spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:38:41.152Z","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:38:41.158Z","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}4{"parentUuid":null,"isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":"Begin"},"uuid":"4bfff762-e37a-42cf-9c99-e345f72b05af","timestamp":"2026-10-30T05:38:41.162Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","timestamp":"2026-10-30T05:38:41.175Z","version":"2.1.314","shape":{"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude, running within the Claude Agent SDK."},{"type":"text","text":"CWD: /Users/simon-pierreboucher/wp29/runs/RT0021\nDate: 2026-10-30\n\nYou are 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":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"7aa63bd1-dcf8-453b-ae22-c2def794521b","timestamp":"2026-10-30T05:38:41.175Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"0476c220aebcbeaef8d7e74a9caa092c02714fb4bbb42ef4704f99bdb92ea427"}8{"parentUuid":"4bfff762-e37a-42cf-9c99-e345f72b05af","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"7ecb2635-44d0-4190-9435-df83a3d0957c","timestamp":"2026-10-30T05:38:41.167Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"7ecb2635-44d0-4190-9435-df83a3d0957c","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"c8b6c179-4c42-4e25-bc1d-c8321f9ea8d2","timestamp":"2026-10-30T05:38:41.167Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"c8b6c179-4c42-4e25-bc1d-c8321f9ea8d2","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":"a0c2feb4-81a6-4025-8ec4-db94dcb0ca91","timestamp":"2026-10-30T05:38:41.168Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}12{"parentUuid":"a0c2feb4-81a6-4025-8ec4-db94dcb0ca91","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtAerTt69DeU1S8uuXB","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQStgUKEAgTGAI4AUIIdGhpbmtpbmcSDISw17Z6oGKwYxZ6phoMkWxlIFTZSm4CI6RqIjADxMAnAgrch4t6d1HhVhiB9n9iU5D+rGnZoQM0GL5iiFJIQNrMDDXqZjs4yZeT4UUq0wSRqlOzDMbxq5TZ6xQiEWuiOGuzf2901IO7OUEINP97gn9ENyb9hVZS53NRrM3eYvwowGPZHBJ3VhErJ84Cy1rbPGRm58RxzPzVT4WjEjKP/cXzppxOchae7+IOOhYpEwvzj5X7xDXW0pmbqxHoImiD5KfYcGWk0aaioyQxRm3nWKI9vGJ3cRX+O4TeXmZl8mNDWRHvKzqvnzeyu//ZhSkm8fVSaNPg5v9eMs26x8H+1PJmx/4UrXy0tgzK/Sps3DLAWNW937WjpDWj8fm31l4DD9uLLC0Pz1vKrg0vWvDr95ug/BqyXydeYNACpdb/ay+udc77kihpzMpfx2Urwcvs10b1xBnwkmWv/fBupEF9ZxSGTQQWA1pYBiQIfiundSs05n2umq4HYh38BfyHQf0l2PIFovJy+CzZ5Kiq1XBp+4HGTY0MRdmSRSgv1fXRjSg3tvTTE5pFEs+KOKhP+7hg/UV3gDC8ywO/FOR7MmgFkkO/ONCSiMdb8TgogrNr5nQ8AgIpKIVPJz8KXLw3VIfd4EgxNBw/5jI77bqK+ajF3tW1BB7Yyqh1tJcmNKPxlgogVR1Ix6Yjlv7YdKmKkPBTCDIzDuwoklry9rgyDweqDjFq1/8WKby4+mhwflhVLsVRafxbcvCAfdzQR3Icy7klDfAMvjmfJjpyeak5figU1qmaT+nZl8tLWmAfZf6bitGNWAz4fGfhQsZpIAmHIetapNznlt7Z3UQnIWqZfsZMNNcATTYN3fV/jrsxB1FqU9r1Vnm7ldCAU0GcnCtxIC8iXbgMGAE="}],"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":133,"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":525,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtAeZcPfRj7DKLfxQVX","requestRef":"7aa63bd1-dcf8-453b-ae22-c2def794521b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"22655a1f-a929-4f77-a2b7-0867b7902b7b","timestamp":"2026-10-30T05:38:42.574Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"22655a1f-a929-4f77-a2b7-0867b7902b7b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtAerTt69DeU1S8uuXB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Mni84eXkXtXUyxsfh9167H","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","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":133,"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_011CgXtAeZcPfRj7DKLfxQVX","requestRef":"7aa63bd1-dcf8-453b-ae22-c2def794521b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ef9b91e2-14a1-4aba-91a5-c0627c0acea7","timestamp":"2026-10-30T05:38:43.220Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"ef9b91e2-14a1-4aba-91a5-c0627c0acea7","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Mni84eXkXtXUyxsfh9167H","type":"tool_result","content":"# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n  - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n  - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n  - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 32\ndrwxr-xr-x    6 simon-pierreboucher  staff   192 oct.  30 00:18 .\ndrwxr-xr-x  197 simon-pierreboucher  staff  6304 oct.  30 01:38 ..\n-rw-r--r--    1 simon-pierreboucher  staff   517 oct.  30 00:32 bundle.json\ndrwxr-xr-x    4 simon-pierreboucher  staff   128 oct.  30 00:12 data\n-rw-r--r--    1 simon-pierreboucher  staff  1545 oct.  30 00:12 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6628 oct.  30 00:12 TASK.md\ndata:\ndesign.csv\nREADME.md","is_error":false}]},"uuid":"6b05f8e3-c462-43f5-aa27-7451123937bc","timestamp":"2026-10-30T05:38:43.336Z","toolUseResult":{"stdout":"# T2-simulation — Finite-sample performance of three cluster-robust confidence intervals for a mean: a simulation study\n\n## Scientific question\nWhen observations are grouped in a small number of clusters, how reliable are the usual cluster-robust confidence intervals for a population mean? This is a complete simulation-methodology project: design → implementation → Monte Carlo evaluation with its own uncertainty → identification of failure regimes → figure and table → an executable technical note. The estimand of the inferential procedures is the population mean μ of y, estimated by the sample mean ȳ of N clustered observations; the estimands of the study are, for each of the nine design cells (G ∈ {5, 10, 30} clusters × intra-cluster correlation ICC ∈ {0.0, 0.2, 0.5}) and each of three interval procedures, (a) the actual coverage probability of the nominal 95% interval, (b) for the two sandwich estimators, the relative bias of the variance estimator, E[V̂] / Var(ȳ), where Var(ȳ) is the exact variance of the sample mean under the design, (c) the Monte Carlo standard error of each coverage estimate, and (d) the set of (procedure, cell) pairs whose coverage falls below 0.90 — the failure regimes.\n\n## Inputs\n- `data/design.csv` — simulated-data design written by the task designer (nothing here is observed data): one row per cell with `cell_id`, `G`, `icc`, `cluster_sizes` (the G cluster sizes separated by `|`: the pattern 8, 16, 32, 64 repeated), `N`, `R` = 2000 replications, `B` = 399 bootstrap draws, `seed`, `mu` = 0, `total_variance` = 1, `nominal_level` = 0.95. See `data/README.md`.\n\n## Information-availability rules\n- Data-generating process (per replication): y_ig = μ + u_g + e_ig with u_g ~ N(0, ICC) i.i.d. across clusters and e_ig ~ N(0, 1 − ICC) i.i.d. across observations, independent of u; cluster g has n_g observations as listed in `cluster_sizes`. Exact variance of the sample mean: Var(ȳ) = [ICC · Σ_g n_g² + (1 − ICC) · N] / N².\n- Interval procedures (all three required, exactly as specified, with ȳ as the point estimate and residuals ê_ig = y_ig − ȳ):\n  - **CR0**: V̂_CR0 = Σ_g (Σ_i ê_ig)² / N²; interval ȳ ± 1.96 · √V̂_CR0;\n  - **CR1**: V̂_CR1 = [G / (G − 1)] · V̂_CR0; interval ȳ ± t_{0.975, G−1} · √V̂_CR1 (Student t with G − 1 degrees of freedom);\n  - **WCB** (wild cluster bootstrap-t, unrestricted, Rademacher): for b = 1..B draw cluster weights w_g^b ∈ {−1, +1} with equal probability, form y*_ig = ȳ + w_g^b · ê_ig, compute ȳ* and its V̂_CR1* on the bootstrap sample, t*_b = (ȳ* − ȳ) / √V̂_CR1*; critical value q = the 0.95 empirical quantile of |t*_1|, …, |t*_B|; interval ȳ ± q · √V̂_CR1.\n- Use R = 2000 replications per cell, B = 399 bootstrap draws per replication and the cell's seed from `design.csv`; do not change the grid, R or B. A procedure's coverage in a cell is the fraction of the R intervals that contain μ. The Monte Carlo standard error of a coverage estimate p̂ is √(p̂(1 − p̂)/R).\n- A (procedure, cell) pair is a **failure regime** when its estimated coverage is below 0.90. A pair is **consistent with nominal coverage** when |p̂ − 0.95| ≤ 2 · MC SE.\n\n## Required outputs\n- `out/table1.csv` — 27 rows (3 procedures × 9 cells) with columns `estimator` (`cr0`, `cr1`, `wcb`), `cell_id`, `G`, `icc`, `coverage`, `mc_se_coverage`, `rel_bias_var` (empty for `wcb`), `mean_ci_halfwidth`, `R`.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T2-simulation\" |\n| `R` | integer | — | replications per cell actually used |\n| `B` | integer | — | bootstrap draws per replication actually used |\n| `n_cells` | integer | — | number of design cells simulated |\n| `coverage` | object | — | {\"<estimator>_G<G>_icc<icc>\": number} for the 27 pairs, e.g. `\"cr1_G5_icc0.2\"` (icc written as 0.0, 0.2, 0.5) |\n| `mc_se_coverage` | object | — | same keys: Monte Carlo SE of each coverage estimate |\n| `rel_bias_var` | object | — | 18 keys (cr0 and cr1 only): E[V̂]/Var(ȳ) estimated by the Monte Carlo mean |\n| `failure_cells` | array of strings | — | the pairs with coverage < 0.90, same key format, any order |\n| `n_failure_cells` | integer | — | length of `failure_cells` |\n| `nominal_cells` | array of strings | — | the pairs whose coverage is consistent with nominal (|p̂ − 0.95| ≤ 2 MC SE) |\n| `best_procedure_small_G` | string | — | the procedure with the highest average coverage over the three G = 5 cells |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the design or during the simulation and how handled; empty list if none |\n| `n_input_rows` | object | rows | {\"design.csv\": number of data rows} |\n| `n_analysed` | integer or null | — | total number of replications simulated (cells × R) |\n| `random_seed` | integer or null | — | the seed of cell C1 (the other seeds are in `design.csv`) |\n\n- `out/figure1.png` — coverage against G for the three procedures, one panel per ICC (or an equivalent figure), with the nominal level and the 0.90 failure line marked.\n- `out/report.md` — an executable technical note with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. \"Uncertainty\" must discuss the Monte Carlo error of the coverage and bias estimates; \"Limitations and open issues\" must state what the design does not cover (distributions, heterogeneity, regressors, other weights).\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/table1.csv` and `out/figure1.png` from `data/design.csv` only, deterministically (same seeds → same numbers).\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Vectorise the bootstrap (a B × G weight matrix per replication is enough); the full grid runs in a few minutes in numpy. The analysis must complete within 10 minutes.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ntotal 32\ndrwxr-xr-x    6 simon-pierreboucher  staff   192 oct.  30 00:18 .\ndrwxr-xr-x  197 simon-pierreboucher  staff  6304 oct.  30 01:38 ..\n-rw-r--r--    1 simon-pierreboucher  staff   517 oct.  30 00:32 bundle.json\ndrwxr-xr-x    4 simon-pierreboucher  staff   128 oct.  30 00:12 data\n-rw-r--r--    1 simon-pierreboucher  staff  1545 oct.  30 00:12 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6628 oct.  30 00:12 TASK.md\ndata:\ndesign.csv\nREADME.md","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ef9b91e2-14a1-4aba-91a5-c0627c0acea7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}15{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"6b05f8e3-c462-43f5-aa27-7451123937bc","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}16{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}17{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"02a526c10a43549861d5a30171117ef34593ed6ea082d65897219a69d0d8a1c9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Mni84eXkXtXUyxsfh9167H","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}18{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"f61a28e9-f58d-4a0c-b27b-2944ac7201c6","timestamp":"2026-10-30T05:38:43.342Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"7aa63bd1-dcf8-453b-ae22-c2def794521b","keep":2,"tail":["02a526c10a43549861d5a30171117ef34593ed6ea082d65897219a69d0d8a1c9","4d2942944be634a2e99bd143ebaba27680e4b46157922fd0f024fc36812631b0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7e32df9efe983f323de5c924d545a9961bb7564eb484d1f309d69f15d20eb66c"}19{"parentUuid":"6b05f8e3-c462-43f5-aa27-7451123937bc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtAoztbdLm28cnipHUg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PTnCEJ2HG9LT2u5ejHXmCx","name":"Bash","input":{"command":"cat data/README.md; cat data/design.csv; cat gate_spec.json; cat bundle.json; shasum -a 256 data/*","description":"Inspect data files and gate spec"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3159,"cache_read_input_tokens":4315,"output_tokens":123,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3159},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtAoj1uQuNPqLRCEkNf","requestRef":"f61a28e9-f58d-4a0c-b27b-2944ac7201c6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6b1bca76-2105-453a-85ea-6303663edd1e","timestamp":"2026-10-30T05:38:45.056Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"6b1bca76-2105-453a-85ea-6303663edd1e","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PTnCEJ2HG9LT2u5ejHXmCx","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}\n{\n  \"task_id\": \"T2-simulation\",\n  \"family\": \"T2\",\n  \"split\": \"transfer\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T04:32:27.189577+00:00\",\n  \"files\": {\n    \"TASK.md\": \"22849122c96cf5f55a070b010b46d61fcd43177c89a6278a0e8dfc609113cb73\",\n    \"data/README.md\": \"73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67\",\n    \"data/design.csv\": \"f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50\",\n    \"gate_spec.json\": \"30f9d1aec40a303349e47e2a432ac95c1403984a0b951eefb117ace32d657e1e\"\n  }\n}f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50  data/design.csv\n73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67  data/README.md","is_error":false}]},"uuid":"474c0ea9-767a-43c8-b484-88534cc6d273","timestamp":"2026-10-30T05:38:45.120Z","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}\n{\n  \"task_id\": \"T2-simulation\",\n  \"family\": \"T2\",\n  \"split\": \"transfer\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T04:32:27.189577+00:00\",\n  \"files\": {\n    \"TASK.md\": \"22849122c96cf5f55a070b010b46d61fcd43177c89a6278a0e8dfc609113cb73\",\n    \"data/README.md\": \"73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67\",\n    \"data/design.csv\": \"f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50\",\n    \"gate_spec.json\": \"30f9d1aec40a303349e47e2a432ac95c1403984a0b951eefb117ace32d657e1e\"\n  }\n}f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50  data/design.csv\n73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67  data/README.md","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6b1bca76-2105-453a-85ea-6303663edd1e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"a50fb2c15bd46dbf7bc0287a25f41ffcef3a13625594e46ad293d0e6a3be3393","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01PTnCEJ2HG9LT2u5ejHXmCx","name":"Bash","input":{"command":"cat data/README.md; cat data/design.csv; cat gate_spec.json; cat bundle.json; shasum -a 256 data/*","description":"Inspect data files and gate spec"}}]}}22{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"9fb71d47-0980-45cb-ad35-27b60c6df51a","timestamp":"2026-10-30T05:38:45.123Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"f61a28e9-f58d-4a0c-b27b-2944ac7201c6","keep":4,"tail":["a50fb2c15bd46dbf7bc0287a25f41ffcef3a13625594e46ad293d0e6a3be3393","33e259516b849862bdfcaf9da0d3c1fd8336b5db1166f1d510bfebd382770f79"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ed2a37362164772f854de032eaec03347df9bddc589150a2bbe61f1a6e09a846"}23{"parentUuid":"474c0ea9-767a-43c8-b484-88534cc6d273","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtAwcXW77UkMsPfXk2p","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":2279,"cache_read_input_tokens":7474,"output_tokens":2514,"output_tokens_details":{"thinking_tokens":1402},"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":2279},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":14436,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtAwLf4XjxXArRXob4D","requestRef":"9fb71d47-0980-45cb-ad35-27b60c6df51a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"14513013-963a-45ce-b05e-36b69907585c","timestamp":"2026-10-30T05:39:00.919Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"14513013-963a-45ce-b05e-36b69907585c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtAwcXW77UkMsPfXk2p","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017MXEWGPArqH8Ufui4n6LYT","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — T2-simulation\n\n**Question.** With few clusters, how reliable are cluster-robust 95% CIs for a population mean μ (point estimate ȳ)?\n\n**Estimands (per cell × procedure).** Design: G ∈ {5,10,30} × ICC ∈ {0,0.2,0.5}; procedures CR0 (z), CR1 (t_{G−1}), WCB (wild cluster bootstrap-t, Rademacher, unrestricted, B=399).\n(a) actual coverage P(μ ∈ CI); (b) for CR0/CR1, E[V̂]/Var(ȳ) with exact Var(ȳ) = [ICC Σn_g² + (1−ICC)N]/N²;\n(c) MC SE √(p̂(1−p̂)/R); (d) failure regimes: coverage < 0.90; nominal-consistent: |p̂−0.95| ≤ 2 MC SE.\nMeaningful under the stated Gaussian random-intercept DGP with the fixed unbalanced cluster sizes (8,16,32,64 repeated); conclusions are conditional on this design.\n\n**Outputs.** out/results.json (task_id, R, B, n_cells, coverage{27}, mc_se_coverage{27}, rel_bias_var{18}, failure_cells, n_failure_cells, nominal_cells, best_procedure_small_G, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/table1.csv (27 rows: estimator, cell_id, G, icc, coverage, mc_se_coverage, rel_bias_var (blank for wcb), mean_ci_halfwidth, R); out/figure1.png; out/report.md (6 sections); out/analysis.py; out/claims.json. Key format `<est>_G<G>_icc<icc>` with icc as 0.0/0.2/0.5.\n\n**Information rules.** Use exactly the DGP, procedures, R=2000, B=399, per-cell seeds from design.csv; no grid change. Only data/design.csv as input.\n\n**Invalidity.** Changing R/B/grid/seeds, different procedure definitions, non-deterministic output, or runtime >10 min. Design inconsistencies (e.g. N ≠ Σ n_g) would need to be reported.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read completely\",\"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":2279,"cache_read_input_tokens":7474,"output_tokens":2514,"output_tokens_details":{"thinking_tokens":1402},"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":2279},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtAwLf4XjxXArRXob4D","requestRef":"9fb71d47-0980-45cb-ad35-27b60c6df51a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dc1e6dcc-fd55-4235-99e9-11b652c7d5ce","timestamp":"2026-10-30T05:39:09.367Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"dc1e6dcc-fd55-4235-99e9-11b652c7d5ce","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017MXEWGPArqH8Ufui4n6LYT","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"6c7f6cbf-7b4e-4592-9bb2-9d0b4ee11e4e","timestamp":"2026-10-30T05:39:09.420Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"dc1e6dcc-fd55-4235-99e9-11b652c7d5ce","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"35268c14422db25a15972bd75473fa048e7c84a33afc2fc663e2c5af03a11ee9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_017MXEWGPArqH8Ufui4n6LYT","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — T2-simulation\n\n**Question.** With few clusters, how reliable are cluster-robust 95% CIs for a population mean μ (point estimate ȳ)?\n\n**Estimands (per cell × procedure).** Design: G ∈ {5,10,30} × ICC ∈ {0,0.2,0.5}; procedures CR0 (z), CR1 (t_{G−1}), WCB (wild cluster bootstrap-t, Rademacher, unrestricted, B=399).\n(a) actual coverage P(μ ∈ CI); (b) for CR0/CR1, E[V̂]/Var(ȳ) with exact Var(ȳ) = [ICC Σn_g² + (1−ICC)N]/N²;\n(c) MC SE √(p̂(1−p̂)/R); (d) failure regimes: coverage < 0.90; nominal-consistent: |p̂−0.95| ≤ 2 MC SE.\nMeaningful under the stated Gaussian random-intercept DGP with the fixed unbalanced cluster sizes (8,16,32,64 repeated); conclusions are conditional on this design.\n\n**Outputs.** out/results.json (task_id, R, B, n_cells, coverage{27}, mc_se_coverage{27}, rel_bias_var{18}, failure_cells, n_failure_cells, nominal_cells, best_procedure_small_G, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/table1.csv (27 rows: estimator, cell_id, G, icc, coverage, mc_se_coverage, rel_bias_var (blank for wcb), mean_ci_halfwidth, R); out/figure1.png; out/report.md (6 sections); out/analysis.py; out/claims.json. Key format `<est>_G<G>_icc<icc>` with icc as 0.0/0.2/0.5.\n\n**Information rules.** Use exactly the DGP, procedures, R=2000, B=399, per-cell seeds from design.csv; no grid change. Only data/design.csv as input.\n\n**Invalidity.** Changing R/B/grid/seeds, different procedure definitions, non-deterministic output, or runtime >10 min. Design inconsistencies (e.g. N ≠ Σ n_g) would need to be reported.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read completely\",\"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":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"6c217e2a-18d0-4581-9f81-57cc920c1ec8","timestamp":"2026-10-30T05:39:09.423Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"9fb71d47-0980-45cb-ad35-27b60c6df51a","keep":6,"tail":["35268c14422db25a15972bd75473fa048e7c84a33afc2fc663e2c5af03a11ee9","64b1b9f4353e91a17fdc270472ddd5fa74bd80d1f06cb4f0a45a2479f1a5ec25"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5afb23165db53ff59efe4893e1dbad91e757b1ac98aaf5be7e44401246fe4f36"}28{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"6c7f6cbf-7b4e-4592-9bb2-9d0b4ee11e4e","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}29{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}30{"parentUuid":"6c7f6cbf-7b4e-4592-9bb2-9d0b4ee11e4e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCjXZrZPtQZ4jrZjKu","type":"message","role":"assistant","content":[{"type":"text","text":"Now the analysis script (includes the design audit, a naive i.i.d. baseline, and the main simulation)."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2529,"cache_read_input_tokens":9753,"output_tokens":4092,"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":2529},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtCjFCZMPo9ThoDNZYf","requestRef":"6c217e2a-18d0-4581-9f81-57cc920c1ec8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"53ea0ace-0914-4557-b459-e0be0e8d2cc6","timestamp":"2026-10-30T05:39:10.604Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"53ea0ace-0914-4557-b459-e0be0e8d2cc6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtCjXZrZPtQZ4jrZjKu","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01L9wMkdt2xevpsGRBmjwBCd","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild cluster bootstrap-t CIs for a mean.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nRandom numbers: per cell numpy default_rng(seed from design.csv); draw order per cell:\n  u = sqrt(icc)*N(0,1) of shape (R,G); e = sqrt(1-icc)*N(0,1) of shape (R,N);\n  Rademacher weights W = 2*integers(0,2,(R,B,G))-1.\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nOUT = os.path.join(ROOT, \"out\")\ndesign = pd.read_csv(os.path.join(ROOT, \"data\", \"design.csv\"))\nn_raw = len(design)\n\n# ---------------- design audit ----------------\ndata_issues = []\ncells = []\nfor _, row in design.iterrows():\n    sizes = np.array([int(s) for s in str(row[\"cluster_sizes\"]).split(\"|\")])\n    assert len(sizes) == row[\"G\"], f\"{row.cell_id}: len(cluster_sizes) != G\"\n    assert sizes.sum() == row[\"N\"], f\"{row.cell_id}: sum(cluster_sizes) != N\"\n    assert int(row[\"R\"]) == 2000 and int(row[\"B\"]) == 399\n    cells.append(dict(cell_id=row[\"cell_id\"], G=int(row[\"G\"]), icc=float(row[\"icc\"]), sizes=sizes,\n                      N=int(row[\"N\"]), R=int(row[\"R\"]), B=int(row[\"B\"]), seed=int(row[\"seed\"]),\n                      mu=float(row[\"mu\"]), level=float(row[\"nominal_level\"])))\nassert design[\"cell_id\"].is_unique and not design.isna().any().any()\nif (design[\"G\"] == 5).any():\n    data_issues.append({\n        \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n        \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"})\n\n# exclusion ledger: nothing is excluded\npd.DataFrame([{\"step\": 1, \"rule\": \"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",\n               \"n_before\": n_raw, \"n_after\": n_raw, \"n_removed\": 0,\n               \"rationale\": \"all 9 cells consistent; no filtering\"}]).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\ndef key(est, c):\n    return f\"{est}_G{c['G']}_icc{c['icc']:.1f}\"\n\nCHUNK = 250\nrows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nfor c in cells:\n    G, N, R, B, icc, mu, sizes = c[\"G\"], c[\"N\"], c[\"R\"], c[\"B\"], c[\"icc\"], c[\"mu\"], c[\"sizes\"]\n    rng = np.random.default_rng(c[\"seed\"])\n    gid = np.repeat(np.arange(G), sizes)\n    u = np.sqrt(icc) * rng.standard_normal((R, G))\n    e = np.sqrt(1 - icc) * rng.standard_normal((R, N))\n    W = 2 * rng.integers(0, 2, size=(R, B, G)) - 1\n    y = mu + u[:, gid] + e\n    ybar = y.mean(axis=1)\n    resid = y - ybar[:, None]\n    S = np.zeros((R, G))\n    for g in range(G):\n        S[:, g] = resid[:, gid == g].sum(axis=1)       # cluster residual sums\n    V0 = (S ** 2).sum(axis=1) / N ** 2\n    V1 = G / (G - 1) * V0\n    var_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n    z = stats.norm.ppf(0.5 + c[\"level\"] / 2)               # 1.959964\n    tcrit = stats.t.ppf(0.5 + c[\"level\"] / 2, G - 1)\n    # wild cluster bootstrap-t: y* = ybar + w_g * resid; cluster sums of y*-ybar* are w_g S_g - n_g D\n    q = np.empty(R)\n    for s in range(0, R, CHUNK):\n        Wc, Sc = W[s:s + CHUNK].astype(float), S[s:s + CHUNK]\n        WS = Wc * Sc[:, None, :]                            # (r,B,G)\n        D = WS.sum(axis=2) / N                              # ybar* - ybar\n        Sstar = WS - sizes[None, None, :] * D[:, :, None]\n        V1s = G / (G - 1) * (Sstar ** 2).sum(axis=2) / N ** 2\n        with np.errstate(divide=\"ignore\", invalid=\"ignore\"):\n            tstar = np.abs(D / np.sqrt(V1s))\n        tstar = np.where(np.isfinite(tstar), tstar, 0.0)    # D=0 & V1s=0 cannot co-occur with positive V; guard only\n        # 0.95 empirical quantile = inverted-CDF definition: the ceil(0.95*B)=380th order statistic\n        q[s:s + CHUNK] = np.quantile(tstar, c[\"level\"], axis=1, method=\"inverted_cdf\")\n    # naive i.i.d. baseline (ignores clustering)\n    s2 = resid.var(axis=1, ddof=1)\n    Viid = s2 / N\n    hw = {\"cr0\": z * np.sqrt(V0), \"cr1\": tcrit * np.sqrt(V1), \"wcb\": q * np.sqrt(V1),\n          \"iid\": z * np.sqrt(Viid)}\n    err = np.abs(ybar - mu)\n    for est in [\"cr0\", \"cr1\", \"wcb\", \"iid\"]:\n        p = float(np.mean(err <= hw[est]))\n        se = float(np.sqrt(p * (1 - p) / R))\n        if est == \"iid\":\n            base_cov[key(\"iid\", c)] = p\n            continue\n        k = key(est, c)\n        coverage[k], mcse[k] = p, se\n        rb = None\n        if est in (\"cr0\", \"cr1\"):\n            rb = float(np.mean(V0 if est == \"cr0\" else V1) / var_exact)\n            relbias[k] = rb\n        rows.append(dict(estimator=est, cell_id=c[\"cell_id\"], G=G, icc=icc, coverage=p, mc_se_coverage=se,\n                         rel_bias_var=rb, mean_ci_halfwidth=float(hw[est].mean()), R=R))\n    print(f\"{c['cell_id']} G={G} icc={icc}: \" + \", \".join(f\"{k2}={coverage[key(k2, c)]:.4f}\" for k2 in [\"cr0\", \"cr1\", \"wcb\"]))\n\ntable = pd.DataFrame(rows)\ntable[\"_o\"] = table[\"estimator\"].map({\"cr0\": 0, \"cr1\": 1, \"wcb\": 2})\ntable = table.sort_values([\"_o\", \"G\", \"icc\"]).drop(columns=\"_o\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nfailure = sorted(k for k, p in coverage.items() if p < 0.90)\nnominal = sorted(k for k, p in coverage.items() if abs(p - 0.95) <= 2 * mcse[k])\nsmall = {est: np.mean([coverage[key(est, c)] for c in cells if c[\"G\"] == 5]) for est in [\"cr0\", \"cr1\", \"wcb\"]}\nbest_small = max(small, key=small.get)\n\nresults = {\n    \"task_id\": \"T2-simulation\",\n    \"R\": int(cells[0][\"R\"]), \"B\": int(cells[0][\"B\"]), \"n_cells\": len(cells),\n    \"coverage\": coverage, \"mc_se_coverage\": mcse, \"rel_bias_var\": relbias,\n    \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n    \"best_procedure_small_G\": best_small,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": {\"design.csv\": n_raw},\n    \"n_analysed\": int(sum(c[\"R\"] for c in cells)),\n    \"random_seed\": int(cells[0][\"seed\"]),\n    \"baseline_coverage_iid\": base_cov,\n    \"mean_coverage_small_G\": {k: float(v) for k, v in small.items()},\n    \"exact_var_ybar\": {f\"G{c['G']}_icc{c['icc']:.1f}\": float((c['icc'] * (c['sizes'] ** 2).sum() + (1 - c['icc']) * c['N']) / c['N'] ** 2) for c in cells},\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n    json.dump(results, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\nGs = sorted({c[\"G\"] for c in cells})\nfor ax, icc in zip(axes, [0.0, 0.2, 0.5]):\n    for est, mk in [(\"cr0\", \"o\"), (\"cr1\", \"s\"), (\"wcb\", \"^\"), (\"iid\", \"x\")]:\n        src = base_cov if est == \"iid\" else coverage\n        p = np.array([src[f\"{est}_G{G}_icc{icc:.1f}\"] for G in Gs])\n        se = np.sqrt(p * (1 - p) / 2000)\n        ax.errorbar(Gs, p, yerr=2 * se, marker=mk, capsize=3,\n                    label=est.upper() + (\" (naive baseline)\" if est == \"iid\" else \"\"),\n                    linestyle=\":\" if est == \"iid\" else \"-\")\n    ax.axhline(0.95, color=\"k\", lw=1, label=\"nominal 0.95\")\n    ax.axhline(0.90, color=\"r\", lw=1, ls=\"--\", label=\"failure line 0.90\")\n    ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels(Gs)\n    ax.set_title(f\"ICC = {icc}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±2 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(\"Coverage of nominal 95% intervals for the mean (R=2000 per cell)\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best_small)\nEOF\ntime ~/wp29/venv/bin/python out/analysis.py","description":"Write and run the simulation script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2529,"cache_read_input_tokens":9753,"output_tokens":4092,"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":2529},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtCjFCZMPo9ThoDNZYf","requestRef":"6c217e2a-18d0-4581-9f81-57cc920c1ec8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"540a51e6-f583-47dd-9d66-e2ccef08ce2c","timestamp":"2026-10-30T05:39:39.939Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"540a51e6-f583-47dd-9d66-e2ccef08ce2c","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.5/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RT0021/out/state/out/analysis.py': [Errno 2] No such file or directory\n~/wp29/venv/bin/python out/analysis.py  0,01s user 0,00s system 87% cpu 0,021 total","is_error":true,"tool_use_id":"toolu_01L9wMkdt2xevpsGRBmjwBCd"}]},"uuid":"24eddfa5-9766-49a1-9288-4694a5997b52","timestamp":"2026-10-30T05:39:40.003Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.5/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RT0021/out/state/out/analysis.py': [Errno 2] No such file or directory\n~/wp29/venv/bin/python out/analysis.py  0,01s user 0,00s system 87% cpu 0,021 total","sandboxed":false,"sourceToolAssistantUUID":"540a51e6-f583-47dd-9d66-e2ccef08ce2c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"e487e58212309cd7d9f21e1d3b28ee442e685e4479983af3362bc2264dc6715b","message":{"role":"assistant","content":[{"type":"text","text":"Now the analysis script (includes the design audit, a naive i.i.d. baseline, and the main simulation)."},{"type":"tool_use","id":"toolu_01L9wMkdt2xevpsGRBmjwBCd","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild cluster bootstrap-t CIs for a mean.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nRandom numbers: per cell numpy default_rng(seed from design.csv); draw order per cell:\n  u = sqrt(icc)*N(0,1) of shape (R,G); e = sqrt(1-icc)*N(0,1) of shape (R,N);\n  Rademacher weights W = 2*integers(0,2,(R,B,G))-1.