1{"type":"atis-latch","atis":"","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:41:22.861Z","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","content":"Review"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:41:22.865Z","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}4{"parentUuid":null,"isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":"Review"},"uuid":"5b108359-4520-457f-b68b-5c9c68415920","timestamp":"2026-10-30T05:41:22.869Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","timestamp":"2026-10-30T05:41:22.879Z","version":"2.1.314","shape":{"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude, running within the Claude Agent SDK."},{"type":"text","text":"CWD: /Users/simon-pierreboucher/wp29/runs/RT0020\nDate: 2026-10-30\n\nYou are an independent scientific reviewer. In the current working directory, `TASK.md` describes a bounded scientific task and the directory `out/` contains the deliverables submitted by another assistant (you have not seen how they were produced and you must not look for their working transcript). There is no network access. Use `~/wp29/venv/bin/python` if you need to re-run or test code. Do not modify any file under `out/` except that you must create `out/review/review.json`.\n\nReview the deliverables against `TASK.md` only. Specifically check:\n1. Does `out/results.json` contain every required key with legitimately computed values? Re-run `out/analysis.py` in a scratch copy if needed and compare.\n2. Are the information-availability rules of `TASK.md` respected by the code (for example no use of future information, no use of forbidden inputs)? Read the code to verify; do not trust the report.\n3. Are the central claims in `out/report.md` and `out/claims.json` supported by the numbers in `out/results.json`, with appropriate uncertainty and caveats? Flag any claim that is stronger than the evidence.\n4. Are counts, exclusions, units, signs and magnitudes internally consistent? Are baseline comparisons present when the task requires them?\n5. Are limitations stated honestly? Is anything declared complete that is not?\n\nYou have no reference answers; do not guess what the \"right\" number is. Report only issues you can justify from the files. Write `out/review/review.json` as {\"verdict\": \"accept\"|\"revise\", \"issues\": [{\"id\": \"R1\", \"severity\": \"critical\"|\"major\"|\"minor\", \"location\": \"<file or key>\", \"issue\": \"...\", \"suggested_fix\": \"...\"}], \"summary\": \"...\"}. Use \"revise\" if there is at least one critical or major issue. Be concise and specific. End with a one-paragraph plain-text summary.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"6d532d07-7480-4d23-9332-bae1e747067f","timestamp":"2026-10-30T05:41:22.879Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["99833769e4310fc124186eb9e97416cea64dc8ececb015cbe8928bf0c2bd9984","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"52640a31fdb98b1e83bd7031d0a90eecb89bfc45a96e202f786eafe22b24fb76"}8{"parentUuid":"5b108359-4520-457f-b68b-5c9c68415920","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"b7e6b676-9492-4a87-95bc-5287c1f5d47b","timestamp":"2026-10-30T05:41:22.873Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"b7e6b676-9492-4a87-95bc-5287c1f5d47b","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"96fad295-6ddf-4fb0-9281-f201f6876732","timestamp":"2026-10-30T05:41:22.873Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"96fad295-6ddf-4fb0-9281-f201f6876732","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":"f1566835-da16-4bf9-81c1-56495d573724","timestamp":"2026-10-30T05:41:22.873Z","rendered":[{"content":"<system-reminder>\nAttribution for git commits and pull requests you create from here on (this replaces Claude Code's own earlier attribution guidance, such as a previous copy of this reminder; the user's own instructions about these lines, such as a CLAUDE.md or memory rule, take precedence over this reminder, but do not add attribution lines this reminder leaves out):\n- End git commit messages with:\nCo-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>\n- End pull request descriptions with:\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\n</system-reminder>"}],"renderedRole":"user","renderedBesideToolResult":true,"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}12{"parentUuid":"f1566835-da16-4bf9-81c1-56495d573724","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNdgc1iDNQX7H3BQ9D","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSlQUKEAgTGAI4AUIIdGhpbmtpbmcSDENg+7mp5+1QpVAccBoM0Dfgk8gozrmohUHnIjBxbB2Psk4eA2RT8lLgUAKlBWHqV+C0waMllZyjKa52F/0YI7c4EG+4Davt3CeZCbkqsgT3o2Zx6wUPxJm6t7ucjsxBUEwJ2QVUrIZJhoQ68r6hOzbhUKMTvoMICkF+ZOnrZJK0X0TkqrHqnAIrIstHpcTgq5A8fE1ulqQdHCBpvqnL1XVvNE6qZ5GA4I89Q9ySFB437tAJgbwUjNNYw+xbyCTbmwBCByOJd8zkirxE8dgqP3t5iinKswNHM62DDVWRzRj4BvJCrcASG83cDX8wdzU1i9rUZG6dHfV0r6lM1oCHmviN+4JM3ObDyUuUfxDjtwoYJbrEeQ2LcvvscDWj+YG3EuY1D0EeZaXPRWRbz2uc2u92n6l8GG0tVbCqe7FEtCcRqpNMpFDJpvXWLYJK4KrS8MI1hXOht55OOr7/3RXJNzN1a1ORTWNDYm9pQKZOh/QT+A+4f+dIvULSmU+JLdnF+DyAILcOuzCWPq4ekEW5upf3/DBAYUbxGmc+0tNXJFbivkYsnqTGxF0jE2aHWwFiKdM5OaXqaSXia3i4khb8PRTLaZCCOAwVbf4vEo0HEYW9CvrHhHUx4u69Tvij3pngfYsZQnGTenugfFiDI89P3FsyZwImwlRjQfJNCMpAZ9FqZzuQ2kkVogeqxFlUarjVJP34Kv3m8XVUG7S6eAJILM7UqFJpanck+6bmpOeTq2NyXudU9cuxdLthH55OHyO/oAhBS3v1pUZ5ICcnh+UwEeh4S4npb0jgVzl8KvtAovmexykEdkNuxBCpD1tpRTPiIovDy5N4/a+VoOeRG6z5ns0qGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":716,"cache_read_input_tokens":1504,"output_tokens":122,"output_tokens_details":{"thinking_tokens":17},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":456,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtNdQEaXQsfNNtTP2Rb","requestRef":"6d532d07-7480-4d23-9332-bae1e747067f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8647c660-1dd9-4876-84c1-883adadae73a","timestamp":"2026-10-30T05:41:24.973Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"8647c660-1dd9-4876-84c1-883adadae73a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNdgc1iDNQX7H3BQ9D","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_013XDgYgEhyvzCfhfHeZzM5a","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Read task and deliverables"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":716,"cache_read_input_tokens":1504,"output_tokens":122,"output_tokens_details":{"thinking_tokens":17},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtNdQEaXQsfNNtTP2Rb","requestRef":"6d532d07-7480-4d23-9332-bae1e747067f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9b3792b6-69bc-4a81-bc50-49f837b58400","timestamp":"2026-10-30T05:41:25.577Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"9b3792b6-69bc-4a81-bc50-49f837b58400","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_013XDgYgEhyvzCfhfHeZzM5a","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 240\ndrwxr-xr-x 11 simon-pierreboucher staff 352 oct. 30 01:41 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:38 ..\n-rw-r--r-- 1 simon-pierreboucher staff 8544 oct. 30 01:40 analysis.py\n-rw-r--r-- 1 simon-pierreboucher staff 1888 oct. 30 01:41 claims.json\n-rw-r--r-- 1 simon-pierreboucher staff 188 oct. 30 01:38 exclusions.csv\n-rw-r--r-- 1 simon-pierreboucher staff 79877 oct. 30 01:40 figure1.png\n-rw-r--r-- 1 simon-pierreboucher staff 7743 oct. 30 01:41 report.md\n-rw-r--r-- 1 simon-pierreboucher staff 6922 oct. 30 01:40 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:41 review\ndrwxr-xr-x 10 simon-pierreboucher staff 320 oct. 30 01:40 state\n-rw-r--r-- 1 simon-pierreboucher staff 2202 oct. 30 01:40 table1.csv\n{\n \"task_id\": \"T2-simulation\",\n \"R\": 2000,\n \"B\": 399,\n \"n_cells\": 9,\n \"coverage\": {\n \"cr0_G5_icc0.0\": 0.7805,\n \"cr1_G5_icc0.0\": 0.9115,\n \"wcb_G5_icc0.0\": 0.855,\n \"cr0_G5_icc0.2\": 0.721,\n \"cr1_G5_icc0.2\": 0.8845,\n \"wcb_G5_icc0.2\": 0.854,\n \"cr0_G5_icc0.5\": 0.717,\n \"cr1_G5_icc0.5\": 0.8755,\n \"wcb_G5_icc0.5\": 0.849,\n \"cr0_G10_icc0.0\": 0.8965,\n \"cr1_G10_icc0.0\": 0.9435,\n \"wcb_G10_icc0.0\": 0.936,\n \"cr0_G10_icc0.2\": 0.857,\n \"cr1_G10_icc0.2\": 0.9155,\n \"wcb_G10_icc0.2\": 0.9295,\n \"cr0_G10_icc0.5\": 0.853,\n \"cr1_G10_icc0.5\": 0.9065,\n \"wcb_G10_icc0.5\": 0.9325,\n \"cr0_G30_icc0.0\": 0.9275,\n \"cr1_G30_icc0.0\": 0.94,\n \"wcb_G30_icc0.0\": 0.943,\n \"cr0_G30_icc0.2\": 0.921,\n \"cr1_G30_icc0.2\": 0.935,\n \"wcb_G30_icc0.2\": 0.946,\n \"cr0_G30_icc0.5\": 0.9165,\n \"cr1_G30_icc0.5\": 0.93,\n \"wcb_G30_icc0.5\": 0.9425\n },\n \"mc_se_coverage\": {\n \"cr0_G5_icc0.0\": 0.009255262016820486,\n \"cr1_G5_icc0.0\": 0.006350895606133045,\n \"wcb_G5_icc0.0\": 0.007873214083206426,\n \"cr0_G5_icc0.2\": 0.010028933143659899,\n \"cr1_G5_icc0.2\": 0.007147018609182434,\n \"wcb_G5_icc0.2\": 0.007895695029571494,\n \"cr0_G5_icc0.5\": 0.010072512099769353,\n \"cr1_G5_icc0.5\": 0.007382403064043579,\n \"wcb_G5_icc0.5\": 0.008006216334823835,\n \"cr0_G10_icc0.0\": 0.006811304941052046,\n \"cr1_G10_icc0.0\": 0.005162739098579358,\n \"wcb_G10_icc0.0\": 0.00547284204047586,\n \"cr0_G10_icc0.2\": 0.007827866886962246,\n \"cr1_G10_icc0.2\": 0.006219314672855845,\n \"wcb_G10_icc0.2\": 0.005724061058374553,\n \"cr0_G10_icc0.5\": 0.007918049002121673,\n \"cr1_G10_icc0.5\": 0.006509905913298595,\n \"wcb_G10_icc0.5\": 0.005609979946488223,\n \"cr0_G30_icc0.0\": 0.005798437289477226,\n \"cr1_G30_icc0.0\": 0.005310367218940704,\n \"wcb_G30_icc0.0\": 0.005184158562389852,\n \"cr0_G30_icc0.2\": 0.006031542091372652,\n \"cr1_G30_icc0.2\": 0.005512485827646179,\n \"wcb_G30_icc0.2\": 0.005053909377897473,\n \"cr0_G30_icc0.5\": 0.006185780063985464,\n \"cr1_G30_icc0.5\": 0.005705260730238364,\n \"wcb_G30_icc0.5\": 0.005205465877325487\n },\n \"rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.6616434596045324,\n \"cr1_G5_icc0.0\": 0.8270543245056654,\n \"cr0_G5_icc0.2\": 0.5313958571125164,\n \"cr1_G5_icc0.2\": 0.6642448213906453,\n \"cr0_G5_icc0.5\": 0.48335023384407516,\n \"cr1_G5_icc0.5\": 0.6041877923050938,\n \"cr0_G10_icc0.0\": 0.8558047169939658,\n \"cr1_G10_icc0.0\": 0.9508941299932954,\n \"cr0_G10_icc0.2\": 0.7624366224508259,\n \"cr1_G10_icc0.2\": 0.8471518027231398,\n \"cr0_G10_icc0.5\": 0.7737432482368367,\n \"cr1_G10_icc0.5\": 0.859714720263152,\n \"cr0_G30_icc0.0\": 0.943796503270819,\n \"cr1_G30_icc0.0\": 0.9763412102801576,\n \"cr0_G30_icc0.2\": 0.9313668684580917,\n \"cr1_G30_icc0.2\": 0.9634829673704397,\n \"cr0_G30_icc0.5\": 0.9252598675851053,\n \"cr1_G30_icc0.5\": 0.9571653802604538\n },\n \"failure_cells\": [\n \"cr0_G5_icc0.0\",\n \"wcb_G5_icc0.0\",\n \"cr0_G5_icc0.2\",\n \"cr1_G5_icc0.2\",\n \"wcb_G5_icc0.2\",\n \"cr0_G5_icc0.5\",\n \"cr1_G5_icc0.5\",\n \"wcb_G5_icc0.5\",\n \"cr0_G10_icc0.0\",\n \"cr0_G10_icc0.2\",\n \"cr0_G10_icc0.5\"\n ],\n \"n_failure_cells\": 11,\n \"nominal_cells\": [\n \"cr1_G10_icc0.0\",\n \"cr1_G30_icc0.0\",\n \"wcb_G30_icc0.0\",\n \"wcb_G30_icc0.2\",\n \"wcb_G30_icc0.5\"\n ],\n \"best_procedure_small_G\": \"cr1\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct weight vectors exist (16 distinct |t*| values, as |t*| is invariant to w -> -w); B=399 draws therefore repeat these few values and the 0.95 quantile of |t*| is coarse.\",\n \"handling\": \"Kept as specified (B=399, Rademacher, random draws, numpy linear-interpolation quantile); discussed in report as a known feature of WCB with very few clusters.\"\n }\n ],\n \"n_input_rows\": {\n \"design.csv\": 9\n },\n \"n_analysed\": 18000,\n \"random_seed\": 20261101,\n \"avg_coverage_G5\": {\n \"cr0\": 0.7395,\n \"cr1\": 0.8905,\n \"wcb\": 0.8526666666666666\n },\n \"mc_se_rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.012963511182344976,\n \"cr1_G5_icc0.0\": 0.01620438897793122,\n \"cr0_G5_icc0.2\": 0.012975387163286884,\n \"cr1_G5_icc0.2\": 0.016219233954108608,\n \"cr0_G5_icc0.5\": 0.011854909267984598,\n \"cr1_G5_icc0.5\": 0.01481863658498075,\n \"cr0_G10_icc0.0\": 0.011793478824212352,\n \"cr1_G10_icc0.0\": 0.013103865360235948,\n \"cr0_G10_icc0.2\": 0.012887411160981703,\n \"cr1_G10_icc0.2\": 0.014319345734424112,\n \"cr0_G10_icc0.5\": 0.014100595197540216,\n \"cr1_G10_icc0.5\": 0.015667327997266903,\n \"cr0_G30_icc0.0\": 0.006765949452231232,\n \"cr1_G30_icc0.0\": 0.006999258054032309,\n \"cr0_G30_icc0.2\": 0.00853308139600021,\n \"cr1_G30_icc0.2\": 0.008827325582069187,\n \"cr0_G30_icc0.5\": 0.008700682520806436,\n \"cr1_G30_icc0.5\": 0.009000706056006657\n },\n \"avg_coverage_G5_paired_diff\": {\n \"cr1_minus_cr0\": {\n \"diff\": 0.1509999999999999,\n \"mc_se\": 0.004619864044982199\n },\n \"cr1_minus_wcb\": {\n \"diff\": 0.037833333333333385,\n \"mc_se\": 0.0034783787896010433\n }\n },\n \"cells_within_2se_of_failure_line\": [\n \"cr1_G5_icc0.0\",\n \"cr0_G10_icc0.0\",\n \"cr1_G10_icc0.5\"\n ],\n \"baseline_iid_coverage\": {\n \"iid_G5_icc0.0\": 0.9405,\n \"iid_G5_icc0.2\": 0.46,\n \"iid_G5_icc0.5\": 0.2865,\n \"iid_G10_icc0.0\": 0.957,\n \"iid_G10_icc0.2\": 0.488,\n \"iid_G10_icc0.5\": 0.3125,\n \"iid_G30_icc0.0\": 0.9515,\n \"iid_G30_icc0.2\": 0.485,\n \"iid_G30_icc0.5\": 0.2985\n },\n \"check_mc_var_ybar_over_exact\": {\n \"G5_icc0.0\": {\n \"mc_var_ybar_over_exact\": 1.03532630144612,\n \"mean_ybar\": 0.00028867307788429486\n },\n \"G5_icc0.2\": {\n \"mc_var_ybar_over_exact\": 1.0645917096631416,\n \"mean_ybar\": 0.010497786660162045\n },\n \"G5_icc0.5\": {\n \"mc_var_ybar_over_exact\": 0.9463288431559199,\n \"mean_ybar\": -0.005763243574855418\n },\n \"G10_icc0.0\": {\n \"mc_var_ybar_over_exact\": 0.9335632526902219,\n \"mean_ybar\": -8.481537588492616e-05\n },\n \"G10_icc0.2\": {\n \"mc_var_ybar_over_exact\": 0.9685288371506661,\n \"mean_ybar\": 0.004033474563745705\n },\n \"G10_icc0.5\": {\n \"mc_var_ybar_over_exact\": 0.979581002751385,\n \"mean_ybar\": -0.0013932598375193423\n },\n \"G30_icc0.0\": {\n \"mc_var_ybar_over_exact\": 0.9985616155092211,\n \"mean_ybar\": -0.000782799084647925\n },\n \"G30_icc0.2\": {\n \"mc_var_ybar_over_exact\": 0.9393486739255914,\n \"mean_ybar\": 0.0021016344076126483\n },\n \"G30_icc0.5\": {\n \"mc_var_ybar_over_exact\": 1.0404439013279725,\n \"mean_ybar\": -0.0024768417619560603\n }\n },\n \"n_degenerate_bootstrap_draws\": 0,\n \"wcb_quantile_method\": \"numpy.quantile linear interpolation (type 7) of |t*_b|, b=1..B\",\n \"seeds_by_cell\": {\n \"C1\": 20261101,\n \"C2\": 20261102,\n \"C3\": 20261103,\n \"C4\": 20261104,\n \"C5\": 20261105,\n \"C6\": 20261106,\n \"C7\": 20261107,\n \"C8\": 20261108,\n \"C9\": 20261109\n }\n}[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G=5 and G=10 cells, WCB at all G=5 cells, CR1 at G=5 with ICC 0.2 and 0.5; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5_icc0.0 and cr0_G10_icc0.0 lie within 2 MC SE of 0.90, so their classification is fragile.\"},\n {\"id\":\"C2\",\"text\":\"CR1 has the highest average coverage over the G=5 cells (0.891 vs 0.853 WCB and 0.740 CR0); the CR1-WCB gap is many paired MC SEs.\",\"results_keys\":[\"best_procedure_small_G\",\"avg_coverage_G5\",\"avg_coverage_G5_paired_diff\"],\"status\":\"supported\",\"caveat\":\"Specific to Rademacher unrestricted WCB with B=399 and Gaussian DGP.\"},\n {\"id\":\"C3\",\"text\":\"Only 5 pairs are consistent with nominal 95% coverage (CR1 at G=10 and G=30 with ICC=0; WCB at all G=30 cells); CR0 never is.\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE screen without multiplicity control.