=399, per-cell seed; no change to grid.\n\n**Invalidity/impossibility:** changing R/B/grid/seeds; procedures deviating from spec; nondeterminism; runtime >10 min. Nothing appears impossible.\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":1985,"cache_read_input_tokens":7260,"output_tokens":1421,"output_tokens_details":{"thinking_tokens":348},"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":1985},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt7diBA33gpdTRPN41g","requestRef":"0a1d9b38-342b-4a7c-8080-e6e512430325","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"eb86a45b-d54a-4c9d-bb1b-3e6dad3852aa","timestamp":"2026-10-30T05:38:12.220Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"eb86a45b-d54a-4c9d-bb1b-3e6dad3852aa","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BCFz42ncAgDxwphvbdb6w7","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"ba02d6cf-fd90-483d-94b0-2c1dd6aa52f8","timestamp":"2026-10-30T05:38:12.266Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"eb86a45b-d54a-4c9d-bb1b-3e6dad3852aa","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"5def881549f1861446ea2305b689c0b07e660da0bf4053282297877824d05923","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01BCFz42ncAgDxwphvbdb6w7","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?\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 the nominal 95% interval (fraction of R=2000 intervals containing μ=0);\n(b) for CR0/CR1: relative bias E[V̂]/Var(ȳ), Var(ȳ) = [ICC Σ n_g² + (1−ICC) N]/N² (exact under the DGP), E[V̂] by Monte Carlo mean;\n(c) MC SE of coverage √(p̂(1−p̂)/R);\n(d) failure regimes: coverage < 0.90; \"nominal-consistent\": |p̂−0.95| ≤ 2 MC SE.\nMeaningful under the stated Gaussian random-intercept DGP with given unbalanced cluster sizes; results are Monte Carlo estimates with MC error.\n\n**Outputs:** out/table1.csv (27 rows: estimator, cell_id, G, icc, coverage, mc_se_coverage, rel_bias_var [empty for wcb], mean_ci_halfwidth, R); out/results.json (task_id, R, B, n_cells, coverage, mc_se_coverage, rel_bias_var, failure_cells, n_failure_cells, nominal_cells, best_procedure_small_G, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues); out/analysis.py; out/claims.json; plus protocol files (state/, exclusions.csv).\n\n**Information rules:** use only data/design.csv; DGP and procedures exactly as specified; R=2000, B=399, per-cell seed; no change to grid.\n\n**Invalidity/impossibility:** changing R/B/grid/seeds; procedures deviating from spec; nondeterminism; runtime >10 min. Nothing appears impossible.\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":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"5b6ed6e6-8542-4ba0-8dba-20c0f10d5a1e","timestamp":"2026-10-30T05:38:12.270Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"0a1d9b38-342b-4a7c-8080-e6e512430325","keep":6,"tail":["5def881549f1861446ea2305b689c0b07e660da0bf4053282297877824d05923","6f1579b2342e7025de685e6129cb3d4f5cdea2ea8cc2373a130a6847dc506e2e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3bf26ec2cd8d0cc380e29b71b712e8938e0ed2660d74c515a12a95ae04e06e5a"}28{"parentUuid":"ba02d6cf-fd90-483d-94b0-2c1dd6aa52f8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8X9pAW1Xjpw2UNJ7t","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":1436,"cache_read_input_tokens":9245,"output_tokens":296,"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":1436},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":393,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt8Wxf8cStwmRfjXm6m","requestRef":"5b6ed6e6-8542-4ba0-8dba-20c0f10d5a1e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"df120e3b-a918-41e3-a856-f8ed9178acca","timestamp":"2026-10-30T05:38:13.414Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"df120e3b-a918-41e3-a856-f8ed9178acca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8X9pAW1Xjpw2UNJ7t","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RPpuwoYoDWZ12DkMy8yjH8","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape);print(d.isna().sum().sum(), d.duplicated().sum(), d.seed.duplicated().sum())\nfor _,r in d.iterrows():\n s=[int(x) for x in r.cluster_sizes.split('|')]\n print(r.cell_id,len(s)==r.G,sum(s)==r.N, s==[ [8,16,32,64][i%4] for i in range(r.G)], sum(np.array(s)**2))\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":1436,"cache_read_input_tokens":9245,"output_tokens":296,"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":1436},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt8Wxf8cStwmRfjXm6m","requestRef":"5b6ed6e6-8542-4ba0-8dba-20c0f10d5a1e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6fda6da1-ef58-41d0-a258-95c3ec764bc7","timestamp":"2026-10-30T05:38:15.111Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"6fda6da1-ef58-41d0-a258-95c3ec764bc7","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","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);print(d.isna().sum().sum(), d.duplicated().sum(), d.seed.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_01RPpuwoYoDWZ12DkMy8yjH8"}]},"uuid":"b3590334-35e0-4181-ab4f-2a09fee9494f","timestamp":"2026-10-30T05:38:15.296Z","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);print(d.isna().sum().sum(), d.duplicated().sum(), d.seed.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":"6fda6da1-ef58-41d0-a258-95c3ec764bc7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"611bd10458189dc0f1b76ec6681ce4361334446ca24b0872347386b40f6a9ce1","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01RPpuwoYoDWZ12DkMy8yjH8","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape);print(d.isna().sum().sum(), d.duplicated().sum(), d.seed.duplicated().sum())\nfor _,r in d.iterrows():\n s=[int(x) for x in r.cluster_sizes.split('|')]\n print(r.cell_id,len(s)==r.G,sum(s)==r.N, s==[ [8,16,32,64][i%4] for i in range(r.G)], sum(np.array(s)**2))\n\"","description":"Audit design.csv consistency"}}]}}32{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"abfd71b0-4611-4dfe-95be-2a1b1e8bd772","timestamp":"2026-10-30T05:38:15.299Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"5b6ed6e6-8542-4ba0-8dba-20c0f10d5a1e","keep":8,"tail":["611bd10458189dc0f1b76ec6681ce4361334446ca24b0872347386b40f6a9ce1","b20bae4e1879a8d270444e9d9e7abe93fae0c5ef2a25c58c680dc14a73f7e20e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"86747918e52b4e4f623031d024043d63372896bde4a6e75614b49b60a23b1b7c"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b3590334-35e0-4181-ab4f-2a09fee9494f","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}34{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}35{"parentUuid":"b3590334-35e0-4181-ab4f-2a09fee9494f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8k7vQ3ePku2UERVxu","type":"message","role":"assistant","content":[{"type":"text","text":"Working directory moved to out/state; returning to root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1016,"cache_read_input_tokens":10681,"output_tokens":341,"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":1016},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt8jwG4WUVHrqsrmZAz","requestRef":"abfd71b0-4611-4dfe-95be-2a1b1e8bd772","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9a664683-c4cf-4420-93e5-0dab4f1be44a","timestamp":"2026-10-30T05:38:16.246Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"9a664683-c4cf-4420-93e5-0dab4f1be44a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8k7vQ3ePku2UERVxu","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VWLsgmjAUbGfyVLE3z28XH","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0020 && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape);print(d.dtypes.to_dict());print(d.isna().sum().sum(), d.duplicated().sum(), d.seed.duplicated().sum())\nfor _,r in d.iterrows():\n s=[int(x) for x in r.cluster_sizes.split('|')]\n print(r.cell_id,len(s)==r.G,sum(s)==r.N, s==[ [8,16,32,64][i%4] for i in range(r.G)], sum(np.array(s)**2))\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":1016,"cache_read_input_tokens":10681,"output_tokens":341,"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":1016},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt8jwG4WUVHrqsrmZAz","requestRef":"abfd71b0-4611-4dfe-95be-2a1b1e8bd772","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b4f978a4-2f00-4ff7-aec6-df3689e72b0c","timestamp":"2026-10-30T05:38:18.195Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"b4f978a4-2f00-4ff7-aec6-df3689e72b0c","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VWLsgmjAUbGfyVLE3z28XH","type":"tool_result","content":"(9, 11)\n{'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 True 5504\nC2 True True True 5504\nC3 True True True 5504\nC4 True True True 11200\nC5 True True True 11200\nC6 True True True 11200\nC7 True True True 38400\nC8 True True True 38400\nC9 True True True 38400","is_error":false}]},"uuid":"aac7550a-f5e7-48ce-a9fe-28cbc3810d09","timestamp":"2026-10-30T05:38:18.378Z","toolUseResult":{"stdout":"(9, 11)\n{'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 True 5504\nC2 True True True 5504\nC3 True True True 5504\nC4 True True True 11200\nC5 True True True 11200\nC6 True True True 11200\nC7 True True True 38400\nC8 True True True 38400\nC9 True True True 38400","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b4f978a4-2f00-4ff7-aec6-df3689e72b0c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"ab5e8ffad0fa88ea32cae97a6504b0762b2270b08e214d7bdec296720c99e814","message":{"role":"assistant","content":[{"type":"text","text":"Working directory moved to out/state; returning to root."},{"type":"tool_use","id":"toolu_01VWLsgmjAUbGfyVLE3z28XH","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0020 && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nd=pd.read_csv('data/design.csv');print(d.shape);print(d.dtypes.to_dict());print(d.isna().sum().sum(), d.duplicated().sum(), d.seed.duplicated().sum())\nfor _,r in d.iterrows():\n s=[int(x) for x in r.cluster_sizes.split('|')]\n print(r.cell_id,len(s)==r.G,sum(s)==r.N, s==[ [8,16,32,64][i%4] for i in range(r.G)], sum(np.array(s)**2))\n\"","description":"Audit design.csv consistency"}}]}}39{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"a6951c1e-44f9-450e-b55f-584ef120fb63","timestamp":"2026-10-30T05:38:18.381Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"abfd71b0-4611-4dfe-95be-2a1b1e8bd772","keep":10,"tail":["ab5e8ffad0fa88ea32cae97a6504b0762b2270b08e214d7bdec296720c99e814","23f620ff6ec77cf638592d1d94640ff301c66642fe7e940e765e63b504129530"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5bbfeb69c08546679f938365c2a830018955fa25e5b50fb68fc1e10ce9a1a7f8"}40{"parentUuid":"aac7550a-f5e7-48ce-a9fe-28cbc3810d09","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt8yLujF7QrUf55EpuW","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SB2v23ZqocRrtCfLNKGYHU","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0020/out && cat > state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 | rows x cols |\n|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 x 11 |\n| data/README.md | 73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 | documentation |\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, all 2000), B (int, all 399), seed (int, 20261101..20261109, all distinct), mu (0.0), total_variance (1.0), nominal_level (0.95). Units: dimensionless (simulated y with unit total variance). No dates.\n\nChecks run: missing values = 0; duplicate rows = 0; duplicate seeds = 0; for every cell len(cluster_sizes)==G, sum(cluster_sizes)==N, sizes follow 8,16,32,64 repeated pattern (all True). Σn_g² = 5504 (G=5), 11200 (G=10), 38400 (G=30).\n\nAnomalies / notes: none in the file. Methodological note (not a data error): with G=5 Rademacher weights there are only 2^5=32 distinct weight vectors (16 distinct |t*| values since |t*| is invariant to w→−w), so B=399 draws heavily repeat and the 0.95 quantile of |t*| is coarse. Recorded in results `data_issues`.\n\nInformation availability: the design file is synthetic and fully allowed; no violation. No exclusions are needed (all 9 cells × 2000 replications simulated); exclusions.csv records a single no-op step.\nEOF\nprintf 'step,rule,n_before,n_after,n_removed,rationale\\n1,none: all design cells x R replications simulated,18000,18000,0,No filtering; every replication of every cell is analysed (9 cells x 2000)\\n' > exclusions.csv\ncd state && ~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 computed\",\"shape 9x11\",\"no NA/duplicates/duplicate seeds\",\"cluster_sizes length==G, sum==N, pattern verified\",\"exclusions.csv written (0 removed)\"],\"notes\":\"G=5 Rademacher has only 32 weight vectors -> noted\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P1 passed: design audited, no exclusions.\" >> 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":598,"cache_read_input_tokens":11697,"output_tokens":1066,"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":598},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt8y5HRBPapJVqUy8UU","requestRef":"a6951c1e-44f9-450e-b55f-584ef120fb63","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ec1fd0aa-09f4-42e6-b7aa-1b59cf6b0239","timestamp":"2026-10-30T05:38:28.707Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"ec1fd0aa-09f4-42e6-b7aa-1b59cf6b0239","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SB2v23ZqocRrtCfLNKGYHU","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"e206fd90-2594-44f0-a17d-96f8eec35a8f","timestamp":"2026-10-30T05:38:28.752Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ec1fd0aa-09f4-42e6-b7aa-1b59cf6b0239","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"7d1e5a53403edf86ea5befb417062e056e2dd0ab7468216534092843e06ca18d","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01SB2v23ZqocRrtCfLNKGYHU","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0020/out && cat > state/data_audit.md <<'EOF'\n# Data audit (P1)\n| file | SHA-256 | rows x cols |\n|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 x 11 |\n| data/README.md | 73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 | documentation |\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, all 2000), B (int, all 399), seed (int, 20261101..20261109, all distinct), mu (0.0), total_variance (1.0), nominal_level (0.95). Units: dimensionless (simulated y with unit total variance). No dates.\n\nChecks run: missing values = 0; duplicate rows = 0; duplicate seeds = 0; for every cell len(cluster_sizes)==G, sum(cluster_sizes)==N, sizes follow 8,16,32,64 repeated pattern (all True). Σn_g² = 5504 (G=5), 11200 (G=10), 38400 (G=30).\n\nAnomalies / notes: none in the file. Methodological note (not a data error): with G=5 Rademacher weights there are only 2^5=32 distinct weight vectors (16 distinct |t*| values since |t*| is invariant to w→−w), so B=399 draws heavily repeat and the 0.95 quantile of |t*| is coarse. Recorded in results `data_issues`.\n\nInformation availability: the design file is synthetic and fully allowed; no violation. No exclusions are needed (all 9 cells × 2000 replications simulated); exclusions.csv records a single no-op step.