\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nOUT = os.path.join(ROOT, \"out\")\ndesign = pd.read_csv(os.path.join(ROOT, \"data\", \"design.csv\"))\nn_raw = len(design)\n\n# ---------------- design audit ----------------\ndata_issues = []\ncells = []\nfor _, row in design.iterrows():\n    sizes = np.array([int(s) for s in str(row[\"cluster_sizes\"]).split(\"|\")])\n    assert len(sizes) == row[\"G\"], f\"{row.cell_id}: len(cluster_sizes) != G\"\n    assert sizes.sum() == row[\"N\"], f\"{row.cell_id}: sum(cluster_sizes) != N\"\n    assert int(row[\"R\"]) == 2000 and int(row[\"B\"]) == 399\n    cells.append(dict(cell_id=row[\"cell_id\"], G=int(row[\"G\"]), icc=float(row[\"icc\"]), sizes=sizes,\n                      N=int(row[\"N\"]), R=int(row[\"R\"]), B=int(row[\"B\"]), seed=int(row[\"seed\"]),\n                      mu=float(row[\"mu\"]), level=float(row[\"nominal_level\"])))\nassert design[\"cell_id\"].is_unique and not design.isna().any().any()\nif (design[\"G\"] == 5).any():\n    data_issues.append({\n        \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n        \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"})\n\n# exclusion ledger: nothing is excluded\npd.DataFrame([{\"step\": 1, \"rule\": \"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",\n               \"n_before\": n_raw, \"n_after\": n_raw, \"n_removed\": 0,\n               \"rationale\": \"all 9 cells consistent; no filtering\"}]).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\ndef key(est, c):\n    return f\"{est}_G{c['G']}_icc{c['icc']:.1f}\"\n\nCHUNK = 250\nrows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nfor c in cells:\n    G, N, R, B, icc, mu, sizes = c[\"G\"], c[\"N\"], c[\"R\"], c[\"B\"], c[\"icc\"], c[\"mu\"], c[\"sizes\"]\n    rng = np.random.default_rng(c[\"seed\"])\n    gid = np.repeat(np.arange(G), sizes)\n    u = np.sqrt(icc) * rng.standard_normal((R, G))\n    e = np.sqrt(1 - icc) * rng.standard_normal((R, N))\n    W = 2 * rng.integers(0, 2, size=(R, B, G)) - 1\n    y = mu + u[:, gid] + e\n    ybar = y.mean(axis=1)\n    resid = y - ybar[:, None]\n    S = np.zeros((R, G))\n    for g in range(G):\n        S[:, g] = resid[:, gid == g].sum(axis=1)       # cluster residual sums\n    V0 = (S ** 2).sum(axis=1) / N ** 2\n    V1 = G / (G - 1) * V0\n    var_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n    z = stats.norm.ppf(0.5 + c[\"level\"] / 2)               # 1.959964\n    tcrit = stats.t.ppf(0.5 + c[\"level\"] / 2, G - 1)\n    # wild cluster bootstrap-t: y* = ybar + w_g * resid; cluster sums of y*-ybar* are w_g S_g - n_g D\n    q = np.empty(R)\n    for s in range(0, R, CHUNK):\n        Wc, Sc = W[s:s + CHUNK].astype(float), S[s:s + CHUNK]\n        WS = Wc * Sc[:, None, :]                            # (r,B,G)\n        D = WS.sum(axis=2) / N                              # ybar* - ybar\n        Sstar = WS - sizes[None, None, :] * D[:, :, None]\n        V1s = G / (G - 1) * (Sstar ** 2).sum(axis=2) / N ** 2\n        with np.errstate(divide=\"ignore\", invalid=\"ignore\"):\n            tstar = np.abs(D / np.sqrt(V1s))\n        tstar = np.where(np.isfinite(tstar), tstar, 0.0)    # D=0 & V1s=0 cannot co-occur with positive V; guard only\n        # 0.95 empirical quantile = inverted-CDF definition: the ceil(0.95*B)=380th order statistic\n        q[s:s + CHUNK] = np.quantile(tstar, c[\"level\"], axis=1, method=\"inverted_cdf\")\n    # naive i.i.d. baseline (ignores clustering)\n    s2 = resid.var(axis=1, ddof=1)\n    Viid = s2 / N\n    hw = {\"cr0\": z * np.sqrt(V0), \"cr1\": tcrit * np.sqrt(V1), \"wcb\": q * np.sqrt(V1),\n          \"iid\": z * np.sqrt(Viid)}\n    err = np.abs(ybar - mu)\n    for est in [\"cr0\", \"cr1\", \"wcb\", \"iid\"]:\n        p = float(np.mean(err <= hw[est]))\n        se = float(np.sqrt(p * (1 - p) / R))\n        if est == \"iid\":\n            base_cov[key(\"iid\", c)] = p\n            continue\n        k = key(est, c)\n        coverage[k], mcse[k] = p, se\n        rb = None\n        if est in (\"cr0\", \"cr1\"):\n            rb = float(np.mean(V0 if est == \"cr0\" else V1) / var_exact)\n            relbias[k] = rb\n        rows.append(dict(estimator=est, cell_id=c[\"cell_id\"], G=G, icc=icc, coverage=p, mc_se_coverage=se,\n                         rel_bias_var=rb, mean_ci_halfwidth=float(hw[est].mean()), R=R))\n    print(f\"{c['cell_id']} G={G} icc={icc}: \" + \", \".join(f\"{k2}={coverage[key(k2, c)]:.4f}\" for k2 in [\"cr0\", \"cr1\", \"wcb\"]))\n\ntable = pd.DataFrame(rows)\ntable[\"_o\"] = table[\"estimator\"].map({\"cr0\": 0, \"cr1\": 1, \"wcb\": 2})\ntable = table.sort_values([\"_o\", \"G\", \"icc\"]).drop(columns=\"_o\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nfailure = sorted(k for k, p in coverage.items() if p < 0.90)\nnominal = sorted(k for k, p in coverage.items() if abs(p - 0.95) <= 2 * mcse[k])\nsmall = {est: np.mean([coverage[key(est, c)] for c in cells if c[\"G\"] == 5]) for est in [\"cr0\", \"cr1\", \"wcb\"]}\nbest_small = max(small, key=small.get)\n\nresults = {\n    \"task_id\": \"T2-simulation\",\n    \"R\": int(cells[0][\"R\"]), \"B\": int(cells[0][\"B\"]), \"n_cells\": len(cells),\n    \"coverage\": coverage, \"mc_se_coverage\": mcse, \"rel_bias_var\": relbias,\n    \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n    \"best_procedure_small_G\": best_small,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": {\"design.csv\": n_raw},\n    \"n_analysed\": int(sum(c[\"R\"] for c in cells)),\n    \"random_seed\": int(cells[0][\"seed\"]),\n    \"baseline_coverage_iid\": base_cov,\n    \"mean_coverage_small_G\": {k: float(v) for k, v in small.items()},\n    \"exact_var_ybar\": {f\"G{c['G']}_icc{c['icc']:.1f}\": float((c['icc'] * (c['sizes'] ** 2).sum() + (1 - c['icc']) * c['N']) / c['N'] ** 2) for c in cells},\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n    json.dump(results, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\nGs = sorted({c[\"G\"] for c in cells})\nfor ax, icc in zip(axes, [0.0, 0.2, 0.5]):\n    for est, mk in [(\"cr0\", \"o\"), (\"cr1\", \"s\"), (\"wcb\", \"^\"), (\"iid\", \"x\")]:\n        src = base_cov if est == \"iid\" else coverage\n        p = np.array([src[f\"{est}_G{G}_icc{icc:.1f}\"] for G in Gs])\n        se = np.sqrt(p * (1 - p) / 2000)\n        ax.errorbar(Gs, p, yerr=2 * se, marker=mk, capsize=3,\n                    label=est.upper() + (\" (naive baseline)\" if est == \"iid\" else \"\"),\n                    linestyle=\":\" if est == \"iid\" else \"-\")\n    ax.axhline(0.95, color=\"k\", lw=1, label=\"nominal 0.95\")\n    ax.axhline(0.90, color=\"r\", lw=1, ls=\"--\", label=\"failure line 0.90\")\n    ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels(Gs)\n    ax.set_title(f\"ICC = {icc}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±2 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(\"Coverage of nominal 95% intervals for the mean (R=2000 per cell)\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best_small)\nEOF\ntime ~/wp29/venv/bin/python out/analysis.py","description":"Write and run the simulation script"}}]}}34{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"b4c34731-f177-4fc6-8e5b-a2620e3d1522","timestamp":"2026-10-30T05:39:40.007Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"6c217e2a-18d0-4581-9f81-57cc920c1ec8","keep":8,"tail":["e487e58212309cd7d9f21e1d3b28ee442e685e4479983af3362bc2264dc6715b","7ad07b60a4ff61fdacdc1a82943f45f110c80655350b2eb9c431b94ea7df93ab"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9084fba7ab7817a464d42ecada39da3e4e6b64e33559d4c6ede65837a88eb682"}35{"parentUuid":"24eddfa5-9766-49a1-9288-4694a5997b52","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEzJrh4M5iPf2ez45J","type":"message","role":"assistant","content":[{"type":"text","text":"The shell was still in out/state; rerunning from the workspace root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4299,"cache_read_input_tokens":12282,"output_tokens":140,"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":4299},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtEz315mEzryxzdGmfZ","requestRef":"b4c34731-f177-4fc6-8e5b-a2620e3d1522","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"396f7645-25ee-4de0-8c54-dbdba8f14f23","timestamp":"2026-10-30T05:39:41.512Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"396f7645-25ee-4de0-8c54-dbdba8f14f23","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtEzJrh4M5iPf2ez45J","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017SxYLyRBmGU8cqrMx79qN8","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0021 && ls out/state && echo \"(re-issue)\"","description":"Return to workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4299,"cache_read_input_tokens":12282,"output_tokens":140,"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":4299},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtEz315mEzryxzdGmfZ","requestRef":"b4c34731-f177-4fc6-8e5b-a2620e3d1522","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5b337940-2913-4ba8-800d-3f2b6692c660","timestamp":"2026-10-30T05:39:42.249Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"5b337940-2913-4ba8-800d-3f2b6692c660","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017SxYLyRBmGU8cqrMx79qN8","type":"tool_result","content":"contract.md\nlog.md\nphases.json\n(re-issue)","is_error":false}]},"uuid":"46fd1e08-4b20-4160-abd0-d76e6a89eb90","timestamp":"2026-10-30T05:39:42.287Z","toolUseResult":{"stdout":"contract.md\nlog.md\nphases.json\n(re-issue)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5b337940-2913-4ba8-800d-3f2b6692c660","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"58fb27ed96b460616336f8ceefbfadcc6a511a9422077ead2865a3cbc1da3ed5","message":{"role":"assistant","content":[{"type":"text","text":"The shell was still in out/state; rerunning from the workspace root."},{"type":"tool_use","id":"toolu_017SxYLyRBmGU8cqrMx79qN8","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0021 && ls out/state && echo \"(re-issue)\"","description":"Return to workspace root"}}]}}39{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"37a6ec94-5481-49a7-afbd-0811c473fe69","timestamp":"2026-10-30T05:39:42.290Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"b4c34731-f177-4fc6-8e5b-a2620e3d1522","keep":10,"tail":["58fb27ed96b460616336f8ceefbfadcc6a511a9422077ead2865a3cbc1da3ed5","2bc562302eab5da196bd7d794be162e0f50307c405379704c513dc31642f64a3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"80397a20b08603dfb18e71fcd57ffb8371eaa16a1030cc0a08bf01d6af854ebb"}40{"parentUuid":"46fd1e08-4b20-4160-abd0-d76e6a89eb90","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFA3FsZKyUFVR2S2cg","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":165,"cache_read_input_tokens":16581,"output_tokens":4105,"output_tokens_details":{"thinking_tokens":26},"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":165},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":351,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtF9mdbMRu4xa4ANpCD","requestRef":"37a6ec94-5481-49a7-afbd-0811c473fe69","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9e6ad154-9eba-4aaf-8cb7-10a31d221920","timestamp":"2026-10-30T05:39:43.779Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"9e6ad154-9eba-4aaf-8cb7-10a31d221920","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtFA3FsZKyUFVR2S2cg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KTY3gJGX8rVFP76JMpCDF2","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild cluster bootstrap-t CIs for a mean.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nRandom numbers: per cell numpy default_rng(seed from design.csv); draw order per cell:\n  u = sqrt(icc)*N(0,1) of shape (R,G); e = sqrt(1-icc)*N(0,1) of shape (R,N);\n  Rademacher weights W = 2*integers(0,2,(R,B,G))-1.\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nOUT = os.path.join(ROOT, \"out\")\ndesign = pd.read_csv(os.path.join(ROOT, \"data\", \"design.csv\"))\nn_raw = len(design)\n\n# ---------------- design audit ----------------\ndata_issues = []\ncells = []\nfor _, row in design.iterrows():\n    sizes = np.array([int(s) for s in str(row[\"cluster_sizes\"]).split(\"|\")])\n    assert len(sizes) == row[\"G\"], f\"{row.cell_id}: len(cluster_sizes) != G\"\n    assert sizes.sum() == row[\"N\"], f\"{row.cell_id}: sum(cluster_sizes) != N\"\n    assert int(row[\"R\"]) == 2000 and int(row[\"B\"]) == 399\n    cells.append(dict(cell_id=row[\"cell_id\"], G=int(row[\"G\"]), icc=float(row[\"icc\"]), sizes=sizes,\n                      N=int(row[\"N\"]), R=int(row[\"R\"]), B=int(row[\"B\"]), seed=int(row[\"seed\"]),\n                      mu=float(row[\"mu\"]), level=float(row[\"nominal_level\"])))\nassert design[\"cell_id\"].is_unique and not design.isna().any().any()\nif (design[\"G\"] == 5).any():\n    data_issues.append({\n        \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n        \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"})\n\n# exclusion ledger: nothing is excluded\npd.DataFrame([{\"step\": 1, \"rule\": \"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",\n               \"n_before\": n_raw, \"n_after\": n_raw, \"n_removed\": 0,\n               \"rationale\": \"all 9 cells consistent; no filtering\"}]).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\ndef key(est, c):\n    return f\"{est}_G{c['G']}_icc{c['icc']:.1f}\"\n\nCHUNK = 250\nrows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nfor c in cells:\n    G, N, R, B, icc, mu, sizes = c[\"G\"], c[\"N\"], c[\"R\"], c[\"B\"], c[\"icc\"], c[\"mu\"], c[\"sizes\"]\n    rng = np.random.default_rng(c[\"seed\"])\n    gid = np.repeat(np.arange(G), sizes)\n    u = np.sqrt(icc) * rng.standard_normal((R, G))\n    e = np.sqrt(1 - icc) * rng.standard_normal((R, N))\n    W = 2 * rng.integers(0, 2, size=(R, B, G)) - 1\n    y = mu + u[:, gid] + e\n    ybar = y.mean(axis=1)\n    resid = y - ybar[:, None]\n    S = np.zeros((R, G))\n    for g in range(G):\n        S[:, g] = resid[:, gid == g].sum(axis=1)       # cluster residual sums\n    V0 = (S ** 2).sum(axis=1) / N ** 2\n    V1 = G / (G - 1) * V0\n    var_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n    z = 1.96                                               # as specified in TASK.md\n    tcrit = stats.t.ppf(0.5 + c[\"level\"] / 2, G - 1)\n    # wild cluster bootstrap-t: y* = ybar + w_g * resid; cluster sums of y*-ybar* are w_g S_g - n_g D\n    q = np.empty(R)\n    for s in range(0, R, CHUNK):\n        Wc, Sc = W[s:s + CHUNK].astype(float), S[s:s + CHUNK]\n        WS = Wc * Sc[:, None, :]                            # (r,B,G)\n        D = WS.sum(axis=2) / N                              # ybar* - ybar\n        Sstar = WS - sizes[None, None, :] * D[:, :, None]\n        V1s = G / (G - 1) * (Sstar ** 2).sum(axis=2) / N ** 2\n        with np.errstate(divide=\"ignore\", invalid=\"ignore\"):\n            tstar = np.abs(D / np.sqrt(V1s))\n        tstar = np.where(np.isfinite(tstar), tstar, 0.0)    # guard only (0/0 does not occur with continuous data)\n        # 0.95 empirical quantile = inverted-CDF definition: the ceil(0.95*B)=380th order statistic\n        q[s:s + CHUNK] = np.quantile(tstar, c[\"level\"], axis=1, method=\"inverted_cdf\")\n    # naive i.i.d. baseline (ignores clustering)\n    s2 = resid.var(axis=1, ddof=1)\n    Viid = s2 / N\n    hw = {\"cr0\": z * np.sqrt(V0), \"cr1\": tcrit * np.sqrt(V1), \"wcb\": q * np.sqrt(V1),\n          \"iid\": z * np.sqrt(Viid)}\n    err = np.abs(ybar - mu)\n    for est in [\"cr0\", \"cr1\", \"wcb\", \"iid\"]:\n        p = float(np.mean(err <= hw[est]))\n        se = float(np.sqrt(p * (1 - p) / R))\n        if est == \"iid\":\n            base_cov[key(\"iid\", c)] = p\n            continue\n        k = key(est, c)\n        coverage[k], mcse[k] = p, se\n        rb = None\n        if est in (\"cr0\", \"cr1\"):\n            rb = float(np.mean(V0 if est == \"cr0\" else V1) / var_exact)\n            relbias[k] = rb\n        rows.append(dict(estimator=est, cell_id=c[\"cell_id\"], G=G, icc=icc, coverage=p, mc_se_coverage=se,\n                         rel_bias_var=rb, mean_ci_halfwidth=float(hw[est].mean()), R=R))\n    print(f\"{c['cell_id']} G={G} icc={icc}: \" + \", \".join(f\"{k2}={coverage[key(k2, c)]:.4f}\" for k2 in [\"cr0\", \"cr1\", \"wcb\"])\n          + f\", iid={base_cov[key('iid', c)]:.4f}\")\n\ntable = pd.DataFrame(rows)\ntable[\"_o\"] = table[\"estimator\"].map({\"cr0\": 0, \"cr1\": 1, \"wcb\": 2})\ntable = table.sort_values([\"_o\", \"G\", \"icc\"]).drop(columns=\"_o\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nfailure = sorted(k for k, p in coverage.items() if p < 0.90)\nnominal = sorted(k for k, p in coverage.items() if abs(p - 0.95) <= 2 * mcse[k])\nsmall = {est: float(np.mean([coverage[key(est, c)] for c in cells if c[\"G\"] == 5])) for est in [\"cr0\", \"cr1\", \"wcb\"]}\nbest_small = max(small, key=small.get)\n\nresults = {\n    \"task_id\": \"T2-simulation\",\n    \"R\": int(cells[0][\"R\"]), \"B\": int(cells[0][\"B\"]), \"n_cells\": len(cells),\n    \"coverage\": coverage, \"mc_se_coverage\": mcse, \"rel_bias_var\": relbias,\n    \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n    \"best_procedure_small_G\": best_small,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": {\"design.csv\": n_raw},\n    \"n_analysed\": int(sum(c[\"R\"] for c in cells)),\n    \"random_seed\": int(cells[0][\"seed\"]),\n    \"baseline_coverage_iid\": base_cov,\n    \"mean_coverage_small_G\": small,\n    \"exact_var_ybar\": {f\"G{c['G']}_icc{c['icc']:.1f}\": float((c['icc'] * (c['sizes'] ** 2).sum() + (1 - c['icc']) * c['N']) / c['N'] ** 2) for c in cells},\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n    json.dump(results, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\nGs = sorted({c[\"G\"] for c in cells})\nfor ax, icc in zip(axes, [0.0, 0.2, 0.5]):\n    for est, mk in [(\"cr0\", \"o\"), (\"cr1\", \"s\"), (\"wcb\", \"^\"), (\"iid\", \"x\")]:\n        src = base_cov if est == \"iid\" else coverage\n        p = np.array([src[f\"{est}_G{G}_icc{icc:.1f}\"] for G in Gs])\n        se = np.sqrt(p * (1 - p) / 2000)\n        ax.errorbar(Gs, p, yerr=2 * se, marker=mk, capsize=3,\n                    label=est.upper() + (\" (naive baseline)\" if est == \"iid\" else \"\"),\n                    linestyle=\":\" if est == \"iid\" else \"-\")\n    ax.axhline(0.95, color=\"k\", lw=1, label=\"nominal 0.95\")\n    ax.axhline(0.90, color=\"r\", lw=1, ls=\"--\", label=\"failure line 0.90\")\n    ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels(Gs)\n    ax.set_title(f\"ICC = {icc}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±2 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(\"Coverage of nominal 95% intervals for the mean (R=2000 per cell)\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best_small)\nEOF\ntime ~/wp29/venv/bin/python out/analysis.py","description":"Write and run the simulation script from root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":165,"cache_read_input_tokens":16581,"output_tokens":4105,"output_tokens_details":{"thinking_tokens":26},"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":165},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtF9mdbMRu4xa4ANpCD","requestRef":"37a6ec94-5481-49a7-afbd-0811c473fe69","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e7a4c33d-382f-4fce-8d6c-dac94c58d18b","timestamp":"2026-10-30T05:40:09.089Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}42{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e7a4c33d-382f-4fce-8d6c-dac94c58d18b","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}43{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}44{"parentUuid":"e7a4c33d-382f-4fce-8d6c-dac94c58d18b","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KTY3gJGX8rVFP76JMpCDF2","type":"tool_result","content":"C1 G=5 icc=0.0: cr0=0.7970, cr1=0.9190, wcb=0.8690, iid=0.9440\nC2 G=5 icc=0.2: cr0=0.7195, cr1=0.8815, wcb=0.8470, iid=0.4650\nC3 G=5 icc=0.5: cr0=0.7205, cr1=0.8795, wcb=0.8565, iid=0.2960\nC4 G=10 icc=0.0: cr0=0.8835, cr1=0.9395, wcb=0.9260, iid=0.9500\nC5 G=10 icc=0.2: cr0=0.8590, cr1=0.9165, wcb=0.9390, iid=0.4685\nC6 G=10 icc=0.5: cr0=0.8530, cr1=0.9170, wcb=0.9365, iid=0.3150\nC7 G=30 icc=0.0: cr0=0.9305, cr1=0.9440, wcb=0.9460, iid=0.9555\nC8 G=30 icc=0.2: cr0=0.9240, cr1=0.9400, wcb=0.9515, iid=0.4820\nC9 G=30 icc=0.5: cr0=0.9160, cr1=0.9290, wcb=0.9415, iid=0.2980\nfailure cells: ['cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5', 'cr0_G5_icc0.0', 'cr0_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.2', 'cr1_G5_icc0.5', 'wcb_G5_icc0.0', 'wcb_G5_icc0.2', 'wcb_G5_icc0.5']\nbest procedure at G=5: cr1\n~/wp29/venv/bin/python out/analysis.py  1,69s user 0,14s system 99% cpu 1,840 total","is_error":false}]},"uuid":"c938a679-8d11-44f5-93fa-310ee0b58fa0","timestamp":"2026-10-30T05:40:10.970Z","toolUseResult":{"stdout":"C1 G=5 icc=0.0: cr0=0.7970, cr1=0.9190, wcb=0.8690, iid=0.9440\nC2 G=5 icc=0.2: cr0=0.7195, cr1=0.8815, wcb=0.8470, iid=0.4650\nC3 G=5 icc=0.5: cr0=0.7205, cr1=0.8795, wcb=0.8565, iid=0.2960\nC4 G=10 icc=0.0: cr0=0.8835, cr1=0.9395, wcb=0.9260, iid=0.9500\nC5 G=10 icc=0.2: cr0=0.8590, cr1=0.9165, wcb=0.9390, iid=0.4685\nC6 G=10 icc=0.5: cr0=0.8530, cr1=0.9170, wcb=0.9365, iid=0.3150\nC7 G=30 icc=0.0: cr0=0.9305, cr1=0.9440, wcb=0.9460, iid=0.9555\nC8 G=30 icc=0.2: cr0=0.9240, cr1=0.9400, wcb=0.9515, iid=0.4820\nC9 G=30 icc=0.5: cr0=0.9160, cr1=0.9290, wcb=0.9415, iid=0.2980\nfailure cells: ['cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5', 'cr0_G5_icc0.0', 'cr0_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.2', 'cr1_G5_icc0.5', 'wcb_G5_icc0.0', 'wcb_G5_icc0.2', 'wcb_G5_icc0.5']\nbest procedure at G=5: cr1\n~/wp29/venv/bin/python out/analysis.py  1,69s user 0,14s system 99% cpu 1,840 total","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e7a4c33d-382f-4fce-8d6c-dac94c58d18b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}45{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"bbfcaa417d42a6cfd142ff039be914ddf080aea351aa8087c8f4dda80d5f088b","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KTY3gJGX8rVFP76JMpCDF2","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild cluster bootstrap-t CIs for a mean.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nRandom numbers: per cell numpy default_rng(seed from design.csv); draw order per cell:\n  u = sqrt(icc)*N(0,1) of shape (R,G); e = sqrt(1-icc)*N(0,1) of shape (R,N);\n  Rademacher weights W = 2*integers(0,2,(R,B,G))-1.\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nOUT = os.path.join(ROOT, \"out\")\ndesign = pd.read_csv(os.path.join(ROOT, \"data\", \"design.csv\"))\nn_raw = len(design)\n\n# ---------------- design audit ----------------\ndata_issues = []\ncells = []\nfor _, row in design.iterrows():\n    sizes = np.array([int(s) for s in str(row[\"cluster_sizes\"]).split(\"|\")])\n    assert len(sizes) == row[\"G\"], f\"{row.cell_id}: len(cluster_sizes) != G\"\n    assert sizes.sum() == row[\"N\"], f\"{row.cell_id}: sum(cluster_sizes) != N\"\n    assert int(row[\"R\"]) == 2000 and int(row[\"B\"]) == 399\n    cells.append(dict(cell_id=row[\"cell_id\"], G=int(row[\"G\"]), icc=float(row[\"icc\"]), sizes=sizes,\n                      N=int(row[\"N\"]), R=int(row[\"R\"]), B=int(row[\"B\"]), seed=int(row[\"seed\"]),\n                      mu=float(row[\"mu\"]), level=float(row[\"nominal_level\"])))\nassert design[\"cell_id\"].is_unique and not design.isna().any().any()\nif (design[\"G\"] == 5).any():\n    data_issues.append({\n        \"issue\": \"With G=5 Rademacher weights take only 2^5=32 distinct values (16 distinct |t*| up to sign symmetry, two of which (all weights equal) give t*=0); the B=399 bootstrap draws therefore repeat these few values and the WCB critical value is coarse.\",\n        \"handling\": \"Kept as specified (B=399 i.i.d. Rademacher draws, not full enumeration); noted as a limitation in the report.\"})\n\n# exclusion ledger: nothing is excluded\npd.DataFrame([{\"step\": 1, \"rule\": \"keep all design rows passing consistency checks (G=len(sizes), N=sum(sizes), R=2000, B=399)\",\n               \"n_before\": n_raw, \"n_after\": n_raw, \"n_removed\": 0,\n               \"rationale\": \"all 9 cells consistent; no filtering\"}]).to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\ndef key(est, c):\n    return f\"{est}_G{c['G']}_icc{c['icc']:.1f}\"\n\nCHUNK = 250\nrows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nfor c in cells:\n    G, N, R, B, icc, mu, sizes = c[\"G\"], c[\"N\"], c[\"R\"], c[\"B\"], c[\"icc\"], c[\"mu\"], c[\"sizes\"]\n    rng = np.random.default_rng(c[\"seed\"])\n    gid = np.repeat(np.arange(G), sizes)\n    u = np.sqrt(icc) * rng.standard_normal((R, G))\n    e = np.sqrt(1 - icc) * rng.standard_normal((R, N))\n    W = 2 * rng.integers(0, 2, size=(R, B, G)) - 1\n    y = mu + u[:, gid] + e\n    ybar = y.mean(axis=1)\n    resid = y - ybar[:, None]\n    S = np.zeros((R, G))\n    for g in range(G):\n        S[:, g] = resid[:, gid == g].sum(axis=1)       # cluster residual sums\n    V0 = (S ** 2).sum(axis=1) / N ** 2\n    V1 = G / (G - 1) * V0\n    var_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n    z = 1.96                                               # as specified in TASK.md\n    tcrit = stats.t.ppf(0.5 + c[\"level\"] / 2, G - 1)\n    # wild cluster bootstrap-t: y* = ybar + w_g * resid; cluster sums of y*-ybar* are w_g S_g - n_g D\n    q = np.empty(R)\n    for s in range(0, R, CHUNK):\n        Wc, Sc = W[s:s + CHUNK].astype(float), S[s:s + CHUNK]\n        WS = Wc * Sc[:, None, :]                            # (r,B,G)\n        D = WS.sum(axis=2) / N                              # ybar* - ybar\n        Sstar = WS - sizes[None, None, :] * D[:, :, None]\n        V1s = G / (G - 1) * (Sstar ** 2).sum(axis=2) / N ** 2\n        with np.errstate(divide=\"ignore\", invalid=\"ignore\"):\n            tstar = np.abs(D / np.sqrt(V1s))\n        tstar = np.where(np.isfinite(tstar), tstar, 0.0)    # guard only (0/0 does not occur with continuous data)\n        # 0.95 empirical quantile = inverted-CDF definition: the ceil(0.95*B)=380th order statistic\n        q[s:s + CHUNK] = np.quantile(tstar, c[\"level\"], axis=1, method=\"inverted_cdf\")\n    # naive i.i.d. baseline (ignores clustering)\n    s2 = resid.var(axis=1, ddof=1)\n    Viid = s2 / N\n    hw = {\"cr0\": z * np.sqrt(V0), \"cr1\": tcrit * np.sqrt(V1), \"wcb\": q * np.sqrt(V1),\n          \"iid\": z * np.sqrt(Viid)}\n    err = np.abs(ybar - mu)\n    for est in [\"cr0\", \"cr1\", \"wcb\", \"iid\"]:\n        p = float(np.mean(err <= hw[est]))\n        se = float(np.sqrt(p * (1 - p) / R))\n        if est == \"iid\":\n            base_cov[key(\"iid\", c)] = p\n            continue\n        k = key(est, c)\n        coverage[k], mcse[k] = p, se\n        rb = None\n        if est in (\"cr0\", \"cr1\"):\n            rb = float(np.mean(V0 if est == \"cr0\" else V1) / var_exact)\n            relbias[k] = rb\n        rows.append(dict(estimator=est, cell_id=c[\"cell_id\"], G=G, icc=icc, coverage=p, mc_se_coverage=se,\n                         rel_bias_var=rb, mean_ci_halfwidth=float(hw[est].mean()), R=R))\n    print(f\"{c['cell_id']} G={G} icc={icc}: \" + \", \".join(f\"{k2}={coverage[key(k2, c)]:.4f}\" for k2 in [\"cr0\", \"cr1\", \"wcb\"])\n          + f\", iid={base_cov[key('iid', c)]:.4f}\")\n\ntable = pd.DataFrame(rows)\ntable[\"_o\"] = table[\"estimator\"].map({\"cr0\": 0, \"cr1\": 1, \"wcb\": 2})\ntable = table.sort_values([\"_o\", \"G\", \"icc\"]).drop(columns=\"_o\")\ntable.to_csv(os.path.join(OUT, \"table1.csv\"), index=False, float_format=\"%.6f\")\n\nfailure = sorted(k for k, p in coverage.items() if p < 0.90)\nnominal = sorted(k for k, p in coverage.items() if abs(p - 0.95) <= 2 * mcse[k])\nsmall = {est: float(np.mean([coverage[key(est, c)] for c in cells if c[\"G\"] == 5])) for est in [\"cr0\", \"cr1\", \"wcb\"]}\nbest_small = max(small, key=small.get)\n\nresults = {\n    \"task_id\": \"T2-simulation\",\n    \"R\": int(cells[0][\"R\"]), \"B\": int(cells[0][\"B\"]), \"n_cells\": len(cells),\n    \"coverage\": coverage, \"mc_se_coverage\": mcse, \"rel_bias_var\": relbias,\n    \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n    \"best_procedure_small_G\": best_small,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": data_issues,\n    \"n_input_rows\": {\"design.csv\": n_raw},\n    \"n_analysed\": int(sum(c[\"R\"] for c in cells)),\n    \"random_seed\": int(cells[0][\"seed\"]),\n    \"baseline_coverage_iid\": base_cov,\n    \"mean_coverage_small_G\": small,\n    \"exact_var_ybar\": {f\"G{c['G']}_icc{c['icc']:.1f}\": float((c['icc'] * (c['sizes'] ** 2).sum() + (1 - c['icc']) * c['N']) / c['N'] ** 2) for c in cells},\n}\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n    json.dump(results, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\nGs = sorted({c[\"G\"] for c in cells})\nfor ax, icc in zip(axes, [0.0, 0.2, 0.5]):\n    for est, mk in [(\"cr0\", \"o\"), (\"cr1\", \"s\"), (\"wcb\", \"^\"), (\"iid\", \"x\")]:\n        src = base_cov if est == \"iid\" else coverage\n        p = np.array([src[f\"{est}_G{G}_icc{icc:.1f}\"] for G in Gs])\n        se = np.sqrt(p * (1 - p) / 2000)\n        ax.errorbar(Gs, p, yerr=2 * se, marker=mk, capsize=3,\n                    label=est.upper() + (\" (naive baseline)\" if est == \"iid\" else \"\"),\n                    linestyle=\":\" if est == \"iid\" else \"-\")\n    ax.axhline(0.95, color=\"k\", lw=1, label=\"nominal 0.95\")\n    ax.axhline(0.90, color=\"r\", lw=1, ls=\"--\", label=\"failure line 0.90\")\n    ax.set_xscale(\"log\"); ax.set_xticks(Gs); ax.set_xticklabels(Gs)\n    ax.set_title(f\"ICC = {icc}\"); ax.set_xlabel(\"number of clusters G\")\naxes[0].set_ylabel(\"coverage (±2 MC SE)\")\naxes[0].legend(fontsize=8, loc=\"lower right\")\nfig.suptitle(\"Coverage of nominal 95% intervals for the mean (R=2000 per cell)\")\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\nprint(\"failure cells:\", failure)\nprint(\"best procedure at G=5:\", best_small)\nEOF\ntime ~/wp29/venv/bin/python out/analysis.py","description":"Write and run the simulation script from root"}}]}}46{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"5d7ca76c-af44-4573-8ec4-f547b7021230","timestamp":"2026-10-30T05:40:10.974Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"37a6ec94-5481-49a7-afbd-0811c473fe69","keep":12,"tail":["bbfcaa417d42a6cfd142ff039be914ddf080aea351aa8087c8f4dda80d5f088b","35615724bc0cd1839384ae709855eb1f7b10621c9b13242deeab980eccb656c0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"df4ebfa9bbcec39b634871fa6f88832e490d704463a418699a0fa23303fbe782"}47{"parentUuid":"c938a679-8d11-44f5-93fa-310ee0b58fa0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHGhA6d7g88ePfbUXd","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":4750,"cache_read_input_tokens":16746,"output_tokens":830,"output_tokens_details":{"thinking_tokens":145},"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":4750},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1218,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtHGQHwhv3vpJcUjpJP","requestRef":"5d7ca76c-af44-4573-8ec4-f547b7021230","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"850a5791-5bd5-4d48-ac18-3874ea7ae128","timestamp":"2026-10-30T05:40:13.581Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"850a5791-5bd5-4d48-ac18-3874ea7ae128","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHGhA6d7g88ePfbUXd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013L61LNMXGoq6BSjtyAuyCz","name":"Bash","input":{"command":"cat out/table1.csv; python3 -c \"import json;d=json.load(open('out/results.json'));print(d['nominal_cells'],d['mean_coverage_small_G'])\"\ncat > /tmp/xcheck.py <<'EOF'\n# Independent naive re-implementation for cell C2, first 50 replications, same draw order\nimport numpy as np, pandas as pd\nfrom scipy import stats\nd=pd.read_csv('data/design.csv'); r=d.iloc[1]\nsizes=np.array([int(s) for s in r.cluster_sizes.split('|')]); G=len(sizes); N=sizes.sum(); R,B=2000,399; icc=r.icc\nrng=np.random.default_rng(int(r.seed))\nu=np.sqrt(icc)*rng.standard_normal((R,G)); e=np.sqrt(1-icc)*rng.standard_normal((R,N)); W=2*rng.integers(0,2,size=(R,B,G))-1\ngid=np.repeat(np.arange(G),sizes)\ndef crv(y):\n    yb=y.mean(); res=y-yb\n    return yb, G/(G-1)*sum(res[gid==g].sum()**2 for g in range(G))/N**2\nqs=[]\nfor rep in range(50):\n    y=u[rep,gid]+e[rep]; yb,V1=crv(y); res=y-yb\n    t=[]\n    for b in range(B):\n        ys=yb+W[rep,b,gid]*res; ybs,V1s=crv(ys); t.append(abs(ybs-yb)/np.sqrt(V1s))\n    qs.append(np.sort(t)[379])\nprint(np.round(qs[:10],5))\nEOF\n~/wp29/venv/bin/python /tmp/xcheck.py","description":"Show table and run independent bootstrap