\"},\n {\"id\":\"C4\",\"text\":\"CR0 and CR1 variance estimators are biased downward, most at small G and high ICC (CR0 ratio 0.48-0.66 at G=5, 0.93-0.94 at G=30).\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\"],\"status\":\"supported\",\"caveat\":\"MC estimate; agrees with closed-form expectation within 2 SE in 8 of 9 cells (2.46 SE in G5_icc0.2).\"},\n {\"id\":\"C5\",\"text\":\"The naive i.i.d. baseline interval covers only 0.29-0.49 when ICC>0, so all cluster-robust procedures improve on it in clustered cells.\",\"results_keys\":[\"baseline_iid_coverage\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Baseline is supplementary, not a required estimand.\"},\n {\"id\":\"C6\",\"text\":\"At G=10 with ICC>0, WCB covers better than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences (0.014 and 0.026) are of the order of 2-4 MC SE of individual coverages; not formally tested.\"}\n]","is_error":false}]},"uuid":"7acbd846-2f96-449e-8607-b5c6890ae746","timestamp":"2026-10-30T05:41:25.665Z","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 240\ndrwxr-xr-x 11 simon-pierreboucher staff 352 oct. 30 01:41 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:38 ..\n-rw-r--r-- 1 simon-pierreboucher staff 8544 oct. 30 01:40 analysis.py\n-rw-r--r-- 1 simon-pierreboucher staff 1888 oct. 30 01:41 claims.json\n-rw-r--r-- 1 simon-pierreboucher staff 188 oct. 30 01:38 exclusions.csv\n-rw-r--r-- 1 simon-pierreboucher staff 79877 oct. 30 01:40 figure1.png\n-rw-r--r-- 1 simon-pierreboucher staff 7743 oct. 30 01:41 report.md\n-rw-r--r-- 1 simon-pierreboucher staff 6922 oct. 30 01:40 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:41 review\ndrwxr-xr-x 10 simon-pierreboucher staff 320 oct. 30 01:40 state\n-rw-r--r-- 1 simon-pierreboucher staff 2202 oct. 30 01:40 table1.csv\n{\n \"task_id\": \"T2-simulation\",\n \"R\": 2000,\n \"B\": 399,\n \"n_cells\": 9,\n \"coverage\": {\n \"cr0_G5_icc0.0\": 0.7805,\n \"cr1_G5_icc0.0\": 0.9115,\n \"wcb_G5_icc0.0\": 0.855,\n \"cr0_G5_icc0.2\": 0.721,\n \"cr1_G5_icc0.2\": 0.8845,\n \"wcb_G5_icc0.2\": 0.854,\n \"cr0_G5_icc0.5\": 0.717,\n \"cr1_G5_icc0.5\": 0.8755,\n \"wcb_G5_icc0.5\": 0.849,\n \"cr0_G10_icc0.0\": 0.8965,\n \"cr1_G10_icc0.0\": 0.9435,\n \"wcb_G10_icc0.0\": 0.936,\n \"cr0_G10_icc0.2\": 0.857,\n \"cr1_G10_icc0.2\": 0.9155,\n \"wcb_G10_icc0.2\": 0.9295,\n \"cr0_G10_icc0.5\": 0.853,\n \"cr1_G10_icc0.5\": 0.9065,\n \"wcb_G10_icc0.5\": 0.9325,\n \"cr0_G30_icc0.0\": 0.9275,\n \"cr1_G30_icc0.0\": 0.94,\n \"wcb_G30_icc0.0\": 0.943,\n \"cr0_G30_icc0.2\": 0.921,\n \"cr1_G30_icc0.2\": 0.935,\n \"wcb_G30_icc0.2\": 0.946,\n \"cr0_G30_icc0.5\": 0.9165,\n \"cr1_G30_icc0.5\": 0.93,\n \"wcb_G30_icc0.5\": 0.9425\n },\n \"mc_se_coverage\": {\n \"cr0_G5_icc0.0\": 0.009255262016820486,\n \"cr1_G5_icc0.0\": 0.006350895606133045,\n \"wcb_G5_icc0.0\": 0.007873214083206426,\n \"cr0_G5_icc0.2\": 0.010028933143659899,\n \"cr1_G5_icc0.2\": 0.007147018609182434,\n \"wcb_G5_icc0.2\": 0.007895695029571494,\n \"cr0_G5_icc0.5\": 0.010072512099769353,\n \"cr1_G5_icc0.5\": 0.007382403064043579,\n \"wcb_G5_icc0.5\": 0.008006216334823835,\n \"cr0_G10_icc0.0\": 0.006811304941052046,\n \"cr1_G10_icc0.0\": 0.005162739098579358,\n \"wcb_G10_icc0.0\": 0.00547284204047586,\n \"cr0_G10_icc0.2\": 0.007827866886962246,\n \"cr1_G10_icc0.2\": 0.006219314672855845,\n \"wcb_G10_icc0.2\": 0.005724061058374553,\n \"cr0_G10_icc0.5\": 0.007918049002121673,\n \"cr1_G10_icc0.5\": 0.006509905913298595,\n \"wcb_G10_icc0.5\": 0.005609979946488223,\n \"cr0_G30_icc0.0\": 0.005798437289477226,\n \"cr1_G30_icc0.0\": 0.005310367218940704,\n \"wcb_G30_icc0.0\": 0.005184158562389852,\n \"cr0_G30_icc0.2\": 0.006031542091372652,\n \"cr1_G30_icc0.2\": 0.005512485827646179,\n \"wcb_G30_icc0.2\": 0.005053909377897473,\n \"cr0_G30_icc0.5\": 0.006185780063985464,\n \"cr1_G30_icc0.5\": 0.005705260730238364,\n \"wcb_G30_icc0.5\": 0.005205465877325487\n },\n \"rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.6616434596045324,\n \"cr1_G5_icc0.0\": 0.8270543245056654,\n \"cr0_G5_icc0.2\": 0.5313958571125164,\n \"cr1_G5_icc0.2\": 0.6642448213906453,\n \"cr0_G5_icc0.5\": 0.48335023384407516,\n \"cr1_G5_icc0.5\": 0.6041877923050938,\n \"cr0_G10_icc0.0\": 0.8558047169939658,\n \"cr1_G10_icc0.0\": 0.9508941299932954,\n \"cr0_G10_icc0.2\": 0.7624366224508259,\n \"cr1_G10_icc0.2\": 0.8471518027231398,\n \"cr0_G10_icc0.5\": 0.7737432482368367,\n \"cr1_G10_icc0.5\": 0.859714720263152,\n \"cr0_G30_icc0.0\": 0.943796503270819,\n \"cr1_G30_icc0.0\": 0.9763412102801576,\n \"cr0_G30_icc0.2\": 0.9313668684580917,\n \"cr1_G30_icc0.2\": 0.9634829673704397,\n \"cr0_G30_icc0.5\": 0.9252598675851053,\n \"cr1_G30_icc0.5\": 0.9571653802604538\n },\n \"failure_cells\": [\n \"cr0_G5_icc0.0\",\n \"wcb_G5_icc0.0\",\n \"cr0_G5_icc0.2\",\n \"cr1_G5_icc0.2\",\n \"wcb_G5_icc0.2\",\n \"cr0_G5_icc0.5\",\n \"cr1_G5_icc0.5\",\n \"wcb_G5_icc0.5\",\n \"cr0_G10_icc0.0\",\n \"cr0_G10_icc0.2\",\n \"cr0_G10_icc0.5\"\n ],\n \"n_failure_cells\": 11,\n \"nominal_cells\": [\n \"cr1_G10_icc0.0\",\n \"cr1_G30_icc0.0\",\n \"wcb_G30_icc0.0\",\n \"wcb_G30_icc0.2\",\n \"wcb_G30_icc0.5\"\n ],\n \"best_procedure_small_G\": \"cr1\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct weight vectors exist (16 distinct |t*| values, as |t*| is invariant to w -> -w); B=399 draws therefore repeat these few values and the 0.95 quantile of |t*| is coarse.\",\n \"handling\": \"Kept as specified (B=399, Rademacher, random draws, numpy linear-interpolation quantile); discussed in report as a known feature of WCB with very few clusters.\"\n }\n ],\n \"n_input_rows\": {\n \"design.csv\": 9\n },\n \"n_analysed\": 18000,\n \"random_seed\": 20261101,\n \"avg_coverage_G5\": {\n \"cr0\": 0.7395,\n \"cr1\": 0.8905,\n \"wcb\": 0.8526666666666666\n },\n \"mc_se_rel_bias_var\": {\n \"cr0_G5_icc0.0\": 0.012963511182344976,\n \"cr1_G5_icc0.0\": 0.01620438897793122,\n \"cr0_G5_icc0.2\": 0.012975387163286884,\n \"cr1_G5_icc0.2\": 0.016219233954108608,\n \"cr0_G5_icc0.5\": 0.011854909267984598,\n \"cr1_G5_icc0.5\": 0.01481863658498075,\n \"cr0_G10_icc0.0\": 0.011793478824212352,\n \"cr1_G10_icc0.0\": 0.013103865360235948,\n \"cr0_G10_icc0.2\": 0.012887411160981703,\n \"cr1_G10_icc0.2\": 0.014319345734424112,\n \"cr0_G10_icc0.5\": 0.014100595197540216,\n \"cr1_G10_icc0.5\": 0.015667327997266903,\n \"cr0_G30_icc0.0\": 0.006765949452231232,\n \"cr1_G30_icc0.0\": 0.006999258054032309,\n \"cr0_G30_icc0.2\": 0.00853308139600021,\n \"cr1_G30_icc0.2\": 0.008827325582069187,\n \"cr0_G30_icc0.5\": 0.008700682520806436,\n \"cr1_G30_icc0.5\": 0.009000706056006657\n },\n \"avg_coverage_G5_paired_diff\": {\n \"cr1_minus_cr0\": {\n \"diff\": 0.1509999999999999,\n \"mc_se\": 0.004619864044982199\n },\n \"cr1_minus_wcb\": {\n \"diff\": 0.037833333333333385,\n \"mc_se\": 0.0034783787896010433\n }\n },\n \"cells_within_2se_of_failure_line\": [\n \"cr1_G5_icc0.0\",\n \"cr0_G10_icc0.0\",\n \"cr1_G10_icc0.5\"\n ],\n \"baseline_iid_coverage\": {\n \"iid_G5_icc0.0\": 0.9405,\n \"iid_G5_icc0.2\": 0.46,\n \"iid_G5_icc0.5\": 0.2865,\n \"iid_G10_icc0.0\": 0.957,\n \"iid_G10_icc0.2\": 0.488,\n \"iid_G10_icc0.5\": 0.3125,\n \"iid_G30_icc0.0\": 0.9515,\n \"iid_G30_icc0.2\": 0.485,\n \"iid_G30_icc0.5\": 0.2985\n },\n \"check_mc_var_ybar_over_exact\": {\n \"G5_icc0.0\": {\n \"mc_var_ybar_over_exact\": 1.03532630144612,\n \"mean_ybar\": 0.00028867307788429486\n },\n \"G5_icc0.2\": {\n \"mc_var_ybar_over_exact\": 1.0645917096631416,\n \"mean_ybar\": 0.010497786660162045\n },\n \"G5_icc0.5\": {\n \"mc_var_ybar_over_exact\": 0.9463288431559199,\n \"mean_ybar\": -0.005763243574855418\n },\n \"G10_icc0.0\": {\n \"mc_var_ybar_over_exact\": 0.9335632526902219,\n \"mean_ybar\": -8.481537588492616e-05\n },\n \"G10_icc0.2\": {\n \"mc_var_ybar_over_exact\": 0.9685288371506661,\n \"mean_ybar\": 0.004033474563745705\n },\n \"G10_icc0.5\": {\n \"mc_var_ybar_over_exact\": 0.979581002751385,\n \"mean_ybar\": -0.0013932598375193423\n },\n \"G30_icc0.0\": {\n \"mc_var_ybar_over_exact\": 0.9985616155092211,\n \"mean_ybar\": -0.000782799084647925\n },\n \"G30_icc0.2\": {\n \"mc_var_ybar_over_exact\": 0.9393486739255914,\n \"mean_ybar\": 0.0021016344076126483\n },\n \"G30_icc0.5\": {\n \"mc_var_ybar_over_exact\": 1.0404439013279725,\n \"mean_ybar\": -0.0024768417619560603\n }\n },\n \"n_degenerate_bootstrap_draws\": 0,\n \"wcb_quantile_method\": \"numpy.quantile linear interpolation (type 7) of |t*_b|, b=1..B\",\n \"seeds_by_cell\": {\n \"C1\": 20261101,\n \"C2\": 20261102,\n \"C3\": 20261103,\n \"C4\": 20261104,\n \"C5\": 20261105,\n \"C6\": 20261106,\n \"C7\": 20261107,\n \"C8\": 20261108,\n \"C9\": 20261109\n }\n}[\n {\"id\":\"C1\",\"text\":\"11 (procedure, cell) pairs have coverage below 0.90: CR0 at all G=5 and G=10 cells, WCB at all G=5 cells, CR1 at G=5 with ICC 0.2 and 0.5; none at G=30.\",\"results_keys\":[\"failure_cells\",\"n_failure_cells\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"cr1_G5_icc0.0 and cr0_G10_icc0.0 lie within 2 MC SE of 0.90, so their classification is fragile.\"},\n {\"id\":\"C2\",\"text\":\"CR1 has the highest average coverage over the G=5 cells (0.891 vs 0.853 WCB and 0.740 CR0); the CR1-WCB gap is many paired MC SEs.\",\"results_keys\":[\"best_procedure_small_G\",\"avg_coverage_G5\",\"avg_coverage_G5_paired_diff\"],\"status\":\"supported\",\"caveat\":\"Specific to Rademacher unrestricted WCB with B=399 and Gaussian DGP.\"},\n {\"id\":\"C3\",\"text\":\"Only 5 pairs are consistent with nominal 95% coverage (CR1 at G=10 and G=30 with ICC=0; WCB at all G=30 cells); CR0 never is.\",\"results_keys\":[\"nominal_cells\",\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"2-SE screen without multiplicity control.\"},\n {\"id\":\"C4\",\"text\":\"CR0 and CR1 variance estimators are biased downward, most at small G and high ICC (CR0 ratio 0.48-0.66 at G=5, 0.93-0.94 at G=30).\",\"results_keys\":[\"rel_bias_var\",\"mc_se_rel_bias_var\"],\"status\":\"supported\",\"caveat\":\"MC estimate; agrees with closed-form expectation within 2 SE in 8 of 9 cells (2.46 SE in G5_icc0.2).\"},\n {\"id\":\"C5\",\"text\":\"The naive i.i.d. baseline interval covers only 0.29-0.49 when ICC>0, so all cluster-robust procedures improve on it in clustered cells.\",\"results_keys\":[\"baseline_iid_coverage\",\"coverage\"],\"status\":\"supported\",\"caveat\":\"Baseline is supplementary, not a required estimand.\"},\n {\"id\":\"C6\",\"text\":\"At G=10 with ICC>0, WCB covers better than CR1.\",\"results_keys\":[\"coverage\",\"mc_se_coverage\"],\"status\":\"supported\",\"caveat\":\"Differences (0.014 and 0.026) are of the order of 2-4 MC SE of individual coverages; not formally tested.\"}\n]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"9b3792b6-69bc-4a81-bc50-49f837b58400","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"c0cc5357d0fe97480f85325dfa868b05b3369595054738499019c36cea2f3f6e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_013XDgYgEhyvzCfhfHeZzM5a","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Read task and deliverables"}}]}}16{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"de749b8b-98ad-48b9-a42b-abbf30e9a90d","timestamp":"2026-10-30T05:41:25.669Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"6d532d07-7480-4d23-9332-bae1e747067f","keep":2,"tail":["c0cc5357d0fe97480f85325dfa868b05b3369595054738499019c36cea2f3f6e","27d9b7295b20356cadbf6a308525baa30e5bb00323811e34155205f1cffe7bd6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3608131fcb28908dddfbb2a18d10e12129f3feed80f99459df4bc7948adc1acb"}17{"type":"last-prompt","lastPrompt":"Review","leafUuid":"7acbd846-2f96-449e-8607-b5c6890ae746","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}18{"type":"atis-latch","atis":"","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}19{"parentUuid":"7acbd846-2f96-449e-8607-b5c6890ae746","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtNn9bBgawY8dV65ySE","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01R2Kn1DuBddUEKqSrbpocZS","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/table1.csv; cat out/exclusions.csv; ls out/state; cat data/design.csv","description":"Read code, report, table"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":8354,"cache_read_input_tokens":2220,"output_tokens":127,"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":8354},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXtNmqVuFzmWhBUhBCjS","requestRef":"de749b8b-98ad-48b9-a42b-abbf30e9a90d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ce92aedf-32da-4f38-8183-83b7f260bb22","timestamp":"2026-10-30T05:41:40.130Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"ce92aedf-32da-4f38-8183-83b7f260bb22","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01R2Kn1DuBddUEKqSrbpocZS","type":"tool_result","content":"\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t CIs for a mean.\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png.\nRandomness: one numpy default_rng(seed) per cell (seed from design.csv). Per replication, draws in\nfixed order: u (G normals), e (N normals), W (B x G Rademacher via rng.integers(0,2)).\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nDATA = os.path.join(ROOT, \"data\", \"design.csv\")\nOUT = os.path.join(ROOT, \"out\")\nEST = [\"cr0\", \"cr1\", \"wcb\"]\n\n\ndef simulate_cell(row):\n G, icc, N, R, B, mu = int(row.G), float(row.icc), int(row.N), int(row.R), int(row.B), float(row.mu)\n sizes = np.array([int(x) for x in row.cluster_sizes.split(\"|\")])\n assert len(sizes) == G and sizes.sum() == N\n gid = np.repeat(np.arange(G), sizes)\n var_exact = (icc * np.sum(sizes.astype(float) ** 2) + (1 - icc) * N) / N ** 2\n tcrit = stats.t.ppf(0.975, G - 1)\n zcrit = 1.96\n adj = G / (G - 1)\n rng = np.random.default_rng(int(row.seed))\n res = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"v_iid\"]}\n n_degenerate = 0\n for r in range(R):\n u = rng.normal(0.0, np.sqrt(icc), G) # scale 0 when icc=0 -> u = 0\n e = rng.normal(0.0, np.sqrt(1 - icc), N)\n y = mu + u[gid] + e\n ybar = y.mean()\n ehat = y - ybar\n S = np.bincount(gid, weights=ehat, minlength=G) # cluster residual sums\n v0 = np.sum(S ** 2) / N ** 2\n v1 = adj * v0\n # wild cluster bootstrap-t (unrestricted, Rademacher), vectorised over B\n W = rng.integers(0, 2, size=(B, G)) * 2 - 1\n d = (W * S).sum(axis=1) / N # ybar* - ybar\n Sstar = W * S - np.outer(d, sizes) # cluster sums of bootstrap residuals\n v1s = adj * np.sum(Sstar ** 2, axis=1) / N ** 2\n if np.any(v1s <= 0):\n n_degenerate += int(np.sum(v1s <= 0))\n v1s = np.where(v1s <= 0, np.nan, v1s)\n tabs = np.abs(d) / np.sqrt(v1s)\n q = np.nanquantile(tabs, 0.95) # numpy default (linear interpolation)\n res[\"ybar\"][r], res[\"v0\"][r], res[\"v1\"][r], res[\"q\"][r] = ybar, v0, v1, q\n res[\"v_iid\"][r] = np.var(y, ddof=1) / N # naive i.i.d. baseline\n hw = {\"cr0\": zcrit * np.sqrt(res[\"v0\"]), \"cr1\": tcrit * np.sqrt(res[\"v1\"]),\n \"wcb\": res[\"q\"] * np.sqrt(res[\"v1\"]), \"iid\": zcrit * np.sqrt(res[\"v_iid\"])}\n out = {\"var_exact\": var_exact, \"n_degenerate\": n_degenerate, \"R\": R}\n for k, h in hw.items():\n cov = np.abs(res[\"ybar\"] - mu) <= h\n out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean()), \"ind\": cov.astype(float)}\n for k, v in [(\"cr0\", res[\"v0\"]), (\"cr1\", res[\"v1\"])]:\n out[k][\"rel_bias\"] = float(v.mean() / var_exact)\n out[k][\"rel_bias_mcse\"] = float(v.std(ddof=1) / np.sqrt(R) / var_exact)\n out[\"mc_var_ybar_ratio\"] = float(np.var(res[\"ybar\"], ddof=1) / var_exact)\n out[\"mean_ybar\"] = float(res[\"ybar\"].mean())\n return out\n\n\ndef main():\n d = pd.read_csv(DATA)\n R_all, B_all = d.R.unique(), d.B.unique()\n assert len(R_all) == 1 and len(B_all) == 1\n R, B = int(R_all[0]), int(B_all[0])\n cov, se, rb, rb_se, base, chk = {}, {}, {}, {}, {}, {}\n rows, issues = [], []\n n_deg = 0\n ind_g5 = {k: [] for k in EST}\n for row in d.itertuples(index=False):\n o = simulate_cell(row)\n n_deg += o[\"n_degenerate\"]\n tag = f\"G{int(row.G)}_icc{float(row.icc):.1f}\"\n for k in EST:\n key = f\"{k}_{tag}\"\n p = o[k][\"coverage\"]\n cov[key] = p\n se[key] = float(np.sqrt(p * (1 - p) / o[\"R\"]))\n if k != \"wcb\":\n rb[key] = o[k][\"rel_bias\"]\n rb_se[key] = o[k][\"rel_bias_mcse\"]\n rows.append({\"estimator\": k, \"cell_id\": row.cell_id, \"G\": int(row.G), \"icc\": float(row.icc),\n \"coverage\": p, \"mc_se_coverage\": se[key],\n \"rel_bias_var\": o[k].get(\"rel_bias\", None), \"mean_ci_halfwidth\": o[k][\"hw\"], \"R\": o[\"R\"]})\n if int(row.G) == 5:\n for k in EST:\n ind_g5[k].append(o[k][\"ind\"])\n base[f\"iid_{tag}\"] = o[\"iid\"][\"coverage\"]\n chk[tag] = {\"mc_var_ybar_over_exact\": o[\"mc_var_ybar_ratio\"], \"mean_ybar\": o[\"mean_ybar\"]}\n print(f\"{row.cell_id} {tag}: \" + \", \".join(f\"{k}={cov[f'{k}_{tag}']:.4f}\" for k in EST))\n table = pd.DataFrame(rows)\n table.