\nEOF\nprintf 'step,rule,n_before,n_after,n_removed,rationale\\n1,none: all design cells x R replications simulated,18000,18000,0,No filtering; every replication of every cell is analysed (9 cells x 2000)\\n' > exclusions.csv\ncd state && ~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"sha256 computed\",\"shape 9x11\",\"no NA/duplicates/duplicate seeds\",\"cluster_sizes length==G, sum==N, pattern verified\",\"exclusions.csv written (0 removed)\"],\"notes\":\"G=5 Rademacher has only 32 weight vectors -> noted\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P1 passed: design audited, no exclusions.\" >> log.md","description":"Write data audit, exclusions, update ledger"}}]}}43{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"e78b9c58-93ca-4220-80ad-b7b1e8be2527","timestamp":"2026-10-30T05:38:28.755Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"a6951c1e-44f9-450e-b55f-584ef120fb63","keep":12,"tail":["7d1e5a53403edf86ea5befb417062e056e2dd0ab7468216534092843e06ca18d","302f01b9704631add2a010db8ecb8f70bdcce723d3c5f4ca722d367e00f5f0f1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"268f78bd1b4a64d18fe23bdc5b385c83ef9b0cd118a708b2b5d999fe8bbf5ca5"}44{"parentUuid":"e206fd90-2594-44f0-a17d-96f8eec35a8f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt9jyGaran6rYaAwSL7","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":1081,"cache_read_input_tokens":12295,"output_tokens":4721,"output_tokens_details":{"thinking_tokens":696},"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":1081},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6236,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt9jheW3UUETnzxsx4m","requestRef":"e78b9c58-93ca-4220-80ad-b7b1e8be2527","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6134159f-7dc8-4aab-ab25-2bc4b073f63f","timestamp":"2026-10-30T05:38:36.146Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"6134159f-7dc8-4aab-ab25-2bc4b073f63f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt9jyGaran6rYaAwSL7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01RKGbWiUBh4i7UrcbnS79jy","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0020/out && cat > analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t CIs for a mean.\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png.\nRandomness: one numpy default_rng(seed) per cell (seed from design.csv). Per replication, draws in\nfixed order: u (G normals), e (N normals), W (B x G Rademacher via rng.integers(0,2)).\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nDATA = os.path.join(ROOT, \"data\", \"design.csv\")\nOUT = os.path.join(ROOT, \"out\")\nEST = [\"cr0\", \"cr1\", \"wcb\"]\n\n\ndef simulate_cell(row):\n G, icc, N, R, B, mu = int(row.G), float(row.icc), int(row.N), int(row.R), int(row.B), float(row.mu)\n sizes = np.array([int(x) for x in row.cluster_sizes.split(\"|\")])\n assert len(sizes) == G and sizes.sum() == N\n gid = np.repeat(np.arange(G), sizes)\n var_exact = (icc * np.sum(sizes.astype(float) ** 2) + (1 - icc) * N) / N ** 2\n tcrit = stats.t.ppf(0.975, G - 1)\n zcrit = 1.96\n adj = G / (G - 1)\n rng = np.random.default_rng(int(row.seed))\n res = {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(icc), G) if icc > 0 else np.zeros(G)\n if icc == 0:\n rng.normal(0.0, 0.0, G) # keep stream layout identical across cells (draw discarded)\n e = rng.normal(0.0, np.sqrt(1 - icc), N)\n y = mu + u[gid] + e\n ybar = y.mean()\n ehat = y - ybar\n S = np.bincount(gid, weights=ehat, minlength=G) # cluster residual sums\n v0 = np.sum(S ** 2) / N ** 2\n v1 = adj * v0\n # wild cluster bootstrap-t (unrestricted, Rademacher), vectorised over B\n W = rng.integers(0, 2, size=(B, G)) * 2 - 1\n d = (W * S).sum(axis=1) / N # ybar* - ybar\n Sstar = W * S - np.outer(d, sizes) # cluster sums of bootstrap residuals\n v1s = adj * np.sum(Sstar ** 2, axis=1) / N ** 2\n if np.any(v1s <= 0):\n n_degenerate += int(np.sum(v1s <= 0))\n v1s = np.where(v1s <= 0, np.nan, v1s)\n tabs = np.abs(d) / np.sqrt(v1s)\n q = np.nanquantile(tabs, 0.95) # numpy default (linear interpolation)\n res[\"ybar\"][r], res[\"v0\"][r], res[\"v1\"][r], res[\"q\"][r] = ybar, v0, v1, q\n res[\"v_iid\"][r] = np.var(y, ddof=1) / N # naive i.i.d. baseline\n hw = {\"cr0\": zcrit * np.sqrt(res[\"v0\"]), \"cr1\": tcrit * np.sqrt(res[\"v1\"]),\n \"wcb\": res[\"q\"] * np.sqrt(res[\"v1\"]), \"iid\": zcrit * np.sqrt(res[\"v_iid\"])}\n out = {\"var_exact\": var_exact, \"n_degenerate\": n_degenerate, \"R\": R}\n for k, h in hw.items():\n cov = np.abs(res[\"ybar\"] - mu) <= h\n out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean())}\n for k, v in [(\"cr0\", res[\"v0\"]), (\"cr1\", res[\"v1\"])]:\n out[k][\"rel_bias\"] = float(v.mean() / var_exact)\n out[k][\"rel_bias_mcse\"] = float(v.std(ddof=1) / np.sqrt(R) / var_exact)\n out[\"mc_var_ybar_ratio\"] = float(np.var(res[\"ybar\"], ddof=1) / var_exact)\n out[\"mean_ybar\"] = float(res[\"ybar\"].mean())\n return out\n\n\ndef main():\n d = pd.read_csv(DATA)\n R_all, B_all = d.R.unique(), d.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 cov, se, rb, rb_se, base, chk = {}, {}, {}, {}, {}, {}\n rows, issues = [], []\n n_deg = 0\n for row in d.itertuples(index=False):\n o = simulate_cell(row)\n n_deg += o[\"n_degenerate\"]\n tag = f\"G{int(row.G)}_icc{float(row.icc):.1f}\"\n for k in EST:\n key = f\"{k}_{tag}\"\n p = o[k][\"coverage\"]\n cov[key] = p\n se[key] = float(np.sqrt(p * (1 - p) / o[\"R\"]))\n if k != \"wcb\":\n rb[key] = o[k][\"rel_bias\"]\n rb_se[key] = o[k][\"rel_bias_mcse\"]\n rows.append({\"estimator\": k, \"cell_id\": row.cell_id, \"G\": int(row.G), \"icc\": float(row.icc),\n \"coverage\": p, \"mc_se_coverage\": se[key],\n \"rel_bias_var\": o[k].get(\"rel_bias\", None), \"mean_ci_halfwidth\": o[k][\"hw\"], \"R\": o[\"R\"]})\n base[f\"iid_{tag}\"] = o[\"iid\"][\"coverage\"]\n chk[tag] = {\"mc_var_ybar_over_exact\": o[\"mc_var_ybar_ratio\"], \"mean_ybar\": o[\"mean_ybar\"]}\n print(f\"{row.cell_id} {tag}: \" + \", \".join(f\"{k}={cov[f'{k}_{tag}']:.4f}\" for k in EST))\n table = pd.DataFrame(rows)\n table.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n failure = [k for k, p in cov.items() if p < 0.90]\n nominal = [k for k, p in cov.items() if abs(p - 0.95) <= 2 * se[k]]\n g5 = {k: np.mean([cov[f\"{k}_G5_icc{i:.1f}\"] for i in (0.0, 0.2, 0.5)]) for k in EST}\n best = max(g5, key=g5.get)\n if 5 in d.G.values:\n issues.append({\"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct weight vectors exist (16 distinct |t*| values, as |t*| is invariant to w -> -w); B=399 draws therefore repeat these few values and the 0.95 quantile of |t*| is coarse.\",\n \"handling\": \"Kept as specified (B=399, Rademacher, random draws, numpy linear-interpolation quantile); discussed in report as a known feature of WCB with very few clusters.\"})\n if n_deg:\n issues.append({\"issue\": f\"{n_deg} bootstrap draws had non-positive V_CR1*\", \"handling\": \"Excluded those draws from the |t*| quantile (nan-quantile).\"})\n results = {\n \"task_id\": \"T2-simulation\", \"R\": R, \"B\": B, \"n_cells\": int(len(d)),\n \"coverage\": cov, \"mc_se_coverage\": se, \"rel_bias_var\": rb,\n \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n \"best_procedure_small_G\": best,\n \"feasibility\": \"complete\", \"feasibility_reason\": None, \"data_issues\": issues,\n \"n_input_rows\": {\"design.csv\": int(len(d))},\n \"n_analysed\": int(len(d) * R), \"random_seed\": int(d.loc[d.cell_id == \"C1\", \"seed\"].iloc[0]),\n # supplementary keys\n \"avg_coverage_G5\": {k: float(v) for k, v in g5.items()},\n \"mc_se_rel_bias_var\": rb_se,\n \"baseline_iid_coverage\": base,\n \"check_mc_var_ybar_over_exact\": chk,\n \"n_degenerate_bootstrap_draws\": int(n_deg),\n \"wcb_quantile_method\": \"numpy.quantile linear interpolation (type 7) of |t*_b|, b=1..B\",\n \"seeds_by_cell\": {r.cell_id: int(r.seed) for r in d.itertuples(index=False)},\n }\n with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n # figure\n fig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\n Gs = sorted(d.G.unique())\n style = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t Rademacher\")}\n for ax, icc in zip(axes, sorted(d.icc.unique())):\n for k in EST:\n p = np.array([cov[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n s = np.array([se[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n ax.errorbar(Gs, p, yerr=1.96 * s, fmt=style[k][0], capsize=3, label=style[k][1])\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(Gs)\n ax.set_title(f\"ICC = {icc:.1f}\"); ax.set_xlabel(\"number of clusters G\")\n axes[0].set_ylabel(\"coverage (R=2000; bars ±1.96 MC SE)\")\n axes[0].legend(loc=\"lower right\", fontsize=8)\n fig.tight_layout()\n fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n print(\"failure cells:\", failure)\n print(\"best procedure at G=5:\", best)\n\n\nif __name__ == \"__main__\":\n main()\nEOF\ncd .. && time ~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1081,"cache_read_input_tokens":12295,"output_tokens":4721,"output_tokens_details":{"thinking_tokens":696},"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":1081},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt9jheW3UUETnzxsx4m","requestRef":"e78b9c58-93ca-4220-80ad-b7b1e8be2527","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9182131b-6e3c-4247-ac68-8da198cabb62","timestamp":"2026-10-30T05:39:05.462Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"9182131b-6e3c-4247-ac68-8da198cabb62","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01RKGbWiUBh4i7UrcbnS79jy","type":"tool_result","content":"C1 G5_icc0.0: cr0=0.7805, cr1=0.9115, wcb=0.8550\nC2 G5_icc0.2: cr0=0.7210, cr1=0.8845, wcb=0.8540\nC3 G5_icc0.5: cr0=0.7170, cr1=0.8755, wcb=0.8490\nC4 G10_icc0.0: cr0=0.8965, cr1=0.9435, wcb=0.9360\nC5 G10_icc0.2: cr0=0.8570, cr1=0.9155, wcb=0.9295\nC6 G10_icc0.5: cr0=0.8530, cr1=0.9065, wcb=0.9325\nC7 G30_icc0.0: cr0=0.9275, cr1=0.9400, wcb=0.9430\nC8 G30_icc0.2: cr0=0.9210, cr1=0.9350, wcb=0.9460\nC9 G30_icc0.5: cr0=0.9165, cr1=0.9300, wcb=0.9425\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\n~/wp29/venv/bin/python out/analysis.py 2,00s user 0,07s system 99% cpu 2,078 total","is_error":false}]},"uuid":"ff2585f4-7cdd-40c6-b651-7d62cc052e13","timestamp":"2026-10-30T05:39:07.587Z","toolUseResult":{"stdout":"C1 G5_icc0.0: cr0=0.7805, cr1=0.9115, wcb=0.8550\nC2 G5_icc0.2: cr0=0.7210, cr1=0.8845, wcb=0.8540\nC3 G5_icc0.5: cr0=0.7170, cr1=0.8755, wcb=0.8490\nC4 G10_icc0.0: cr0=0.8965, cr1=0.9435, wcb=0.9360\nC5 G10_icc0.2: cr0=0.8570, cr1=0.9155, wcb=0.9295\nC6 G10_icc0.5: cr0=0.8530, cr1=0.9065, wcb=0.9325\nC7 G30_icc0.0: cr0=0.9275, cr1=0.9400, wcb=0.9430\nC8 G30_icc0.2: cr0=0.9210, cr1=0.9350, wcb=0.9460\nC9 G30_icc0.5: cr0=0.9165, cr1=0.9300, wcb=0.9425\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\n~/wp29/venv/bin/python out/analysis.py 2,00s user 0,07s system 99% cpu 2,078 total","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"9182131b-6e3c-4247-ac68-8da198cabb62","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}47{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"cccac06a1a65ba7ed88971fd3f74f8dc1efdecafbd3ae62fb5c7bf808d0ad17e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSnhEKEAgTGAI4AUIIdGhpbmtpbmcSDCH7bxdMzzU08Jn+GxoMGkuLhDGVicggaafYIjB9zVsVh6lkYc4GOClD442mMS54177CKGucOBASaHnRMXoge8Mhxp2GLTfLvCrm5qMquxCL9KnijtlZT3bv1uh/+XNH1bs0C92h89DeGI/P4bheFGLWHUKtbVJvsWAOIelIFGxICfrY9YPYVuiEHwqnAWYlJLnRpDu1nrEqdhqwRJQJZ0Tj914MKxXNZWyzBCiIoJmjbM9CVVPChB6p3CLDcmSVRtHj1WzHxXfCdGfwPDXavyyFsr6XnKXOUgzkyXJ3jFAdEg79hAQHNDJOe/KZt+OwpzyAZr33nAzv3KU0EDOPJBxQqTliRBqiQA7SzgrHm/DGFkw4wNYP16KjDWLPmyt1BUh3Pn3j4ptuCmPqTJX5bWvyJn5Uc9LeOXbsfdPQ1XwQhUVtarOiK34/TvL1mZWWHT15CAeF2A/iA5DgdKHwYCKLZfeDhpiLjMOsD1SnAbqwW11A1ygjLP4dqAjTpRQ6us7UPEdCHufEuiMt/gkZG0ic1WL9yulYTWxjUaTV0jDkFoNh2wMCt6drPQH1wcIYdkUWFNIfYfr8vn2AHHJ0h2U0HIPq4uti3CeF7ApRCtvXAo7LddZpgBNhKWKWHb/ywb5swg6P+Or7OEC4B9iazw2WOX2+FLcfKtXSEZJFvdVkV5ZVQ5LXu9Ev8tuwi2g18pBlRNsbYKJ4Lo/e/1ZzeyOejhVgTblvmY1qZn6w1kpJgf2/LZbWiYljbFpL9NNoOZSBIKfJZ1MXVpeMziCtaaGoKznwDH9MNelh7/EuvfehNfqcZEE/MJVFjPKDdh20xeXDYUrWe6RNr8cLY+sOh09W4hAi0q6FmlSE4ccE9JoriZa2+HAPAPWULY4LdtS4BhEnFdYtjQriQgkjiVRYtcUX8M9WDsLkyE3c4QaSWE+rJxIaqBQ8tVNl1FFgKsQ2xp9dqxbL9P7LCGv5PVyVrpipsHjjhRB2+Q98cZesY1GHw3oUlo/zGy9ZN8Zu8W9KkOvQWTDTmQzAffbwKpjFWvflvwyUFIhBx8caYcf8QuQLrx6h2h11txqBeEkd9TSgb0EJgwvp2I8mlGabs0F8Qm7bFjZ1fUWU1afkcSuZtwbz1yw0WMK6Ut3LvBhtLmhUJ1YQ8Ogy24PkguInCHKAacCJAKOQVSw3TVlU/SKyjJxGjDPE0MGacFe0bPn91n9+6wkFHsZt0PBjNj4jNUC+i9QrOMdTqdyFble/ebWdLwg7ic8Zxpf9gsxIArZ+RrGgExJ7GGPLtrLxZWCJWsY2pHRxDpctJ/88fYkSbU1/w2QYE2R6T/Z2zHxmBxhG4oCN3381K0QmhEa04QzDzBvzTN2plUfso8Z8cUlWp+xUk8Rnz4FQwy9pKJDblOvZ60jXq+bHWJmqQtKTnRwn09D3mfottb3MzljqrPSdSRL98h9aLJBi/k1jwCzuvbuGYWhlF6/xHYVKak9ZHUlfCT6KgJeUuQ/HTmtBJ5U1XFTgxBLgQhPjfsx09y0ec7ljJd0bgIW5hHB0NCOlEU8gJVzLyMzhTnObnAQCBm1DsL4JcMgWNDzEtaTIlDO/4QaW60PeoOTort23XYIc301AAE9K9rajXYfue3YCCleD4N/tnp6niHWYgWlBRkSzA/CpvayCPwZNVXZ7SpXmWWHy3o9/Qv0PrCr+Drjf11defeuwa9F6wB/XTzuExKk/dBa8jcMTT3we89/6W5ytF6oVCQcXVZ2HqXxzDrQ73pQ01pe5u+t6Ygh6QEABOOQXqACXmRU6AjdggC9DpV12IavxAs1OWgVsuq7L5HEFWdAtScK5Z4dSwBYtcOjjU0NvZZs5Mjvyt4njqznlB0aOt8FE11XLqs2RNFshM/TQRs/0WLY11M3M3e9fc4p2VeYjLrbKqWagF4LgHJ7VWx1FwSEtP0IjNy1/wQ4lMd8DOFZrY/cHYQ886xNOeNm1K5BeRCGZHjt25AaDjQdNLhvmP8ePTXGBRE8Gp6r8vzlcNGyh6SKKyNNrSag080ZKvxAHDlk4E/XhhwgS17rOjrAgp26J7woBsLUCkpaDA7vtdLOK/HJ7o/FGSQY+b17PbwqNQUj61p3mH4EGP3HIr09p22R14GVSJHqMvm5IPalAjfZPprxHTMUsT1/wyZQypQ2gLtjY7oqlkHuPwKqFggoj/XIql65lP49rl6O4dD69bGOOGtdtLI3Bv/Vzoq1jqnR3oUCcXEzhMIuXImwCnDlke5FSKLS3Zpqtyf/XNjbiWXwRXXnXi54iXNS6cH+JfzuGCMc+MDDokYy3w0cTo/gZutRrX1M7hhPKSb+xywTcCMj1RbEnFwEkrop0G75ewEwRlzaOTDgCoe9qmZhyQheH6bCr0WvYbgS7jUsYTSDU59/auIpXY4nUrmFWpL5KTBavZrBRglgBD6NclL1SG0ufHz9v57MxXWXB3rHCpXvoyVqoQbNaRjW+6zJP0Fj4qEDjTocGEBeVnxQsDTPeHzKcpxwZEfCno6qKhZBRg0eHN94Twh092gzyXVMEKKBMdGaKExNrBXqprzpYuOC+KDRD9sIO2zK3e7J3JlDcaxllFZ0JvLqIlLnavgDCyKCFfLfHx5MoibSJKhLxcWnAE10uaNdjtHPHSOTf8+9piIPd+vdHbOEXqClSvcRrBTjZM+VHKH2H6w6OVAGeuf7imSiP9yWJYhHDo1xPh46xZRiOHWn/KSJ4JFlNCuoUIfCtJ1fTRu419DsvZrHcD5pHIpxF9321M+wDJ9ro5BoBkF+pwOYdNUAItyrniwwbftGj2tTtcn7bwucvkdHJXgItZrMWCtB8Q5T40h8Q+VBfWG+JfizVgXmGGMyP15xdf9VuPuyeRbluy3TM+bxiUEnRIYgtdzcp/VdChqJok0wadayux3ypGAE="},{"type":"tool_use","id":"toolu_01RKGbWiUBh4i7UrcbnS79jy","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0020/out && cat > analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t CIs for a mean.\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png.\nRandomness: one numpy default_rng(seed) per cell (seed from design.csv). Per replication, draws in\nfixed order: u (G normals), e (N normals), W (B x G Rademacher via rng.integers(0,2)).