check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4750,"cache_read_input_tokens":16746,"output_tokens":830,"output_tokens_details":{"thinking_tokens":145},"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":4750},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtHGQHwhv3vpJcUjpJP","requestRef":"5d7ca76c-af44-4573-8ec4-f547b7021230","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cdf92152-a950-48ed-85b6-2519dcdf74da","timestamp":"2026-10-30T05:40:18.535Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"cdf92152-a950-48ed-85b6-2519dcdf74da","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013L61LNMXGoq6BSjtyAuyCz","type":"tool_result","content":"estimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.000000,0.797000,0.008994,0.653105,0.129219,2000\ncr0,C2,5,0.200000,0.719500,0.010045,0.507338,0.336360,2000\ncr0,C3,5,0.500000,0.720500,0.010034,0.505404,0.509842,2000\ncr0,C4,10,0.000000,0.883500,0.007174,0.845792,0.106538,2000\ncr0,C5,10,0.200000,0.859000,0.007782,0.759525,0.300190,2000\ncr0,C6,10,0.500000,0.853000,0.007918,0.766830,0.458667,2000\ncr0,C7,30,0.000000,0.930500,0.005686,0.934972,0.063658,2000\ncr0,C8,30,0.200000,0.924000,0.005926,0.918508,0.194818,2000\ncr0,C9,30,0.500000,0.916000,0.006203,0.915377,0.298167,2000\ncr1,C1,5,0.000000,0.919000,0.006101,0.816381,0.204651,2000\ncr1,C2,5,0.200000,0.881500,0.007227,0.634173,0.532712,2000\ncr1,C3,5,0.500000,0.879500,0.007279,0.631755,0.807465,2000\ncr1,C4,10,0.000000,0.939500,0.005331,0.939769,0.129613,2000\ncr1,C5,10,0.200000,0.916500,0.006186,0.843917,0.365209,2000\ncr1,C6,10,0.500000,0.917000,0.006169,0.852034,0.558011,2000\ncr1,C7,30,0.000000,0.944000,0.005141,0.967212,0.067561,2000\ncr1,C8,30,0.200000,0.940000,0.005310,0.950180,0.206765,2000\ncr1,C9,30,0.500000,0.929000,0.005743,0.946942,0.316451,2000\nwcb,C1,5,0.000000,0.869000,0.007545,,0.244381,2000\nwcb,C2,5,0.200000,0.847000,0.008050,,0.881468,2000\nwcb,C3,5,0.500000,0.856500,0.007839,,1.418667,2000\nwcb,C4,10,0.000000,0.926000,0.005853,,0.144604,2000\nwcb,C5,10,0.200000,0.939000,0.005352,,0.468497,2000\nwcb,C6,10,0.500000,0.936500,0.005453,,0.717148,2000\nwcb,C7,30,0.000000,0.946000,0.005054,,0.069891,2000\nwcb,C8,30,0.200000,0.951500,0.004804,,0.221774,2000\nwcb,C9,30,0.500000,0.941500,0.005248,,0.340898,2000\n['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'cr1_G30_icc0.2', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5'] {'cr0': 0.7456666666666667, 'cr1': 0.8933333333333332, 'wcb': 0.8574999999999999}\n[9.39083 6.01159 3.05737 4.20897 2.8571  3.98798 5.3703  2.86971 1.79276\n 2.64592]","is_error":false}]},"uuid":"9679c1d5-301b-4130-b597-252f4a3e4e36","timestamp":"2026-10-30T05:40:19.467Z","toolUseResult":{"stdout":"estimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.000000,0.797000,0.008994,0.653105,0.129219,2000\ncr0,C2,5,0.200000,0.719500,0.010045,0.507338,0.336360,2000\ncr0,C3,5,0.500000,0.720500,0.010034,0.505404,0.509842,2000\ncr0,C4,10,0.000000,0.883500,0.007174,0.845792,0.106538,2000\ncr0,C5,10,0.200000,0.859000,0.007782,0.759525,0.300190,2000\ncr0,C6,10,0.500000,0.853000,0.007918,0.766830,0.458667,2000\ncr0,C7,30,0.000000,0.930500,0.005686,0.934972,0.063658,2000\ncr0,C8,30,0.200000,0.924000,0.005926,0.918508,0.194818,2000\ncr0,C9,30,0.500000,0.916000,0.006203,0.915377,0.298167,2000\ncr1,C1,5,0.000000,0.919000,0.006101,0.816381,0.204651,2000\ncr1,C2,5,0.200000,0.881500,0.007227,0.634173,0.532712,2000\ncr1,C3,5,0.500000,0.879500,0.007279,0.631755,0.807465,2000\ncr1,C4,10,0.000000,0.939500,0.005331,0.939769,0.129613,2000\ncr1,C5,10,0.200000,0.916500,0.006186,0.843917,0.365209,2000\ncr1,C6,10,0.500000,0.917000,0.006169,0.852034,0.558011,2000\ncr1,C7,30,0.000000,0.944000,0.005141,0.967212,0.067561,2000\ncr1,C8,30,0.200000,0.940000,0.005310,0.950180,0.206765,2000\ncr1,C9,30,0.500000,0.929000,0.005743,0.946942,0.316451,2000\nwcb,C1,5,0.000000,0.869000,0.007545,,0.244381,2000\nwcb,C2,5,0.200000,0.847000,0.008050,,0.881468,2000\nwcb,C3,5,0.500000,0.856500,0.007839,,1.418667,2000\nwcb,C4,10,0.000000,0.926000,0.005853,,0.144604,2000\nwcb,C5,10,0.200000,0.939000,0.005352,,0.468497,2000\nwcb,C6,10,0.500000,0.936500,0.005453,,0.717148,2000\nwcb,C7,30,0.000000,0.946000,0.005054,,0.069891,2000\nwcb,C8,30,0.200000,0.951500,0.004804,,0.221774,2000\nwcb,C9,30,0.500000,0.941500,0.005248,,0.340898,2000\n['cr1_G10_icc0.0', 'cr1_G30_icc0.0', 'cr1_G30_icc0.2', 'wcb_G30_icc0.0', 'wcb_G30_icc0.2', 'wcb_G30_icc0.5'] {'cr0': 0.7456666666666667, 'cr1': 0.8933333333333332, 'wcb': 0.8574999999999999}\n[9.39083 6.01159 3.05737 4.20897 2.8571  3.98798 5.3703  2.86971 1.79276\n 2.64592]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"cdf92152-a950-48ed-85b6-2519dcdf74da","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"abfa8ede38eb6d312f2e1886d01e2e6ed6b87894a015f5af777aea960f694825","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_013L61LNMXGoq6BSjtyAuyCz","name":"Bash","input":{"command":"cat out/table1.csv; python3 -c \"import json;d=json.load(open('out/results.json'));print(d['nominal_cells'],d['mean_coverage_small_G'])\"\ncat > /tmp/xcheck.py <<'EOF'\n# Independent naive re-implementation for cell C2, first 50 replications, same draw order\nimport numpy as np, pandas as pd\nfrom scipy import stats\nd=pd.read_csv('data/design.csv'); r=d.iloc[1]\nsizes=np.array([int(s) for s in r.cluster_sizes.split('|')]); G=len(sizes); N=sizes.sum(); R,B=2000,399; icc=r.icc\nrng=np.random.default_rng(int(r.seed))\nu=np.sqrt(icc)*rng.standard_normal((R,G)); e=np.sqrt(1-icc)*rng.standard_normal((R,N)); W=2*rng.integers(0,2,size=(R,B,G))-1\ngid=np.repeat(np.arange(G),sizes)\ndef crv(y):\n    yb=y.mean(); res=y-yb\n    return yb, G/(G-1)*sum(res[gid==g].sum()**2 for g in range(G))/N**2\nqs=[]\nfor rep in range(50):\n    y=u[rep,gid]+e[rep]; yb,V1=crv(y); res=y-yb\n    t=[]\n    for b in range(B):\n        ys=yb+W[rep,b,gid]*res; ybs,V1s=crv(ys); t.append(abs(ybs-yb)/np.sqrt(V1s))\n    qs.append(np.sort(t)[379])\nprint(np.round(qs[:10],5))\nEOF\n~/wp29/venv/bin/python /tmp/xcheck.py","description":"Show table and run independent bootstrap check"}}]}}51{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"62c63758-8b8b-4cf2-90e7-32d5d44427ad","timestamp":"2026-10-30T05:40:19.470Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"5d7ca76c-af44-4573-8ec4-f547b7021230","keep":14,"tail":["abfa8ede38eb6d312f2e1886d01e2e6ed6b87894a015f5af777aea960f694825","e0514ed6a714cbefe175c33d2ceedd4fce66ef942fd541057187ecd9d136353b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b225b60d3fff2036db61e8a6b3e678dfae8d61fc7c1e92237821713f201a005c"}52{"parentUuid":"9679c1d5-301b-4130-b597-252f4a3e4e36","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHu1DWau8xQVQzZZnX","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":2038,"cache_read_input_tokens":21496,"output_tokens":643,"output_tokens_details":{"thinking_tokens":251},"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":2038},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1987,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtHtj6Yg4vg76nAAy2S","requestRef":"62c63758-8b8b-4cf2-90e7-32d5d44427ad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b387f41c-4b94-4466-859a-61b6a802a415","timestamp":"2026-10-30T05:40:22.802Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"b387f41c-4b94-4466-859a-61b6a802a415","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtHu1DWau8xQVQzZZnX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01G8pysnRrxFpBoWyRnK1Sms","name":"Bash","input":{"command":"cat >> /tmp/xcheck.py <<'EOF'\n# vectorized formula as in analysis.py\ny=u[:50][:,gid]+e[:50]; yb=y.mean(1); res=y-yb[:,None]\nS=np.stack([res[:,gid==g].sum(1) for g in range(G)],1)\nWS=W[:50]*S[:,None,:]; D=WS.sum(2)/N; Ss=WS-sizes*D[:,:,None]; V1s=G/(G-1)*(Ss**2).sum(2)/N**2\nqv=np.quantile(np.abs(D/np.sqrt(V1s)),0.95,axis=1,method='inverted_cdf')\nprint('max abs diff loop vs vectorized:',np.max(np.abs(qv-np.array(qs))))\nEOF\n~/wp29/venv/bin/python /tmp/xcheck.py","description":"Compare loop vs vectorized bootstrap quantiles"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2038,"cache_read_input_tokens":21496,"output_tokens":643,"output_tokens_details":{"thinking_tokens":251},"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":2038},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtHtj6Yg4vg76nAAy2S","requestRef":"62c63758-8b8b-4cf2-90e7-32d5d44427ad","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b26c5812-b715-4ab8-873f-518dd6ffaa36","timestamp":"2026-10-30T05:40:25.639Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}54{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b26c5812-b715-4ab8-873f-518dd6ffaa36","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}55{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}56{"parentUuid":"b26c5812-b715-4ab8-873f-518dd6ffaa36","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01G8pysnRrxFpBoWyRnK1Sms","type":"tool_result","content":"[9.39083 6.01159 3.05737 4.20897 2.8571  3.98798 5.3703  2.86971 1.79276\n 2.64592]\nmax abs diff loop vs vectorized: 4.440892098500626e-15","is_error":false}]},"uuid":"f592613a-53db-4055-a77b-c4e9ea335e96","timestamp":"2026-10-30T05:40:26.567Z","toolUseResult":{"stdout":"[9.39083 6.01159 3.05737 4.20897 2.8571  3.98798 5.3703  2.86971 1.79276\n 2.64592]\nmax abs diff loop vs vectorized: 4.440892098500626e-15","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b26c5812-b715-4ab8-873f-518dd6ffaa36","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}57{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"3888b999bdbb2c290418df02d98800b26e984945a4739f84979005b0ce8420e9","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01G8pysnRrxFpBoWyRnK1Sms","name":"Bash","input":{"command":"cat >> /tmp/xcheck.py <<'EOF'\n# vectorized formula as in analysis.py\ny=u[:50][:,gid]+e[:50]; yb=y.mean(1); res=y-yb[:,None]\nS=np.stack([res[:,gid==g].sum(1) for g in range(G)],1)\nWS=W[:50]*S[:,None,:]; D=WS.sum(2)/N; Ss=WS-sizes*D[:,:,None]; V1s=G/(G-1)*(Ss**2).sum(2)/N**2\nqv=np.quantile(np.abs(D/np.sqrt(V1s)),0.95,axis=1,method='inverted_cdf')\nprint('max abs diff loop vs vectorized:',np.max(np.abs(qv-np.array(qs))))\nEOF\n~/wp29/venv/bin/python /tmp/xcheck.py","description":"Compare loop vs vectorized bootstrap quantiles"}}]}}58{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"7e0a6889-646c-4ce0-af63-89014822b977","timestamp":"2026-10-30T05:40:26.570Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"62c63758-8b8b-4cf2-90e7-32d5d44427ad","keep":16,"tail":["3888b999bdbb2c290418df02d98800b26e984945a4739f84979005b0ce8420e9","ddebae21e2b71c55c8c82d87f9a9aba17a3cae765de9eb2a25b6d6ce0c9ce8f0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"095d488d4f4f127a4e7d6f62aeeaa9f005a5111de62988981fcdedab2e38671e"}59{"parentUuid":"f592613a-53db-4055-a77b-c4e9ea335e96","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtJRke7XHrUX767eAxH","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":726,"cache_read_input_tokens":23534,"output_tokens":1240,"output_tokens_details":{"thinking_tokens":478},"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":726},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4657,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtJR6DPe1oEjTDQtE6T","requestRef":"7e0a6889-646c-4ce0-af63-89014822b977","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"14f7cde4-9eb8-4ce6-ac2b-3a2f4a4bb180","timestamp":"2026-10-30T05:40:32.653Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}60{"parentUuid":"14f7cde4-9eb8-4ce6-ac2b-3a2f4a4bb180","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtJRke7XHrUX767eAxH","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WV9ZBbUzYxj3WCkDTf4xqe","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    \"exact_var_ybar\":''','''    \"exact_rel_bias_var\": exact_rb,\n    \"exact_var_ybar\":''')\ns=s.replace('''failure = sorted(''','''# analytic E[V_CR0]/Var(ybar) (verification of the Monte Carlo bias estimates):\n# S = A y with A = C - n 1'/N (C: G x N cluster indicator); E[S'S] = tr(A Sigma A'),\n# Sigma = icc * C'C + (1-icc) I.\nexact_rb = {}\nfor c in cells:\n    G, N, icc, sizes = c[\"G\"], c[\"N\"], c[\"icc\"], c[\"sizes\"]\n    C = (np.repeat(np.arange(G), sizes)[None, :] == np.arange(G)[:, None]).astype(float)\n    A = C - np.outer(sizes, np.ones(N)) / N\n    Sigma = icc * C.T @ C + (1 - icc) * np.eye(N)\n    v_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n    ev0 = np.trace(A @ Sigma @ A.T) / N ** 2 / v_exact\n    exact_rb[key(\"cr0\", c)] = float(ev0)\n    exact_rb[key(\"cr1\", c)] = float(G / (G - 1) * ev0)\n\nfailure = sorted(''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'))\nfor k in d['rel_bias_var']:\n  m=d['rel_bias_var'][k];x=d['exact_rel_bias_var'][k];print(k,round(m,4),round(x,4),round(m/x-1,4))\"","description":"Add analytic relative bias and compare"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":726,"cache_read_input_tokens":23534,"output_tokens":1240,"output_tokens_details":{"thinking_tokens":478},"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":726},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtJR6DPe1oEjTDQtE6T","requestRef":"7e0a6889-646c-4ce0-af63-89014822b977","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a2b6bd2c-dda5-4bcd-aaf1-128db3a86799","timestamp":"2026-10-30T05:40:37.937Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"a2b6bd2c-dda5-4bcd-aaf1-128db3a86799","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WV9ZBbUzYxj3WCkDTf4xqe","type":"tool_result","content":"cr0_G5_icc0.0 0.6531 0.6641 -0.0165\ncr1_G5_icc0.0 0.8164 0.8301 -0.0165\ncr0_G5_icc0.2 0.5073 0.4995 0.0157\ncr1_G5_icc0.2 0.6342 0.6244 0.0157\ncr0_G5_icc0.5 0.5054 0.4883 0.0351\ncr1_G5_icc0.5 0.6318 0.6104 0.0351\ncr0_G10_icc0.0 0.8458 0.8393 0.0077\ncr1_G10_icc0.0 0.9398 0.9326 0.0077\ncr0_G10_icc0.2 0.7595 0.7599 -0.0005\ncr1_G10_icc0.2 0.8439 0.8443 -0.0005\ncr0_G10_icc0.5 0.7668 0.7544 0.0165\ncr1_G10_icc0.5 0.852 0.8382 0.0165\ncr0_G30_icc0.0 0.935 0.9486 -0.0143\ncr1_G30_icc0.0 0.9672 0.9813 -0.0143\ncr0_G30_icc0.2 0.9185 0.9267 -0.0089\ncr1_G30_icc0.2 0.9502 0.9587 -0.0089\ncr0_G30_icc0.5 0.9154 0.9253 -0.0107\ncr1_G30_icc0.5 0.9469 0.9572 -0.0107","is_error":false}]},"uuid":"ab1aecec-32e6-40da-8483-4ddbe7ee47ca","timestamp":"2026-10-30T05:40:39.820Z","toolUseResult":{"stdout":"cr0_G5_icc0.0 0.6531 0.6641 -0.0165\ncr1_G5_icc0.0 0.8164 0.8301 -0.0165\ncr0_G5_icc0.2 0.5073 0.4995 0.0157\ncr1_G5_icc0.2 0.6342 0.6244 0.0157\ncr0_G5_icc0.5 0.5054 0.4883 0.0351\ncr1_G5_icc0.5 0.6318 0.6104 0.0351\ncr0_G10_icc0.0 0.8458 0.8393 0.0077\ncr1_G10_icc0.0 0.9398 0.9326 0.0077\ncr0_G10_icc0.2 0.7595 0.7599 -0.0005\ncr1_G10_icc0.2 0.8439 0.8443 -0.0005\ncr0_G10_icc0.5 0.7668 0.7544 0.0165\ncr1_G10_icc0.5 0.852 0.8382 0.0165\ncr0_G30_icc0.0 0.935 0.9486 -0.0143\ncr1_G30_icc0.0 0.9672 0.9813 -0.0143\ncr0_G30_icc0.2 0.9185 0.9267 -0.0089\ncr1_G30_icc0.2 0.9502 0.9587 -0.0089\ncr0_G30_icc0.5 0.9154 0.9253 -0.0107\ncr1_G30_icc0.5 0.9469 0.9572 -0.0107","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a2b6bd2c-dda5-4bcd-aaf1-128db3a86799","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}62{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"f42fd4fbe01e094c050d255a3f12ce14c36b8197bbff3da074e1a82381f18fb4","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WV9ZBbUzYxj3WCkDTf4xqe","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    \"exact_var_ybar\":''','''    \"exact_rel_bias_var\": exact_rb,\n    \"exact_var_ybar\":''')\ns=s.replace('''failure = sorted(''','''# analytic E[V_CR0]/Var(ybar) (verification of the Monte Carlo bias estimates):\n# S = A y with A = C - n 1'/N (C: G x N cluster indicator); E[S'S] = tr(A Sigma A'),\n# Sigma = icc * C'C + (1-icc) I.\nexact_rb = {}\nfor c in cells:\n    G, N, icc, sizes = c[\"G\"], c[\"N\"], c[\"icc\"], c[\"sizes\"]\n    C = (np.repeat(np.arange(G), sizes)[None, :] == np.arange(G)[:, None]).astype(float)\n    A = C - np.outer(sizes, np.ones(N)) / N\n    Sigma = icc * C.T @ C + (1 - icc) * np.eye(N)\n    v_exact = (icc * (sizes ** 2).sum() + (1 - icc) * N) / N ** 2\n    ev0 = np.trace(A @ Sigma @ A.T) / N ** 2 / v_exact\n    exact_rb[key(\"cr0\", c)] = float(ev0)\n    exact_rb[key(\"cr1\", c)] = float(G / (G - 1) * ev0)\n\nfailure = sorted(''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'))\nfor k in d['rel_bias_var']:\n  m=d['rel_bias_var'][k];x=d['exact_rel_bias_var'][k];print(k,round(m,4),round(x,4),round(m/x-1,4))\"","description":"Add analytic relative bias and compare"}}]}}63{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"58a247d5-67d0-4fde-b612-bdbdb10f6dd7","timestamp":"2026-10-30T05:40:39.823Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"7e0a6889-646c-4ce0-af63-89014822b977","keep":18,"tail":["f42fd4fbe01e094c050d255a3f12ce14c36b8197bbff3da074e1a82381f18fb4","1ad2eaecdfbd4a2144e0cb74ea03c03fe3b3ca6e8806784b2270160050b6139d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9cf6e906f82830cc434c133205205ad0b12400891da7df546194f89aff7ccf6f"}64{"parentUuid":"ab1aecec-32e6-40da-8483-4ddbe7ee47ca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtKQ2VQaJsRCTwdAT2i","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":1756,"cache_read_input_tokens":24260,"output_tokens":694,"output_tokens_details":{"thinking_tokens":105},"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":1756},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":644,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtKPkNaRodtvpkcgPrG","requestRef":"58a247d5-67d0-4fde-b612-bdbdb10f6dd7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"57111de6-9ccd-46f9-a37f-f39824a801b7","timestamp":"2026-10-30T05:40:44.637Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}65{"parentUuid":"57111de6-9ccd-46f9-a37f-f39824a801b7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtKQ2VQaJsRCTwdAT2i","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01N4R1CyvfLFQsgbKnp4SdUu","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''rows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}''','''rows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nrelbias_se = {}''')\ns=s.replace('''            relbias[k] = rb\n''','''            relbias[k] = rb\n            Vk = V0 if est == \"cr0\" else V1\n            relbias_se[k] = float(Vk.std(ddof=1) / np.sqrt(R) / var_exact)\n''')\ns=s.replace('''    \"exact_rel_bias_var\": exact_rb,''','''    \"mc_se_rel_bias_var\": relbias_se,\n    \"exact_rel_bias_var\": exact_rb,\n    \"z_rel_bias_mc_vs_exact\": {k: float((relbias[k] - exact_rb[k]) / relbias_se[k]) for k in relbias},''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'))\nfor k in d['rel_bias_var']: print(k, round(d['mc_se_rel_bias_var'][k],4), round(d['z_rel_bias_mc_vs_exact'][k],2))\"","description":"Add MC SE of variance-bias estimates"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1756,"cache_read_input_tokens":24260,"output_tokens":694,"output_tokens_details":{"thinking_tokens":105},"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":1756},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtKPkNaRodtvpkcgPrG","requestRef":"58a247d5-67d0-4fde-b612-bdbdb10f6dd7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"118717d8-d3a5-4141-8add-05a48d1ab6ba","timestamp":"2026-10-30T05:40:48.374Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}66{"parentUuid":"118717d8-d3a5-4141-8add-05a48d1ab6ba","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01N4R1CyvfLFQsgbKnp4SdUu","type":"tool_result","content":"cr0_G5_icc0.0 0.0124 -0.89\ncr1_G5_icc0.0 0.0155 -0.89\ncr0_G5_icc0.2 0.0126 0.62\ncr1_G5_icc0.2 0.0157 0.62\ncr0_G5_icc0.5 0.0126 1.36\ncr1_G5_icc0.5 0.0157 1.36\ncr0_G10_icc0.0 0.0113 0.57\ncr1_G10_icc0.0 0.0126 0.57\ncr0_G10_icc0.2 0.0132 -0.03\ncr1_G10_icc0.2 0.0147 -0.03\ncr0_G10_icc0.5 0.0144 0.87\ncr1_G10_icc0.5 0.016 0.87\ncr0_G30_icc0.0 0.0068 -2.0\ncr1_G30_icc0.0 0.007 -2.0\ncr0_G30_icc0.2 0.0085 -0.97\ncr1_G30_icc0.2 0.0088 -0.97\ncr0_G30_icc0.5 0.0083 -1.2\ncr1_G30_icc0.5 0.0085 -1.2","is_error":false}]},"uuid":"76c1c6f2-b1f2-4ffe-8c88-885181f365b6","timestamp":"2026-10-30T05:40:50.231Z","toolUseResult":{"stdout":"cr0_G5_icc0.0 0.0124 -0.89\ncr1_G5_icc0.0 0.0155 -0.89\ncr0_G5_icc0.2 0.0126 0.62\ncr1_G5_icc0.2 0.0157 0.62\ncr0_G5_icc0.5 0.0126 1.36\ncr1_G5_icc0.5 0.0157 1.36\ncr0_G10_icc0.0 0.0113 0.57\ncr1_G10_icc0.0 0.0126 0.57\ncr0_G10_icc0.2 0.0132 -0.03\ncr1_G10_icc0.2 0.0147 -0.03\ncr0_G10_icc0.5 0.0144 0.87\ncr1_G10_icc0.5 0.016 0.87\ncr0_G30_icc0.0 0.0068 -2.0\ncr1_G30_icc0.0 0.007 -2.0\ncr0_G30_icc0.2 0.0085 -0.97\ncr1_G30_icc0.2 0.0088 -0.97\ncr0_G30_icc0.5 0.0083 -1.2\ncr1_G30_icc0.5 0.0085 -1.2","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"118717d8-d3a5-4141-8add-05a48d1ab6ba","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}67{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"a07f73745d22c74f3d0442d58d86dd607ac5649b997fe3dbdcc1c92c9ff0fbdf","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01N4R1CyvfLFQsgbKnp4SdUu","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''rows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}''','''rows, coverage, mcse, relbias, base_cov = [], {}, {}, {}, {}\nrelbias_se = {}''')\ns=s.replace('''            relbias[k] = rb\n''','''            relbias[k] = rb\n            Vk = V0 if est == \"cr0\" else V1\n            relbias_se[k] = float(Vk.std(ddof=1) / np.sqrt(R) / var_exact)\n''')\ns=s.replace('''    \"exact_rel_bias_var\": exact_rb,''','''    \"mc_se_rel_bias_var\": relbias_se,\n    \"exact_rel_bias_var\": exact_rb,\n    \"z_rel_bias_mc_vs_exact\": {k: float((relbias[k] - exact_rb[k]) / relbias_se[k]) for k in relbias},''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'))\nfor k in d['rel_bias_var']: print(k, round(d['mc_se_rel_bias_var'][k],4), round(d['z_rel_bias_mc_vs_exact'][k],2))\"","description":"Add MC SE of variance-bias estimates"}}]}}68{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"1ba0f10d-a191-45aa-baea-21fbdb8f933a","timestamp":"2026-10-30T05:40:50.234Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"58a247d5-67d0-4fde-b612-bdbdb10f6dd7","keep":20,"tail":["a07f73745d22c74f3d0442d58d86dd607ac5649b997fe3dbdcc1c92c9ff0fbdf","03a8705746993b2368df13f498aa4b06c51aeac8dae97969139def080af31227"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"47bcbb2b7bf8602ea13c73a8edc6bab0e8ac00a3c85d5d4fa3a69a1465a02da1"}69{"parentUuid":"76c1c6f2-b1f2-4ffe-8c88-885181f365b6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtLAZ9t7u9yb7yEYuhr","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":1102,"cache_read_input_tokens":26016,"output_tokens":1866,"output_tokens_details":{"thinking_tokens":85},"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":1102},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":529,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtLAGnFKj1bu7JVAt4w","requestRef":"1ba0f10d-a191-45aa-baea-21fbdb8f933a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"26d2cb62-a585-401d-b644-c28785f44b88","timestamp":"2026-10-30T05:40:52.208Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}70{"parentUuid":"26d2cb62-a585-401d-b644-c28785f44b88","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtLAZ9t7u9yb7yEYuhr","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Es6Q1jRm27pG4qGjpjZFH4","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && rm -f out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py > /dev/null && cmp /tmp/r1.json out/results.json && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json, pandas as pd, numpy as np\nd=json.load(open('out/results.json')); t=pd.read_csv('out/table1.csv'); ex=pd.read_csv('out/exclusions.csv')\nchk=[]\nchk.append((\"27 coverage keys / 27 mcse keys / 18 bias keys\", len(d['coverage'])==27 and len(d['mc_se_coverage'])==27 and len(d['rel_bias_var'])==18))\nchk.append((\"table1 has 27 rows, wcb rel_bias blank\", len(t)==27 and t[t.estimator=='wcb'].rel_bias_var.isna().all() and t[t.estimator!='wcb'].rel_bias_var.notna().all()))\nchk.append((\"coverage in [0,1], MC SE >0\", all(0<=v<=1 for v in d['coverage'].values()) and all(v>0 for v in d['mc_se_coverage'].values())))\nchk.append((\"MC SE = sqrt(p(1-p)/R)\", all(abs(d['mc_se_coverage'][k]-np.sqrt(p*(1-p)/2000))<1e-12 for k,p in d['coverage'].items())))\nchk.append((\"table matches json\", all(abs(r.coverage-d['coverage'][f\"{r.estimator}_G{r.G}_icc{r.icc:.1f}\"])<1e-6 for r in t.itertuples())))\nchk.append((\"failure_cells == {cov<0.90}, n matches\", set(d['failure_cells'])=={k for k,p in d['coverage'].items() if p<0.9} and d['n_failure_cells']==len(d['failure_cells'])))\nchk.append((\"nominal_cells rule\", set(d['nominal_cells'])=={k for k,p in d['coverage'].items() if abs(p-0.95)<=2*d['mc_se_coverage'][k]}))\nchk.append((\"CR1 bias = G/(G-1) * CR0 bias\", all(abs(d['rel_bias_var'][f'cr1_G{G}_icc{i}']-G/(G-1)*d['rel_bias_var'][f'cr0_G{G}_icc{i}'])<1e-12 for G in (5,10,30) for i in ('0.0','0.2','0.5'))))\nchk.append((\"MC bias vs analytic within 2.5 MC SE\", all(abs(z)<=2.5 for z in d['z_rel_bias_mc_vs_exact'].values())))\nchk.append((\"CR1 halfwidth >= CR0 halfwidth (t>z, G/(G-1)>1)\", all(t[(t.estimator=='cr1')].mean_ci_halfwidth.values > t[(t.estimator=='cr0')].mean_ci_halfwidth.values)))\nchk.append((\"CR1 coverage >= CR0 coverage in every cell (nested intervals)\", all(d['coverage'][k.replace('cr0','cr1')]>=p for k,p in d['coverage'].items() if k.startswith('cr0'))))\nchk.append((\"n_analysed = 9*2000\", d['n_analysed']==18000))\nchk.append((\"exclusion ledger sums\", (ex.n_before-ex.n_removed==ex.n_after).all() and ex.n_after.iloc[-1]==9))\nchk.append((\"best_procedure_small_G = argmax mean G=5 coverage\", d['best_procedure_small_G']==max(d['mean_coverage_small_G'],key=d['mean_coverage_small_G'].get)))\nwith open('out/state/checks.md','w') as f:\n    f.write(\"# Verification checks (P4)\\n\\n- Clean re-run (deleted outputs, re-ran analysis.py): results.json byte-identical -> PASS\\n- Independent loop implementation of WCB (cell C2, first 50 reps) vs vectorised: max |diff| in q = 4.4e-15 -> PASS\\n- Exact N = sum(cluster sizes), G = len(sizes) asserted in analysis.py -> PASS\\n\")\n    for n,ok in chk: f.write(f\"- {n} -> {'PASS' if ok else 'FAIL'}\\n\")\n    f.write(\"\\nNote: rel. bias z-scores vs analytic values range %.2f..%.2f (one at -2.0, cr0/cr1 G30 icc0.0 share the same z; consistent with MC noise across 9 independent cells).\\n\"%(min(d['z_rel_bias_mc_vs_exact'].values()),max(d['z_rel_bias_mc_vs_exact'].values())))\nfor n,ok in chk: print(ok,n)\nEOF","description":"Reproducibility and consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1102,"cache_read_input_tokens":26016,"output_tokens":1866,"output_tokens_details":{"thinking_tokens":85},"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":1102},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtLAGnFKj1bu7JVAt4w","requestRef":"1ba0f10d-a191-45aa-baea-21fbdb8f933a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a2fd315c-c012-4302-9167-e0404e13e8c1","timestamp":"2026-10-30T05:41:05.338Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}71{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a2fd315c-c012-4302-9167-e0404e13e8c1","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}72{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}73{"parentUuid":"a2fd315c-c012-4302-9167-e0404e13e8c1","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Es6Q1jRm27pG4qGjpjZFH4","type":"tool_result","content":"IDENTICAL\nTrue 27 coverage keys / 27 mcse keys / 18 bias keys\nTrue table1 has 27 rows, wcb rel_bias blank\nTrue coverage in [0,1], MC SE >0\nTrue MC SE = sqrt(p(1-p)/R)\nTrue table matches json\nTrue failure_cells == {cov<0.90}, n matches\nTrue nominal_cells rule\nTrue CR1 bias = G/(G-1) * CR0 bias\nTrue MC bias vs analytic within 2.5 MC SE\nTrue CR1 halfwidth >= CR0 halfwidth (t>z, G/(G-1)>1)\nTrue CR1 coverage >= CR0 coverage in every cell (nested intervals)\nTrue n_analysed = 9*2000\nTrue exclusion ledger sums\nTrue best_procedure_small_G = argmax mean G=5 coverage","is_error":false}]},"uuid":"e92dc720-f71a-4777-88ac-f7ab94c2376f","timestamp":"2026-10-30T05:41:07.648Z","toolUseResult":{"stdout":"IDENTICAL\nTrue 27 coverage keys / 27 mcse keys / 18 bias keys\nTrue table1 has 27 rows, wcb rel_bias blank\nTrue coverage in [0,1], MC SE >0\nTrue MC SE = sqrt(p(1-p)/R)\nTrue table matches json\nTrue failure_cells == {cov<0.90}, n matches\nTrue nominal_cells rule\nTrue CR1 bias = G/(G-1) * CR0 bias\nTrue MC bias vs analytic within 2.5 MC SE\nTrue CR1 halfwidth >= CR0 halfwidth (t>z, G/(G-1)>1)\nTrue CR1 coverage >= CR0 coverage in every cell (nested intervals)\nTrue n_analysed = 9*2000\nTrue exclusion ledger sums\nTrue best_procedure_small_G = argmax mean G=5 coverage","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a2fd315c-c012-4302-9167-e0404e13e8c1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}74{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"ef4d54ab0e888b2415e6560334a978628cf94658ed6814cc0543a1b2e2c4bd65","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Es6Q1jRm27pG4qGjpjZFH4","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json && rm -f out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py > /dev/null && cmp /tmp/r1.json out/results.json && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json, pandas as pd, numpy as np\nd=json.load(open('out/results.json')); t=pd.read_csv('out/table1.csv'); ex=pd.read_csv('out/exclusions.csv')\nchk=[]\nchk.append((\"27 coverage keys / 27 mcse keys / 18 bias keys\", len(d['coverage'])==27 and len(d['mc_se_coverage'])==27 and len(d['rel_bias_var'])==18))\nchk.append((\"table1 has 27 rows, wcb rel_bias blank\", len(t)==27 and t[t.estimator=='wcb'].rel_bias_var.isna().all() and t[t.estimator!='wcb'].rel_bias_var.notna().all()))\nchk.append((\"coverage in [0,1], MC SE >0\", all(0<=v<=1 for v in d['coverage'].values()) and all(v>0 for v in d['mc_se_coverage'].values())))\nchk.append((\"MC SE = sqrt(p(1-p)/R)\", all(abs(d['mc_se_coverage'][k]-np.sqrt(p*(1-p)/2000))<1e-12 for k,p in d['coverage'].items())))\nchk.append((\"table matches json\", all(abs(r.coverage-d['coverage'][f\"{r.estimator}_G{r.G}_icc{r.icc:.1f}\"])<1e-6 for r in t.itertuples())))\nchk.append((\"failure_cells == {cov<0.90}, n matches\", set(d['failure_cells'])=={k for k,p in d['coverage'].items() if p<0.9} and d['n_failure_cells']==len(d['failure_cells'])))\nchk.append((\"nominal_cells rule\", set(d['nominal_cells'])=={k for k,p in d['coverage'].items() if abs(p-0.95)<=2*d['mc_se_coverage'][k]}))\nchk.append((\"CR1 bias = G/(G-1) * CR0 bias\", all(abs(d['rel_bias_var'][f'cr1_G{G}_icc{i}']-G/(G-1)*d['rel_bias_var'][f'cr0_G{G}_icc{i}'])<1e-12 for G in (5,10,30) for i in ('0.0','0.2','0.5'))))\nchk.append((\"MC bias vs analytic within 2.5 MC SE\", all(abs(z)<=2.5 for z in d['z_rel_bias_mc_vs_exact'].values())))\nchk.append((\"CR1 halfwidth >= CR0 halfwidth (t>z, G/(G-1)>1)\", all(t[(t.estimator=='cr1')].mean_ci_halfwidth.values > t[(t.estimator=='cr0')].mean_ci_halfwidth.values)))\nchk.append((\"CR1 coverage >= CR0 coverage in every cell (nested intervals)\", all(d['coverage'][k.replace('cr0','cr1')]>=p for k,p in d['coverage'].items() if k.startswith('cr0'))))\nchk.append((\"n_analysed = 9*2000\", d['n_analysed']==18000))\nchk.append((\"exclusion ledger sums\", (ex.n_before-ex.n_removed==ex.n_after).all() and ex.n_after.iloc[-1]==9))\nchk.append((\"best_procedure_small_G = argmax mean G=5 coverage\", d['best_procedure_small_G']==max(d['mean_coverage_small_G'],key=d['mean_coverage_small_G'].get)))\nwith open('out/state/checks.md','w') as f:\n    f.write(\"# Verification checks (P4)\\n\\n- Clean re-run (deleted outputs, re-ran analysis.py): results.json byte-identical -> PASS\\n- Independent loop implementation of WCB (cell C2, first 50 reps) vs vectorised: max |diff| in q = 4.4e-15 -> PASS\\n- Exact N = sum(cluster sizes), G = len(sizes) asserted in analysis.py -> PASS\\n\")\n    for n,ok in chk: f.write(f\"- {n} -> {'PASS' if ok else 'FAIL'}\\n\")\n    f.write(\"\\nNote: rel. bias z-scores vs analytic values range %.2f..%.2f (one at -2.0, cr0/cr1 G30 icc0.0 share the same z; consistent with MC noise across 9 independent cells).