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n failure = [k for k, p in cov.items() if p < 0.90]\n nominal = [k for k, p in cov.items() if abs(p - 0.95) <= 2 * se[k]]\n g5 = {k: np.mean([cov[f\"{k}_G5_icc{i:.1f}\"] for i in (0.0, 0.2, 0.5)]) for k in EST}\n best = max(g5, key=g5.get)\n # paired MC SE of the difference in average G=5 coverage between best and each other procedure\n # (same replications -> paired; cells independent -> variance of mean over 3 cells = sum/9)\n g5_diff = {}\n for k in EST:\n if k == best:\n continue\n cell_vars = [np.var(a - b, ddof=1) / len(a) for a, b in zip(ind_g5[best], ind_g5[k])]\n g5_diff[f\"{best}_minus_{k}\"] = {\"diff\": float(g5[best] - g5[k]), \"mc_se\": float(np.sqrt(sum(cell_vars)) / len(cell_vars))}\n near = [k for k, p in cov.items() if abs(p - 0.90) <= 2 * se[k]]\n if 5 in d.G.values:\n issues.append({\"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct weight vectors exist (16 distinct |t*| values, as |t*| is invariant to w -> -w); B=399 draws therefore repeat these few values and the 0.95 quantile of |t*| is coarse.\",\n \"handling\": \"Kept as specified (B=399, Rademacher, random draws, numpy linear-interpolation quantile); discussed in report as a known feature of WCB with very few clusters.\"})\n if n_deg:\n issues.append({\"issue\": f\"{n_deg} bootstrap draws had non-positive V_CR1*\", \"handling\": \"Excluded those draws from the |t*| quantile (nan-quantile).\"})\n results = {\n \"task_id\": \"T2-simulation\", \"R\": R, \"B\": B, \"n_cells\": int(len(d)),\n \"coverage\": cov, \"mc_se_coverage\": se, \"rel_bias_var\": rb,\n \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n \"best_procedure_small_G\": best,\n \"feasibility\": \"complete\", \"feasibility_reason\": None, \"data_issues\": issues,\n \"n_input_rows\": {\"design.csv\": int(len(d))},\n \"n_analysed\": int(len(d) * R), \"random_seed\": int(d.loc[d.cell_id == \"C1\", \"seed\"].iloc[0]),\n # supplementary keys\n \"avg_coverage_G5\": {k: float(v) for k, v in g5.items()},\n \"mc_se_rel_bias_var\": rb_se,\n \"avg_coverage_G5_paired_diff\": g5_diff,\n \"cells_within_2se_of_failure_line\": near,\n \"baseline_iid_coverage\": base,\n \"check_mc_var_ybar_over_exact\": chk,\n \"n_degenerate_bootstrap_draws\": int(n_deg),\n \"wcb_quantile_method\": \"numpy.quantile linear interpolation (type 7) of |t*_b|, b=1..B\",\n \"seeds_by_cell\": {r.cell_id: int(r.seed) for r in d.itertuples(index=False)},\n }\n with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n # figure\n fig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\n Gs = sorted(d.G.unique())\n style = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t Rademacher\")}\n for ax, icc in zip(axes, sorted(d.icc.unique())):\n for k in EST:\n p = np.array([cov[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n s = np.array([se[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n ax.errorbar(Gs, p, yerr=1.96 * s, fmt=style[k][0], capsize=3, label=style[k][1])\n ax.axhline(0.95, color=\"k\", ls=\"--\", lw=1, label=\"nominal 0.95\")\n ax.axhline(0.90, color=\"r\", ls=\":\", lw=1, label=\"failure line 0.90\")\n ax.set_xscale(\"log\"); ax.minorticks_off(); ax.set_xticks(Gs); ax.set_xticklabels(Gs)\n ax.set_title(f\"ICC = {icc:.1f}\"); ax.set_xlabel(\"number of clusters G\")\n axes[0].set_ylabel(\"coverage (R=2000; bars ±1.96 MC SE)\")\n axes[0].legend(loc=\"lower right\", fontsize=8)\n fig.tight_layout()\n fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n print(\"failure cells:\", failure)\n print(\"best procedure at G=5:\", best)\n\n\nif __name__ == \"__main__\":\n main()\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t intervals for a mean with few clusters\n\nAll numbers below are produced by `out/analysis.py` (run: `~/wp29/venv/bin/python out/analysis.py`, ≈2 s) and are cited by their key in `out/results.json`. Full per-cell values are in `out/table1.csv`; the figure is `out/figure1.png`.\n\n## Question\nWhen N observations are grouped in few (G = 5, 10, 30) unbalanced clusters with intra-cluster correlation ICC ∈ {0, 0.2, 0.5}, what is the actual coverage of three nominal-95% cluster-robust intervals for the mean μ (CR0 with z critical value; CR1 with t_{G−1}; unrestricted Rademacher wild cluster bootstrap-t, WCB), how biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ), and in which (procedure, cell) pairs does coverage fall below 0.90?\n\n## Data and exclusions\nNo observed data. The only input is `data/design.csv` (`n_input_rows`: 9 rows; SHA-256 recorded in `out/state/data_audit.md`): 9 cells, cluster sizes 8,16,32,64 repeated (N = 128, 264, 864), R = 2000 (`R`), B = 399 (`B`), one seed per cell (C1 seed = `random_seed`; all seeds in `seeds_by_cell`). The audit found no missing values, duplicates or inconsistencies (sizes count = G, sum = N). No exclusions: all `n_cells` = 9 cells × 2000 replications = `n_analysed` = 18000 replications were simulated and analysed (`out/exclusions.csv`, one no-op step). `feasibility` = \"complete\". One design feature is recorded in `data_issues`: at G = 5 Rademacher weights take only 32 distinct values (16 distinct |t*|), so the bootstrap critical value is coarse; kept as specified. No bootstrap draw had a non-positive variance (`n_degenerate_bootstrap_draws` = 0).\n\n## Method\nPer replication (numpy `default_rng(cell seed)`, draws in fixed order u, e, W): y_ig = μ + u_g + e_ig, u_g ~ N(0, ICC), e_ig ~ N(0, 1−ICC), μ = 0. With ê = y − ȳ and S_g = Σ_i ê_ig: V̂_CR0 = Σ S_g²/N², CI ȳ ± 1.96√V̂_CR0; V̂_CR1 = G/(G−1)·V̂_CR0, CI ȳ ± t_{0.975,G−1}√V̂_CR1; WCB: B×G Rademacher matrix W, ȳ*−ȳ = Σ_g w_g S_g/N, bootstrap cluster residual sums w_g S_g − n_g(ȳ*−ȳ), V̂*_CR1 from these, t*_b = (ȳ*−ȳ)/√V̂*_CR1, q = 0.95 quantile of |t*| (numpy linear interpolation, `wcb_quantile_method`), CI ȳ ± q√V̂_CR1. Coverage = share of R intervals containing μ; MC SE = √(p̂(1−p̂)/R); relative bias = mean(V̂)/Var(ȳ) with Var(ȳ) = [ICC Σn_g² + (1−ICC)N]/N². Failure regime: coverage < 0.90; nominal-consistent: |p̂ − 0.95| ≤ 2 MC SE. Baseline (P2): the naive i.i.d. interval ȳ ± 1.96·s/√N on the same draws (`baseline_iid_coverage`).\n\nVerification (`out/state/checks.md`): byte-identical re-run; vectorised WCB matches a brute-force construction of y* (diff 7e-15); MC relative bias of CR0 matches the closed-form E[V̂_CR0]/Var(ȳ) within 2 MC SE in 8/9 cells (z = +2.46 in G5_icc0.2); MC Var(ȳ)/exact in [0.93, 1.06] (`check_mc_var_ybar_over_exact`).\n\n## Results\nCoverage (`coverage`, MC SE in `mc_se_coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive i.i.d. baseline |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.781 | 0.912 | 0.855 | 0.941 |\n| 5 | 0.2 | 0.721 | 0.885 | 0.854 | 0.460 |\n| 5 | 0.5 | 0.717 | 0.876 | 0.849 | 0.287 |\n| 10 | 0.0 | 0.897 | 0.944 | 0.936 | 0.957 |\n| 10 | 0.2 | 0.857 | 0.916 | 0.930 | 0.488 |\n| 10 | 0.5 | 0.853 | 0.907 | 0.933 | 0.313 |\n| 30 | 0.0 | 0.928 | 0.940 | 0.943 | 0.952 |\n| 30 | 0.2 | 0.921 | 0.935 | 0.946 | 0.485 |\n| 30 | 0.5 | 0.917 | 0.930 | 0.943 | 0.299 |\n\n- **Failure regimes** (`failure_cells`, `n_failure_cells` = 11): CR0 at every G = 5 and G = 10 cell (6 pairs); WCB at all three G = 5 cells; CR1 at G = 5 with ICC = 0.2 and 0.5. No procedure fails at G = 30.\n- **Nominal-consistent pairs** (`nominal_cells`, 5 pairs): cr1_G10_icc0.0, cr1_G30_icc0.0, wcb_G30_icc0.0, wcb_G30_icc0.2, wcb_G30_icc0.5. CR0 is never consistent with 0.95, even at G = 30 (0.917–0.928).\n- **Best at G = 5** (`best_procedure_small_G` = \"cr1\"): average G = 5 coverage 0.891 for CR1, 0.853 for WCB, 0.740 for CR0 (`avg_coverage_G5`). The CR1 − WCB difference is 0.038 with paired MC SE 0.0035 (`avg_coverage_G5_paired_diff`), so the ranking is not a Monte Carlo artefact. At G = 10 with ICC > 0, WCB covers better than CR1 (0.930/0.933 vs 0.916/0.907).\n- **Variance bias** (`rel_bias_var`): both sandwich estimators are biased downward, most at small G and high ICC. CR0: 0.66, 0.53, 0.48 at G = 5 (ICC 0, 0.2, 0.5); 0.86, 0.76, 0.77 at G = 10; 0.94, 0.93, 0.93 at G = 30. CR1: 0.83, 0.66, 0.60 at G = 5; 0.95, 0.85, 0.86 at G = 10; 0.98, 0.96, 0.96 at G = 30. The unbalanced sizes (one 64-observation cluster dominates) make the bias much worse than the balanced-cluster factor (G−1)/G.\n- **Baseline**: the naive i.i.d. interval is fine at ICC = 0 but covers only 0.29–0.49 when ICC > 0 (`baseline_iid_coverage`), whatever G is. All three cluster-robust procedures improve on it there.\n- Mean CI half-widths are in `table1.csv` (`mean_ci_halfwidth`). At G = 5 the WCB interval is on average *wider* than CR1 but still covers less. One plausible explanation (not tested here) is that q varies a lot across replications, because the bootstrap distribution has only 16 distinct |t*| values.\n\n## Uncertainty\nEach coverage is a binomial proportion over R = 2000 independent replications. Its MC SE (`mc_se_coverage`) is 0.005–0.010, so a 95% MC interval is about ±0.010–0.020. The figure shows ±1.96 MC SE bars. Classifications near the 0.90 threshold are therefore fragile. cr1_G5_icc0.0 (0.912), cr0_G10_icc0.0 (0.897) and cr1_G10_icc0.5 (0.907) are within 2 MC SE of 0.90 (`cells_within_2se_of_failure_line`); a different seed could move them across the line. The \"nominal-consistent\" label is a 2-SE screen, not a test with multiplicity control: across 27 pairs, some misclassification is expected. With R = 2000 we cannot resolve coverage differences much smaller than ≈0.02. The relative-bias estimates have MC SE 0.007–0.016 (`mc_se_rel_bias_var`). Because V̂ is right-skewed at small G, the normal approximation behind that SE is rough, which matches the one 2.46-SE discrepancy from the exact value in G5_icc0.2. The paired SE for the G = 5 ranking uses the fact that all procedures are evaluated on the same replications. The bootstrap critical value adds its own simulation noise (B = 399), and that noise is included in the WCB coverage estimate.\n\n## Limitations and open issues\n- **Distributions**: only Gaussian random effects and errors are covered. Skewed or heavy-tailed u_g/e_ig, which are known to matter for few-cluster inference, are not.\n- **Heterogeneity**: the design has a homoskedastic random intercept and a single fixed size pattern (8,16,32,64). It does not cover heteroskedasticity across clusters, cluster-size–outcome correlation, or other degrees of imbalance. Results may depend strongly on the dominant 64-observation cluster.\n- **Regressors**: only the mean (intercept-only model) is studied. Regression slopes, leverage and fixed effects are not covered.\n- **Other weights / variants**: only Rademacher weights, the unrestricted (non-null-imposed) WCB-t, and the symmetric percentile-t interval with numpy's linear-interpolation quantile are studied. Webb 6-point weights, restricted WCB (WCR), enumeration of all 2^G weight vectors at G = 5, CR2/CR3 (bias-reduced) estimators, and other degrees-of-freedom corrections are not evaluated. Results for the WCB at G = 5 are specific to these choices.\n- G ∈ {5, 10, 30} only; the location of the transition between 10 and 30 is not resolved.\n- The single 2.46-SE deviation between the MC and exact CR0 bias (G5_icc0.2) is reported, not removed. We read it as MC noise in a skewed estimator (see `out/state/checks.md`).\nestimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.0,0.7805,0.009255262016820486,0.6616434596045324,0.12968375504872767,2000\ncr1,C1,5,0.0,0.9115,0.006350895606133045,0.8270543245056654,0.2053873084131136,2000\nwcb,C1,5,0.0,0.855,0.007873214083206426,,0.24887049821365717,2000\ncr0,C2,5,0.2,0.721,0.010028933143659899,0.5313958571125164,0.34226817384823977,2000\ncr1,C2,5,0.2,0.8845,0.007147018609182434,0.6642448213906453,0.5420689658141673,2000\nwcb,C2,5,0.2,0.854,0.007895695029571494,,0.9061312200606192,2000\ncr0,C3,5,0.5,0.717,0.010072512099769353,0.48335023384407516,0.4988937266037328,2000\ncr1,C3,5,0.5,0.8755,0.007382403064043579,0.6041877923050938,0.7901254837417955,2000\nwcb,C3,5,0.5,0.849,0.008006216334823835,,1.3624621157327816,2000\ncr0,C4,10,0.0,0.8965,0.006811304941052046,0.8558047169939658,0.10685157692463605,2000\ncr1,C4,10,0.0,0.9435,0.005162739098579358,0.9508941299932954,0.12999492086527678,2000\nwcb,C4,10,0.0,0.936,0.00547284204047586,,0.14486128327147552,2000\ncr0,C5,10,0.2,0.857,0.007827866886962246,0.7624366224508259,0.3013090672758269,2000\ncr1,C5,10,0.2,0.9155,0.006219314672855845,0.8471518027231398,0.36657061583787093,2000\nwcb,C5,10,0.2,0.9295,0.005724061058374553,,0.46023383942186563,2000\ncr0,C6,10,0.5,0.853,0.007918049002121673,0.7737432482368367,0.46142207182836037,2000\ncr1,C6,10,0.5,0.9065,0.006509905913298595,0.859714720263152,0.5613630368331044,2000\nwcb,C6,10,0.5,0.9325,0.005609979946488223,,0.7220840148315424,2000\ncr0,C7,30,0.0,0.9275,0.005798437289477226,0.943796503270819,0.06396913625447695,2000\ncr1,C7,30,0.0,0.94,0.005310367218940704,0.9763412102801576,0.06789192490779818,2000\nwcb,C7,30,0.0,0.943,0.005184158562389852,,0.06964679151269985,2000\ncr0,C8,30,0.2,0.921,0.006031542091372652,0.9313668684580917,0.19630299136684284,2000\ncr1,C8,30,0.2,0.935,0.005512485827646179,0.9634829673704397,0.20834090827857807,2000\nwcb,C8,30,0.2,0.946,0.005053909377897473,,0.2220803814359477,2000\ncr0,C9,30,0.5,0.9165,0.006185780063985464,0.9252598675851053,0.29923728217350937,2000\ncr1,C9,30,0.5,0.93,0.005705260730238364,0.9571653802604538,0.3175874535825968,2000\nwcb,C9,30,0.5,0.9425,0.005205465877325487,,0.3381330862468605,2000\nstep,rule,n_before,n_after,n_removed,rationale\n1,none: all design cells x R replications simulated,18000,18000,0,No filtering; every replication of every cell is analysed (9 cells x 2000)\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json\nverify_exact.py\nverify_wcb.py\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","is_error":false}]},"uuid":"2ef35ba1-05f9-4b82-a3f8-f0fdd0833d62","timestamp":"2026-10-30T05:41:40.187Z","toolUseResult":{"stdout":"\"\"\"T2-simulation: finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t CIs for a mean.