\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nDATA = os.path.join(ROOT, \"data\", \"design.csv\")\nOUT = os.path.join(ROOT, \"out\")\nEST = [\"cr0\", \"cr1\", \"wcb\"]\n\n\ndef simulate_cell(row):\n G, icc, N, R, B, mu = int(row.G), float(row.icc), int(row.N), int(row.R), int(row.B), float(row.mu)\n sizes = np.array([int(x) for x in row.cluster_sizes.split(\"|\")])\n assert len(sizes) == G and sizes.sum() == N\n gid = np.repeat(np.arange(G), sizes)\n var_exact = (icc * np.sum(sizes.astype(float) ** 2) + (1 - icc) * N) / N ** 2\n tcrit = stats.t.ppf(0.975, G - 1)\n zcrit = 1.96\n adj = G / (G - 1)\n rng = np.random.default_rng(int(row.seed))\n res = {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(icc), G) if icc > 0 else np.zeros(G)\n if icc == 0:\n rng.normal(0.0, 0.0, G) # keep stream layout identical across cells (draw discarded)\n e = rng.normal(0.0, np.sqrt(1 - icc), N)\n y = mu + u[gid] + e\n ybar = y.mean()\n ehat = y - ybar\n S = np.bincount(gid, weights=ehat, minlength=G) # cluster residual sums\n v0 = np.sum(S ** 2) / N ** 2\n v1 = adj * v0\n # wild cluster bootstrap-t (unrestricted, Rademacher), vectorised over B\n W = rng.integers(0, 2, size=(B, G)) * 2 - 1\n d = (W * S).sum(axis=1) / N # ybar* - ybar\n Sstar = W * S - np.outer(d, sizes) # cluster sums of bootstrap residuals\n v1s = adj * np.sum(Sstar ** 2, axis=1) / N ** 2\n if np.any(v1s <= 0):\n n_degenerate += int(np.sum(v1s <= 0))\n v1s = np.where(v1s <= 0, np.nan, v1s)\n tabs = np.abs(d) / np.sqrt(v1s)\n q = np.nanquantile(tabs, 0.95) # numpy default (linear interpolation)\n res[\"ybar\"][r], res[\"v0\"][r], res[\"v1\"][r], res[\"q\"][r] = ybar, v0, v1, q\n res[\"v_iid\"][r] = np.var(y, ddof=1) / N # naive i.i.d. baseline\n hw = {\"cr0\": zcrit * np.sqrt(res[\"v0\"]), \"cr1\": tcrit * np.sqrt(res[\"v1\"]),\n \"wcb\": res[\"q\"] * np.sqrt(res[\"v1\"]), \"iid\": zcrit * np.sqrt(res[\"v_iid\"])}\n out = {\"var_exact\": var_exact, \"n_degenerate\": n_degenerate, \"R\": R}\n for k, h in hw.items():\n cov = np.abs(res[\"ybar\"] - mu) <= h\n out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean())}\n for k, v in [(\"cr0\", res[\"v0\"]), (\"cr1\", res[\"v1\"])]:\n out[k][\"rel_bias\"] = float(v.mean() / var_exact)\n out[k][\"rel_bias_mcse\"] = float(v.std(ddof=1) / np.sqrt(R) / var_exact)\n out[\"mc_var_ybar_ratio\"] = float(np.var(res[\"ybar\"], ddof=1) / var_exact)\n out[\"mean_ybar\"] = float(res[\"ybar\"].mean())\n return out\n\n\ndef main():\n d = pd.read_csv(DATA)\n R_all, B_all = d.R.unique(), d.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 cov, se, rb, rb_se, base, chk = {}, {}, {}, {}, {}, {}\n rows, issues = [], []\n n_deg = 0\n for row in d.itertuples(index=False):\n o = simulate_cell(row)\n n_deg += o[\"n_degenerate\"]\n tag = f\"G{int(row.G)}_icc{float(row.icc):.1f}\"\n for k in EST:\n key = f\"{k}_{tag}\"\n p = o[k][\"coverage\"]\n cov[key] = p\n se[key] = float(np.sqrt(p * (1 - p) / o[\"R\"]))\n if k != \"wcb\":\n rb[key] = o[k][\"rel_bias\"]\n rb_se[key] = o[k][\"rel_bias_mcse\"]\n rows.append({\"estimator\": k, \"cell_id\": row.cell_id, \"G\": int(row.G), \"icc\": float(row.icc),\n \"coverage\": p, \"mc_se_coverage\": se[key],\n \"rel_bias_var\": o[k].get(\"rel_bias\", None), \"mean_ci_halfwidth\": o[k][\"hw\"], \"R\": o[\"R\"]})\n base[f\"iid_{tag}\"] = o[\"iid\"][\"coverage\"]\n chk[tag] = {\"mc_var_ybar_over_exact\": o[\"mc_var_ybar_ratio\"], \"mean_ybar\": o[\"mean_ybar\"]}\n print(f\"{row.cell_id} {tag}: \" + \", \".join(f\"{k}={cov[f'{k}_{tag}']:.4f}\" for k in EST))\n table = pd.DataFrame(rows)\n table.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n failure = [k for k, p in cov.items() if p < 0.90]\n nominal = [k for k, p in cov.items() if abs(p - 0.95) <= 2 * se[k]]\n g5 = {k: np.mean([cov[f\"{k}_G5_icc{i:.1f}\"] for i in (0.0, 0.2, 0.5)]) for k in EST}\n best = max(g5, key=g5.get)\n if 5 in d.G.values:\n issues.append({\"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct weight vectors exist (16 distinct |t*| values, as |t*| is invariant to w -> -w); B=399 draws therefore repeat these few values and the 0.95 quantile of |t*| is coarse.\",\n \"handling\": \"Kept as specified (B=399, Rademacher, random draws, numpy linear-interpolation quantile); discussed in report as a known feature of WCB with very few clusters.\"})\n if n_deg:\n issues.append({\"issue\": f\"{n_deg} bootstrap draws had non-positive V_CR1*\", \"handling\": \"Excluded those draws from the |t*| quantile (nan-quantile).\"})\n results = {\n \"task_id\": \"T2-simulation\", \"R\": R, \"B\": B, \"n_cells\": int(len(d)),\n \"coverage\": cov, \"mc_se_coverage\": se, \"rel_bias_var\": rb,\n \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n \"best_procedure_small_G\": best,\n \"feasibility\": \"complete\", \"feasibility_reason\": None, \"data_issues\": issues,\n \"n_input_rows\": {\"design.csv\": int(len(d))},\n \"n_analysed\": int(len(d) * R), \"random_seed\": int(d.loc[d.cell_id == \"C1\", \"seed\"].iloc[0]),\n # supplementary keys\n \"avg_coverage_G5\": {k: float(v) for k, v in g5.items()},\n \"mc_se_rel_bias_var\": rb_se,\n \"baseline_iid_coverage\": base,\n \"check_mc_var_ybar_over_exact\": chk,\n \"n_degenerate_bootstrap_draws\": int(n_deg),\n \"wcb_quantile_method\": \"numpy.quantile linear interpolation (type 7) of |t*_b|, b=1..B\",\n \"seeds_by_cell\": {r.cell_id: int(r.seed) for r in d.itertuples(index=False)},\n }\n with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n # figure\n fig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\n Gs = sorted(d.G.unique())\n style = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t Rademacher\")}\n for ax, icc in zip(axes, sorted(d.icc.unique())):\n for k in EST:\n p = np.array([cov[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n s = np.array([se[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n ax.errorbar(Gs, p, yerr=1.96 * s, fmt=style[k][0], capsize=3, label=style[k][1])\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(Gs)\n ax.set_title(f\"ICC = {icc:.1f}\"); ax.set_xlabel(\"number of clusters G\")\n axes[0].set_ylabel(\"coverage (R=2000; bars ±1.96 MC SE)\")\n axes[0].legend(loc=\"lower right\", fontsize=8)\n fig.tight_layout()\n fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n print(\"failure cells:\", failure)\n print(\"best procedure at G=5:\", best)\n\n\nif __name__ == \"__main__\":\n main()\nEOF\ncd .. && time ~/wp29/venv/bin/python out/analysis.py","description":"Write and run analysis script"}}]}}48{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"e65c86a7-4cbb-4af0-abe9-f1f8f11ae4d5","timestamp":"2026-10-30T05:39:07.589Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"e78b9c58-93ca-4220-80ad-b7b1e8be2527","keep":14,"tail":["cccac06a1a65ba7ed88971fd3f74f8dc1efdecafbd3ae62fb5c7bf808d0ad17e","b9476da7d4d69d728488939147753c35a657f4729c69a88064819cc9c3aa78e0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a5ef1a9048c0bb8c463bc9787ea644a2a5c5c725d023a36f7f537fdb45ac10b9"}49{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"ff2585f4-7cdd-40c6-b651-7d62cc052e13","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}50{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}51{"parentUuid":"ff2585f4-7cdd-40c6-b651-7d62cc052e13","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCbmUrAGG3JYLgkYbU","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":5305,"cache_read_input_tokens":13376,"output_tokens":997,"output_tokens_details":{"thinking_tokens":409},"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":5305},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4185,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtCbUNpDb1R1nLmBQPv","requestRef":"e65c86a7-4cbb-4af0-abe9-f1f8f11ae4d5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f1428a49-40ee-4daa-9510-8b97666ab123","timestamp":"2026-10-30T05:39:12.874Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}52{"parentUuid":"f1428a49-40ee-4daa-9510-8b97666ab123","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCbmUrAGG3JYLgkYbU","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LdSGKMThr92koSHZX4uHVR","name":"Bash","input":{"command":"sed -i '' 's/ u = rng.normal(0.0, np.sqrt(icc), G) if icc > 0 else np.zeros(G)\\n//' out/analysis.py && ~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\ns=s.replace(\"\"\" u = rng.normal(0.0, np.sqrt(icc), G) if icc > 0 else np.zeros(G)\n if icc == 0:\n rng.normal(0.0, 0.0, G) # keep stream layout identical across cells (draw discarded)\n\"\"\",\"\"\" u = rng.normal(0.0, np.sqrt(icc), G) # scale 0 when icc=0 -> u = 0\n\"\"\")\nopen('out/analysis.py','w').write(s)\nEOF\ncp out/results.json /tmp/r_old.json; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r_old.json && echo same; ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k in ['rel_bias_var','mc_se_rel_bias_var','baseline_iid_coverage','check_mc_var_ybar_over_exact','avg_coverage_G5','nominal_cells','n_degenerate_bootstrap_draws']: print(k,r[k])\n\"","description":"Simplify u draw, rerun, inspect results"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5305,"cache_read_input_tokens":13376,"output_tokens":997,"output_tokens_details":{"thinking_tokens":409},"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":5305},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtCbUNpDb1R1nLmBQPv","requestRef":"e65c86a7-4cbb-4af0-abe9-f1f8f11ae4d5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"87896074-b5bf-4fd0-921a-40c9f18da486","timestamp":"2026-10-30T05:39:16.867Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"87896074-b5bf-4fd0-921a-40c9f18da486","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LdSGKMThr92koSHZX4uHVR","type":"tool_result","content":"same\nrel_bias_var {'cr0_G5_icc0.0': 0.6616434596045324, 'cr1_G5_icc0.0': 0.8270543245056654, 'cr0_G5_icc0.2': 0.5313958571125164, 'cr1_G5_icc0.2': 0.6642448213906453, 'cr0_G5_icc0.5': 0.48335023384407516, 'cr1_G5_icc0.5': 0.6041877923050938, 'cr0_G10_icc0.0': 0.8558047169939658, 'cr1_G10_icc0.0': 0.9508941299932954, 'cr0_G10_icc0.2': 0.7624366224508259, 'cr1_G10_icc0.2': 0.8471518027231398, 'cr0_G10_icc0.5': 0.7737432482368367, 'cr1_G10_icc0.5': 0.859714720263152, 'cr0_G30_icc0.0': 0.943796503270819, 'cr1_G30_icc0.0': 0.9763412102801576, 'cr0_G30_icc0.2': 0.9313668684580917, 'cr1_G30_icc0.2': 0.9634829673704397, 'cr0_G30_icc0.5': 0.9252598675851053, 'cr1_G30_icc0.5': 0.9571653802604538}\nmc_se_rel_bias_var {'cr0_G5_icc0.0': 0.012963511182344976, 'cr1_G5_icc0.0': 0.01620438897793122, 'cr0_G5_icc0.2': 0.012975387163286884, 'cr1_G5_icc0.2': 0.016219233954108608, 'cr0_G5_icc0.5': 0.011854909267984598, 'cr1_G5_icc0.5': 0.01481863658498075, 'cr0_G10_icc0.0': 0.011793478824212352, 'cr1_G10_icc0.0': 0.013103865360235948, 'cr0_G10_icc0.2': 0.012887411160981703, 'cr1_G10_icc0.2': 0.014319345734424112, 'cr0_G10_icc0.5': 0.014100595197540216, 'cr1_G10_icc0.5': 0.015667327997266903, 'cr0_G30_icc0.0': 0.006765949452231232, 'cr1_G30_icc0.0': 0.006999258054032309, 'cr0_G30_icc0.2': 0.00853308139600021, 'cr1_G30_icc0.2': 0.008827325582069187, 'cr0_G30_icc0.5': 0.008700682520806436, 'cr1_G30_icc0.5': 0.009000706056006657}\nbaseline_iid_coverage {'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}\ncheck_mc_var_ybar_over_exact {'G5_icc0.0': {'mc_var_ybar_over_exact': 1.03532630144612, 'mean_ybar': 0.00028867307788429486}, 'G5_icc0.2': {'mc_var_ybar_over_exact': 1.0645917096631416, 'mean_ybar': 0.010497786660162045}, 'G5_icc0.5': {'mc_var_ybar_over_exact': 0.9463288431559199, 'mean_ybar': -0.005763243574855418}, 'G10_icc0.0': {'mc_var_ybar_over_exact': 0.9335632526902219, 'mean_ybar': -8.481537588492616e-05}, 'G10_icc0.2': {'mc_var_ybar_over_exact': 0.9685288371506661, 'mean_ybar': 0.004033474563745705}, 'G10_icc0.5': {'mc_var_ybar_over_exact': 0.979581002751385, 'mean_ybar': -0.0013932598375193423}, 'G30_icc0.0': {'mc_var_ybar_over_exact': 0.9985616155092211, 'mean_ybar': -0.000782799084647925}, 'G30_icc0.2': {'mc_var_ybar_over_exact': 0.9393486739255914, 'mean_ybar': 0.0021016344076126483}, 'G30_icc0.5': {'mc_var_ybar_over_exact': 1.0404439013279725, 'mean_ybar': -0.0024768417619560603}}\navg_coverage_G5 {'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8526666666666666}\nnominal_cells ['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5']\nn_degenerate_bootstrap_draws 0","is_error":false}]},"uuid":"cdbde2e9-73c0-4aab-9cfb-52aca2120d2b","timestamp":"2026-10-30T05:39:19.033Z","toolUseResult":{"stdout":"same\nrel_bias_var {'cr0_G5_icc0.0': 0.6616434596045324, 'cr1_G5_icc0.0': 0.8270543245056654, 'cr0_G5_icc0.2': 0.5313958571125164, 'cr1_G5_icc0.2': 0.6642448213906453, 'cr0_G5_icc0.5': 0.48335023384407516, 'cr1_G5_icc0.5': 0.6041877923050938, 'cr0_G10_icc0.0': 0.8558047169939658, 'cr1_G10_icc0.0': 0.9508941299932954, 'cr0_G10_icc0.2': 0.7624366224508259, 'cr1_G10_icc0.2': 0.8471518027231398, 'cr0_G10_icc0.5': 0.7737432482368367, 'cr1_G10_icc0.5': 0.859714720263152, 'cr0_G30_icc0.0': 0.943796503270819, 'cr1_G30_icc0.0': 0.9763412102801576, 'cr0_G30_icc0.2': 0.9313668684580917, 'cr1_G30_icc0.2': 0.9634829673704397, 'cr0_G30_icc0.5': 0.9252598675851053, 'cr1_G30_icc0.5': 0.9571653802604538}\nmc_se_rel_bias_var {'cr0_G5_icc0.0': 0.012963511182344976, 'cr1_G5_icc0.0': 0.01620438897793122, 'cr0_G5_icc0.2': 0.012975387163286884, 'cr1_G5_icc0.2': 0.016219233954108608, 'cr0_G5_icc0.5': 0.011854909267984598, 'cr1_G5_icc0.5': 0.01481863658498075, 'cr0_G10_icc0.0': 0.011793478824212352, 'cr1_G10_icc0.0': 0.013103865360235948, 'cr0_G10_icc0.2': 0.012887411160981703, 'cr1_G10_icc0.2': 0.014319345734424112, 'cr0_G10_icc0.5': 0.014100595197540216, 'cr1_G10_icc0.5': 0.015667327997266903, 'cr0_G30_icc0.0': 0.006765949452231232, 'cr1_G30_icc0.0': 0.006999258054032309, 'cr0_G30_icc0.2': 0.00853308139600021, 'cr1_G30_icc0.2': 0.008827325582069187, 'cr0_G30_icc0.5': 0.008700682520806436, 'cr1_G30_icc0.5': 0.009000706056006657}\nbaseline_iid_coverage {'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}\ncheck_mc_var_ybar_over_exact {'G5_icc0.0': {'mc_var_ybar_over_exact': 1.03532630144612, 'mean_ybar': 0.00028867307788429486}, 'G5_icc0.2': {'mc_var_ybar_over_exact': 1.0645917096631416, 'mean_ybar': 0.010497786660162045}, 'G5_icc0.5': {'mc_var_ybar_over_exact': 0.9463288431559199, 'mean_ybar': -0.005763243574855418}, 'G10_icc0.0': {'mc_var_ybar_over_exact': 0.9335632526902219, 'mean_ybar': -8.481537588492616e-05}, 'G10_icc0.2': {'mc_var_ybar_over_exact': 0.9685288371506661, 'mean_ybar': 0.004033474563745705}, 'G10_icc0.5': {'mc_var_ybar_over_exact': 0.979581002751385, 'mean_ybar': -0.0013932598375193423}, 'G30_icc0.0': {'mc_var_ybar_over_exact': 0.9985616155092211, 'mean_ybar': -0.000782799084647925}, 'G30_icc0.2': {'mc_var_ybar_over_exact': 0.9393486739255914, 'mean_ybar': 0.0021016344076126483}, 'G30_icc0.5': {'mc_var_ybar_over_exact': 1.0404439013279725, 'mean_ybar': -0.0024768417619560603}}\navg_coverage_G5 {'cr0': 0.7395, 'cr1': 0.8905, 'wcb': 0.8526666666666666}\nnominal_cells ['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5']\nn_degenerate_bootstrap_draws 0","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"87896074-b5bf-4fd0-921a-40c9f18da486","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}54{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"67a5ff1854ea24e81a331da6340aee3229aab5da95190f2fdd7a765b9f01862f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LdSGKMThr92koSHZX4uHVR","name":"Bash","input":{"command":"sed -i '' 's/ u = rng.normal(0.0, np.sqrt(icc), G) if icc > 0 else np.zeros(G)\\n//' out/analysis.py && ~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\ns=s.replace(\"\"\" u = rng.normal(0.0, np.sqrt(icc), G) if icc > 0 else np.zeros(G)\n if icc == 0:\n rng.normal(0.0, 0.0, G) # keep stream layout identical across cells (draw discarded)\n\"\"\",\"\"\" u = rng.normal(0.0, np.sqrt(icc), G) # scale 0 when icc=0 -> u = 0\n\"\"\")\nopen('out/analysis.py','w').write(s)\nEOF\ncp out/results.json /tmp/r_old.json; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r_old.json && echo same; ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k in ['rel_bias_var','mc_se_rel_bias_var','baseline_iid_coverage','check_mc_var_ybar_over_exact','avg_coverage_G5','nominal_cells','n_degenerate_bootstrap_draws']: print(k,r[k])\n\"","description":"Simplify u draw, rerun, inspect results"}}]}}55{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"83335b53-75b2-4329-afb2-2949657c1e3b","timestamp":"2026-10-30T05:39:19.036Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"e65c86a7-4cbb-4af0-abe9-f1f8f11ae4d5","keep":16,"tail":["67a5ff1854ea24e81a331da6340aee3229aab5da95190f2fdd7a765b9f01862f","052012aee5535277dc388a43f332adb7b41a4c33ca4cc4bb14b61358ddc478fc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1af616c9dc48156050a28601d7cb20e4d0503319c1897c253f9283fe2c140922"}56{"parentUuid":"cdbde2e9-73c0-4aab-9cfb-52aca2120d2b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDSeLGBXEbV3X9gSCv","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":2764,"cache_read_input_tokens":18681,"output_tokens":972,"output_tokens_details":{"thinking_tokens":297},"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":2764},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2896,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtDSRwK1YPwtrZVg6pW","requestRef":"83335b53-75b2-4329-afb2-2949657c1e3b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2f1c9f80-a042-49ce-b2a7-653ee7ad31ec","timestamp":"2026-10-30T05:39:23.041Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}57{"parentUuid":"2f1c9f80-a042-49ce-b2a7-653ee7ad31ec","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtDSeLGBXEbV3X9gSCv","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014xLGiJbunS2wq6NeGfASvJ","name":"Bash","input":{"command":"cat > out/state/verify_exact.py <<'EOF'\n# Verification only (not part of deliverable pipeline): exact E[V_CR0]/Var(ybar) vs Monte Carlo.