\\n\"%(min(d['z_rel_bias_mc_vs_exact'].values()),max(d['z_rel_bias_mc_vs_exact'].values())))\nfor n,ok in chk: print(ok,n)\nEOF","description":"Reproducibility and consistency checks"}}]}}75{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"979aa118-c2ab-48a6-a213-2e35cc779abe","timestamp":"2026-10-30T05:41:07.651Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"1ba0f10d-a191-45aa-baea-21fbdb8f933a","keep":22,"tail":["ef4d54ab0e888b2415e6560334a978628cf94658ed6814cc0543a1b2e2c4bd65","6d74ef1f14d9ac67fa955e60dfa6acb38c9f91d99818109bc1fbdaffe6dbe7da"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"95f2312212efbc0ae1131727a0689565404f059e5f4db5254ab6dc471d45e075"}76{"type":"tools-used","tools":["Bash","Read"],"sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}77{"parentUuid":"e92dc720-f71a-4777-88ac-f7ab94c2376f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMT1NxDKsNjvhfGffe","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":2159,"cache_read_input_tokens":27118,"output_tokens":305,"output_tokens_details":{"thinking_tokens":224},"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":2159},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2313,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtMSj1sDJ8NMCbmujdc","requestRef":"979aa118-c2ab-48a6-a213-2e35cc779abe","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"880333ba-0220-42c0-b404-cfbc92041a2f","timestamp":"2026-10-30T05:41:11.362Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"880333ba-0220-42c0-b404-cfbc92041a2f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMT1NxDKsNjvhfGffe","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016e9ds3D6QpMkp2JZN6nUE6","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/figure1.png"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2159,"cache_read_input_tokens":27118,"output_tokens":305,"output_tokens_details":{"thinking_tokens":224},"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":2159},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtMSj1sDJ8NMCbmujdc","requestRef":"979aa118-c2ab-48a6-a213-2e35cc779abe","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f144e621-9627-43da-a358-5bc71f08c6e1","timestamp":"2026-10-30T05:41:11.790Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}79{"parentUuid":"f144e621-9627-43da-a358-5bc71f08c6e1","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016e9ds3D6QpMkp2JZN6nUE6","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"iVBORw0KGgoAAAANSUhEUgAABpoAAAIiCAYAAADYTBtlAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAT/gAAE/4BB5Q5hAABAABJREFUeJzs3Qd4W+XVB/CjYVveK44dxyYJIQOyQwaEvfdIgEAZhbJbCoUySqHMFsoqZbRQaBlt+YAEAoQZNpQRyN4DEjI8EjvxXpK1vuf/SlfWtizLtmT/f3n0SNG9kq7W1fV73nOOzul0OoWIiIiIiIiIiIiIiIioi/RdvQERERERERERERERERERA01EREREREREREREREQUNWY0ERERERERERERERERUVQYaCIiIiIiIiIiIiIiIqKoMNBEREREREREREREREREUWGgiYiIiIiIiIiIiIiIiKLCQBMRERERERERERERERFFhYEmIiIiIiIiIiIiIiIiigoDTURERERERERERERERBQVBpqIiIiIiIiIiIiIiIgoKgw0ERERxQmn0ymvv/66nHvuuTJ8+HBJS0tTp3333Vddt2DBArHb7X29mRQDn332mRxxxBGSlZUlOp1OnbZv396vX9svvvhCPc8jjzwyIbdh4cKFcuyxx0pubq6YTCYZM2aM/P73v5fGxsawjxXutHv37oDb4brzzjtPcnJyJCMjQ0477TTZsmVLyO066aSTpKioSOrr6xPyPUk0l1xyiXrNXnzxxR57jL1798qll14qQ4cOFaPRqB7v7rvvlnjFz1H827hxoyQlJck111zT6X5Kr9er/c/MmTPloYceErPZ3KPbVlVVJS+88IKcffbZMmzYMElOTpbMzEyZPn26PPjgg9LW1hb29l9++aXaD+bn56tjpokTJ8ojjzwiNpst5G2wDOtgXdwGtz355JPlf//7X9jHwu/0L37xC/XdTElJUcdq1113ndTU1ET9/MkF+7hg+7pQ1992221iMBhkxYoVfAmJiIjihLGvN4CIiIhEysvLZc6cObJ06VL1BzUGP6ZNm6YGfH766Sd57bXXZP78+eo6rEOJq6ysTM444wxpaWlRA/ylpaXqPUdQgeLTLbfcIg8//LAa9J8xY4YUFBTIkiVL5IEHHlAB4K+//loGDx4c9LaFhYVy4oknBl2WmpoaEGw+5ZRT1MDZ0Ucfrf7/7rvvysqVK2Xt2rUqyOUN+4RFixbJ//3f/6mB4b6GgcB77rlH7rrrrrgOjMS7yy+/XAU299tvP5k7d64aeJ88eXKfbQ/2UxjM//zzzxmUTFA33nijCjT94Q9/CLo8PT1dBXq0IMy2bdtk8eLFaj+H4w8EpLBOT20b9mEIGuBzfvDBB6vADR7/1ltvlZdeekl99gYNGhRw2+eff159X/AbiskbCBhhIsfNN98sn3zyidp/Yr/tzWq1qqASlmN97HPxeB9++KE6Iej185//POCxVq9erR6joaFBJk2aJIcddpjaVz/55JPq+4rtLS4u7pHXiALddNNN8tRTT8lvf/tb9fkkIiKivsdAExERUR/D7PVDDjlEdu7cqQaXn376aRk9erTPOpWVlXL//ffLK6+80mfbSbHx8ccfS3Nzs1x00UXyn//8Z8C8rAjQYFY9Zo8nknfeeUcFmZB99sEHH8isWbPU9a2trXL++eerAcarrrpK3nzzzaC3Hzt2bMTZL2+99ZYauESQBsEauOOOO+RPf/qT/Otf/1KDpxpkUl1//fUqywrbMZDek/6svb1d3nvvPRWERICRAWjqLgRpsO+69tprZciQIUHXQRDHfz/1zTffyDHHHCPLli1TwRQEfXoCgj3YxyFghMC8pqKiQgWBEODBvg4BJ//sol/+8pcqQIWAO7YV6urq1LEUgkaPPvqomijgDftzBJmmTJkin376qSeAj+uQGXXllVeqgOo+++zjuQ2yyX/2s5+pIJP3/tnhcKjtRnAK5++//36PvEYUKC8vT2Xo4dgYAcVTTz2VLxMREVEfY+k8IiKiPoaBEgSZDj/8cDVY4h9kAsyS/dvf/qYGoinxs9cAJREHEgQzEHTxHrxLBBhg1Wbda0Em7fk8++yz6hzfyw0bNnT7sbQSQFdccYXnuquvvlqdY7a8f9mg2tpaNaN7oL0n/RlKJyKjBBlyDDJRLPdhKMfYFZgAg1KR0JMBlMcff1xuv/12nyAToDydtn9D5iiCsN4ee+wxdd1ll13mCTIBAkeYsAMoj+ddchjfLQSfAPftnSWKoD3uy2KxqG3yn3CAoPz+++8vd955p+d6ZJ3j2Az3g2AeMk+p92ifT+0zTkRERH2LgSYiIqI+9OOPP6oBFPj73/+uStuEg1It/qqrq9UgOAJU6B2DEloIWiFbBqW3vB144IGqxAxm8YaCGb1Y59VXX/W5HgM6GFDBYDseA4+FQRdkXDQ1NQXcj3dd/a1bt8qFF16oZlNj9jEGiLRtx+Xjjz9e9TrAfWLARtv+cJDdhYwMrb/CmWeeqWY+Y1Y2HlcbgPC3bt06tQyD6+ixoJXOibb0ypo1a+SCCy5Qg2IocYXBstmzZ6vZ4N607dJmQqPEmNYTI9S2Brs91sWs6t/85jeq7B6ew8iRI9X9hepJgfcOrzNKL6L3hdbH4o9//KPKrgr3WCgp9Ktf/UpKSkpUlgVu551Zh7JxJ5xwgnrfMDCOkkSbNm2KuI+L9/UY4MPrg5JheF54TMxkR5lBf9357HQFZvOD90CmBsGA8ePHq8uxCAJrfT4wU1uDzyd490lB+UwMpKJH1KhRo6J+vFi+J3gP8Bn0/2wH662BzxxmoU+dOtXzeUTJLAwK+w8m+/dFQjAO33W89hjkxese7X7t+++/V/tO3B73h+eH7xT2VdhPdAX6yGCwE31lUFoRn0dMEMDnEc81Etg+9KiBHTt2+LyG0e7zI3n9QkHGCG6Hsnlw1FFH+WxTsH1mV77DGuwrzznnHPV6YR+KnmMoGbhq1SrpCu/PLd4PfD8Q0MdrhNfqiSee8KyLgMBZZ52l3it8/vDb+t1334W87z179qiMnnHjxqn18bk96KCDVKZhsNd8/fr16rcRZeDwu6c9r2C/DcF+M5HFjF5AuA22/4ADDlC/v12F+0GQBPupaMovavs39FHqC9o2Y//n3wfp7bffVufINPKH9wbfJbxv3kH6b7/9Vt0P9ldYxx/64wEyVYM9Fvpl+n8f8Xk4/fTTg94uHGyD1p8RZVCxPfgNxfcZvfmQ0RirzyO+E9p3Fplb+N3E7wyui/R7hn0zjlPxXdF6FY4YMUJ9j4IFIrt6zBgN/P7heSNTHMeZRERE1LdYOo+IiKgPodwHBgVQ718b0OmKH374QQ3+YTAJA3ro/YOSWiiV89VXX6nSMSg3ow2MXHzxxWqgEQOSwQbOMZsef7BnZ2erwUhNfX29CiBgwAaDE1qABwPeKHmDsmFoou09QO69jVqAA4OhGHDUSnV99NFHcsMNN6igDwYMMCiHcjkYDML2YyAYAxv+MJCNwTgMlGLQAwN5eF4YcAg3axuvBZajRwNeczQ7x2uH1wmzkTHDWcsgicQbb7yhBrkwoIL7Q/8G9LbA4C0GpjDIgow1wMArXn8M6iAghvW1QbRDDz004sfEe4HXCdkseO74P14rvB547ZBl4w0DrggEYR28BygphIAmBpwwMxv9N9DTIlj/C5QgwmuK+8Dsdnw+cD8o1YaSQQg8YWAOA/UYuEJQBq/j8uXL1UBrsPsMBa8htlPrgzFmzBj1WJhZjpnkeI+8RfvZ6SotEBfss+0dCAo1KIgBWm3gGIOIeM/x3UIpvmADj4Dni7JO2mXAgB5gdj5K9eHz1FOlrKJ5T9DfBQOY/p9t8L6MHmXHHXecbN68WQ2iY5+A/RMG+VEaEGXjcL8YmPeHoCaeO14n7L9QdhSf5Wj3a8iiQBAFg7X4/CAIjs8t+sXgu40MU2xfZ/BdwP4R3ykMqOK7gvd3165dKtMNfW6QgdYZPA983jD5wLtnTnf2+ZG8fqHg84ptwuuAzzE+C3jPNN6Xo/kOw4MPPqgCQthe/E5gX6j1JcSg/euvv64G3bsC24HsFHzGMMCOQDzeZwTnMcCNfSA+g7gerwOCinhtcBn7LmT5ecPzQZ81fI4QvMC+DqUz8ZlF9iFee3xmvP31r39V/YMQIEJAFb95eO/w24DAD94jLajhDxnO2KdiYB7br+13UfoO73UknyUNvk+YgIDnHA08HoTqQdfTtmzZos7xOfXeB2OyBX5rAa9VMLgeAVvsm7XfWG0/He42gKAFPiv4zYz0dv/+97/DBodCwYQJfEewD0LACkFQHBtin4UAjv97F83nUYNAO44RsI/GfWB/jOOozuB4A+vjmA+fZezj8NuH2+N7jeAd9oGxOGbsKuwP8dzxvUJQm4iIiPqQk4iIiPrMhRdeiKmnzssuuyyq20+bNk3d/uKLL3ZaLBbP9Zs2bXIWFxerZU899ZTn+j179jiTkpKcGRkZzubm5oD7e+SRR9RtLr/8cp/rzznnHHX9+eef72xoaPBc39bWph4byy666CKf29x1113qeu3+2tvbAx5vw4YNziVLlgRcv2XLFuc+++yjbrt48WKfZVhfr9c7U1NTnV9++aXnervd7rz55ps9j4nt8rZy5Ur13LOzs52ffPKJzzI8Rk5OjlqO1y4SlZWVzszMTPVY//jHP3yWvfHGG06DweA0Go3O1atXB31dcN4VL7zwgue5zZ49W732mu+++049nk6nc27bts3ndjfeeKO6zaRJk5xVVVWe6/E+HnXUUWrZ3LlzQz7Weeed5/PZevbZZ9X1Q4cOdebm5jrffPNNzzKz2ew88sgj1fK7777b5z4///xzdf0RRxwR9HqcDj74YGdtba3P5wDvF5Z5v9fRfnZCbUM42vfovffeC7p87NixavmBBx4Y8nn5n/CcXnnllYD7Wrdunfps4zXcuXOnOmmv56JFi9Q6jz76qPq//2c4GrF+Tzr7bDscDufMmTPVOvhc4vOiqaurc55wwglq2R133OFzO20fg9M999yj7sdbtPu1Dz74wOc7ofnnP/+p1sd76/9Y2rbgO6L54osvPJ8B/8e32WzOTz/91BkpfH9xX8OGDYvJPj+S168z+HzgtvhcBBPt5+Xdd99V1+P7unz5cp9lb7/9ttp/4rY1NTURbaf3dmCbGxsbPcs++ugjdT0+I3htH3/8cZ/fDvy2Yfkll1zic58tLS3O4cOHq2X47mFdTXl5uXPq1Klq2XPPPedzO3wmtm/fHrCN2I/gs4p9J+471G/mr3/9a/XZ0bz22mue7Q/2GQ9Fe14vv/xy2Ncs1Oft0EMPVcv//Oc/h/ysdvXk/d3pzAUXXKBuc9ppp/lcj99VXI/f7VCuu+46z75Gc8MNN6jrrr/++pC3y8rKUuusXbvWcx3eL1y3atWqoLfBb36w34Fw8JrjNtjn4/be/vSnP6ll+E63trZ2+/OofYe7+vprTj31VHVbHDNUV1f7LMP3zP/3qDvHjP6/H539rixcuFAtP+OMM7r8vIiIiCi2GGgiIiLqQyeeeKL6A/nWW2/t8m0xaIfb5uXl+Qyo+QcLRo4c6XP96aefrq7/z3/+E3AbBCOw7KuvvvIZ/MZ1o0aN8hkY9h74KCwsVIOC3gOC2uBAfn6+s6mpqcvPTwto3HTTTT7XYyAQ12MQyR+CWSUlJUEDTdrAx/PPPx/08f7yl7+o5RiIigQGbLH+scceG3S5NpjiH0TsbqAJwS3/gR445ZRT1PIXX3zRcx0GqNLT09X1X3/9dcBtfvzxRxWgwkDXjh07Ah4LA2579+71uQ0GPwcNGqSWYxDQ31tvvaWWIUDSlaAGtmH9+vUB93fNNdcEDVxF89mJJtCkDXTOmTMnYNn//vc/z+Dd6NGjfZatWLHC+dvf/tb5zTffqPcLg23ff/+953OI5/v+++8H3KcWGPQ+nXvuuWpZWVmZGmjG4J03BBysVquzq2L9nnT22cYgu/Z4wYIdCN4mJyerfYb3cu27tP/++/sMrHZnv9aZWbNmqdtg/9dZoGn+/Pnqut/85jfO7goXaIp2nx/J6xeLQFNXPy/Tp09X13/22WdB7/faa69Vy72DQuF4b0ewCQOTJ09Wyw855JCAZQggYBkG8b39/e9/V9f//Oc/D/qYCJBh+ZQpU5xdDf4g0Bbs+4P3Pthv7bhx49RyBLEidcABB6jbYKJFpIEm7Es2b96sArNYdthhhwUNbiHAi89WV0+Rfg/nzZunHj8lJcUn6APYr2oTHkK57bbb1DpXXnml57orrrhCXXf77beHvJ0WsP3222891yE4iOvwmxmMFsj0/x2IJNCE3wR/2P9p7533Pi3az6P2HUYwv6vwW6btdzAhoDPdPWbsaqDphx9+CBssJSIiot7D0nlEREQJCmVHAD0ftPIu3tBn5Morr1QlYFBSDD2EAKWQUNYNZaYuuugiz/oo14KSLCgn5F3KDWWTACVd0HPDH8qhoOQRSvSgdBrKuHhDCaNwTe1Rxg4lt1D6BOWZ0OMDk2FQdgpQbijY80avBH8or4NyU1oPKO/SVijvgtJYc+bMCbodWomscH06gm0HXs9gUKIPpXS0/iaxghI96CviD2Wq8B6gpJYGZaBQqhDvKUrd+EP5NTxvrewWek35P5ZWGk6D1xDlelB2y/+9BjwWeG9HJFACD2Wmgj2vUPfX1c9ONG655RZVxgul1FC6CqV5UBIQZdJQZtFoNKrSVP7lh1D6Tit/p0H5IPTiwH0+/PDDctNNN6neQd7QpwilkvC9Q5k8lM7SSqjh8fF4WjN7lAdEOTCUZtN606B3E/rRxEI070k4KKsIeD7BSruhBCbKIKJ8HfrX+T8P7INClXnq6n7Nu98RSi6hxB3KcWl9zlCWSvsMobReOHif8b1AqTSUXcM+pidKjUW7z4/k9evtzwv2Hyijhe+Sf48wDfZN6HuF7/d1110X8XZg/6Q9pjd8BlC6tCv7Le0zix5Sod57/L7hM4Y+Qih3p8HnCSXQsAxlSLG/Aq3/Fz5b6A8YrBRYsN9aPCd8N7ryvcPnG/z34/60nmD+UBr2v//9r/p8+8N7h75fPQGfDa0MLsrKRVNaOFH4/+4C3guUqP3DH/6gvvfaPq07n0fwLh0aKe0YEPs1lAaNdP1ojxm7Svtsa591IiIi6jsMNBEREfUhrYcNGjt3FQYSvXu3+MOANAb+/AcdTz31VFUXH315vK9HUAS8B2kB/TLgL3/5izqFE+x5aM3tg9m0aZPqMRIuIKD1iPB/3qHuN9j16B+g3U9nAyWRvhedvf5oQu+9XqyUlpYGvV4beEawJdJt1LYTgaZg24keMMFogcNgy7Vl3tsR6+cV7WcnGhMnTpRXXnlFBTLQcwsnDYIKv/jFL+TPf/5zl3pNoMcKgkUIbmCA1/8zi94W3v0uAEEU9HdBIKmwsFANqqEfDpqyox8HenT87ne/U4Er3G+wAb6u6up70hltX4KAGU6dfQ/9A03h9iVd3a8BerLdeOONakC2O58hBGwxGI7AIXqy4YTr0EPtrLPOUu9lsEH83trnR/L6xUJXPi9afx0EnDoLfnX197E7+y30dwr2mY2kTxR+Z7TXHD1oEChBr5qufrZi+b3THj9YYNKbd08w9ORDoAI9rrDvw4QDfE96C4Jp2I9hksQf//hH1Vcs1PuFdTrrr+f93LtzOwQLQ90u2G0ipfXmC3V9eXl5tz+P3dkHoGcYBAveBtPdY8au0vod4nOL72+w/n5ERETUOxhoIiIi6kNoEo6m4JjV2VvwRziakGOQFY+NwWlkTrz88stqMPTnP/+5z/pYpmVj7L///mHvO9ggRmpqasj1MbCFQAFm2WI7MJCBQQPMnv7oo4/UQDoyVIIJNXAbbNBSew547pihHUnwL171ZEZCVx8rltvS1fvqzmenqzCTG9kVyEZCNgIeY/r06TJ37lw1EApdmXGPYCcyXpB5heyEzgb/MLiJwMzMmTNVxgog4IWMCQxoIwNC+05cdtll6ruMAFi8fda07yEytkINpmuCZWCE25d0db+GjIlf//rXngwxBKoQgNAeA9kEGGSP9DN0zTXXqKASMlg+/fRTlSH4wgsvqNMxxxyjZvnjsfpSuNcvFrryedE+CwgOdjZojoBuLLcjmu1EdgaCuuFowd2ysjL1+UEA8/bbb1e/OQgaIJMDn0UEmhGcDvXZiuX3DvsaBPMQ1Ao3ySJYdhIyg2+44Qa59dZb1T4GxyvecL8IrnbV5ZdfHjS7EJDJiCxoBEluvvlmldETjLbPRCANQZ5gWdNagMZ7/6pdxnsUTFNTkycA6H87BJpwu0mTJkX0WD0hms9jd/cBXQ2Sd/eYsavwOwj4fjHIRERE1LcYaCIiIupDKJuDmcKYPYxZvJ2VaPKmzVTVZo/6QwkobSaq/6xWZGdgQBYlcTAgi/JjGPTGYLr/bHltQBjlTbRB9VhARgqeM7IzXn/99YDSPFu2bAl6u+LiYjUbHs8Nl/1t37496CAaSsigdNEzzzwTk2wPvKZ4Dnj9g5Wl094X/9e+N3X2GYmX7eytz0534DP0q1/9KuD6b775Rp0jmNCVgThtMDNcWUnNXXfdpTJUFi5c6BmExvMHBJ802mWtNFe80fYlGIRHQCzWurJfW7BggRroR0k2DKb7i+YzVFRUpAbRcdJKGyLIgMDTc889FzQzoyu6s8+P188CBod7qvxarLYTmT34nET6HUdJMASZEHj805/+FLC8J/ZPoWAfiYBQbW2tynbrCpQJRcAUZUMR9MHn2BsCPFrGYFegVGKwQBOyO/Eao2wl9rUPPfRQyPvIzs5W32kcC6BE7BFHHBGwDq6HyZMne67Typlqy0LdBpm+3tlJuB3KLmI5gtKRPFak8LyDBa+0Yxnv73I0n8fu0j43kZai7aljxlDw2YZgJYWJiIiod/XelFgiIiIKgNJQ6LehzYjXejiE8vXXXwf0FEI5LczC9YdyWrg/9J7wH3TETFPMEsdgNQZI0NcE/Gf9w4knnqjOkTmBXkexHhxAX5Zg/R9effXVoLdDOSqYN29ewDI8Xwwg+0MmAWZJY4Afr1csaK+/9tr5QyYDBBsA6y0oeYSSSBiY1gIi3lBiCwOJCF5or2siiPazE2v47qB/BrajK70v3n//fZWlhCBTZ+WIEIRGWTb0Ygo2iOldygnl83o7682bNptc63MUal+C4GBP6Mp+TfsMBcusQiBz5cqV3d4eBP60oNOaNWu6fX/d2ef35PsaDWwfsgCRCYKAXLyK5jMb7rOFoM/HH38svUXbZ6CcZjQQ7MHvJ0pSaj3CNMjSQrC2q6dLLrkk4HEQEEbgBBlDyMb0LlEaCrJ6AJmH/tDXCwEcBB9mzZrluR6XkS2JIE6wfozab4f//lx7LBx3+GeiYb+L0qaAcq5dhaxLf3gMbVu0731v7EOD0XooIeCoZQ+F01PHjKFon23/nohERETU+xhoIiIi6mPouYKSTV9++aXqS4DSMf6qqqrU7GLvQQwMPiCQgEEtzG71DlLhPlCyB0L1VtAGX5EBgIFLlFQJ1mAaj4FBFgzeomk1tiXY9v3zn//s0vMeNWqUGhBH9gWCHd4DLPfff7/Pdd4w0xmlXJ599lmf4Alud8cdd3hm9Pu788471YAZbh8s2IQgFHoVBRt8CuaKK65QgQJkTfg/dww6oXwXHq8rTexjDe+plkWBMmHe/RAwUI1lGDxGGbquznbvS9F+dqK1ZMmSgOsQiEBJPTzm3//+94CSPU8++aRnwNnbhx9+qD47gF4+4Ur9YJAO7xECWffcc09A7yj/QKd2ecKECdIXtODGxo0bgy5HUB2DgSgjhyyiYD1qMACM7060It2vaeXY8Jpp/VW0QAAGursSVMEg/AcffBBwG/QL0YIKsfh+dXef31Pva7TuvfdedY6sL/z++cPr984776jAX19BqUr8PiMT9oEHHgjaHwkD3RiE9/9sYdKD9+8lgsIIPIbr2xRryB6CSH/X/CFoqQWG/PdBsYLvHCaCYOIDPgv/+te/IirXhmMi7D+RLeidbYUSd1r2KUr7eU9GwG/yb3/7W8/kHu/3Ar/luC9kPCOw7w3lHVEGDt8B7ywd7KNR1hSPieM3bb/cFQgaIVvV24MPPqh+35AlqfXOivbz2F0omYjse5QzxLbg/fKGYwnv17+njhlD0T7b2mediIiI+g5L5xEREfUx9GpBwASD1vhjHRkOKKOCZvIYTNdKw2BAw7tMljYTFr0TUHoIt8VsXQzeYuATAxAYtLn66quDPu5FF12k+h88//zznnJWWlNlfyiPg4EWzLBFEAWzpFFbH+WBUE4FAxt4HtoAeiQw0xjbhgFhPAcMEuA6PFdk4GCA6JFHHgm4HV4DbDcGezDwiowhDMasWLFCDVLjPv/xj38EDOCjpw5eJ5TswoA3BtAwIIjnjEEPBA4wWITA30EHHdTp9mPwH68LXmMM/uB2GIjCNnz77bdqoAwBiGgGnmIJpZvQjwbBF3ym8FonJSXJF198oQaMkFWA7Uwk0X52ooXPHGbv4/1FnxMMiKKvGt7jJ554wpOV6A1BTwz447uCEk8IQqDkkVbyDgN3wcpqecNgIrI9MGjoX2IPg6TIdEJJK/SkQiN0vMfYf3TWh6ynoC8WSqFhe/HdxHcMg7wYdMQJ+zMEfzAgi/4vyPrDvg4Dpwj2YBAXARO83hdeeGFU2xDpfg3BpL/+9a9qv4HtRCkvBG7wvUBJTmQ0RJr9iGwlBM7w2cAgK8qV4fksXrxYBXeRudrdsnmx2OdHC59vPB4+awicYV8P+H9nGXmd3S8G1H//+9+r7/ABBxygXiuUOUWpSOyT8ToiiNfVPk2xgvJp6LuFcmnYTvTzwj4dvzkIUqxdu1ZNbjj33HPVbzjgtxKfa2Qj4vnguSHAgYwgfAfw2dMyXnvaySefrL6D+HxEC/syBGRxH8iqDtVfKVr4/cQxBF4jbOull14adD30ivL+HGCfjN9dBO+QdYPvBfoWYcIIgiK4TgsqecPnFusgsKT9JiJ4i+8+Jg4g0OUfGMZ24buH4w2UMkW2Dj772H9gn4XstWgDJ9iXY3+D7zKOqxBgwucKAS+87tindufzGAv4/mP/jtcM24gMaLzWyEjE93TatGk+pfx64pgxFHwu8VscrKQhERER9S5mNBEREcUBDGogawJlWdDXAYMkGEzAH+gIBmBGPgY2EMDwhkEs/JGPQU4MSmAdDARpQRWUUgo1MxiDu0cffbTn/8HKS2kwgIqBGQyOHXzwwWrA/LXXXlPbg0FBPH40M2iR9YEgB3pTYVAWg5h4Thgwx0B8uJnwyHpAdgRuhwwJZLngsjb7Hj11/GF2LQZiMNtZG3zDa4yBGQyeIUtq7ty5EW8/BnLwvmFwF6V/8JpgEAWZZxhURMZKX0NGBwaHMCCFQTVcxmcLg+GYoY7XLNhrFe+i/exEA4OVKLeEmdPIUqisrFSBEASbMJs9mNtuu00NzOG7jIFyZGbgMrYN33P8P1w2E/qUYCARg2fBAll4zxBowHcYzxn9Q7AeMqYQSOwLGOzEZwsD6wi+YLARGQIYjPXe1+F1Q6AJQU6sh+8NrsNrjCARvofRinS/hkFSBGAxqI3vCPrqYN+AQDTeZ/SAiRTeI2RMYjAV+0Z8RvCZxMDqww8/rB4H+9BY6M4+P1oIEiKoi0F+LesDJ+zzuuuWW25Rrw/6a6EEGb4rKC1ZXV2tApLYz/d1WU8EjfA5xeQGvKfY5yMLBZ8XBDuQRXnfffd51sf3D/t/vEcYTMd3EgFjvI74LvRm9iiCplp2iff3sCuwvVqg9O67747xFnaUGkQwHu839hvBTtgn+sP3F7/jxx13nJpogP0P9kP43uE7jeCVP7w/+IyhLKC2z8Jrg8AUgk34LAaD7zf2s1iOySn47iG4i98A3D7acpX4nCCIhUA3MptQ8g8BQkxAwvPq7ucxFvB7g+1BcB77bRz7IRCPQBO2FUHA3jhm9IfjLTx/vE6YMEBERER9S+f0LzJMRERElMAw4IDBUAxqeJecISIiGmgw4I/gKzJnIul9RL0DQSEElZC1jsvUdZjQ8ec//1lN3GBGExERUd9jRhMRERElHMyO9e/vgtnQ6FmAIBNm38Y6q4WIiCjRoDQcssNQTjIWWWhE8QCljpFpiTKtDDIRERHFBwaaiIiIKOGgFwJKEqGnAXoRoHQL+uCg1BjKkWFADeWwiIiIBrq//OUvqjRbZ33hiBIFyiNiwhHK+REREVF8YOk8IiIiSjhffvml6s+D2vzoYYUBNPQcQqPum266SfUwICIiIopHLJ1HRERE/Q0DTURERERERERERERERBQVls4jIiIiIiIiIiIiIiKiqDDQRERERERERERERERERFFhoImIiIiIiIiIiIiIiIiiwkATERERERERERERERERRYWBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREVFUGGgiIiIiIiIiIiIiIiKiqDDQRERERERERERERERERFFhoImIiIiIiIiIiIiIiIiiwkATERERERERERERERERRYWBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREVFUGGgiIiIiIiIiIiIiIiKiqDDQRERERERERERERERERFFhoImIiIiIiIiIiIiIiIiiwkATERERERERERERERERRYWBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREVFUGGgiIiIiIiIiIiIiIiKiqDDQRERERERERERERERERFFhoImIiIiIiIiIiIiIiIiiwkATERERERERERERERERRYWBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIiIEmIiIiIiIiIiIiIiIi6j3MaCIiIiIiIiIiIiIiIqKoMNBERHFj+PDhotPp5Isvvgi5zqZNm+SGG26QSZMmSV5eniQnJ8vgwYPlqKOOkgcffFCqqqpC3ra8vFxuv/12mTFjhgwaNEiSkpIkPz9fZs2aJXfeeads27ZN4tGXX34pJ510ktrWtLQ0mThxojzyyCNis9miur+Wlhb5wx/+IKNHjxaTySSFhYVyzjnnyJo1a2K+7URERPGAxxg9e4zR2toqb7/9tlx55ZVywAEHqPtKTU2VMWPGyG9+8xt1DEZERNQf8Rij58cxjjzySDVWFOp09dVXd/t9JKLu0zmdTmcM7oeIKCYHaDt27JDPP/9cHUh4czgcKkj08MMPi91uV8GRadOmSVZWluzZs0e+//57aWpqkvT0dPn0009l5syZPrd/4okn5JZbbhGLxSI5OTlqOQ54amtrZenSpVJTU6MCT/PmzZPZs2fHzbv5/PPPy+WXX64Ono444gi1zZ999pna7hNOOEHeffddMRqNEd9fQ0ODHH744SqoVFJSooJsZWVlsnjxYhW0e//99+WYY47p0edERETU23iM0bPHGP/617/kiiuuUJdHjhypJgRhIGnJkiWye/duyc7Olg8//DDg+IyIiCjR8Rij58cxMD6EwBVuW1RUFLAcE48vvvjibr6TRNRtCDQREcWDYcOGIfDt/PzzzwOW/fKXv1TL8vPznfPnz3c6HA6f5RaLxfn88887i4uLnW+++abPsgcffFDdNjU11fn00087rVarz3KbzeZ84403nKNHj3b+9a9/dcaLbdu2OZOTk51Go9H5ySefeK6vra11Tp48WT0nPLeuuOKKK9TtTjzxRGdbW5vn+hdeeEFdP3jwYGdTU1NMnwcREVFf4zFGzx5jvPjii+oYY926dT7Xt7a2Oi+66CJ1f8OHD3e2t7d3+70kIiKKJzzG6PlxjCOOOCLkWBERxQ8Gmogo7g/Q3n33XXV9SkqKc/Xq1WHvo6qqyrlp0ybP/7G+wWBw6nQ656JFi8LeFgGWFStWOOPFb37zG/W8r7rqqoBlixcvVssKCgpUoCwSe/bsUQd7OJWVlQUsP+GEE9R9PvHEEzHZfiIionjBY4yePcYIB8GmrKwsdZ9ffvllt++PiIgonvAYo+ePMRhoIkoM7NFERHHvgQceUOfXXnutqusbDvo1oR+ARiu1d9ZZZ6k063AyMjJkypQpEi/Q6wB+9rOfBSw76KCDZNiwYapsIMreRQJl8VDG5tBDD1Vl8/ydd9556nzhwoXd3nYiIqJEwGOM2BxjhKP1aoKKiopu3x8REVEi4DFGzx9jEFF8YaCJiOIaavh+88036vIFF1zQpduir9N7770X1W37Gnopbdu2TV0+8MADg66jXb9y5cqI7lNbr7P7W7VqVVTbTERElEh4jBG7Y4xwMOFn+/bt6nKwvgpERET9DY8xeuYY44033pDrrrtOrr76arnvvvtUL0giih8MNBFRXMPBB8p8pqSkyIQJE7p0WwRq6urq1OVp06bFdLu++OIL1diyqyfcLhI7duxQ5zk5OSrTKhgtK0lbN9L7LC0tDXt/NTU10tzcHNF9EhERJSoeY8TuGCOcF154Qc1cLigokFmzZnX7/oiIiOIdjzF65hjjySefVKdnnnlG/vCHP8jMmTPllFNOUYE9Iup7xr7eACKicPbu3avOc3NzxWAwRHVbwOBGLGFG7sUXXxzV7SKhBXrS09NDrqMduDU1NcXkPr0PBHGfoQ4MiYiI+gMeY8TuGCOUH3/8UW666SZ1+f7771cTh4iIiPo7HmPE9hjj8MMPl1/84hdyyCGHyNChQ6Wqqko+++wzuf3221WLgNNOO02++uor0euZT0HUlxhoIiKKwtixY+XFF1/ka0dEREQx1V+OMZAhffrpp6tywOg3efnll/f1JhEREQ1oiXqMce+99/r8f/jw4XLppZfK8ccfr/p4f/vtt7JgwQI555xz+mwbiYil84gozg0aNEidowQeavxHc1tAyZZEos3yaWlp6TRDKTMzMyb36V0uL9L7JCIiSlQ8xojdMYY/zFI+6aSTZNOmTXLiiScm5KAWERFRtHiM0XPHGP5l+JDpBMhsIqK+xYwmIoprkydPVr2NLBaLrF27Vv0/UiNGjFA9jurr62XZsmWeWsCxgIGTBx54oMu3u/XWW9Usos4MGzZMnWPbcSAWrIxdeXm5z7qR3mdZWVnQ5dr95eXlsWweERH1ezzGiN0xhrfW1lbVL2Hp0qWq1A0adycnJ8fkPSMiIkoEPMbomWOMYMaMGaPOKysrY3J/RBQ9BpqIKK7l5+fLwQcfrFKh/+///q9LgSbU5z355JPl5ZdfVrc988wzY7Zdu3fvln//+99dvt0ll1wSUaApOztbBcq2bdsmy5cvlyOOOCJgHVwPkb4mU6ZM8bldd++PiIgokfEYI3bHGBpMDMLxFvokoEH3u+++K6mpqTF7z4iIiBIBjzFif4wRSm1trTpnj2mivscuaUQU95AFBH/7299kzZo1YddFibwffvjB8/+bb75ZBZxQr/fDDz8Me1uUlFu5cmVE23TkkUeK0+ns8gm3ixT6GsArr7wSsOy7776THTt2SEFBgcyaNSui+0PQzWg0ytdff+2ZReTt1VdfVeexDMgRERHFMx5jxOYYA2w2m8ydO1c+/vhjNbnlgw8+YCleIiIasHiMEbtjjFAwxoKxHpg2bVq374+IuoeBJiKKe6eddppcccUVYjab5eijj5bXX39dHVD4D27897//VQMbGzZs8FyPWTJ//OMf1fqzZ8+WZ555Rq3rzeFwyDvvvKMOTL788kuJF9dff70qNfPcc8/Jp59+6rke/ap+9atfqcs33XSTGAwGn9v9/Oc/V1lTCMz514lG/WI8f7yemHWsQXYWAnGDBw/21DgmIiLq73iMEZtjDBxLXXTRRfL222/LuHHj5KOPPpLc3NxeeheJiIjiD48xYnOM8cUXX6hMaf8xILQZuPTSS1WbBPR7wmUi6lssnUdECeEf//iHKif36KOPyjnnnCNFRUUqMJSVlaWymJYsWSINDQ3qAKO4uNjntrfddpuYTCb5/e9/L1dffbU6RzkX9CLS+jdVV1eroA7K1cWL4cOHy9NPPy2XX365HH/88XLUUUepQZvPP/9campq1HW//e1vA263c+dO2bx5s+zduzdg2cMPP6xmES1atEj2228/NYsI2U0oTYjnjxKDTDknIqKBhMcY3T/GwKCQlhldWlqqBpCCQdY0M6eJiGig4DFG948xVq1aJTfccIMa58FEYtxXRUWFqkajjQHNnz9fCgsLe/GdJaJgGGgiooSA8ncIkiDbBllJOEjBrBaUu8OBBjKZUBoOy5G54w8HMmeffbYK3KCky/fffy9NTU3qoASzZn75y1+qGTD77LOPxBNs07777isPPPCA2mZkdY0cOVKl4SPjCaXwugLBusWLF8v999+vDsYWLlyognVnnXWW3HnnnTJx4sQeey5ERETxiMcY3T/G0PojACazhJtEw0ATERENFDzG6P4xBvo8YcLw0qVL1SRhZEZhkizu77jjjpPrrrsu7sZxiAYqndM/95CIiIiIiIiIiIiIiIgoAuzRRERERERERERERERERFFhoImIiIiIiIiIiIiIiIiiwkATERERERERERERERERRYWBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREVFUGGgiIiIiIiIiIiIiIiKiqBijuxmFU1lZKe+++67su+++kp6ezheLiIion2tpaZGffvpJTj31VCkuLu6xx+ExBhER0cDCYwwiIiJKhGMMBpp6AIJMV111VU/cNREREcWxZ555Rq688soeu38eYxAREQ1MPMYgIiKieD7GYKCpByCTSXuTJkyY0BMPQURERHFk7dq1apKJdgzQU3iMQURENLDwGIOIiIgS4RiDgaYeoJXLQ5Dp4IMP7omHICIiojjU0yVzeYxBREQ0MPEYg4iIiOL5GEMfk3shIiIiIiIiIiIiIiKiAYeBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREVFUGGgiIiIiIiIiIiIiIiKiqDDQRERERERERERERERERFFhoImIiIiIiIiIiIiIiIiiwkATERERERERERERERERRYWBJiIiIiIiIiIiIiIiIooKA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREVFUGGgiIiKifqn+zbfE0dYWcjmWYR0iIiIiIiIiIoqesRu3JSIiIopLCCDt+v3vZdedd4o+O0t0Op3PcqfTKY6GRhGrVf0/Z/aZfbSlRERERERERESJjYEmIiIi6neyTjxBBZkQSEJACcEmaTOrABM4EWDCKSlJrUtEREQUqaPmH+W5jGMLi92iLqcYUnwmt3w+93O+qERERDQgMNBERL1m0/Tpokvx/ePLG/5Ic1osMnbpUr4rRNQt+tRUGbPkeyn75a+k9bvvxLTfKGmvKBdbWbnoTCkqyJR20EFS+vRTal0iIiKiaFgdVmm2NqvLNodNMpIz+EISERHRgMNAExH1WhkrZ1OzOM0WTxkrZ2ubCi6pwFOqyVPGCuuyjBXRwIHsIqfDgWiz6E0mn2X2xkZxtJlFnA4xFhb6BKpttbVir60Vp90hyfuU+gSMbHV10v7TT5J32aXibG9XwSZdSrLr8cwWBpmIiIgoalqmEv6WuWTRJbKieoXr/+KUz875LOTEOiIiIqL+ioEmIuoVKE3VsHChJ7MAWQQ/nXmmWHfsFENpiSQPLVHLkGHAMlYUC6pEGk46nc8f+whqOFpbVWBDn5Ym+pSUjmXt7WKtqhLBssxMMebl+dxn2/r1Ina76NPTJWXkSN9lq1eLvbFJdElGST/oIN9la9ZIe1mZiMMpmccf5/OY5k2bpG3lShUsyTz2GEkqKvIsw20a33tfnA67ZBxyiKROmuRZZm9ulr1PPa22xzRxgmSfcorPY+6+735xNDdL0tChUvDra3yW7XniSTFv3iw6g0FKnnjcZ1ntf1+Sxg8XqW0d+uhffLan8aOPZO+TfxOn0yGFv/+92ibP89iwQWUP4bXL+8UvJP/SX3iWOcxm+eHgWWpZ5jHHqPv1tvWUU8W6c6ckDx8uIxd94LOs8rbbpPmTT9XlMWtWiy7ZFSyCupdecr0GIjL8tdckdcJ4z7LW75dIxfXXq8svn5opM/ckyciydtfrahT5zbHbxPrOyer/LGtDRERE0fh+9/eeIBOghN6S3Utk5pCZfEGJiIhoQGGgKc6x1Bj1F8g0QHBJK2OFc5XBgAHzPXuktaw8oTMMHBaLGvAXvT4gIwNZFwhgIOCRVFjoswxBDXt9g8rWSNlvP9EZO3bL1t27xVpWpgIQpv3HiiE7u+M+a2qkbdUqcSLIMGaMJA8b1rEtbW3S+AECBXY1cJ82bZrPY9a+/LI428xiHJQv2Wec4bOsfsECad9ZJjqDXgquu85nWeOiRdLy3XcqAFFw/W98gjC4vn7+fHE6nCrAkDpxomeZZetWqbr/z+o54vG8HxMBiB0X/VwFINIPPkgG33STz2PuuPgSsVZWqmDJsBdf8FlWccst0vzFl+q2oxd/K7qkJM+yPU880RGAeP11SR0/zrOs6ZNPpOKG36rLQ+6/X3LmzPYsay8vl59OdgVs8i65RApv/Z3PY24/9zwRm03SZx0s+zz/vM+yXffcI5YNG8UwaJCM/vorn2V1//eyCrTCqFlf+wSaWr5dLNUPPaQup4zc1zfQtHOn7HnsMXXZkJ7uE2hytrVJrXsbsufMCQg0Nb77rtjr6sQ0fnxAoKl1xQpXho/Xa+Z5zLKd0rZsueez5M3R1CSWH390X3aViPFsj90uNgTpsKzZdxm+F9hetazd1cPAmxYI1PYJvsv0Xhvgt9x7mdNv2cd/8Fy8cle51FjSPYc9uhybvPzDatFpX7enDxH55TcBj01EREQDj91hF5vTJla7VZXCQ2k87dznst0qDy1xHcN5e2rVUzKjaAazmoiIiGhAYaApjrHUGPU2lJrCIDoGhY35+T7LLNu2uQaPnU6fIIKWkdG+Y6eI3SYZRx6pskQ8yzb/IC2Lv1VBmMxjj/UJNol7kBtlrFLGjvUJMiFws/vue9TAsmnCBMm78AKfx9x1x51i27tXjIWDZcjdd/ssq370r9K6bJm67bCX/usTvEG2Rt28V1WwBJkcCO5omj77THbfdbca7C66/TbJOvnkjue/datsm3OWK1vj4p8HBEQ2Tz1QPcf0Qw6RfZ77l8+ynZddLpaNG8VYUCCjvvqfz7I9jz4qDQvfVpdHLf5WjLm5nmWN770n1Q8/oi7v8+KLkn5Qx8xI84aNUn7Nr9Xlwtt+L3k//7lnGbJqdt12m7qcffZZAYGmvU88Kfb6evW6+geasC2tS5aoXlr+gabW5Suk/tV56rLKVvEKNKnMm/ddmShZJ5/k8xnB56blG9cgfipeJz/mtWvVeVJxccAy665dKtim03sFFNwQuHA0NrouOxziW6BEFzoAES444Z355LAHPCa2w6mWOYMsM7guIODoz+BeFiRYgqCe5zHtfsv0oZfhexrqPn0eM1jwRu8O7CDjyw+CYLq0NNfgiN9ifLdRvk4MelefI+9lqamSMnq02i7DoPyA56E+h3q9pIwaFfCY+N7gtsaCQYHLZh3sLrep933O6vM0RfIuvVQ9H+Mg39umpDZIwYQWldTWvC1VUmqNsnmoa9mYCqO0fJErpYfXit7oFGnZE/C4RERE1D0Op6MjMGP3DdIEC+AEDehEcLugy6K9ncOqtrs7kOHErCYiIiLqqqPmH+W5jPEaZEpDisG33328VmXROYONMlG3LF68WGbNmiV5eXmS7FXip6swhHdferpMNSbJCptVbm9pkVbVi8IuJqNRHigp8VkWOEecugpDmAhJ2PCHkdf1yE/J1enFoBOpczikxW/ZGINRMKS7x+mQMr9B3eOSksQgOql1OmQJgjheTklKlny9TixOkXl+s/xPTEqW8UaDuu3jba1i9lp2RFKSui2256k2s2z1GhCfaDDIb1PT1PP4t8UsH1utnmWDdDr5T2aW2tYP2tvlMbNvtsLCrCzJ1Ollvc0m17b4ZiQ8lp4hE41GaXM65ZTGBp9l15lS5Ux3hsYFjY2yy+uPs1OTk9X2QMa0vZJcZBanXSdN3w0SW13HQLVpvwZJG9ukLu+1GOTU11Pl/ewc9f8vre1yT2urz2O+lJkpxXqD7LTb5ZJm1+0096aly6HuINbxDfXq/dRckmKSn7szjq5qapIfvV67I4xJclc6sh5EHmptlUVWV5ktKNXr5d+ZWeryaxazPG32fkdEPszKliSdTpbbrHJzi/cnROQfGRky2mCUWodDzm5yBUY0t6SmyonJrtdhTmOD1Hvtks9OTpFfuQNvNzY3y0p7xzM50GiUh9NdjYafamuT170+P7k6nSzIcmU/LWq3yEN+WSkLMrMkV6+XzTab/NLvfX7Evc9pdzrlRL/3+Vcmk5yd4nrtLm5q9Pms4/N6izvAeHdLi/zP1vG5G20wyN/TM1TM4iWLWf6D7C83vEvzM7PU9+17mzVgWx9KS5fBer1UORzyu1bf1/XyFJNMMhrV/d7Y0iwdjyhyTFKSHJuUrO73H+Y2n20dYzDIWckp6nbvtVtkjVdgKEenk5+nmNTtVtts8pXX84CLUlJELzqpdNh9vltwdFKSuj2+z+95fXZgnMEgxXq9ut+vrFbxXjpEp5fhBteyTXa7NHh9BtJFJyPcy/Aa1Hgt07s/l1jW7HRKnd/POT4HYEWgxS9ipIVecdvuDaXEr1UXtkpBik7K/pcnrdUpsnaYTh48xxWo+t1rDpmwwylpgy0q2LTH4pTJL3UEyKPR3t4utbW18u2338rBBx8s8X6MQdTf1Jprff6fOT1TnTct9T1GyDP5lkQlSgj4STe4J4rgR1yPiSquy9p16tzgXg/LgpyHW+ZZB/dtdF/X3ft2T2wZiCa0mOXRn3ZLjcUgx77evWoNPMYgIiIaeH/TpI5KldJrStXlsr+XSduPbTH/mybWxxjMaIpjGIpFAEkLNuH81ro6cep08ufCol4NMmH4zajTqaHKJr/BTAyepolO/f3jPWgPw/V6tRzBkqU2q0+wBMsmGxGg0clim1UqvQaCC3U6OT0lRX1Al9pssswrQINhtVtS01SQZaPNLvP9AjR3p6VJgU4v1U5HQHDi5tRUmW5E4EfknKZGnwHWS1NMcqE7AHFlU5Ns8XouByUlyZ1prgDEn1tbfAaYC/V6+WuGa8B/vsUs//ALQLi2VSdLrdaAQNPpKckyymCUGocjINCEAfQT3IOIGCg3e73uhTq9THMHUrJ0vrdL1ulkH3cmQ5Z35gYSLRDQcQ8+4+9Hf3Y8hPtvRX8290B1sGXe7zreF+8xbZvX5ewUvWRl6MVh04lZr/MJAKUn6WVwhnt7dU6f+wz2J6qWUBKY5yJicTqlxYlWvIG3xYA8Buwdgsfw/Szjs73Fjmud0ug3kxEBtpU2q7pFRZAMka+tVsHf0j8FyWbBsh/sdmkNEtf/3mZTAQI8H2y3t3V2m/zT3KaWeX8/YIfdLo+2taplG70CUNpzvKelRX2+dwfZ1ntaW9T3Duv5e6ytTUxiVq+Pv5csFllgsaj7rfW77afWdvmqoV29b74hFlHP/Ti/oJUG36TZfsE3b7f4BZe8/ctidu0og/jUalWnYDbb7XJ/m+++QYNA3xN+AVhv//UKkvn7LMTjwXq7XZ2CQWB2ly14uKdFnLIuxO1wix3BMpnc/ANP3nw/MQkGA15JOtcgWJL7cpL7srHj8ocZOhn7ZbpkVhvlh31EBZnasUxcl/80zyrDy1JUICrlQN8BaiJKbPijbMgFQ9RlW73N548yGuB0vkEaz+UuBmW6FLDxDwoxYNOrnPgDx+E+t3ece18OugwH2Tav2+OPGhx22UUuGdsuzSaDvJfp+hswmLXpJtkxKFWG13A6KFEi40QWIupNeV4BpOyTO9pnDDpxkLSUhR4fixfMaOrB2caxigaiR4ZWakyXkixOi2sY11BQIPu++abqs+LdqB09VsRml8E33ySmsWN9enKosmA2m+RfdaXknHmmZ5m1ulr1JUG2VPaZZ8iQu+7y2YYfZh4k9oYGMU2aKCPmuUpnadBfpXXpUtGZTDJ21UqfZbv/dJ9q1g4jP/pQkvfZx7Osbv582X2n63GGPvmEZB13nGdZ2+rVrl4o+DJd+2spuOYan9dj85Sp6nLm8ccHNLLfcvwJrqbyw4bJSDS091L261/7NJXXe80G3/Pk32Tv3/+uLg9/bb6kTpjQ8bp++JFU/OY36vKQ+/4kOWed5VnWvn27bD3xJHU59+cXSZG7ZJlm08RJqj8P+g/595jZdvY5Yl63Tgw5OTL6u8U+yypvv10aFryhLu/3vy8lafBgz7La//xHqh56WHQGgyo3lz5rlmdZ64qVUnnLLapcXP4Vl/tsq72x0VVuzWiQjEMPk/zLLg14vxytrZJUMlQKfvUrn2X1b7wp1ooK0SUZZdDVV/ssQ68glJZDqa7MY44RQ6ZrFrHWg8iyZYvoFvxCUpL3qDJVWoaBKa9dnA6dWOqTJLXAIvsc4S5jlVEozhs3i72mRpXK0iWniCHDFejTODGojzJaWO6VPko0YCGwpE6OTk6xWMepSgvaHFYx280qndtss7jOHThvF7O9Xdpx7mhX/7c4XNd1nFvF7LCqc+1yu8Pmus6J/9vEgpMT17nOLc7gQbdgjljjkGvec3gymbQgkybZ6pQX/88sxl1JMuRwh+Q8uzmufvv7+nGIEhWKNVyy6BJVukorM7H0gqU8VogxlBYLV64sZE+bHihzFqyPTqjb2bvwO0K+9Dq9JOmT1MmoNwY991w2JIlR53se7nZhb++/zH05ktvhskErbRxDzkdGyyWZTlnh15fV31SzWV5s0onuph+69Xg8xiCKjzJW+Numsd01SdJkMElGckbcl7EiosT03a7v5IqPrvC57l/H/0tmDuloqRELsT7GYEZTAkDfCwQTdv7iUjWgr7Hv2ROQrmGtqJSWL109YOx+QQSn2exp4o7+LP79M7Tm7eiXE0DrcWMNMg/e6Dp4R5DKHwIhnsf3y+bRGb2a0Pvf1mAMczuvZUEe05CVJY7sbNFnucqceUsu3UdS9t/ftV1+mQDJ+46QjKOPVsv07gwlz7Jh+0juBReIzmiQlJEjfR8vN1cG33Sj2mbTAQcEPGbxQw+q6ZPeAUENglZOi0V07uwkb4U33ywFv/mNWmbI7ohiA/rxePfk8ZY2dYrs98nHQZfhtRn23/9IKEV/uD3kspw5s0MuS508WZ2CSSosVCdZLOKo7wgyaSWrQLsO56pnimqVE9hzxVuw12zA6+VAQ+88Tm9tS2/cR88uR9ahRacTs04n7ThHWU73/3HuuazXrtP7LLP4LAt9O3Xf7usdcRzk/XKiK99x8f66gCAT4LrHztLJX5bWSc7owN8LIkpM3+/+3hNkAgTA47lXihawCdqXxukOoji7EIjxWr9Ltwty+3C3Y8CmZwM2ngBKkIBNsMBLrAI2QR+3BwM2ier7JJ2s8OtVGQwCUUvM7RKfex8iioQWQPKfyIIqKJ+d8xknshD1Izguxwnfd9RB0v7vfT2OgfH9D7gu1G3EGfQ6u8MedtljKx4L2L6nVj0lM4pmxPV+h4GmBOe02YMHdgyGwKbyplQxDhniCqS4e6l4lqWkSOrUqWpZ8ogRAY+Tefxx4mhpkeSSkoBl2aecIqkTJ/kEgDy3O+EEdX8I0Bjz8wMavJc+8w8VxDKNGeOzLGW/kTLi7YXqPhHI8WE0yuhlS9W2BnvMEa+/JqEU/u6WkMvwPHAKBplhRXf8IegyBIHyL7885P1mnXhiyGX+z9vnfnNygpapS0jY4VoDg0wqewl9Zg6v9Q02Hdcm+uUvhh5gR1lDBhoCgw1Byt1R38C74ROk8QrW+AdxfAI57uUd6+jFrNeLRWcIXN8rmISTLY4PNiKlczrF5HRKitMpyV6XTQ7Xubrsfe5wnXuv27HMITtKjPJlkt9viJclmSbZvH8DB4CI+gn8gff0qqcDrn90+aNyz8H3iF3sQbNfOs2W0QI30d7O7/YM2MQ2YBNR4CXKgE2owAsDNv2Y3SpibRVpb3Wdq1ObSHuL69zaKvM7jzF5zEs18DiDqB9ItIksNPCCE/7XqYYR3o/jfT9+13X5fvBPtaRwP+8g6+Oy/3MMej/er5/XfQRc57ct3q95sOu07Qt3nf/2xbsV1Svifr/DQFMC0ErnIZvJu3QeAkP6dN+AUe6FF0juRRcGjW4i02XU558FfQyUOhv+8v+F3Ab/Unrecs4+O+QyPCZOwSQVFalTMHqTSUyjRwddhudm8Ms4oh7+Y8vSJGJpFDE3dlzGubnB7//acpwafK5r3GqU1urcgCCTer+NTp9gU+OWVsl5x1WqkKi78Elr14kncBM0wBMsi8criBM8YNSREeS/LrJ++oNk0UuKziAmnaHjXG90XzZKst51nqJPcp+7L3vOk3zO1cmQLCZ9sqTghMsGXE4SkyFFDdzpMGMa/eV8Trog14Vfx/mfM+SStM7D9U/lZsuMpuC94IgocTRYGuTljS/7DAJpNtRskHPePadPtqu/BWzCBV66HPDpQsDG5/bMsBm4MPlMBXtwagkIAAULCnUWNOpY7r5PR+edLM8zpcjKpNCVF3zWbWO5RqL+OpGlO9kFnQYaGJzoWnAiVMCCwQnqZ556+yKZsXuP6AYfIPLLbyTeMNAU57z7M6HHT3tFudjKykVnSpG2FSuk/NfXqrJ6KK+nlcAjcn14HCLtzR1BIE/QpzFIYKgxRCCpUcQWmwbaOSOs6jyr1OwTZPIPNjWWmSRnRKI07e5s8Dvel/fNfVhR4s3pELPTrs4tYndf1s7Rk8cu7er/rr48Fk/vHne/HvT0wTJPjx/3daofkPsc17t7AWFmTqLDwBpqgaPfiMlokmQVpHH9P8WY4rNMXed32fv/al1jis9lz3257w/nGHxMVN+nJMkKU0cfvnBlbb5qNsvhvbJVRBQrTe1NsqLKNatv6e6lsrF2Y9wFbKINvHQ54MOADcULu80roOMXwOlSAMj7Nt7rtEo8mGG2yOdlFZGtnFHY05tDRD3s64qvg05kwXVHzD9CknRJ/S5zgqgvjqPxD4FbdVk7ua8z6Awdy4Jd57e+/3U4D3Y/2jphrwty35778doWvXYb/NP7Pm6obVGXxbVc99mfZKejTV7ODl3aH6V7l6QkycyWPRKPGGhKoCATAko/nXmmWmYoKJDkoSVqGdbxDjZRP5ipZzN7BX18M4M6zybyCiz11eC60SSSkimSkuU6N2WJ7PzeJ4CELXsnI11dPq25RWUTINik1jFli5zx9x4KegRbxxDlfSR+DgRSr5H2b7abxWJznaPJqff/1XKb69z7smddbZnNdxn+738Zp/7Q1wEHAUGDNH4Bn1gEg7TbsDdC18wzRV589FWTQSa1WiU7jb3fiOJVq7XVUy5i6a6lsqF2Q5cHak7d91QZljUspgEb7z443E9TQvyN4RPQ8Q/mhAnwtEew3OGaWBb39EaRpHSRpFTXKVm7nOY6Jae5/58efPmi37n+FiOifgfBoIrmClmzZ42s3rNaVlevlvW160OuX2eu69Xto64FJzoNWLgH+UMFLMIFGyIKWOjDByf8r/N+nFDBCc9ttOBEsCCH//0ECXwEBDmCXBf0fvyuU7cJ9nqHuh+83nrf2+C6eO471Fuc798rl2QmJ3RVFgaa4ljjog9VIEmSksS85UfZcvzxYq+tVctslZUqEIVlWAfr5sx2BaEoDsrMBQ0CBcskCpFNFEHJhh6BgAuCQipIlN0RJPIPGqUEu87rNsYgO8ZHRos0V3n++70pRW4vcPXtKrTZZKbZ4huo2v80GYgHtcGCOd4Bn24Hg/yWoV9EfxAsQydF7xvcCRbo8Q/yBF3H/74NKWpgkQdC8W12k1VWRXiUc0ZjuyxYUS6XHhrYo5CI+kabrU1WVa9S2UoILq3fu171OgoGM4mxn262Noe9z8rmSrn/0Pu5/6b4hB6kYbN8OgsARXCbRMnwNnY1ABQmKKRuo53cyw3dnFjyCcrKM9BE1F8msqyvWe8JLOG8xlzTpfsoySiRjOQMT8Cis0yITgMWfsGJzrIpIs3U8A9OdBrkCHEdggTdDU6o+wkW3AkTnPDZXgYnqB/6PkmnMpYiqcqyxNwelz0gGWiKYwgc7b7zVtEZ2kXXslddh8p4TpVIYVfXoZUF/lxgkCkWZeaaOu0z1Gk2UYzKzEUlOVRQSPt/iOu8/48/vnphFgE+s0/nZvtG43dVx1U0HkEfNOv2CeYgK8fREezxz9gJFvDxDg6FCwZhnXaHq/9aosMM77Cl2YKUaQuX6eN9XwGBH2QN6ZM5aDiA4bva2m6X2pZ2z6mmpV0mt6TJvKb6iO6jxpklL26oYqCJqA/h9xCDOwgqLdm1RNbuXat+h4NBsH/ioIkyY8gM1RsBv6e/+vRX/aKBLsVzNpAlfDCn06BQJ8vtCXIciIlp/sEcFcDxDugECwp1sly7DkEmloMnoh76u6GsqcyVqeQOKv1Q90PYihsIcHRWhn1w2mB58cQX+TcpEUXP6ZT5qZFXZZmXamCgibro6UNk7NlVAR88D++AwNOHxGUTsF5rCNtZn6GQfYnc/0eQqa/gjymfAFCIIJBPNpFf0AhBpgT6gwzZTIjA+0TjTSm+WU1+kHkTLDgTNOvHL7gTLNDjCe5omUFBgkD9oq+Pzhg04OMp6dYDwSDMLiLqzh+AjWabO2hkkZrmjuCRdyAJy2qbXZcttmDls+7v0uOOMydIuR+ifsJqt6pgktZjCdlLoSZc4Lds/KDxMr1ougouTSqYJKk4fnL77Re/jfhx522ex0BTv80GaotBb6Aw1yVKTw1UBggZ4PHO+PFfHmFQCNlALG8TsTarXVjgnqhvtFhbZN3edZ6gEk51lvCl7oZmDJWJBRPVsQayZ+77/r5OH4cTWYjiZHwYFXtQaQqTdwIut7v+j4ls6vquXMZtbb6X1f1aY3fZYZPzTCmysmBQRE/3vLb4bEnBjKZ4hsZe4f6g8Q46xWkTsLDwhQ0bBPIOGoUJHPVV6S/U9vYuIddZNlHA8myR5IzgZeb6o/QCcbbskd0GgzyYnxew+IbBBTLCapV2nU7MSSaxvH68T/CnP/T1wWyozoI0AQEfd5An2DL/+/LuB6Qtw6xvor5kdzilvtU3WKTOVQDJoi7XtbZ7Akq4bLX3fpA3y8T+TEQ9CdlJKH+3rGqZylhatWeVKo8XDCYsjMsf5wosFc2QKYOnSBoGu0M4b/M3stzod5zgnSbt9F1Xjuz206GuwN8s+CM6bACoG0EhLLeHnqwUVzAZJ1QAKFSZt5Bl4LwDQF63QckL6lH21EFS02T229EEV2tOkyHsA0nU49C3cXvjdp8SeFvqt4Tt54i/nccNGqeCSlpwaVBqxyDvb5+bEvGo6bz3r5aZl62MxVMh6sNAjT1EQCSaYIwreBL15a4GhRKlT2QYM8wW+bysQiKSUSjxiCOQFKMyc1FkE6EZbZ/Q+WUOBSs5lx2+BxH+j9mCnM0Xcpbyzqad8lPDT7KtYZvrVFoq27Js0mpDffhATQa9rDFotUgdIi27pKcFLcUWrkxbmECPT9ZPiD4/7OtD/UG7zeETGKpFEKnZEhhIcp8QZHLEOG6EXW9OapLkpSdLfnqKOs/LwOVk1+X0ZFm6rVZe+n5nxPd53AHxeaBGlKjsDrtsrN3oKoW3e4msrFoZ8hgAEzHG5o1VQSVkLE0dPFX1OojUjKY6+dKrD2Qi/lHW58f2tnC9f8IFgLxLxwW7jZYNlCAThnAsGmmfn4DScZH0Bkrm3w8JzuFwypNjXpTHyn6M+DZ3sg8kUcw1tTfJ2j1rZfVeVxk8XG5sbwx7m30y9/EElHA+KneUKvseynnNrbIyI7Lg/XnNCVL+lHqWFqgJCIgEy7Dp7HI0wZ5uZuRQ7MoMG5Jcx32Y/O1zOdn1/2CXt/0vcSZPhcBA04AsMxdJSblQQaOmvi8zF2k5uVCZRBi4SKAyc/GswdLQEUhq3Cbb6l3n5U3lUWUgITU9OzlbUpNSI8768S4BF6zsm/ft1bpewSE0kSQa6MxWuyfDqAbl6Pyyjjxl6tzXNZljn0Vq1OskN903UOS6nKICSHlp7utwOT1ZctOSxaAP//09cvRgeX15uZiDltXzZUrSy1kHlsTwGRENPJgxvLl2s6cU3vKq5dJsbQ65/ujc0SqwhKylAwsPlGxM5qHgbO3d7A0UJgCEU59N/uoqXefBnKC9gSIMGuHvDAP/PB7o5XtxvLOrwSyV9W2u84Y22VVvll0NbVJZb5aqRrPYujiD5mP2gSTq9jHGT/U/uTKV9q6R1dWr1aTWcKXu04xpMmHQBE9gaULBBMkzBVZWCWeG1Znw2QWJGagJEyjptBRZdwMw3czC6QftF+IqUINAsArSxPoyAjzu4I76fySXI3wMfVL0Y86PjBaJdPJcnOKRdH+BPy4/vit4YMjS0FF+rq/LzAXLDAoXNPK5LtP1paVeP6jb3bJbBZN8MpQatkmNuSbi+0lPSpeC1AKVzh4KglMPHfEQeycQdWOApNli8ytP1xEs8ulz1OwqU9faHvtZ5ilGvStQlOEKCmlBIy1Q1BFIcmUkZaUaYx74zU5LknvPGC+3LFjT6br3nj5eslP5+0LU1eMDlKRBUAml8FASL9xM4pHZIz09lqYVTpNcU24/ygYyR1DmrbMAUJjScH11/N5V+EM80j4/wZaHvI37ZExhNhB1rwdkm80VOHIHjXZ5gkjuyw3o4Rr7XlyN7ANJ1OUJrd4l8NDTMdzkFRieNdynBN5+OfuJYSCWEsVxSZeDJl7Bl5hk3nQj8JMo/RAToVSvd0Clq5e7E2gJeTlYdk+wy90I1AwgbXHaA5KBpv6ivVnkm8d6qMxcqPJyfkGjcNlELDMX99AHaXvDdldmklcwCdeZ7ZHPdB2cNlhGZI+QfbP3VefqlDVCBZl+8eEvwgaa4KlVT6kZzsw2InKVZ2los3oFiCwdAaRW36CRdrndHvuD8/RkgyuzCMEiv0BRR6ZRx7K0ZENcfIcf/mizZJiM0hwmCwvL504v7dXtIkrUQVocF2il8JbtXha2oTYGfLQeS9OKpvn0POhTGBgpWxIYzIm2N1CIPlPxR9dJMCdUGbgIg0a4jtlA1IdaLDafAJInkOSVndSdyTWYRDMk2yRDslPlx+om2duFMlnsA0kUvtQuJq4gqKQFljobM8hIylDZSpMGT5KJgyaq4FKfZ0bbLCIb3wleoixoRk53yqCFychhoCZGdMFLnPVKoMUv6BLNYw3EIGs/4HA6JdIQGyrNtMdhD0gGmvoz/MHXaTm5TkrQ4Y9HRpL7lTpznSeI5J2hVNFcETb13Bt6DQ3LHNYRSHIHloZnD1eZS8F8t+s7WVG9otP7xjoYwJo5ZGaXnxtRvLPZHSpAVNdi9S1T5xUo8r6+rtUq9lg3OEK2T2pSkECRb7DI+2RKStwD1dQkgxocQolAc7tDHIKDN52YkvXqeenjICBGFK+BJfRbVKXwdi2VpVVLZW/b3pDrl2SUqGwlBJemF06XwvTCnisFjez9pipXaQmcEACKVGuNyHPHSdzBwECnWT8RBIBCBYU46YsSGH7Dd/uXsUMWklberr5NGrtR2hclfIuyTVKcnSpDclzBJFdQySTFOa7LOB7SJtE89/U2+eO7GyK+f/aBJOpQa65VwSQtYwnZSm1hJm2gj+PInJGebCUElvbN2Vf0yNiI5bGFuUGkabdIU6XrvLHSdbwRKXO9yLwLY7dN/SJQE21wxT/Q0p0Mm0izePx75iTu37+UwOV7JVsczsgmstQ4s2RxHPaAZKCpv0jNFbn4Ha+Sc1mcVTjAZwVVtlT6ZCZpgaV6S33E95OZlCkjclwZSd5ZSkMzh4ZtmhnM/M3zI1533uZ5DDRRQrDY7EECRV49jfyuR3ZSrKFVkXdQCKXoctOTArOPvPobJRkGRir60tuP7etNIEoo6LGoSuG5s5aqW6tDrjskfYgnYwmnIRlDul+Tv2VvR/AIgzzNOFW7L2vXV/VNFlFSpAGgMNeFuw3LQ9MAZbU7VBBJK1+HTKTdWiDJHVjCMVR3jpMGZ5pUAKlYCyDlpEqx1/mgjBTRd9L70dvZU0vk4UWb2AeSqLPvt8MqP9b96MlUwnlZU1nY22QlZ3nK3+EcmUuZyZnRv9ZWs+t4onGXSJPXSf3fK7CETOV4E5P+MdGUTvMPukRwOSBAxEANkXelGkw41o53cJzjOndNotGut9juka44OA57QDLQ1F9gR140oa+3gnpZq7VVdjTucAWSGrepBpk439GwQ9odkf9BhsGigHJ32SMk35Qfs/JX5405Tz7Z8YnPdd4ZVJip5L0uUV/MIEFJFZ+eRn6BojrPMtcJ/ZBiLcmgC5pdpAWLtH5H2nXITurK4AgRkQY9GFVQadcSFWDCJJVQBqcOlulDXIElBJiQwRTRMYI2wBMQMNrtdV4t0rJHxBn7nnEBENQ59IYQAaAQQSFkAzHDn6jLkJW9p8nim4nkl5G0p9mikgmiNSgj2ZOBpGUfeQeSBmemxHyCDftAEgWHzGfvEnjr964PW4YfWUmjckb5BJZQejei4ws1QWWPV9AoWBBpl0hbbe+8XZjwffx9gcGeaDN3EKhh5QWihDjWqWnGsY5vAMlz3tgmVQ2WHmlxEI89IBloIkqAwe8ac01AdhJO4QaE/CXrk2VY9jBPdpIWWBqWNUzSMIjSw1BOJz813+c6pMjj+eFAMtWY6rMuUayaPnuXousIIvllHzW7LvdEA2iUbvMtT9cRLPIEkjwBpGTJSDHGRX8jIup/9rTucZXCc2cthZtVjMkmKqg0xFUKD8cLnn2TKjFT7xs8CggiVbsCTChFEws4VskoFMkscp2ryzgvEvnwNtf2RDoQdMQtsdkmooH+N0pLuwoguQJJ7jJ2XiXtqhrNYutGCeCctCQVRHIFjbxL2qVKcY5JlbtLMfbNrHn2gaSBzmq3yqbaTbJm7xpZXb1anaMcfzi5KbmegBLOxw0aF1h6H8cYbfWBZey0wJEWSMLxRncnqBhSXMcVmUNEsoa4zrUT/j//YpHW0GWDA45TDry4e9tDRHHX+qC6yeIVPHJnHzW6/r87Bsc6Rr1OCrNc5Xq37W3pUhZ3PPaATOhAk8PhkMcff1yeeeYZ2b59uxQUFMjcuXPl3nvvlfT04H1ivFVVVcldd90l7733nrpcVFQks2fPlnvuuUdycnJ65TkQaWwOmypZo2UnefdQampviviFQhNMLTPJk6GUNUKKM4rF0Mfpy5/P/bxPH58Sf6ZIfatvsEidq6wjS0AACdlH3fnBDyXTZPTKNHIHixBESgsMGqGMXWoyywYQUd/NLF5WtUz1WEJgKVxzbQz+TCs8UGbk7i8z0obKCKdBdBjE2bVd5MfvfANJCCLZQs9Q7pLUvODBo4zB7usxAFQokpwRembvp10rM0FEnQeRUO7XP/vI0yfJPVO3vRsTdDCxxif7yN0fqaNPkknSkuN7uIJ9IGkgqWqp8imBt6FmQ9gqKgadQUbnjvYEliYXTJYS0yDRYRIKjilqykW2L+2hMnY693GEV9BIXcYxRbHrPKvY1YIi3AQ/ln8j6rdwDIMg0e5G33J2KgNbBZLaVFZ2d4aUko16dTxT5A4kFbknzGCijHY+KL2jfG9/6AEZ30dunbjhhhvkiSeeUMGhG2+8UTZu3Kj+v3LlSvnkk09EH6bERXV1tcycOVMqKyvlqquukvHjx8u6devk6aeflv/973/yzTffSFpaz2d5hJVe4EoF9ub0Opj3bn6IdSkhtFhbZHvDdk8QSTvtaNqhgk2RQJk5BI78S93h/7mm3B5/DkSx+mGva+3oY+SdedQRQHJdX9dqVet2p7RKMPi7Aj2LctOSVFDIP1CkBYu0jCSsi4MFIqJ4VG+ul6VVSz2l8LY2bA25bpYuSaYZsmSGXS/T29pkv+pdot/8ou+xZrRQCkYLHHkHj9S51+X0wSLG5O4/HhF1CUr/InCkBZC8s5C0XgEoJxytFKO+o4ydO/vIP5AUj7Nwu4J9IKk/s9gtsrFmo09gqaq1Kuxt8pGtlLWvTDINlon6dBlnc0oqxrN+XC6y4j1XEKmtrvsbl5LtDhz5BY28/49jDZShI6IByWy1d5SvawxSzq7BLHubLd16DFOSXh3TFPkEjlLV5BnX/1PVOFNXqtX0hx6QCbvnXb9+vTz55JMyZ84cWbBggef6ESNGyHXXXSevvvqqnH/++SFvf//998uOHTvk5Zdflp/97Gee62fNmqVu9+ijj8of/vAH6VO//EbkkdG+12FmBwYAEGTyLneGdSmuZgHuadsTEEzC/8M11vZnMphkePbwjnJ3Oa7sJJSvMaFfAFEcaWu3e4JF3oEiND3UStPVei1vMse+vxHSjnM9pel8y9T5Zhq5znPSksXA/kZElIhQHrRhpywr+1KWos9S7Ub5wRz6GCPD4ZADzRaZ3maWGWazjG63SpfzLZFV5ClfN9gveORV1g5ZSr3Z0yjYhKuWva6SOjqDSPqg8OsS9bPBFdeMXL9AkrtPEgJJ3TkGQy9JbQDFNZjiFUhy90nq6sAKEfXt2MWull2egBLON9RuCDsJ1ig62V9nkok2kUktzTKxcY8UW3eKTlb3XBk7LSMpufPqRTHDyd9Ecae13eYXOPILJDWa1ZhTd2hZ194BJO//D8lKlazU2Lc8yE5LknvPGC+3LFjT6br3nj5e9euONwkbaHrllVfUD+L111/vc/0VV1wht956q7z00kthA02ff/65pKamynnnnedz/bnnniuXXnqpvPDCC30faIKbfujrLaBO6hKjv4FW7u6nendgqXGbylyKVJ4pz7fUnfs0JH2IapBJ1Nuwf22y2FT5Od/soiBl6tzL2qyxb+KOGbGe0nTePY38gkla5lFP/NgTEfUqu9Xd3Nq75xHOd0tzY6WsaK2QJbZ6WWKwyaYkozhD7PNSHQ6ZaraooNKMNouMbW8PfeCfNqjz4BFOKRkSl4JNzgq3LlGCl3mp9Ms+0krc4bruDK5g7o3WJ8C7pJ13RpJ3iRciSjzok4yyd2t2r5DVu5fImtqNsqc9fD/FwTabTLK0yySzRSZZcExhFVPEpSZClbHz+39nZez6Aid/E/WqJrM1IPNIO77ReiQ1dnPCMoIzPkGkrMBydpl9mHX98EebJcNklOYwzxPL504vlXiUsIGmpUuXqtJ4M2bM8LneZDLJ5MmT1fJwLBaLWtd/QBL3iQDUTz/9JHv37pVBg7xmQNKA1djeGLTcHXoq2ZyR7eQQMCrJKAkIJuGEvkpEPcnhcNXa7wgQuYNFnkwj30BSXYtV2u0xKJ8UZGaId6AoIPvIL6CUlmxg4IiI+of2lo7gkTqvVsEjVxBJCyjtFmmtQbhf3aRVp5OVphRZYkqRpSaTbEhJFnuSTgQn8f0DyORwyGSLRQWVppvNMs7qlCQVJNpHpKgoSO8jLZg0WMQQf7Phui05raMKAFGC9KKsbvIKGrmzj3Z59UlCmZfulBEelJHiDhr5BpC088GZKWI08DtDlNAcdveElV3ibKiU8tpNsrp2o6xuLpM17TXyg9MitjDxnCSnUw5AUMlikYkqsNQuRXb7wC1jx8nfRDHr/Rg0E8nTI8msSvt2B8aQOvohubKsvf9flAD9HxO9B2T8v7ohoLcSgkApKSkBy4YOHSrffvuttLe3S3Jy8Lrv48aNk82bN8uqVatUYEqD/9fVuerG7ty5s9NAU1lZmZSXl/tct3btWteFU08V8X/8k04Sef551+V//UvkjjuC3zHKAc6a5bp88MEi24M0b95/f5HPPnNd/uQTkYsuCn5fjzwicsEFrssoE/jFF4HrpKaK/PST6/KWLSKHHRb8vq69VuS221yXf/97kRdfDL7eqlUihYUiNptIaYgoK16ff/7TdfmZZ0Tuvjv4em+9JTJzpuvy9Okifq+3MmGCyEcfuS5/+KHIJZcEv6/HHkPamuvy3LkiX33lWYS/2XZn62XbsAzZ9tidrlJ3u9bJtvK1sjcr8j+4Ui1OGbHHJiP22GXfaruMuO0RGTF0ouyTUijJIzHbdkXgjc48U+Tpp12Xn3pK5I9/DH7n77wjMm2a6/LUqSK7dgWuM2mSyKJFrsvvvy9y2WXB7+vJJ0XOPtt1ec4ckcWLA9fJyRHZuNF1ecMGkWOOCX5fN94octNNHZdffjn4eriP3FyR1laRkSODr3PWWSJ/+5vr8hNPiPz5z8HX++ADEe27i+dcHaRc0IEHirz7bsdrd+WVwe8Lr/ns2a7LZ5whsmRJ4Dp5eajZ6bq8Zo3ICScEv6/f/U5Ey7T8zW9E5s8Pvt4PP4hkZoo0NYmMDjELG5/Rxx/v+Ow++KBnkU2nl9qUDKk1ZUrt409JTWGJK1D08GNS6zS6rteWmzKlzpQh9h4YbMtO1kn+nl2SZ26SPEuT5OPc3Kz+n3/8UZI35zRXAOmBP0ruG/PEFKwEw9atIuiJh33vAQcEfyBkqP7lLx37NO2yv08/7bgP7CPr6wPXwT71jTdcl19/3bVfC+a550ROPtl1+cQTRVYHKQUxZIjICvd3etkykdNOC35f2Nf/6leuy7/8pWu/Fgz29fhdq6kRGT8++DoXXijy8MOuyw880PEZ8Yd9/ZgxrsujRok0Nweug3299hmdN6/js+sP+3rtM3/88fihC1ynpASzQFyXv//etV8LBvv6q65yXb7iio7vqL+yMhGjUaSqquO77g/7em0fcf/9rv1aMNjX77ef6/K++4q0tQWuc+SRSJd2Xf6//+vYp/n7739Fjj3Wdfnoozv2ke3dS88PhscYiXCM4RRBJds0p8hvrxI5cH9X8Gje8yL1FSKpTtcynCJoRWTW6WSVKVmWpJpUYGldSrLYQvwhkexwyiRDhkxPK5EZmSNkwp9flORmHaJTIq0GEVV2vEbkzMP8jjHcx3ED5hgDg2NNHccYGh5jhDzG8IHP/MSJrsvjxonU1gaug4l/Cxe6Lr/5Zsfvnb9nn+34ncR3dPnywHUGD+74vcV3HX87BYO/Q667znX51792/e0UTJwcYzhEJzWmTNmVniuV6Xmy6/JrZNfQfV2ZSd8ul12SIlVpOWLvRuN5lKsb0rRXiiu3SVFLnQxpqZXiVvd5S60UrloiKempPMYAHmPwGCMhjjG8YD+Nvw3NDSJXni+ycZlIutN1SnOfZ+qkdcRgWWerkzXJSbI6JVnWmFKk1uC3X/E7rCi22mSixRVQwvlYS7sk40+2vFKRQfu7+inOe0+kxX2MgXPt8qmn+B5j/IrjGAqPMXiMMYDGMTCWWrv+B9nV5pDd5Xtk1+/ukN1pubIrLVd2p+d6LrclBY7fd0VBa70Maa2TIhzboDfSubNdAaTl38qQh/4ohS11geNN2NcfmFjjGEsjHcf4W3yOYyRsoKm1tTVokAmQqaStEyrQhJJ7b731lsydO1cee+wxGT9+vOr7hOuTkpLEarWq23fmueeek3vuuaebz4Z6U7u9XXY07pBtRY3y09Gpsq3AINsKjLK9wCBtKe6jriUPdNwgRJCpwJ4q+w6d6Oqh9PkaGfH+dyqwVNiIPyW9PHmESG4+0uhkoDv6L19IU2qmpLSb5a3m4Duzz5aVyVwZeMx6d3DIlKkGIupSMqTGsI/UfrjJFUCqGyK1J/7Os7whxas29Wd7RAQnERlzXNTboHc4JC9FJ3l5ma7g0MolkrdrpwocuQJI7mBSWrLkLnpbctOSJWntGpGTQgw0njldZLS7F4bTLBKmzjcRBeIxRh/SOzuCRLm1Isued2UebV0mcoKlI3iEdbTxm7LHRcrcl/Pdp07gl3C1O1tpSXKKrElNEWuIklRGu1Mmltlk+larzNhqlUk7rZKy6kuRfPcxxiUvxe75E1HEMMBSn5IulWl5siu9VHYt3u4q9fJTklSecLMKLmGQpd07c3ArTu5JfhnFnT5GplEnQ/aUu4NHtTJECyS11MqQS34mQ355maQmG1yDQJ+FmMxiZKYSdeAxRpyxmkXMVSJFdt/gkXa+5Q8i91/v6tmNuRQjXfueHUajOo5Yk5Isq1NS5Mdkgzh0oXsRIvv5gHa7TDJmyqSUApn4w14pWP6TVxBJL9KS6pqsss7rGOP64b36chBRfHA4RfY2ubOQjIWye+xRsksd7/gGktof+l/HjQ66sMvjUIPb6l0BpJY6KTr5GBkyfIirL9JVl8iQvRUyuK1BkpGt6T1h9kh3QOUHh0iTezyM+pzOify1BDRhwgSprq6WKkQI/SB49Nprr6nyeKECTYB1rrvuOtm9e7f6v8FgkMsvv1zd75tvvimrV6+WidoMvi7ONr7qqqtUVtXBiDhTn2iwNLiykrzK3eFyRXOFOFBKJQJGnVFKs0plRJarxN2+OfuqywguZSZn9vhz6G+m3/eJz//b2u3icDpV2qf649ht6e3uKHuCwm61td3u29PI3ceo47qOZShf19Ie+/5GyQa9X0k69ynN1fPIVZ4uxVPGDrVqWXOfKDqLFy+WWbNmxfS3v8ePMSLtadNfSobgkLe92dPvyLv3UUD5urYgWRvRNrZWfY5cZeqs6QWyLtkoSxzNstRcJauad4jFYQ15DDJu0DiZUTRDphdNl8mDJ0uqMTU220VEXeoXoPohufsi7ap3lbHTytvhuu70qTQl6aXY3f9IlbFz90ca4i75MqSPewVQ30vIYwwKKGMnjbtc59pJ/R/HIJUiba6qOuE063SyFgElFVhyBZca/LOV/JQmZcvErBEyKX+8TCyeKaOLZ0pSEo8liEjEZnfInmZL8HJ27v+jL6QN0aYoGfU6T+/Hjh5Ivj2RCjJYtrc/HWMkbEZTcXGxbNiwQQWT/DObKioqVMm7cEEmOOecc2TOnDnqgKqpqUnGjBkjgwcPVn2fjEaj7Kelp4VRWlqqTtQ3EDCqbK70CSThfHvjdqk1Rz5IlJGUEdA3CafSzFJJ0vMPu1jRAkgNrVZ5bXmZPPLhZjHbHGIy6uXqI0bL2VNLJDstKS4DR41tNqlBUMgrUKQuN3v1O/I6WWyOHqnT6h800oJFnj5HngBSsuqH5N+HjogSR68fY2CWrNbTJilNEobD4epr5BMwChI8wjmeYyygJ4E7eOTT70hdHuzqhZRZKLbkDNlQu1GW7F4iS3cvlZXV36om3KF6OR6Qd4BMHzJdBZemDp4qaYn0PhAlIEx60ppMewJJ6Ifk1SepqRv9AjDpRxtI0YJGWn8kBJYQYMpJS+LxGvW/Y4z+PpkFk1dQxs4TONot0ljpDhx5BZJw7OHseiAaf0luSzKqgNLq1FRZnZomW/UizjB/2mEyyoRBE2RiwUSZVDBJXc5PjSC9moj6HavdoYJEHQEk93ljRyCpusmi+kN29xinI4BkkiFZHYEknPIzUsQQoloD9U8JG2iaPn26fPTRR7JkyRI5zKufkNlsVn2WDj/88IjuB1lM3j2akN20cuVKOeKIIyQN9bwpLphtZlXuzjs7SQsoWeyRl6QrTCuUfbP39Qkm4f+DUgfxD7xeMn9pmdy5cJ0KMGlw+Y/vbpCHF22Se88YL3On9+zAKn5M61q9A0UdwaI6/0CS+7ruzOIIJdNk7AgQacEir0CRK5CUoq5DFpJ31hcRUbc8fUjgde0INNlFdAbfQBPW/eU3vf+C2yxeWUfewSMEjao7gke4HMUgTgAE2NILggSMfINHanmI2cB2h1021W2Spbu+kyVrlsiK6hXSYm0J/nCik7F5Y1W2kgosFU5ltjRRDLXbHGogpbKhzXPuykDqCCTVtQbPKIwEBk4KM1MCso9UVpI7OwnHdMwWJ0qwySwoY9fklW0ULIiEy92evKJzHV9kDpGGjMGyNtUka/QOWW1vlLVtu6XJbg576+FZwz1BJZxG5owUoz5hh/iIKEJmq12qG5GJ1Ca7GzFRxisTqdEVUNrbbFHx8O5kW6s+SN7ZSDjOUYEk13UYr+LEZvKXsL9C5557rtx///2qv5J3oOmf//yn6q10wQUXeK7bunWr6rk0duzYsPfpcDhUKT273S633357j24/Bc8aQRaSCiI1dmQobW/YrrKWnKoKcedwcIWDLgSRcK7K3bkvpyd59bWhPgky3bJgTcjlCDhpy7sSbMJAAgJHWtBIyzzyZB/5XV/fZu3Wj24wSBxCzyLfTKOO81wtaOTOSMK6yayVT0R9BWVcEKQJBkGbUMu6CztfS2OQgJFf8Ajn5iBNcKNhNAXNNlLnnrJ2RSLpg0T0hi5nVv9Q94Ms2eXKWFpetVyarE0h1x+VO8pTCm9a4TTJRmYUEUVV7gUzcb2DRp4sJJWd5Bpk6c5x3aCMFFcZO6/sI095uxyWeiFKuMksMSxj1ykTMp+HdJyytMtFYs8okq1Oi6xurZA1Netk9Z7Vsq1hk0jowwc1joEMJQSUEFyaOGii5Jhyur+dRBSXmdYdGUiuYxvvzCSMcXVHerLBM0mmI5DkW84ObRUYRKIBFWhCj6ZrrrlG/va3v6nydyeffLJs3LhRnnjiCZWNdP7553vWPeaYY2THjh0qkKFpbm5WJfJmz54tI0aMkIaGBnnllVdk+fLlct9998lRRx3VR8+s/7M5bJ5ydz4ZSo3bVF+lSKFHErKR/DOUhmYM5UyeOIRyechkisSdb6+T8SVZYrM7/QJF7p5G3llHze3dKmkSrpasp6eRX5k676wj7TwnLZkpwUQ0cKnBm72BwaOA8nXVIiFKx3UZBlg6Cx5hGQZ7YlRGFMeSW+q3eErhLataFvbYBccoWsbStKJpkmfKi8l2EPVnDodT9rZYArKPVF8kd3m77pZ7wbGbp4SdmqXrDiS5M5PQT4ATgogSZDKLfxk7nyCSVzZSlGXsAnov4tgjq9h1nlns939XMEmSOya41pnrZO3etbKqepWsKVso6/auC5ntrBmZPdKTrYRzHE8YujgZhojiS7PF5sk8CtoXqdEs9d3ItIYsk9GVieRdzs4rkMS+j9TTEjbQBMhmGj58uDz77LPy3nvvqb5M1157rdx7772i1+vD3hb9myZNmiQvv/yy7Nq1S5XJQzm+RYsWyQknnCDx4qj5kQW8Pp/7ucSbVmurKm3nX+4OJfCsIRpfB4PA0fDs4TIiq6PUHc4xWMMIe+J4fUW5T7m8cMxWh5z8+NcxffwUo95Tms6np5F39pF7GS7jB5qfLyIidxBp5/eB/Y68L2NQCSVxugsznVXgqDAwYKSCSu6AUvpgkSRTj789CCxhIszSXUtVcAmBpXA9IIdlDfMElnCO0rxE5PudQrk6735I6rzeHUhyz9q12p3dKk3sk33kLveinWOQxZTEAVuihNAHZex8M5D8/p+aG3byCibV/lj3o6zZs0ZlKq3Zu0aNf3Q2gVYFlQa5SuCNLxgvWclZ3Xw+RNSrPb3NCCJ5Hdd4B5Dcp+5OkM5NS1IBo+IgASTVKynLJOkpCT3MT/1AQn8C0V/pxhtvVKdwtm/fHjTQhAymRIMG0tiJYQAczR77GrZlb9ten6ykn+p/Uue7W3ZHfD/J+mRXMMkrkIQTBmzi4XlS99S3tquyebGUkWIMCBR1ZBr5BpJwSks2MHBERBSN1r0izx/fvdcOZXL8g0davyPvy2n5XS5fF+vjmrKmMhVUUoGl3ctkT9uesJNhtKASzgvTC3t1e4niTaPZqjKRgvVD0gJLmFAUrdQkg0/2kXcASTvHMSIRJQi7VWTT+31Uxs7r/5jAYuj6vgNjIQgqaYGl9TXr1ZhNKOjPuF/ufq5MpUETZdLgSarEvx69q4gobifI+Jevc2UgdQSSWtu7ly2Jcr2+GUju86yOQBInyVAi4FF4nPPPVDrljVNkZ9NO2SdzH3lvznu9th3IQCpvKvfJTkLvJJyH60XgLzcl16fMnRZYGpI+hKng/Qh+hJdsq5Wl22tl6bY62VwV+WfEe7bG+TP3Ccw+cvc34o8sEVEcSM0LETzSeiK5s5FSMmNWvi7WKporPD2WEFyqag1d0qcovcgnsFScUdyr20rU130DtACSTyDJq6QdysJEK9mgd2cheZe0cweQ3H2R2DOAqJ9pqxV59We9Vsauu2MiP9T+IKv2rPIElnAMEU5OSo5PCbzx+eMlIzkjJttDRN0v1YuWDFomkqsfkhZI6ggsWSKszBMM/vwZnJniyjzK6gggefdIGpyVIilGZlpT/8BAU4JF0putzZ7LPaG5vdmTmaR6KLmzk8oay8TmjOwPR8zGwQxfFUjKGiH75rgylDBTJ9eU2yPbTX0Hn8Wte1rcQaVaWbK9Vsrrut9/Y2xRltx8wtiYbCMREXUDMosPuS4weISTMSXhXlpkXGtBJZyHGyQqSC3wBJVwKsksYXYs9UsWm10NqCD7CDN0PVlIKqjkutydvgEGvc7TcLojeKRddpW5w8Qili0mIlcZO/cxRzfK2HVXdWu1q/ydO2MJ2UoWuyX0fk5nkNG5o30CS5ggzP0aUe9DH8e9zRZPCTvX8Y1vSbuqxu6V6tWObVTZOhzTeAJJHT2SCjJTJMnAjEUaOBhoSiDf7/7e0xcg3AFOJIEBzNbVMpOQpaRlJ1W3VUd8Pyhph+CRf4YSyt2lYHYR9Us2u0M27Gr0ZCwt216nZoGEkp5skKnDcsWg08kXP4QuP+TvuANYfoiIKC6YskSOuk0S1Z7WPT6BJWSGh4L+j1rGEk44zuEAEfWHY7eqJktHHyR39pF3n6S9zaGP5TqDcd4ClHzxyz5SWUnuMncYaMGADBGRj6R0kePuiUkZu+5ot7fLxtqNsrra1VcJAabOWgHgmEELKOF8XP44SUOpYCLqUVa7Q6qbLD49kPwzkXDcg2BTtJIMOnfwqCNo5N8XCeXueGxD5IuBpgSB4NDTq572/L+hvcHTqykUq92qBlO8y91pp1Zb5M0y0chay07y7qGEPgSsJdz/ma12WVVW78lWWrGjTlrC1J9Febvpw3Nl+vA8mTEiTw4YkiVGg14aWq0y8/5PxBxB2rEpSS9nHVgS42dCREQDQU1bjSyrWuYJLuG4J1xJGy2ohAATjnEYWEpM0+/7JKL1lt5+rPS3si+YsasFkHwCSe6MpOoms3RjrEVlGhX5BZA8gaRskxRmmSTZyNm6RBSFlAyRGVf06kuHcRQEkVbvXe0JLG2s2ahK44Vi1BllTN4Yn8ASqrjwmIEo9hnW1Y2uTKSAvkjISKpvkz3NFulOkacUo94TOMJkGP8AEv6fl5Ysek6QIeoyBpoSKJtpRfUKz/+R0YTBk5lDZkqDpaEjiISSd/Wuc/RUsjsja0iHNO/SzFIZnj3cE0jSyt1lp2T34DOjeNPQZpXlO2plybY6lbG0prw+bDpxSW6qzBieJ9NH5Kng0siC9KAH3NlpSXLvGePllgVrOt2Ge08fr2rwExERdfq7ZWmQZbuXqWMlBJe21G8JuW5mcqZMK5zmyVoalTuKk2b6cT8hh9Mpep1OUpMTs+49BkNrW9rdgy3ufkg+Je3aul32JctklGJ3nwDvjCQtE4nNp4ko0ZltZtlQs8HTVwnnnVVyQelcBJO0wNIB+QeIyWjqtW0m6q+TmLXA0S7/bKRGV1CpOxnWkJZs8PR6DMhEynId7+SkJTFITNRDGGhKwGwmzfWfXy/J+mSptbjK6UUizZjmE0jSMpQQZEoycGB/IKpuNKtMJZTCw2lzVVPY2SGjCzM82Uo44Qc8UnOnl6rzOxeuC5rZhEwmBJm09YiIiPw1tjfK8t3LPaXwfqj7QZwS/IcrPSldDiw80BNYGpM7Rgz6xAw6UNcylY58+HPZXtMqw/PT5Iubj4rL4/tGs80naOR9rg3AdKcBtTbY4gkkBclISk/hn4NE1H9g34rei1pACeebazeH7TedpE+S/fP3l4mDJsqkwZNk0qBJUpRexIFooi5osdgCytchA6kjI6lN6rrR6xEyTcaOzCNPPyTXRBktoJSZYuR3l6gP8S+LBOCfzaRptjaHvM3gtMG+5e5y9lWXcT3Tuwf2gTcGXbQyeMhY2lETuoyiUa+T8UOzVUAJwaVpw3IlNz2522Vt0k1GMVjt0mLpyLhLTzGIKckgD3+0mYEmIqKell4QeF3LXhFkQusMIumDwq/bi1qsLbK8armnFN6m2k3icDpC9o+cOniqpxQeBo6Meh7uDiQo1fva8jI1sAE4f+7rbXL21BKVXd1bWtttAdlHnnN3ebtwpYg7g1J1nuwjNcjiF0jKTpWsVA62EFH/1mptlfU16z2BJZxqzDVhb4MgkspUcgeW9s/bX5IN0f+NS/3bQC3N6z2G1GSx+QSMvDORtIkxTebQwdxI5KYl+ZSu6wgkuTKTcMrg5BiiuMe/vBM0m0ljMphkVvEsGZkz0qfcXUZyRq9uJ8UnND/cuKtRBZRcpzrZ02QJuX5qkkGmDstxZSwNz5PJ++RIWnLsdxMoY4P71Yku4cvaEBElpF9+I/LI6MjX7eVBo1XVqzwZSxhAClUKOMWQIpMHT1ZBJZzGDRqnZibTwDR/aVlA1jQu//HdDfLwok2qhG8ssqaDlX6prPc9RyniaGGiD/oeefogucvYeWcnoScmJ48RUVzym6CCnONXdC3i1Imc2Nwq+WkFUU1mwdgIelB7l8BDVnO4dgE4TkDZO60EHoJL6DVNNJBL83p/p3C8ErSUnVdmUncmxsCgDFevR610nW9Ju1QpyjIl/GtJRC4MNCVoNpPGbDfL+fufr3o1EaFx4pryBk8ZvBU76tTsk1BQm3basDyZiYylEXkyrjhLkgw918y5v87yISLqF5LTRJAppOu534FQvRMwYKQFltbuXSs2R/DfLgSRMFiklcLDoBFnIZMWZArXBxIBJ215uGCT1e5QfY+8g0bIPqrUBmHqzVLTEn3/ALSxHJyZ4pN95B1AwvmgjBQxsAE1EfWTySzfJ+nkzzl56vLz2dnyaZ0tosksyGjGMYF3YKneUh/2oYdmDPUElSYXTJbRuaPZIoAGVGlejcPhlNrW9pCZSLvVsU6bmK2Obh3TFGSk+ASN/C8PzkqRFCODSEQDBQNNCZzNpHlq1VNqwIWzGgeeJrNVlu+oc2UrbauTVeX10h6mlj9KrCCgpPVY2q8gQ/QcyCAiGpCO2mdoROt9HuPHbbe3q8EirRQeLrc7gg/co+zdhEETPKXwMHjEZtwUrFweMpkiccfCdWrgAxNxPIGkhjZPmTtkfjvC9KqMdNauq3xdR98ALZCETKWenNRDRBRPsDt9Or1j2KnBoFfX6fzWQ0nc7Y3bZXX1almz1xVY2lK3JWQPRq1c7rj8cR3ZSgUTZVCqV+lfon5YmlerXFPTbHEfw7iDSAgc1bsDSY1tUtVgkXZ79EEkTHgpzEzxKV/nm42UqibO8JiGiLwx0JTA2UwarIOBGmY19X8Y/EBQCdlKOEdZvHCDIfsNznAHlXLVeUluWm9uLhERJZA2W5ua5IKJKxi8iRWrwyrr965Xxyo4YRAJGdnBGHQGVf5Oy1jCbOS0JP52UXivryj3KZcXjsXmkIueXxLVS5qdmhSQfaT6I7mzkxBEQr9JIqIB76Yf1Evw/a7vZMVHV3Tsg3U6WXLBf1UPxXV71snqVU/L6r2rZe2etdLY3hj2ZRuWNczVV8kdWBqVO4p9GKlfleYFm90he5otagKMd/k6BJJwjhMyr23dmBWTZHCV6NUCRurc/X9tggyzq4koGgw0xbH5m+dHvO68zfMYaOpnMNhXVtsmS1RgqUb1V9q2tyXsjBOUvkNAyXXKlfyMlF7dZiIiShyfz/XNVTrljVNU74N9MveR9+a8F/X9ouzdxpqNnlJ4mBCDIFYwep1eNeHWAktTC6dKelJ61I9NA9PHG3Z3+z7Skw0d2UfefZG8ytulswk1EVG3K7T8+tNfh5xwokkzpsmEggkqsIRejMhuzjXl8tWnhC3NC6g+gyCRq2xdkHJ2DWapbjJ3K7M6xaj37X+kZSBldfw/Pz2ZlW2IqEcw0BTHzhtznqysXulzXa25VqWVY2Amz5Tnsy4lNtTQ3VzV5JOxVNVoCXsAMWWfHJmBoNKIPJm6Ty4HQIiIKOrBoGZrs+dyV9gddtlct9lTCm951XLVVyEYnehkTN4YTyk8BJaykrP4rlHUdta0ytbq0BNxgkE/geuPG+UTSMoyGVmGmoioFyq0BAsyjcge4clUwvnI7JFi0DNDlBKnNO+db6+TA4ozpdli9+mLhB6P2v/3Noce34lEahImxWiBI+9+SB2Bpdy0JB7PEFGfYaApjs0YMqNH1qX4gNksayvqZck2V4+lZdtrpdEcvPk5YABEZSq5eyxNGJotyUbW+CciotgMBmEyC1js4f8IxoSXH+t+9JTCQ2Cpqb0p5Pr75eyngko4TSuaJtkp2XzLqFvMVrssWrdb5i0tk8U/1XT59igtfMHMYXwXiIj6qN80JpmcP/Z8mTR4kspW4rEBJXppXrPVIac++U3Uj5WZYlTBIi1wpGVTe2cmcVIMEcU7BpoSDHomaP0TKLG0WGyyYmedLN1Wq8rhrSqrVwcjoRRmpbj7K7kCS2MKM5neTEREPT4Y1NDe4HOsgctb67d6SuEtq1om9Zb6kPeHWclaKbxphdMkPzWf7xrF5HO6tqJB5i8rk4WrKqUpzOSczhx3QCHfESKiPuw3jX5MmHzCPtPU30vzQk5akqcHkqcnkieg5OrxmGlKisljERH1JQaaEqx/AiWOmmaL6quEbCWc1lc2ij1Msd19B6V7MpZQDq80L5UBRSIi6vXBIGQ0Ldy6UNrt7Z7gkpbtFAx6Omml8HBekFbAd41ipq6lXd5cWaECTJt2B2bOoYzwaROL5cFFm8QSwaxjU5JezjqwhO8QEVEfZTNpnlr1lDp24CRaiteJwuiZ3RUoW3f5Yft6gkro/YjLqcksA0lEAwMDTUQxUl7X6umthPOte0L3C9DrRA4oznJlLA3Pk2nD86QgM4XvBRERxcVg0B3f3BHyNkMzhvoElorSi3p4K2mgwcScr7fsVQ24P95QJe123wASmljPmTpU5k4rlVGFmeq6jBRj2GbdmntPHy/ZqZw1TETUV9lMGqyDCS3MaqJ4Ov74duteeWNFhSrR22a1d+n2Y4uy5Jqj9uux7SMiincMNBFFweFwypY9zZ7AEsrhocljKOilNLkkR6aPyFXBpQOH5TI1moiIEmIwqDCt0BNUQk9IBJqIekJZbau8tqxMXl9eHnBchUk6R44ZrIJLR48dHNCncu70UnWOpt3B+ikgkwlBJm09IiLqGfM3z4943Xmb5zHQRH1u0+5GeXNFhby1qkKqGsP3Kg2HpXmJaKBjoIkoAla7Q9ZVNLizlepk2Y5aqW+1hm3keODwXE+PpYkl2ZJiZLo0ERElTmkblMR76pinZJ+sfVjWhnqM2WpXs4ZRGu/brTUBy0cMSpdzppXIWVNLVA+DcBBEOmFckWre/fCiTSrgZDLq5ZYTx6rbZ6cxk4mIqKedN+Y8WVm90uc6lOB1OB2i1+klz5Tnsy5RX6huMsvbqypV9tKGXY0By4fmpMpJ44vkP9/tkHaW5iUiiggDTURBtLXbZeXOOlniLoO3cmd92LRplL1DCbzpCC6NyFMp0wZMvSUiIkrQbKadTTtld+tuGZY9rFe3iwZGkHNdRaPMW7ZTFq6qlCazzWd5apJBTp4wRM6dXqqOrSLp3zH9vk8CJglp509/uVWdYOntx8b0uRARkS9kP/v3mj7ljVPUcUVJRom8N+c9vmTUZ+M8H23YrXo/fvXj3oAe2ijDe/KEIpkztUSN7+j1OhldmMnSvEREEWKgiUhE6lvbZen2Ok9/JWQv2fwOOrwNy0/z9FdCxhL+zyamRESUKNiom/pCXUu7Kkszb2mZbNrdFLB8cmmOCi6dOnFIt0sMpyYbxeF0ij6CIBUREcXWUfOPCshogvLmcp9l/gEpop5oe/D9tlp5Y0W5fLButzRbfCe3YILw4aMGyeypJXLc/oWSmuxbiYaleYmIIsdAEw1IlfVtnqASzn+oag65LsYnkKE0w52thODS4E5KtxAREcUzNuqm3oLZwl9v2atK4328vkra3ZlGmvz0ZJkzdaicM61UzRqOFjOViIjiV6oxVU1y4eRM6i1bqpvlzZXl8tbKSqmobwtYPq44S2UunT6pWFWoCYeleYmIIsNAE/V7OKDduqdFBZSWbqtVs1mCHWhokg161VNJCypNHZYr2ams6U9ERP0HG3VTTyurbZXXlpXJ68vLpbLB7LMM1YWPHDNY5k4rlaPHDpZko55vCBFRP8JMJeoLtS3t8s5q9F0ql9XlDQHLC7NS5MwpQ2XOlBIZUxTZ5BaW5iUiihwDTdTv2OwO1cxRy1Zatr1OalraQ66fnmxQwSStDN6k0hwxJfmmSxMREfUnbNRNPcFstcuH63er0njfbq0JWD48P01lLp19YIkUMjuciIiIuslis8tnG6tlwYoK+WJzdUALhLRkg5w4ztV36eCR+d3upc3SvEREoTHQRP1iUGPlznpXxtL2Wlmxo05a2u0h10eJFvRX0jKW9h+SKUYDZ9ISEdHAwUbdFMvM8fWVjSq4tHBVhTSafXsfmJL0cvKEIXLutFI1oYdlk4iIiKi7xx7Ld9TJGysr5N3VlQHHHmh/cMjIQao07wnjiiQ9JfqhT5bmJSKKHANNlHAa2qyyfAf6K9XJkm01sraiQax231kr3kpyU9XAxgx3cGnfQekc5CAiogGPjbqpO+pa2lVgad6yctm4qzFg+eTSHFUa77RJQyTTxBLERERE1D07alrkjRUV8taqCtlR0xqwfHRhhspcOmNysQzJTuXLTUTUyxhoorhX1Wj2lMHD+eaqJnGGjivJmMJMmT4iV2UtIcDEAwwiIqLOsVE3dcbucMo3W/bKvGVl8vH6Kmm3O3yW56Uny5wpQ1XT7NGFkfU+ICIiIgqlodUq766tlDdXVMiyHXUBywdlJMsZk4fK7ClDZVxxFicVExH1IQaaKO5SoLfXtKpMJWQsIbi0szZwporGqNfJhJJsV7bS8DyZNjxXctKSe3WbiYiIEhEbdVOkympb5bXl5bJgeblU1Lf5LEOrgyNGF8i500vl6LGFkmxkOWIiIiKKXrvNIV/+sEfeWFEun26sDpjYkmLUy/HouzRlqBw2ahBbIRARxQkGmqjPZ8ai3IrWXwnBpb3NlpDrpyYZ5MBhrmwlZC1NKc2V1GRDr24zERER0UDogfnh+t0yf1mZfLOlJmD5sPw0VRrvrKklUpRt6pNtJCIiov4z6Xh1eYO8uaJc3l5dKXWt1oB1Zo7IU8cdJ04okiyW5SUiijsMNFGvD1qsKW/wlMFbsaNOmiy+jRu95aYlybThHf2VkAqdZOBMWSIiIqKesK6iQeYtLVP9l/yba5uS9HLyhCEqwITBHh26bRMRERFFqbyuVRauqpQFK8rlpz0tAcvRY3vO1KGqPF5pXhpfZyKiOMZAE/WoRrNVlu+ok6XuHkuYoYI06FCG5qTK9OG5KqiE4NLIggzRoyYLEREREfWI+tZ2eWtlhcxfVi4bdjUGLJ9UmiPnTiuVUycN4QxiIiIi6pYms1U+WLtb3lhZLt/9VBt0wvFpk4plztQSmVSSzYktREQJgoEmiqk9TRZPthLOURbP4Qy9/qjBGZ6gEs4RaCIiIiKinuVwOOXrLXtVabyP1lcF9D/IS09WjbWRvTSmKJNvBxEREUXNZnfIV1v2yhsrKuSj9bvF4jcBOdmgl2P2H6yOPY4cM5g9H4mIEhADTdStGro7a1s9QaWl2+tk297AVGeNQa+T8cVZ7v5KeeocgxhERERE1DvKalvlteXlsmB5uVTUt/ksQxL5EaMLVHDpmP0LOchDRERE3RozQqY0gksojxesHzd6cCO4dOrEIZKTxvEhIqJExkBTnJt+3ycRrbf09mN7Zebr5qomFVT6HsGlbbVS3RR4oOBdx39KaUcZvCn75Eh6Cj9yRERERL3dI/PD9bvltWXl8s3WveL0yzYflp+mgkvogTAkm9nlREREFL3dDWbV6xEBJowh+SvNS5U5U0pUgGn4oHS+1ERE/QRH/RNMW7tdHE6n6HU6SU029OhjoZfS2op6WbKtTgWXlm2vDWgK7S07NcnVX8mdsTS+OJszYYmIiIj6yLqKBlUaD/2X/I/hMCHo5PFDZO70UjUhiD0xiYiIKFqt7TY1qQXBJZTm9Z/UkmkyyqkTi+WsqUNVFpNOx17cRET9TUIHmhwOhzz++OPyzDPPyPbt26WgoEDmzp0r9957r6Sndz4rorm5WZ544gl55ZVX1O1TUlJk9OjRcuWVV8rFF18cFz98/plKRz78uWyvaZXh+Wnyxc1HxfSxmi02WbHDFVRCObxVZfUBdXO9FWWZ3NlKrqyl0YMzOUhBRERE1IfqW9tVeZp5S8tUuRp/k0pzZO60EtVkO8uU1CfbSERERInP7nDK4q018sbKclm0bre0ttt9lhv1OjlyTIHMmVoiR48dLKaknp0sTURE/TjQ1NraKl9//bWsX79eqqurVeAGwaDx48fLIYccImlpad26/xtuuEEFimbPni033nijbNy4Uf1/5cqV8sknn4herw8bpDrppJPk22+/VUGla6+9Vm0vgk6/+MUv1H09+OCD0p/VNFtUXyUtsITBCBwohLJvQbqa8YqMpRkj8qQkNzUugnFEREREAxnKG6Mk3vxl5Wo2MbLSvaEnJsrToDzemKLMPttOIiIiSnw/VDXJghXlsnBlpexuNAcsn1SSrY47MKklPyOlT7aRiIj6SaDpgw8+kH/84x+yaNEisdlsqgGgNwQnjEajCvRcffXVcuKJJ3b5MRC8evLJJ2XOnDmyYMECz/UjRoyQ6667Tl599VU5//zzQ97++++/V0Gw66+/Xv761796rv/Vr34lY8eOVVlS8RRoami1ymvLy1StW8D5c19vk7Onlkh2WuezUfEelNe1qaCSFljauqcl5PpoBj2uONsdVMqVacPzZBAPEIiIiIjiRnldq+q79Prycqmobws4ljt8dIGcO61Ujtm/kOWMiYiIKGp7mizy9upKeXNluayrCMyYLs42yZlThqp+j/sN5qQWIqKBKKaBpq+++kplFi1btkyGDx8ul156qRx88MEycuRIyc/PV8GO2tpa2bJliyxevFg+/PBDOfnkk2XatGny6KOPyqGHHhrxYyHzCPeHQJG3K664Qm699VZ56aWXwgaaGhtdP4zFxcU+1ycnJ8ugQYPEYrFIvJi/tEzuXLhOzF6zU3H5j+9ukIcXbZJ7zxiv6uv7z2z9sbpZliCwtM0VXNrlDlIFk2zUy+TSHFfG0og8mbpPjmSynAoRERFRXDFb7fLRhip1fIgsJv8eCPvkpanSeGcdWCJDslP7ajOJiIioHxxzfLyhSt5YUS7/+3FvQAWc9GSDnDxhiMyeOlQOGpHPVgpERANcTANNRx55pJx55pnyl7/8RQ477LCQ66FsHsrVwZdffimPPfaYui2ynyK1dOlSVRpvxowZPtebTCaZPHmyWh4ObpeTkyMPPfSQCorNnDlTlc7797//LcuXL1cZWfEAgwi3LFgTcjkCTlhuczhk/yFZnmylZTvqpL7VGvJ2aMQ4bZirtxKCSxNKsiXFyHq5RERERPFoXUWDvLasTN5aVSkNbb7HeKYkvZw8foicM61UZo7I40APERERRQWTljGu9MaKCnl/7S5pstgCMqYPG4W+S0Pl+AOKJDWZ40hERNQDgaYVK1bIpEmTunSbI444Qp1WrVrVpdtVVlaqzKOUlMB6r0OHDlW9l9rb21WGUjC5ubny9ttvy+WXXy5z5871XJ+ZmalK8SFgFomysjIpLy/3uW7t2rUSq3J5yGSKxG1vhl9vcGaKJ6iEcnioz2/AEQIRERHFpZ48xqDEgGPBt1ZVyPxlZbK+sjFoDwRktaMHQhYz0YmIKEI8xiB/P+1pljdXVqgAk385XsDE5rOmDpXTJxXL4CwTX0AiIurZQFNXg0zekIXUFcg+ChZk0rKatHVCBZogIyNDxo8fL6effrrMmjVLlfX7+9//rkruLVy4UI477rhOt+O5556Te+65R3rC6yvKfcrldcXw/DQVUNKCS8Py01RvLCIiIkoMPXmMQfE9k/jbrTUyb1mZfLh+t7T7HQvmpiXJ7CklMnd6iYwtyuqz7SQiosTFYwyCupZ2eWdNpQourSqrDzphGX2XZk8ZqgJNREREvRZoiobD4VAl8LoqLS1Nqqurgy4zm82edULBjGAEl/7617/K1Vdf7bn+Zz/7mQo+odfT1q1bxWAInwZ82WWXyQknnBBw31dddZV018cbdndp/aIsk9xx6gEyfXguZ5gQEREluJ48xqD4U17XKq8vL5fXlpUHzCRGEvrhowtk7rRSOWb/wSx3TERE3cJjjIHLYrPL55uqVXDp883VYrX79l1KTTLICeMKZc7UEjlkv0GshENERH0XaBo9erTq0XTaaad5sopuvfVWufbaa2XUqFE+6/7f//2f/PznPxe73d7lxykuLpYNGzaIxWIJyGyqqKhQZfXCZTMhwISA1DnnnONzPYJTp5xyivztb3+T7du3y8iRI8NuR2lpqTr1hCZz5D2rID8jWU6ZOKRHtoWIiIh6V08eY1D8NNn+aEOV6r309Za94vQd65F98tJk7rQSOevAEhmSndpXm0lERP0MjzEGFqfTKSt21ssbK8rl3TW7Ano9ovjNrJH5KmP6xPFFkpHS53PSiYgoAcX812PLli3S1NTk+X9bW5sqR4eeR/6Bpu6YPn26fPTRR7JkyRI57LDDPNcjeIR+T4cffnjY2yMYBcGCXDabzee8r2Sauvb2sDY/ERERUfxbX9kg85eWyVurKgMGe1KMejl5whCVvTRzRJ7o2VOTiIiIorCzplX1XXpzZblsr2kNWD5qcIbKXDpzSjEntBARUbcZe2v2RKyde+65cv/998tjjz3mE2j65z//qbKoLrjgAs91KIFntVpl7NixnusOOOAAFah68cUX5ZZbbvFcX19fr/oz5ebmyn777Sd96bgDiuS7n2q7sH5hj24PEREREUWnodUqC1dXyLylZbK+sjFg+cSSbBVcOm1SsWSnJvFlJiIioq4fb7RZ5b01u1Rwaen2uoDl+enJcvrkYpkzpUTGD81iL28iIoqZhM2HnTBhglxzzTWqxN2cOXPk5JNPlo0bN8oTTzwhRxxxhJx//vmedY855hjZsWOHT8Dr+uuvl//85z+qrB/6HRxyyCFSW1urAlW7du1SWVid9WfqaWdPLZGHF20Ss18T6GBMSXpVVoWIiIiI4oPD4ZRvt9bI/GVlsmj9bmn3O6bLTUtSZWrOmVbCJttEREQUFavdIV9u3qOylz7eWBVwvJFs1KuJyWdNHSqHjSqQJEPX+6QTERH120ATIJtp+PDh8uyzz8p7772n+jKhF9S9994ren34H85hw4apsntY99NPP5VXX31VUlNTZfLkyarHFIJXfS07LUnuPWO83LJgTafr3nv6eM5+JSIiIooDFfVtqu/Sa8vK1WX/PgiHjyqQc6eXyjH7D5YUY99ObCIiIqLEg4nUaysa5I0VFfLO6kqpaWkPWGfG8DyZM3WonDRhCMeLiIioxyV0oAkZRzfeeKM6hbN9+/ag148cOVL+/e9/SzybO93VBPzOheuCZjYhkwlBJm09IiIiIup9ZqtdPt5QpbKXvt6yV/wrR5fmpcrcA0tVBnpxTirfIiIiIuoyTGB5S/VdqpAt1c0By0cMSpfZU4aqU2leGl9hIiJK7EDTsmXLxGQyqctNTU3q/Ouvv1b9j7wtXbq0Jx6+30EQ6YRxRfL6inJPKT2TUS+3nDhWzppaojKfiIiIiKj3ra9sUJlLGPBBXwRvKUa9nDxhiCqNd9CIfNHrdXyLiIiIqEuaLTb5YO0ulb303baagMksOWlJctrEYpk9dahMKc1h3yUiIuo/gabHH39cnbzdfffdAT92SPX1v46CQzDpskNHyH8Xb5ftNa1SlG2SSw8dwZeLiIiIqJc1tFpl4eoKlb20rqIxYPnEkmyZO61UTptUzFI1RERE1GU2u0NlSGMiy4frd4vZ6lvhJsmgk6PHDla9Ho8aW8BSvERE1P8CTS+88EKs73JAm37fJz7/r222qPOy2lafZUtvP7bXt42IiIhooHA4nLL4pxqZt7RMFq3fHdBoG7OJUaYGAab9h2T12XYSERFR4tpQ2ShvriyXt1ZVyp4m1/iPtyn75MicqSVy6oQhkpue3CfbSERE1CuBposvvjjWd0leUpON4nA6Rc9MMCIiIqJe6YXw+rJyeW15mZTXtfksw+HYYaMK5NxppXLsAYM5m5iIiIi6rKrRLAtXVajSeJt2u9pPeCvJTZU56Ls0tUT1YCIiIhowpfModpipRERERNS7LDa7fLS+SpXGQ9ka/14IpXmpcs6BpXL2gSVSnJPKt4eIiIi6pLXdpo413lhZIV//uEccfscamSlGOWXiEJW9NG1YLvs8EhHRwAs0Wa1WaWpqkuzsbDEYDD7L5s2bJ88995xUVFTIuHHj5I477pAJEybEehOIiIiIiKIqV4Pg0lurKqS+1eqzLMWol5PGF6nSeAftm88BHyIiIupyGd7vfqqRBSsqZNG6XdLSbvdZbtDr5MjRBTJ76lA5dv9CMSX5jqkRERENqEDTn/70J3n44YdVMCk3N9dz/aOPPio333yzON1TQjdu3Cgff/yxLF++XPbdd99YbwYRERERUacaWq3y9uoKmb+sXNZWNAQsnzA0W+ZOL5XTJxVLdmoSX1EiIiLqkh+rmlTm0lsrK2RXgznosQb6PJ4+uVgGZaTw1SUiooQU80DTV199Jccdd5xPkKmtrU3uueceycjIkAULFshBBx0kb775plx++eXyyCOPyFNPPRXrzSAiIiIiCjmjePFPNSp7adG63WKxOXyW56QlyZmTh6rspQOKs/gqEhERUZfsbbbIO6srVd+lYBNZhmSb5MwpQ1XvpVGFmXx1iYgo4cU80PTjjz+qAJK3Tz/9VJXTu+222+TYY49V11100UXy0UcfqWVERERERD2tor5NXl9WLq8tL5PyujafZTqdyGGjCmTutBI57oBCSTGyXA0RERFFzmy1yycbq+TNFRXyxQ97xO7XeCk92SAnjh8iZ00dKjP3zVel8oiIiPqLmAea9u7dK6WlpT7Xff/996LT6eTkk0/2uX7mzJkqw4mIiIiIqCdYbHb5eEOVKo331Y97xF3F2aMkN1VlLp11YIkMzUnlm0BERERdypJetqNO3lhRLu+t3SVNZpvPcsSSDtlvkJw1tUSOH1coackxH4YjIiKKCzH/hcvJyZG6urqAQJPRaJQDDzzQ5/r09HQVgCIiIiIiiqWNuxpl3tIyeWtVhdS3Wn2WJRv1ctL4Ijl3WqkctG++6DmjmIiIiLpg294WeXNFuby5qkLKan2zpGFsUabMmTpUzpg8VAqzTHxtiYio34t5oGm//faThQsXyo033qj+X19fL99++61MnTpVUlJ8mxqWl5dLYWFhrDeBiIiIiAaghjarvL26UuYvLQvaDwHNtlEa7/RJQyU7LalPtpGIiIgSU31ru7yzZpfKXlq5sz5geUFmipw5uVhmTylhj0ciIhpwYh5ouvLKK+Xiiy+Wc845R4466ih57bXXpK2tTfVk8vfFF1/I/vvvH+tNICIiIqIBVLLmu59qZP6yMvlg3W6x2Bw+y3PSkuTMyUNVebwDirP6bDuJiIgo8bTbHPL55moVXPpsU7VY7b41eE1JejlhXJHMnjJUDt1vkBgN+j7bViIion4VaLrgggvk3XffVQEmrf/SaaedJldddZXPelu3bpUvv/xSHnnkkVhvAhERERH1c5X1bfL68nJ5bXlZQMkaVGbGYM+500vl2P0LxZRk6LPtJCIiosTidDplZVm9vLmiQt5ZUxlQghfHGQeNyFel8U4cXySZJmZJExERxTzQpNfrZd68efK73/1OfvzxRxk5cqRMmzYt6A831jv88MP5LhARERFRpyw2u3yyoVrmLSuTr37cI07fScVSkpsq5xxYKmdPK5GhOal8RYmIiChiZbWt8ubKCnVCDyZ/IwvSZc7UEjlzylAeZxAREfV0oEmDnkw4hevlhBMRERERUTgbdzWq0nhvrayQOr9ZxclGvZw0vkiVxjt433zR63V8MYmIiCgijWarvI++SysrZMm22oDleenJcvqkYpW9hF6POqQzERERUe8FmoiIiIiIotXQZpW3V1fKa8vKZE15Q8Dy8UOz5NxppXL6pKGSncaSNURERBQZq92hMqMXrKiQTzZUBfR3TDbo5bgDClXfpSPGFEgS+y4RERF1ioEmIiIiIooLDodTvttWI/OXlskH63YHDPxkpyapQZ9zppXIuOLsPttOIiIiSixo37C+slEWrCiXt1dVSk1Le8A604fnyuwpJXLKhCGcxEJERNRFDDQRERERUZ+qrG+TBcvL5bXl5bKzttVnGSrUHLrfIFUaD7OLTUmGPttOIiIiSiy7GtrkrZWV8saKcvmxujlg+bD8NJkzpURNZNknP61PtpGIiKg/YKCJiIiIiHqdxWaXTzZUq95L//txjzidvsuH5qSq4NJZBw6VklwO/BAREVFkmi02WbRut7y5sly+3VoTcIyRZTLKaarvUolM3SeHfZeIiIhigIEmIiIiIuo1m3Y3yrylZfLWygqpa7X6LEs26uXEcUUqwDRrZL7o9Wy4TURERJ2zO5zyzZa98ubKChVkarPafZYnGXRy5JjBctbUoXLU2MGSYmSGNBERUSwx0EREREQ0AE2/75OI1lt6+7HdfqyGNqu8s7pSZS+tKW8IWD5+aJYKLp0+qVhy0pK7/XhEREQ0MI4xMIHljRUVsnBVhVQ1WgKWTy7NkTlTh8qpE4slL53HGERERAkTaKqrq5OTTjpJjj32WPnTn/4Ucr3bb79dvvjiC/nggw8kKysr1ptBRERERF3Q1m4Xh9Mpep1OUpO7P8vX4XDKd9tq5LVl5fL+2l1isTl8lmenJql+COdMK5Fxxdl8r4iIiPqpWB9jVDeZ5e1VlbJgRYVs3NUYsBzld3GMMXvqUBlZkNHtxyMiIqI+CDQ988wzsnbtWlm4cGHY9a699lp5/PHH5dlnn5Wbbrop1ptBRERERF2YRXzkw5/L9ppWGZ6fJl/cfFS3mm6/vqxcXlteLjtrW32W6XQih+43SM6ZVirHH1AopiSWrSEiIupveuIYA8GqjzbsVtlLX/24Rxx+fZcyUoxyyoQhKrg0Y3gey+8SEREleqDpnXfekdmzZ0thYWHY9YqKimTOnDkqIMVAExEREVHistjs8unGatV7KdjgD2YWI3Pp7ANLpCQ3ra82k4iIiBKIlh395ooK+WDdbmm22HyWG/Q6OXzUIJkztUSO4wQWIiKi/hVo2rBhg/zsZz+LaN0ZM2bIu+++G+tNICIiIqJegL4I85eWy5sry6Wu1eqzLNmolxPGFcm500pl1sh8ziwmIiKiiGypbnL3XaqUivq2gOXjirNUcAm9HQsyU/iqEhER9cdAU2trq2RkRFYDF+u1tLTEehOIiIiIKEINrVZ5bXmZ7G4wq//j/Lmvt8nZU0skOy0pYP1Gs1X1RXhtWZmsLm8IOvgzd1qpnDG5WHLS2HSbiIhooOrKMUZNs0XeWV0pb6yskDVBji+KskxyxpRimTOlRMYUZfbacyAiIqI+CjTl5+fLjh07IloX62F9IiIiIup985eWyZ0L14nZ5vBch8t/fHeDPLxok9x7xniZO71Ula75flutzF9WJh+s2yVma8f6kJ2aJGdOLla9l8YPze6DZ0JERESJdoxx+uRi+WxTtbyxoly+2LxHbH61d9OSDXLiuCKVvXTwyHxVKo+IiIgGSKBp2rRp8vrrr8tdd93V6boLFixQ6xMRERFR7w8A3bJgTcjlGAzC8k83VcnGXU2ys7bVZ7lOJ3LIyEEqEHU8+yIQERFRF48x/ANR2vHFofsNktlThqoSvOkpMR+2IiIioh4Q81/sSy65RM4++2y59dZb5YEHHgi53u9//3tZv3693HPPPbHeBCIiIiLqpJQNBnci8eH6Kp//D81JlbMPLFGn0rw0vs5EREQU1TGGd5BpdGGGnDW1RM6YPFSKsk18RYmIiAZ6oGnOnDlyyimnyMMPPyxff/21XHHFFTJp0iTJysqSpqYmWblypTz33HPy7bffyqmnniqzZ8+O9SYQERERURivrygPmEEcjkGnk5MnDpG500pUFpOepWuIiIgoBscYM0fkyR2nHqB6POqQzkREREQJqUdykOfPny9XXXWVvPTSS7J48eKA5U6nUy666CL5xz/+0RMPT0RERERhfLxhd5den6nDcuTJn03ha0pEREQxPcbQ63Ts70hERNQP9EigKTU1Vf7zn//IzTffrPowrVu3ThobG1VW0/jx41XW08SJE3vioYmIiIioE01mW5deo9Z2O19TIiIiivkxRqPZyleViIioH+jRrooTJkxQJyIiIiKKH5mmrh0CZpmSemxbiIiIqP/gMQYREdHApO/rDSAiIiKi3nXcAUVdXL+wx7aFiIiI+g8eYxAREQ1MMc9ouvfee7u0Ppo93nHHHbHeDCIiIiIK4eypJfLwok0RNes2JenlrANL+FoSERFRp3iMQURENDDFPNB09913q+CR0+ns8UCTw+GQxx9/XJ555hnZvn27FBQUyNy5c1WwKz09vdPtvOeee0IuNxqNYrWyVjARERH1P9lpSXLvGePllgVrOl333tPHS3YqS+cRERERjzGIiIioF3s0mUwmmTNnjlx44YUyaNAg6Sk33HCDPPHEEzJ79my58cYbZePGjer/K1eulE8++UT0+tCVAbF9++23X8D1a9askYcfflhOO+20HttuIiIior42d3qpOr9z4bqgmU3IZEKQSVuPiIiIiMcYRERE1CuBpgULFsgLL7wg8+bNk9dee00FbC699FI58cQTVfZSrKxfv16efPJJFTDCY2pGjBgh1113nbz66qty/vnnh7z9xIkT1cnfVVddpc4vu+yymG0rERERUTxCEOmEcUXy+opyTyk9k1Evt5w4Vs6aWqIyn4iIiIh4jEFEREThhE75iRKyi95++20pKytTJewQEDrllFOktLRUbrvtNvnxxx9j8jivvPKKKs93/fXX+1x/xRVXSFpamrz00ktdvs+WlhYVoCopKVGBMSIiIqL+DsGkyw4dIUXZJvV/nF966AgGmYiIiIjHGERERNQ3gSZNYWGh3HLLLbJhwwb5+uuv5aSTTpK///3vMnbsWDn88MPVdd2xdOlSVRpvxowZAWX7Jk+erJZ3FTKwGhsb5ZJLLhGDwdCt7SMiIiIiIiIiIiIiIurveqRHk79Zs2ap05///Ge54IILVP+kzz77TA499NCo77OyslL1f0pJSQlYNnToUPn222+lvb1dkpOTI77P5557TpX3Q6m/SCFzq7y83Oe6tWvXRnx7IiIior44xph+3yc+/69ttrget7bVZ9nS24/lG0RERNSP8BiDiIiIEjLQ9N1336m+TfPnz5eGhgY5+OCD5eijj+7Wfba2tgYNMmlZTdo6kQaaNm/erLKsjjnmGNXnqSvBqXvuuSfi9YmIiIji8RgjNdkoDqdT9DHsqUlERETxh8cYRERElDCBpqqqKvnPf/6jAkybNm2SoqIiufLKK1W20JgxY7p9/+jDVF1dHXSZ2Wz2rNOVAy24/PLLu7Qdl112mZxwwgkBs42vuuqqLt0PERERUW8eYzBTiYiIaGDiMQYRERHFfaDpjTfeUMGlDz/8UJWhO+WUU+Shhx5SPZpi2feouLhY9X+yWCwBmU0VFRWqrF6k2Uw2m00FxfLz82X27Nld2o7S0lJ1IiIiIoolHmMQERFRT+AxBhEREcV9oOnss8+W1NRUmTt3rlx44YUyePBgdf3q1atD3mbq1Kldfpzp06fLRx99JEuWLJHDDjvMJ5tp1apVcvjhh0d8X++8847KwPrNb34TshwfERERERERERERERER9ULpvLa2NnnllVfUKRJ2u73Lj3HuuefK/fffL4899phPoOmf//yn6s10wQUXeK7bunWrWK1WGTt2bNiyeUgfJyIiIiIiIiIiIiIioj4KNN11113SGyZMmCDXXHON/O1vf5M5c+bIySefLBs3bpQnnnhCjjjiCDn//PM96x5zzDGyY8cOcTqdAfdTWVkpixYtkhkzZqj7JCIiIiIiIiIiIiIion4eaAJkMw0fPlyeffZZee+991RfpmuvvVbuvfde0ev1Ed3Hiy++qDKqLr/88h7fXiIiIiIiIiIiIiIiov6kR0rn9RaDwSA33nijOoWzffv2kMtuu+02dSIiIiIiIiIiIiIiIqKuiSzth4iIiIiIiIiIiIiIiMgPA01EREREREREREREREQUFQaaiIiIiIiIiIiIiIiIKCoMNBEREREREREREREREREDTURERERERERERERERNR7mNFERERERERERERERERE8Rdoqq6ulvb29pDL9+zZI//73/96chOIiIiIiIiIiIiIiIgokQJNL7/8sgwZMkSdsrOz5Re/+IXU1NQErPfRRx/JUUcd1RObQERERERERERERERERIkWaFqyZIlcdNFFYrPZZPbs2TJp0iT597//LVOnTpUNGzbE+uGI/r+9O4Gzqf7/OP6ZfcdgrGNfW4TKVkmWIpWQRETx005EsmUL/VuF5FeIJKWfopJSihayFCJbZR+7rLNv9//4fMe97jbMjLkzc2dez8fjdu+c77nnnHvude/pvM/n+wUAAAAAAAAAAIUlaJo4caJUrFhRtm3bJosWLZK1a9fK0qVLJTY21lQvbdmyJbdXCQAAAAAAAAAAgMIQNG3evFkef/xxKVOmjG1a+/btTeAUFBQkrVq1MvMAAAAAAAAAAADAu+V60HTy5EkzNpOzWrVqyY8//ijh4eHSpk0b2bhxY26vGgAAAAAAAAAAAN4cNFWoUEH27t3rtq1atWqyatUqW9i0YcOG3F49AAAAAAAAAAAAvDVouvHGG+Wrr77KtL1q1aombCpevLhMmzYtt1cPAAAAAAAAAAAAbw2a7rrrLtm0aZP8/PPPlw2bqlSpkturBwAAAAAAAAAAgLcGTT179pSEhAS56aabLjmfhkxbtmyRPXv25PYmAAAAAAAAAAAAIA/4e2KhQUFBWZpPx2rSGwAAAAAAAAAAALxPrlc0AQAAAAAAAAAAoGjweNAUFxcnffr0kZ07d7q0rV271rQBAAAAAAAAAADA+3g8aEpMTJT3339fDh8+7NK2e/du0wYAAAAAAAAAAADvkydd51kslrxYDQAAAAAAAAAAAPIQYzQBAAAAAAAAAACgYAdNPj4+ebUqAAAAAAAAAAAA5AF/Ty24VatW5j4lJcXcP/vssxIZGWkLnb7//ntPrRoAAAAAAAAAAADeHDSlp6ebQMk6PpPe2z8GAAAAAAAAAACAd/NY0LRq1Spzf/LkSSlTpoy88cYbtionAAAAAAAAAAAAeD+Pj9HE2EwAAAAAAAAAAACFk8eDJgAAAAAAAAAAABROBE0AAAAAAAAAAAAomEFTcHCw9O7dWypUqODSVqNGDenVq5enNwEAAAAAAAAAAAAe4C8eFhYWJnPmzHHb1rRpU3MDAAAAAAAAAACA96HrPAAAAAAAAAAAAOQIQRMAAAAAAAAAAADyP2hq3ry5/PTTT9l+3g8//CC33HJLbm4KAAAAAAAAAAAAvCloqlChgtx2221yww03yNSpU+Xvv//OdN7t27fLa6+9JvXr15fbb79dKleunJubAgAAAAAAAAAAAG8KmhYuXCg///yzlC5dWgYNGiR169aVUqVKyY033ih33HGHCZQ0hCpRooTUq1dPhg0bJtHR0bJ69WpZsGBBtteXnp4ukydPNusJDg6WSpUqyeDBgyUuLi7Lyzh16pQMGTJEatasaZYRFRUlLVu2NK8DAAAAAAAAAAAAmfOXXHbzzTfL8uXLZffu3fK///3PdKWn1Us7duwQHx8fE+RoF3ta+XTfffdJ1apVc7wuDbO0cqpTp04mYNJ16N+bNm2SFStWiK/vpXO0/fv3m+2IjY2Vvn37Su3ateXs2bOyZcsWOXToUI63CwAAAAAAAAAAoCjI9aDJqkaNGqZiSW+esG3bNpk2bZp07txZPv30U9v0atWqyYABA+Tjjz+WBx988JLL6Nmzp6SmpppgqXz58h7ZTgAAAAAAAAAAgMIqV7vOy0sfffSRWCwWGThwoMP0fv36SWhoqMyfP/+Sz9dKq19++UWGDh1qQqaUlBSJj4/38FYDAAAAAAAAAAAUHl4bNG3YsMF0jde4cWOH6TrOUoMGDUz7pSxbtszcV65cWe655x4JCQmRsLAw033e5UIqAAAAAAAAAAAAeLDrPE87fPiwlC5dWoKCglzaKlasKGvWrJHk5GQJDAx0+/xdu3bZKqBq1aol77//vpn/9ddfl4ceeshUOD3yyCOX3Y6DBw9KTEyMw7StW7fm+HUBAABwjAEAADyF8xgAACC3eW3QpN3cuQuZrFVN1nkyC5rOnz9v7iMiImTlypW2+Tp27CjVq1eXESNGSO/evU3V1KXMnj1bxo0bd4WvBgAAgGMMAADgeZzHAAAAuc1rgyYdh+n48eNu2xITE23zZEa7ylPdu3d3CKMiIyOlQ4cOMm/ePFP1dNVVV11yO/r27Stt27Z1qWh67LHHsvV6AAAAOMYAAACexnkMAACQ27w2aKpQoYJs375dkpKSXCqbDh06ZLrVy6yaSUVHR5v7cuXKubSVL1/e3J8+ffqy21GpUiVzAwAAyE0cYwAAAE/gGAMAAOS2S/cLV4A1atRI0tPTZf369S7VTJs3b5Ybb7zxks9v3LixuXceX8l+WpkyZXJ1mwEAAAAAAAAAAAoTjwdNaWlpphu6nj17yu233y6bNm2yVQvpdK0+yokHHnhAfHx85M0333SYPnPmTDM2U48ePWzTdu/eLTt37nSYT8di0vGZ5s+fL7GxsbbpR44ckSVLlkjt2rWlZs2aOdo2AAAAAAAAAACAosCjXedp4HPHHXfImjVrJCwszPxt7Y6uWLFiMmzYMOnTp49MmDAh28uuV6+ePPXUU/LWW29J586dpX379rJjxw6ZOnWqtGjRQh588EHbvK1bt5b9+/eLxWJxGIvptddeM2MpNW3a1GxHcnKyzJgxw9xPmzYtl/YCAAAAAAAAAABA4eTRiqaxY8fKb7/9JosXL5Y9e/Y4BD1+fn4mIFq+fHmOl6/VTBoWbdu2zYROH3/8sfTv31+WLl0qvr6Xf2mPPvqofPrppxIeHi4vvPCCTJw4UerUqSMrV640ARkAAAAAAAAAAADyqaLpf//7nwlz7r33Xvn3339d2rVruoULF+Z4+RpWDR482NwuZd++fZm2adilNwAAAAAAAAAAABSgiqbDhw9L/fr1M20PDQ2V8+fPe3ITAAAAAAAAAAAA4I1BU6lSpeTQoUOZtmuXdxUqVPDkJgAAAAAAAAAAAMAbg6bWrVvLnDlzJD4+3qVt79698t5770m7du08uQkAAAAAAAAAAADwxqBpzJgxcvr0aWnUqJHMmDFDfHx85JtvvpHhw4fL9ddfL0FBQeYxAAAAAAAAAAAAvI9Hg6aaNWvK999/L/7+/jJ69GixWCzy2muvycsvvyyVKlUybXoPAAAAAAAAAAAA7+Pv6RXccMMN8scff8iff/4pO3bsMGFTrVq1pGHDhp5eNQAAAAAAAAAAALw5aLK69tprzQ0AAAAAAAAAAACFg0e7zgMAAAAAAAAAAEDh5dGgydfXV/z8/C55Cw8Pl6uvvloGDhwohw8f9uTmAAAAAAAAAAAAwFuCpl69ekm9evXMuEx169aVe++919zq1Kljpl133XVy5513ir+/v0ydOtWM27Rnzx5PbhIAAAAAAAAAAAC8JWjau3evLFu2TLZt2yafffaZuW3fvl2WLl1q2p566inZsmWLfPnll3LmzBkZPXq0JzcJAAAAAAAAAAAA3hA0jRo1Sh577DFp166dS1v79u2lX79+Mnz4cPP3XXfdJY888oh8//33ntwkAAAAAAAAAAAAeEPQtHnzZqlWrVqm7dWrVzfVTFbadd6pU6c8uUkAAAAAAAAAAADwhqCpRIkSl6xQWrFihRQrVsz299mzZ6V48eKe3CQAAAAAAAAAAAB4Q9DUrVs3Wbx4sTz++OOya9cuSUtLk/T0dPNYpy1ZskS6d+9um3/lypVy9dVXe3KTAAAAAAAAAAAAkEv8xYMmTpxoQqV3331XZs6cKb6+GbmWhk0Wi0Xatm1r5lGJiYmm67zmzZt7cpMAAAAAAAAAAADgDUFTSEiIfPXVV7Js2TJZunSp7N2710yvWrWq3HPPPdK+fXvbvMHBwTJp0iRPbg4AAAAAAAAAAAC8JWiy0kDJPlQCAAAAAAAAAACA9/PoGE0AAAAAAAAAAAAovDxe0ZSamipLliyRdevWyenTp834TPZ8fHxk9uzZnt4MAAAAAAAAAAAAeFPQdOrUKWnZsqX8+eefYrFYTKik98r6mKAJAAAAAAAAAADAO3m067xRo0bJzp07ZdasWbJ7924TLC1fvlx27Ngh3bt3l0aNGsm///7ryU0AAAAAAAAAAACANwZNX331lfTq1UseeeQRKVasmJnm5+cnderUkfnz50tISIgMHz7ck5sAAAAAAAAAAAAAbwyajh49aqqWlL9/Ri99iYmJtvaOHTvKF1984clNAAAAAAAAAAAAgDcGTSVLlpS4uDjzOCIiQgICAuTgwYO2dv379OnTntwEAAAAAAAAAAAAeGPQVLt2bdm+fXvGinx9pWHDhjJ37lxJSkqS+Ph4mTdvnlSvXt2TmwAAAAAAAAAAAABvDJruuOMOWbRokQmW1LPPPivr1q0zlU5lypSR3377TQYNGuTJTQAAAAAAAAAAAICHZAyc5CEjRoyQIUOGSFBQkPm7a9euZqym+fPni5+fn3Tp0kUeeOABT24CAAAAAAAAAAAAvDFo8vHxsYVMVp07dzY3AAAAAAAAAAAAeDePdZ0XGxtrqpZefPFFT60CAAAAAAAAAAAAhbGiKTw8XEqUKGHGYgIAFA6pqaly9OhRM/Zeenp6fm8OkCd8fX1NhXa5cuVMF8AAAAAAAADIg4om1bJlS/nxxx89uQoAQB6GTAcOHJDz589LSkqKWCwW9j0KPf2c6+ddP/f6+dd/BwAAAAAAALjIo5flvvrqq9KiRQsZM2aMDB48WIoVK+bJ1QEAPMhayaTf5RUqVDDj8AFFJWw6fPiwnDt3zvw7iI6Ozu9NAgAAAAAAKBpBU+vWrSUxMVEmTJhgblFRURIaGuowj56o3L17tyc3AwCQCzRk0u9sQiYUNdbPvVY16b8DAAAAAAAA5FHQVLlyZa54B4BCQsdk0rFqqGRCUaSfe/38MzYZAAAAAABAHgZNq1at8uTiAQB5jJAJRRmffwAAAAAAAFe+4sX0quLJkydL3bp1JTg4WCpVqmTGgoqLi8vyCSN3t/DwcI9vOwAAAAAAAAAAgLfzaEWT1U8//STffvutHDt2zARBGgzFxsbKxo0b5brrrpMSJUrkaLmDBg2SqVOnSqdOncxyd+zYYf7etGmTrFixwnRxcznNmzeXRx991GFaQEBAjrYHAIDMzJ07Vx555BGxWCy5vpP0Iok5c+bIww8/zBsAAAAAAACAwlPRlJaWJg888IC0bNlSJk2aJO+9954cPnzYtPn7+0vHjh3l7bffztGyt23bJtOmTZPOnTvLZ599Jv369ZM33njD3FauXCkff/xxlpZTvXp16dmzp8NNtxkAgNykvy1HjhzJt52q6+7atasUK1bM3PSxXgByObNmzZJ69epJaGioGXtx7NixDuMU7du3z211sM4HAAAAAACAws+jFU0vv/yyfPrppyb8adeunVx11VW2Nu3qTiuRli1bJiNGjMj2sj/66CNzVfjAgQMdpmvgNGzYMJk/f748+OCDWVpWcnKyudFlHgDAU0JCQswtP2gwdPfdd5vHWmGsnnzySbnnnntk7dq1mVYAz5w5U55++mn573//Ky1atDAXeejvbEpKikycONFhXv29v+mmm2x/85sKAAAKq7+aN8/SfLV//tnj2wIAAFDoK5rmzZsnvXr1kmeeeUZKly7t0q7B0+7du3O07A0bNpgTY40bN3aYrgFWgwYNTHtWLFq0yFylHRERIWXKlJH+/fvL2bNnc7RNAICCS7uVu+2220x4UqVKFVPV06FDB5eqnvfff1+uvvpqCQwMlOjoaBk5cqSkpqa6LEfDF11OWFiY3H///aZL2CVLlpjnashy5513Oixbu87TSh+rVatWmb+/+eYbufXWW81vkT7366+/dtieUaNGyTXXXGPWU7FiRVN5m5VKJHvanax2V6u/y02bNjW3Dz74wPxW/vDDD5k+T/fFQw89ZLr80wpgDaaef/55efPNN13GQyxZsqSUK1fOdiNoAgAARYUlPkHS4+LNPQAAQFHk0Yom7U5Hx07KjI7NdPr06RwtW7vg0/AqKCjIpU1PxK1Zs8ZUKemJwsxoSKUnB2vWrCnnzp0z1VVvvfWW/Pjjj+b5WTlJdvDgQYmJiXGYtnXr1hy9JgCAZ+kYfuXLl5evvvrKfO93795dhgwZYkIXpdP79OkjEyZMkPvuu082b94sjz32mKkIeumll2zL0dBGwxT93Th69Kh06dLFzK8+/PBDU/GjXeXZLzszGtxoBXCNGjXkxRdfNM/bv3+/REZGmnb9nZsxY4bptk5/c/R3Vbf7UgGRs9WrV0ulSpVMYGWljzVI++WXX6RNmzZun5eYmGgu4LCnVVnx8fHy22+/mSonKw2kEhISpGrVqqaiWC/cYMzDK8MxBgAABZNzpdI/bdtKyv4D4l+lstRcvlwKOo4xAACAVwVNWiV06tSpTNv/+ecfiYqKytGy9SSXu5BJWU+K6TyXCprWrVvn8LdWX1133XXm6vUpU6aY+8uZPXu2jBs3LtvbDwCFRf369eX48eN5vl6tQv3jjz+y9RwNPubMmWP7nXj00UfNBQZW//d//2e6dR0+fLj5u3bt2mZsIw2DRo8ebev6TpejFUq6HA1s9KIFHctI5y1btqyZR7uY07EEL0crlrR7WaVhlgZT69evl7Zt25ppL7zwgm1eDXF0e5s0aWIuuKhQoUKWXrdulwZjznTapcaN0qosfQ0aft1yyy2yc+dOmTx5smmzjrmoF2W88sorcvPNN5v989NPP5lt1lDvciEbLo1jDAAA4AkcYwAAAK/qOk9PSulYSTqWkjOtZHrvvfekZcuWOVq2djGUlJSU6RXY1nmy67nnnjPhlF7VnhV9+/Y11U/2t3feeSfb6wUAeF6dOnUcKnQ0qLHvhk7HIGru1Oe+Vu3o741eHGFVt25dh+VolZTerCGTdVpWurjT7l7tt0fZP+/zzz83XfVpta5ewGH93dSqYU/TEKxbt27SunVrE67pvtGu+5R1XCetLtbfTh2fqWHDhqa73Ndff938/h86dMjj21iYcYwBAAA4xgAAAFLUK5q0IkjDplatWpkxLZReff7333+bq8Z1fIdhw4blaNl6Mm779u3m5J9zZZOe2NITX5eqZsqMnkjTZZ88eTJL82tXRHoDgKIqu1VF+cm5KzcdI8ndxRA5WU5Ol23/POsYTtpVn7XytnPnzibI0d9N7U5PAyatgNLuYbNKQy8dC8qZBlralhn9fdWxqLSKSrsI1CDtu+++M23a1V9mNHRS2gWgBmTIGY4xAACAJ3CMAQAAvKqi6cYbb5RPP/3UdLWjA4krHa/iiSeeMOM4LF682Ax8nhONGjUyJ+K0eyHnaiYdU0PXnRP6fB1zyf6qdABA0aDd4P3s1Oe+jtungYuO55fXdPwkHc9QQ6amTZuaiiwNfLJLu7XTvvh37Nhhm6YXa+g0vSDkcvz9/c14ThqKLViwQKpVqybXX399pvPrGFZKnwMAeeGv5s2zdAOA3HBm8RJJT0jItF3bdB4AAICiwqMVTequu+4yV1/rFdB6gkuv7q5Vq5YZeyInXdtZ6XgRkyZNkjfffNOhm6OZM2easZl69Ohhm7Z7924zMLt2dWT177//SqlSpVyWq+NKpKamyj333JPjbQMAeCcdm0m//zXY0UoivXBBx+EbNGiQbXymvKS/WzrW4bvvviu33367/PbbbzJhwoRsL6dNmzYmGNKxCK1jUj311FPmog2tOrbSLvIaN25sxopSe/bsMWMuaYXS+fPnTX/+CxculC+//NLWdZ6OVeXn52eWr4GcBnV6UUmXLl2kcuXKubYvACA7LPEJ5v87tFLUJzTvv78BFF4aIB0ZPlzOfv65VJrxtvg6HSNqyHTwiSclfu1a83eJTh3zaUsBAAAKUdCk9MTT3XffbW65pV69euYkmZ4w05OB7du3N0HW1KlTzXgaDz74oMOJM+2+x74LIz1Rt3btWjPWhZ4Ii42NlWXLlsnKlSvNIOv9+/fPtW0FAHgH/S3R8QM1aBo9erRERUXJ448/LuPHj8+X7dGLNcaMGWNuOvaR/j5NmTLFTM8ODYWWLl0qAwYMMKGT0u73pk2bZguMrBdm2HcHq7+b06dPN7+3erJWg6nvv/9ebr31Vodlv/LKK7J3714zv1Y7Pf/882Z7UbBltbqjtlOVH1AQOX9O/2nbVlL2HxD/KpWl5vLl+bZdAAqfYu3ampBJgyQNlDRssrKkp9tCptCmTc28AAAARYGPJSeDU2SRXt2sYzNp6KNjJuW2tLQ0U9GkV3pr1ZSuQyud9IRgeHi4bb6qVau6BE06uPrbb78tf/75p6lu0quxtdKqa9eu8uyzzzoM8p5dv/76q7n6e82aNdKsWbMrfp0AUBDo+HpKvyuBouhS/wby6rc/N9fjHDRlVgFC0ARvZA2aAgiaAHiAfdWSBkrJh2Ik9WCM+AQHiSUxyUxzV+2UE954jAEAAAq+3P7t92hF0/Hjx2XgwIFmEPM777zTdNmjXRI5D5ieUxoODR482NwuRUMoZ/fee6+5AQAAFEVUgAAAigKtMhK9kMLPz2FayoEDYklJEZ+QEAl0GlcydvVqST93TnyCgiTCrpthdW75t5L0118SrONNW9JN2OQTFJix3FwOmQAAALyFR4MmHWR8xYoVMm/ePFmyZIkZ0yEyMlK6desmvXv3Nl3wAAAAAAAA72F6C9Hwxq4LXktamqQcPiyW5GTxDQ2VgPLlHZ4T+8tqSY+LM23hzW9xaDu3bJkk6QWiqWkSNcCxG/uzS7+S2B9+MKFQ2RHDHZZ7/oeVcmLKlIy254dKeIsWtrbE7dtlb9cHRFJTpdQTj0sZ+25909Jkd7s7zcPwVq2k0tvTHdZ5bOIkSd6zRwIqVnQNmr75Ws5//Y15XPOXX+TQ009LwubN5m8NnAiZAABAUXTxqNADtOsVHbz8gw8+kKNHj5pxL+rXry///e9/pWnTpnLVVVeZcTAAAAAAIKfOLF5iurLKjLbpPEBB59yzvSU1VZJjDknS3r2Scvy4y/yxP/8i51eskLi161zazn75pZz87ztycuZMl7Yzny2WQ88NlZiBgyT19GmHtnNffy17OneWPffcI/EbNji0xf/2m+y8rr7svPoaOfXeew5t6efPy+7b75A9d90tx9+Y7LLOIyNHyqFnnpHjr77quj1LlsjJqdPk5Ntvu+yDpF07TRB1/rvvJO3cOcd1xsVK0q5dJhRKO3vWcaH+/iZkMlJSXNsu0JDKmc+FXlgu1ZbRnuzSDgAAUBR5tKLJXlhYmKli0ltMTIwJn15++WUZNWqUDBs2LK82AwAAAEAhogHSkeHD5eznn7utJLAfS0WV6NQxn7YUBYWGB6knTpgQxzc8XPxLlrzYZrFI3C+/iCUlVfxKlJDQ6xu6fN5ST54Q36BgKdnrIYe20ws/kYSNG83yy0+c4PBZ1CDl9PwPM9omTZSQa66xtcX+9JPEDHjGtJUbNVIiu3e3taUeOya727Qxj0t0e0DKjx3rsM5DgwZJemyshDRsKGFNFzhuz8cLJeH3300FUel+/RzaEv/cKue+/NI8LjNkiEhkpK1NA5uk7TsyHp8/77jzfP1MxZJ1P2YewFwivLGGPw5tGV3PZbzoVBG7ZTku1/G5vmHh4l+mjJnHJ8hxnGW/iAgJu6mZWVZg1aqO6/PxkZK9e4v4+0lQ9eou21P6qScl/Xys+Xw4i3rySSnZs6fpfu/IsOGmmkkrmSxJyeam3zdUNQEAgKImz4Imqz179piu9ObPny/nzp3LtfGaAAAAkHV6srRYu7aZjiGhJ+fPfbOck/Io8PRzrCGTBknWE7xWeiLYGjLpuCk6LzxDwwetjNGAwS883IQ0trbUVIlbt860+ZcqLSH1rnV47plPP5W0M2fENzxCIh/o6tB2av6Hkrhtm3luhVdfMQGBfZBy5rPPTFvF11+XoOrVbG36/XVkxAhb6FO8Qwdbm1YH7e2QMV5vyb59pOxzzzms8+Cjj5lu4cKaN5fKM9913J7335eknTtNuOEcNCVs/F3Ofv6FeVz2hVEO369p/56SxD//NI81wHDg4yuWxET3Ac0VhTeXb3NXlaPhjV9UafHxDxAfu8ofZcK3pk3N9ACncY18AgMlskcPs+zgq+q6rDPqmWfEkpQovsWLu7SVGTRQSv2nb0bgZDeWkirVr5+UfOSRjDAp0C6QEpGIVi3NzR3tYq+yU9WVvbLDM7/gtdgdd2TapqGVLcBet87sj+RDMZJ6MEZ8goMcvosYpwkAABQVeRI0nT17VhYuXGgCpl9//dVcJXbdddfJ66+/Lj169MiLTQAAAMAFVICgMNETuXpC1xoo6b0GTCrtxAmJPxhjTgR740lfDW+0ukQDBt+ICFOhYZWenGyrntHQI7hOHYfnnv7kE0mPixf/kpFS/N6MUMXq3zlzJWn3Pya0Kf/iiw5tp+bNk3PLvjbrjn57ugSUK+fw3XFs0iTTVnHyGw5j1yRs2yb7uz9oHpce0N9Ufdi/joN9/2MeR7RtK9FT3nRYp3bvlnLwoARWq+YSNMWt/VViV3xvHleYNFHELmhIPX5cErdsydgfcXEu+y89Pj7blTe6T7Rdtzm7XapdKhTyDQsTv5IlM57vezEsU34lIyW0USPT5l+2nGNbWJiU6N7NtIXUr++ySq1GsqSlin/p0i5tZYc9b/aB/eu1ihowQEo/+WRGeBPsWAlU/J67zc0dDfOqzJ3jtk2XVe6FUW7brMvNTFDNmpm2FbR/t/ZVktbvlj0dMyol/aKiJLBiNGETAAAocjwaNC1dutSES3qfmJgoZcqUkWeeecZ0n6djNQEAACDvUQGCwh42aTdWypKY5BIymfAmNtZWeaMBgP0J5IStW02bBixBNWo4rEcraCzJSSbYKdaunUObjoOTcqGiodyIES5tsStXmeVWnjVT/OwqOk4tWCAnpkw1bZXeflvCmjaxtcWt3yAH//MfW/WF6erLuq1nz8qBhx8xj4t37pwRwtg58eYUSTt1SoKvvdYlaIr96UeJ/3WtCQacg6aUQ4dNV2BmHfFO416lp5txeKz7MbOuz3Lcpdplx8NJcaho8Q0LzdiXga5Bin/pUhJyww3iExggfqVKObTpc0p07WqWFXrDje4rXXx8xN8uZLMqN/oFU33kHM6Y5z3/vJQZPNhss3ZXZy+y2wPm5o52o1flg3lu2/TzWX7MGMlMifs6Z9oWXNe1qsh+ucgZrZazD5nsgzAfX1+H7yIqgwEAQFHh0aCpQ4cOEhQUJPfcc48Jl9q1ayd+TmXwAAAAyFuFuQKkIDID2+v+TU93qSzQKgytTNE27ZLKx+5YWQe916BA35uAsmUdTgxrUJK8e3dGW4UKpt22vuTkjG7K0tLM9OCrrnJY57lvvzUnyrVCJqKlY5dT53/4wQQN2m2Yc7dgsatXS8KmzWZbI3v2cBjXRsOZszreS1q6FO/cyWH8meSYQ3Jy2jSxWNJNBYx9QKNdesX0HyCW9DQJue46iXrqKYd1HhrynKTExIh/VGmJnjbNoe3YS/9nxrbR7am2ZLHtc33gkT62oESVfvpph8/x+ZWr5NAzz5jH5Se8KCW6dHEYD+dAr4wwJ/Khh6TcSMfA6NhLL4klKUlCmzRxCZrOf7fCVNfo++gcNKUcOGCqj1R6YpL42fcclppmQiN3XZhdsvImF8IbbdPPp313dBre6GfDzGPJ+F6w8i8TZcYC0jb7sMy0lS4lJe7vklF5U+86xxX6+0uZYc+btsBKlVy2R98HS3KKWbezcqNHS7mRIzMqb5zCm1J9+5qbO6E33ihVP5zvtk0/u+XHj5PM2I+R5CykXr1M2+wrzlB4Wcd5y6z7Wet3ESETAAAoSjwaNL399tvSrVs3KWHXPzcAAAAKdgVIcP36LiFT4q6/zBgqZtwSu4oL0/bXX5K8f79IukXCbr5Z/MIvBiLJ+/ZJ/O+/m9AjrFkzh5PMqSdPZoxnYkmXkAYNzIlh+wDixLS3TIgQWKO6lLjQLZHVibemm26z9KR+mWcHuYyhEn8hEKnw2qvia1cBcfaLL+TskiViSUs3lQn2FStxa9fJ8VdfNeFN6ScedxijI+XQIdmv1SNpaVK8Y0eJGtDfYZ1/N7/VdFEVcsP1UvldxzFd9j3QzRZA1F77q0Pb0ZdekrOLPjWPa/74owSULXNxW5d8bropU5VmvivhzZtf3Od/bpMDDz9sHpd5bojDyfa0uDg52O9R87j4vR2kwssvO67zxRcl7cRJCapb1yVoOv3hAolbvVrE19claIpbvUZOXRjvpFj7Ox2CpqTdu+X0vA/M45DrGzoETennzpoxlFRA+QqOAY2Pj8SuXHnhoa/D+szr3LHDBGoapjlLPXFckvfuNY/1/cxMzsMbx+dZ2zVoynawExJigkIzT5rjeDmm27v612VUwYSFO7Tp56H4fZ1NW1Adx+oUDV3KDB2aEd7YjU1kVeGVV0TS08y4Ry5tGpilpWXapZre3NHPoP3n0GFby5VzqY6ybauPj5S68Hl1J/T66zNt84+MzLQNyO+wKTP6+3m5eQAAAAoTjwZNjz/+uCcXDwBAtowcOVJmz54tx44dk8mTJ8vAgQMv+5yxY8fK3LlzZd++feZvffzII49kVCjkk9tuu02qVq1qtkU9/PDDZvtWrVqVb9sE75RZBUi6DtbudJX28Zf/T+LW/GoqE676c6tD29nPFsupC5/H6l8tFb/wi+FN/MZNcmRkxpgdOqaLfdCUcuyYCXZUqScedwiaNND69513zMPwVq1cgqZzy5ZJ8p49ElCxokvQpCHT+W++ubCSSQ5juiTHxGS8jgsVQ/bS42Ilcdu2jLZTpx3aNHzSMWRMmwZuTjTcscTH28aEsWetFrFWjTm22YUrTtUjGvZc3DjHNh+/i23Oy9Wumy62uX5X+fheqJpysz1iXW56ukuli4/duDLOwY59JZYGjo7LtG/L/DVqxZMz3/AwU13jrpsvv1KlJSA6+sIyLLZxU8xn2d9fJDUj0DnxxmQJndfA9pkOqFjBhIUmoKlW3XF9xUtImSEZXZ8FOY15pCpOnmzCMQ0NXdreeMO8h+7CG61wcq5ystKqCL25E1i1qlSY6Nglnm1bAwOlVJ+MrvPcCWvSONM2f6eu5AAAAACgwAZNKj09Xd5//31ZvHix7Nmzx0yrXr26dO7cWXr16iW+9v8DDQCAh6xbt04mTZokixYtkptvvlmKFSuWpecNGTJEnnLqyqmgmTJliqSlpeXZ+jTgeumll0y4pYGXBnj6m34p+/fvl2HDhsnKlSvl3Llz0qxZM3njjTdcxmzMybLhAW7CCbGGE+4+a/ZhgVO7QyDiHE7YHwemZT1kyWj3yTSccAhanEJhH/8AEe2CSwMUp5fpExgkflql4+crPkFBTm2BElitmtkuv9KuJ+lD6l8nlqRkCa5d27XthhvELzLSZcwW09aggRnzR/ev8zqD69aRyF4PmTBKAzV7WuGjXcLp/nUeY0arZ8qOHGn2kQYVzsqOHGG21a+46/dgVP/+UrJnz4vvt1N3YhG33272QWBlx+7Pwlu2lOpfLzP7XgMge1o1VmvNatPmPK6Nvg91Nbj083MItayqLVwomTHd2l3o2s4aMlnHTUk+FCOpF8ZLSty61bRZq/SC69SRCv/3kttlajVeqQtjIrkT3vyWTNvsq9EAAAAAoCjxaNCUkJAg7du3l59++sn8j2P58uXN9GXLlslXX30l8+bNM4+D3QykCgBAbvr777/NvV7o4O5kZmbCw8PNLbclJydLoF2VxZUo7jROhictWbJE+vbtK6+88orcdddd5vdcK7wiIyPNmIzuxMfHy+233y5VqlQxv/uhoaHy2muvSatWrWT79u1S9sLYMjlZNq6MfQWIdp2n4YORlGTa7KuadMB502Wem+7NirW9QwKrVjFBQkAZx5PtWqVU8c03TXjjPLZJYOXKUnnuHLPMgAoZx4k2vr5S9dNFplLGXddflWfPzhjzSCtXnJSfOEHKvzg+I7xwCm9KP9rP3DILEWqvWe22Tcc6qvH1MslMlTlzMm0rO/S5TNt0v+rNHd13DlVe9ttTsaJEPf1UppUuJR/qmek67bsEzM74M7pO58DLyi883Nzc0ffIvps9d+1Xwjlk0kBpz4UKOL+oKAmsGG0bi4xxxwAAAAAg93m0nGjChAny448/yuDBg+XEiRNy8OBBczt58qS5Qly7+JmYSVcQAADkFu1a7qGHMsYa0UpaDZq0Ymbjxo3mgggNOsLCwkx1zUcffeTSdZ5W1mRGK3Ccgytdtk6z78pO/9bu+nr27GnGLrzvvvvM9N9//13atm0rEREREhUVJZ06dZK9F8Ycyc7r0+70nLf5888/l7p165rXpu3WsM0qJ+vWEEi3XX/bddl6r+Hdy05jwNhbs2aNWfecOXPk+uuvN89750KXaDqe45UsG7l3ct7vQkCkFSA63pK26TxWxe6801R6lOrbx2VZIfXrS2TXrlKiSxeXLsU0mDBdg91+uxnDxZ52hxbWtKnp4su+Sz2zHT4+Zpyf4Lp1JTC6otvgJ6B8efGPinJp04BMl+0bHJytYBne6dw3yx1CJvuAVMNPnaZtOo/OCwBX6q/mzR1uKTExZrre208HAAAoKjwaNC1cuFC6du1qThzp1chWeoJNTxppm/MJPQAAPNG13JtaUSEiR44cMbdKlSqZLtzuv/9++f777+WPP/4wXbRpEKQXSXjC+PHj5YYbbpDffvvNVPRoNU+LFi2kadOmsmHDBtOtnL+/v7Rp08ZUBV+J48ePy4wZM+TDDz80Qc/Zs2elT5+LAUFO1q1VWDpvu3btHKbr3+vXr5eUlBS3z0tMTDT39hXMfn5+pqJLq56vZNnIvQoQa3dzWgFiPSnvHDYBBVGJTh2l/EsvZVqtZB2LTOfReQEgt/kGh4hPaKi5BwAAKIo82nVeTEyMqVzKjJ7g0m5yAABe7kLXqC7uvFPkvfcyHs+aJfLCC+7n+/RTkZtuynjcrJmWBLnOc9VVIj/8kPF4xQqRNm2y1bWctXu5cnYVFVrlY18JpBU0GjppOKO/UblNu38bNGiQQyWSVlSNGzfONm3+/Pnm4gztNq5Lly45XpeGOzpGorVbOv091qouna6Bj14Ekt11a0Vyamqqwz5U+rcGQdpu7SbXnoZZepGJbsPUqVMlKCjIBG1Hjx61jZWV02XDcxUg1iBK5+XkPAq6y31G9TPO5xhAbqn988/sTAAAgLwKmvSk0j///JNpu7bpPAAA5Id///3XdDO3YsUKE3pooJGUlCQtW7b0yPqaNGni8LdW8GiXcs5jQGkY5NzNXXZpKGMNmVSFChXEYrGYSqfKlSt7dN3OSpcuLZ999pk8/vjjJvDTaiatVNKga8+ePbm6LmSN9YS7dml3qQoQQiYAAAAAAJCvQZMO/D19+nRzr2NA2Pv2229Nlz7aZREAwMsdOXL5ef7zn4zb5fz66+XnyUY106X07t1bdu/eLZMmTZIaNWpIaGioPPPMMxIXF5flZeiYT0pDHOtYMJl186ZjJdlLT0+XBx98UEaNGuUyb8mSJeVKBAQEOPxt3TZdZ07XrYGRdq+noZy9Y8eOmfVpe2Y0vNu1a5ecPn3arLtUqVLSuHFjs9+vdNnIGSpAAAAAAABAgQ+aJkyYIMuXLzdXLDds2FCuueYaM33btm2yadMmc9JIx6sAACA/6FhMGjJ16tTJ/J2WliZ//fWXVKxYMcvLKFOmjLk/fPiw7XkbN27M0nNvvPFG2bJli1SvXt0WWOWVnKxbx1Rq1KiR+W23H+/pm2++MaGRc7jljnXMRg2dfv/9d5mlXSrm0rIBAAAAAACQ9zx6VqtKlSpmwPNu3bqZE3cffPCBuWmXPN27dzfd9ug8AADkh7p168pHH30kf/zxh2zdutWMmaRdy2WHhiAREREyfPhw8/umwYheaJEVI0aMMM/p0aOHrF+/Xvbu3SsrV66UgQMH5nr3dbm17qFDh8qiRYtk8uTJJizS+08//VSef/552zyLFy82+/bQoUO2afPmzZPVq1ebrvJ0/jZt2sitt94qvXr1ytayAQAAAAAAUIQqmpSOA6GDqmuXQidOnDDToqKibF34AACQX+bOnSuPPfaYNGvWzFTa6BhCWt20b9++LC9Du5nTsGrIkCFy3XXXyQ033CCvvPKKqea9nKuuukrWrFljuq/TLmYTEhIkOjradDNnrfzxlJyuu2PHjjJ79mxTCaYBUNWqVWXOnDlyzz332OY5e/asCYrsuxDULgo1jNNjAR0/SrvtGzNmjBmvKTvLBgB3/mre3OHvtFOnzH1KTIxDW+2ff2YHAgAAAEAu87FoAoRc9euvv8pNN91kTuDpyUsAKAysVS61atXK700BCty/gbz67c/N9bg9MZ+WLuLnK35243RxYh7ewPnzbIlPsI2d5xMaYpvO5xmAt/HGYwwAAFDw5fZvv0crmqZPn266z1mxYoXb9jvuuEPuu+8+czU5AAAA8o9vcIjtxDzgbQiQAAAAACD/+Hu6SyIdbDwztWvXlvfee4+gCQAAII9xYh4AAAAAAOQGX/FwFzP16tXLtP2aa67x+GDnAAAAAAAAAAAA8MKgSQcBT0xMzLRd2y7VDgAAAAAAAAAAgCIaNGnXeN99912m7d9++63UqFHDk5sAAAAAAAAAAAAAbwyaunfvbsKkF154QZKTkx0qncaMGWPaHnzwQU9uAgAAAAAAAAAAADzEXzxo0KBB8vXXX8vEiRNlxowZUrduXTN9586dcurUKWnevLkMHjzYk5sAAAAAAAAAAAAAbwyaAgICTNXS5MmTZcGCBbJp0yZbl3rDhg2TZ555xswDACj8Gk1ckaX5Noxs4/FtAQAAAAAAAOAFQZPSIGno0KHmBgCAVUJymqRbLOLr4yMhgX7sGAAAAAAAAMALeTxoAgDAvlLpbHyK/O/3g/La8l2SmJouwf6+8niL2tLl+mgpHkqVKwAAAAAAAOBNfPN7AwAARccnGw5Kk0krZMJXO0zIpPT+xaXbzXRt97SEhASZNGmSNGjQQMLCwqREiRJy4403yuuvvy7nz5+XsWPHio+Pj+1WtmxZadeunaxfv95lWX/99Ze0bdtWQkNDpVSpUvLoo49KbGysx18DAAAAAAAAUFBQ0QQAyBMaIg39dEum7Ro4Wdu7NqrkkW3QIOm2226TmJgYGTdunDRp0sQETX/88YdMnz7dhEUqOjpaNmzYIBaLRY4ePSoTJkwwYdOuXbskKirKzKOBUuvWreXaa6+V1atXy+nTp6VPnz7y8MMPy6JFizyy/QAAAAAAAEBBQ9AEAPA47S5v9Od/Zmne0V/8KW2vKeeRbvRGjRol27dvN7dq1arZpuvjjh07mrBoypQp4ufnJ+XKlTNt5cuXlzFjxshnn30ma9eulXvuucdMX7BggRw/ftzcR0ZGmmkaVt19993yzz//SM2aNXN9+wEAAAAAAICChq7zAAAet2hjjK2rvMtJTEmXTzfG5Po2aHXS/PnzpUePHg4hkz1rYORcBTVr1izzODAw0DZdq5i0Isr+OXfccYf4+vrKL7/8kuvbDwAAAAAAABREVDQBAK5Ij1lr5dDphEvOc/RsYraW+co3O2Xer/suO1/FyBD58D9Ns7TMEydOyKlTp+Tqq6++7LwHDhyQ8PBw8zguLs7cN23a1HSVZ3XkyBFb1ZNVQECAlCxZ0rQBAAAAAAAARYFXVzSlp6fL5MmTpW7duhIcHCyVKlWSwYMH204KZkd8fLxUr17dDPz+9NNPe2R7AaAw0pBp37/xl7xltZrJSue/3DL1drmAK6cqVKggmzdvlt9++81UM1WpUkU++OAD8ffn+gwAAAAAAADAnlefMRs0aJBMnTpVOnXqZAKmHTt2mL83bdokK1asMN0XZdXo0aPN1e4AgOzRqqLL0Yqm7IRNwf6+Uq54cK6s2yoqKspUG+n4TJejgZJ1jCW9mCE2Nlbuvfde8/ti7T5Px27au3evw/NSUlJM1ZS2AQAAAAAAAEWB1wZN27Ztk2nTpknnzp3l008/tU3XcTcGDBggH3/8sTz44INZWtbGjRvlzTfflFdeecUEVgCArMtK13Wzf9krLy69fMBjNbRdXelzi/txlHJKK1Z1fKaZM2fKyJEj3Y7TdObMGbfPfeKJJ+TVV181vzvW34mbb77Z/Nboc0qUKGGmfffdd6ba9pZbbsnVbQcAAAAAAAAKKq/tOu+jjz4yA7sPHDjQYXq/fv0kNDTUDPieFWlpaeY57dq1M6EVACD3dbk+2lQpZUVwgK/cd0O0R96GCRMmmAolHW/pnXfeMd3j7du3T7788ktp27atLFmyxO3ztIpJq2hfeuklOXfunJmmFzOUKVPG3OtyVq1aZbpeve+++2zVUAAAAAAAAEBh57VB04YNG0zXeI0bN3aYrmM1NWjQwLRnhY7xtHPnTnnrrbc8tKUAgOKhATL+3muztCPGd7hWiocEeGSnFStWTFavXi39+/eX6dOnS7Nmzcxvxvjx480FB126dMn0uY8++qi5OEErm1R4eLjppjU1NVVuuukmc7FC69atZe7cuR7ZdgAAAAAAAKAg8tqu8w4fPiylS5eWoKAgl7aKFSvKmjVrJDk52TaWhjs6tsaYMWPM+ExVq1Y1V7Vn18GDByUmJsZh2tatW7O9HAAo7Lo2qmTuR3/+p9vxmrSSSUMm63yeolWvo0aNMjd3xo4da27OIiIi5PTp0w7T6tSpI99++63HthVFG8cYAACAYwwAAOANvDZoio+PdxsyWauarPNcKmh6/PHHpXr16vLss8/meDtmz54t48aNy/HzAaAo0RCp7TXlZNHGGHn1m50mcNIu9XRMpvuujzaVTwAycIwBAAA8gWMMAACQ27w2aNIr0o8fP+62LTEx0TZPZnQMJx20/aeffpKAgJyf2Ozbt68Z18O5oumxxx7L8TIBoDBqNHGFw98paem2+xk/7jY3tWFkm3zZPqCg4RgDAABwjAEAALyB1wZNFSpUkO3bt0tSUpJLZdOhQ4dMt3qZVTPpc7SKqX379lKuXDn5559/bM9TZ8+eNdN0GSVKlLjkdlSqVMncAADZExLoL+kWi/j6+LDrAI4xAABAHuE8BgAAyG1eGzQ1atTIjIuxfv16ad68uUM10+bNm+XWW2/N9LkJCQly4sQJ+eqrr8zNXbWT3nTA9yFDhnjsNQBAUUKlEgAAAAAAAFD4eG3Q9MADD8ikSZPkzTffdAiaZs6cacZm6tGjh23a7t27JSUlRerWrWv+DgsLk//9738uy9Tw6cknn5R27dqZ7mquu+66PHo1AAAAAAAAAAAA3sdrg6Z69erJU089JW+99ZZ07tzZdIO3Y8cOmTp1qrRo0UIefPBB27ytW7eW/fv3i8ViMX/rmExdunRxWea+ffvMfY0aNdy2AwAAAAAAAAAAoBAETUqrmapWrSrvvvuu6QJPx1Tq37+/jB8/Xnx9ffN78wAAAAAAAAAAAAo1rw6a/Pz8ZPDgweZ2KdZKpcvR0Mpa9QQAyGWv1c7afEP+YtcDAAAAAAAAXsKrgyYAgBdLiRexpIv4+IoEhOb31gAAAAAAAADIAYImAEDecK5UmtpQ5NQekZLVRQZs4l0AAAAAAAAAvBBBEwDA82bcLBJ3wnFa3MmM+9P7HbvVC4sSeWI17woAAAAAAADgBXzzewMAAEWAhkyxxxxvlrSMNr23n+4cSOWyhIQEmTRpkjRo0EDCwsKkRIkScuONN8rrr78u58+fl7Fjx4qPj4/tVrZsWWnXrp2sX7/eYTlHjhyRHj16yDXXXCP+/v5y2223eXS7AQAAAAAAgIKIiiYAQJGhQZIGQjExMTJu3Dhp0qSJCZr++OMPmT59upQqVcrMFx0dLRs2bBCLxSJHjx6VCRMmmLBp165dEhUVZeZJSkqSkiVLyrPPPiv/+9//JDExMZ9fHQAAAAAAAJD3CJoAAEXGqFGjZPv27eZWrVo123R93LFjRzl9+rRMmTJF/Pz8pFy5cqatfPnyMmbMGPnss89k7dq1cs8995jpVatWlWnTppnHP//8s+zbty+fXhUAAAAAAACQf+g6DwBQJGh10vz58013d/Yhk73IyEi3VVCzZs0yjwMDAz2+nQAAAAAAAIA3oaIJAHBl3u8gcvbgpeeJO5n15em8Uxtmbd7ilUR6f5GlWU+cOCGnTp2Sq6+++rLzHjhwQMLDwzM2Jy7O3Ddt2lRat26dte0CAAAAAAAAigiCJgDAldGQ6dSe3NuLlrTcXV4OVKhQQVatWiWpqamyevVqefHFF+WDDz4Qf39+NgEAAAAAAAB7nDEDAFwZrSq6nNP7MwKkrPDxE4msknvrviAqKkpKlixpxme6HA2UatasaR7XrVtXYmNj5d5775VNmzbRfR4AAAAAAABgh6AJAHBlstJ13Wu1RWKPZW15YaVFBmzK9XfFx8fHjM80c+ZMGTlypNtxms6cOeP2uU888YS8+uqrMm3aNBk8eHCubxsAAAAAAADgrXzzewMAAMgrEyZMMBVKOt7SO++8I5s3b5Z9+/bJl19+KW3btpUlS5a4fV5gYKAMGjRIXnrpJTl37pxtuj5fbzr2k1Y9Wf9OTk7mTQUAAAAAAECRQNAEACgyihUrZsZc6t+/v0yfPl2aNWsmDRo0kPHjx0u7du2kS5cumT730UcflbS0NFPZZNWwYUNz06Dq999/t/19+PDhPHpFAAAAAAAAQP6i6zwAgOeFRblOizuZMW6Tjsmk3eVdat5cFBoaKqNGjTI3d8aOHWtuziIiIuT06dMO0ywWi8e2EwAAAAAAAPAGVDQBADzvidWemRcAAAAAAABAvqKiCQCQPwJDRSzpIj5c8wAAAAAAAAB4K4ImAEDeGPIXexoAAAAAAAAoZLiMHAAAAAAAAAAAADlC0AQAAAAAAAAAAIAcIWgCAAAAAAAAAABAjhA0AQAAAAAAAAAAIEf8c/Y0AACyp+UnLbM038quK9m1AAAAAAAAgJcgaAIA5IuE1ASxWCzi4+MjIf4hvAsAAAAAAACAFyJoAgDkCftKJQ2YbvvkNjmVeEoqhVeSZfct410AAAAAABQYfzVvnqX5av/8s8e3BQAKOsZoAgDkuXVH15mQSSWlJeXJOt977z3x9/eXM2fOOEy/+eabTVXVkSNHHKa3bdtW7rjjDtvf33zzjdx5551SunRpCQ4Oltq1a0vfvn1l27Ztpn3fvn1mOdabrqtSpUry+OOPy9mzZ/PkNQIAAAAAPMMSnyDpcfHmHgDgiKAJAJCntJppxuYZtr/PJp810zytdevWkpaWJitXXqysOn/+vKxfv14qV64sK1assE1PTk6WX375Rdq0aWP+njhxotx1111StWpVWbRokezatUvmzZsnJUuWlCFDhjis59NPPzWhlQZPM2fOlC+//FIGDBjg8dcHAAAAAMg9Wqlkf/MrXUos8fHm3n46AICu8wAA+VDNtPH4RtvfWtG0/uh6aVK+iUfXW6VKFalZs6YJlDp16mSm/fTTT1KxYkV56KGHzHS9V7/++qvEx8eboGnjxo3ywgsvyKRJk2TYsGEOy2vatKmcPn3aYT0aPpUrV848jo6Olm7duplqKAAAAAAAAKAwoqIJAJBv1UxWb29+O8+qmr7//nvb3/pYp7Vq1cpleqlSpaRhw4bywQcfSEhIiDz77LNulxkZGZnp+vbs2WNCpptuuimXXwkAAAAAAABQMPjn9wYAALzbf779jxyJdRzfKDOJqYlyPOG4y3StcGrzvzYS7B+crXWXDy8vs+6YleX5tULpnXfekZiYGFNt9MMPP8jQoUOlWbNm8u+//8rOnTulbt26ZrqGTzrWknaTV6NGDQkMDMzSOnQcJz8/P0lNTZWkpCRp0aKFvPHGG9l6XQAAAAAAAIC3IGgCAFwRDZkOnD9wxXvRXQCV2zQ88vX1Nd3k3X333bJ161YzLTg42IRNOl0DKB236a233srROmbNmiVNmjSR9PR02b9/v4wcOVLuvfdes2xdNwAAAACg4DuzeIkUa9dWfENC3LanJyTIuW+WS4lOHfN82wCgoCFoAgBcEa0qupJqJntlQspkq6opq+u2Hz+pQYMGpmu80NBQU71kHU+pZcuWZnr16tUlJSXFVD+pOnXqyI8//ijJyclZqmrSMZ90LChVu3ZtCQ8PN13nrVq1yoRaAAAAAICCHzIdGT5czn7+uVSa8bZL2KQh08EnnpT4tWvN34RNAIo6giYAwBXJStd1Ov7Sw988fNmgKToiWua2m2u6rPMUDZB03CUNmnR8JisNmrSLuypVqki1atVM4KR69uwpb775pmkbNmyYy/JOnz59yXGa/P0zfmrj4+M98noAAAAAALlLK5k0ZNIgSQMlDZusLOnptpAptGlTMy8AFHUETQAAj1t3dJ0Zh+lydJ71R9dLk/JNPLYtGi698sor8tFHH5nAyUq7u9NKpvfee0+6detmm37DDTfIuHHjTBd4Bw4ckAceeECqVq0qx44dk88++0y2bNkiy5Yts81/6tQpOXr0qK3rPB0DqmzZsqaqCQAAAABQ8GkFk4ZL1kBJ7zVgUmknTkj8wRgTMrmrdgKAnPirefMszVf755+lICJoAgB43Ce7PsnyvAt3LfRo0NS8eXMJCgoyFUYtWrSwTQ8ICJCbb75Zvv32W1u3eVajR482gdO0adOkU6dO5rmVKlWS2267TV5//XWHee+77z5zr1VZZcqUMWM/zZgxw3TbBwAAABR23n6iDIWfJTlZ0s6dk/TYWPErXVr8wsNtbSnHj8u5L76QtLg4CWvUyCFskgtdqVsSk8S/XDmXkOnkjBnm+X4lSkiZZ55xWGfcuvWSEhMjPkFBEnF7G/ENCrK1pf77r7n5Bgaa5foGZ707eQCFlyU+wfQQpOeXfEILfqBN0AQA8LhudbrJpuObHKadSjwl6ZZ08fXxlZLBJR3m9aSQkBBJTEx027Z8+fJMn3fXXXeZW2a0ykkPAAAAAAB474kyFDz6+dFwyD6cUfEbN0nKoRhJj0+QyAe6OrSd+fQzObdsmQmTKrz+mgRGR9vazi79So6MGGEeV3zjdSnWvr2tLe3kSTn+2oWLCdPSJeymm0ygdOCRPpKwebNtvsDq1V0qmc59s1ySdu0S/zJlXIKmM4sWybkvvzSPa/26xuG1nF2yRI6/+pp5XHnuXAlrevHCy9hfVkvMU0+JT2CglBkyxOF1pp4+LTH9+4tvYJCE33ablOz1kMM6T0ydKpa0dAmsFC0lunRxaItbu07Szp8T3+AQCW9+i0ObLlf3t67Tr1gx8fHzc35LAHhAbacLMP5p21ZS9h8Q/yqVpeYlzlcVFARNAACPa1y+sUfmBQAAAFCwePuJMuS+9Ph4Sdq9W9Lj4iSgfHkJrFLlYltSkglZNBAKvvoqKdmrl8Nz99xzjyTt3iNBNapL9QtBjdW/M2dK7MqV5nGJzp3EJyDA1pYcc1DiVq82j9NOnxGxC5p8w8Jsj7VyyZ6vXXWTblNmNIBxZklKMvdateTSlpx8cR1O7boPrHyCAp2WmWiWa5btdGFjely8JPz2u3kcWPXiPrU6Nfd9s+9Drr/eJWjSECph40azL+r8/ptj25QpcubjheZxjRUrJDC6oq3tzGeL5cTkySaEKj9xgoQ1bWprS/rnHzn+RkZb8Xvulgi7MZHTk5Pl1OzZpi2oVi0Jv/VWh3XGb9gglnSL+BWLkOCrrnJ6nXHaZYh5rs+FMZABFDxe/a9Tx7+YMmWKvPPOO7Jv3z6JioqSrl27yvjx4yXM7kfDnV27dpn5Nm7cKIcPHzbjclSuXFnat28vzz33nJQvXz7PXgcAFEUh/iG2KxsBAAAAAPlPg4m087GSHh8nQdWquYQB8Zs2mwCm5MO9xd+ue/Dz339vQgZtKzdmjES0amlr05Bp3/0ZlTilnnjcodrHx9dXTs+fbx6nnT3rEjSZXiPS0yUt1jEQcg6MNIzQLuusTHd4vr5mHkvKxZBHBVapLMU7djShUlCNGg5t/mXLSuW5c8zz/MuUlfSEBNN1nlYzaQhkScpYVtqZM6bNvqqpyofzJT1Be89w7emiVN8+UuzOdiYwcg6iQhs0kJJ9+5hlB5Qt6xJohTZubIIqrZRykJoiPqGhGcsMcAyozD5JSXEbXl0+FMt4nvJ1em76+XOSeuJExnypaY6bc/KkxP7wg3kcUq+e4/Pi4uTElKnmcbEO97gETYeeHWyWG1SnjlT/fIlDW8zAQRJ3IcCuu2O7wzmEf2fPNuGXvsboN9+UwMqVbW3xGzfKmYWfmNdY4v77JaTetRe39dQpObfsa/O84KuvlpBrrrn4+i0WSdyyxTzPr3hxE4467B/OYwCFL2gaNGiQTJ061YyXMXjwYNmxY4f5e9OmTbJixQrx9fXN9LkxMTFy5MgR89zo6Gjx9/eXrVu3yrvvvisff/yxbN682YytAQDIHSu7ZlxpBgAAAADIHZb0dJG0NIdqHg0lzv/4o6THxklA2TKm+zd7h0eOlJRDh8U/KkoqvvqKQ1vMMwMvntTfvs0EQVaxP/1sqoiUhib2QZMGF8m7d9tCmEsFQvZ0u7VSRbfZuU2FNmwoAWXLmW11pt3Ihbe41Szfx6kbu5IPPywl+/Rxe2FjcN26UuH/XnKZbrY1KMhWpWMNmXR8ptCmTSX5UIykHowRn+AgM03b7Mdp8i9VSjITct115uaOvj/O75Ht9TdqJFXmve+2LbBqVam78feLnwMn1Rd/ltEFnpsxn0o/9aSknjjptkJI1+nj55vRXWFoqEObb/HiElS3rmnzi7hY/eVctaXvaVYruuzbL1UNZiqanN7PlGPHbJ87S5pj8JW8d6+c/fxz81j3r33QpJ//YxMmZOyLJ59wCJokJUX2PZDRpX9469ZSafpbDsvdc9fdknzwoARVrSrVv/zCoe34629I/G+/mW2t9O47Dq819qefJPaXX8y0yO7dJaBChYurPHxY4n//XXwCgyTk2mskoGJFh9effOiQeZ5vsWIOY4qhcDmzeIkUa9fWpVtOK/1O0i46S3TqKAWR1wZN27ZtM4Oyd+7cWT799FPb9GrVqsmAAQNMWPTggw9m+vzWrVubm7Nbb73VVEXNnTtXhg4d6rHtBwAAAAAAKGy8/URZXks5dlxSjx6RtNhYE6rYn9jXKpqzX3xh2kr27OkQVCRs/VP29+4tlvh4Kd3/aYl66ilbm4YOh/oPMI8jbr/dJcRI+H2jJO/bJwGVKrlsj2+4XSgUnyB+dn87dCvnFAr5RUaKf4Xy4hcWLr5OY3H5ly5tKpn8wsIkuJ5r2FJ96Zfmddsv36r8iy9KZjQQycyVjivkHDJpoLSnY8Zn1i8qSgIrRrsNm/KLfSBoFVSzZqbzR7RqlWmb/tvM7N9niY4dzc2dsObNpe7WLRnBkF3waf18VPlogana8i/tGsiVfmaA+Uz5lyrt0hbauFFGtZqva2joFx5hAhvtms/XKVBz6JLQJfiyb3PqytAhMHN8Hea5utyUFJdgy1q9l7Bpk9v3JH7TJjk97wPzOKJtO4egKWHLFjn8XMZ56PITJ0qJ+zrb2pJjDsmeC+OIlezdS8oOH+6w3L9uutl0LRjWpIkZc8ze0fEvSsqhQ+JXqpRUmDTRoe3c8m8l6e+/TVVXyR49HL57kg8cMEGd7jet+NLKLvv9o5WL2qb7nO4Mc++388jw4SYcdfedYv+dpArib6jXBk0fffSRKVUcOHCgw/R+/frJsGHDZP78+ZcMmjJT5UI/sadPn861bQUAAAAAACjsCsOJsszoOaj0c+cyAhY/f1MpZO/0//4naSdPim94hJR8qKdD29Hx4yVuza+SnpgoNVf+4FCVcer99+XUe++Zx9W++FyCa9d2ONl7esFH5nF48+YOQZNvcJAJmaxj9dgzVSEatKSlSXqc6zhDpsJIK4nchBNhTZqadg2FnBW76y4Jvb6haddqGofnNWsmtS50m+ZMu3+z7y7PmX13ZwWFhqH2IZP9Z1n3m06zfpYJTi/sF/1c6+fKKWRSvoGBJkjNTMlLnMO1D1Fd2gb0Nzd3Stx3nxRr2zaj+squW0WlXSZWeue/Joxy7j5Rg5PSTz9tAqWg2rVclhtyw/USULmSBJRzHXZFQxsNTC3abaFTtZi120V3XRJauzLMbiimoXLaqVPmcVrseZft0eqqpL/+Ml1COju/YoWcuzDuWeT994vYBU3nv/1Wjr+WEVpVfv99CWtycSzt+HXr5GC/R83jsiNGSMleDzl0n7iv6wPmO6hY+/YS1f9ph3UeHjHS7Jug6tWk9BNPOLSdW7bMPF+rE8322Enev990d2gd40s/T7Z9kJqaMX6Zv79XD81QrF1b89tpH2Dbv8/2wbfOWxB5bdC0YcMG0zVe48aOg8YHBwdLgwYNTHtWJCYmSmxsrLnfvn27PP/882a6jtUEAAAAAAAA7zxRZk72+vk5BCraRVXClq0mgAlt0kQCo6NtbUl79sjxV141YZKO4WNfVaDT/mqS0aVaRLt2Ev3mZId1/fvOu5ISE2MCGOegScee0Qois006no5d5YVvWGimVUIOFUSxsS5dmIVcf31G6HPhomkrPdlafvx408Wb8/gyqurHH7kNA1RktwckUh5w2xYYXdHcigJrCJpZdZ5O0883IVPBZbqac9MVn9LgKbxFC/fPCw6WqKczD7cqvuLY3aS96MmO3wv2Sj/aT0rc38UEXwFO4WrIDTdIhVdfMd8PIfUdq/60miiy10MmqHJu0zA5pGFD87zAKo7hr7JWXbntktA+3HJqt68Gy04opmG6fseaTXNTxHHum29MQK6v1zloOvXBfFMNpt97zkHTv3PnypmPPjaPa36/QnztuhY887//ydFx482YbNFvT5eI226ztSVu327CLQ0AtbtC+2o83dZjEyeZ16D7tXiHDg7rPLv0K7GkppguQp3HFEuOicn4Lg8MlIDo6FwJuHwvfKdYfyf13tolZtqJExJ/MMZt8F2QeG3QdPjwYSldurQEufmHUrFiRVmzZo0kJydLoNMH3tmsWbOkf/+LyXfVqlVNNVTz5s2ztB0HDx404z3Z07GeAAAArgTHGAAAwNuOMXL7RFnSP/9I2rlzJigKadDAoe30xwslcccOsSQmSoWX/8+h7fiUKXJqzlzTVn3ZMnP1vFXcuvWm6kppN1P2QZOeOIxdtco8dl6ffbdS7sYSsoZCaW4qiPzLljPd1GkoZE7S2gVNYXoB9dNPmzbnUEi7wqrx3bdm2c7jsgSUKSNVF3yYyZ4Th5DMWWYhE5z24WUq7vQz7E1VechfGm45V1ZZ6feQ/XeRPf1eKDdiRKb/lqt+tCDTddb4aqn5Djahu5Myzw2RUn37mFDJOWjSYMWveImMUMwu1LF+nxW/916xpCRLYNUqrq+lRg3zPedX6uIYbs7jbTmHV/ZtzuGVczVYpuN/paeLj7/jd5v+fiTt3Jnx+I62LhW2GlKZx7HnXYKm4y+/bC4S0DHJnIOmo2PHSdwvv5guC3UsO4fnvTFZTs2fb6quqnw436FiLvbnX8w4d7q/NXi07/5Tu1E9Ne99M5ZY2tmz5jdUAzLzGhOTCnzI5NVBU3x8vNuQyVrVZJ3nckFTx44dpW7duqaqadOmTfLFF1/IyZMns7wds2fPlnHjxmVz6wGg6PkriwF+7QsDzwJFHccYAADAG48xnMMmuTDGiZ4oC7rqKocTZWmxcbK/Z08T3ITdcrOUHzPGYVkH+j0qqUeOSGDNGlJj6VKHttgff5TYlSvN4/ITXnQIT/Tqcg2Z3FYJ2VUQpWVSQWROuloyAjLbMn19TZWT6bqpzsXu7azKjxtrqgf8IiJc2sqNGimiNzf0RGNmYw2ZaiU3XdgBQFbpd5e7iqZAHaPNzThtKqRePXNz33athDiF+7ZlRkebcCszddavuxgMOSk3doyknTmjW+zSFnF7GwmIrmie6zyWmwZh4a1amXDL3yXc8hG/qNJiSU5x+O5X9tvhNtyyBl+XCcWcq5nSExJM1VZafLzLWHGpx45K/Pr15nGJLl0c244fk1OzM7pRLdWvn6nG03H6rNtQ0EMmrw6aQkND5fjx427btBs86zyXEx0dbW7W0Om+++6TRo0amZBquNPgau707dtX2rZt63Il0GOPPZbFVwIARZMlPsH0c64/yj5Og8UC4BgDAAB4Rl6cx7CGTQce6WM7UabCbr7J4USZXtVuvdo89chR1+VcODHoPAZRRtvFAEbDJPtKAe1KTsMbnUfHMrIXcs01JpjSk5XB117rcsKy7tYtmVb8VPi/lzJ9zSH162faBgC4UBmayfn6zIItFdGypbm5bWvTxtzcCWvaJNOLmf1Ll5aaP65y6c7UqvxLL0l6QrzbiweKtb9Tgq++2lQ0OQuMrighN95gqrB8nF6rVpdp6JfR7V5Alrsy9BZeGzRVqFDBjKmUpAOzOe38Q4cOmW71LlfN5M51110nDRs2lLfffjtLQVOlSpXMDQBwaWWeHezQv/U/bdtKyv4D4l+lstRcvtxc9aH9WwPgGAMAAHhOfp7HSI93DIw00AmoUMHc+0dFucwf2a27pJ8/J36Rrl0wlRn6nJR5dlBGmFSsmEObduukN3c0THK+kty2PTqWk914TijanHvlSDt1ytzrWFz2bfTKAXgfrTYKKFs20/aIVu6DLRXZrVumbSV79zY3t8/r2tXc9IUb6d0AACnPSURBVKJrZ8HXXCPVvvhc0s6dlxNvvGEu0tBKJg2s9GYd97AgVzV57a+nVh2lp6fL+gvlZvbVTJs3b5Ybb7wxx8tOSEiQUxd+PAAAV+7M4iWmH3T9YdRAyZlO0zadR+f1VloNq//T/ov21ZvLbrvtNnn44YfF08aOHWvGKywInF+zPtZpuU3HZtTjCncHewAAAMg+6/G9qWayuwg4aecul/8fqPnD91Jj+TdS/sXxLssp2bOHGTA+stsDLm06RpGGVH7Fi+fKQOzA5fgGh5gKBb0HgJzy0Z59nH63NEDS7gxPvvWWJGzcaMZk8itTJmP+4CDbuIfuzqkVFF4bND3wwAPmDXnzzTcdps+cOdOc6OvRo4dt2u7du2XnhVJsq6NHXUuy1cqVK+XPP/+Upk2bemjLAaDo0Uom/ZF098OopcPW/tt1Hp3XE5xDCudAZe7cubYfe19fXylWrJjUq1dPnnrqKdmxY0eW1vHKK6+Y59xyyy25vv2fffaZTJkyRYoyff26H3Lbgw8+aI4dPvjgg1xfNgAAQFENmazH9/5lL54o05NnBf1EGWBfqWR/q/P7b1J34+/m3n46AOT2b6dWL5kqWxHxi4rK9JxaQeK1XedZT/699dZb0rlzZ2nfvr05ETh16lRp0aKFOWlk1bp1a9m/f7/DlcpPPPGEHDlyRFq1aiVVqlQxlVC///67fPzxxxIRESGvv/56Pr0yACh8nAcE1nsNmFTaiRMSfzDG9kOa32XA+tugYmNjZdu2baYr1QYNGsiCBQvMOH6Z0d+R6dOny6xZszyyXSVLunYXUtQUL17cI8vVYFHHKpg8ebL06tXLI+sAAAAoqifK9nTsaDtRFlgx2vb/AwXh2B8AgILg3DfLHX477X8fNXCyP6em85bolPHbWpB4bUWT0mqm1157zZwI1NBJQ6L+/fvL0qVLzUmjS+nevbsZx0mvXn7mmWdk2LBhphs+Hfxyy5Yt5qQiACD3wybrVRhpx4+b6ZbEpAITMqly5cqZW82aNeXee++V5cuXS4cOHeQ///mPnD17NtPnffPNN3L+/Hm58847HaZrhZReBPHQQw+ZCxmio6PlpZccBxH+6KOPpFmzZlKiRAmJjIw0F0HoxQ+ZdSOn1Ve6rLi4OId5NOjS52vopY4dO2aeExUVJeHh4XLTTTfJqlWrsrQfPvnkE6lVq5YEBwfLzTffbAaItjp9+rR5PXqhRkhIiNlXo0ePluTkZNs8586dk0ceecTsSx1LUbsUfPbZZx3WMW3aNKlbt65Zh67rxRdflJSUlGxXpX3++edmOWFhYab977//dnie7ksd8Fr3me6LTp06yd69ex3m0Wna9a5WNQMAAMBzJ8qs/z/A+KwAAGTQ4Kj8Sy9lem7Mek5N5ymIIZPXB01+fn4yePBg2bVrlyQlJcmhQ4fkjTfeMCfT7O3bt89l3IWuXbuaQOrgwYPmhJyOy6Td6+lJr8qVK+fxKwEA73Zq3gfyT9u25pa4a5dDW+zPP9vaYn/80fwwhjRoYAYztEo+FCOn5s51We7uu+82zzv8/PMubXFr10leef755+XMmTPy3XffZTrPjz/+aC5SCLTrg95q4sSJcuutt5ogY+jQoTJixAj5/vvvbe36O6TTfvvtN/npp59MGKXBSGbjBXbp0sX8rjl3I/f++++brmU1uNHftZYtW5rw6+uvvzbrvuuuu+SOO+64bJhy/PhxU9k7b948WasnCkJDTeWwLlPpb+7VV19t1q/VxC+//LL897//dQjQRo0aJRs3bjQhkAY/CxculKuuusohJNKLRfQ51opk7f5WA6vs0G2dMWOGfPjhh7JmzRoTBvbp08fWvn37dlPprF3ibtiwwXSR6+/vL23atLG9HlWtWjUpU6aMaQcAAEDRPVEGAEB+KNGp4yUvwNa2gvzb6bVd5wEACo60s2clZf8B89hiV9Wi0uMTbG3psbFun596MEZST592mZ5y4KBZXkr5Ci5t6Yl51yfttddea+737NmT6TxaIVOxYsVMg6F+/fqZxwMGDDAXNaxYscJ07aq08sfenDlzTGWSVknZdwVrpRdUaLexGixpZZHSiyU0SLGO46TBjoZjeq/Biho5cqQJuDQU0q5nM6MBjFZNWYMh7TZQL8LQyisNcbRKafjw4bb5tapIx0PUbgPHjBljpmmXtQ0bNpQmTZqYv/X5WlGldDwkHc9q0aJFJsCyBj0TJkwwFcqTJk3K8oDOGtLpfihbtqz5e8iQIWaf6HQN3HQ9uo5x48bZnjN//nyzf7/66ivz3ljp+3ep9xgAAACXd7mTYAX9RBkAAMg+giYAwBXzK15cAqpkVIP6OFX0+IaG2NokMND0KZuwebP4BAXaqpp0YGA/p2pUFVC5klhSUiTgwgDCDssNzrtu9qxVsZcKPzSc0S5Z3XHujrVChQqmWzsr7bJ1/PjxpgLo5MmTkp6ebsIYrcjNTO/evU11UkxMjKmA0uqj2rVrmy74lIZOug7tjs+eViMFBARc8vXqc+yrj7S7uTp16tgqoXT7tOJJgyetDNbXnpqaaqZbPfnkk2ZMK63S0kCtXbt2pkpLu7bVLm/1Offff7/DPk1LSzMB0dGjR6V8+fKSFTqfNWSy7lt9v7TSScMt3Q9aUeVc7azrce5iz1oJBgAAAAAAgKwjaAIAXLGSvR4yN3fCmzeXmsuXuwwMrN3laSWThkw6TlP8xk1mHvsy4RpLl2a6zrCmGZUyecEasNSoUSPTeTSM+ffff922OQc7Gq5YQxkNlG6//XZT+aMVQVotpN3vaVdv9mMeOdNu8bQCR8ca1HEGtes4HWfQSpevwdOXX37p8lwdV+lKaDe1Goxp2NSoUSMT4mjoZK1mUhoqHThwwIxxpeNC9ezZU+rVq2cquayvXcdWtA+07PdlVrnbt8q6Dr3XqjDtys9ZyZIlHf7Wrgqzs24AAAAAAIDc8Ffz5g5/p10YTiElJsahrfbPP0tBRNAEAPA455BJ+2Xf0zGjuwy/qCgJrBht2nSezPpzz086BpGGEhoIZeb666+XN998M9vL1vGJtPpGx3HSIEZpJVNmoZWVVgZpF3FayaQhlVY29erVy9Z+4403mu7vNATS8Co7tMs93S5rCKRVVjoeYv/+/W3jUWk11aOPPurQdaAz3Wfdu3c3N+0eUKuttm7dKtdcc42pHtLu9u655x7xJN0PWjFWvXp1s88yo4Gfbo/ODwAAgKJ7ogwAgILANzjE9NiS1aEF8htBEwDA4859s9whZLIPknx8fc00axCl8+Znn+3abZuKi4szXbxNnz7dVOToWEcRERGZPu/OO++UwYMHm8BFxxvKKh3fSEMXHTNp6NChcvjwYXOflaoj7T5PxzPS9bZq1cp0oWfVo0cPmTx5stx1111mHu36TrvS09dSs2ZN061dZnTdOhaTBme6bc8//7wJjazjRdWtW9eEWDrek3ZPt3jxYvn8888dlqHjQd1www0mVNKARyuuQkNDpUqVKib8GjFihLzwwgvi5+dnQivtek8rx7SrvVdffVVyi66ncePGZn8MGjTIVCxpkKfbq+NB1apVy8y3evVqUx2llWIAAADIPd52ogwAgPxQ28svwCBoAgB4nDU4KtaurdtqJZ2mYVN+h0zWMX/0f4LDwsJMKNKiRQuZMmWKCVcuRat/NKTQCiP7LuQup1SpUrJgwQLT/Z2GN9o930svvSTPPPPMZZ+rXeNpF3tr166V+fPnO7RpQKSVR9plnIZGJ06cMCGLhi5t2rS55HLLlClj1q/BklZKaWC0bNkyW/ilAZGOzdS5c2ezrzp06GBe88CBAx3WP3r0aBPqaJhUv359+frrr23d1ekydDyladOmyXPPPWeWra/HviorN+j7smbNGrMftDs/HYNJAzl9ryIjI23zaReE+nqLFSuWq+sHAAAoarz9RBkAAMg+H4t1hHPkml9//VVuuukmc2LLOig7AHi7v//+29xbK0BypQuNtHQRP1/xsxsrx5v/x1SrYjR80S7YtGoH3mH//v0mCNu0adMlq9Eu9W8gr377OcYAAKBo4RgDAAB4wzFG5oMVAADg4S40fEJDzX1hcfPNN8uECRNkz549+b0pyAatupo1a1a2ujwEAAAAAABABrrOAwDkCW+uVMqOfv365fcmIJu0e0QAAAAAAADkDBVNAAAAAAAAAAAAyBGCJgBAljGsH4oyPv8AAAAAAACuCJoAAFni6+sr6enpnGxHkQ2Z9POv/w4AAAAAAABwEWdLAABZEhQUZE62Hz58mLAJRYr9517/HQAAAAAAAOAif7vHAABkqly5cpKcnCznzp2T8+fPm8oOHx8f9hiKRCWTNWTSfwcAAAAAAAC4iIomAECW+Pv7S+XKlSUiIkICAgIImVAkaJiqn3f93OvnX/8dAAAAAAAA4CLOlgAAskxPskdHR7PHAAAAAAAAABhUNAEAAAAAAAAAACBHCJoAAAAAAAAAAACQIwRNAAAAAAAAAAAAyBGCJgAAAAAAAAAAAOSIf86ehkuJi4sz91u3bmVHAQBQBFh/863HAJ7CMQYAAEULxxgAAMAbjjEImjxgz5495v6xxx7zxOIBAEABPwbw9PI5xgAAoGjhGAMAABTkYwwfi8ViyZUlwebw4cOydOlSqV69uoSFheV60qgnl9555x2pV6+e1+31hIQEad26tXz//fcSEhIiBU1B2b783I68XLe3f56Bgvj9gfz5ztErgPTg7O6775YKFSp47G3gGMM7//0VpO3Lr23J6/VyjIHCoiB9fyBzHGMU3u/kgv5vsCBtX1E4xvDmzzJQkL8/kD/fObl9HoOKJg/QN+bRRx8VT9IPV7NmzcTbWEvxmjRpkushXGHavvzcjvxYt7d+noGC+P2Bwv2dwzGGd/77K0jbl1/bkl/r9eZ/70BB+/5A4f7O4RjDO/8NFqTtK0rHGN78bx0oiN8fKBzfOb75vQEAAAAAAAAAAADwTgRNyFMBAQEyZswYc18QFZTty8/tKCj7APA2/NsB+PfnDd8P+bUtBWkfAN6EfzsA/wa95TuCYwzAuxSk7w8UDnSdhzwVGBgoY8eOLbB7vaBsX35uR0HZB4C34d8OwL8/b/h+yK9tKUj7APAm/NsB+DfoLd8RHGMA3qUgfX+gcKCiyctER0ebtFnvAW/H5xkA3zkFB9/JKEz4PAPgO6fg4DsZhQWfZQB852TOx2KxWC7RDgAAAAAAAAAAALhFRRMAAAAAAAAAAAByhKAJhVJqaqo888wzUrJkSSlRooT07dtXEhMT83uzAOCKffLJJ3LLLbdIeHi4VK1alT0K5CGOLwAUZhxjAPmHYwwAhRXHF0UHQRMKpUmTJsnKlStl69at8vfff8v27dtl6NCh+b1ZAHDFIiMj5emnn5aJEyeyN4E8xvEFgMKMYwwg/3CMAaCw4vii6GCMJhRKlStXlldeeUW6detm/l6+fLncf//9cvr0afHz88vvzQOAK7ZkyRIZOHCg7Nu3j70J5BGOLwAUBRxjAHmPYwwAhR3HF4UfFU1F3KlTp2TIkCFSs2ZNCQ4OlqioKGnZsqX8/PPPebL+l156yQRA1atXFx8fn8t2A5Weni6TJ0+WunXrmu2tVKmSDB48WOLi4mzznDlzRg4ePCgNGjSwTbv++uvl/PnznJAFioC//vpLRo8eLU2bNjXfaREREeb7QCuA7L8rvPH7DfAWHF8AKIw4xgDyH8cYAAobji9QWPjn9wYg/+zfv19uu+02iY2NNWMY1a5dW86ePStbtmyRQ4cO5ck2jBgxwoyjpEGQBkSXM2jQIJk6dap06tTJnIDdsWOH+XvTpk2yYsUK8fX1NYGS0rGZrKyPrW0ACq/33ntPpk+fLh06dJAePXpIQECA6Upz1KhRpm/gtWvXSkhIiFd+vwHegOMLAIUVxxhA/uIYA0BhxPEFCg0LvIK+Ve5uYWFhOV7mLbfcYomOjrYcPnw4W89LS0uzzJo1y5KamprpPLNnz7YkJSVddlm7d++2Pb7mmmssVapUyXTeP//80+Lj42Pp3Lmzw/SpU6eaffHhhx+av0+fPm3+3rlzp22e48ePm2n//PPPZbcJuWfSpEmWLl26WKpVq2b2/6XeX7V27VpL69atLeHh4ZaIiAhL27ZtLZs2beItQbZs2LDBcubMGZfpI0eONJ/DadOmee33m73Fixdf9t9UUaLf+Q8++KClbt26lmLFillCQkIsderUsQwaNMjt75zOf++991pKlChhCQ0NNb+J33//vaUoyu1jDI4v4GkcXyC/cIxR9HB8cWU4xuAchrfhGAP5geOLomlnITyHQdDkRQdozZs3t3zwwQcOt48//jhHy/vxxx/NMvUkpkpOTrbExcVl6bnLly83z+3evbvbk7EDBgww7fPmzcvWNl3uRKz1JPFPP/3kMD0hIcH8A7vzzjtt0ypVquSwb3SbNbi41Mlj5D59v0qWLGlp06aNJTIy8pLv76+//moJCgqyVK9e3fLGG2+Ymz7W0GnLli28Pbhi+jnSz+Rjjz3m1d9vVgRNjlasWGFp2bKlZfjw4Zbp06db3nnnHcvTTz9twpLy5ctbjh07ZptXLzrQ76YyZcqY/5nU+Rs0aGDx9/e3fPfdd5aiJjePMTi+QF7g+AIFDccYhRfHF1eGYwzOYXgbjjFQkHB8UbitKITnMAiavOjHrnfv3rm2vOeff94sc8mSJZa7777b4ufnZ/6uVauWObl0OZMnTzbzd+vWzeFkrP6D0On6jyS7Lnci9o477rD4+vpaEhMTXdpuuukmS+nSpW1/jxs3zlK/fn3LoUOHTDVTs2bNLP3798/2NuHKZKeio1GjRiYMjImJsU3Txzrt9ttv563AFVu2bJn5fho9erRXf7/pNmkA9cknn1gqV65sHrt7HjLoftL37eWXX7btkvvvv9/sb/uKyfPnz5v9Wbt2bUt6enqR2n25eYzB8QXyAscXKGg4xih6OL7IGo4xOIfhbTjGQEHC8UXR9IkXn8MgaPKyAzTtrkk/SFeqY8eOZplRUVHmJOb8+fMt7733njkZqtP18eW8+eabZt6uXbuaiqgnn3zS/D1ixIgcbdPlTsRee+21Jrl1R//B6bqt3VmlpKSYYEnLCbX8sE+fPpb4+PgcbRdyx6Xe37///tu8f/o+OdNp2qXYkSNHeCuQYxrOaOCsV3vYd6vpjd9vc+bMcemGhC70Mrdu3Tqzj4YNG2b+jo2NNdWTrVq1cpl3/PjxZl59TlGSm8cYHF8gr3F8gfzGMUbRxPFF1nCMwTkMb8YxBvITxxdF1zovPodB0OQlrGMlWCuPNCDSq+vdjUOSFToOji5HuyazH2vk1KlTJpwpV66cGavkcqZMmWKWYx2DR7t/yqnLnYjVbdUu8dx56KGHzPp1fCYUTJd6fxcsWGDev5kzZ7q0vfvuu6Zt6dKlebCVKKys1UhaYpxVfL95J63wOnHihOXgwYOmK0QtJ7fvlnDNmjWZ/l59++23pu2tt96yFCW5eYzB8QXyGscXyG8cYxQNHF/kDMcYnMPwZhxjID9xfFF0JBSicxi+Aq/QuHFjGTt2rCxatEjef/99adWqlbz11lvSvHlziY2NzfbyQkJCzH337t0lMDDQNj0yMlI6dOggR48elV27dl12Of3795ebbrpJ9u7dK3Xq1JExY8aIp4SGhkpSUpLbtsTERNs88D6HDx829xUrVnRps047dOhQnm8XCocXXnjBfF8++uijMnz48Cw/j+837zRr1iyJioqSSpUqSdu2beXMmTMyf/5883up+L7x7DEGxxcoSPj3Dk/jGKPo4PgiZzjG4BxGYcUxBjyJ44uiZVYhOodB0OQl1q1bJ0OGDJGOHTtKr1695OOPP5aJEyfK1q1bZcqUKdleXnR0tLkvV66cS1v58uXN/enTpy+5DL1AqV+/frJmzRq566675K+//pKuXbtKSkqKeEKFChXk5MmTbsMm/QdVunRph9AM3iM+Pt7cBwUFubQFBwc7zANkh548nzBhgjzyyCPy3//+N8vP4/vNe+nv5HfffSeLFy+W0aNHS4kSJcxvhxXfN549xuD4AgUJ/97hSRxjFC0cX+QMxxicwyisOMaAp3B8UfR0LETnMAiavNhzzz1ngpWvvvoqR1cWqZiYGJc267QyZcpk+vz09HTp27evzJ49W8aPHy9Lly6VGTNmyOeffy5dunSR5ORkyW2NGjUy612/fr1LNdPmzZvlxhtvzPV1Im9YK9HchYhUq+FKDtDGjRsnvXv3NleI+Pj4ZOl5fL95Nw062rRpYw7W9P3XCp2hQ4fKSy+9ZNr5vvHsMQbHFyhI+PcOT+EYo+jh+CL3cIzBOYzCgGMMeALHF0VTdGE6h5HffffhylStWtVSq1atbD9Px2KKiIiwVKxY0WHg78OHD5txGmrXrp3pc3XsJh00XD8+EyZMcBlPx8fHx3L33Xc7jP2UG2M0bdmyxSy7c+fODtOnTp1qtuWDDz7I1vqQt+jfGHlp3Lhx5ntBx2/LynhzVny/FU5NmjSxREdHe13/xt54jMHxBfIaxxfIaxxjwIrji5zjGINzGN6AYwzkJY4vUBiOMfzzO+hCzmlqqdVHTZs2zfZzdSym1157TR577DHz/D59+pgqJK1K0vtp06Zl+twVK