\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/design.csv; writes out/results.json, out/table1.csv, out/figure1.png.\nRandomness: one numpy default_rng(seed) per cell (seed from design.csv). Per replication, draws in\nfixed order: u (G normals), e (N normals), W (B x G Rademacher via rng.integers(0,2)).\n\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\nDATA = os.path.join(ROOT, \"data\", \"design.csv\")\nOUT = os.path.join(ROOT, \"out\")\nEST = [\"cr0\", \"cr1\", \"wcb\"]\n\n\ndef simulate_cell(row):\n G, icc, N, R, B, mu = int(row.G), float(row.icc), int(row.N), int(row.R), int(row.B), float(row.mu)\n sizes = np.array([int(x) for x in row.cluster_sizes.split(\"|\")])\n assert len(sizes) == G and sizes.sum() == N\n gid = np.repeat(np.arange(G), sizes)\n var_exact = (icc * np.sum(sizes.astype(float) ** 2) + (1 - icc) * N) / N ** 2\n tcrit = stats.t.ppf(0.975, G - 1)\n zcrit = 1.96\n adj = G / (G - 1)\n rng = np.random.default_rng(int(row.seed))\n res = {k: np.empty(R) for k in [\"ybar\", \"v0\", \"v1\", \"q\", \"v_iid\"]}\n n_degenerate = 0\n for r in range(R):\n u = rng.normal(0.0, np.sqrt(icc), G) # scale 0 when icc=0 -> u = 0\n e = rng.normal(0.0, np.sqrt(1 - icc), N)\n y = mu + u[gid] + e\n ybar = y.mean()\n ehat = y - ybar\n S = np.bincount(gid, weights=ehat, minlength=G) # cluster residual sums\n v0 = np.sum(S ** 2) / N ** 2\n v1 = adj * v0\n # wild cluster bootstrap-t (unrestricted, Rademacher), vectorised over B\n W = rng.integers(0, 2, size=(B, G)) * 2 - 1\n d = (W * S).sum(axis=1) / N # ybar* - ybar\n Sstar = W * S - np.outer(d, sizes) # cluster sums of bootstrap residuals\n v1s = adj * np.sum(Sstar ** 2, axis=1) / N ** 2\n if np.any(v1s <= 0):\n n_degenerate += int(np.sum(v1s <= 0))\n v1s = np.where(v1s <= 0, np.nan, v1s)\n tabs = np.abs(d) / np.sqrt(v1s)\n q = np.nanquantile(tabs, 0.95) # numpy default (linear interpolation)\n res[\"ybar\"][r], res[\"v0\"][r], res[\"v1\"][r], res[\"q\"][r] = ybar, v0, v1, q\n res[\"v_iid\"][r] = np.var(y, ddof=1) / N # naive i.i.d. baseline\n hw = {\"cr0\": zcrit * np.sqrt(res[\"v0\"]), \"cr1\": tcrit * np.sqrt(res[\"v1\"]),\n \"wcb\": res[\"q\"] * np.sqrt(res[\"v1\"]), \"iid\": zcrit * np.sqrt(res[\"v_iid\"])}\n out = {\"var_exact\": var_exact, \"n_degenerate\": n_degenerate, \"R\": R}\n for k, h in hw.items():\n cov = np.abs(res[\"ybar\"] - mu) <= h\n out[k] = {\"coverage\": float(cov.mean()), \"hw\": float(h.mean()), \"ind\": cov.astype(float)}\n for k, v in [(\"cr0\", res[\"v0\"]), (\"cr1\", res[\"v1\"])]:\n out[k][\"rel_bias\"] = float(v.mean() / var_exact)\n out[k][\"rel_bias_mcse\"] = float(v.std(ddof=1) / np.sqrt(R) / var_exact)\n out[\"mc_var_ybar_ratio\"] = float(np.var(res[\"ybar\"], ddof=1) / var_exact)\n out[\"mean_ybar\"] = float(res[\"ybar\"].mean())\n return out\n\n\ndef main():\n d = pd.read_csv(DATA)\n R_all, B_all = d.R.unique(), d.B.unique()\n assert len(R_all) == 1 and len(B_all) == 1\n R, B = int(R_all[0]), int(B_all[0])\n cov, se, rb, rb_se, base, chk = {}, {}, {}, {}, {}, {}\n rows, issues = [], []\n n_deg = 0\n ind_g5 = {k: [] for k in EST}\n for row in d.itertuples(index=False):\n o = simulate_cell(row)\n n_deg += o[\"n_degenerate\"]\n tag = f\"G{int(row.G)}_icc{float(row.icc):.1f}\"\n for k in EST:\n key = f\"{k}_{tag}\"\n p = o[k][\"coverage\"]\n cov[key] = p\n se[key] = float(np.sqrt(p * (1 - p) / o[\"R\"]))\n if k != \"wcb\":\n rb[key] = o[k][\"rel_bias\"]\n rb_se[key] = o[k][\"rel_bias_mcse\"]\n rows.append({\"estimator\": k, \"cell_id\": row.cell_id, \"G\": int(row.G), \"icc\": float(row.icc),\n \"coverage\": p, \"mc_se_coverage\": se[key],\n \"rel_bias_var\": o[k].get(\"rel_bias\", None), \"mean_ci_halfwidth\": o[k][\"hw\"], \"R\": o[\"R\"]})\n if int(row.G) == 5:\n for k in EST:\n ind_g5[k].append(o[k][\"ind\"])\n base[f\"iid_{tag}\"] = o[\"iid\"][\"coverage\"]\n chk[tag] = {\"mc_var_ybar_over_exact\": o[\"mc_var_ybar_ratio\"], \"mean_ybar\": o[\"mean_ybar\"]}\n print(f\"{row.cell_id} {tag}: \" + \", \".join(f\"{k}={cov[f'{k}_{tag}']:.4f}\" for k in EST))\n table = pd.DataFrame(rows)\n table.to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n failure = [k for k, p in cov.items() if p < 0.90]\n nominal = [k for k, p in cov.items() if abs(p - 0.95) <= 2 * se[k]]\n g5 = {k: np.mean([cov[f\"{k}_G5_icc{i:.1f}\"] for i in (0.0, 0.2, 0.5)]) for k in EST}\n best = max(g5, key=g5.get)\n # paired MC SE of the difference in average G=5 coverage between best and each other procedure\n # (same replications -> paired; cells independent -> variance of mean over 3 cells = sum/9)\n g5_diff = {}\n for k in EST:\n if k == best:\n continue\n cell_vars = [np.var(a - b, ddof=1) / len(a) for a, b in zip(ind_g5[best], ind_g5[k])]\n g5_diff[f\"{best}_minus_{k}\"] = {\"diff\": float(g5[best] - g5[k]), \"mc_se\": float(np.sqrt(sum(cell_vars)) / len(cell_vars))}\n near = [k for k, p in cov.items() if abs(p - 0.90) <= 2 * se[k]]\n if 5 in d.G.values:\n issues.append({\"issue\": \"With G=5 and Rademacher weights only 2^5=32 distinct weight vectors exist (16 distinct |t*| values, as |t*| is invariant to w -> -w); B=399 draws therefore repeat these few values and the 0.95 quantile of |t*| is coarse.\",\n \"handling\": \"Kept as specified (B=399, Rademacher, random draws, numpy linear-interpolation quantile); discussed in report as a known feature of WCB with very few clusters.\"})\n if n_deg:\n issues.append({\"issue\": f\"{n_deg} bootstrap draws had non-positive V_CR1*\", \"handling\": \"Excluded those draws from the |t*| quantile (nan-quantile).\"})\n results = {\n \"task_id\": \"T2-simulation\", \"R\": R, \"B\": B, \"n_cells\": int(len(d)),\n \"coverage\": cov, \"mc_se_coverage\": se, \"rel_bias_var\": rb,\n \"failure_cells\": failure, \"n_failure_cells\": len(failure), \"nominal_cells\": nominal,\n \"best_procedure_small_G\": best,\n \"feasibility\": \"complete\", \"feasibility_reason\": None, \"data_issues\": issues,\n \"n_input_rows\": {\"design.csv\": int(len(d))},\n \"n_analysed\": int(len(d) * R), \"random_seed\": int(d.loc[d.cell_id == \"C1\", \"seed\"].iloc[0]),\n # supplementary keys\n \"avg_coverage_G5\": {k: float(v) for k, v in g5.items()},\n \"mc_se_rel_bias_var\": rb_se,\n \"avg_coverage_G5_paired_diff\": g5_diff,\n \"cells_within_2se_of_failure_line\": near,\n \"baseline_iid_coverage\": base,\n \"check_mc_var_ybar_over_exact\": chk,\n \"n_degenerate_bootstrap_draws\": int(n_deg),\n \"wcb_quantile_method\": \"numpy.quantile linear interpolation (type 7) of |t*_b|, b=1..B\",\n \"seeds_by_cell\": {r.cell_id: int(r.seed) for r in d.itertuples(index=False)},\n }\n with open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n json.dump(results, f, indent=2)\n\n # figure\n fig, axes = plt.subplots(1, 3, figsize=(13, 4.2), sharey=True)\n Gs = sorted(d.G.unique())\n style = {\"cr0\": (\"o-\", \"CR0 (z)\"), \"cr1\": (\"s-\", \"CR1 (t, G-1)\"), \"wcb\": (\"^-\", \"WCB-t Rademacher\")}\n for ax, icc in zip(axes, sorted(d.icc.unique())):\n for k in EST:\n p = np.array([cov[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n s = np.array([se[f\"{k}_G{g}_icc{icc:.1f}\"] for g in Gs])\n ax.errorbar(Gs, p, yerr=1.96 * s, fmt=style[k][0], capsize=3, label=style[k][1])\n ax.axhline(0.95, color=\"k\", ls=\"--\", lw=1, label=\"nominal 0.95\")\n ax.axhline(0.90, color=\"r\", ls=\":\", lw=1, label=\"failure line 0.90\")\n ax.set_xscale(\"log\"); ax.minorticks_off(); ax.set_xticks(Gs); ax.set_xticklabels(Gs)\n ax.set_title(f\"ICC = {icc:.1f}\"); ax.set_xlabel(\"number of clusters G\")\n axes[0].set_ylabel(\"coverage (R=2000; bars ±1.96 MC SE)\")\n axes[0].legend(loc=\"lower right\", fontsize=8)\n fig.tight_layout()\n fig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n print(\"failure cells:\", failure)\n print(\"best procedure at G=5:\", best)\n\n\nif __name__ == \"__main__\":\n main()\n# Finite-sample coverage of CR0, CR1 and wild-cluster-bootstrap-t intervals for a mean with few clusters\n\nAll numbers below are produced by `out/analysis.py` (run: `~/wp29/venv/bin/python out/analysis.py`, ≈2 s) and are cited by their key in `out/results.json`. Full per-cell values are in `out/table1.csv`; the figure is `out/figure1.png`.\n\n## Question\nWhen N observations are grouped in few (G = 5, 10, 30) unbalanced clusters with intra-cluster correlation ICC ∈ {0, 0.2, 0.5}, what is the actual coverage of three nominal-95% cluster-robust intervals for the mean μ (CR0 with z critical value; CR1 with t_{G−1}; unrestricted Rademacher wild cluster bootstrap-t, WCB), how biased are the CR0/CR1 variance estimators relative to the exact Var(ȳ), and in which (procedure, cell) pairs does coverage fall below 0.90?\n\n## Data and exclusions\nNo observed data. The only input is `data/design.csv` (`n_input_rows`: 9 rows; SHA-256 recorded in `out/state/data_audit.md`): 9 cells, cluster sizes 8,16,32,64 repeated (N = 128, 264, 864), R = 2000 (`R`), B = 399 (`B`), one seed per cell (C1 seed = `random_seed`; all seeds in `seeds_by_cell`). The audit found no missing values, duplicates or inconsistencies (sizes count = G, sum = N). No exclusions: all `n_cells` = 9 cells × 2000 replications = `n_analysed` = 18000 replications were simulated and analysed (`out/exclusions.csv`, one no-op step). `feasibility` = \"complete\". One design feature is recorded in `data_issues`: at G = 5 Rademacher weights take only 32 distinct values (16 distinct |t*|), so the bootstrap critical value is coarse; kept as specified. No bootstrap draw had a non-positive variance (`n_degenerate_bootstrap_draws` = 0).\n\n## Method\nPer replication (numpy `default_rng(cell seed)`, draws in fixed order u, e, W): y_ig = μ + u_g + e_ig, u_g ~ N(0, ICC), e_ig ~ N(0, 1−ICC), μ = 0. With ê = y − ȳ and S_g = Σ_i ê_ig: V̂_CR0 = Σ S_g²/N², CI ȳ ± 1.96√V̂_CR0; V̂_CR1 = G/(G−1)·V̂_CR0, CI ȳ ± t_{0.975,G−1}√V̂_CR1; WCB: B×G Rademacher matrix W, ȳ*−ȳ = Σ_g w_g S_g/N, bootstrap cluster residual sums w_g S_g − n_g(ȳ*−ȳ), V̂*_CR1 from these, t*_b = (ȳ*−ȳ)/√V̂*_CR1, q = 0.95 quantile of |t*| (numpy linear interpolation, `wcb_quantile_method`), CI ȳ ± q√V̂_CR1. Coverage = share of R intervals containing μ; MC SE = √(p̂(1−p̂)/R); relative bias = mean(V̂)/Var(ȳ) with Var(ȳ) = [ICC Σn_g² + (1−ICC)N]/N². Failure regime: coverage < 0.90; nominal-consistent: |p̂ − 0.95| ≤ 2 MC SE. Baseline (P2): the naive i.i.d. interval ȳ ± 1.96·s/√N on the same draws (`baseline_iid_coverage`).\n\nVerification (`out/state/checks.md`): byte-identical re-run; vectorised WCB matches a brute-force construction of y* (diff 7e-15); MC relative bias of CR0 matches the closed-form E[V̂_CR0]/Var(ȳ) within 2 MC SE in 8/9 cells (z = +2.46 in G5_icc0.2); MC Var(ȳ)/exact in [0.93, 1.06] (`check_mc_var_ybar_over_exact`).\n\n## Results\nCoverage (`coverage`, MC SE in `mc_se_coverage`):\n\n| G | ICC | CR0 | CR1 | WCB | naive i.i.d. baseline |\n|---|---|---|---|---|---|\n| 5 | 0.0 | 0.781 | 0.912 | 0.855 | 0.941 |\n| 5 | 0.2 | 0.721 | 0.885 | 0.854 | 0.460 |\n| 5 | 0.5 | 0.717 | 0.876 | 0.849 | 0.287 |\n| 10 | 0.0 | 0.897 | 0.944 | 0.936 | 0.957 |\n| 10 | 0.2 | 0.857 | 0.916 | 0.930 | 0.488 |\n| 10 | 0.5 | 0.853 | 0.907 | 0.933 | 0.313 |\n| 30 | 0.0 | 0.928 | 0.940 | 0.943 | 0.952 |\n| 30 | 0.2 | 0.921 | 0.935 | 0.946 | 0.485 |\n| 30 | 0.5 | 0.917 | 0.930 | 0.943 | 0.299 |\n\n- **Failure regimes** (`failure_cells`, `n_failure_cells` = 11): CR0 at every G = 5 and G = 10 cell (6 pairs); WCB at all three G = 5 cells; CR1 at G = 5 with ICC = 0.2 and 0.5. No procedure fails at G = 30.\n- **Nominal-consistent pairs** (`nominal_cells`, 5 pairs): cr1_G10_icc0.0, cr1_G30_icc0.0, wcb_G30_icc0.0, wcb_G30_icc0.2, wcb_G30_icc0.5. CR0 is never consistent with 0.95, even at G = 30 (0.917–0.928).\n- **Best at G = 5** (`best_procedure_small_G` = \"cr1\"): average G = 5 coverage 0.891 for CR1, 0.853 for WCB, 0.740 for CR0 (`avg_coverage_G5`). The CR1 − WCB difference is 0.038 with paired MC SE 0.0035 (`avg_coverage_G5_paired_diff`), so the ranking is not a Monte Carlo artefact. At G = 10 with ICC > 0, WCB covers better than CR1 (0.930/0.933 vs 0.916/0.907).\n- **Variance bias** (`rel_bias_var`): both sandwich estimators are biased downward, most at small G and high ICC. CR0: 0.66, 0.53, 0.48 at G = 5 (ICC 0, 0.2, 0.5); 0.86, 0.76, 0.77 at G = 10; 0.94, 0.93, 0.93 at G = 30. CR1: 0.83, 0.66, 0.60 at G = 5; 0.95, 0.85, 0.86 at G = 10; 0.98, 0.96, 0.96 at G = 30. The unbalanced sizes (one 64-observation cluster dominates) make the bias much worse than the balanced-cluster factor (G−1)/G.\n- **Baseline**: the naive i.i.d. interval is fine at ICC = 0 but covers only 0.29–0.49 when ICC > 0 (`baseline_iid_coverage`), whatever G is. All three cluster-robust procedures improve on it there.\n- Mean CI half-widths are in `table1.csv` (`mean_ci_halfwidth`). At G = 5 the WCB interval is on average *wider* than CR1 but still covers less. One plausible explanation (not tested here) is that q varies a lot across replications, because the bootstrap distribution has only 16 distinct |t*| values.\n\n## Uncertainty\nEach coverage is a binomial proportion over R = 2000 independent replications. Its MC SE (`mc_se_coverage`) is 0.005–0.010, so a 95% MC interval is about ±0.010–0.020. The figure shows ±1.96 MC SE bars. Classifications near the 0.90 threshold are therefore fragile. cr1_G5_icc0.0 (0.912), cr0_G10_icc0.0 (0.897) and cr1_G10_icc0.5 (0.907) are within 2 MC SE of 0.90 (`cells_within_2se_of_failure_line`); a different seed could move them across the line. The \"nominal-consistent\" label is a 2-SE screen, not a test with multiplicity control: across 27 pairs, some misclassification is expected. With R = 2000 we cannot resolve coverage differences much smaller than ≈0.02. The relative-bias estimates have MC SE 0.007–0.016 (`mc_se_rel_bias_var`). Because V̂ is right-skewed at small G, the normal approximation behind that SE is rough, which matches the one 2.46-SE discrepancy from the exact value in G5_icc0.2. The paired SE for the G = 5 ranking uses the fact that all procedures are evaluated on the same replications. The bootstrap critical value adds its own simulation noise (B = 399), and that noise is included in the WCB coverage estimate.\n\n## Limitations and open issues\n- **Distributions**: only Gaussian random effects and errors are covered. Skewed or heavy-tailed u_g/e_ig, which are known to matter for few-cluster inference, are not.\n- **Heterogeneity**: the design has a homoskedastic random intercept and a single fixed size pattern (8,16,32,64). It does not cover heteroskedasticity across clusters, cluster-size–outcome correlation, or other degrees of imbalance. Results may depend strongly on the dominant 64-observation cluster.\n- **Regressors**: only the mean (intercept-only model) is studied. Regression slopes, leverage and fixed effects are not covered.\n- **Other weights / variants**: only Rademacher weights, the unrestricted (non-null-imposed) WCB-t, and the symmetric percentile-t interval with numpy's linear-interpolation quantile are studied. Webb 6-point weights, restricted WCB (WCR), enumeration of all 2^G weight vectors at G = 5, CR2/CR3 (bias-reduced) estimators, and other degrees-of-freedom corrections are not evaluated. Results for the WCB at G = 5 are specific to these choices.\n- G ∈ {5, 10, 30} only; the location of the transition between 10 and 30 is not resolved.