\nimport json, numpy as np, pandas as pd\nd = pd.read_csv('data/design.csv'); r = json.load(open('out/results.json'))\nfor row in d.itertuples():\n n = np.array([int(x) for x in row.cluster_sizes.split('|')]); G, N = len(n), n.sum()\n C = np.zeros((G, N)); C[np.repeat(np.arange(G), n), np.arange(N)] = 1\n P = np.eye(N) - 1.0 / N\n Sig = row.icc * C.T @ C + (1 - row.icc) * np.eye(N)\n ev0 = np.trace(C @ P @ Sig @ P @ C.T) / N**2\n vx = (row.icc * np.sum(n**2) + (1 - row.icc) * N) / N**2\n k = f\"cr0_G{G}_icc{row.icc:.1f}\"\n mc, se = r['rel_bias_var'][k], r['mc_se_rel_bias_var'][k]\n print(k, f\"exact={ev0/vx:.4f} mc={mc:.4f} z={(mc-ev0/vx)/se:+.2f}\",\n \"cr1 ratio ok\" if abs(r['rel_bias_var'][k.replace('cr0','cr1')]/mc - G/(G-1)) < 1e-12 else \"CR1 MISMATCH\")\nEOF\n~/wp29/venv/bin/python out/state/verify_exact.py","description":"Compare MC relative bias with exact expectation"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2764,"cache_read_input_tokens":18681,"output_tokens":972,"output_tokens_details":{"thinking_tokens":297},"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":2764},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtDSRwK1YPwtrZVg6pW","requestRef":"83335b53-75b2-4329-afb2-2949657c1e3b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f9b6e61a-db96-4e6d-9aeb-c35434d36b90","timestamp":"2026-10-30T05:39:28.181Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"f9b6e61a-db96-4e6d-9aeb-c35434d36b90","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014xLGiJbunS2wq6NeGfASvJ","type":"tool_result","content":"cr0_G5_icc0.0 exact=0.6641 mc=0.6616 z=-0.19 cr1 ratio ok\ncr0_G5_icc0.2 exact=0.4995 mc=0.5314 z=+2.46 cr1 ratio ok\ncr0_G5_icc0.5 exact=0.4883 mc=0.4834 z=-0.42 cr1 ratio ok\ncr0_G10_icc0.0 exact=0.8393 mc=0.8558 z=+1.40 cr1 ratio ok\ncr0_G10_icc0.2 exact=0.7599 mc=0.7624 z=+0.20 cr1 ratio ok\ncr0_G10_icc0.5 exact=0.7544 mc=0.7737 z=+1.37 cr1 ratio ok\ncr0_G30_icc0.0 exact=0.9486 mc=0.9438 z=-0.70 cr1 ratio ok\ncr0_G30_icc0.2 exact=0.9267 mc=0.9314 z=+0.54 cr1 ratio ok\ncr0_G30_icc0.5 exact=0.9253 mc=0.9253 z=-0.00 cr1 ratio ok","is_error":false}]},"uuid":"965d106a-183e-4afa-a35d-b362026949f2","timestamp":"2026-10-30T05:39:28.409Z","toolUseResult":{"stdout":"cr0_G5_icc0.0 exact=0.6641 mc=0.6616 z=-0.19 cr1 ratio ok\ncr0_G5_icc0.2 exact=0.4995 mc=0.5314 z=+2.46 cr1 ratio ok\ncr0_G5_icc0.5 exact=0.4883 mc=0.4834 z=-0.42 cr1 ratio ok\ncr0_G10_icc0.0 exact=0.8393 mc=0.8558 z=+1.40 cr1 ratio ok\ncr0_G10_icc0.2 exact=0.7599 mc=0.7624 z=+0.20 cr1 ratio ok\ncr0_G10_icc0.5 exact=0.7544 mc=0.7737 z=+1.37 cr1 ratio ok\ncr0_G30_icc0.0 exact=0.9486 mc=0.9438 z=-0.70 cr1 ratio ok\ncr0_G30_icc0.2 exact=0.9267 mc=0.9314 z=+0.54 cr1 ratio ok\ncr0_G30_icc0.5 exact=0.9253 mc=0.9253 z=-0.00 cr1 ratio ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f9b6e61a-db96-4e6d-9aeb-c35434d36b90","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}59{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"fa8628fdcd6092f3947a059d8c5a8499b1e8e7e31df0aa3a24c2ace8f2de7a32","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_014xLGiJbunS2wq6NeGfASvJ","name":"Bash","input":{"command":"cat > out/state/verify_exact.py <<'EOF'\n# Verification only (not part of deliverable pipeline): exact E[V_CR0]/Var(ybar) vs Monte Carlo.\nimport json, numpy as np, pandas as pd\nd = pd.read_csv('data/design.csv'); r = json.load(open('out/results.json'))\nfor row in d.itertuples():\n n = np.array([int(x) for x in row.cluster_sizes.split('|')]); G, N = len(n), n.sum()\n C = np.zeros((G, N)); C[np.repeat(np.arange(G), n), np.arange(N)] = 1\n P = np.eye(N) - 1.0 / N\n Sig = row.icc * C.T @ C + (1 - row.icc) * np.eye(N)\n ev0 = np.trace(C @ P @ Sig @ P @ C.T) / N**2\n vx = (row.icc * np.sum(n**2) + (1 - row.icc) * N) / N**2\n k = f\"cr0_G{G}_icc{row.icc:.1f}\"\n mc, se = r['rel_bias_var'][k], r['mc_se_rel_bias_var'][k]\n print(k, f\"exact={ev0/vx:.4f} mc={mc:.4f} z={(mc-ev0/vx)/se:+.2f}\",\n \"cr1 ratio ok\" if abs(r['rel_bias_var'][k.replace('cr0','cr1')]/mc - G/(G-1)) < 1e-12 else \"CR1 MISMATCH\")\nEOF\n~/wp29/venv/bin/python out/state/verify_exact.py","description":"Compare MC relative bias with exact expectation"}}]}}60{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"54a801b9-6c1b-40f0-9b03-c18346ea63d9","timestamp":"2026-10-30T05:39:28.411Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"83335b53-75b2-4329-afb2-2949657c1e3b","keep":18,"tail":["fa8628fdcd6092f3947a059d8c5a8499b1e8e7e31df0aa3a24c2ace8f2de7a32","502fd9739fde157e75666a6500ac884f5946a5f7711d3bb5ee559a4a873ab0d8"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"bd6817b98b584dbfa6ea6dbad4ec87efebb473f731d110774cf43595205efc17"}61{"parentUuid":"965d106a-183e-4afa-a35d-b362026949f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtE8sHowkACekhZb7J9","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":1361,"cache_read_input_tokens":21445,"output_tokens":634,"output_tokens_details":{"thinking_tokens":81},"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":1361},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":504,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtE8YwToJtQHbrR2zq8","requestRef":"54a801b9-6c1b-40f0-9b03-c18346ea63d9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e0a5b790-d66e-4d3e-ad45-c40b8b9461dc","timestamp":"2026-10-30T05:39:30.040Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"e0a5b790-d66e-4d3e-ad45-c40b8b9461dc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtE8sHowkACekhZb7J9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TGXnRZiqFa6FokbtCCL43X","name":"Bash","input":{"command":"cat > out/state/verify_wcb.py <<'EOF'\n# Verification: vectorised WCB t* equals a brute-force loop building y* explicitly (one sample).\nimport numpy as np\nrng = np.random.default_rng(1); n = np.array([8,16,32,64,8]); G, N = 5, n.sum(); gid = np.repeat(np.arange(G), n)\ny = rng.normal(size=G)[gid]*np.sqrt(.2) + rng.normal(size=N)*np.sqrt(.8); yb = y.mean(); e = y - yb\nS = np.bincount(gid, weights=e); W = rng.integers(0,2,(50,G))*2-1\nd = (W*S).sum(1)/N; v = G/(G-1)*np.sum((W*S-np.outer(d,n))**2,1)/N**2; t_vec = d/np.sqrt(v)\nt_bf = []\nfor w in W:\n ys = yb + w[gid]*e; m = ys.mean(); r = ys - m\n vs = G/(G-1)*np.sum(np.bincount(gid, weights=r)**2)/N**2; t_bf.append((m-yb)/np.sqrt(vs))\nprint(\"max abs diff:\", np.max(np.abs(t_vec-np.array(t_bf))))\nEOF\n~/wp29/venv/bin/python out/state/verify_wcb.py","description":"Brute-force check of vectorised WCB"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1361,"cache_read_input_tokens":21445,"output_tokens":634,"output_tokens_details":{"thinking_tokens":81},"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":1361},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtE8YwToJtQHbrR2zq8","requestRef":"54a801b9-6c1b-40f0-9b03-c18346ea63d9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2d16e80c-faa4-427a-849b-2bcc6bfa3743","timestamp":"2026-10-30T05:39:34.043Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}63{"parentUuid":"2d16e80c-faa4-427a-849b-2bcc6bfa3743","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TGXnRZiqFa6FokbtCCL43X","type":"tool_result","content":"max abs diff: 7.105427357601002e-15","is_error":false}]},"uuid":"28946aa8-9345-4eee-9088-8f6f64cac850","timestamp":"2026-10-30T05:39:34.151Z","toolUseResult":{"stdout":"max abs diff: 7.105427357601002e-15","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2d16e80c-faa4-427a-849b-2bcc6bfa3743","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}64{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"a3fe9f3eb1775cbca904216127c8021b35691fd6fb2ff62dc43dbec69615ddc4","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01TGXnRZiqFa6FokbtCCL43X","name":"Bash","input":{"command":"cat > out/state/verify_wcb.py <<'EOF'\n# Verification: vectorised WCB t* equals a brute-force loop building y* explicitly (one sample).\nimport numpy as np\nrng = np.random.default_rng(1); n = np.array([8,16,32,64,8]); G, N = 5, n.sum(); gid = np.repeat(np.arange(G), n)\ny = rng.normal(size=G)[gid]*np.sqrt(.2) + rng.normal(size=N)*np.sqrt(.8); yb = y.mean(); e = y - yb\nS = np.bincount(gid, weights=e); W = rng.integers(0,2,(50,G))*2-1\nd = (W*S).sum(1)/N; v = G/(G-1)*np.sum((W*S-np.outer(d,n))**2,1)/N**2; t_vec = d/np.sqrt(v)\nt_bf = []\nfor w in W:\n ys = yb + w[gid]*e; m = ys.mean(); r = ys - m\n vs = G/(G-1)*np.sum(np.bincount(gid, weights=r)**2)/N**2; t_bf.append((m-yb)/np.sqrt(vs))\nprint(\"max abs diff:\", np.max(np.abs(t_vec-np.array(t_bf))))\nEOF\n~/wp29/venv/bin/python out/state/verify_wcb.py","description":"Brute-force check of vectorised WCB"}}]}}65{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"e5b9e28c-2e7d-42e7-bdd4-1321b79bcb93","timestamp":"2026-10-30T05:39:34.154Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"54a801b9-6c1b-40f0-9b03-c18346ea63d9","keep":20,"tail":["a3fe9f3eb1775cbca904216127c8021b35691fd6fb2ff62dc43dbec69615ddc4","ea7516b7ab6414249ba589798809a46450b0e3e3eaa992f343f0ef5abaf9f0e0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"57f17a61ef83b0836aa1bce25f5b3110b74fe7d111d5363523d857aa45d19d78"}66{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"28946aa8-9345-4eee-9088-8f6f64cac850","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}67{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}68{"parentUuid":"28946aa8-9345-4eee-9088-8f6f64cac850","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEZLBvwNUcuxMRMCai","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":656,"cache_read_input_tokens":22806,"output_tokens":628,"output_tokens_details":{"thinking_tokens":79},"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":656},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":500,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtEZ3asZ5srpQtRhP36","requestRef":"e5b9e28c-2e7d-42e7-bdd4-1321b79bcb93","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e82d4226-1814-4826-991e-8917c2477c85","timestamp":"2026-10-30T05:39:35.743Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}69{"parentUuid":"e82d4226-1814-4826-991e-8917c2477c85","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEZLBvwNUcuxMRMCai","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01L312BHWLJv4E5rCyx4wZer","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; cp out/table1.csv /tmp/t1.csv; rm out/results.json out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py > /dev/null; cmp out/results.json /tmp/r1.json && cmp out/table1.csv /tmp/t1.csv && echo IDENTICAL; ~/wp29/venv/bin/python -c \"\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json'));t=pd.read_csv('out/table1.csv')\nprint(len(t), t.rel_bias_var[t.estimator=='wcb'].isna().all(), len(r['coverage']),len(r['mc_se_coverage']),len(r['rel_bias_var']))\nprint(all(v>0 for v in r['mc_se_coverage'].values()), r['n_failure_cells']==len(r['failure_cells']), r['n_analysed']==r['n_cells']*r['R'])\nprint(all(0<=v<=1 for v in r['coverage'].values()), (t.mean_ci_halfwidth>0).all())\nprint(set(r['failure_cells'])=={k for k,v in r['coverage'].items() if v<0.9})\nprint(t.groupby('estimator').mean_ci_halfwidth.mean())\n\"; ls -la out/figure1.png","description":"Clean rerun 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":656,"cache_read_input_tokens":22806,"output_tokens":628,"output_tokens_details":{"thinking_tokens":79},"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":656},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtEZ3asZ5srpQtRhP36","requestRef":"e5b9e28c-2e7d-42e7-bdd4-1321b79bcb93","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5a5b2703-70f1-408e-868c-91df837fab64","timestamp":"2026-10-30T05:39:39.405Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}70{"parentUuid":"5a5b2703-70f1-408e-868c-91df837fab64","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01L312BHWLJv4E5rCyx4wZer","type":"tool_result","content":"IDENTICAL\n27 True 27 27 18\nTrue True True\nTrue True\nTrue\nestimator\ncr0 0.266660\ncr1 0.354370\nwcb 0.497167\nName: mean_ci_halfwidth, dtype: float64\n-rw-r--r-- 1 simon-pierreboucher staff 80516 oct. 30 01:39 out/figure1.png","is_error":false}]},"uuid":"d045b788-bf95-489f-80e4-c66294c48df8","timestamp":"2026-10-30T05:39:41.715Z","toolUseResult":{"stdout":"IDENTICAL\n27 True 27 27 18\nTrue True True\nTrue True\nTrue\nestimator\ncr0 0.266660\ncr1 0.354370\nwcb 0.497167\nName: mean_ci_halfwidth, dtype: float64\n-rw-r--r-- 1 simon-pierreboucher staff 80516 oct. 30 01:39 out/figure1.png","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5a5b2703-70f1-408e-868c-91df837fab64","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}71{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"4c0fa292db056100a376dbcb8ffa6b77e160e193340106c33f3a76178e139362","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01L312BHWLJv4E5rCyx4wZer","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; cp out/table1.csv /tmp/t1.csv; rm out/results.json out/table1.csv out/figure1.png; ~/wp29/venv/bin/python out/analysis.py > /dev/null; cmp out/results.json /tmp/r1.json && cmp out/table1.csv /tmp/t1.csv && echo IDENTICAL; ~/wp29/venv/bin/python -c \"\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json'));t=pd.read_csv('out/table1.csv')\nprint(len(t), t.rel_bias_var[t.estimator=='wcb'].isna().all(), len(r['coverage']),len(r['mc_se_coverage']),len(r['rel_bias_var']))\nprint(all(v>0 for v in r['mc_se_coverage'].values()), r['n_failure_cells']==len(r['failure_cells']), r['n_analysed']==r['n_cells']*r['R'])\nprint(all(0<=v<=1 for v in r['coverage'].values()), (t.mean_ci_halfwidth>0).all())\nprint(set(r['failure_cells'])=={k for k,v in r['coverage'].items() if