1aYdHXSpEku451oV3paNaBjoSxcuFAeeuihS27HBx98IPv37zePT5w4Ydat3VypKlWqODy/Xr168tRTT5lxIzp37izt27eXHTt2yNSpU6VFixby4IMPZns/oGDQajX166+/yn/+8x+HtrVr15rP1A033JBPWwdvM336dDNeXOXKlc1VIQsWLHBoL1u2rNx+++1un8v3W+GUkJAgp06dsv2WaMm5ft840+8bRYVszo8xOL5AQcLxBXIbxxiwx/FFznCMwTmMwoBjDOQmji9QaI4x8jvpwuWdPHnS7fQhQ4aY1PLll1/O8W789NNPTUoaGhpqCQ8Pt9x+++2WX3755bLP27BhwxW1W7Vo0cK8Bnc3bXOWmppqee2110zFVWBgoKVChQqWQYMGOVRloWC6XMXajTfeaKrsDh06ZJumj3Va69at82grURhYKy6z891ij+8373TkyBG303/44QeLr6+vpVWrVrZpXbp0MdM2b95sm6a/I5UrVzYVPOnp6ZaiwlPHGBxfIK9wfIG8xDFG0cPxRc5xjJGBcxjei2MM5BWOL4qmI4XwHIaP/ie/wy5c2qBBg0xC2bJlS3OFfmxsrCxbtkxWrlwpTZo0MfchISHsRhQ49hVrWiWnFWuDBw92W7G2Zs0a8xnXvkn79+9ve86xY8dk9erVUr9+/Xx6FQC8QadOneTIkSPSqlUr8/2iV8v+/vvv8vHHH5v+iletWiUNGjQw8/7zzz9mLKGAgADzG1usWDGZOXOmbN261YxJ1LZtWykqOMaAN+L4AkBe4fgi5zjGgDfiGANAXulUGM9h5HfShctbsmSJ5Y477jDVO0FBQab6qH79+paJEydaEhIS2IUosLJbsab9jmpir+OEaYWdfu5///33fNl2AN5l4cKFlrvuusv0Y6y/lcHBwZY6depYnn76acv+/ftd5t++fbulQ4cOluLFi1tCQkIsN998s+W7776zFDUcY8AbcXwBIK9wfJFzHGPAG3GMASCvLCyE5zCoaAIAAAAAAAAAAECO+ObsaQAAAAAAAAAAACjqCJoAAAAAAAAAAACQIwRNAAAAAAAAAAAAyBGCJgAAAAAAAAAAAOQIQRMAAAAAAAAAAAByhKAJAAAAAAAAAAAAOULQBAAAAAAAAAAAgBwhaAIAAAAAAAAAAECOEDQBAAAAAAAAAAAgRwiaAAAAAAAAAAAAkCMETQDyzb59+8THx0fGjh3rle/CyZMnpVevXlKhQgXzOm677bYrXuaqVavMsubOnZsr2wgAQFHEMYYrjjEAAOD4gnMYADzF32NLBoBCbvDgwbJw4UIZOXKkVK9eXcqWLSveQk826W3gwIFSokQJKch2794t06ZNkxUrVsiBAwckMTFRSpcuLQ0aNJB77rnHHCiHhYXl92YCAJBrOMbIGxxjAACKEo4v8gbHFyiqCJoAIIe+++47adu2rYwePdrr9qGGTOPGjZOHH364QAdNWtn1+OOPi7+/v3Tt2tU8Dg0NlaNHj8pPP/0kTz/9tCxZskSWL1+e35sKAECu4RjD8zjGAAAUNRxfeB7HFyjKCJoAFBkpKSmSlpYmwcHBubI8DTtKliyZK8sqTHQfJyUlmUDoSnz//ffSt29fufbaa2XZsmVSsWJFh/YRI0bInj17TFUZAAD5iWOMvMExBgCgKOH4Im9wfAHkDsZoAgoxvZJCx/v54Ycf5LXXXpMaNWpIUFCQ1K5dW95///0sj2Wg07RN57HSShid9u+//5rH2pVZRESEdOzY0QQw6t1335WrrrrKBDt169aVzz//PNNt/eijj+S6664z81auXNmsMzU11WW+I0eOyBNPPGHmCQwMNOMjPfroo3L8+HG327xt2zZ59tlnJTo62ix77dq1l9xncXFxMnz4cNu+KleunOmabf/+/S7LtlgsZj/q46yMq6Tzz5w5U5o0aSLh4eHmVq9evctWRFnfR61CcqbjQlWtWtVh2po1a+TOO+80266vWQOa9u3b2167vl9azaSqVatm23779/7s2bPy/PPPS82aNc1+iIqKku7du5tgx922abd2L774otlvus5PPvkkS9tyKUOHDjX3uiznkMlKuyzU9wsAkLc4xuAYg2MMAADHF5zDuNRxIucwXHEOA4UZFU1AEaCVHwkJCfLYY4+Z0GDGjBkmbNAQ4eabb76iZbdr186EOOPHj5d//vlHpk6dKp06dZLOnTuboEkrUvREhE7v0qWL/PXXXybcsPfFF1+YAOOpp54ygYT+rUGIhjtz5syxzafj8zRr1kySk5PNcjXU0HXq61m5cqX89ttvUrx4cYdl9+jRQ0JCQkxfxHqgU758+UteLaRd4a1evdpsqz7n77//Nsv/9ttvzfL1tepr03330EMPSfPmzU3QpW666aZL7iud/8MPPzRBk47rpF3W7dy5UxYtWmT2X27YtWuX3H777WY/PvPMM2bcqGPHjskvv/wif/zxhzRt2tR8Ds6dOyeLFy+WyZMnm5BQadBnDZn0tej+7tOnj1xzzTUm4Hv77bfNtut+qFKlisN6hwwZYvZfv379pFixYlKnTp0sbUtm9u7dKxs3bpRbb73VLAsAUDBxjMExBscYAACOLziHkVOcwwAKEQuAQmvOnDkW/WfeoEEDS1JSkm16TEyMJTAw0NKtWzfbtL1795p5x4wZ47IcnaZtOo9V7969zbQnn3zSYd5BgwaZ6ZUqVbKcPXvWNv2PP/4w04cNG+ayTl9fX8vvv/9um56enm7p2LGjafv1119t0zt06GCJioqyHDx40GGdGzZssPj5+Tlsu3WbW7RoYUlJScnS/nr33XfNc5577jmH6UuXLjXTe/bs6TBdp+l+yIqFCxfalpGWlubQZv/3ypUrzXz63jm/j9rmTF9flSpVbH9PmTLFzLtu3bpLbo+799RqwIABluDgYMvmzZsdpu/bt88SERHh8Jqt21a7dm1LXFycw/xZ3RZ3vvjiC/Nc3RZnup4TJ0443PQzAwDIOxxjcIyRGY4xAAAcX2TgHAbnMBTnMFBU0HUeUAQ8+eSTpps5K+2GTLvP02qdKzVw4ECHv7XCR2l3c1rZYqXVMvq3u3Vq1cv1119v+1srj6zdpmnVjbXKZunSpdKhQwdTIXXy5EnbTbuO0wojrTpyt33+/lkr3tR1+fr6unTFdtddd0mDBg1M13/p6emSE1rJpLQLQ12HPee/r4S1oku3NTExMdvP1/xMt1UrifRzYr+fw8LCTBWSu/2s3Rk6j8l0JduiFVfK/jNkpV0Nald+9jftwhEAkPc4xuAYI6s4xgAAcHzBOQxnnMMACg+CJqAI0D5gnZUqVSpXTs47LzsyMtLcO3ePZ21zt04dx8nZ1Vdfbe6tYwJpObWGPLNnz3YJGfSm7dotmzMN1LJKu2vTMZ+sr8Gedh93/vx5E7jkhAZs2m2fdh/nSd26dZM2bdrIpEmTpGTJktKqVSt5+eWXHcaYupQTJ06Y90jDJHf7+bvvvsvyfr6SbbEGTNbAyZ52/afbobc77rgjS68LAOAZHGNkDccYHGMAADi+4ByGK85hAIUHYzQBRYCfn5/b6Rm9v12sIspMampqtpedlXVmh/V5PXv2lN69e7udR8dicuZcZeONsvPe6BhcGsCsX79eli9fLj/99JOpABo7dqwsWLDAjJ+Vlf2sAdHzzz+f5W10t5+vZFuuvfZac79582aXtlq1apmbmj9/fpa3EQCQ+zjG8G4cYzjiGAMACgaOL7wbxxeOOL5AUUHQBMDQihN16tQplz1irSrylB07drhM2759u8OV0to1nh6sJCcnmxDEE3Rd33zzjZw5c0ZKlCjhsj1aZVO6dOkcLVsrfrQLOa0Gym5V06XeG71COiAgwGV648aNzU0dPHhQGjZsKKNGjbKFO5kd+OkVVvratZIot/bz5bbFHa2I0+4UdYBxrVarU6dOrmwLACDvcYzBMYbiGAMAwPFF7uIcBscXQEFC13kAjIiICClXrpz88MMPDlVHGjItWbLEo3tJq142btxo+1vX/8orr5jHHTt2tHX11759e/nss89k7dq1LsvQ52i3b1dC16Xd8/3f//2fw/Svv/5aNm3aZMaHyul4Sj169DD3OvaU8zhPl6vysnZLt2LFCofpH330kRw+fNhhmruu/aKjo83JHfugKjw83G14pa9Pt1WrkBYtWuR2e44fP37J7c3utmRGu9lTXbt2dXmdV1ohBwDIOxxjcIyhOMYAAHB8cRHnMDJwDgMoPKhoAmDz9NNPm0qTO++804QuenL/v//9r+nGbMOGDR7bU/Xr1zfj9zz11FNmHCOt/NFQ5aGHHpJmzZrZ5psxY4bccsstcuutt0qvXr1MZYyGNhqG6XN0mnbLllMPP/ywvP/++ybg2Ldvn1nPP//8I2+//bapQtKxhnLq/vvvlwceeEDmzZtnxmvS0ErHgvrrr79Mt3J//vlnps/Vah6tLnrnnXfMwWiDBg1Ml3KLFy82lV4pKSm2eSdMmGDGV7r77rtNVZDO/+WXX8rOnTtNyGXVtGlTc6/d42mwFBwcbN5nvU2cOFFWr15tAh696byBgYFmbKVly5bJDTfcIHPnzr3sa87qtmRGX7OOyaVjMmnYpvtQ163d9GllmHbFp8vXz4xuPwCg4OIYg2MMjjEAABxfcA6Dcxicw0AhZgFQaM2ZM0fLPSwrV650aWvRooWlSpUqDtNSUlIszz33nKVcuXKWoKAgS8OGDS1ffPGFZcyYMWY5e/futc3bu3dvM82Zrkun67qd6fp0vVa6PJ1Xl79gwQJLvXr1LIGBgZbo6GjLCy+8YElOTnZZxokTJyxDhgyx1KpVy2xj8eLFLddee61lwIABlm3bttnmc7fNWREbG2sZNmyYpVq1apaAgABLVFSUpWfPnpZ9+/a5zKvL1/2QVWlpaZa33nrL7NeQkBBLeHi4ec1jx4697P47cuSIpUuXLpaIiAhLWFiYpV27dpbt27e7vI/6/K5du5ppwcHBlsjISEvjxo0tM2fOtKSnpzss8+WXXzav09/f3/Y+WMXFxVnGjx9v9q0uR7e1bt26lv/85z+WtWvXZukzlp1tuZR//vnHvL9XX321ee36vpQvX97sgxkzZpj3DACQtzjG4BiDYwwAAMcXnMPgHIYrzmGgqPLR/+R32AUAAAAAAAAAAADvwxhNAAAAAAAAAAAAyBGCJgAAAAAAAAAAAOQIQRMAAAAAAAAAAAByhKAJAAAAAAAAAAAAOULQBAAAAAAAAAAAgBwhaAIAAAAAAAAAAECOEDQBAAAAAAAAAAAgRwiaAAAAAAAAAAAAkCMETQAAAAAAAAAAAMgRgiYAAAAAAAAAAADkCEETAAAAAAAAAAAAcoSgCQAAAAAAAAAAADlC0AQAAAAAAAAAAIAcIWgCAAAAAAAAAABAjhA0AQAAAAAAAAAAIEcImgAAAAAAAAAAAJAjBE0AAAAAAAAAAADIEYImAAAAAAAAAAAA5AhBEwAAAAAAAAAAAHKEoAkAAAAAAAAAAAA5QtAEAAAAAAAAAACAHCFoAgAAAAAAAAAAQI4QNAEAAAAAAAAAACBHCJoAAAAAAAAAAACQIwRNAAAAAAAAAAAAyBGCJgAAAAAAAAAAAEhO/D/I/K+gG4hXTgAAAABJRU5ErkJggg==","media_type":"image/png"}}]}]},"uuid":"7b18aa11-c066-4dba-9ce6-b2f5ee4903f0","timestamp":"2026-10-30T05:41:11.796Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":76399,"dimensions":{"originalWidth":1690,"originalHeight":546,"displayWidth":1690,"displayHeight":546}}},"sourceToolAssistantUUID":"f144e621-9627-43da-a358-5bc71f08c6e1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}80{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"67201324f5ba4d2d31494fd51163af5be8abf7efb6c34d767f2b0c07efaf67f5","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_016e9ds3D6QpMkp2JZN6nUE6","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0021/out/figure1.png"}}]}}81{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"6f3119e0-1de9-4168-9ee6-5ac1e1ac6c3f","timestamp":"2026-10-30T05:41:11.801Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"979aa118-c2ab-48a6-a213-2e35cc779abe","keep":24,"tail":["67201324f5ba4d2d31494fd51163af5be8abf7efb6c34d767f2b0c07efaf67f5","45737917c6308f2684c875f87f1a7a8bc014ae762945ff12d05f3769ee851f56"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7e25e83dfe4b2229a0d490f760dc9f05475fa37c316118386e0bc6293daf37d7"}82{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"7b18aa11-c066-4dba-9ce6-b2f5ee4903f0","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}83{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}84{"parentUuid":"7b18aa11-c066-4dba-9ce6-b2f5ee4903f0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMkjzXNp8Tkf4AacVY","type":"message","role":"assistant","content":[{"type":"text","text":"Fix minor-tick labels on the log axis."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1544,"cache_read_input_tokens":29277,"output_tokens":1522,"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":1544},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtMkTsQ7cdqn6aBZfW5","requestRef":"6f3119e0-1de9-4168-9ee6-5ac1e1ac6c3f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e85573a1-cf40-4fef-9088-d98d3280c2c4","timestamp":"2026-10-30T05:41:13.340Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}85{"parentUuid":"e85573a1-cf40-4fef-9088-d98d3280c2c4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtMkjzXNp8Tkf4AacVY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KEDJP4RkMBmYG34Ha6qr1p","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('ax.set_xticks(Gs); ax.set_xticklabels(Gs)','ax.set_xticks(Gs); ax.set_xticklabels(Gs); ax.minorticks_off()')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp /tmp/r1.json out/results.json && echo same\ncat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\n| file | SHA-256 | rows | cols |\n|---|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 | 11 |\n| data/README.md | 73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 | (text) | — |\n\nHashes match bundle.json.\n\nSchema: cell_id (C1..C9, unique), G (int: 5,10,30), icc (0.0,0.2,0.5), cluster_sizes (\"|\"-separated ints), N (int), R=2000, B=399, seed (20261101..20261109, distinct), mu=0.0, total_variance=1.0 (unitless; variance of y), nominal_level=0.95. No dates (synthetic design). No missing values, no duplicate rows.\n\nConsistency: for every row len(cluster_sizes)=G and sum(cluster_sizes)=N (128, 264, 864) — asserted in analysis.py. Sizes follow the pattern 8,16,32,64 repeated (G=5: 8,16,32,64,8; G=10: ...,8,16; G=30: 7 full patterns + 8,16). Clusters are strongly unbalanced (one 64-obs cluster carries half of N at G=5).\n\nAnomalies / issues: none in the file. Methodological note recorded in results `data_issues`: at G=5 Rademacher weights have only 32 distinct sign patterns, so the WCB distribution is discrete and coarse.\n\nInformation-availability: design.csv contains only design parameters (no outcomes); nothing violates the rules. Exclusions: none (out/exclusions.csv, 9 -> 9).\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 computed and matched bundle.json\",\"9 rows x 11 cols, no NA/duplicates\",\"len(sizes)=G and sum(sizes)=N asserted for all rows\",\"exclusions.csv written (0 removed)\"],\"notes\":\"see data_audit.md\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive i.i.d. z-interval coverage computed with same replications -> results key baseline_coverage_iid\"],\"notes\":\"baseline ignores clustering; ~0.95 at ICC=0, 0.30-0.48 for ICC>0\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py runs in ~2 s\",\"seeds from design.csv per cell\",\"WCB vectorised; loop cross-check identical to 4e-15\",\"analytic E[V_CR0] added for bias verification\"],\"notes\":\"\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json\",\"14 consistency checks PASS (checks.md)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30: P1 passed (audit, no exclusions). P2 passed (iid baseline). P3 passed (analysis.py; quantile = inverted-CDF 380th order stat of 399; z=1.96 literal as TASK specifies).\n- 2026-10-30: P4 consistency checks pass; running gate.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -30","description":"Fix figure, write audit, 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":1544,"cache_read_input_tokens":29277,"output_tokens":1522,"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":1544},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtMkTsQ7cdqn6aBZfW5","requestRef":"6f3119e0-1de9-4168-9ee6-5ac1e1ac6c3f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8abab625-f9fb-4b98-9bc8-7f57871670b4","timestamp":"2026-10-30T05:41:25.816Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"8abab625-f9fb-4b98-9bc8-7f57871670b4","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KEDJP4RkMBmYG34Ha6qr1p","type":"tool_result","content":"same\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 1.9s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0021/out/state/gate_receipts/20261030T054129.719612Z.json","is_error":false}]},"uuid":"3b2860fd-805f-4bb0-8ce4-45c5a0bc809b","timestamp":"2026-10-30T05:41:29.728Z","toolUseResult":{"stdout":"same\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 1.9s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0021/out/state/gate_receipts/20261030T054129.719612Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8abab625-f9fb-4b98-9bc8-7f57871670b4","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}87{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"54d5642d58aac98e90c1c2ee7947aca5ed376472ae90f1e19c95e43db2e3596f","message":{"role":"assistant","content":[{"type":"text","text":"Fix minor-tick labels on the log axis."},{"type":"tool_use","id":"toolu_01KEDJP4RkMBmYG34Ha6qr1p","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('ax.set_xticks(Gs); ax.set_xticklabels(Gs)','ax.set_xticks(Gs); ax.set_xticklabels(Gs); ax.minorticks_off()')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp /tmp/r1.json out/results.json && echo same\ncat > out/state/data_audit.md <<'EOF'\n# Data audit (P1)\n\n| file | SHA-256 | rows | cols |\n|---|---|---|---|\n| data/design.csv | f4ff004ed50d893eece1aaa7edced04d3c0439aaedf1d391ea4642a87d0ecc50 | 9 | 11 |\n| data/README.md | 73a6595909d92a69db281e283f193348ac244f255fcd5343ef42ae0353394e67 | (text) | — |\n\nHashes match bundle.json.\n\nSchema: cell_id (C1..C9, unique), G (int: 5,10,30), icc (0.0,0.2,0.5), cluster_sizes (\"|\"-separated ints), N (int), R=2000, B=399, seed (20261101..20261109, distinct), mu=0.0, total_variance=1.0 (unitless; variance of y), nominal_level=0.95. No dates (synthetic design). No missing values, no duplicate rows.\n\nConsistency: for every row len(cluster_sizes)=G and sum(cluster_sizes)=N (128, 264, 864) — asserted in analysis.py. Sizes follow the pattern 8,16,32,64 repeated (G=5: 8,16,32,64,8; G=10: ...,8,16; G=30: 7 full patterns + 8,16). Clusters are strongly unbalanced (one 64-obs cluster carries half of N at G=5).\n\nAnomalies / issues: none in the file. Methodological note recorded in results `data_issues`: at G=5 Rademacher weights have only 32 distinct sign patterns, so the WCB distribution is discrete and coarse.\n\nInformation-availability: design.csv contains only design parameters (no outcomes); nothing violates the rules. Exclusions: none (out/exclusions.csv, 9 -> 9).\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 computed and matched bundle.json\",\"9 rows x 11 cols, no NA/duplicates\",\"len(sizes)=G and sum(sizes)=N asserted for all rows\",\"exclusions.csv written (0 removed)\"],\"notes\":\"see data_audit.md\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive i.i.d. z-interval coverage computed with same replications -> results key baseline_coverage_iid\"],\"notes\":\"baseline ignores clustering; ~0.95 at ICC=0, 0.30-0.48 for ICC>0\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py runs in ~2 s\",\"seeds from design.csv per cell\",\"WCB vectorised; loop cross-check identical to 4e-15\",\"analytic E[V_CR0] added for bias verification\"],\"notes\":\"\"}\np['P4']={\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json\",\"14 consistency checks PASS (checks.md)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30: P1 passed (audit, no exclusions). P2 passed (iid baseline). P3 passed (analysis.py; quantile = inverted-CDF 380th order stat of 399; z=1.96 literal as TASK specifies).\n- 2026-10-30: P4 consistency checks pass; running gate.\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -30","description":"Fix figure, write audit, update ledger, run gate"}}]}}88{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"9b7a2364-6b11-45b2-9f8d-2ae595560460","timestamp":"2026-10-30T05:41:29.732Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"6f3119e0-1de9-4168-9ee6-5ac1e1ac6c3f","keep":26,"tail":["54d5642d58aac98e90c1c2ee7947aca5ed376472ae90f1e19c95e43db2e3596f","e6c1a68094b9e9747fa973cec25fb75950bc19cab539cf9e263c1c272204f85f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b3bca2e57245a5056b0f9a962c58f472f21abdc5b4f288982322b3fed51eed0f"}89{"parentUuid":"3b2860fd-805f-4bb0-8ce4-45c5a0bc809b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtP5SuLX9zZWoHxbFhh","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":2107,"cache_read_input_tokens":30821,"output_tokens":212,"output_tokens_details":{"thinking_tokens":52},"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":2107},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":432,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtP5AHiXUVjLn1w9czE","requestRef":"9b7a2364-6b11-45b2-9f8d-2ae595560460","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"19ae182b-ac17-4474-a298-a88a6ab0de6a","timestamp":"2026-10-30T05:41:31.803Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}90{"parentUuid":"19ae182b-ac17-4474-a298-a88a6ab0de6a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtP5SuLX9zZWoHxbFhh","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KE7Wbnpxegfbx55rLUKH3H","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'))\nprint(d['baseline_coverage_iid']); print(d['mean_coverage_small_G']); print(d['exact_rel_bias_var'])\"","description":"Print extra result values for report"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2107,"cache_read_input_tokens":30821,"output_tokens":212,"output_tokens_details":{"thinking_tokens":52},"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":2107},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtP5AHiXUVjLn1w9czE","requestRef":"9b7a2364-6b11-45b2-9f8d-2ae595560460","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6aa55bad-69ab-48f5-be43-f8eeb88433b7","timestamp":"2026-10-30T05:41:32.647Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}91{"parentUuid":"6aa55bad-69ab-48f5-be43-f8eeb88433b7","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KE7Wbnpxegfbx55rLUKH3H","type":"tool_result","content":"{'iid_G5_icc0.0': 0.944, 'iid_G5_icc0.2': 0.465, 'iid_G5_icc0.5': 0.296, 'iid_G10_icc0.0': 0.95, 'iid_G10_icc0.2': 0.4685, 'iid_G10_icc0.5': 0.315, 'iid_G30_icc0.0': 0.9555, 'iid_G30_icc0.2': 0.482, 'iid_G30_icc0.5': 0.298}\n{'cr0': 0.7456666666666667, 'cr1': 0.8933333333333332, 'wcb': 0.8574999999999999}\n{'cr0_G5_icc0.0': 0.6640625, 'cr1_G5_icc0.0': 0.830078125, 'cr0_G5_icc0.2': 0.49950132978723344, 'cr1_G5_icc0.2': 0.6243766622340418, 'cr0_G5_icc0.5': 0.48828125, 'cr1_G5_icc0.5': 0.6103515625, 'cr0_G10_icc0.0': 0.8393021120293873, 'cr1_G10_icc0.0': 0.9325579022548748, 'cr0_G10_icc0.2': 0.7598750380616052, 'cr1_G10_icc0.2': 0.844305597846228, 'cr0_G10_icc0.5': 0.7543877524211225, 'cr1_G10_icc0.5': 0.8382086138012473, 'cr0_G30_icc0.0': 0.9485596707818851, 'cr1_G30_icc0.0': 0.9812686249467777, 'cr0_G30_icc0.2': 0.9267376448823972, 'cr1_G30_icc0.2': 0.9586941153955834, 'cr0_G30_icc0.5': 0.9252970710455054, 'cr1_G30_icc0.5': 0.9572038665987987}","is_error":false}]},"uuid":"436d0250-44ec-4d10-85a7-9af06ca66e19","timestamp":"2026-10-30T05:41:32.710Z","toolUseResult":{"stdout":"{'iid_G5_icc0.0': 0.944, 'iid_G5_icc0.2': 0.465, 'iid_G5_icc0.5': 0.296, 'iid_G10_icc0.0': 0.95, 'iid_G10_icc0.2': 0.4685, 'iid_G10_icc0.5': 0.315, 'iid_G30_icc0.0': 0.9555, 'iid_G30_icc0.2': 0.482, 'iid_G30_icc0.5': 0.298}\n{'cr0': 0.7456666666666667, 'cr1': 0.8933333333333332, 'wcb': 0.8574999999999999}\n{'cr0_G5_icc0.0': 0.6640625, 'cr1_G5_icc0.0': 0.830078125, 'cr0_G5_icc0.2': 0.49950132978723344, 'cr1_G5_icc0.2': 0.6243766622340418, 'cr0_G5_icc0.5': 0.48828125, 'cr1_G5_icc0.5': 0.6103515625, 'cr0_G10_icc0.0': 0.8393021120293873, 'cr1_G10_icc0.0': 0.9325579022548748, 'cr0_G10_icc0.2': 0.7598750380616052, 'cr1_G10_icc0.2': 0.844305597846228, 'cr0_G10_icc0.5': 0.7543877524211225, 'cr1_G10_icc0.5': 0.8382086138012473, 'cr0_G30_icc0.0': 0.9485596707818851, 'cr1_G30_icc0.0': 0.9812686249467777, 'cr0_G30_icc0.2': 0.9267376448823972, 'cr1_G30_icc0.2': 0.9586941153955834, 'cr0_G30_icc0.5': 0.9252970710455054, 'cr1_G30_icc0.5': 0.9572038665987987}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6aa55bad-69ab-48f5-be43-f8eeb88433b7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}92{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"e4d44fc6a5673a713d97c29dc884532dca91db48fd98a7b5c478081c4715f6f2","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KE7Wbnpxegfbx55rLUKH3H","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'))\nprint(d['baseline_coverage_iid']); print(d['mean_coverage_small_G']); print(d['exact_rel_bias_var'])\"","description":"Print extra result values for report"}}]}}93{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"fec0db54-2392-4cb6-8217-8d19dee92e9a","timestamp":"2026-10-30T05:41:32.713Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"9b7a2364-6b11-45b2-9f8d-2ae595560460","keep":28,"tail":["e4d44fc6a5673a713d97c29dc884532dca91db48fd98a7b5c478081c4715f6f2","a831a6e2cc3a166808bed09f36495e6428db86e28ff11f2f3952af4e1a5337c3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d842c5d15c0ffe5805f194dde77c407c4846190c0f7c0604e7340bebf03cdaf7"}94{"parentUuid":"436d0250-44ec-4d10-85a7-9af06ca66e19","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPJC7fVg6XUg9ysz6R","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":878,"cache_read_input_tokens":32928,"output_tokens":498,"output_tokens_details":{"thinking_tokens":132},"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":878},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":778,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtPHtzyFdcUN3UwvybB","requestRef":"fec0db54-2392-4cb6-8217-8d19dee92e9a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"801b7638-5a0b-4933-a64b-702959bfe87a","timestamp":"2026-10-30T05:41:35.011Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}95{"parentUuid":"801b7638-5a0b-4933-a64b-702959bfe87a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPJC7fVg6XUg9ysz6R","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018GVThptK2RzJoahqtCE1zF","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    \"mc_se_rel_bias_var\": relbias_se,''','''    \"mc_se_rel_bias_var\": relbias_se,\n    \"mean_ci_halfwidth\": {f\"{r['estimator']}_G{r['G']}_icc{r['icc']:.1f}\": r[\"mean_ci_halfwidth\"] for r in rows},''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'));print({k:round(v,3) for k,v in d['mean_ci_halfwidth'].items() if 'G5' in k})\"","description":"Add half-widths to results.json"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":878,"cache_read_input_tokens":32928,"output_tokens":498,"output_tokens_details":{"thinking_tokens":132},"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":878},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtPHtzyFdcUN3UwvybB","requestRef":"fec0db54-2392-4cb6-8217-8d19dee92e9a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2bda219c-59f5-4d09-b644-62e86e55c6f6","timestamp":"2026-10-30T05:41:37.302Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}96{"parentUuid":"2bda219c-59f5-4d09-b644-62e86e55c6f6","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018GVThptK2RzJoahqtCE1zF","type":"tool_result","content":"{'cr0_G5_icc0.0': 0.129, 'cr1_G5_icc0.0': 0.205, 'wcb_G5_icc0.0': 0.244, 'cr0_G5_icc0.2': 0.336, 'cr1_G5_icc0.2': 0.533, 'wcb_G5_icc0.2': 0.881, 'cr0_G5_icc0.5': 0.51, 'cr1_G5_icc0.5': 0.807, 'wcb_G5_icc0.5': 1.419}","is_error":false}]},"uuid":"68848fe1-7571-4668-b672-dfc097d6df2a","timestamp":"2026-10-30T05:41:40.561Z","toolUseResult":{"stdout":"{'cr0_G5_icc0.0': 0.129, 'cr1_G5_icc0.0': 0.205, 'wcb_G5_icc0.0': 0.244, 'cr0_G5_icc0.2': 0.336, 'cr1_G5_icc0.2': 0.533, 'wcb_G5_icc0.2': 0.881, 'cr0_G5_icc0.5': 0.51, 'cr1_G5_icc0.5': 0.807, 'wcb_G5_icc0.5': 1.419}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2bda219c-59f5-4d09-b644-62e86e55c6f6","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}97{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"24d6551b0a489cda3e0a0f57e57858125bfbf655970457497255d3290d859739","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_018GVThptK2RzJoahqtCE1zF","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''    \"mc_se_rel_bias_var\": relbias_se,''','''    \"mc_se_rel_bias_var\": relbias_se,\n    \"mean_ci_halfwidth\": {f\"{r['estimator']}_G{r['G']}_icc{r['icc']:.1f}\": r[\"mean_ci_halfwidth\"] for r in rows},''')\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'));print({k:round(v,3) for k,v in d['mean_ci_halfwidth'].items() if 'G5' in k})\"","description":"Add half-widths to results.json"}}]}}98{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"8687c245-1738-4a1c-867d-3efda95e28e1","timestamp":"2026-10-30T05:41:40.566Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"fec0db54-2392-4cb6-8217-8d19dee92e9a","keep":30,"tail":["24d6551b0a489cda3e0a0f57e57858125bfbf655970457497255d3290d859739","5aff8c3e6e4d6c11a39fb29509fe9690ac8466b0f8a8aab8d698fb1f1666dccb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0d4d0cc44660b560a265a6649b30b80bf30a4663ad1becbc3933e00af5ba935b"}99{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"68848fe1-7571-4668-b672-dfc097d6df2a","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}100{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}101{"parentUuid":"68848fe1-7571-4668-b672-dfc097d6df2a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPskxxWDfvwPfMDoM4","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":683,"cache_read_input_tokens":33806,"output_tokens":5826,"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":683},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":566,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtPsUMrtm5pQQwvDWHJ","requestRef":"8687c245-1738-4a1c-867d-3efda95e28e1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0ee43cbf-14a0-4bf6-9141-5eb580bb6ba1","timestamp":"2026-10-30T05:41:42.619Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}102{"parentUuid":"0ee43cbf-14a0-4bf6-9141-5eb580bb6ba1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPskxxWDfvwPfMDoM4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01EtiXyPK4cnngx97ZQ8N7pj","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap intervals for a mean with few clusters\n\nTechnical note for T2-simulation. To reproduce everything: `~/wp29/venv/bin/python out/analysis.py` (about 2 s). It reads only `data/design.csv` and writes `out/results.json`, `out/table1.csv`, `out/figure1.png` and `out/exclusions.csv`. Below, keys in `code` refer to `out/results.json`. Pairs are named `<estimator>_G<G>_icc<icc>`.\n\n## Question\nWhen the data are grouped in only a few, unequal-sized clusters, how close to the nominal 95% do three standard cluster-robust intervals for a population mean μ actually cover? The three intervals are CR0 with a normal critical value, CR1 with a t(G−1) critical value, and the wild cluster bootstrap-t with Rademacher weights (WCB). Which (procedure, design) pairs fall below 90% coverage (the \"failure regimes\")? How biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ)?\n\n## Data and exclusions\nNo observed data are used. The only input is the design file `data/design.csv`: 9 rows (`n_input_rows`), one per cell of G ∈ {5, 10, 30} × ICC ∈ {0, 0.2, 0.5}. Each row gives unequal cluster sizes (8, 16, 32, 64 repeated, so N = 128, 264 and 864), R = 2000, B = 399 and one seed per cell. The SHA-256 hashes match the bundle manifest. In every row the number of listed cluster sizes equals G and their sum equals N; the script asserts both. Nothing was excluded (`out/exclusions.csv`: 9 → 9 cells). We simulated 9 × 2000 = 18 000 replications (`n_analysed`, `R`, `B`, `n_cells`). C1 used seed 20261101 (`random_seed`); the other cells use their own seeds from the design file. One issue is recorded in `data_issues`: with G = 5 the Rademacher weights have only 32 sign patterns, so the WCB reference distribution is coarse.\n\n## Method\n- **DGP.** y_ig = μ + u_g + e_ig, with u_g ~ N(0, ICC) and e_ig ~ N(0, 1−ICC), and μ = 0. Each cell uses `numpy.random.default_rng(seed)`. Draws are made in a fixed order: u (R×G), then e (R×N), then the Rademacher weights (R×B×G).\n- **Exact variance.** Var(ȳ) = [ICC Σ n_g² + (1−ICC) N] / N² (`exact_var_ybar`).\n- **CR0.** V̂ = Σ_g (Σ_i ê_ig)² / N², with interval ȳ ± 1.96 √V̂ (1.96 used literally, as specified).\n- **CR1.** V̂ = G/(G−1) · V̂_CR0, with interval ȳ ± t_{0.975, G−1} √V̂.\n- **WCB.** The bootstrap is vectorised. Write S_g for the cluster sums of the residuals. Then ȳ* − ȳ = D = Σ w_g S_g / N, and the bootstrap residuals have cluster sums w_g S_g − n_g D. These give V̂*_CR1 and |t*_b| = |D| / √V̂*_CR1. The critical value q is the 0.95 empirical quantile of the 399 values of |t*|, using the inverted-CDF definition: the ⌈0.95·399⌉ = 380th order statistic, the usual (B+1)(1−α) choice. The interval is ȳ ± q √V̂_CR1. A plain loop implementation gave the same q (max difference 4e−15; see `out/state/checks.md`).\n- **Evaluation.** Coverage is the share of the R intervals that contain μ (`coverage`), with MC SE √(p̂(1−p̂)/R) (`mc_se_coverage`). The variance relative bias is mean(V̂)/Var(ȳ) (`rel_bias_var`). A pair is a failure when coverage < 0.90 (`failure_cells`). It is \"consistent with nominal\" when |p̂ − 0.95| ≤ 2·SE (`nominal_cells`).\n- **Baseline (P2).** A naive i.i.d. interval, ȳ ± 1.96·s/√N, which ignores clustering, evaluated on the same replications (`baseline_coverage_iid`).\n- **Verification.** E[V̂_CR0] is a quadratic form, so it was computed analytically: tr(AΣA′)/N² with A = C − n1′/N (`exact_rel_bias_var`). This was compared with the Monte Carlo means (`z_rel_bias_mc_vs_exact`).\n\n## Results\nTable 1 (`out/table1.csv`) and Figure 1 (`out/figure1.png`) give all 27 pairs. Coverage (`coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive iid (baseline) |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.797 | 0.919 | 0.869 | 0.944 |\n| 5 | 0.2 | 0.720 | 0.882 | 0.847 | 0.465 |\n| 5 | 0.5 | 0.721 | 0.880 | 0.857 | 0.296 |\n| 10 | 0.0 | 0.884 | 0.940 | 0.926 | 0.950 |\n| 10 | 0.2 | 0.859 | 0.917 | 0.939 | 0.469 |\n| 10 | 0.5 | 0.853 | 0.917 | 0.937 | 0.315 |\n| 30 | 0.0 | 0.931 | 0.944 | 0.946 | 0.956 |\n| 30 | 0.2 | 0.924 | 0.940 | 0.952 | 0.482 |\n| 30 | 0.5 | 0.916 | 0.929 | 0.942 | 0.298 |\n\n1. **Failure regimes** (`failure_cells`, `n_failure_cells` = 11):\n   - CR0 fails in all six cells with G ≤ 10.\n   - CR1 fails at G = 5 when ICC = 0.2 or 0.5; at ICC = 0 its coverage is 0.919.\n   - WCB fails in all three G = 5 cells.\n   - No procedure fails at G = 30.\n2. **Consistent with nominal 0.95** (`nominal_cells`): only 6 of the 27 pairs. These are cr1_G10_icc0.0, cr1_G30_icc0.0, cr1_G30_icc0.2 and WCB in all three G = 30 cells. Every other pair under-covers by more than 2 MC SE. Even at G = 30, CR0 (0.916–0.931) and CR1 at ICC = 0.5 (0.929) are significantly below nominal.\n3. **Best procedure at G = 5** (`best_procedure_small_G` = cr1). Mean coverage over the three G = 5 cells is 0.893 for CR1, 0.857 for WCB and 0.746 for CR0 (`mean_coverage_small_G`). At G = 10 with ICC > 0, WCB covers better than CR1 (0.939/0.937 vs 0.917/0.917). At G = 30, WCB is the closest to nominal.\n4. **WCB at G = 5: wider but covers less.** WCB intervals are on average much wider than CR1 (mean half-width 0.88 vs 0.53 at ICC = 0.2; `mean_ci_halfwidth`), yet they cover less. The bootstrap critical value is very variable: when one large cluster dominates, |t*| takes few distinct values. The result is very wide intervals in some replications and too-narrow ones in others.\n5. **Variance bias** (`rel_bias_var`). Both sandwich estimators are biased downward in every cell, and the bias is worst with few clusters:\n   - CR0: E[V̂]/Var(ȳ) ≈ 0.51–0.65 at G = 5, 0.76–0.85 at G = 10 and 0.92–0.94 at G = 30.\n   - CR1: 0.63–0.82, 0.84–0.94 and 0.95–0.97 at the same G.\n   \n   The downward bias comes from estimating μ by ȳ, which removes variability that a single dominant cluster carries. It is larger when ICC > 0 than when ICC = 0, because the large clusters then contribute more to Var(ȳ). The analytic values (`exact_rel_bias_var`) agree.\n6. **Baseline.** Ignoring clustering (`baseline_coverage_iid`) is fine at ICC = 0 (0.94–0.96) but disastrous at ICC > 0 (0.30–0.48), at every G. All three cluster-robust procedures are a large improvement, but none reaches nominal coverage reliably with 5 clusters.\n\n## Uncertainty\n- **Coverage.** With R = 2000, the MC SE of a coverage estimate is about 0.0049 near 0.95 and at most 0.010 (CR0 at G = 5) (`mc_se_coverage`). So ±2 SE ≈ ±0.01–0.02.\n- **Classifications.** Classifying a pair as a failure is robust when its coverage is far from 0.90. The cases nearest the threshold are:\n  - cr1_G5_icc0.2 (0.8815, SE 0.0072) and cr1_G5_icc0.5 (0.8795, SE 0.0073): about 2.6–2.8 SE below 0.90.\n  - cr0_G10_icc0.0 (0.8835, SE 0.0072): about 2.3 SE below.\n  - cr1_G5_icc0.0 (0.919, SE 0.0061): about 3.1 SE above.\n  \n  Other seeds could plausibly move these by a few hundredths. The \"nominal\" set rests on a 2-SE rule applied to 27 pairs, so a borderline pair could be misclassified by chance (multiple comparisons; no correction was applied, as the task specifies the rule).\n- **Variance bias.