\n- The single 2.46-SE deviation between the MC and exact CR0 bias (G5_icc0.2) is reported, not removed. We read it as MC noise in a skewed estimator (see `out/state/checks.md`).\nestimator,cell_id,G,icc,coverage,mc_se_coverage,rel_bias_var,mean_ci_halfwidth,R\ncr0,C1,5,0.0,0.7805,0.009255262016820486,0.6616434596045324,0.12968375504872767,2000\ncr1,C1,5,0.0,0.9115,0.006350895606133045,0.8270543245056654,0.2053873084131136,2000\nwcb,C1,5,0.0,0.855,0.007873214083206426,,0.24887049821365717,2000\ncr0,C2,5,0.2,0.721,0.010028933143659899,0.5313958571125164,0.34226817384823977,2000\ncr1,C2,5,0.2,0.8845,0.007147018609182434,0.6642448213906453,0.5420689658141673,2000\nwcb,C2,5,0.2,0.854,0.007895695029571494,,0.9061312200606192,2000\ncr0,C3,5,0.5,0.717,0.010072512099769353,0.48335023384407516,0.4988937266037328,2000\ncr1,C3,5,0.5,0.8755,0.007382403064043579,0.6041877923050938,0.7901254837417955,2000\nwcb,C3,5,0.5,0.849,0.008006216334823835,,1.3624621157327816,2000\ncr0,C4,10,0.0,0.8965,0.006811304941052046,0.8558047169939658,0.10685157692463605,2000\ncr1,C4,10,0.0,0.9435,0.005162739098579358,0.9508941299932954,0.12999492086527678,2000\nwcb,C4,10,0.0,0.936,0.00547284204047586,,0.14486128327147552,2000\ncr0,C5,10,0.2,0.857,0.007827866886962246,0.7624366224508259,0.3013090672758269,2000\ncr1,C5,10,0.2,0.9155,0.006219314672855845,0.8471518027231398,0.36657061583787093,2000\nwcb,C5,10,0.2,0.9295,0.005724061058374553,,0.46023383942186563,2000\ncr0,C6,10,0.5,0.853,0.007918049002121673,0.7737432482368367,0.46142207182836037,2000\ncr1,C6,10,0.5,0.9065,0.006509905913298595,0.859714720263152,0.5613630368331044,2000\nwcb,C6,10,0.5,0.9325,0.005609979946488223,,0.7220840148315424,2000\ncr0,C7,30,0.0,0.9275,0.005798437289477226,0.943796503270819,0.06396913625447695,2000\ncr1,C7,30,0.0,0.94,0.005310367218940704,0.9763412102801576,0.06789192490779818,2000\nwcb,C7,30,0.0,0.943,0.005184158562389852,,0.06964679151269985,2000\ncr0,C8,30,0.2,0.921,0.006031542091372652,0.9313668684580917,0.19630299136684284,2000\ncr1,C8,30,0.2,0.935,0.005512485827646179,0.9634829673704397,0.20834090827857807,2000\nwcb,C8,30,0.2,0.946,0.005053909377897473,,0.2220803814359477,2000\ncr0,C9,30,0.5,0.9165,0.006185780063985464,0.9252598675851053,0.29923728217350937,2000\ncr1,C9,30,0.5,0.93,0.005705260730238364,0.9571653802604538,0.3175874535825968,2000\nwcb,C9,30,0.5,0.9425,0.005205465877325487,,0.3381330862468605,2000\nstep,rule,n_before,n_after,n_removed,rationale\n1,none: all design cells x R replications simulated,18000,18000,0,No filtering; every replication of every cell is analysed (9 cells x 2000)\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json\nverify_exact.py\nverify_wcb.py\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","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ce92aedf-32da-4f38-8183-83b7f260bb22","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"5ef3a12b474347edf563e95b30ee85c03ecc7261f68a45e9a63075b0ad4af60d","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01R2Kn1DuBddUEKqSrbpocZS","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/table1.csv; cat out/exclusions.csv; ls out/state; cat data/design.csv","description":"Read code, report, table"}}]}}22{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"1596db18-21be-4c26-b2bd-f50c7d4846d8","timestamp":"2026-10-30T05:41:40.192Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"de749b8b-98ad-48b9-a42b-abbf30e9a90d","keep":4,"tail":["5ef3a12b474347edf563e95b30ee85c03ecc7261f68a45e9a63075b0ad4af60d","2d74927dda7e565c7ad34c97f7d828589c5a01adbeb49bb30881e64d4fa6daec"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"48fd31102d617e9f296e4b2ad5e84d78295e5543e6abca5f5878f8d55405eb0a"}23{"type":"last-prompt","lastPrompt":"Review","leafUuid":"2ef35ba1-05f9-4b82-a3f8-f0fdd0833d62","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}24{"type":"atis-latch","atis":"","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}25{"parentUuid":"2ef35ba1-05f9-4b82-a3f8-f0fdd0833d62","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPr8VAmG7oXEGTnivA","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":10090,"cache_read_input_tokens":10574,"output_tokens":985,"output_tokens_details":{"thinking_tokens":667},"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":10090},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":5967,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtPqvLf3DkShiaXyeE2","requestRef":"1596db18-21be-4c26-b2bd-f50c7d4846d8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1e66a84f-1a99-459c-9c55-b2b1c8f108c4","timestamp":"2026-10-30T05:41:47.800Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"1e66a84f-1a99-459c-9c55-b2b1c8f108c4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtPr8VAmG7oXEGTnivA","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HHuQPJJhfJ53vpqoGzSXHj","name":"Bash","input":{"command":"rm -rf /tmp/rt20 && mkdir -p /tmp/rt20/out && cp -r data /tmp/rt20/ && cp out/analysis.py /tmp/rt20/out/ && cd /tmp/rt20 && time ~/wp29/venv/bin/python out/analysis.py && ~/wp29/venv/bin/python -c \"\nimport json\na=json.load(open('/tmp/rt20/out/results.json'));b=json.load(open('$OLDPWD/out/results.json'))\nprint(a==b)\n\" && cmp out/table1.csv $OLDPWD/out/table1.csv && echo tableok; cat $OLDPWD/out/state/checks.md | head -60","description":"Rerun analysis in scratch 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":10090,"cache_read_input_tokens":10574,"output_tokens":985,"output_tokens_details":{"thinking_tokens":667},"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":10090},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtPqvLf3DkShiaXyeE2","requestRef":"1596db18-21be-4c26-b2bd-f50c7d4846d8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1b51b05a-0448-4ca8-b95a-299601eabdd9","timestamp":"2026-10-30T05:41:50.050Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"1b51b05a-0448-4ca8-b95a-299601eabdd9","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HHuQPJJhfJ53vpqoGzSXHj","type":"tool_result","content":"C1 G5_icc0.0: cr0=0.7805, cr1=0.9115, wcb=0.8550\nC2 G5_icc0.2: cr0=0.7210, cr1=0.8845, wcb=0.8540\nC3 G5_icc0.5: cr0=0.7170, cr1=0.8755, wcb=0.8490\nC4 G10_icc0.0: cr0=0.8965, cr1=0.9435, wcb=0.9360\nC5 G10_icc0.2: cr0=0.8570, cr1=0.9155, wcb=0.9295\nC6 G10_icc0.5: cr0=0.8530, cr1=0.9065, wcb=0.9325\nC7 G30_icc0.0: cr0=0.9275, cr1=0.9400, wcb=0.9430\nC8 G30_icc0.2: cr0=0.9210, cr1=0.9350, wcb=0.9460\nC9 G30_icc0.5: cr0=0.9165, cr1=0.9300, wcb=0.9425\nfailure cells: ['cr0_G5_icc0.0', 'wcb_G5_icc0.0', 'cr0_G5_icc0.2', 'cr1_G5_icc0.2', 'wcb_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.5', 'wcb_G5_icc0.5', 'cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5']\nbest procedure at G=5: cr1\n~/wp29/venv/bin/python out/analysis.py 1,96s user 0,06s system 99% cpu 2,023 total\nTrue\ntableok\n# Verification checks (P4)\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run (deleted results.json, table1.csv, figure1.png; re-ran analysis.py) reproduces byte-identical results.json and table1.csv | PASS |\n| 2 | Figure-only edit (minor ticks) re-run: results.json byte-identical | PASS |\n| 3 | table1.csv has 27 rows; rel_bias_var empty for all wcb rows | PASS |\n| 4 | coverage & mc_se_coverage have 27 keys; rel_bias_var 18 keys | PASS |\n| 5 | all MC SE > 0; all coverages in [0,1]; all mean half-widths > 0 | PASS |\n| 6 | n_failure_cells == len(failure_cells); failure_cells == {coverage<0.90} recomputed | PASS |\n| 7 | n_analysed == n_cells × R = 18000; exclusions ledger 18000 − 0 = 18000 | PASS |\n| 8 | Exact E[V̂_CR0]/Var(ȳ) (closed-form trace computation, state/verify_exact.py) vs MC estimate: z-scores −0.70…+1.40 in 8 cells, +2.46 in G5_icc0.2 (one of 9 beyond 2 MC SE; V̂ is right-skewed at G=5 so the normal MC approximation is rough; no implementation error indicated since the other 8 agree and CR1/CR0 ratio = G/(G−1) exactly) | PASS (with note) |\n| 9 | MC Var(ȳ)/exact Var(ȳ) in [0.93, 1.06] in all cells (check_mc_var_ybar_over_exact), consistent with sampling error of a variance from R=2000 (SE≈0.032); mean ȳ ≈ 0 | PASS |\n| 10 | Vectorised WCB t* equals brute-force explicit y* construction (state/verify_wcb.py): max abs diff 7e-15 | PASS |\n| 11 | Baseline (naive i.i.d. z-interval) behaves as expected: ≈0.95 at ICC=0, 0.29–0.49 with ICC>0 — magnitudes coherent with cluster methods improving on baseline when ICC>0 | PASS |\n| 12 | No degenerate bootstrap draws (n_degenerate_bootstrap_draws = 0) | PASS |\n| 13 | Runtime ≈ 2 s (< 600 s limit) | PASS |\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0020","is_error":false}]},"uuid":"1aea3699-8afc-4b20-a74b-263c37c6c07e","timestamp":"2026-10-30T05:41:52.145Z","toolUseResult":{"stdout":"C1 G5_icc0.0: cr0=0.7805, cr1=0.9115, wcb=0.8550\nC2 G5_icc0.2: cr0=0.7210, cr1=0.8845, wcb=0.8540\nC3 G5_icc0.5: cr0=0.7170, cr1=0.8755, wcb=0.8490\nC4 G10_icc0.0: cr0=0.8965, cr1=0.9435, wcb=0.9360\nC5 G10_icc0.2: cr0=0.8570, cr1=0.9155, wcb=0.9295\nC6 G10_icc0.5: cr0=0.8530, cr1=0.9065, wcb=0.9325\nC7 G30_icc0.0: cr0=0.9275, cr1=0.9400, wcb=0.9430\nC8 G30_icc0.2: cr0=0.9210, cr1=0.9350, wcb=0.9460\nC9 G30_icc0.5: cr0=0.9165, cr1=0.9300, wcb=0.9425\nfailure cells: ['cr0_G5_icc0.0', 'wcb_G5_icc0.0', 'cr0_G5_icc0.2', 'cr1_G5_icc0.2', 'wcb_G5_icc0.2', 'cr0_G5_icc0.5', 'cr1_G5_icc0.5', 'wcb_G5_icc0.5', 'cr0_G10_icc0.0', 'cr0_G10_icc0.2', 'cr0_G10_icc0.5']\nbest procedure at G=5: cr1\n~/wp29/venv/bin/python out/analysis.py 1,96s user 0,06s system 99% cpu 2,023 total\nTrue\ntableok\n# Verification checks (P4)\n| # | check | outcome |\n|---|---|---|\n| 1 | Clean re-run (deleted results.json, table1.csv, figure1.png; re-ran analysis.py) reproduces byte-identical results.json and table1.csv | PASS |\n| 2 | Figure-only edit (minor ticks) re-run: results.json byte-identical | PASS |\n| 3 | table1.csv has 27 rows; rel_bias_var empty for all wcb rows | PASS |\n| 4 | coverage & mc_se_coverage have 27 keys; rel_bias_var 18 keys | PASS |\n| 5 | all MC SE > 0; all coverages in [0,1]; all mean half-widths > 0 | PASS |\n| 6 | n_failure_cells == len(failure_cells); failure_cells == {coverage<0.90} recomputed | PASS |\n| 7 | n_analysed == n_cells × R = 18000; exclusions ledger 18000 − 0 = 18000 | PASS |\n| 8 | Exact E[V̂_CR0]/Var(ȳ) (closed-form trace computation, state/verify_exact.py) vs MC estimate: z-scores −0.70…+1.40 in 8 cells, +2.46 in G5_icc0.2 (one of 9 beyond 2 MC SE; V̂ is right-skewed at G=5 so the normal MC approximation is rough; no implementation error indicated since the other 8 agree and CR1/CR0 ratio = G/(G−1) exactly) | PASS (with note) |\n| 9 | MC Var(ȳ)/exact Var(ȳ) in [0.93, 1.06] in all cells (check_mc_var_ybar_over_exact), consistent with sampling error of a variance from R=2000 (SE≈0.032); mean ȳ ≈ 0 | PASS |\n| 10 | Vectorised WCB t* equals brute-force explicit y* construction (state/verify_wcb.py): max abs diff 7e-15 | PASS |\n| 11 | Baseline (naive i.i.d. z-interval) behaves as expected: ≈0.95 at ICC=0, 0.29–0.49 with ICC>0 — magnitudes coherent with cluster methods improving on baseline when ICC>0 | PASS |\n| 12 | No degenerate bootstrap draws (n_degenerate_bootstrap_draws = 0) | PASS |\n| 13 | Runtime ≈ 2 s (< 600 s limit) | PASS |","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0020","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1b51b05a-0448-4ca8-b95a-299601eabdd9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}28{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"505d574c9c24dda77d066d5bbd90bd819d98d529650d47b7d59c762761d0d81a","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01HHuQPJJhfJ53vpqoGzSXHj","name":"Bash","input":{"command":"rm -rf /tmp/rt20 && mkdir -p /tmp/rt20/out && cp -r data /tmp/rt20/ && cp out/analysis.py /tmp/rt20/out/ && cd /tmp/rt20 && time ~/wp29/venv/bin/python out/analysis.py && ~/wp29/venv/bin/python -c \"\nimport json\na=json.load(open('/tmp/rt20/out/results.json'));b=json.load(open('$OLDPWD/out/results.json'))\nprint(a==b)\n\" && cmp out/table1.csv $OLDPWD/out/table1.csv && echo tableok; cat $OLDPWD/out/state/checks.md | head -60","description":"Rerun analysis in scratch and compare"}}]}}29{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"d57e298e-cdba-4fef-a51d-105896ee4348","timestamp":"2026-10-30T05:41:52.147Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"1596db18-21be-4c26-b2bd-f50c7d4846d8","keep":6,"tail":["505d574c9c24dda77d066d5bbd90bd819d98d529650d47b7d59c762761d0d81a","04eda736664f3d7276d9307d23126926826be4586f65191f089fe82341a676a1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"31be2b27213b73ed517bb1bad8c4ae53c1499b2d5e72d783bd165bd7429be8c9"}30{"parentUuid":"1aea3699-8afc-4b20-a74b-263c37c6c07e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQjJkemsbdYq9QQGbS","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":2475,"cache_read_input_tokens":20664,"output_tokens":579,"output_tokens_details":{"thinking_tokens":130},"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":2475},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1092,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtQj388Z9ZcxDr8nW3S","requestRef":"d57e298e-cdba-4fef-a51d-105896ee4348","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ac239cb9-cf26-4704-88d4-b9b0b32f3d8e","timestamp":"2026-10-30T05:41:54.629Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"ac239cb9-cf26-4704-88d4-b9b0b32f3d8e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtQjJkemsbdYq9QQGbS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014Fvj95pJ1UVtpCd6Vo1M1j","name":"Bash","input":{"command":"cd /tmp && ~/wp29/venv/bin/python -c \"\nimport numpy as np, json\nr=json.load(open('/tmp/rt20/out/results.json'))\nfor G in (5,10,30):\n s=np.array(([8,16,32,64]*8)[:G]);N=s.sum();gid=np.repeat(np.arange(G),s)\n A=np.zeros((G,N));A[gid,np.arange(N)]=1;M=np.eye(N)-1/N\n for icc in (0.0,0.2,0.5):\n Sig=icc*(A.T@A)+(1-icc)*np.eye(N)\n EV=np.trace(A@M@Sig@M@A.T)/N**2; V=(icc*(s**2).sum()+(1-icc)*N)/N**2\n k=f'cr0_G{G}_icc{icc}'; print(k, round(EV/V,4), round(r['rel_bias_var'][k],4), round((r['rel_bias_var'][k]-EV/V)/r['mc_se_rel_bias_var'][k],2))\n\"","description":"Compute exact expected CR0 variance ratio"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2475,"cache_read_input_tokens":20664,"output_tokens":579,"output_tokens_details":{"thinking_tokens":130},"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":2475},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtQj388Z9ZcxDr8nW3S","requestRef":"d57e298e-cdba-4fef-a51d-105896ee4348","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0fcf419f-8217-47b6-83c4-bc2ddd776322","timestamp":"2026-10-30T05:41:57.840Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"0fcf419f-8217-47b6-83c4-bc2ddd776322","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014Fvj95pJ1UVtpCd6Vo1M1j","type":"tool_result","content":"cr0_G5_icc0.0 0.6641 0.6616 -0.19\ncr0_G5_icc0.2 0.4995 0.5314 2.46\ncr0_G5_icc0.5 0.4883 0.4834 -0.42\ncr0_G10_icc0.0 0.8393 0.8558 1.4\ncr0_G10_icc0.2 0.7599 0.7624 0.2\ncr0_G10_icc0.5 0.7544 0.7737 1.37\ncr0_G30_icc0.0 0.9486 0.9438 -0.7\ncr0_G30_icc0.2 0.9267 0.9314 0.54\ncr0_G30_icc0.5 0.9253 0.9253 -0.0\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0020","is_error":false}]},"uuid":"c8376c0e-fcd1-4a12-9c03-4318b48f63e2","timestamp":"2026-10-30T05:41:57.944Z","toolUseResult":{"stdout":"cr0_G5_icc0.0 0.6641 0.6616 -0.19\ncr0_G5_icc0.2 0.4995 0.5314 2.46\ncr0_G5_icc0.5 