v<0.9})\nprint(t.groupby('estimator').mean_ci_halfwidth.mean())\n\"; ls -la out/figure1.png","description":"Clean rerun and consistency checks"}}]}}72{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"6b14874b-87e2-4c1d-94b1-953b5631f2af","timestamp":"2026-10-30T05:39:41.718Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"e5b9e28c-2e7d-42e7-bdd4-1321b79bcb93","keep":22,"tail":["4c0fa292db056100a376dbcb8ffa6b77e160e193340106c33f3a76178e139362","1c1cbcf852dd0ace6d30b4428c853dc56515a5bee110dab25ec1bf6a907f1072"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1a88d92cf21cba65e475fa2a8d8e9ebc7f65040925365500b31e36dcbf3752b4"}73{"type":"tools-used","tools":["Bash","Read"],"sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}74{"parentUuid":"d045b788-bf95-489f-80e4-c66294c48df8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtF7gNNT7xFMhHr7z8S","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014csvcvbk7bVWpuVyMoSB9c","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0020/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":757,"cache_read_input_tokens":23462,"output_tokens":80,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":757},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtF7PWMUgyqRTw5d8cG","requestRef":"6b14874b-87e2-4c1d-94b1-953b5631f2af","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"788e3879-35f5-40c1-8d37-1db6a952c7ce","timestamp":"2026-10-30T05:39:42.805Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}75{"parentUuid":"788e3879-35f5-40c1-8d37-1db6a952c7ce","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014csvcvbk7bVWpuVyMoSB9c","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"9e7fdc6b-9033-46c8-8c08-3ad1b2d3e5ec","timestamp":"2026-10-30T05:39:42.826Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":80516,"dimensions":{"originalWidth":1690,"originalHeight":546,"displayWidth":1690,"displayHeight":546}}},"sourceToolAssistantUUID":"788e3879-35f5-40c1-8d37-1db6a952c7ce","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}76{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"476530454c06ef1b7dbd3ab59173c194276a25ff7e3741eb6944fa1dab701653","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_014csvcvbk7bVWpuVyMoSB9c","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/figure1.png"}}]}}77{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"5a556659-c708-44a7-b67b-bb6bd4d15355","timestamp":"2026-10-30T05:39:42.836Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"6b14874b-87e2-4c1d-94b1-953b5631f2af","keep":24,"tail":["476530454c06ef1b7dbd3ab59173c194276a25ff7e3741eb6944fa1dab701653","e7d0505f05292e0d7d00974ec78f7988ecabfda8673c6e745379718e6c181125"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"664e007caf281355e4fa02a8e7ef3afd7522eb3583038311a1f8a2b12e132b2e"}78{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"9e7fdc6b-9033-46c8-8c08-3ad1b2d3e5ec","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}79{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}80{"parentUuid":"9e7fdc6b-9033-46c8-8c08-3ad1b2d3e5ec","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFCSs3abNmQd1yqCKJ","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":1319,"cache_read_input_tokens":24219,"output_tokens":460,"output_tokens_details":{"thinking_tokens":191},"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":1319},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1609,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtFCBV1zGnWDdf3K44D","requestRef":"5a556659-c708-44a7-b67b-bb6bd4d15355","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"59112d0b-ea04-467f-8999-b5eee9b78d57","timestamp":"2026-10-30T05:39:45.674Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}81{"parentUuid":"59112d0b-ea04-467f-8999-b5eee9b78d57","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFCSs3abNmQd1yqCKJ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01E81UZgbe6KTY7KaHmKvbZH","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\ns=open('out/analysis.py').read()\ns=s.replace('ax.set_xscale(\"log\"); ax.set_xticks(Gs)','ax.set_xscale(\"log\"); ax.minorticks_off(); ax.set_xticks(Gs)')\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r1.json && echo same; cat out/table1.csv","description":"Fix minor ticks, rerun, show table"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1319,"cache_read_input_tokens":24219,"output_tokens":460,"output_tokens_details":{"thinking_tokens":191},"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":1319},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtFCBV1zGnWDdf3K44D","requestRef":"5a556659-c708-44a7-b67b-bb6bd4d15355","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"afc20764-68c0-48bd-a1f4-aea69ae358e2","timestamp":"2026-10-30T05:39:47.270Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}82{"parentUuid":"afc20764-68c0-48bd-a1f4-aea69ae358e2","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01E81UZgbe6KTY7KaHmKvbZH","type":"tool_result","content":"same\nestimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.0,0.7805,0.009255262016820486,0.6616434596045324,0.12968375504872767,2000\ncr1,C1,5,0.0,0.9115,0.006350895606133045,0.8270543245056654,0.2053873084131136,2000\nwcb,C1,5,0.0,0.855,0.007873214083206426,,0.24887049821365717,2000\ncr0,C2,5,0.2,0.721,0.010028933143659899,0.5313958571125164,0.34226817384823977,2000\ncr1,C2,5,0.2,0.8845,0.007147018609182434,0.6642448213906453,0.5420689658141673,2000\nwcb,C2,5,0.2,0.854,0.007895695029571494,,0.9061312200606192,2000\ncr0,C3,5,0.5,0.717,0.010072512099769353,0.48335023384407516,0.4988937266037328,2000\ncr1,C3,5,0.5,0.8755,0.007382403064043579,0.6041877923050938,0.7901254837417955,2000\nwcb,C3,5,0.5,0.849,0.008006216334823835,,1.3624621157327816,2000\ncr0,C4,10,0.0,0.8965,0.006811304941052046,0.8558047169939658,0.10685157692463605,2000\ncr1,C4,10,0.0,0.9435,0.005162739098579358,0.9508941299932954,0.12999492086527678,2000\nwcb,C4,10,0.0,0.936,0.00547284204047586,,0.14486128327147552,2000\ncr0,C5,10,0.2,0.857,0.007827866886962246,0.7624366224508259,0.3013090672758269,2000\ncr1,C5,10,0.2,0.9155,0.006219314672855845,0.8471518027231398,0.36657061583787093,2000\nwcb,C5,10,0.2,0.9295,0.005724061058374553,,0.46023383942186563,2000\ncr0,C6,10,0.5,0.853,0.007918049002121673,0.7737432482368367,0.46142207182836037,2000\ncr1,C6,10,0.5,0.9065,0.006509905913298595,0.859714720263152,0.5613630368331044,2000\nwcb,C6,10,0.5,0.9325,0.005609979946488223,,0.7220840148315424,2000\ncr0,C7,30,0.0,0.9275,0.005798437289477226,0.943796503270819,0.06396913625447695,2000\ncr1,C7,30,0.0,0.94,0.005310367218940704,0.9763412102801576,0.06789192490779818,2000\nwcb,C7,30,0.0,0.943,0.005184158562389852,,0.06964679151269985,2000\ncr0,C8,30,0.2,0.921,0.006031542091372652,0.9313668684580917,0.19630299136684284,2000\ncr1,C8,30,0.2,0.935,0.005512485827646179,0.9634829673704397,0.20834090827857807,2000\nwcb,C8,30,0.2,0.946,0.005053909377897473,,0.2220803814359477,2000\ncr0,C9,30,0.5,0.9165,0.006185780063985464,0.9252598675851053,0.29923728217350937,2000\ncr1,C9,30,0.5,0.93,0.005705260730238364,0.9571653802604538,0.3175874535825968,2000\nwcb,C9,30,0.5,0.9425,0.005205465877325487,,0.3381330862468605,2000","is_error":false}]},"uuid":"41642d1f-1aa4-4124-adc8-3b7178f3892f","timestamp":"2026-10-30T05:39:49.351Z","toolUseResult":{"stdout":"same\nestimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.0,0.7805,0.009255262016820486,0.6616434596045324,0.12968375504872767,2000\ncr1,C1,5,0.0,0.9115,0.006350895606133045,0.8270543245056654,0.2053873084131136,2000\nwcb,C1,5,0.0,0.855,0.007873214083206426,,0.24887049821365717,2000\ncr0,C2,5,0.2,0.721,0.010028933143659899,0.5313958571125164,0.34226817384823977,2000\ncr1,C2,5,0.2,0.8845,0.007147018609182434,0.6642448213906453,0.5420689658141673,2000\nwcb,C2,5,0.2,0.854,0.007895695029571494,,0.9061312200606192,2000\ncr0,C3,5,0.5,0.717,0.010072512099769353,0.48335023384407516,0.4988937266037328,2000\ncr1,C3,5,0.5,0.8755,0.007382403064043579,0.6041877923050938,0.7901254837417955,2000\nwcb,C3,5,0.5,0.849,0.008006216334823835,,1.3624621157327816,2000\ncr0,C4,10,0.0,0.8965,0.006811304941052046,0.8558047169939658,0.10685157692463605,2000\ncr1,C4,10,0.0,0.9435,0.005162739098579358,0.9508941299932954,0.12999492086527678,2000\nwcb,C4,10,0.0,0.936,0.00547284204047586,,0.14486128327147552,2000\ncr0,C5,10,0.2,0.857,0.007827866886962246,0.7624366224508259,0.3013090672758269,2000\ncr1,C5,10,0.2,0.9155,0.006219314672855845,0.8471518027231398,0.36657061583787093,2000\nwcb,C5,10,0.2,0.9295,0.005724061058374553,,0.46023383942186563,2000\ncr0,C6,10,0.5,0.853,0.007918049002121673,0.7737432482368367,0.46142207182836037,2000\ncr1,C6,10,0.5,0.9065,0.006509905913298595,0.859714720263152,0.5613630368331044,2000\nwcb,C6,10,0.5,0.9325,0.005609979946488223,,0.7220840148315424,2000\ncr0,C7,30,0.0,0.9275,0.005798437289477226,0.943796503270819,0.06396913625447695,2000\ncr1,C7,30,0.0,0.94,0.005310367218940704,0.9763412102801576,0.06789192490779818,2000\nwcb,C7,30,0.0,0.943,0.005184158562389852,,0.06964679151269985,2000\ncr0,C8,30,0.2,0.921,0.006031542091372652,0.9313668684580917,0.19630299136684284,2000\ncr1,C8,30,0.2,0.935,0.005512485827646179,0.9634829673704397,0.20834090827857807,2000\nwcb,C8,30,0.2,0.946,0.005053909377897473,,0.2220803814359477,2000\ncr0,C9,30,0.5,0.9165,0.006185780063985464,0.9252598675851053,0.29923728217350937,2000\ncr1,C9,30,0.5,0.93,0.005705260730238364,0.9571653802604538,0.3175874535825968,2000\nwcb,C9,30,0.5,0.9425,0.005205465877325487,,0.3381330862468605,2000","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"afc20764-68c0-48bd-a1f4-aea69ae358e2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}83{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"b7b84f89d12c75da4ca71f6f91c528e2cfc1fe0b91b6009e6ac598d9ee82cb88","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS4AkKEAgTGAI4AUIIdGhpbmtpbmcSDNvydeZYAfQ9Bf0MYhoMfCCXUCxi3xrdWm3GIjCvX8U+9mALt3oq8QOXfD1B87g6uJ2M1VW8NUl6zEnT91h3KGkoe21AH1VyVXarj54q/QhV/PAwh1Xl9fBzuuI6GgFerLkjO+8rV2yficRLVtx4nxi8ijdK9/WyJAeXpPocD2oMB4rRAkI5I6T9ZFugWNBa0V74ZGuwNATa/uBpz3zuFpLCEK3xL10gtOCzSPMOYNns1+2qyj08/kPxNaXWH1nzFMvfOw9M8Qi7Xq4xN/C2z1vrbNcZaFb7tKcqr4xCyPpwKBgsicxUuBvJJKPxEt47CKr7JUtqn4k+42oDekfuL9rIGeCb/V+soU3Jr26pgiWndxMQcUhMGfP7g9Rdwl+o/9VNEl3LI7dxxTAD0geP2ztyr7H9eAAykp6S4nZq9CjuviCpypzLmf7bOWNs0KW1iGoRH1IyKQR2WmKgEFFidpOzxlFQo67XuVjEdVJ9rkWwlgRBqJH5l7zzazzIpJSoBWK76RCN1FovWTu23F/XEj3pXJMmdyUUUlpXHYVnsFXJznxSiO0/CjjTW8bZnoyW0/HjbjOXivCWT435bAErSvw/YC62p/6C8W+6MIlox7uvcQDNq5NZlEHhoz/8CqoTHKdfKpiwgVMuSkAOThXdgN3aJTPVmFmiugwUGB9vNpN3Q7JmRydTCLVAdnkZn6vvUnM5qmBKObhijI9z6dmuwYA+1saKkD+IV5fsn0o8gHjAtiB+RqaNaoj7PfVNJm7Zj+gPQwe7EW2IzU2rCgQfD1jhTEz5L4FzSqzom9SYDHoHdqlEeeHSGt2yPsIcaOqivYuEgTMxCRnpvkIQ49P2qcDcolm8GwUgUnAWI2qhiL5gvw/sQJ6vxBd/qhmLuGjeVorSXi7LsOm8MctlczGOt6xR3ZoIjmTIu5pE9Jgj7gtJkeDLPMlf/+o+eKE7HJE/7P2IzzYaLs7dtXl+5G0O94QUAH1w0fDkPgTodmxTJWETXdm5s1Qa7N69rkJAg/Jjo4E/UmCc2QvRbHKzQiqh+gItR2Ol/xttim/XuR4YFkI39hdRByKqqJ4CeXtDul4ZwdJf3mi66B0Pgg7GEDU2dGEYJQJZ1WXXYfSyM2fRq0fen53Jg+OsF5zH4u4g7uwJdFwlxAo6NJJMeGPhAh5CxHKU5D39tf9EUGsSB96qShifzKdJkMZVZ25qK+W2u0kxmOL+oB8MJY/+kRJYn817QVITArDKnJaOChWUTgP4i65QS21W6MFnQryFJ0b8z/J7nU0F67XbbIyS9VcxzSYrD8t7BYkWxP76qzp0BNsFFKVwsn8ceIJGH35T4dMcz1jaP2NFi37WQCy4VVs7HazLEpzZctMZxbiULem/7CzAEuFnBvW17L3jWkaeTTQS0Qu9vkZK5uahLbyvkE+bZpR85Hhueo8WbhcReVaFH6DoRpaIvnc6gMreH80k+Jo2IN1JpujPYp0LgLzzv6EKm9+xpb2kYjGR/IAQzPZhFyLGXfOJwsYWqFrRRkbXi6xmrYV4e2nKxTYB9sgOsOTGGf0DMMtQcRk6dLsAxmHd+xrxdCW+J0iRj6znr6gm+XSO1dgRnM/UUFCl1PzcNh34280SF3DSPOWbPau6dBV0Zh0YAQ=="},{"type":"tool_use","id":"toolu_01E81UZgbe6KTY7KaHmKvbZH","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\ns=open('out/analysis.py').read()\ns=s.replace('ax.set_xscale(\"log\"); ax.set_xticks(Gs)','ax.set_xscale(\"log\"); ax.minorticks_off(); ax.set_xticks(Gs)')\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp out/results.json /tmp/r1.json && echo same; cat out/table1.csv","description":"Fix minor ticks, rerun, show table"}}]}}84{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"6a14a618-1cfa-4e3e-a770-ce961f06e700","timestamp":"2026-10-30T05:39:49.353Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"5a556659-c708-44a7-b67b-bb6bd4d15355","keep":26,"tail":["b7b84f89d12c75da4ca71f6f91c528e2cfc1fe0b91b6009e6ac598d9ee82cb88","7afb9cf34d8598141cd93bca94f870cc88ad5e1bf9dec444310595e09608696d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d9cee0488f19ca2619a4e7d732a2cf362a55cd16752398b9b6d93aef53007689"}85{"parentUuid":"41642d1f-1aa4-4124-adc8-3b7178f3892f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFgKuQUhh8LnpkpygA","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":1723,"cache_read_input_tokens":25538,"output_tokens":1388,"output_tokens_details":{"thinking_tokens":92},"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":1723},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":635,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtFg3YWGbpvjmqCxqqr","requestRef":"6a14a618-1cfa-4e3e-a770-ce961f06e700","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9a4bb4f5-c40a-408c-a877-d77bf760cef0","timestamp":"2026-10-30T05:39:50.955Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"9a4bb4f5-c40a-408c-a877-d77bf760cef0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFgKuQUhh8LnpkpygA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ESWVf43f3uSc2e5K13ZxM3","name":"Bash","input":{"command":"cd out/state && cat > checks.md <<'EOF'\n# Verification checks (P4)\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run (deleted results.json, table1.csv, figure1.png; re-ran analysis.py) reproduces byte-identical results.json and table1.csv | PASS |\n| 2 | Figure-only edit (minor ticks) re-run: results.json byte-identical | PASS |\n| 3 | table1.csv has 27 rows; rel_bias_var empty for all wcb rows | PASS |\n| 4 | coverage & mc_se_coverage have 27 keys; rel_bias_var 18 keys | PASS |\n| 5 | all MC SE > 0; all coverages in [0,1]; all mean half-widths > 0 | PASS |\n| 6 | n_failure_cells == len(failure_cells); failure_cells == {coverage<0.90} recomputed | PASS |\n| 7 | n_analysed == n_cells × R = 18000; exclusions ledger 18000 − 0 = 18000 | PASS |\n| 8 | Exact E[V̂_CR0]/Var(ȳ) (closed-form trace computation, state/verify_exact.py) vs MC estimate: z-scores −0.70…+1.40 in 8 cells, +2.46 in G5_icc0.2 (one of 9 beyond 2 MC SE; V̂ is right-skewed at G=5 so the normal MC approximation is rough; no implementation error indicated since the other 8 agree and CR1/CR0 ratio = G/(G−1) exactly) | PASS (with note) |\n| 9 | MC Var(ȳ)/exact Var(ȳ) in [0.93, 1.06] in all cells (check_mc_var_ybar_over_exact), consistent with sampling error of a variance from R=2000 (SE≈0.032); mean ȳ ≈ 0 | PASS |\n| 10 | Vectorised WCB t* equals brute-force explicit y* construction (state/verify_wcb.py): max abs diff 7e-15 | PASS |\n| 11 | Baseline (naive i.i.d. z-interval) behaves as expected: ≈0.95 at ICC=0, 0.29–0.49 with ICC>0 — magnitudes coherent with cluster methods improving on baseline when ICC>0 | PASS |\n| 12 | No degenerate bootstrap draws (n_degenerate_bootstrap_draws = 0) | PASS |\n| 13 | Runtime ≈ 2 s (< 600 s limit) | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"naive iid z-interval coverage computed on same draws, stored as baseline_iid_coverage\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py implemented, seeds per cell from design.csv\",\"runs in ~2s\",\"outputs results.json, table1.csv, figure1.png\"],\"notes\":\"\"}\np['P4']={\"status\":\"running\",\"checks\":[\"see checks.md items 1-13: all PASS\"],\"notes\":\"\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2,P3 passed (baseline iid; analysis.py). P4 checks done, running gate.