** The MC SE of the relative bias is 0.007–0.016 (`mc_se_rel_bias_var`). The Monte Carlo means agree with the analytic expectations (`exact_rel_bias_var`): z-scores range from −2.0 to 1.36 over the 9 independent cells (`z_rel_bias_mc_vs_exact`). This is consistent with pure MC noise and confirms the implementation.\n- **Bootstrap error.** The WCB coverage also includes bootstrap randomness (B = 399), which is part of the procedure as specified. It is absorbed into the binomial MC SE.\n- **Comparisons between procedures.** All procedures in a cell use the same replications, so their differences are positively correlated. The marginal SEs are therefore conservative for those differences. We did not compute paired SEs separately. The G = 5 gap between CR1 and WCB (0.036 on average) is several times the marginal SE of each mean (≈0.004).\n\n## Limitations and open issues\n- **Distribution.** Only Gaussian random intercepts and Gaussian errors. Skewed or heavy-tailed u_g or e_ig, which usually hurt few-cluster inference more, are not covered.\n- **Heterogeneity.** Within-cluster variance and ICC are the same in every cluster. Cluster sizes follow one fixed unbalanced pattern (8/16/32/64) and are not random or informative about the outcome. Balanced designs, or designs even more dominated by one cluster, may behave differently. At G = 5, half of the sample is in one cluster, which drives much of the small-G behaviour.\n- **Regressors.** The estimand is a simple mean, so there are no regressors and no leverage from covariates. Results for regression coefficients, fixed effects, or treatment indicators that vary only at the cluster level can differ substantially.\n- **Other methods and weights.** We did not study:\n  - CR2/CR3 (bias-reduced linearisation) or Bell–McCaffrey/Satterthwaite degrees of freedom;\n  - the restricted (null-imposed) WCB or the WCB p-value inversion;\n  - Webb six-point or Mammen weights;\n  - full enumeration of the 32 Rademacher patterns at G = 5;\n  - the equal-tailed rather than symmetric bootstrap-t.\n  \n  The WCB results apply only to the unrestricted, symmetric, Rademacher version with B = 399.\n- **Specification choices.**\n  - The \"0.95 empirical quantile\" was implemented as the inverted-CDF (380th of 399) order statistic. Interpolated quantile definitions would change q slightly.\n  - CR0 uses the literal 1.96 as specified.\n- **Design coverage.** Only the 9 cells and R = 2000 required by the task were run. No other G values or ICC values were explored.\n- **Feasibility.** The task was completed as specified (`feasibility` = \"complete\").\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G<=10 cells, CR1 at G=5 with ICC 0.2 and 0.5, WCB at all G=5 cells; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5 (icc0.2/0.5) and cr0_G10_icc0.0 lie only ~2.3-2.8 MC SE below 0.90.\"},\n {\"id\":\"C2\",\"text\":\"Only 6 of 27 pairs are consistent with nominal 95% coverage (CR1 at G10/ICC0, G30/ICC0, G30/ICC0.2; WCB at all G=30 cells).\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE rule applied to 27 pairs without multiplicity correction.\"},\n {\"id\":\"C3\",\"text\":\"With G=5, CR1 has the highest average coverage (0.893) ahead of WCB (0.857) and CR0 (0.746).\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_small_G\"],\"status\":\"supported\",\"caveat\":\"Specific to unrestricted Rademacher WCB with symmetric bootstrap-t and B=399.\"},\n {\"id\":\"C4\",\"text\":\"At G=10 with ICC>0 and at G=30, WCB is closer to nominal than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences at G=30 are of the order of 1-3 MC SE; paired SEs not computed.\"},\n {\"id\":\"C5\",\"text\":\"CR0 and CR1 variance estimators are biased downward in every cell, strongly at G=5 (CR0 0.51-0.65, CR1 0.63-0.82), and Monte Carlo bias estimates agree with analytic expectations.\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\",\"exact_rel_bias_var\",\"z_rel_bias_mc_vs_exact\"],\"status\":\"supported\",\"caveat\":\"Bias depends on the unbalanced cluster-size pattern.\"},\n {\"id\":\"C6\",\"text\":\"At G=5 WCB intervals are wider on average than CR1 intervals yet cover less.\",\"results_keys\":[\"mean_ci_halfwidth\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Explanation (variable, discrete bootstrap critical value) is interpretive, not separately tested.\"},\n {\"id\":\"C7\",\"text\":\"The naive i.i.d. interval covers ~0.95 at ICC=0 but only 0.30-0.48 when ICC>0.\",\"results_keys\":[\"baseline_coverage_iid\"],\"status\":\"supported\",\"caveat\":\"Baseline not required by the task; included for context.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'));c=d['coverage'];s=d['mc_se_coverage']\nfor k in ['cr1_G5_icc0.2','cr1_G5_icc0.5','cr0_G10_icc0.0','cr1_G5_icc0.0']: print(k,(c[k]-0.9)/s[k])\nprint(min(s.values()),max(s.values()))\"","description":"Write report and claims; verify cited SE distances"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":683,"cache_read_input_tokens":33806,"output_tokens":5826,"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":683},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtPsUMrtm5pQQwvDWHJ","requestRef":"8687c245-1738-4a1c-867d-3efda95e28e1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5cea0d83-d80a-47b1-9bd8-11a3d0e57e6b","timestamp":"2026-10-30T05:42:30.420Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}103{"parentUuid":"5cea0d83-d80a-47b1-9bd8-11a3d0e57e6b","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01EtiXyPK4cnngx97ZQ8N7pj","type":"tool_result","content":"cr1_G5_icc0.2 -2.559861052493601\ncr1_G5_icc0.5 -2.816160570266047\ncr0_G10_icc0.0 -2.3000257724717574\ncr1_G5_icc0.0 3.114356564106536\n0.004803527349771207 0.01004539073406306","is_error":false}]},"uuid":"50445437-e8e3-46ce-8a55-1fe1fc01b475","timestamp":"2026-10-30T05:42:30.491Z","toolUseResult":{"stdout":"cr1_G5_icc0.2 -2.559861052493601\ncr1_G5_icc0.5 -2.816160570266047\ncr0_G10_icc0.0 -2.3000257724717574\ncr1_G5_icc0.0 3.114356564106536\n0.004803527349771207 0.01004539073406306","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"5cea0d83-d80a-47b1-9bd8-11a3d0e57e6b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}104{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"376d82f58b92dc0f513f280c56d8c4ce4d5fd37fe3e197ff42004fa2f59c47df","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01EtiXyPK4cnngx97ZQ8N7pj","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap intervals for a mean with few clusters\n\nTechnical note for T2-simulation. To reproduce everything: `~/wp29/venv/bin/python out/analysis.py` (about 2 s). It reads only `data/design.csv` and writes `out/results.json`, `out/table1.csv`, `out/figure1.png` and `out/exclusions.csv`. Below, keys in `code` refer to `out/results.json`. Pairs are named `<estimator>_G<G>_icc<icc>`.\n\n## Question\nWhen the data are grouped in only a few, unequal-sized clusters, how close to the nominal 95% do three standard cluster-robust intervals for a population mean μ actually cover? The three intervals are CR0 with a normal critical value, CR1 with a t(G−1) critical value, and the wild cluster bootstrap-t with Rademacher weights (WCB). Which (procedure, design) pairs fall below 90% coverage (the \"failure regimes\")? How biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ)?\n\n## Data and exclusions\nNo observed data are used. The only input is the design file `data/design.csv`: 9 rows (`n_input_rows`), one per cell of G ∈ {5, 10, 30} × ICC ∈ {0, 0.2, 0.5}. Each row gives unequal cluster sizes (8, 16, 32, 64 repeated, so N = 128, 264 and 864), R = 2000, B = 399 and one seed per cell. The SHA-256 hashes match the bundle manifest. In every row the number of listed cluster sizes equals G and their sum equals N; the script asserts both. Nothing was excluded (`out/exclusions.csv`: 9 → 9 cells). We simulated 9 × 2000 = 18 000 replications (`n_analysed`, `R`, `B`, `n_cells`). C1 used seed 20261101 (`random_seed`); the other cells use their own seeds from the design file. One issue is recorded in `data_issues`: with G = 5 the Rademacher weights have only 32 sign patterns, so the WCB reference distribution is coarse.\n\n## Method\n- **DGP.** y_ig = μ + u_g + e_ig, with u_g ~ N(0, ICC) and e_ig ~ N(0, 1−ICC), and μ = 0. Each cell uses `numpy.random.default_rng(seed)`. Draws are made in a fixed order: u (R×G), then e (R×N), then the Rademacher weights (R×B×G).\n- **Exact variance.** Var(ȳ) = [ICC Σ n_g² + (1−ICC) N] / N² (`exact_var_ybar`).\n- **CR0.** V̂ = Σ_g (Σ_i ê_ig)² / N², with interval ȳ ± 1.96 √V̂ (1.96 used literally, as specified).\n- **CR1.** V̂ = G/(G−1) · V̂_CR0, with interval ȳ ± t_{0.975, G−1} √V̂.\n- **WCB.** The bootstrap is vectorised. Write S_g for the cluster sums of the residuals. Then ȳ* − ȳ = D = Σ w_g S_g / N, and the bootstrap residuals have cluster sums w_g S_g − n_g D. These give V̂*_CR1 and |t*_b| = |D| / √V̂*_CR1. The critical value q is the 0.95 empirical quantile of the 399 values of |t*|, using the inverted-CDF definition: the ⌈0.95·399⌉ = 380th order statistic, the usual (B+1)(1−α) choice. The interval is ȳ ± q √V̂_CR1. A plain loop implementation gave the same q (max difference 4e−15; see `out/state/checks.md`).\n- **Evaluation.** Coverage is the share of the R intervals that contain μ (`coverage`), with MC SE √(p̂(1−p̂)/R) (`mc_se_coverage`). The variance relative bias is mean(V̂)/Var(ȳ) (`rel_bias_var`). A pair is a failure when coverage < 0.90 (`failure_cells`). It is \"consistent with nominal\" when |p̂ − 0.95| ≤ 2·SE (`nominal_cells`).\n- **Baseline (P2).** A naive i.i.d. interval, ȳ ± 1.96·s/√N, which ignores clustering, evaluated on the same replications (`baseline_coverage_iid`).\n- **Verification.** E[V̂_CR0] is a quadratic form, so it was computed analytically: tr(AΣA′)/N² with A = C − n1′/N (`exact_rel_bias_var`). This was compared with the Monte Carlo means (`z_rel_bias_mc_vs_exact`).\n\n## Results\nTable 1 (`out/table1.csv`) and Figure 1 (`out/figure1.png`) give all 27 pairs. Coverage (`coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive iid (baseline) |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.797 | 0.919 | 0.869 | 0.944 |\n| 5 | 0.2 | 0.720 | 0.882 | 0.847 | 0.465 |\n| 5 | 0.5 | 0.721 | 0.880 | 0.857 | 0.296 |\n| 10 | 0.0 | 0.884 | 0.940 | 0.926 | 0.950 |\n| 10 | 0.2 | 0.859 | 0.917 | 0.939 | 0.469 |\n| 10 | 0.5 | 0.853 | 0.917 | 0.937 | 0.315 |\n| 30 | 0.0 | 0.931 | 0.944 | 0.946 | 0.956 |\n| 30 | 0.2 | 0.924 | 0.940 | 0.952 | 0.482 |\n| 30 | 0.5 | 0.916 | 0.929 | 0.942 | 0.298 |\n\n1. **Failure regimes** (`failure_cells`, `n_failure_cells` = 11):\n   - CR0 fails in all six cells with G ≤ 10.\n   - CR1 fails at G = 5 when ICC = 0.2 or 0.5; at ICC = 0 its coverage is 0.919.\n   - WCB fails in all three G = 5 cells.\n   - No procedure fails at G = 30.\n2. **Consistent with nominal 0.95** (`nominal_cells`): only 6 of the 27 pairs. These are cr1_G10_icc0.0, cr1_G30_icc0.0, cr1_G30_icc0.2 and WCB in all three G = 30 cells. Every other pair under-covers by more than 2 MC SE. Even at G = 30, CR0 (0.916–0.931) and CR1 at ICC = 0.5 (0.929) are significantly below nominal.\n3. **Best procedure at G = 5** (`best_procedure_small_G` = cr1). Mean coverage over the three G = 5 cells is 0.893 for CR1, 0.857 for WCB and 0.746 for CR0 (`mean_coverage_small_G`). At G = 10 with ICC > 0, WCB covers better than CR1 (0.939/0.937 vs 0.917/0.917). At G = 30, WCB is the closest to nominal.\n4. **WCB at G = 5: wider but covers less.** WCB intervals are on average much wider than CR1 (mean half-width 0.88 vs 0.53 at ICC = 0.2; `mean_ci_halfwidth`), yet they cover less. The bootstrap critical value is very variable: when one large cluster dominates, |t*| takes few distinct values. The result is very wide intervals in some replications and too-narrow ones in others.\n5. **Variance bias** (`rel_bias_var`). Both sandwich estimators are biased downward in every cell, and the bias is worst with few clusters:\n   - CR0: E[V̂]/Var(ȳ) ≈ 0.51–0.65 at G = 5, 0.76–0.85 at G = 10 and 0.92–0.94 at G = 30.\n   - CR1: 0.63–0.82, 0.84–0.94 and 0.95–0.97 at the same G.\n   \n   The downward bias comes from estimating μ by ȳ, which removes variability that a single dominant cluster carries. It is larger when ICC > 0 than when ICC = 0, because the large clusters then contribute more to Var(ȳ). The analytic values (`exact_rel_bias_var`) agree.\n6. **Baseline.** Ignoring clustering (`baseline_coverage_iid`) is fine at ICC = 0 (0.94–0.96) but disastrous at ICC > 0 (0.30–0.48), at every G. All three cluster-robust procedures are a large improvement, but none reaches nominal coverage reliably with 5 clusters.\n\n## Uncertainty\n- **Coverage.** With R = 2000, the MC SE of a coverage estimate is about 0.0049 near 0.95 and at most 0.010 (CR0 at G = 5) (`mc_se_coverage`). So ±2 SE ≈ ±0.01–0.02.\n- **Classifications.** Classifying a pair as a failure is robust when its coverage is far from 0.90. The cases nearest the threshold are:\n  - cr1_G5_icc0.2 (0.8815, SE 0.0072) and cr1_G5_icc0.5 (0.8795, SE 0.0073): about 2.6–2.8 SE below 0.90.\n  - cr0_G10_icc0.0 (0.8835, SE 0.0072): about 2.3 SE below.\n  - cr1_G5_icc0.0 (0.919, SE 0.0061): about 3.1 SE above.\n  \n  Other seeds could plausibly move these by a few hundredths. The \"nominal\" set rests on a 2-SE rule applied to 27 pairs, so a borderline pair could be misclassified by chance (multiple comparisons; no correction was applied, as the task specifies the rule).\n- **Variance bias.** The MC SE of the relative bias is 0.007–0.016 (`mc_se_rel_bias_var`). The Monte Carlo means agree with the analytic expectations (`exact_rel_bias_var`): z-scores range from −2.0 to 1.36 over the 9 independent cells (`z_rel_bias_mc_vs_exact`). This is consistent with pure MC noise and confirms the implementation.\n- **Bootstrap error.** The WCB coverage also includes bootstrap randomness (B = 399), which is part of the procedure as specified. It is absorbed into the binomial MC SE.\n- **Comparisons between procedures.** All procedures in a cell use the same replications, so their differences are positively correlated. The marginal SEs are therefore conservative for those differences. We did not compute paired SEs separately. The G = 5 gap between CR1 and WCB (0.036 on average) is several times the marginal SE of each mean (≈0.004).\n\n## Limitations and open issues\n- **Distribution.** Only Gaussian random intercepts and Gaussian errors. Skewed or heavy-tailed u_g or e_ig, which usually hurt few-cluster inference more, are not covered.\n- **Heterogeneity.** Within-cluster variance and ICC are the same in every cluster. Cluster sizes follow one fixed unbalanced pattern (8/16/32/64) and are not random or informative about the outcome. Balanced designs, or designs even more dominated by one cluster, may behave differently. At G = 5, half of the sample is in one cluster, which drives much of the small-G behaviour.\n- **Regressors.** The estimand is a simple mean, so there are no regressors and no leverage from covariates. Results for regression coefficients, fixed effects, or treatment indicators that vary only at the cluster level can differ substantially.\n- **Other methods and weights.** We did not study:\n  - CR2/CR3 (bias-reduced linearisation) or Bell–McCaffrey/Satterthwaite degrees of freedom;\n  - the restricted (null-imposed) WCB or the WCB p-value inversion;\n  - Webb six-point or Mammen weights;\n  - full enumeration of the 32 Rademacher patterns at G = 5;\n  - the equal-tailed rather than symmetric bootstrap-t.\n  \n  The WCB results apply only to the unrestricted, symmetric, Rademacher version with B = 399.\n- **Specification choices.**\n  - The \"0.95 empirical quantile\" was implemented as the inverted-CDF (380th of 399) order statistic. Interpolated quantile definitions would change q slightly.\n  - CR0 uses the literal 1.96 as specified.\n- **Design coverage.** Only the 9 cells and R = 2000 required by the task were run. No other G values or ICC values were explored.\n- **Feasibility.** The task was completed as specified (`feasibility` = \"complete\").\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G<=10 cells, CR1 at G=5 with ICC 0.2 and 0.5, WCB at all G=5 cells; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5 (icc0.2/0.5) and cr0_G10_icc0.0 lie only ~2.3-2.8 MC SE below 0.90.\"},\n {\"id\":\"C2\",\"text\":\"Only 6 of 27 pairs are consistent with nominal 95% coverage (CR1 at G10/ICC0, G30/ICC0, G30/ICC0.2; WCB at all G=30 cells).\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE rule applied to 27 pairs without multiplicity correction.\"},\n {\"id\":\"C3\",\"text\":\"With G=5, CR1 has the highest average coverage (0.893) ahead of WCB (0.857) and CR0 (0.746).\",\"results_keys\":[\"best_procedure_small_G\",\"mean_coverage_small_G\"],\"status\":\"supported\",\"caveat\":\"Specific to unrestricted Rademacher WCB with symmetric bootstrap-t and B=399.\"},\n {\"id\":\"C4\",\"text\":\"At G=10 with ICC>0 and at G=30, WCB is closer to nominal than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences at G=30 are of the order of 1-3 MC SE; paired SEs not computed.\"},\n {\"id\":\"C5\",\"text\":\"CR0 and CR1 variance estimators are biased downward in every cell, strongly at G=5 (CR0 0.51-0.65, CR1 0.63-0.82), and Monte Carlo bias estimates agree with analytic expectations.\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\",\"exact_rel_bias_var\",\"z_rel_bias_mc_vs_exact\"],\"status\":\"supported\",\"caveat\":\"Bias depends on the unbalanced cluster-size pattern.\"},\n {\"id\":\"C6\",\"text\":\"At G=5 WCB intervals are wider on average than CR1 intervals yet cover less.\",\"results_keys\":[\"mean_ci_halfwidth\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Explanation (variable, discrete bootstrap critical value) is interpretive, not separately tested.\"},\n {\"id\":\"C7\",\"text\":\"The naive i.i.d. interval covers ~0.95 at ICC=0 but only 0.30-0.48 when ICC>0.\",\"results_keys\":[\"baseline_coverage_iid\"],\"status\":\"supported\",\"caveat\":\"Baseline not required by the task; included for context.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;d=json.load(open('out/results.json'));c=d['coverage'];s=d['mc_se_coverage']\nfor k in ['cr1_G5_icc0.2','cr1_G5_icc0.5','cr0_G10_icc0.0','cr1_G5_icc0.0']: print(k,(c[k]-0.9)/s[k])\nprint(min(s.values()),max(s.values()))\"","description":"Write report and claims; verify cited SE distances"}}]}}105{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"927c3333-40f6-4c02-8228-099eccb67653","timestamp":"2026-10-30T05:42:30.495Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"8687c245-1738-4a1c-867d-3efda95e28e1","keep":32,"tail":["376d82f58b92dc0f513f280c56d8c4ce4d5fd37fe3e197ff42004fa2f59c47df","56de737b06ae33228f17bb6542125a4e133a2b7ae605631fa4c080a05ee860f2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a1c926fa26dee36d7c91ee31f944694a55968cab67a2c631c3d884d20531cefd"}106{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"50445437-e8e3-46ce-8a55-1fe1fc01b475","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}107{"type":"atis-latch","atis":"","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}108{"parentUuid":"50445437-e8e3-46ce-8a55-1fe1fc01b475","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtTZFrDEg7jcGVLT8gE","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":5936,"cache_read_input_tokens":34489,"output_tokens":483,"output_tokens_details":{"thinking_tokens":46},"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":5936},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":403,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtTYxyjzWEN6oLaCaVB","requestRef":"927c3333-40f6-4c02-8228-099eccb67653","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c13b4fb3-6f73-4389-ad5c-0b2de90910ba","timestamp":"2026-10-30T05:42:32.205Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}109{"parentUuid":"c13b4fb3-6f73-4389-ad5c-0b2de90910ba","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtTZFrDEg7jcGVLT8gE","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01EiqKGvvCBGisEdSy9yvZGm","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json\",\"14 consistency checks PASS (checks.md)\",\"gate run 1 receipt out/state/gate_receipts/20261030T054129.719612Z.json: all contract/reproducibility checks ok; only report/claims/phase-ledger failures expected before P5\"],\"notes\":\"results.json later extended with mean_ci_halfwidth key (additive; re-verified by gate run 2)\"}\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, keys cited\",\"claims.json 7 claims all referencing existing keys\",\"gate run 2 (see log.md for receipt)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Update ledger and run gate again"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5936,"cache_read_input_tokens":34489,"output_tokens":483,"output_tokens_details":{"thinking_tokens":46},"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":5936},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtTYxyjzWEN6oLaCaVB","requestRef":"927c3333-40f6-4c02-8228-099eccb67653","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0139f45d-1cac-46d8-86a4-eae9cbc8a067","timestamp":"2026-10-30T05:42:35.254Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}110{"parentUuid":"0139f45d-1cac-46d8-86a4-eae9cbc8a067","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01EiqKGvvCBGisEdSy9yvZGm","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0021/out/state/gate_receipts/20261030T054237.397407Z.json","is_error":false}]},"uuid":"e1bf4ab7-f608-4fb2-aa22-f2a1424236a2","timestamp":"2026-10-30T05:42:37.404Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 34 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0021/out/state/gate_receipts/20261030T054237.397407Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"0139f45d-1cac-46d8-86a4-eae9cbc8a067","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}111{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"093243ee6aaebaba469fc3c45cab5ed5e16482ef53a12a92d08f2cb4b6bd1f04","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01EiqKGvvCBGisEdSy9yvZGm","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run byte-identical results.json\",\"14 consistency checks PASS (checks.md)\",\"gate run 1 receipt out/state/gate_receipts/20261030T054129.719612Z.json: all contract/reproducibility checks ok; only report/claims/phase-ledger failures expected before P5\"],\"notes\":\"results.json later extended with mean_ci_halfwidth key (additive; re-verified by gate run 2)\"}\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, keys cited\",\"claims.json 7 claims all referencing existing keys\",\"gate run 2 (see log.md for receipt)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | grep -v \"\\[ok\\]\"","description":"Update ledger and run gate again"}}]}}112{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"0ad54763-353b-4b34-9424-a0535764cd50","timestamp":"2026-10-30T05:42:37.408Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"927c3333-40f6-4c02-8228-099eccb67653","keep":34,"tail":["093243ee6aaebaba469fc3c45cab5ed5e16482ef53a12a92d08f2cb4b6bd1f04","62f979706f105affc69a7d4c2dfc982537f5808b2915bc222879d2294ccd99bc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b71f3e779bd00618835b4c7ab4450deae88017040a66b90c61c9508803cf4de9"}113{"parentUuid":"e1bf4ab7-f608-4fb2-aa22-f2a1424236a2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtU4qqXLj3GqUqyct6t","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01TzR3Wm13Gv6bh84mpSW46m","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'][2]=\"gate run 2 PASSED (0/34 failed): out/state/gate_receipts/20261030T054237.397407Z.json\"\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P4 passed (gate run 1 receipt 20261030T054129.719612Z). P5 passed; gate run 2 PASSED (20261030T054237.397407Z).\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -2","description":"Record receipt and confirm final gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":578,"cache_read_input_tokens":40425,"output_tokens":333,"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":578},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtU4YUWyFMx3QTR4JKS","requestRef":"0ad54763-353b-4b34-9424-a0535764cd50","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d772a880-40ab-4fca-be2b-fc6975ba04e9","timestamp":"2026-10-30T05:42:40.752Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}114{"parentUuid":"d772a880-40ab-4fca-be2b-fc6975ba04e9","isSidechain":false,"promptId":"25aa2f58-654c-45be-870b-28c4bf96be0c","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01TzR3Wm13Gv6bh84mpSW46m","type":"tool_result","content":"  [ok] reproducibility: regenerated in 1.8s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0021/out/state/gate_receipts/20261030T054242.678639Z.json","is_error":false}]},"uuid":"364ffdcd-3631-4a3c-a31b-8f817aef1606","timestamp":"2026-10-30T05:42:42.686Z","toolUseResult":{"stdout":"  [ok] reproducibility: regenerated in 1.8s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RT0021/out/state/gate_receipts/20261030T054242.678639Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d772a880-40ab-4fca-be2b-fc6975ba04e9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}115{"type":"api-request-blob","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","hash":"fc9be89da43e44a3a1ac54fb6a366374d7772aaca764f988734d4271712ce99f","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01TzR3Wm13Gv6bh84mpSW46m","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'][2]=\"gate run 2 PASSED (0/34 failed): out/state/gate_receipts/20261030T054237.397407Z.json\"\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30: P4 passed (gate run 1 receipt 20261030T054129.719612Z). P5 passed; gate run 2 PASSED (20261030T054237.397407Z).\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . 2>&1 | tail -2","description":"Record receipt and confirm final gate"}}]}}116{"type":"api-request","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","id":"77bdce81-0a28-4c05-9408-c367a8737812","timestamp":"2026-10-30T05:42:42.689Z","version":"2.1.314","querySource":"sdk","shapeHash":"40d439ad0217171b1ae1cc74a72a28ef98144eed6705724c0338d8d3733b0db9","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":"0ad54763-353b-4b34-9424-a0535764cd50","keep":36,"tail":["fc9be89da43e44a3a1ac54fb6a366374d7772aaca764f988734d4271712ce99f","154dd5b8ce8ac9486c2ced116390078f4a2f477592a7812d8f1f922ab5c0dffd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",37,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"46533d7234bfbcc58f00b7ef9fc3c64b8676b38d1cd8ce02c4a3a68710aa526b"}117{"parentUuid":"364ffdcd-3631-4a3c-a31b-8f817aef1606","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtUTNf4K5AfSahXMcf3","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":422,"cache_read_input_tokens":41003,"output_tokens":1513,"output_tokens_details":{"thinking_tokens":21},"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":422},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6827,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtUT5JdkYVxUGV3ZASY","requestRef":"77bdce81-0a28-4c05-9408-c367a8737812","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ee20a112-5db7-4990-9e9f-e2cc31685b14","timestamp":"2026-10-30T05:42:51.031Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}118{"parentUuid":"ee20a112-5db7-4990-9e9f-e2cc31685b14","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtUTNf4K5AfSahXMcf3","type":"message","role":"assistant","content":[{"type":"text","text":"I ran the full simulation as specified: 9 cells × 2000 replications, with 399 bootstrap draws per replication and each cell's seed from the design file. All six required files are in `out/`, and the final gate run passes all 34 checks. Re-running `out/analysis.py` from scratch reproduces `results.json` exactly, in about 2 seconds.\n\n**Main findings (coverage of the nominal 95% interval):**\n- **Failure regimes:** 11 of the 27 (procedure, cell) pairs cover less than 90%:\n  - CR0 in all six cells with 10 or fewer clusters.\n  - CR1 at 5 clusters when ICC is 0.2 or 0.5 (0.882 and 0.880); at ICC 0 it reaches 0.919.\n  - The wild cluster bootstrap fails in all three 5-cluster cells (0.85–0.87).\n  - Nothing fails at 30 clusters.\n- **Close to nominal:** only 6 pairs are within 2 Monte Carlo standard errors of 0.95: CR1 at (10 clusters, ICC 0), (30, ICC 0) and (30, ICC 0.2), and the bootstrap in all three 30-cluster cells. CR0 is still below nominal even at 30 clusters (0.916–0.931).\n- **Best procedure with 5 clusters:** CR1, averaging 0.893, ahead of the bootstrap (0.857) and CR0 (0.746). With 10 clusters and ICC above 0, and at 30 clusters, the bootstrap comes closer to nominal than CR1.\n- **Bootstrap at 5 clusters:** its intervals are wider on average than CR1's (half-width 0.88 vs 0.53 at ICC 0.2) yet cover less. My explanation is that its critical value varies a lot from sample to sample; that is an interpretation I did not test separately.\n- **Variance bias:** both sandwich estimators underestimate the true variance in every cell. The ratio of expected estimate to true variance is 0.51–0.65 for CR0 and 0.63–0.82 for CR1 at 5 clusters, rising to 0.92–0.97 at 30 clusters. I also calculated these expectations exactly; the simulated values agree within MC noise (z-scores from −2.0 to 1.4).\n- **Simple comparison:** an interval that ignores clustering covers about 0.95 when ICC is 0 but only 0.30–0.48 otherwise.\n\nMonte Carlo standard errors are 0.005–0.010 for coverage and 0.007–0.016 for the variance ratios. As a check, a plain loop version of the bootstrap gave the same critical values as the fast version in the script.\n\n**Choices and limitations:**\n- **Critical values:** CR0 uses 1.96 exactly as the task states. For the bootstrap, I took the \"0.95 empirical quantile\" to be the 380th of the 399 sorted values; a different quantile definition would shift it slightly.\n- **Few sign patterns at 5 clusters:** with 5 clusters the ±1 bootstrap weights have only 32 possible combinations, so the bootstrap distribution is coarse. I kept the specified 399 random draws rather than listing all 32, and recorded this under `data_issues`.\n- **Borderline results:** three failure calls sit only about 2.3–2.8 standard errors below 0.90 (CR1 at 5 clusters with ICC 0.2 and 0.5, and CR0 at 10 clusters with ICC 0), so other seeds could move them. The \"close to nominal\" list uses the task's 2-standard-error rule across 27 pairs with no correction for multiple comparisons.\n- **What the design does not cover:** only normal distributions, one fixed pattern of unequal cluster sizes, a plain mean with no regressors, and the unrestricted bootstrap with ±1 weights. Other variance corrections (such as CR2), the restricted bootstrap and other weight schemes were not studied.\n- **Extra keys:** besides the required ones, `results.json` holds the clustering-ignoring comparison, the exact variance ratios, and their standard errors.\n\nFiles are in `out/`:\n- `analysis.py`\n- `results.json`\n- `table1.csv`\n- `figure1.png`\n- `report.md`\n- `claims.json`\n- `exclusions.csv`\n- `state/` (contract, data audit, checks, phase ledger, log, gate receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":422,"cache_read_input_tokens":41003,"output_tokens":1513,"output_tokens_details":{"thinking_tokens":21},"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":422},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtUT5JdkYVxUGV3ZASY","requestRef":"77bdce81-0a28-4c05-9408-c367a8737812","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c909561f-81a2-44a8-958a-0393135a22dd","timestamp":"2026-10-30T05:42:56.547Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0021","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","version":"2.1.314","gitBranch":"HEAD"}119{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"c909561f-81a2-44a8-958a-0393135a22dd","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc"}120{"type":"cost-state","sessionId":"27b4a706-c176-492b-b31a-0d828e3835fc","totalCostUSD":0.8279705999999999,"totalAPIDuration":233963,"totalAPIDurationWithoutRetries":233957,"totalToolDuration":21378,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":255554,"startTime":1793338721001,"modelUsage":{"claude-opus-5-5":{"inputTokens":40,"outputTokens":27072,"thinkingTokens":3086,"cacheReadInputTokens":433828,"cacheCreationInputTokens":39921,"cacheCreationEphemeral5mInputTokens":39921,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.8279705999999999}},"hasUnknownModelCost":false}121