0.4883 0.4834 -0.42\ncr0_G10_icc0.0 0.8393 0.8558 1.4\ncr0_G10_icc0.2 0.7599 0.7624 0.2\ncr0_G10_icc0.5 0.7544 0.7737 1.37\ncr0_G30_icc0.0 0.9486 0.9438 -0.7\ncr0_G30_icc0.2 0.9267 0.9314 0.54\ncr0_G30_icc0.5 0.9253 0.9253 -0.0","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0020","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"0fcf419f-8217-47b6-83c4-bc2ddd776322","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"7c0502f41071066da5b3861b946b81c224ce7950b8a7dd5a4ac93b71089e3a85","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_014Fvj95pJ1UVtpCd6Vo1M1j","name":"Bash","input":{"command":"cd /tmp && ~/wp29/venv/bin/python -c \"\nimport numpy as np, json\nr=json.load(open('/tmp/rt20/out/results.json'))\nfor G in (5,10,30):\n s=np.array(([8,16,32,64]*8)[:G]);N=s.sum();gid=np.repeat(np.arange(G),s)\n A=np.zeros((G,N));A[gid,np.arange(N)]=1;M=np.eye(N)-1/N\n for icc in (0.0,0.2,0.5):\n Sig=icc*(A.T@A)+(1-icc)*np.eye(N)\n EV=np.trace(A@M@Sig@M@A.T)/N**2; V=(icc*(s**2).sum()+(1-icc)*N)/N**2\n k=f'cr0_G{G}_icc{icc}'; print(k, round(EV/V,4), round(r['rel_bias_var'][k],4), round((r['rel_bias_var'][k]-EV/V)/r['mc_se_rel_bias_var'][k],2))\n\"","description":"Compute exact expected CR0 variance ratio"}}]}}34{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"fa07b6f0-8fe1-4848-9e90-9dbd130d84ef","timestamp":"2026-10-30T05:41:57.946Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"d57e298e-cdba-4fef-a51d-105896ee4348","keep":8,"tail":["7c0502f41071066da5b3861b946b81c224ce7950b8a7dd5a4ac93b71089e3a85","b2c7535fe9a7456687557b2bf7a348171ddae45e1eccac4f07b7c83fbd14ae58"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"35a5ccdf816dbd7cf504439d4f9e58219dca616eb8725507005d0ce4bb01bb1c"}35{"parentUuid":"c8376c0e-fcd1-4a12-9c03-4318b48f63e2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRA9EyGaEmeZeDs9YY","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":866,"cache_read_input_tokens":23139,"output_tokens":546,"output_tokens_details":{"thinking_tokens":277},"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":866},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1990,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtR9peFyXYbb6yEKDaq","requestRef":"fa07b6f0-8fe1-4848-9e90-9dbd130d84ef","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0f5f7cf5-fae5-4f37-a53c-c65959b315b9","timestamp":"2026-10-30T05:42:01.313Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"0f5f7cf5-fae5-4f37-a53c-c65959b315b9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRA9EyGaEmeZeDs9YY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BaaLfrmHXiyHmb1HdojZZo","name":"Bash","input":{"command":"cd /tmp/rt20 && ~/wp29/venv/bin/python -c \"\nimport sys; sys.path.insert(0,'out'); import analysis as a, pandas as pd, numpy as np\nd=pd.read_csv('data/design.csv')\nfor row in d[d.G==10].itertuples(index=False):\n o=a.simulate_cell(row); x=o['wcb']['ind']-o['cr1']['ind']; print(row.cell_id, x.mean(), x.std(ddof=1)/np.sqrt(len(x)))\n\"","description":"Paired WCB-CR1 difference at G=10"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":866,"cache_read_input_tokens":23139,"output_tokens":546,"output_tokens_details":{"thinking_tokens":277},"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":866},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtR9peFyXYbb6yEKDaq","requestRef":"fa07b6f0-8fe1-4848-9e90-9dbd130d84ef","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a136535e-fe60-4802-aa5d-63e451c452aa","timestamp":"2026-10-30T05:42:02.960Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"a136535e-fe60-4802-aa5d-63e451c452aa","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BaaLfrmHXiyHmb1HdojZZo","type":"tool_result","content":"C4 -0.0075 0.003496854156881189\nC5 0.014 0.0038612763080830776\nC6 0.026 0.004321034097045973\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0020","is_error":false}]},"uuid":"0ab37160-331a-42f3-8066-8fcecf75a2b4","timestamp":"2026-10-30T05:42:03.996Z","toolUseResult":{"stdout":"C4 -0.0075 0.003496854156881189\nC5 0.014 0.0038612763080830776\nC6 0.026 0.004321034097045973","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0020","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a136535e-fe60-4802-aa5d-63e451c452aa","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"3a6814ee9dc107cde7283fd60df6e998791a12d8fba66c79b7861613587486e3","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01BaaLfrmHXiyHmb1HdojZZo","name":"Bash","input":{"command":"cd /tmp/rt20 && ~/wp29/venv/bin/python -c \"\nimport sys; sys.path.insert(0,'out'); import analysis as a, pandas as pd, numpy as np\nd=pd.read_csv('data/design.csv')\nfor row in d[d.G==10].itertuples(index=False):\n o=a.simulate_cell(row); x=o['wcb']['ind']-o['cr1']['ind']; print(row.cell_id, x.mean(), x.std(ddof=1)/np.sqrt(len(x)))\n\"","description":"Paired WCB-CR1 difference at G=10"}}]}}39{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"d74ef049-7d00-4a54-bae5-56df02e952d6","timestamp":"2026-10-30T05:42:03.998Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"fa07b6f0-8fe1-4848-9e90-9dbd130d84ef","keep":10,"tail":["3a6814ee9dc107cde7283fd60df6e998791a12d8fba66c79b7861613587486e3","91f87fd11923520e11606419d3f198b6972e35dd47ecfd3889729c6053d45c25"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1c11bb715bc728ecf33ced2d3b439228314d161ab77a47ca775c0fd8c7a3e9e2"}40{"type":"last-prompt","lastPrompt":"Review","leafUuid":"0ab37160-331a-42f3-8066-8fcecf75a2b4","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}41{"type":"atis-latch","atis":"","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}42{"type":"tools-used","tools":["Bash","Read"],"sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}43{"parentUuid":"0ab37160-331a-42f3-8066-8fcecf75a2b4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRbyVgWjyxr7VpyVTy","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS/QYKEAgTGAI4AUIIdGhpbmtpbmcSDLBEPwdtCzkjIKvj4hoMvo2stcDhCKJq8gVAIjAnm7MpWzoKZqcbPAEPEADNRv4S9HHwR38f7sCt2BYw8YqKidpVkv+KQhxd++cstsoqmgYLFYwioth6ob19xKmiz9Q2NQ4OjefC86XueuGtOR9Mm8XJRZ7Q/vKNJuUBlbSIjgYYrUMtyhkswK+/R4yi8ra13BFmYX3eUVM30M43k3WFnk/kmYTHZuRMMEGF6xRMYTkuWqG1dtKynZXRYvOKK3tyqJRJ1d0DPl+5vFdEavvhpSFVnUkZMZIp7sF+regl61zTPOJNFWSQi4n00HOQQtQ+yXGkBMRcsQNvIjI/ACRn/BjdsaRR8dDNDuU8xx/GoNaR0OQHc666T9kp4RdapxY0/k9co3y/fJN2ieh1oH+b5QmkONNDwPW1GlWp2dnRxamFaZo7dtt555EMQGu4DlvtkOBuMxZhLrrfQ3HdfyY3l3VoC5yyfFZkGrrHqPzR8Wc8GN/UbWbpx/sdftKpgcWpG6xaNwlqOpHrBiWHZOgapcdqCQdIKVi2Iq0JDGAVGNd9w2b2Yjl583Chp6B4EgPgeL9bX0gXKR4KBXQPEy1k9/6JQr+tm2gHcjw2v3tZuPg4y7lQ/Qdt8ELicLZByMZKx4jgkL6uG4ry9q9MuweNlMciUh5K1Y8wSakG3oEDYkNcGgQfPjbYYo2YoRkzzO7VBhS8/ZXYKMbGgpVl6nvNqyK/yv0QZIeV5jJ0kx5aQwNmuJAEUIVUctCt96Vvania3PKMJAnHrBtPaZglAuYZPwCF5mcrC7Lp1dfngyALG/iEAHGNA64xpkJEFbqqDoQrsOG0YLyioEvZX7nlYGZfDD/xBx2yIpkxkjdknYViUf+zmxQxZ2GN8bucEGCVjreYy0lQeW6soZ5t5Lemk+WS/6xkGv33WaELhcbBamSmPum9ToG1Fillkn2jFU3xLoXyH1z2mtoRsBz73zLa1C0Wm1+ps3XlIq5veCTM6Ao+4HxK/r/lvaM3mHPvXYFpK05B+kv1YN89ptes+cOgo6MSupDvRfFOrT7STYFQ0OK4LugpF7LBpbEe2EIE/Laee3AebPT5bBsCXS+pSzB+2q7E1q+EiKTVIHoMrsE1R/VmnBzIDBNiEcth4YpYo9tqtM6k13mXcct1bBUb9RgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":637,"cache_read_input_tokens":24005,"output_tokens":146,"output_tokens_details":{"thinking_tokens":65},"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":637},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":387,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtRbiNT12UiR9C31VWA","requestRef":"d74ef049-7d00-4a54-bae5-56df02e952d6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3f8ebd38-3a38-4db5-a57d-6ab912a259be","timestamp":"2026-10-30T05:42:05.634Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}44{"parentUuid":"3f8ebd38-3a38-4db5-a57d-6ab912a259be","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRbyVgWjyxr7VpyVTy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Y4qcpvhwWcY1kU8FwAGxmL","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/figure1.png"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":637,"cache_read_input_tokens":24005,"output_tokens":146,"output_tokens_details":{"thinking_tokens":65},"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":637},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtRbiNT12UiR9C31VWA","requestRef":"d74ef049-7d00-4a54-bae5-56df02e952d6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"971d056b-7d16-4690-84fa-4a6d9a56434c","timestamp":"2026-10-30T05:42:05.993Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"971d056b-7d16-4690-84fa-4a6d9a56434c","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Y4qcpvhwWcY1kU8FwAGxmL","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"fdd21124-cae9-4b06-b340-0d1188d44549","timestamp":"2026-10-30T05:42:06.024Z","toolUseResult":{"type":"image","file":{"base64":"iVBORw0KGgoAAAANSUhEUgAABpoAAAIiCAYAAADYTBtlAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAT/gAAE/4BB5Q5hAABAABJREFUeJzs3Qd4lFXWB/B/Jr33SoAQegm9FxEbIuqq2Lsoa1tR10ZHQEAX9VN0dS2Ia2PtDRRsoNTQCb0mECA9Ib0n33PuZFoyE5Iwycwk/9/zzDMzd96ZvJnA5Oaee85xqq6urgYRERERERERERERERFRI2ka+wQiIiIiIiIiIiIiIiIiBpqIiIiIiIiIiIiIiIioyZjRRERERERERERERERERE3CQBMRERERERERERERERE1CQNNRERERERERERERERE1CQMNBEREREREREREREREVGTMNBERERERERERERERERETcJAExERERERERERERERETUJA01ERERERERERERERETUJAw0ERERERERERERERERUZMw0ERERERERERERERERERNwkATERERERERERERERERNQkDTURERERERERERERERNQkDDQRERERERERERERERFRkzDQRERERERERERERERERE3CQBMRERERERERERERERE1CQNNRERERERERERERERE1CQMNBEREREREREREREREVGTMNBERERERERERERERERETcJAExERERERERERERERETUJA01ERERERERERERERETUJAw0EZHDiYmJgZOTE9atW2fxmEOHDuHJJ59Ev379EBQUBDc3N4SFhWHcuHF46aWXkJaWZvG5p0+fxsyZMzF06FCEhITA1dUVwcHBGDlyJObMmYPExETYoz///BMTJkxQ5+rl5YW+ffvi5ZdfRkVFRZNer7CwELNmzUK3bt3g4eGB8PBw3HTTTUhISLD6uRMREdkC5xTNO6coKirCDz/8gL///e/o1auXei1PT090794djz/+uJpzERERtQacUzT/OsXFF1+s1oIsXR566KEL/jkSUdM5VVdXV1/A84mIbDKBO3nyJNauXasmGsaqqqpUkGjJkiWorKxUwZHBgwfDz88PGRkZiI+PR35+Pry9vfH7779j2LBhJs9funQpnn32WZSWliIgIEA9LhOi7OxsbNu2DVlZWSrw9Pnnn+P666+Hvfjggw/wwAMPqMnV2LFj1Tn/8ccf6rzHjx+PlStXwsXFpcGvl5ubi4suukgFlaKjo1WQLTk5GZs3b1ZBu59++gmXXnpps35PREREzY1ziuadU7z//vuYMmWKut25c2e1AUgWlrZu3YrU1FT4+/tjzZo1deZjREREjoZziuZfp5D1HwlcyXMjIiLqPC4bi++5554L/EkSUZNJoImIyJF07NhRAuTVa9eurfPYww8/rB4LDg6u/uKLL6qrqqpMHi8tLa3+4IMPqqOioqq//fZbk8deeukl9VxPT8/qt99+u7q8vNzk8YqKiupvvvmmulu3btX/93//V20vEhMTq93c3KpdXFyqf/vtN/14dnZ2df/+/dX3JN9bY0yZMkU978orr6wuLi7Wjy9fvlyNh4WFVefn51v1+yAiImppnFM075ziww8/VHOKffv2mYwXFRVV33XXXer1YmJiqsvKyi74Z0lERGRLnFM0/zrF2LFjLa4FEZHtMdBERK1mArdy5Uo17u7uXr1nz556XyMtLa360KFD+vtyvLOzc7WTk1P16tWr632uBFh27txZbS8ef/xx9X0/+OCDdR7bvHmzeiw0NFQFyhoiIyNDTQblkpycXOfx8ePHq9dcunSpVc6fiIjIVjinaN45RX0k2OTn56de888//7zg1yMiIrIlzimaf07BQBORfWOPJiJqNV588UV1/dhjj6m6v/WRfk3SH0BHV2pv0qRJKg27Pj4+PhgwYADshfQ+ELfddludx4YPH46OHTuqsoFS9q4hpCyelLUZPXq0KptX26233qquv//++ws+dyIiInvEOYV15hT10fVqEmfOnLng1yMiIrJHnFM0/5yCiOwDA01E1CpIjd+NGzeq23fccUejnit9nVatWtWk59qa9FJKTExUtwcNGmT2GN34rl27GvSauuPO93q7d+9u0jkTERHZM84prDenqI9s8ElKSlK3zfVZICIicnScUzTPnOKbb77B1KlT8dBDD2HhwoWq9yMR2R4DTUTUKsjkRMqBuru7Iy4urlHPlUBNTk6Ouj148GCrnte6detU48vGXuR5DXHy5El1HRAQoDKtzNFlJemObehrtm/fvt7Xy8rKQkFBQYNek4iIyFFwTmG9OUV9li9frnYyh4aGYuTIkRf8ekRERPaGc4rmmVO88cYb6vLOO+9g1qxZGDZsGCZOnKgCe0RkOy42/NpERFaTmZmprgMDA+Hs7Nyk5wpZ7LAm2aF7zz33NOl5DaEL9Hh7e1s8Rjexy8/Pt8prGk8U5TUtTRyJiIgcEecU1ptTWHL06FE8/fTT6vaiRYvURiEiIqLWhnMK684pLrroItx3330YNWoU2rVrh7S0NPzxxx+YOXOmagFwzTXXYP369dBomFdBZAsMNBERNaMePXrgww8/5HtMREREnFPUZERfe+21qvyv9Jd84IEH+C+DiIioBTnqOsX8+fNN7sfExGDy5Mm44oorVJ/uTZs24euvv8ZNN91ks3MkassY4iWiViEkJERdSwk8qfnflOcKKeHiSHS7gAoLC8+boeTr62uV1zQul9fQ1yQiInIUnFNYb05Rm+xanjBhAg4dOoQrr7zSIRe5iIiIGopziuabU9QuwyeZTkIym4jINpjRREStQv/+/VVvo9LSUuzdu1fdb6hOnTqpHkfnzp3D9u3b9bWCrUEWUl588cVGP2/atGlql9H5dOzYUV3LuctEzVwZu9OnT5sc29DXTE5ONvu47vWCgoJYNo+IiFodzimsN6cwVlRUpPonbNu2TZW+kUbebm5uVvmZERER2SPOKZpnTmFO9+7d1fXZs2et8npE1HgMNBFRqxAcHIwRI0aoVOlPP/20UYEmqd971VVX4bPPPlPPve6666x2Xqmpqfjvf//b6Ofde++9DQo0+fv7q0BZYmIiduzYgbFjx9Y5RsZFQ9+TAQMGmDzvQl+PiIjIkXBOYb05hY5sBJL5lfRNkIbdK1euhKenp9V+ZkRERPaIcwrrzyksyc7OVtfsIU1kOyydR0SthmQBiTfffBMJCQn1Hisl8o4cOaK//8wzz6iAk9TzXbNmTb3PlZJyu3btatA5XXzxxaiurm70RZ7XUNLnQKxYsaLOY1u2bMHJkycRGhqKkSNHNuj1JOjm4uKCDRs26HcZGfvf//6nrq0ZkCMiIrInnFNYZ04hKioqcPPNN+PXX39Vm1l+/vlnlt4lIqI2g3MK680pLJE1FFnLEYMHD77g1yOipmGgiYhajWuuuQZTpkxBSUkJLrnkEnz11VdqwlF7sePjjz9WCx0HDhzQj8sumgULFqjjr7/+erzzzjvqWGNVVVX48ccf1cTlzz//hL144oknVOmZZcuW4ffff9ePS7+qRx55RN1++umn4ezsbPK8u+++W2VNSWCudh1pqW8s37+8n7ILWUeysyQQFxYWpq+BTERE1NpwTmGdOYXMne666y788MMP6N27N3755RcEBga20E+RiIjI9jinsM6cYt26dSozuvYaj7QRmDx5smqDIP2e5DYR2QZL5xFRq/Kf//xHlZN79dVXcdNNNyEiIkIFhvz8/FQW09atW5Gbm6smIFFRUSbPnTFjBjw8PDB9+nQ89NBD6lrKu0gvIl3/pvT0dBXUkXJ19iImJgZvv/02HnjgAVxxxRUYN26cWsRZu3YtsrKy1Ng///nPOs87deoUDh8+jMzMzDqPLVmyRO0yWr16Nbp06aJ2GUl2k5QmlO9fSgwyJZ2IiFozzikufE4hi0S6TOj27durBSVzJEuamdJERNRacU5x4XOK3bt348knn1TrOLJRWF7rzJkzqtqMbo3niy++QHh4eAv+ZInIGANNRNSqSPk7CZJIto1kJckkRna9SLk7mYhIJpOUhpPHJXOnNpno3HjjjSpwIyVe4uPjkZ+fryYtsqvm4YcfVjtkOnToAHsi5xQbG4sXX3xRnbNkdXXu3Fml6UvGk5TCawwJ1m3evBmLFi1Sk7Xvv/9eBesmTZqEOXPmoG/fvs32vRAREdkDzikufE6h65cgZPNKfZtmGGgiIqLWinOKC59TSJ8n2RC8bds2tQlYMqNkE6y83uWXX46pU6fa3ToNUVvjVF0755CIiIiIiIiIiIiIiIioAdijiYiIiIiIiIiIiIiIiJqEgSYiIiIiIiIiIiIiIiJqEgaaiIiIiIiIiIiIiIiIqEkYaCIiIiIiIiIiIiIiIqImYaCJiIiIiIiIiIiIiIiImoSBJiIiIiIiIiIiIiIiImoSBpqIiIiIiIiIiIiIiIioSRhoIiIiIiIiIiIiIiIioiZhoImIiIiIiIiIiIiIiIiaxKVpTyNrOnv2LFauXInY2Fh4e3vzzSUiImplCgsLceLECVx99dWIiopqlq/B+QQREVHrxzkFERER2eN8goEmOyBBpgcffNDWp0FERETN7J133sHf//73ZnltzieIiIjaDs4piIiIyJ7mEww02QHJZNL9YOPi4mx9OkRERGRle/fuVZtKdL/zmwPnE0RERK0f5xRERERkj/MJBprsgK5cngSZRowYYevTISIiombSnCVyOZ8gIiJqOzinICIiInuaT2is9kpERERERERERERERETUpjDQRERERERERERERERERE3CQBMRERERERERERERERE1CQNNRERERERERERERERE1CQMNBEREREREREREREREVGTMNBERERERERERERERERETcJAExERERERERERERERETUJA01ERERERERERERERETUJAw0ERERERERERERERERUZMw0ERERERERERERERERERNwkATERERERERERERERERMdBERERERERERERERERELYcZTURERERERERERERERNQkDDQRERERERERERERERFRkzDQRERERERERERERERERE3i0rSnERERERERERHRuC/GNehNWHvzWr5ZRERE1Cox0EREREREREREZCXFFcWorq6Gk5MTPF08+b4SERFRq8dAExERERERERFRE9XOVJr4zUScyj+FDr4dsOqGVXxfiYiIqNVz6B5NVVVV+L//+z/06NEDHh4eaN++PZ566ikUFhY26PlpaWl46KGH1PPc3NzQoUMHPP744zh37lydY59//nm1G8nc5eWXX26G746oDXu5W8MuRERERERERERERGRTDp3R9OSTT2Lp0qW4/vrrVYDp4MGD6v6uXbvw22+/QaOxHEdLT0/HsGHDcPbsWTz44IPo06cP9u3bh7fffht//fUXNm7cCC8vrzrPk8BWSEiIydigQYOa5fsjohrlRUB1FeCkAVzr/r8kImoK9lMgIiIiIiIiInswzsF7PjpsoGn//v144403cMMNN+Drr7/Wj3fq1AlTp07F//73P9x+++0Wn79o0SKcPHkSn332GW677Tb9+MiRI9XzXn31VcyaNavO86677jrExMQ0w3dERHpPHzF9M5YOALJPAEGxwNRdfKOIqFmwnwIRERERERER2YNiB+v56LCBphUrVqg3+oknnjAZnzJlCqZNm4ZPPvmk3kDT2rVr4enpiVtvvdVk/JZbbsHkyZOxfPlys4EmkZeXp7KdXFwc9u0jIiJq89hPgYiIiIiIiIjswVoH7/nosD2atm3bpkrjDR061GRcejX1799fPV6f0tJSdaxEBI3Ja0oA6sSJE8jMzKzzvL59+8Lf3189V7Kffv75Zyt9R0RERERERERERERERI7FYVNypLeS9Epyd3ev81i7du2wadMmlJWVwc3Nzezze/fujcOHD2P37t0qMKUj93NyctTtU6dO6fsxBQQE4O9//7sKLgUGBqrnvvbaa5g4cSI++OAD3HvvvQ067+TkZJw+fdpkbO/ever66quvrnO+EyZMUK8v3n//fcyePdvs60r5QDk3MWLECCQlJdU5pmfPnvjjjz/Ubelhddddd5l9rZdffhl33HGHui1lBdetW1fnGF0wThw7dgxjxowx+1qPPfYYZsyYoW5Pnz4dH374odnj5H0PDw9HRUUF2rdvb/YYeX/ee+89dfudd97B888/b/a47777TvXfEkOGDKnzfou4uDj88ssv6vaaNWss/vzkZyxZbuLmm2/G+vXr6xzj4+ODo0ePqtvy7+Liiy82+1qPP/64yrYTzzzzjMq6M0d6hQUHB6tgqKUyjVLCUfqJibfeegsLFiwwe9yPP/6IwYMHq9sDBw5ESkpKnWP69euH1atXq9s//fQT7r//frOvJaUqb7zxRnVbSlZu3ry5zjHy/0R6pYkDBw7g0ksvNfta0lPt6aef1t+WEpbmyGvI/7eisip0fiUf0OwDFkeaHDNp0iS8+eab6rb0aFu8eLHZ15KgsO7/unzP0qetNum3tnLlSv17J//nzZH3XHrDib/97W/YunVrnWOCgoJUiU+RkJCA8ePHm32t5557Tp+ZKf9GvvjiC7PHHTlyBL6+vsjPz0e3bt3MHiP/Rl9