\" >> log.md\ncd ../.. && ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Write checks, update ledger, run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1723,"cache_read_input_tokens":25538,"output_tokens":1388,"output_tokens_details":{"thinking_tokens":92},"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":1723},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtFg3YWGbpvjmqCxqqr","requestRef":"6a14a618-1cfa-4e3e-a770-ce961f06e700","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dad69784-1a89-48a8-aed4-27287c9ff935","timestamp":"2026-10-30T05:40:01.203Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}87{"parentUuid":"dad69784-1a89-48a8-aed4-27287c9ff935","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 34 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/table1.csv: present\n [ok] file:out/figure1.png: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:R: ok\n [ok] key:B: ok\n [ok] key:n_cells: ok\n [ok] key:coverage: ok\n [ok] key:mc_se_coverage: ok\n [ok] key:rel_bias_var: ok\n [ok] key:failure_cells: ok\n [ok] key:n_failure_cells: ok\n [ok] key:nominal_cells: ok\n [ok] key:best_procedure_small_G: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 1 steps consistent\n [ok] reproducibility: regenerated in 2.0s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0020/out/state/gate_receipts/20261030T054003.316148Z.json","is_error":true,"tool_use_id":"toolu_01ESWVf43f3uSc2e5K13ZxM3"}]},"uuid":"ee561663-e1e2-4321-a4fd-c7d7c3ccb994","timestamp":"2026-10-30T05:40:03.321Z","toolUseResult":"Error: Exit code 1\nPGAR GATE pgar_gate/1.0 — FAILED (10 of 34 checks failed)\n [ok] file:out/results.json: present\n [FAIL] file:out/report.md: missing or empty\n [ok] file:out/analysis.py: present\n [FAIL] file:out/claims.json: missing or empty\n [ok] file:out/table1.csv: present\n [ok] file:out/figure1.png: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:R: ok\n [ok] key:B: ok\n [ok] key:n_cells: ok\n [ok] key:coverage: ok\n [ok] key:mc_se_coverage: ok\n [ok] key:rel_bias_var: ok\n [ok] key:failure_cells: ok\n [ok] key:n_failure_cells: ok\n [ok] key:nominal_cells: ok\n [ok] key:best_procedure_small_G: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [FAIL] section:Question: heading not found\n [FAIL] section:Data and exclusions: heading not found\n [FAIL] section:Method: heading not found\n [FAIL] section:Results: heading not found\n [FAIL] section:Uncertainty: heading not found\n [FAIL] section:Limitations and open issues: heading not found\n [FAIL] claims_json: out/claims.json missing\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 1 steps consistent\n [ok] reproducibility: regenerated in 2.0s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0020/out/state/gate_receipts/20261030T054003.316148Z.json","sandboxed":false,"sourceToolAssistantUUID":"dad69784-1a89-48a8-aed4-27287c9ff935","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}88{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"ccda9de2999c4b0f15a40a0f10cfea0f79dc4b5a435d72989aebb2e975fe542b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01ESWVf43f3uSc2e5K13ZxM3","name":"Bash","input":{"command":"cd out/state && cat > checks.md <<'EOF'\n# Verification checks (P4)\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run (deleted results.json, table1.csv, figure1.png; re-ran analysis.py) reproduces byte-identical results.json and table1.csv | PASS |\n| 2 | Figure-only edit (minor ticks) re-run: results.json byte-identical | PASS |\n| 3 | table1.csv has 27 rows; rel_bias_var empty for all wcb rows | PASS |\n| 4 | coverage & mc_se_coverage have 27 keys; rel_bias_var 18 keys | PASS |\n| 5 | all MC SE > 0; all coverages in [0,1]; all mean half-widths > 0 | PASS |\n| 6 | n_failure_cells == len(failure_cells); failure_cells == {coverage<0.90} recomputed | PASS |\n| 7 | n_analysed == n_cells × R = 18000; exclusions ledger 18000 − 0 = 18000 | PASS |\n| 8 | Exact E[V̂_CR0]/Var(ȳ) (closed-form trace computation, state/verify_exact.py) vs MC estimate: z-scores −0.70…+1.40 in 8 cells, +2.46 in G5_icc0.2 (one of 9 beyond 2 MC SE; V̂ is right-skewed at G=5 so the normal MC approximation is rough; no implementation error indicated since the other 8 agree and CR1/CR0 ratio = G/(G−1) exactly) | PASS (with note) |\n| 9 | MC Var(ȳ)/exact Var(ȳ) in [0.93, 1.06] in all cells (check_mc_var_ybar_over_exact), consistent with sampling error of a variance from R=2000 (SE≈0.032); mean ȳ ≈ 0 | PASS |\n| 10 | Vectorised WCB t* equals brute-force explicit y* construction (state/verify_wcb.py): max abs diff 7e-15 | PASS |\n| 11 | Baseline (naive i.i.d. z-interval) behaves as expected: ≈0.95 at ICC=0, 0.29–0.49 with ICC>0 — magnitudes coherent with cluster methods improving on baseline when ICC>0 | PASS |\n| 12 | No degenerate bootstrap draws (n_degenerate_bootstrap_draws = 0) | PASS |\n| 13 | Runtime ≈ 2 s (< 600 s limit) | PASS |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P2']={\"status\":\"passed\",\"checks\":[\"naive iid z-interval coverage computed on same draws, stored as baseline_iid_coverage\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py implemented, seeds per cell from design.csv\",\"runs in ~2s\",\"outputs results.json, table1.csv, figure1.png\"],\"notes\":\"\"}\np['P4']={\"status\":\"running\",\"checks\":[\"see checks.md items 1-13: all PASS\"],\"notes\":\"\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P2,P3 passed (baseline iid; analysis.py). P4 checks done, running gate.\" >> log.md\ncd ../.. && ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Write checks, update ledger, run gate"}}]}}89{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"9828a539-b33b-43c6-a9bf-53cc2e45d56c","timestamp":"2026-10-30T05:40:03.324Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"6a14a618-1cfa-4e3e-a770-ce961f06e700","keep":28,"tail":["ccda9de2999c4b0f15a40a0f10cfea0f79dc4b5a435d72989aebb2e975fe542b","b35ec3c0ffaecf6088e7ba91e4aa978dbfa6a340d6f545718a72e80e9cb3fa09"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"6a52b73e14d45b7558c2711215af36f41569095daf555560bf4a1a08b2700ab3"}90{"parentUuid":"ee561663-e1e2-4321-a4fd-c7d7c3ccb994","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtGi3dCJ7fZbdg2ubij","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":2112,"cache_read_input_tokens":27261,"output_tokens":1646,"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":2112},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6530,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtGhmW8KBqZQ4epTU6r","requestRef":"9828a539-b33b-43c6-a9bf-53cc2e45d56c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"30d9489b-77dc-475f-b7b3-ab0db74d9736","timestamp":"2026-10-30T05:40:10.924Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}91{"parentUuid":"30d9489b-77dc-475f-b7b3-ab0db74d9736","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtGi3dCJ7fZbdg2ubij","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01YbawfZh9BpMP6refim4hXM","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\ns=open('out/analysis.py').read()\ns=s.replace(\"\"\" out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean())}\"\"\",\"\"\" out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean()), \"ind\": cov.astype(float)}\"\"\")\ns=s.replace(\"\"\" n_deg = 0\n\"\"\",\"\"\" n_deg = 0\n ind_g5 = {k: [] for k in EST}\n\"\"\")\ns=s.replace(\"\"\" base[f\"iid_{tag}\"]\"\"\",\"\"\" if int(row.G) == 5:\n for k in EST:\n ind_g5[k].append(o[k][\"ind\"])\n base[f\"iid_{tag}\"]\"\"\")\ns=s.replace(\"\"\" best = max(g5, key=g5.get)\n\"\"\",\"\"\" best = max(g5, key=g5.get)\n # paired MC SE of the difference in average G=5 coverage between best and each other procedure\n # (same replications -> paired; cells independent -> variance of mean over 3 cells = sum/9)\n g5_diff = {}\n for k in EST:\n if k == best:\n continue\n cell_vars = [np.var(a - b, ddof=1) / len(a) for a, b in zip(ind_g5[best], ind_g5[k])]\n g5_diff[f\"{best}_minus_{k}\"] = {\"diff\": float(g5[best] - g5[k]), \"mc_se\": float(np.sqrt(sum(cell_vars)) / len(cell_vars))}\n near = [k for k, p in cov.items() if abs(p - 0.90) <= 2 * se[k]]\n\"\"\")\ns=s.replace(\"\"\" \"mc_se_rel_bias_var\": rb_se,\"\"\",\"\"\" \"mc_se_rel_bias_var\": rb_se,\n \"avg_coverage_G5_paired_diff\": g5_diff,\n \"cells_within_2se_of_failure_line\": near,\"\"\")\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));print(r['avg_coverage_G5_paired_diff'],r['cells_within_2se_of_failure_line'],r['coverage']==json.load(open('/tmp/r1.json'))['coverage'])\"","description":"Add paired diff SE and near-threshold keys"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2112,"cache_read_input_tokens":27261,"output_tokens":1646,"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":2112},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtGhmW8KBqZQ4epTU6r","requestRef":"9828a539-b33b-43c6-a9bf-53cc2e45d56c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"55cf55ff-d61a-4e66-a4e4-f69303ac2845","timestamp":"2026-10-30T05:40:17.513Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}92{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"55cf55ff-d61a-4e66-a4e4-f69303ac2845","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}93{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}94{"parentUuid":"55cf55ff-d61a-4e66-a4e4-f69303ac2845","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01YbawfZh9BpMP6refim4hXM","type":"tool_result","content":"{'cr1_minus_cr0': {'diff': 0.1509999999999999, 'mc_se': 0.004619864044982199}, 'cr1_minus_wcb': {'diff': 0.037833333333333385, 'mc_se': 0.0034783787896010433}} ['cr1_G5_icc0.0', 'cr0_G10_icc0.0', 'cr1_G10_icc0.5'] True","is_error":false}]},"uuid":"dd2d9e58-f38d-43d7-bb8e-90ee4f4e4a27","timestamp":"2026-10-30T05:40:19.590Z","toolUseResult":{"stdout":"{'cr1_minus_cr0': {'diff': 0.1509999999999999, 'mc_se': 0.004619864044982199}, 'cr1_minus_wcb': {'diff': 0.037833333333333385, 'mc_se': 0.0034783787896010433}} ['cr1_G5_icc0.0', 'cr0_G10_icc0.0', 'cr1_G10_icc0.5'] True","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"55cf55ff-d61a-4e66-a4e4-f69303ac2845","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}95{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"62e004370415c7cab252679b92c4acaf38f1a4b9f1dca924ecade6e19bf89505","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01YbawfZh9BpMP6refim4hXM","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\ns=open('out/analysis.py').read()\ns=s.replace(\"\"\" out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean())}\"\"\",\"\"\" out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean()), \"ind\": cov.astype(float)}\"\"\")\ns=s.replace(\"\"\" n_deg = 0\n\"\"\",\"\"\" n_deg = 0\n ind_g5 = {k: [] for k in EST}\n\"\"\")\ns=s.replace(\"\"\" base[f\"iid_{tag}\"]\"\"\",\"\"\" if int(row.G) == 5:\n for k in EST:\n ind_g5[k].append(o[k][\"ind\"])\n base[f\"iid_{tag}\"]\"\"\")\ns=s.replace(\"\"\" best = max(g5, key=g5.get)\n\"\"\",\"\"\" best = max(g5, key=g5.get)\n # paired MC SE of the difference in average G=5 coverage between best and each other procedure\n # (same replications -> paired; cells independent -> variance of mean over 3 cells = sum/9)\n g5_diff = {}\n for k in EST:\n if k == best:\n continue\n cell_vars = [np.var(a - b, ddof=1) / len(a) for a, b in zip(ind_g5[best], ind_g5[k])]\n g5_diff[f\"{best}_minus_{k}\"] = {\"diff\": float(g5[best] - g5[k]), \"mc_se\": float(np.sqrt(sum(cell_vars)) / len(cell_vars))}\n near = [k for k, p in cov.items() if abs(p - 0.90) <= 2 * se[k]]\n\"\"\")\ns=s.replace(\"\"\" \"mc_se_rel_bias_var\": rb_se,\"\"\",\"\"\" \"mc_se_rel_bias_var\": rb_se,\n \"avg_coverage_G5_paired_diff\": g5_diff,\n \"cells_within_2se_of_failure_line\": near,\"\"\")\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));print(r['avg_coverage_G5_paired_diff'],r['cells_within_2se_of_failure_line'],r['coverage']==json.load(open('/tmp/r1.json'))['coverage'])\"","description":"Add paired diff SE and near-threshold keys"}}]}}96{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"9bd1a4bf-6605-4828-83cb-3752a160a496","timestamp":"2026-10-30T05:40:19.593Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"9828a539-b33b-43c6-a9bf-53cc2e45d56c","keep":30,"tail":["62e004370415c7cab252679b92c4acaf38f1a4b9f1dca924ecade6e19bf89505","47ea5f9bc073b1701e1b4c2b406eb5ea7b05392b696338321ffda8eddcb40d6e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"45aefd3fdb315dcace0a0a8843b5e264a184eb9282e2dda7c61771b3b80f7c85"}97{"parentUuid":"dd2d9e58-f38d-43d7-bb8e-90ee4f4e4a27","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHubSA8APvYa87pSGL","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":1791,"cache_read_input_tokens":29373,"output_tokens":5305,"output_tokens_details":{"thinking_tokens":139},"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":1791},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1030,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtHuLK1HzdSLUqNiqqd","requestRef":"9bd1a4bf-6605-4828-83cb-3752a160a496","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bedbbba5-5f6e-47d8-bdc0-fffa8a889faa","timestamp":"2026-10-30T05:40:23.419Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}98{"parentUuid":"bedbbba5-5f6e-47d8-bdc0-fffa8a889faa","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHubSA8APvYa87pSGL","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JjjjYxXoHrcW96grBUPUga","name":"Bash","input":{"command":"cd out && cat > report.md <<'EOF'\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t intervals for a mean with few clusters\n\nAll numbers below are produced by `out/analysis.py` (run: `~/wp29/venv/bin/python out/analysis.py`, ≈2 s) and are cited by their key in `out/results.json`. Full per-cell values are in `out/table1.csv`; the figure is `out/figure1.png`.\n\n## Question\nWhen N observations are grouped in few (G = 5, 10, 30) unbalanced clusters with intra-cluster correlation ICC ∈ {0, 0.2, 0.5}, what is the actual coverage of three nominal-95% cluster-robust intervals for the mean μ (CR0 with z critical value; CR1 with t_{G−1}; unrestricted Rademacher wild cluster bootstrap-t, WCB), how biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ), and in which (procedure, cell) pairs does coverage fall below 0.90?\n\n## Data and exclusions\nNo observed data. The only input is `data/design.csv` (`n_input_rows`: 9 rows; SHA-256 recorded in `out/state/data_audit.md`): 9 cells, cluster sizes 8,16,32,64 repeated (N = 128, 264, 864), R = 2000 (`R`), B = 399 (`B`), one seed per cell (C1 seed = `random_seed`; all seeds in `seeds_by_cell`). The audit found no missing values, duplicates or inconsistencies (sizes count = G, sum = N). No exclusions: all `n_cells` = 9 cells × 2000 replications = `n_analysed` = 18000 replications were simulated and analysed (`out/exclusions.csv`, one no-op step). `feasibility` = \"complete\". One design feature is recorded in `data_issues`: at G = 5 Rademacher weights take only 32 distinct values (16 distinct |t*|), so the bootstrap critical value is coarse; kept as specified. No bootstrap draw had a non-positive variance (`n_degenerate_bootstrap_draws` = 0).\n\n## Method\nPer replication (numpy `default_rng(cell seed)`, draws in fixed order u, e, W): y_ig = μ + u_g + e_ig, u_g ~ N(0, ICC), e_ig ~ N(0, 1−ICC), μ = 0. With ê = y − ȳ and S_g = Σ_i ê_ig: V̂_CR0 = Σ S_g²/N², CI ȳ ± 1.96√V̂_CR0; V̂_CR1 = G/(G−1)·V̂_CR0, CI ȳ ± t_{0.975,G−1}√V̂_CR1; WCB: B×G Rademacher matrix W, ȳ*−ȳ = Σ_g w_g S_g/N, bootstrap cluster residual sums w_g S_g − n_g(ȳ*−ȳ), V̂*_CR1 from these, t*_b = (ȳ*−ȳ)/√V̂*_CR1, q = 0.95 quantile of |t*| (numpy linear interpolation, `wcb_quantile_method`), CI ȳ ± q√V̂_CR1. Coverage = share of R intervals containing μ; MC SE = √(p̂(1−p̂)/R); relative bias = mean(V̂)/Var(ȳ) with Var(ȳ) = [ICC Σn_g² + (1−ICC)N]/N². Failure regime: coverage < 0.90; nominal-consistent: |p̂ − 0.95| ≤ 2 MC SE. Baseline (P2): the naive i.i.d. interval ȳ ± 1.96·s/√N on the same draws (`baseline_iid_coverage`).\n\nVerification (`out/state/checks.md`): byte-identical re-run; vectorised WCB matches a brute-force construction of y* (diff 7e-15); MC relative bias of CR0 matches the closed-form E[V̂_CR0]/Var(ȳ) within 2 MC SE in 8/9 cells (z = +2.46 in G5_icc0.2); MC Var(ȳ)/exact in [0.93, 1.06] (`check_mc_var_ybar_over_exact`).\n\n## Results\nCoverage (`coverage`, MC SE in `mc_se_coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive i.i.d. baseline |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.781 | 0.912 | 0.855 | 0.941 |\n| 5 | 0.2 | 0.721 | 0.885 | 0.854 | 0.460 |\n| 5 | 0.5 | 0.717 | 0.876 | 0.849 | 0.287 |\n| 10 | 0.0 | 0.897 | 0.944 | 0.936 | 0.957 |\n| 10 | 0.2 | 0.857 | 0.916 | 0.930 | 0.488 |\n| 10 | 0.5 | 0.853 | 0.907 | 0.933 | 0.313 |\n| 30 | 0.0 | 0.928 | 0.940 | 0.943 | 0.952 |\n| 30 | 0.2 | 0.921 | 0.935 | 0.946 | 0.485 |\n| 30 | 0.5 | 0.917 | 0.930 | 0.943 | 0.299 |\n\n- **Failure regimes** (`failure_cells`, `n_failure_cells` = 11): CR0 at every G = 5 and G = 10 cell (6 pairs); WCB at all three G = 5 cells; CR1 at G = 5 with ICC = 0.2 and 0.5. No procedure fails at G = 30.\n- **Nominal-consistent pairs** (`nominal_cells`, 5 pairs): cr1_G10_icc0.0, cr1_G30_icc0.0, wcb_G30_icc0.0, wcb_G30_icc0.2, wcb_G30_icc0.5. CR0 is never consistent with 0.95, even at G = 30 (0.917–0.928).\n- **Best at G = 5** (`best_procedure_small_G` = \"cr1\"): average G = 5 coverage 0.891 for CR1, 0.853 for WCB, 0.740 for CR0 (`avg_coverage_G5`). The CR1 − WCB difference is 0.038 with paired MC SE 0.0035 (`avg_coverage_G5_paired_diff`), so the ranking is not a Monte Carlo artefact. At G = 10 with ICC > 0, WCB covers better than CR1 (0.930/0.933 vs 0.916/0.907).\n- **Variance bias** (`rel_bias_var`): both sandwich estimators are biased downward, most at small G and high ICC. CR0: 0.66, 0.53, 0.48 at G = 5 (ICC 0, 0.2, 0.5); 0.86, 0.76, 0.77 at G = 10; 0.94, 0.93, 0.93 at G = 30. CR1: 0.83, 0.66, 0.60 at G = 5; 0.95, 0.85, 0.86 at G = 10; 0.98, 0.96, 0.96 at G = 30. The unbalanced sizes (one 64-observation cluster dominates) make the bias much worse than the balanced-cluster factor (G−1)/G.\n- **Baseline**: the naive i.i.d. interval is fine at ICC = 0 but covers only 0.29–0.49 when ICC > 0 (`baseline_iid_coverage`), whatever G is. All three cluster-robust procedures improve on it there.\n- Mean CI half-widths are in `table1.csv` (`mean_ci_halfwidth`). At G = 5 the WCB interval is on average *wider* than CR1 but still covers less. One plausible explanation (not tested here) is that q varies a lot across replications, because the bootstrap distribution has only 16 distinct |t*| values.\n\n## Uncertainty\nEach coverage is a binomial proportion over R = 2000 independent replications. Its MC SE (`mc_se_coverage`) is 0.005–0.010, so a 95% MC interval is about ±0.010–0.020. The figure shows ±1.96 MC SE bars. Classifications near the 0.90 threshold are therefore fragile. cr1_G5_icc0.0 (0.912), cr0_G10_icc0.0 (0.897) and cr1_G10_icc0.5 (0.907) are within 2 MC SE of 0.90 (`cells_within_2se_of_failure_line`); a different seed could move them across the line. The \"nominal-consistent\" label is a 2-SE screen, not a test with multiplicity control: across 27 pairs, some misclassification is expected. With R = 2000 we cannot resolve coverage differences much smaller than ≈0.02. The relative-bias estimates have MC SE 0.007–0.016 (`mc_se_rel_bias_var`). Because V̂ is right-skewed at small G, the normal approximation behind that SE is rough, which matches the one 2.46-SE discrepancy from the exact value in G5_icc0.2. The paired SE for the G = 5 ranking uses the fact that all procedures are evaluated on the same replications. The bootstrap critical value adds its own simulation noise (B = 399), and that noise is included in the WCB coverage estimate.\n\n## Limitations and open issues\n- **Distributions**: only Gaussian random effects and errors are covered. Skewed or heavy-tailed u_g/e_ig, which are known to matter for few-cluster inference, are not.\n- **Heterogeneity**: the design has a homoskedastic random intercept and a single fixed size pattern (8,16,32,64). It does not cover heteroskedasticity across clusters, cluster-size–outcome correlation, or other degrees of imbalance. Results may depend strongly on the dominant 64-observation cluster.\n- **Regressors**: only the mean (intercept-only model) is studied. Regression slopes, leverage and fixed effects are not covered.\n- **Other weights / variants**: only Rademacher weights, the unrestricted (non-null-imposed) WCB-t, and the symmetric percentile-t interval with numpy's linear-interpolation quantile are studied. Webb 6-point weights, restricted WCB (WCR), enumeration of all 2^G weight vectors at G = 5, CR2/CR3 (bias-reduced) estimators, and other degrees-of-freedom corrections are not evaluated. Results for the WCB at G = 5 are specific to these choices.\n- G ∈ {5, 10, 30} only; the location of the transition between 10 and 30 is not resolved.\n- The single 2.46-SE deviation between the MC and exact CR0 bias (G5_icc0.2) is reported, not removed. We read it as MC noise in a skewed estimator (see `out/state/checks.md`).\nEOF\ncat > claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G=5 and G=10 cells, WCB at all G=5 cells, CR1 at G=5 with ICC 0.2 and 0.5; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5_icc0.0 and cr0_G10_icc0.0 lie within 2 MC SE of 0.90, so their classification is fragile.\"},\n {\"id\":\"C2\",\"text\":\"CR1 has the highest average coverage over the G=5 cells (0.891 vs 0.853 WCB and 0.740 CR0); the CR1-WCB gap is many paired MC SEs.\",\"results_keys\":[\"best_procedure_small_G\",\"avg_coverage_G5\",\"avg_coverage_G5_paired_diff\"],\"status\":\"supported\",\"caveat\":\"Specific to Rademacher unrestricted WCB with B=399 and Gaussian DGP.\"},\n {\"id\":\"C3\",\"text\":\"Only 5 pairs are consistent with nominal 95% coverage (CR1 at G=10 and G=30 with ICC=0; WCB at all G=30 cells); CR0 never is.\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE screen without multiplicity control.\"},\n {\"id\":\"C4\",\"text\":\"CR0 and CR1 variance estimators are biased downward, most at small G and high ICC (CR0 ratio 0.48-0.66 at G=5, 0.93-0.94 at G=30).\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\"],\"status\":\"supported\",\"caveat\":\"MC estimate; agrees with closed-form expectation within 2 SE in 8 of 9 cells (2.46 SE in G5_icc0.2).\"},\n {\"id\":\"C5\",\"text\":\"The naive i.i.d. baseline interval covers only 0.29-0.49 when ICC>0, so all cluster-robust procedures improve on it in clustered cells.\",\"results_keys\":[\"baseline_iid_coverage\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Baseline is supplementary, not a required estimand.\"},\n {\"id\":\"C6\",\"text\":\"At G=10 with ICC>0, WCB covers better than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences (0.014 and 0.026) are of the order of 2-4 MC SE of individual coverages; not formally tested.\"}\n]\nEOF\ncd state && ~/wp29/venv/bin/python - <<'EOF'\nimport json,glob;p=json.load(open('phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"checks.md items 1-13 PASS\",\"gate run 20261030T054003: contract keys + reproducibility ok; failures only for P5 deliverables (report, claims, sections, ledger terminality)\",\"results.json extended with supplementary keys after first gate -> re-verified by second gate\"],\"notes\":\"\",\"gate_receipts\":[\"out/state/gate_receipts/20261030T054003.316148Z.json\"]}\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, every number keyed\",\"claims.json C1-C6\",\"final gate run (receipt appended)\"],\"notes\":\"\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Added supplementary keys (paired diff SE, near-threshold cells); P4 passed; P5 report/claims written; running final gate.\" >> log.md\ncd ../.. && ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Write report, claims, ledger; run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1791,"cache_read_input_tokens":29373,"output_tokens":5305,"output_tokens_details":{"thinking_tokens":139},"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":1791},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtHuLK1HzdSLUqNiqqd","requestRef":"9bd1a4bf-6605-4828-83cb-3752a160a496","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5ed4cbfa-f6ca-40ac-b81d-dee62b1193da","timestamp":"2026-10-30T05:41:04.961Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}99{"parentUuid":"5ed4cbfa-f6ca-40ac-b81d-dee62b1193da","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JjjjYxXoHrcW96grBUPUga","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\n [ok] file:out/results.json: present\n [ok] file:out/report.md: present\n [ok] file:out/analysis.py: present\n [ok] file:out/claims.json: present\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 [ok] section:Question: present\n [ok] section:Data and exclusions: present\n [ok] section:Method: present\n [ok] section:Results: present\n [ok] section:Uncertainty: present\n [ok] section:Limitations and open issues: present\n [ok] claims_json: 6 claims, all keys resolve\n [ok] phase_ledger: consistent\n [ok] exclusion_ledger: 1 steps consistent\n [ok] reproducibility: regenerated in 2.1s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0020/out/state/gate_receipts/20261030T054107.159475Z.json","is_error":false}]},"uuid":"554ce091-1b9c-4555-8625-7891fb7fb32f","timestamp":"2026-10-30T05:41:07.166Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\n [ok] file:out/results.json: present\n [ok] file:out/report.md: present\n [ok] file:out/analysis.py: present\n [ok] file:out/claims.json: present\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 [ok] section:Question: present\n [ok] section:Data and exclusions: present\n [ok] section:Method: present\n [ok] section:Results: present\n [ok] section:Uncertainty: present\n [ok] section:Limitations and open issues: present\n [ok] claims_json: 6 claims, all keys resolve\n [ok] phase_ledger: consistent\n [ok] exclusion_ledger: 1 steps consistent\n [ok] reproducibility: regenerated in 2.1s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0020/out/state/gate_receipts/20261030T054107.159475Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"5ed4cbfa-f6ca-40ac-b81d-dee62b1193da","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}100{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"7a11e13afa4b3755df8e596f5d0a20987d8b3f976ba19335f3e32229315411fa","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JjjjYxXoHrcW96grBUPUga","name":"Bash","input":{"command":"cd out && cat > report.md <<'EOF'\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t intervals for a mean with few clusters\n\nAll numbers below are produced by `out/analysis.py` (run: `~/wp29/venv/bin/python out/analysis.py`, ≈2 s) and are cited by their key in `out/results.json`. Full per-cell values are in `out/table1.csv`; the figure is `out/figure1.png`.\n\n## Question\nWhen N observations are grouped in few (G = 5, 10, 30) unbalanced clusters with intra-cluster correlation ICC ∈ {0, 0.2, 0.5}, what is the actual coverage of three nominal-95% cluster-robust intervals for the mean μ (CR0 with z critical value; CR1 with t_{G−1}; unrestricted Rademacher wild cluster bootstrap-t, WCB), how biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ), and in which (procedure, cell) pairs does coverage fall below 0.90?\n\n## Data and exclusions\nNo observed data. The only input is `data/design.csv` (`n_input_rows`: 9 rows; SHA-256 recorded in `out/state/data_audit.md`): 9 cells, cluster sizes 8,16,32,64 repeated (N = 128, 264, 864), R = 2000 (`R`), B = 399 (`B`), one seed per cell (C1 seed = `random_seed`; all seeds in `seeds_by_cell`). The audit found no missing values, duplicates or inconsistencies (sizes count = G, sum = N). No exclusions: all `n_cells` = 9 cells × 2000 replications = `n_analysed` = 18000 replications were simulated and analysed (`out/exclusions.csv`, one no-op step). `feasibility` = \"complete\". One design feature is recorded in `data_issues`: at G = 5 Rademacher weights take only 32 distinct values (16 distinct |t*|), so the bootstrap critical value is coarse; kept as specified. No bootstrap draw had a non-positive variance (`n_degenerate_bootstrap_draws` = 0).\n\n## Method\nPer replication (numpy `default_rng(cell seed)`, draws in fixed order u, e, W): y_ig = μ + u_g + e_ig, u_g ~ N(0, ICC), e_ig ~ N(0, 1−ICC), μ = 0. With ê = y − ȳ and S_g = Σ_i ê_ig: V̂_CR0 = Σ S_g²/N², CI ȳ ± 1.96√V̂_CR0; V̂_CR1 = G/(G−1)·V̂_CR0, CI ȳ ± t_{0.975,G−1}√V̂_CR1; WCB: B×G Rademacher matrix W, ȳ*−ȳ = Σ_g w_g S_g/N, bootstrap cluster residual sums w_g S_g − n_g(ȳ*−ȳ), V̂*_CR1 from these, t*_b = (ȳ*−ȳ)/√V̂*_CR1, q = 0.95 quantile of |t*| (numpy linear interpolation, `wcb_quantile_method`), CI ȳ ± q√V̂_CR1. Coverage = share of R intervals containing μ; MC SE = √(p̂(1−p̂)/R); relative bias = mean(V̂)/Var(ȳ) with Var(ȳ) = [ICC Σn_g² + (1−ICC)N]/N². Failure regime: coverage < 0.90; nominal-consistent: |p̂ − 0.95| ≤ 2 MC SE. Baseline (P2): the naive i.i.d. interval ȳ ± 1.96·s/√N on the same draws (`baseline_iid_coverage`).\n\nVerification (`out/state/checks.md`): byte-identical re-run; vectorised WCB matches a brute-force construction of y* (diff 7e-15); MC relative bias of CR0 matches the closed-form E[V̂_CR0]/Var(ȳ) within 2 MC SE in 8/9 cells (z = +2.46 in G5_icc0.2); MC Var(ȳ)/exact in [0.93, 1.06] (`check_mc_var_ybar_over_exact`).\n\n## Results\nCoverage (`coverage`, MC SE in `mc_se_coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive i.i.d. baseline |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.781 | 0.912 | 0.855 | 0.941 |\n| 5 | 0.2 | 0.721 | 0.885 | 0.854 | 0.460 |\n| 5 | 0.5 | 0.717 | 0.876 | 0.849 | 0.287 |\n| 10 | 0.0 | 0.897 | 0.944 | 0.936 | 0.957 |\n| 10 | 0.2 | 0.857 | 0.916 | 0.930 | 0.488 |\n| 10 | 0.5 | 0.853 | 0.907 | 0.933 | 0.313 |\n| 30 | 0.0 | 0.928 | 0.940 | 0.943 | 0.952 |\n| 30 | 0.2 | 0.921 | 0.935 | 0.946 | 0.485 |\n| 30 | 0.5 | 0.917 | 0.930 | 0.943 | 0.299 |\n\n- **Failure regimes** (`failure_cells`, `n_failure_cells` = 11): CR0 at every G = 5 and G = 10 cell (6 pairs); WCB at all three G = 5 cells; CR1 at G = 5 with ICC = 0.2 and 0.5. No procedure fails at G = 30.\n- **Nominal-consistent pairs** (`nominal_cells`, 5 pairs): cr1_G10_icc0.0, cr1_G30_icc0.0, wcb_G30_icc0.0, wcb_G30_icc0.2, wcb_G30_icc0.5. CR0 is never consistent with 0.95, even at G = 30 (0.917–0.928).\n- **Best at G = 5** (`best_procedure_small_G` = \"cr1\"): average G = 5 coverage 0.891 for CR1, 0.853 for WCB, 0.740 for CR0 (`avg_coverage_G5`). The CR1 − WCB difference is 0.038 with paired MC SE 0.0035 (`avg_coverage_G5_paired_diff`), so the ranking is not a Monte Carlo artefact. At G = 10 with ICC > 0, WCB covers better than CR1 (0.930/0.933 vs 0.916/0.907).\n- **Variance bias** (`rel_bias_var`): both sandwich estimators are biased downward, most at small G and high ICC. CR0: 0.66, 0.53, 0.48 at G = 5 (ICC 0, 0.2, 0.5); 0.86, 0.76, 0.77 at G = 10; 0.94, 0.93, 0.93 at G = 30. CR1: 0.83, 0.66, 0.60 at G = 5; 0.95, 0.85, 0.86 at G = 10; 0.98, 0.96, 0.96 at G = 30. The unbalanced sizes (one 64-observation cluster dominates) make the bias much worse than the balanced-cluster factor (G−1)/G.\n- **Baseline**: the naive i.i.d. interval is fine at ICC = 0 but covers only 0.29–0.49 when ICC > 0 (`baseline_iid_coverage`), whatever G is. All three cluster-robust procedures improve on it there.\n- Mean CI half-widths are in `table1.csv` (`mean_ci_halfwidth`). At G = 5 the WCB interval is on average *wider* than CR1 but still covers less. One plausible explanation (not tested here) is that q varies a lot across replications, because the bootstrap distribution has only 16 distinct |t*| values.\n\n## Uncertainty\nEach coverage is a binomial proportion over R = 2000 independent replications. Its MC SE (`mc_se_coverage`) is 0.005–0.010, so a 95% MC interval is about ±0.010–0.020. The figure shows ±1.96 MC SE bars. Classifications near the 0.90 threshold are therefore fragile. cr1_G5_icc0.0 (0.912), cr0_G10_icc0.0 (0.897) and cr1_G10_icc0.5 (0.907) are within 2 MC SE of 0.90 (`cells_within_2se_of_failure_line`); a different seed could move them across the line. The \"nominal-consistent\" label is a 2-SE screen, not a test with multiplicity control: across 27 pairs, some misclassification is expected. With R = 2000 we cannot resolve coverage differences much smaller than ≈0.02. The relative-bias estimates have MC SE 0.007–0.016 (`mc_se_rel_bias_var`). Because V̂ is right-skewed at small G, the normal approximation behind that SE is rough, which matches the one 2.46-SE discrepancy from the exact value in G5_icc0.2. The paired SE for the G = 5 ranking uses the fact that all procedures are evaluated on the same replications. The bootstrap critical value adds its own simulation noise (B = 399), and that noise is included in the WCB coverage estimate.\n\n## Limitations and open issues\n- **Distributions**: only Gaussian random effects and errors are covered. Skewed or heavy-tailed u_g/e_ig, which are known to matter for few-cluster inference, are not.\n- **Heterogeneity**: the design has a homoskedastic random intercept and a single fixed size pattern (8,16,32,64). It does not cover heteroskedasticity across clusters, cluster-size–outcome correlation, or other degrees of imbalance. Results may depend strongly on the dominant 64-observation cluster.\n- **Regressors**: only the mean (intercept-only model) is studied. Regression slopes, leverage and fixed effects are not covered.\n- **Other weights / variants**: only Rademacher weights, the unrestricted (non-null-imposed) WCB-t, and the symmetric percentile-t interval with numpy's linear-interpolation quantile are studied. Webb 6-point weights, restricted WCB (WCR), enumeration of all 2^G weight vectors at G = 5, CR2/CR3 (bias-reduced) estimators, and other degrees-of-freedom corrections are not evaluated. Results for the WCB at G = 5 are specific to these choices.\n- G ∈ {5, 10, 30} only; the location of the transition between 10 and 30 is not resolved.\n- The single 2.46-SE deviation between the MC and exact CR0 bias (G5_icc0.2) is reported, not removed. We read it as MC noise in a skewed estimator (see `out/state/checks.md`).\nEOF\ncat > claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G=5 and G=10 cells, WCB at all G=5 cells, CR1 at G=5 with ICC 0.2 and 0.5; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5_icc0.0 and cr0_G10_icc0.0 lie within 2 MC SE of 0.90, so their classification is fragile.\"},\n {\"id\":\"C2\",\"text\":\"CR1 has the highest average coverage over the G=5 cells (0.891 vs 0.853 WCB and 0.740 CR0); the CR1-WCB gap is many paired MC SEs.\",\"results_keys\":[\"best_procedure_small_G\",\"avg_coverage_G5\",\"avg_coverage_G5_paired_diff\"],\"status\":\"supported\",\"caveat\":\"Specific to Rademacher unrestricted WCB with B=399 and Gaussian DGP.\"},\n {\"id\":\"C3\",\"text\":\"Only 5 pairs are consistent with nominal 95% coverage (CR1 at G=10 and G=30 with ICC=0; WCB at all G=30 cells); CR0 never is.\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE screen without multiplicity control.\"},\n {\"id\":\"C4\",\"text\":\"CR0 and CR1 variance estimators are biased downward, most at small G and high ICC (CR0 ratio 0.48-0.66 at G=5, 0.93-0.94 at G=30).\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\"],\"status\":\"supported\",\"caveat\":\"MC estimate; agrees with closed-form expectation within 2 SE in 8 of 9 cells (2.46 SE in G5_icc0.2).\"},\n {\"id\":\"C5\",\"text\":\"The naive i.i.d. baseline interval covers only 0.29-0.49 when ICC>0, so all cluster-robust procedures improve on it in clustered cells.\",\"results_keys\":[\"baseline_iid_coverage\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Baseline is supplementary, not a required estimand.\"},\n {\"id\":\"C6\",\"text\":\"At G=10 with ICC>0, WCB covers better than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences (0.014 and 0.026) are of the order of 2-4 MC SE of individual coverages; not formally tested.\"}\n]\nEOF\ncd state && ~/wp29/venv/bin/python - <<'EOF'\nimport json,glob;p=json.load(open('phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"checks.md items 1-13 PASS\",\"gate run 20261030T054003: contract keys + reproducibility ok; failures only for P5 deliverables (report, claims, sections, ledger terminality)\",\"results.json extended with supplementary keys after first gate -> re-verified by second gate\"],\"notes\":\"\",\"gate_receipts\":[\"out/state/gate_receipts/20261030T054003.316148Z.json\"]}\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, every number keyed\",\"claims.json C1-C6\",\"final gate run (receipt appended)\"],\"notes\":\"\"}\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Added supplementary keys (paired diff SE, near-threshold cells); P4 passed; P5 report/claims written; running final gate.\" >> log.md\ncd ../.. && ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .","description":"Write report, claims, ledger; run gate"}}]}}101{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"9439b6e7-d580-4046-a034-505568d36981","timestamp":"2026-10-30T05:41:07.169Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"9bd1a4bf-6605-4828-83cb-3752a160a496","keep":32,"tail":["7a11e13afa4b3755df8e596f5d0a20987d8b3f976ba19335f3e32229315411fa","efad654c914a0ecdbf34373376dd7a93a63c0c3a915e67ef238d309d3148a46a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a83e0d361eacad9168b6dc252b6f917c8707d0dbd30ea26af79cc65bfa9f7d70"}102{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"554ce091-1b9c-4555-8625-7891fb7fb32f","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}103{"type":"atis-latch","atis":"","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}104{"parentUuid":"554ce091-1b9c-4555-8625-7891fb7fb32f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMR1qNXnaDqTTsxkP6","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":5960,"cache_read_input_tokens":31164,"output_tokens":354,"output_tokens_details":{"thinking_tokens":76},"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":5960},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":521,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtMQkTXLXjVEfKCa7kX","requestRef":"9439b6e7-d580-4046-a034-505568d36981","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f17a3e10-0157-40aa-9720-077a503a1226","timestamp":"2026-10-30T05:41:08.731Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}105{"parentUuid":"f17a3e10-0157-40aa-9720-077a503a1226","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMR1qNXnaDqTTsxkP6","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LRzBamPb5UeewjebAUBuK4","name":"Bash","input":{"command":"cd out/state && ~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P5']['checks'].append(\"final gate PASSED 34/34: out/state/gate_receipts/20261030T054107.159475Z.json\")\np['P5']['gate_receipts']=[\"out/state/gate_receipts/20261030T054107.159475Z.json\"]\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate passed (20261030T054107). All phases passed.\" >> log.md","description":"Record final gate receipt"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5960,"cache_read_input_tokens":31164,"output_tokens":354,"output_tokens_details":{"thinking_tokens":76},"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":5960},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtMQkTXLXjVEfKCa7kX","requestRef":"9439b6e7-d580-4046-a034-505568d36981","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"338e0319-a7c4-4092-ad92-a04d84ea212c","timestamp":"2026-10-30T05:41:10.466Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}106{"parentUuid":"338e0319-a7c4-4092-ad92-a04d84ea212c","isSidechain":false,"promptId":"beebe07d-24ce-4f2f-b688-d231cd282397","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LRzBamPb5UeewjebAUBuK4","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"8cddae0e-23ff-473a-a74b-e672b09f7f46","timestamp":"2026-10-30T05:41:10.512Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"338e0319-a7c4-4092-ad92-a04d84ea212c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}107{"type":"api-request-blob","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","hash":"28cb7406890f261d0baf2596eb45b2cd036bdf6bf25bd68877250b569498503b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LRzBamPb5UeewjebAUBuK4","name":"Bash","input":{"command":"cd out/state && ~/wp29/venv/bin/python - <<'EOF'\nimport json;p=json.load(open('phases.json'))\np['P5']['checks'].append(\"final gate PASSED 34/34: out/state/gate_receipts/20261030T054107.159475Z.json\")\np['P5']['gate_receipts']=[\"out/state/gate_receipts/20261030T054107.159475Z.json\"]\njson.dump(p,open('phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 Final gate passed (20261030T054107). All phases passed.\" >> log.md","description":"Record final gate receipt"}}]}}108{"type":"api-request","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","id":"88f634a5-91ec-4871-9675-b557b30cc466","timestamp":"2026-10-30T05:41:10.515Z","version":"2.1.314","querySource":"sdk","shapeHash":"e298605f8056f107a17e73eaae2c795170b203440dd834d80157b775de2efa6e","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":"9439b6e7-d580-4046-a034-505568d36981","keep":34,"tail":["28cb7406890f261d0baf2596eb45b2cd036bdf6bf25bd68877250b569498503b","ec6885eb3844de534829159564ec44e88f1b9d874d7d5bdd106211743c5e6c75"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c0ad2e7f480bc33e90272fed96633834f6081b4b36bad456c6e90037c94f45a2"}109{"parentUuid":"8cddae0e-23ff-473a-a74b-e672b09f7f46","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMfFpyj49V6mJ3Zx2j","type":"message","role":"assistant","content":[{"type":"text","text":"I've finished the full simulation study: all 9 design cells × 2,000 replications (B = 399), and the final gate passed all 34 checks. Running `out/analysis.py` again gives byte-identical results in about 2 seconds.\n\n**Main results:**\n- **Failure regimes (coverage below 0.90):** 11 of the 27 (procedure, cell) pairs.\n - CR0 fails in every G=5 and G=10 cell.\n - The wild cluster bootstrap (WCB) fails in all three G=5 cells (about 0.85).\n - CR1 fails at G=5 when ICC is 0.2 or 0.5.\n - Nothing fails at G=30.\n- **Consistent with 95% coverage:** only 5 pairs: CR1 at G=10 and G=30 with ICC=0, and WCB in all three G=30 cells. CR0 never reaches nominal coverage, even at G=30 (0.917–0.928).\n- **Best procedure at G=5:** CR1, with average coverage 0.891, against 0.853 for WCB and 0.740 for CR0. The CR1 − WCB gap is 0.038 with a Monte Carlo standard error of 0.0035, so the ranking is not simulation noise. At G=10 with ICC above 0, WCB covers better than CR1.\n- **Variance bias:** both sandwich estimators underestimate the variance, most with few clusters and high ICC. CR0's ratio of estimated to exact variance is 0.48–0.66 at G=5 and about 0.93 at G=30.\n- **Simple baseline:** an ordinary interval that ignores clustering covers only 0.29–0.49 whenever ICC is above 0.\n\n**How I checked the code:**\n- The vectorised bootstrap matches a direct, slow implementation to within 7e-15.\n- The simulated CR0 bias matches the exact theoretical value within 2 Monte Carlo standard errors in 8 of 9 cells. The exception is G=5, ICC=0.2, at 2.46 standard errors; I report it rather than hide it.\n- The simulated variance of the mean is within 0.93–1.06 of the exact value in every cell.\n\n**Limitations (also in the report):**\n- The design covers only normally distributed data, one fixed pattern of unequal cluster sizes, a model with no regressors, Rademacher bootstrap weights, and the unrestricted bootstrap variant.\n- Three pairs are within 2 standard errors of the 0.90 line, so a different seed could move them across it: CR1 at G=5/ICC=0, CR0 at G=10/ICC=0, and CR1 at G=10/ICC=0.5.\n- With only 5 clusters, the bootstrap has just 32 possible weight patterns, so its critical value is coarse. I kept the method exactly as specified and noted this under `data_issues`.\n\nEverything is in `out/`. Open `report.md` first; it also has the full coverage table. The `state/` folder holds the audit trail: data audit, checks, phase ledger, log and gate receipts.\n\nFiles are in `out/`:\n- `report.md`\n- `results.json`\n- `table1.csv`\n- `figure1.png`\n- `analysis.py`\n- `claims.json`\n- `exclusions.csv`"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":369,"cache_read_input_tokens":37124,"output_tokens":1091,"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":369},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtMf4BbX2v6geczNGa8","requestRef":"88f634a5-91ec-4871-9675-b557b30cc466","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6bf7d570-62f8-4245-89e1-077660462f85","timestamp":"2026-10-30T05:41:20.409Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","version":"2.1.314","gitBranch":"HEAD"}110{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"6bf7d570-62f8-4245-89e1-077660462f85","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b"}111{"type":"cost-state","sessionId":"65ce79ed-b826-489e-9312-f65c092b3c6b","totalCostUSD":0.6795262,"totalAPIDuration":188066,"totalAPIDurationWithoutRetries":188058,"totalToolDuration":15704,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":203899,"startTime":1793338676528,"modelUsage":{"claude-opus-5-5":{"inputTokens":38,"outputTokens":21657,"thinkingTokens":3186,"cacheReadInputTokens":331446,"cacheCreationInputTokens":35989,"cacheCreationEphemeral5mInputTokens":35989,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.6795262}},"hasUnknownModelCost":false}112