//XX9v92XXnrJ7HHyb16C5rrPwuzs7DrHSBD/+++/V7e//fZbPPLII2Zf691338U111yj/z+6Y8eOOseEhYVhz549+v/r8rlmjnxGSOlT8Y9//MOkLKqx48ePq6xS+azu1auX2WMko/WVV17Rf6bpbtf2+++/619DPiPPnTtX5xj5TP3mm2/U7a+++kp9rpmzbNkyXHXVVer2lVdeqf+ejUVGRmLnzp3q9vbt2/XvXW3yWa97zx9++GH1uWaOfNbL78GsrCzVa9CcO++8E0uWLFG3X3zxRf2/kdrks7579+7qdteuXVFQUFDnGPms1/0b/fzzz+tkFevIZ73u3/wVV1yh/z1nLDo6Wr8pJD4+Xn2umSOf9dJLUZe1rPs/au73q2Qap6WlmfxeNyaf9brPCCmh+8aLc0wez9E4oRJA8LMlwMva/2exixNR7Gbam1HIZ71kV4tPP/1U/5lW28cff4zLLrsM1sb5BOcTgvOJRs4niorQuXNns8dwPmHA+YQB5xMGnE/UM5944406nyk5JTnoML0D4Ku9Hxsbi+LiYqvMJ2SebE2cU3BOITin4JxCh2sUBlyjMOAahW3mFDklOaisrkTwwmD9mDXnFNbmsIEm+UPRXJBJSLaR7hhLgSZZHJOFO/lDShZkZYFOFoVl3NXVFeXl5er5xsfXJiX25HlPPvmkWoCXgMP5yELkvHnzGvGdEhERUcuoBuBkdG2/OJ8gIiKyX75DfKHx0Khy//aOcwoiIiKyBqdqR5j5mCEZKZKRIFHB2iR49OWXX6qMEEuBJiHHyO751NRUdd/Z2RkPPPCAel3ZwS+70XW7/i2RoJFEMiVDQHZtN3W3kERCJQtLds4TUS1LBwDZJ4CgWGDqLr49RNQsJn4Qh1POQIdKYNXkullYF0KyQCXz2Fq/6zmfICIisk9bUrZgyi9T1O0wzzD8fvPvVn19zimIiIjahonN2KPJ2vMJh85oioqKUmUwJJhUO7PpzJkzquRdfUEmcdNNN6kSYBLokXJUUjJISjxJyShJbevSpct5z0NX2sxcPydzpCycpdJwRERERJxPEBEROSbZx/v2bm2Jc5FblqvGaveGtidcoyAiIiJr0MBBSe+dqqqqOr1RSkpKVA8QXV+a85EsJqmTKH0nJMgk2U27du3C2LFjVQ+Q89H15pH+QkRERERERETUNsWnxmNnurYfpyitLMXW1Lr9XImIiIhaG4fNaLrllltUkyzpryRBIp333ntP9Va64447TBrHS8+lHj161PuaEriSUnqVlZWYOXOmfryiogKFhYXw9/evU7bm7bffRnBwsEo1IyIreHsUsrIOmY5VVwEaDZCbBLxgaIAXHNwDeHgj33YiIiIiIrKrbCadt3a/haERQ+06q4mIiIiozQaapEfTo48+ijfffFOVv7vqqqtw8OBBLF26VGUj3X777fpjL730Upw8edKkEWdBQYEqkXf99dejU6dOyM3NxYoVK7Bjxw4sXLgQ48aNMzlWjrnuuuvQs2dPBAYG4vDhw3j//ffVY/I8T0/PFn8PiFqlwgwEV1TUc0CVybFERNYgc4SCmvUfh2xeSURERM2qrLIM2SXZ6pJVnKW/rbscP3cc+7P213meZDhJVtOwyGH8CREREVGr5bCBJiHZTNIj6d1338WqVatUX6bHHnsM8+fPh0ayH+oh/Zv69euHzz77DCkpKapMnpTjW716NcaPH29yrASRJk2ahPj4eHz33XcquCRf67LLLsOzzz6rAlZERETk2KVusmumDqW2PhkiIiJqdlXVVcgrzdMGjkpqBY6Ka40VZyO/PL/JX+utlZMxNLccTk8fser3QERERK14M2x5gf62I3DoQJP0V3rqqafUpT5JSUlmA02SidQQ7u7uKnuJiIiI2kDjbo12jCVuiIiIHEtJRYlJwEiXeaQPGhUbHsspyUFFdX2VFKxnp5sGW12dwJwmIiIiavBm2JJsfc9HR+DQgSYiauOqKoDMY4CzC6CRiyvg7AponI1uuwCsh05EjWnc7QSWuCEiIrIDlVWVyC3L1QeIdAEjc6XrZKyoosiqX9/TxRNBHkEI9ghW10GeQdrrmkuwZzAC3QMxb/M87M3cW+9rvdVtOIZyIwsRERE1djNsWa5DbIZloImIHFdRFvDmoPMf5+RcE3SqCULpb7vUBKksBKjU47Vv13pendu1rk1uu5oJitV+bQvnavb8nFviXSZyyEWpksoStatZdv7ItdyX28UVxSitKEXJ6udQUpqHEifgv17yf9DJfIkbueMdCjy80VbfDhERUatSVF5kCBoZZRiZCySdKz2nStxZi8ZJowJDxgEjCSJJwMg4gKS7eLl6nfc1t6RsOW+QSbBXE5FjG/eFoZd7fdbevLbZz4WI2thm2MpSh9gMy0ATEdleYRaQuA44sQ4ozLD+61dXAhWVUkwDrYuTmSBWcwbC6gmK1QmEWQra1XNOxrftfJcGNV55Vbk+8KML9uhvmwsGGY9JYKgmcKQPHhkFknTHy3HFlcWokGzH83GXi2v9JW4qzmFYiWOkqBMREdmK/N6VgJClLKPaY/J725q8Xb3rZBkZB5H0j3kGwd/NH85W3qz1xeEvGnzs54c/t/tFIiJqGPks02UYSPYjEZElsmlGNtpIzyXddWF5oclt3SW/LB+/nfqtzmu8tfstDI0YatdZTc0WaEpPT8d3332HdevWYf/+/eq+vBGhoaHo06cPLr74Yvztb39DWFhYc50CEdmrsiLg1GZtYEkuqQlNex3ZYTjwHqCqXFtGr7LC6Hata5Pb5TXHGt+2cLwEqexWNVBZpr20NrrAU53gV1MDYecpr2gxq+x8gbrGnJ9cNLAX8kdRWVVZnawfc/drB3vMBXdqP1779Srt+v+SeW8F+mNoSro2q4mIiKiNkDmCLHRYyjLSX2qykSTIVC3zUitxcXJBoEegxSwjGdcFkOQ4DxcP2NKt3W/FrvRdJmPZRZmocgI01UCQV4jJsUTkmGpnKk38ZiJO5Z9CB98OWHXDKpudFxE1X6UUKcmrCwDVFxw636XICqV9HSEz2uqBpoSEBCxcuBDff/89ysrK4O7ujujoaHTs2FFNWLOzs/H1119jxYoVeOyxx3Dddddh5syZiIuLs/apEJG9qKoEzu4GTqzVBpaS4+sJjsiSbgP/UHX3BSa8iGZVVaUNNqkAVO0AlYxVGt02DmiZC37VFwgzF/wy/jq1g2XGX6eh52d8uxx2Tfc9ttosNPPBryqNC0qdXVGq0aBE44ISZxeUaJxRonFCqVw7aVSptxKNBqVOTurdUfflgmqUolpda29XoaS6CiWoRGl1JUpqLqVVFSiprkBJVbkVl4RanuwadHd2V4tLHs4eJrfl2uQxF3eTcfXcX+YgubIQ7wQGWPwaOz08sNXDnY27iYioVWQW55Tk6ANE+uBRrfJ1uvuyGcWafN18TbOLajKMamccyX05VkrcOYqhkUPrLkB/EIdTzkB0FbCKZbSIiIhaLDhUWFGIwrKaII/udkUhCsoKVMBHruX++QJG1s7AtgZ7z2qyaqBp8uTJ+OijjxATE4Np06ZhwoQJGDhwIFxdTUvTSABq165dWLVqFT799FN1zD333IP333/fmqdDRLZSXQ1kHTcElpLWAyW55o+VHYgdRgCxF2svn90MFKTBbqgMFI02ENDafkZS795iUKwxGWGNCYTVF/yq53mWgnbmvraVM2fk1SSoU+wkwR4nlEiAR26rMY0a0z9e85gKDOluq/s1gSHj55ocU4VSp2qUaqQHgYWFHeu1J2gWmupqeKgLIPuK3dW1k7q4VzvBw0lTc18DdydneOguGrl2gbuTKzw0LvDQuMJd4wpPuXZ2g7vGDZ7O7uq2R03wyE3jDieX+ko+Gmesmc9Sqy4uw73+Hg3LasrXhsCJyPGwnwK1VrKJM7883zTLqNhyBlJeWZ5Vv76rxrVOgEgfNDLqf6S7uDm7WfXrExERUespwduY7KA65edqgkdybQ/BIVeNK3xcfVSfR7mWEr/Gt+u7nPjiDsz3c60/q2lpDwx7/DBafaBpz549+Pbbb3HNNdfUe5ybmxuGDRumLvPnz1fZT/PmzbPmqRBRSytIBxL/qgku/QnkJls40AmI6m8ILLUfDrjattxFmyS7H5xkMV5q1Hs45K5ci317yov0l9KKmtsVcrsExTKmysCVoFj/HO1Fe7sMJVJOTl5fegpVlaPcAUu+6bjogj9V1XBXt6vUfbntWTOmbst1lS5QJGNV+ucZxgyvZe4YmVA4UjAm3sMdOz3Cz3ucymoqKWNWE1ErwX4KZM/KKsvMZhnVDhrpAkkN6knYCP7u/mb7Ghnf15Wzk8USe91NS0RERM2/JiPBHnOBn/MFh2o/T9ZxbM1N4wYfNx94uXjpryXw05SAkVsTN9fIJqKlnufvI/mWlwuG1vSHa9WBph07djTpedKrSS5E5EDKCoGTmwx9ltL2WT42KNYQWIoZA3gFWT7WO9TkrpT2WuFUiGon4MqCIgR7hVo8lmxHfiHKREPXt8dcX5/6+vcYH6/r92PcB0j/eM1tR+z3YzyBkVJuns6e2pJuDSz95inXGjeV8SOZP+5O2uwfyQqSDCHPmmvJGPJwcoI7nOEiWWstmrHWiNKNxs+T82xhX/j5NvjYzz2dGWgiclDsp0C2bvycV5pXf58jo2wkyVCyJplLWMoy0gWMdI8HeASoHbhERETUOpVXluvLyZktI1dzW1dqTn9tJnAkazO2JvOc+gI+uiCRt4u3NnhkLkjkor12tYMqRvGp8djpev7SwTvdNHbbq8nqPZqIqJWSBeSzOw2BpeStlvv8eAUbAkudxgKBHRv+dR7eaHI3PmULFv8yRd3+ICAIv0/ee0HfRltb3JBf/sbBHuPgTZ1ATq3Hawd3LAWGdOPWbALd0iwHd7TBIH1fn/p6Ahn1ATJ5PaPbcnFWWWRUpxdaVQNLI5rtZ1be6EDYrbvexy73hgUsby123MAmERFZl8x5amcZ6YJItcvXSU8ka26OcYITAj0C65Sl0wWN9PcleOQZpHbj2uNuVyIiImp4cKh2ppC5rKD6sol0F2v3X2wKWR9paBm5+rKJ5HZr2yDzxeEvGnzs54c/bxuBpk2bNqF79+4IDg4+77EnTpzAunXrVG8nIrLDHj6ZR2sCS2uBpA1AqYXa7i6eQMeRhuBSeJ+a3kYXegrVeHv32/r7uRrtmCP/wSyNCfUl3swFb4xLwFkK/NQKHBm/jnFgyB52mDSVNIBuUHCndmCo5nizz7UQCJKLI/+bahXk80Ij6eUt179h6K5PsDb5TMMO9jl/iT0iInLcuVluWW6dTKM6QaSaAJLs/rUmma8YB4dMytYZZSLJeIB7ADes2KO3RwGFGSZDHxdloNIJcJZ9WC93M63IUGtjHRERtb5SuA0J/DQkYCSVY2xN5irGJeXkWmUCuRkyghqUWeTqDRfpmUxm3dr9VuxK32Uyll2UiSon6YkNBHmFmBxrj6z+0x0zZgw+/vhj3H777ep+dnY2YmJisHLlSlx00UUmx27evBlTpkxhoInIXuSnavsr6bKW8s+aP85JA0QNNOqzNBRwcW+etNH0nfr7pU5olvTQ2v1+zAZvapWAs5QlpB+z8Hr2MEloKhcp1WYmuGMu6GMpuFP7eH0wyCgrSLKIZPLB4A8RERE1hSzU1A4Q1e59pHv8XOk5lQVuzc0yge6BdbOMapWqkwCSHCcLL+TgJMhUkGYyZFIovNZjRERkX2RDs2T7qHJyRsEe49JyujJyupJz9fUdsnYPxaaQtZbaWUG6YE/tTCGTMnI1wSNdqTkJLDE41DKGRg6tW/b7gziccgaiq4BVtR5rE4Em+c9Z+35BQQEqKmz/n4yIainNB5I2GgJLGQctv0XBXY36LI0GPAOa9e2snc2k869t/8LjAx5Xk4DzlYCrkzFkrnxcRSkqqh3380lShS2WajPuA2QuA8hS1o+Z15Px1paWTERERI5BFmwkIGScdWSx11FJtprnWZMsxFjKMqqdheTv7q+CTURERNS8a0ayptPUMnL659UEkexhXUiCOo3JDrIUMJLXYcl+sgXmqxG1JdKn5MwObVDp+FrgzHZtvxJzpKyDcZ+lgPYteqq1s5l0juQcwaN/PAp7pgvMNLb02/myfmoHjtjvh+gCyGdcLVlFGfq09GCv0HqPJSKiC1sckkUe4ywjkz5HtYJJEmSydpZ2nYCR0f3aYzLnIiIiMv49JoEK3W1qGHmvZANwfYEffTZRAwJG1uyD2FS1M4HMBodqSs7V13dIrrlRhRwdA01ErZlMeDIOGTKWpM9SmXYyVIerNxAzyhBcCusF2KhvjUw+/m/7/1m1cXLt4I654E29gaF6gkMmWUTs90PkGMz0R7j9/T446+qEqPJqrHlgn01Oi4jIkZtVm8suMhtIKs62ekNqXzdffXCodtm62uXr/Nz8WKKXrPO3lvSwtYMSSUSEFt8YK7/PhCP3Rm7o+oxkCtcpI1crK0hXUs74WsZrB49sHRyS9SFdgKfeMnL1ZRPVlJaT9SMGh4gMGGgiam1yzwCJRn2WLNUEd5Iin4MNgaV2gwEXN9hDQ+aF8QtxIPtAvcfd3etu9AjqUScwZK4EnJR8Y78fIiIiosYtLOWV5ZkGjmr1NzIuXyfHWpPM3+r0OaonkOTqzBK/ZEVlRUB+iraHrcl1rbHyIr7tRG1M7TL/uWW5asye1hx0waGGlpMzLj9nrrScNXsZNjU4ZKlkXGMCRvKYrBMxOETk4IEme/rAJWpVSnK1mUq6wFLmEcvHhnQ37bPk4Qd7cjLvJGZtmIXdGbvPe+y+zH14evDT/GwhIiIiaiDZdZ1TklM3y6jYTBZSSbbVm1kHuAdYzDLS9TvSjctiEP+GJKurKNNuxDMJHJkJKMnfWEREDSjzL79bt6ZuxbDIYRf0fkkwx1JwqNF9h8oLUQ3blvSTYI5JSbmaa+MycrUzhSwFiWSDMecERG000PTKK6/gf//7n7pdXl6uPgxmzpyJkJAQk+POnDnTHF+eqPX/cXR6myGwJD2XLKUe+0QYAkuxYwG/KNgjmVCtOLQCr+14TdXrbQiZ2FljMkdERETkqGQOlVeapw8O6QJI5vocyUXXT8JaJKvcYpaRUf8jeczf3V9lKRE1i6pKoDDTcvAor2asKPPCv5b07PKNAHwjtddHf2FmE1EbzWbSeX3n61gwcoEqGacvLVernJwKGNUuP2d0LQEiWweHnJ2cm1xGrvbzpLoMg0NEjfD2KKAww2To46IMVDoBzvLR8HI30z7SZtoBtMpA065du9TF2JYtW8weyw8dogbU/k7bbwgsndxo+Q8ZNx8gZowhuBTa3WZ9lhoqOT8ZszfOxo60HY1+7ueHP2egiYiabNwX40zuZ9fMilJdTB9be/NavstErYCjNO6W3cy1s4zMlaqTi2QnWbPXgZSmCfQINClTZ5xlZJx1JLe5w5ianfxfLc6pP3gktyVL6UL/L0hpcZ9w0yCSX6ThtrqOBDwDTf/GkoUfltAjapPZTDp7M/fiuh+us8k5uTi5mJSR0wV7Gh0wYnCIyLYKM+q0PwkyvmOpNUprDjRVVdm2bidRq3Au2RBYkn5LtSLaehoXIHqIUZ+lQYCD1KeXHbhfHv4Sr+x4RS2o6CZIE2MnYuNZ06i8LKTI8ZJ6LQsbOrd2v7XFz5uIWi8PWXdW9cftO0BPRI7VuFv6T54rPWfa68goaFS7fJ3sdrYmKU9TO8PIUp8jKW3nrHG26tcnsqg0v1bg6KyZnkipgDX+v3qF1BM8qrmW3cH8909EFsgmlTd2vmGV90fWPqSUnHFWUO3ScnIt980FjIyDQ5JdzE38RNSmejQRUT1kl55xn6WsY5aPDetlCCx1HAm4+zrcW3u24CzmbJqD+JR4/Vi3wG5YOHohegT1qHP8xG8m4lT+KUT7RGPVData+GyJqLWqnal0el4PRFen4LRTJKLnMouJqDWxZuNuXYNtS1lGuoCR7nHJOrJmKRwpa6PLOqodMNJnIRkFliTriKhFlZcABan1B4/kuswKpRzd/esJHkVpryVLycXNGt8ZEbVh7+19DwmZCfUec03sNege1N18NpEumOTqDTeNG4NDRNTqtHig6ezZs6o3U9euXREQENDSX57IPlSUAsnxhsDS2V01u+jNkD+QOo/TBpY6XaT9Y8lBycLMN0e/wZLtS1R9Yt1iyf1x9+Ohvg/B1UGysYiodcktKseXO5KxqvRhlFU7w82pEldvSMSNA6Ph78XPJaK20Li7oqpCZR1J0Kh2hpG5XkcN7SnZULIYZSnLSAJGqs9RTRDJz91PZXkTtbjKCqAw3ahknS5oJBejgJJsortQEiC1lHmkvx0BuHnD5iQTqpbKggw4owqV0MDZJ7TeY4nIvknvpJe3vYwvj3553mPPFJxRG2iZYUREbZHVA027d+/GH3/8gXvuuQfBwcH68czMTNx111345ZdftF/YxQUzZ87EnDlzrH0KRPZHSkqm7TXqs7QZqCkXV4e7n7bPki64FNzF7vssNURqYSqe3/S8SVm8zv6d1SSsd0hvm54bEbVdX2xLxpzv96GkQoL9XbSD1cCulQewZPUhzP9bH9w8pL2tT5OImqFx9xNrn0CoZyhySnNUkMmaXDQudTOMjIJGxrclO0nK3hDZ9G+VoiwzWUe1spEK0rW/JC+ElP42DhTpA0e1Akoe/o7zN5CZZtwpNVnSKU7hiH76kE1Oi4gu3J6MPZixfoaqsNIQsqnFeCMLEZFFZYXa1innTgG5p7QlhR2c1QNN//nPf/DTTz/hn//8p8n4Aw88gDVr1iA2Nhb9+/fHhg0bMG/ePPTt2xfXXWebhnlEzSrnZE1gaS2Q+Jf2jzdzNK5A+2GGcnhRAwBnl1a1uPPD8R/w0taXkF+u/dCUXbj39r4Xj/R/hAsrRGQzX7xwJ54tuK1m0azuYlZJRSWe/VpbHoPBJqLW17i7oLxAXRrKz82vTrk646CRcUBJjuVuZrK56mqgJNcoWGSchWScjZQKVJVf4BdzAnzC6g8e+UUBnkGAhhl5RGTfyqvK8c6ed1S5POkX3RifH/6cgSYigpqDSSAptyaYZHyRMUvrxA7M6qvZmzdvxoQJE0zGTp48iR9++AH9+vXDli1b4O7ujoyMDAwaNAjvvfceA03UOhRlawNKuqylnETLx4bHAbFjgdhxQMcR9lHyoRlkFGVg3uZ5+PP0n/qxGL8YvDD6BfQL7WfTcyOitk3K5c0pmGQxyKQl49WY88M+jO8dwTJ6RA46F3n2z2ctPu6qcUXXgK6GknXGGUdGAaVA90CW+CX7UlZkIXCUYtobyVIVhcbwDDT0O6qdjaQrb+cd1qo2yxFR23Xi3AlM3zAdB7IO6MfiQuJUWTzj0rVSSleCUDImcwWdW7vf2uLnTEQ22MwjpYJ1QSMVQEo2ZCfJtQSa2hiX5ujB1K1bN5MxKaUnHnnkERVkEqGhobjzzjuxfPlya58CUcsoLwZObTEEllL2WC4l4RcNdJaMpXFAp7GAcZ3uVkiymH5K/AmL4hchryxPjTnBCXf1uguPDXgMHi4etj5FImrjvtp5GiVoSGNwJ5SUV+HrnacxeXSnFjgzIrIGWfj56shXqqdCcWVxvTuW/zn4n9x5TPajogwoSK0bPNL3Rap5rNQKixduvrVK2NUKHsl9nwjAlXN3Imobc4cVh1bg/3b8n+rlKDxdPPHMkGdwY9cb62QqT/xmoiqpF+0TjVU3rLLRWRNRswWSCjMNQSN9EMkoqFTWxFJ3Hv6AfwcgQC7ttdf+7YEfHweKs+HIrB5oKigoQEBAgMnY1q1b1QfyuHHjTMY7d+6M7GzHfgOpDamqBFITgONrtYElCTLVTD7Mfmh0uqimHN44ICjWcWqMXyBplL1gywL8fup3/Vh73/Z4YdQLGBg+0KbnRkRtkwS/MwpKcSy9QF2OphXg+91nGvUavx5IY6CJyEEczTmK+ZvnY3fG7gYd/9bKyRj6wD6WuqPm/1uiMKP+4JHcLsq88K8lPb9ql6yrHUySa3dfa3xnREStoqf07I2zsSVli36sb2hfLB69GB38Otj03IiomfpTFqabL2mnCyQ1NSvcM8goiNTREEjSjcmasTk/PQ1HZ/VAU3R0NI4dO2YytmnTJhV86tKlpsl2jYqKCvj4+Fj7FIisF72W8ne6jCUpiydpkeY4uwEdhhv6LEX2BzTObe4nsSZpDRZuWaiaauvc3uN2PD7wcXi5etn03IiobQSUzuaW4Ghavj6opAJL6QXILb6w3hN5JRfau4KImltJRQneTXgXy/ctR0V1RYOft9NNw8bddOGlU+oEjoyvU4CCNKCRfT7qcHIGfMJrBY+MA0g1Y1Lqro1sciMiulA/nfgJL8S/gPya7AQXJxc83P9hTO4zGS4algQlctgNPjL/MlfSTtc3qbKsaa8t5YJ1mUj6IJIElNprb7u33ViH1T8xBw8ejI8++ghTp05FZGSk6tm0d+9e3HTTTXWOPXDgAKKioqx9CkRNJ2mRiX8agkvyAWRJRF+g8zhtYKn9cMCt7QZSckpyVJm81Umr9WPtfNphwagFGBIxxKbnRkStT2VVNZKzi1QA6Wi6Iah0PL0AhWWVzfI1/Txcm+V1icg6Np/drDKqk/OT9WN+bn76Er7nw8bdZFZpfv3BI939pi5UGPMKMS1ZVzt4pPoghbTJzWxERM0htzRXbZT9Oeln/Vgn/05YPGYxegf35ptOZM8qy4G8M2ZK2tVc5LGqhm88M3DSzrmMS9oZZyf5RwOuns3wDQHwrttmpbIgA86oQiU0cDZuw2Lm2FYZaJo2bRq++uor9OjRA927d8f+/fuh0Wjw+OOP1zl25cqVdcrpEbV4E91TmwyBpdS9lo+VD5bYmsCS9FnyDm7JM7VbUiJPytNII0ydm7vdrPodeLt6N+k1x31h+rmge+3TBadNHlt789omnzcR2b+yiiokZRXqy90dy5DrfJzILFSPNYSbswaxod7oEuaDrmG+2utwH6w7nI5FPx1q8Llc3iv8Ar4TImrOkr0vb38ZK0+s1I95uXhh6sCp6OzfWTXzNpZdlIkqJ0BTDQTJwn4NNu5ug71WjcvVqeuzdcfKCi78a0l5lPqCR6oPUjjg0pC+gUREZA2bzm5SpfLSi9L1Y3f0vANPDHyCPaWJ7EFFKZB7um45O10gSeZtTckUd9IAfu3MBJFq7ksgycUdNvHwxjpDKfN6ILo6BSlO4Yh+uuHrF60m0NSvXz98++23mD59uspkkj5M8+bNw8iRI02OW7NmDdLT0zFhwgRrnwJR/amTZ3cDJ2r6LCXHW96BKCUnJKCkK4cXxCbwtXf/LN66GKtOGJpeRnhHYN7IeRgZZfr//UJJA04piVW7+SYRtQ7FZZU4nmFc6k6bpZSUVaSylxrCy81ZBZF0F11QqX2gJ1ycNXWOD/f1wKu/HEFJAwJWHq4aTBoU3aTvjYiah8wLvjv2HV7Z8Yqak+hc2uFSTBs6Tc1JzG1KmfhBHE45A9FVwCpuWGmdu1sL0s1nHRlfWyqH3RgunmYykGoHlCIAt6ZtvCLHlFtUji93JGNV6cMoq3aGm1Mlrt6QiBsHRsPfi9nRRLZWXFGM13a8hs8OfaYfC/MKUz2lR0SNsOm5EbW5TT+qhJ1xjySj7CSZs6FhawEmpNylBIuMy9kZl7iT0sPO/H3cXJql2OjVV1+tLvUZP3488vO19U/Jil7u1rDjnj7SdmqmZx03BJaS1gMlhsUIEy4eQIcRhsCSlMbT1F2cJOCv03/h+U3PI6M4Q/923ND1Bjw9+Gn4ul14U2FmKhG1Tvkl5fqeSVLmTlf67nROsfq4bgg/Dxd0DfdFV+OgUrgvIv08oNE0PBgtiz3z/9YHz36dcN5j51/bB/6enIwS2YsTuSdUNvWOtB36sXCvcMwYNgOXdLjEpudGzdiwuSjLKOuoVvAor2a8MKNpixLGNK61eh/VCh7peiO5+7EPEhm83A1flAzFnIJJKIFkp9X0p64Gdq08gCUrd2O+z9e4edYnfNeIbGR/5n6V6ZyYm6gfm9BpAmYOmwl/d3/+XIisqbSgbjk74+wkNWdrAmd3bSBJFzzSl7SrCSjJHI1lhm2GXe1au/IibSqhpAa6tpEeQrKL8YRRn6W80xYOdAKi+hsCS9JnydWjhU/WsUifgyXblqgdxDphnmF4fuTzGBM9xqbnRkT2I7uwTJ+ZJCXvJFtJrlPzShr8GiE+7vpgkpS66xLqgy7hPgj1cbdaduPNQ9qr6znf7zOb2SSZTBJk0h1HRLZVWlmKZXuX4f2976O8qlyNaZw0uL3H7fjHgH80uWQv2ZDsMig5V3/wSC4FqU2ss2/MSVuiziTjqFbwSO57BnGzGTWaBJmeLbjNYqCzBK7ax7clc15B1MIqqirU3OGdPe+golr7u0Q2yM4ePlsFmoioCYrP1S1pp89OSgaKDe01GkXWrs2VtNNlJ3mHcZ5mxxhoam1qZyotHQBknwCCYoGpu9Bqo+SnNhsCS2n7LB8r74MusBQzBvAKaskzdWgbz2zE3E1zkVaUph+7tvO1eHbIs9z9Q9QGSdmq9PxSbe8kCSgZZSplFTa8KXqUvwe6GGUo6a4DvFqmV4UEkcb3jsBXO09jyepDKuDk4aLBs1f2wCSWuSGyG9tSt6kspqS8JP1Yz6CemDtiLnqHsGG3XSorrBtAyjNTyq6i+MK/lgSHjINHqqRdrYCSLEw4889fap5yeXNK7pDUO21A0yzt+Jwf9ql5B8voEbWMk3knMWP9DCRkGqoYjIgcgQWjFiDcmz1YiSxuBJIyw+dOmpazMy5xZ1S6ulGkClKdIJJRZpJXMDPGHRhn2uR4KiuAszsNgaXkrUDNrtY65ANKF1iSfkuBHVv6bB1eYXmhymL6+ujX+rFgj2C1sDOuwzibnhsRNb+qqmqcOVds0jtJAkrH0gqQX9qw3eVS0a5DkFdNqTtDUKlzmA983G0/FZHFnvtHd8LHm5NUX6gIfw9MHs2+fET24FzJOdWHyTibWno3Ptr/UdW020XqsFPLN2cuSKuVdWSmD1Jp3oV/LVmM0JWxM846Mr72iWBVArIp2azSkJ6PoqS8Cl/vPM15BlELbIr78siXeHn7y6ovk3B3dsc/B/0Tt/a4VWVEE7XpQJKUrlNBpJO1Akk11+WFTXttj4C65eyM+yTJ4+y/3mrxLzNyjA/AzCOGwFLSBst/uEpT3o4jtYGlzuOAsN5MqbwAW1K2YO7GuThbeFY/JqnlM4bOQID8ciCiVqOisgons4uMSt3l41iGZCgVori8skGv4aJxQqcQb6NSd77qOjbUGx6uzs3+PRBR61ogWnlipdrsklOaox+/KPoi1UshyifKpufXKlVVaktQmwsaGd+WXkkXSurr1xc88pXxcMD9wnt/EjW3Xw+kNvL4NAaaiJpRRlEG5myagw1nNujHegf3xqIxixDrH9vk1x33helG2+wSbWmw0wWnTR5jz2myi96WUnbYXEk7XVCpouFl7ets6DfJRKopaacb8/Cz9ndDDoSBJrJP8oescZ8lafxrjuxCiRpo1GdpKODi3tJn2+oUlRfh1R2v4vPDn+vHgjyCMGv4LFze8XKbnhsRXZjSikokZhbWlLwr0GcqyVh5ZcMaqLu7aNA51NA7SV2H+aJjsBdcnbk7kIguvMzNgi0LEJ8Srx8L9QzFtKHT1DzEWn3a2tSmraJsMwGkWtlIkqUkvV0vhJOzIQNJHzTSBY6MxjwDuZuVWoWS8kqV+d0YeSUWqnEQ0QX79eSvqtTuudJz6r6zkzOm9J2Cv/f9O1w1rlZ9hyXDWjbGcF5CNqn0JPO3OiXtai55Z4DKhpezNyH9LM2VtFP32wNu7IlKljHQRPahNB9I2mgILGUctHxscFejPkujAU9m1ljT9tTtmL1xttqVoyOLOhJkkmATETmGorIKlY0kQSRV6q7mcjKrEFUNiyepsnZdavVO6hrmi3aBnnCWenhERFZUXlmO5fuXq2bdZVXaP46d4ISbu9+Mxwc+rhp3U60AksyhTbKOzGUjpTZ9scGYd6iZrKPafZBCAA0zWKn1b9pZfyQTq/amqOykggaWEtbx87DuYjcRAfll+Vgcvxg/nvhR/3Z09OuIRaMXoW9oX6u8RcxUohZTWQ7knq5bzk6XnZR7BqhuWNURU07abPLaJe38dcGkaJYjtqP+j1/uSMaq0odRVu0MN6dKXL0hETfaeR/pZgk0HTp0SF336NHjgo6hVv6heXq7IbB0ZjtQVWH5j1rjPkvyQUhWJ3WLl+5cik8PfopqaFeh/d39MWvYLIyPGc9dOkR2PAE5llHTOymtpn9SekGjdtcGermqAFIXkwwlH0T4efD/PhG1iJ1pO9UO5OO5x/VjXQO7Ys7wOegf1r/t/RTKi82XrVPXRr2Rmlo/35iHf/3BIz8JIIUBLm7W+M6IHFJZRRU2HMvAyoQU/Lo/rcF9Ks25vFe4Vc+NqK3blroNMzfMREphin7slu63qH5MXq5e1vtCL3dr2HFPH7He16TW2+9SAkm6/kjGJe3kWuZ8Tckyl8xyv3Zmgkg1/ZHkMc7n7N4X25Ix5/t9Nf0fu2gHq4FdKw9gyepDmP+3Prh5SPu2EWjavn07hg0bhldffbXeINKaNWvw1FNPYefOnejb1zq7C8jOd1xmHAKOr9UGlk5uBMoKzB/r6g3EjDIEl8J6sbRGM9udvhuzNs5SpWp0xrUfhzkj5iDEM6S5vzwRnYeUZMgqLKspd1cTVKq5ZOSXNvj9C/dz12clda7JUpJLsA9LjhKRbeSW5uK1na/hqyNf6cc8nD3wUL+HcHfvuy+szM3bo5CVpd3cpvOh0R/tWS8E628HB/cAHt6IFtlsJSXqamcd5dUKKJVoS/5cEFlcUwEj4xJ2kaa9kXwiADcrLsIRtbLg0sZjmSq49MuBVOSX1A0uRfp74LKeYfh822mUVZ5/UdDDVYNJg6Kb6YyJ2pbSylK8sfMNfHTgI/1mWVm/mD9yPsZEj2n+Eygv0gYDpKWDNQNa5PjKiuqWtDPOTpL+SU0h82LJOtIHkWoCSLrAkmwYcmbxMkf2xQt34tmC27SRJclAq6WkohLPfp2gbttjsMnq//ree+89dOrUCY899li9x8nj//73v/Gf//wHb731lrVPg+yBpHImGvVZkj+qLUXcowcbAkvtBjPC3oITszd3vYn/7v+vfmImZWmmD52Oq2OvZiYDkQ0CSim5JfpAknFQ6VxRw+v5Rwd6mpS661xz29/TflOsiajtfd6tTlqNl7a+hKySLP34yKiRqlxve18r/OFUmIHgivqyDowWhQszLrzpclFm/cEjuVZfp4H1S+tbZKgveKS77+7HzVpEjVReqQ0urUpIwZr9qcgzE1ySjO+r4iIxsW8kBrQPgEbjhLh2AfqFn/rMv7YP52NEVnAo+xCmr5+OY+eOmZT8nz18NgI9ApvnPa6dqbR0AJB9AgiKBabuap6vSfapJK8mcKTLRDLukZSsnRM2hbO7IYhkXNJONyb9k1iiuFVXq5lTMMlikElLxqsx54d9GN87wu7K6Fk90LRu3TpMmjQJGk39zcDlcTnuu+++s/YpkK2U5AJJGwyBpcx60oVDugOdx2kDSx1HAR5+LXmmBGBvxl7M3DgTibmJ+vdjTLsxeH7k8wjzCuN7RNSMKquqcTqnSJuhlFGgvz6eXtDgOv/SI6ljkJc2mBRuCCrFhnrDy427mIjIfp3OP40X4l/AxjOGDCLpA/nckOcwodME+9roIln5kl1kXK7OXB8k2VBlqQx0Q8mOaClRZ1yyzriEne7aM0j+mLLWd0jU5klwafPxLG1w6UCq2c09Yb7uKrh0dd9IDOwQqIJLxnS7ig2lbupmMkmQyR53HxM5ksqqSny4/0O8uftNVNT83vVx9cGMYTO4WZasO/cz6YtUKzupqZnnUsGpTkk7XX+k9trWIZzjtVlf7TyNEjSkVLUTSsqr8PXO05g8uhPsidVXopKTk9GtW8Pqlnbp0gUnTxpKdZGDqSgDTm816rO0w3INUSnLoctYih2r3XFJNlFWWYb/7PkPlu1bhqqan5dMzJ4d8iyu63KdfS3uELWChYuTWYUmvZPk+kRGAUrNLEKY4+asUcEjXak7XUApJsQL7i5suE5EjqO8qhwfH/gYb+9+GyWVJfrxSV0n4clBT6rekLY7uRJg49JafZFqAkkVhnNtMgkO6YNHtQJHut5IsrjAcidELaJCgksnaoJL+1ORYya4FCrBpT4RmNg3CoM71g0u1SZBJNldLAtF0kNBAk4eLho8e2UPTLLz5t1EjiA5PxmzNszCzvSd+rEhEUOwcNRCRPpE2vTcyMECSUVZ5kva6e6X5jXttSWbvE4QSZed1AHwCmK2OVn064HGlVT89UBa6w80SaZSRb0lKgzkuPNlPpEdkZIg6QcMgSXpsyQ1ac1x8wViRhuCS6Hd+WFqBw5kHVBNMo3Ty0dEjsC8kfM4MSO6ACXllTieoQ0kHTMKKCVlFqKiqmElkjxdnVUQSXfRBZU6BHnBxZm/K5vDkIW/mdzPLtD2u0rOLjJ5bNvMy5rl6xO1JQkZCZi3eR6O5Bgy3mP9Y1U/yEHhg2BzpbnAr7Mb/zyZ85oNHhllI0mZE1eP5jhrImpkcCk+MVv1XJLgUnZhWZ1jQnwkcykCE+MiMTgmSGWQN4YEk+4f3Qkfb05CUlYRIvw97G4RiMgRy+1+e+xbVW63qEK7BuWmccPjAx/Hnb3uhEYygokM/2CAgvRaJe2MgkhybWkt83w8A42CSEYX3ZhnAH8O1CSFpRU4nVPcqOfklTS8vYLDBprat2+P3bt3N+hYOS46mo0w7Zp8GOsCS9JvyVL9eo0LED0EiK0ph9duIODMHVv2oryyHO/ufRfvJbyHyupKNebl4oWnhzyNG7veyCwmogaSsnYqiJSWr0rdHaspeXcqu0jNZxvC18NFBZEkK0kFlcK1QaUof8/z7pSl5uXp5oKq6mpomNlJZDX5ZflYunMpPj/8ub4fpCwO/b3v3zG5z2S4Nsd8UT6Q0w82fRFBVyO/Tum62vfDAXdfa545ETVDueL4RG3m0up9qcgyG1xyw5WSuRQXhaGdGh9cIqLmk1Wchec3P491yev0Y90Du2PxmMXoGtiVb31bVFWpzTivXc5OH0hKBiq1GwgbzSvEKIBkVNJOd5/zPrJycOn3Q+n4KSEFaw+nN7jqjY6fh2vrDzSNGzcOn332GZ5//nmEh4dbPC4tLQ0rVqzAHXfcYe1TaLveHlU3EFRY04Au5yTwslFJQynN8bChLr5ecQ6QuN4QXMo+bvnrhfUyZCx1HMkPXDt1OPswZm2cpZpl6gyNGIr5o+ajnU87m54bkb3KKSwz9E5S2Un56jolt+Hlk2TRwpCdpA0qSUBJyrCwRKV9YKYSUfPuPv7t1G94Mf5FpBen68eHRQzDrOGzEOMfY80vpm3GnfiX9pK03vLmqPpKndz0oaG8nUcAs/GJHDi4tC0pWwWXft6XisyajGVjwd5uGN8nAlfHRargErPHiezP2lNrVZApuyRb3ZfMJdmk8ki/R5pnowrZh8oKIP+sUQBJl42kCyadAaqamMkhbT2MS9qpIFJH7X257eZl7e+GyGxwaVXCWaw7nNHo4JKxy3tZjru0mkDTk08+iWXLlmH8+PH4/PPP0b179zrHHDlyBLfeeitKSkrwxBNPWPsU2i75g1oaEZsjWSzmHpN69MZ9ls7ustxnSWrHd67JWOp0kXY3J9ktaYz5wb4P8Paet/VNMj1dPFUPhFu638L0cmrzZBE0I7/UqHeSNpgkl8yCurtdLYn09zAJKHUN90GXUB8EejekiSMRUeuTUpCCRfGLsO60YfdxgHsAnhnyDK6JvcY6wXZZZNAFluSSd/rCXs/VE+hy6YWfFxHZLLi0XYJLe7XBJZnj1Rbo5Yor+0Ti6r6RGMbgEpHdKiwvxL+2/QvfHP1GPyabZBeNXoSB4QNtem5kpX7vMm8zV9JO7ued0a5hNpaUUJR1S5MgklFmkl87ljImm1XG+f1gGn7am2IxuBQb4o1LeoTho80nUVZ5/uCTh6sGkwZFt/5AU9euXfHWW2/hwQcfRO/evTF69Gj0798ffn5+yM/Px65du7Bx40a1wPfee++p48kGygqBj68HTm4GKoot7+yMGWMILgV34c5OB3Es5xhmbpypejLpDAwbiBdGvYD2fu1tem5ELa2qqhpnc4tVQOm4KntnCCrllTSsp6CsiUqvJAkgSak7ue4a7ovOod7wtcN0ZSIiW5CNLZ8d/Axv7n4TxUbzy791/hueGvwUAj0Cm/7iBRnaTCVdYKm+rHtZSOg0Fji0sunNnInIIeZ4O07lqMwlWbxJNxNcCpDgUu8ITOwbieGxwXBl30siu7YzbSdmbJiBMwVn9GM3dL0Bzw55Ft6u3jY9N2qg8mIgVxdIqhVEkuv8FNkN3/i308kZ8G9Xq5ydUXaSzP+Y6UYOFly6Ki5SzVF6RPiqzXjdwn3x7NcJ5339+df2gb+na+sPNIn7778fHTt2xHPPPYe//vpLXYwNGDAAL730Ei67jM21baasADj+h+mYxhVoP8xQDi9qAODcLP9EqJlUVlXiw/0f4t+7/43ymlRid2d31STzjp53MIuJWn2DZ+mVpM1Oqgkq1WQoFZc3bEeUi8YJMSHeqsRdF6NL51AfeLg6N/v3QETkqPZn7ce8TfNwMPugfqyjX0fMGT4HQyOHNv4Fi88BJzcZAkvp++uvpy/Z9rpLUKx2h8DLvzPQRNQKg0u7knOwsia4lJZXN7gkCy/je4djYt8ojOzM4BKRo/SVlnUMqcqi6+kY5BGE50c8j3Edxtn69Kj2xvXa5eyMA0mFhpLJjSJrkuZK2unuS3ljrlGSAwSXViWk4M8jloNLEliSAJMuuGTs5iHa5IA53+9DiZnnSyaTBJl0x9mbZosiSBBpx44dSEpKwr59+5CXl6eymvr06YOYGCvWZKcLEx4HxI4FYscBHUcAbtwh4qgScxNVL6aEDEPku29oX5XF1Mm/k03PjciaSisqkZRZpM9K0gWVTmQUNijFWLi7aBArWUn6kneSoeSDjsHe3OlKRNTI8jZv7noTnx36DFU15ZddNC54IO4BdZENLw1etDi1uSawtB5I2W25nLO7PxAz2hBYCuvJrHuiVkyqoexKPqfPXDLXM9PPwwVX1GQujeocAjcXjU3OlYga72jOUZXFZNxX+uL2F6sgU7BnMN/SllaSa6aknVF2UlFW017XxcN8STvdfZ9wQMPPbnLc4NK6Ixkoa0JwqTYJIo3vHYGvdp7GktWHVMDJw0WDZ6/sgUkDo+HvZX+ZTDrNnq4iQSUGluyQhz/wjx2AT6itz4SskMX06cFPsXTXUpRWanf0uWnc8I8B/8Ddve6Gs4ZZGOSYissqcTzDUOZOSt7J9cnsIlWHvyG83ZxrspIMvZPkOjrQC84aK/QIISJq4026F21dhNTCVJNSvXNHzEVsQGz9T64oBU5vM2Qsnd5uubGzqxfQYYQhsBTZD2jI/MbbzDy3MFNb91/Kr3iH1H8sEdk0uLQ7+ZwKLP20NxVnztUt9+4rwaVeEarn0qguDC4RORrZoPLxgY+xdOdSlFVpe+R6uXhh2tBpuK7Lddbp6UimqquB4hzzJe102UkSaGoKKW1Yu5ydcWaSzLX4M6W2ElwK9cbEuIYHl2qTYNL9ozvh481JSMoqQoS/ByaPtv8kAtZFa6tkJwGDTA7vVN4pzN44GzvTd+rH+gT3wQujX0DngM42PTeihsorKVcBpGNGvZMkS0kWFGQe3BBSf99Q7s5XfzvS34N/oBARWVlaYRpe3Poifjv1m37Mz81P9WGShSGNNGOurbJCm6WU+Kc2sHQq3nKfUGc3bTlnCSpJv9B2gwAXt8af6MMb644tHQBknwACOwJTdzX+NYmoWYNLCadzsWpvilq8MRtccnfB5b2kLF4kRncNgbsLN9UROaKUghRVkWVr6lbTvtKjX0B7X/ssCeUQ5A9o2VSjL2lnJjNJWmk0hWSU1wki6QJLHQDPQAaSqNVqTHBpYt9IdA9vfHCpNbB6oCk29jy7F2uRN/348Xqa+RKR2Z0/Kw6twGs7XkNJZYm+TM0j/R7BfX3uU7cd2ZCFhoWr+mybyT5vjiSroFTfM0kbTNIGlczV1rck1NddW+bOOKgU7oNgb7c2+UuciKils6i/OPIFXt/5uiqZpzMxdiKeGfyMaXmbqiptXyVdxlLSRqAs3/wLS3ZRu4GGjCUJMrl6tsB3RET2EFzadyYPK/eeVYs3p3OKzWaoa4NLURjTNYR9M4kc/P/8yhMrsSh+EQrKtQEPWb/4R/9/4N7e99pvRZa3RwGFGaZjEtAROSeBl7sZxiVzx9xmF2uQ+ZX0QDIuZ1c7O8nSRp7z8QwyBJGMS9rJmNz2DLD2d0PkEMGllTU9lywFl66WzKU2HFwyZvXVaOnJ5Onp2eiAExE1zOn805izaQ62pW7Tj/UI6qF6MXUP6t5qS6hVVVdD4+QETzc7nXiS/g+H1LwSQ6m7DEOmUk6RhZJIZrQL8DTpnaSCSqG+dl2LloioNTucfRjzN89HQqahF2S0TzRmD5+Nke1GanfQZh41ZCxJn6XibMsvGBEHdBqrDSxJWTwPv5b5RojILuaL+8/m6TOXTmUX1TnGy80Zl/XUZi6N7RZq98Gl2hvlsgu0G6mSs4tMHuNGOWrLzpWcw/wt8/HryV/1Y10CumDxmMVqTcOuSZCpIM38Y1KS19JjjVVVCeSnmC9pJ/cloFSpLTPYaN5hlrOR5L67j3W+ByIHll9Sjt8Ppqs5iqXgUmddWTwGl5o/0BQcHIysrCy4uLjgvvvuw5133omgoCBrfxmiNvkH2ZdHvsQr219BUYX2jzEXJxf8ve/f8UDfB+CqaT0L8LX/ALt4yVpVkzQm2Avrnhlns/Mig6qqarXj9FhGvgooGWcqya6PhpAWSR2DvWsyk2qCSmG+akeIt7tjZ+UREbUWReVF+M+e/+CjAx+hUhZSauYf9/a5Fw92vAoeUgIv/kNtcEkWRiwJ6WbIWOo4GvBmc2+itva3zIGUPBVYksWbk1nmg0uXSnApLhIXd7f/4FJ9PN1c9BvliAhYf3q92jCbWazNAnKCk+op/djAx+Du7N523qLKciDvjPmSdnKRx6oa9ve0KSfAN6JWEEkXVJJLNODm1QzfEFHbCi5JdnW3cJ82n7lkidVX8lJSUvD9999j+fLleOqpp/Dcc8/h2muvxeTJk3HFFVfwB0HUlP9XBSlqUrYlZYt+rGtgV5XF1Cu4F99TajbllVVqIeCYUe8kCSydyCxASXndX77muDo7ITZEV+quJqgU7oOYYG+HXkAgImrtNpzZgBe2vIAzBWf0Y/28ozFHE45ufy0Dzs2x/GRZ1IiVwNJYbZ8lv8iWOWkisqvg0qHUfH1wKTHTUHJTx9PVGZf0DFNlZy7uHuaw1QuYqURkecOKbJaV0rs6kd6RWDh6IYZEDGmdb5tkJR1fWyuIVHM7/yxQ3bC/o01I/0u/dmaCSLrraMClDQXsiC4Qg0sOEmiSTKZJkyapS2pqKj788EN1mTBhAtq1a4d77rlHZTp17tzZ2l+apA5sbVIzVnafSu1775D6jyW7/OPsu2Pf4V/b/qWvX+zs5IzJfSbjoX4PwU2aZRNZQUl5pfrjX2UmpeWrkncSUErKKkR5ZXWDXsPDVVNT4k4CSb76oFLHIC+4OJtpDE9ERHZJdhu/tPUlrE5arR/zrQaeyMrGjYmnYPYT3SfckLEkl8CYljxlIrKjv1+OpBVgVcJZrNybghMZhWbnjJf0CMPEuCiM6xEKLzdmshO1RgkZCZixYQZO5p3Uj13b+VpMGzoNvm6+aLWKMoGPr2vcc6TPtgSSjMvZGQeS/KIA59ZTxYbIlsEl6bn019F6Mpf6RqnsJWYuNV6zzugiIiIwbdo0ddm4caPKclq6dCkWL16srh999NHm/PJtj7lmg0sHANkngMCOwNRdtjgraqK0wjQ8v/l5tZtYJ9Y/Vu386RPSh+8rNUlhaYW+xJ223J02U0lq41c1LJ4EXw8Xfak77bU2qCR9lTRSD4+IiBxSVUkuvt72Gv4v8XvkVxv66o0vKMRz2TkIrTT6Y8wzUJuppAJLY4GQrgBLRBG1WUfSDJlLMreszd2lJrjUNxLjuoexTDJRK1ZeVY53E97Fewnv6cvu+rv7Y87wObgi5go4bJbShZBNwuZK2unu+0YCGsfM6CSy9+DSbwfTsCoh1WJwSdazrpKyeAwuXbAW2zo0ePBgJCUl4cCBA9iyZYvq40RE5ncB/njiR7wY/yLyy/PVmMZJg3t634NH+z/atuoXU5OdKyozCiZpr4+nF+DMueIGv0awtxs663snSVDJV5W8C/N1ZxlUIqLWoLwYSN6q+isdS/wd8yvPYpeHYZ4RVV6BmVnZuKi4BHDzAWJHGTKWwvsAGmarErVlsmFJdgVLgEnmmrW5uWgwrnuo2hl8aQ8Gl4jaghO5JzBj/Qzsz9qvHxvdbjTmj5yPUC8Hqqwj1YGk/6TuIllKDeXqCVz0rGlmkncY501EtgguSc8l481ytYJLV/eVzKVWnGHZ2gJN8fHxKpPp888/R15eHoYOHYp33nkHt956a3N/aSKHLFUzb/M8rEtepx/r6NdR9WLqH9bfpudG9hmUzCgoNWQopRmCSpkFpQ1+nQg/DxVA6qxK3hkylIK8WZqRiKjVNaA+s7Nm0eRPFWQqqSrDuwF+WO7vhwpXbZDJuboad+UX4WG/XvAacb82YymqP0u2EBGOZ0hZPG1w6XCadlOcMTdnDcZ2D1ULN5f2DIePO8viEbUFVdVV+N+h/+HVHa+itFL7t6iniyeeHvw0bup2k/1vVCw+B5zcZAgspRsCZY3m7geM+ac1z46IrBRckqwlya5mcKl5NMusLy0tDR9//LEKMB08eBDh4eGYMmWK6s3Us2fP5viSRA4fMJA+CAvjFyK3NFeNOcEJd/S8A1MHTlUTNGrb/z7O5pbgqPROMil7V4DcYkNpo/rIvD460FMFkSQ7SZepJNd+Hqz1TETUKkmZl9S9hkUTWUApN/RL2ezhjhdCInDK1fB7oI9bEOb2eRA9etwAuHrY6MSJyJ6cyCjAT3tTVPbSoVTzwaWLuoWohRsJLnFuSdT2yv7P3jgbm1M268f6hvTFojGL1MZZu1RWCJzaYpgjpewGqusuTCvu/kBFCVATQCMi+5Cnei5JcCkFfx3JNBtc6qori+cgwaUhC38zuZ9ds4k8ObvI5LFtMy9Dmwg0XXvttVi9erXarXDVVVepfkwTJ06EszNrjRKZk1WcpQJMv578VT8W7RONBaMWYHDEYL5pbUhlVbX65SFBpKM1vZOO1ZS8KyxrWE1oZ40TYoK99L2TdJlKcvF04+cwEVGrVl0NZBwyLJokrQdKtBtYjGVrNFgSHIiVPt76MS8XL7W55dbut8KZPQKI2rykzELVb0kWbw6k5NV5P1ydnXBRVymLF4nLejG4RNRWrU5cjQVbFiCvTPs54eLkggf7PYgH4h6Ai8aOMhorSoHT2w1zpNPbgCoLmzZdvYAOIwzlgiP7Aa/2BArSWvqsichMcOm3A2lqA0xrCS7Vx9PNBVXV1dDYe1ZoDat/6q9cuRKenp64+uqrVSbTb7/9pi6WSEDq9ddfb9LXqqqqUs+VUnzS/yk0NBQ333wz5s+fD29vwx/O9WVezZ07F6tWrVK3IyIicP3112PevHkICAioc/zhw4fx3HPP4c8//0RZWRkGDhyojr3kkkuadP5EvyT9ghe2vICc0hz9m3Fbj9vwxMAn4CWTG2qVpPlgUlahodxdhlzn40RmodnGhOZIzfvYEG90DfdFF33JOx90DPZWjxERURsJLOUkGvUQWA8Upls+PKwnvouIxStFx5BbaejZd2mHSzFt6DREeEeg1Xm5W92eCyLnpOljTx9p2fMiskMnswzBpf1n6waXXDROGNNVMpeicHmvcPh7MiueqK2SSiyyYfbnxJ/1Y538O2Hx6MXoHdIbNldZAaTs0ZYKljmSZC9VWOhX7OwGRA81BJbaDQJcWEaeyF60peDSNjvNVGqoZtleUFxcjC+//LJBx15IoOnJJ5/E0qVLVXDoqaeeUmX65P6uXbtUcEtTT4Pi9PR0DBs2DGfPnsWDDz6IPn36YN++fXj77bfx119/YePGjfDyMiz0Hz9+HCNHjoSLiwueffZZ+Pv747333sP48ePx888/47LLHPsfArWscyXnsCh+EX5OMkzKoryjMH/UfAyLHMYfRytRXFap6tgbyt1ps5SSsopU9lJDeLk5q+wkXYaS9toH7YO8VPYSERG1MblntJlKuuBSbrLlY4Ni9YsmicExmL/nTWxP265/ONwrHDOGzcAlHdrQpik3L21pHCduyiASkk2vCy7tPZNrNrg0qou2LN4VvcIR4MXFV6K2bvPZzZi1cRbSiwybW6Tsv2yY9XCxUdndqiptXyXdxpuTG4HSugFzReYAUQMNgaX2w7Tzg/p4h9Ydk80r1ZWAkzPgHVL/sUTUpOCSzE/WH7UcXJL5ifRdkk3Y1AoDTYmJiWgJ+/fvxxtvvIEbbrgBX3/9tX68U6dOmDp1Kv73v//h9ttvt/j8RYsW4eTJk/jss89w22236cclmCTPe/XVVzFr1iz9+PTp03Hu3Dns2LED/fv3V2N33303evfujUcffRSHDh2y/+aGZBfWnlqLeZvnIaskSz8mzTGfGvwUvF3Pn4lH9tl00Lhvki6odDqnWG02bwjZESq/JPVBJclUCvNBpJ8HNAwoERG1XbKIYRxYyjpm+VjfKCB2rHbRJGYMENAeZZVleH/v+3j/t4UorykRI30gb+95Ox4b8Fjrn3swU4mojtM5RWpXsCze7DldN7jkrAsuxUXgil4RCPRmcImIgJKKEry28zV8evBT/dsR5hWmyv6PjBrZsm+R/KEtcyJdxpIEl4qzLR8fHmcILHUcAXj4N+7rPbyx7tjSAUD2CSCwIzB1V+O/ByJqdHCpW3hN5hKDS20j0NSxY8s0+luxYgWqq6vxxBNPmIxPmTIF06ZNwyeffFJvoGnt2rWqxN+tt95qMn7LLbdg8uTJWL58uT7QVFhYiB9++AEXX3yxPsgkfHx88MADD2DOnDnYtm0bhg4davXvk1pXavlLW1/Cjyd+NNlJPH/kfIxs18KTMmqS7MIyVeJOW+quQGUryXVqXkmDXyPU111f6s44UynEx43BaiIi0vZUOrnJEFhK22f5XfEKNiyadBqrzWAy2vi0LXUb5m+ej6S8JP1Yj6AemDtiLvqE9OG7TdSGnDlXjJ/3pmBlQgp2J58zG1wa2TlYLdxc0TsCQQwuEZGR/Vn7MX39dCTmGjaXT4iZgJnDZ8LfvZFBm6Y6d8qoXPBfQH6K5WODuxrmSLL5xju4Zc6RiBolt9hQFo/BJcdnR535GkcCO1Iar3Zwx8PDQwWD5PH6lJaWqmNrZyHJa0oA6sSJE8jMzERISAgSEhLU8SNGjKjzOsOHD9efDwNNZMlfp//CvE3zkF5sSC2/vsv1eGbIM/B1Y3qnPZEAdnp+qbZ3Unq+ylKSy/H0AmQVljX4ddoFeKJzTZk740wllhshIiITZYXavgG6rKWzu7Sl3cxx9wNiRhsWTkJ7yuTVbIneV3a8gu+Ofacf83TxxKP9H1WlbeyqOTcRNZuz54q1mUt7U7DrVN3gkiTNj1DBpSiM7x2OYB93/jSIyERFVQWW7V2G/+z5DyqqK9SYrGHMGjYLV8Ve1bzvVn5azfyoJmspx7Bxpg7/DkBszcYbCSz5RfInSeQAwaW/jmagvLLabOaSzE8m9o1AlzCumzoKhy1OLr2VJAjk7l53MtyuXTsVJCors7woLCXvcnJysHv3bpNxuS/j4tSpU/qvpXtdc19LnDlzpkHnnZycjM2bN5tc9u7dq33w8ccNB+7cCURGAs89Zxh7/33t2OefG8YefVQ7dvSoYUwCYl27Gu4XVQGz90m6lmHst9+0z3vxRcPYv/6lHfv1V8OYlBWUsSxDmTd07w4MM+ojdOyY9piHHzaMSY8uGXv3XcPY9Onase2G3gAYP147JvV0RUWF9v6VVxqO2bpVOzZjhmHsnXe0Y199ZRh78EHt2IkThrEhQ4CePQ33MzK0xxhnu61Zox17+WXD2OLF2rE//jCM3Xyzdqzm34fSubPUWzTcP3xYe8w//qHu5pflY87Hd+LR3x/VB5lCPUPx76SBmH/je/A9cNzwXOnzFRVluF9aqn2tq682jG3Zoh2bM8cw9tZb2rFvvzWMPfCAduzkScPYwIHyD99wPyVFe8xddxnGfvpJO/baa4axF17Qjv35p2Hshhu0Y/n5hrFOnYAxYwz3DxzQHmP87/qTT7Rj//2vYeypp7RjCQmGsYsvBtq3R25ROd5ffwJp54rQPT0JnocPYtmGRDWODRu0z5s3z/C8pUu1Yz8assZw333asdOnDWP9+qGqX39Vk37toXS8+8NOPDtpGq7/50fo+/wvGLbod9y5LB7P/3gAn8afwtbEbLNBJvnjPKYsF5ed2oWHRnbAKzf1w/ePjsK+zx/HxtXz8dHkoZh9dS/c6nEOg0f0RsDs6YYny3sg5yXviY68VzIm752OvKfy3urIey7HyM9AR342MiY/Kx35GcqY/Ex15GctY/Kz15F/E/JvQ0f+zcgx8m9IR/5tyZj8W9ORf4MyJv8mdeTfqozJv10d+Tdt3MNOPnPlmGeeMYx98IF2bMUKw5j8H5Ix+T+lI//X5P+cjvxflGPk/6aO/J+VMfk/rCP/t2VM/q/ryGeAjMlngo58Vshnho58lsgx8tmiI585MiafQTry2SRj8lmlI59hMiafaUI+4+S+fObpyGehjMlno458ZsqYcZ9D+WyVMfms1ZHPYPks1pHPaDnGqBSs+iyXMfls15HPfBmT3wE68ruh9ue8/A4x3lwhv2PkGPmdoyO/i2RMfjfpyO8sGZPfYTpXXKEd0ykv196/yugP0/h47ZhRyVq8/bZ2zKg8LqZM0Y4Zl+kdPNj0sy0tTXvMnXcaxn7+WTv26quGsUWLtGNr1xrGbrxRO5ZrVEYoNhYYPdpw/9Ah7TGPPWYY+/RT7djy5Yaxp5/Wju3Zg+Zgk/mE7t8Z5xMXNp+45UZgYBjw8xzggwnAix2BT24ANvwfcGaHaZCp2hnofClw2fNAh2nAG+VA8eXA8IeB8N6G/3M181nZLPHjlFG4dtkokyDTRQfL8N33Qbin9z3aIFMbm0/oFRVpj/nb3wxjFzifUBcdeUyOkWN15DVkTF5TR76WjMnX1pFzkjE5Rx05d/kedOR7k2Pke9XhfMLwXnA+od6G1NwSfLDkU0ya/DpGvvgHXlh10CTIpIJLscF44bo+2Lr+ZXy65B7cPqyDNsjE+YRjzCdq/ta0Fs4p2tYahSJ/d8mYfG7qyN9nRnMKcer6i3HPwj54c/eb+iDT8KNl+OYbP0OQyZpzisSDwIhQ4Mn+wL+HAa90A76+H9j5Ud0gU6GUiBkLXPsG8PgeYH1X4KFvgE4TDEGm5p5TyDrb/4x+b3NOYXgvuEZheC+4RqEPLn390WpMvmMRBs9bjae+3IPfD6WbBJkkuPTkZd3w2+nv8cu/bsXjA4IMQSauUcDe1yiEw25nLCoqMhtkEpKppDvGzc18PWkpuffdd9/h5ptvxmuvvYY+ffqovk8y7urqivLycvV83esIc1/P+Gs1xLJlyzDP+A9Za3u5G3A2GSiq1N6Wuv6iqhI4/JN2TPQ3WjCmZrHp7CbM3TQXqVWp+rFrYq/Bc0Ofg/82o4AAmfVF7EjMWfQbSiq0E/zDYTHqesHKA1iy+hDm93KH0a9uiyrghJN+4Th6PBfHj5ZoS9+NfBTHvUNR/C+jPwi71kxAS2sCA0ZcnZ0QE+yNrpmn0GXnBnS57xZ0vWgwOoV4w+PGG7R/aLz/T8CrpoFohVGghYioGTT7fIKsx6kayDsCrN+t3Y3b/U+gZxUQ/3rdY53dgOihgF8v4IX/AqMmAfPe1j6WvAKottwP9FTeKSzYsgBbRufp95KFeIZg2oCnccW0B+A0yGGn/UR0Hmme/vi5OhKr/rMJ25JkwTkACAvQPy5FPIaVZ2Li9tUYv3Quwvr20D5Q3rC/Yal145yCapONK18e+RIvX52FYhdXNebu7I4n+z2G26ZPg2agleYUzlVARDHwyyztHCklARgvi86JgNF+QMXJE+hxmTZjac0B4JMVwP+eAgaO5Q+QyE7lunriV+9Y/PThNqzXZS61N9qkJbkMmhJctWM1Jj5yE7r8reb/83t1+0eSY3Cqlt8gDiguLg7p6elIk51GtUjw6Msvv1Tl7iwFmoQcM3XqVKSmagMBzs7OqueSvO63336LPXv2oG/fvvj6669x44034q233sLDxlk7akPEAZUdNX36dCyS3UwN2C102ngnJKB2ID/44IPYtGmT2fJ8jaILJOnIHw+yM9ZJA7jWLIILNkZuNoXlhXhl+ytqYqYT5BGk+iFc0uGS5vvCrcgX25Lx7NdGu4cs+Nekvrh5iHZXUWlFJRIzC2tK3mkvR9Pz1Zi5NFxz3F00Rn2T5NpX3e4Y7AVXZ4dNACUiOyAZRyNHjrTO7/qWmE+Ym1NYwjmFKdkBnX7A0D/g5EagVII/Zsj8LGqgoRRe+2GAm9F8rQHKK8uxfP9yvLPnHZRVabNvneCEm7vfjMcHPs4SvUStVHpeCX7el6rK4m1Lykbtv+oluDQkJghX943Elb0jEOan3SBJjs8h5xTkMDKLMzFn4xysP7NeP9YruBcWj16M2IDYC3vx8hLg9FbDHEkyuavqbvRU3HyAjiMNc6TwOLPlgm1q6QAg+4S2R+bUXbY+GyK7IJlLv+p7Lpkvi9c93BdXxUWyLF4rm08Ih93aGBUVpYI8EkyqnWkkZeykrF59QSZx00034YYbblCTqPz8fHTv3h1hYWGq15KLiwu6dOmi/1q6161NN2aurJ457du3V5dmw8Uem9qashVzNs3BmYIzJg0ypw+bjkCPQJuem6OQsnhzvq+n8bmRGd/uxU/7UnAyqwgnswpR1cCwuY+7i1EwyQddw33QJdQX7QI9VSNkIiJ71+zzCXMsbV5p62R1N+u4oX+A9BIoMipFWZsslOgWTTqOADya3kB7V/ouzN88H8fOGUprdgnooja39A/r3+TXJSL7lJFfitX7UrAyIQVbzQSXxJCYQEyMi8SEuEiEM7hE9jqnILv028nfMG/zPJwr1Zbb1DhpMCVuCh7s9yBcNdrMpkapLAfO7KwJLP0JJG8FKi1U/3B2BzoMq5kjjQWiBgDOTfiaRGS3waWJfSNVgEnW4ah1cthA05AhQ/DLL79g69atGGNUc7WkpET1Wbrooosa9DqSxdS/v+EPcclu2rVrF8aOHQuvmjJYkj0lwSyJ9NW2paY/yWDpEUFtVlF5EV7b+RpWHDL0mAl0D8Ss4bNwRcwVNj03R/PVztP6cnnnU1FVjXWHa+fUGwR6uaKrZCWFGwWVwnwR7ucOJ9nmSUREDd+8wl2bBudOAYnrDTty87X9PM0K7moILElzau/gC/5Xl1uaq+YdXx0x9IGQkjYP9XtI9WFq0mIQEdmlzAIJLqViVUIK4hOzzG6sGtRRG1ySxZsIf2YuEVHjSG/pF7e+iB+O/6Af6+DbAYvGLEK/UNMyV/WSlg2pe42yujcB5dJMyQzpGdlusGGOFD0EcOXnF5GjBZdWJZzFhmOZZoNLPSK0mUsMLrUdLRpoOnz4MHJyclTWUKw0rroAt9xyiypVJ/2VjANN7733nuqXdMcdd+jHjh8/rnou9ehRU4vagqqqKlVKr7KyEjNnztSP+/j44JprrsE333yjyun1q2n6W1BQgPfffx9du3ZVWVDUNu1I24HZG2cjOT9ZP3ZZh8tUkCnY88IXk9qaXw8Yelo1lASOVEDJpOydj7apMRER0YXKT9NmKqmspfVATqLlY/3ba3fiqoWTMYCfNjPeGqTi9ZqkNWoxKKvEkDU1Mmqkmne09+WOdKLWIKugFGv2p2HV3rPYfNx8cGlAhwB9cCkqwNMWp0lErcC21G2YuWEmUgpT9GM3d7sZTw1+Cl7ny2CXtMqMw4aMpaQNQIk2G6ouJyCynyFjqcNwwJ1ZDUSOVoHolwOpKnOJwSVqkUDTxo0bVTk56ZOk89///hczZszQ90ISUqbujTfewKWXXtqkryNZRo8++ijefPNNVf7uqquuwsGDB7F06VKVjXT77bfrj5WvcfLkSfXHuY4EiSQ4dP3116NTp07Izc3FihUrsGPHDixcuBDjxo0z+XqLFy/G77//jiuuuAJPPvkk/Pz8VFBLvtdVq1YxO6INKqkowdJdS/HJgU9QDe2/LT83P8wcNhMTOk3gv4kmyi+xUKPZAtkhsfqJhmUwEhERNUhRtra3km5HbsYhy8f6hJtmLAXGaJujWNnp/NN4If4FbDyz0aQH5LNDnsVVna7ivIPIwWUXlmHNfu3izabjWag0E13q3z5A9VySsnjtGFwiogtQWlmKN3e9if/u/69+PSPEMwTzRs7DRdEW/r6WNbWcJMP8SC6F6Za/SGhPoznSKMCT7QSIHA2DS2TTQNPs2bNV4EYXaPr0009x3333ISAgAHfddRciIyNVs8nvv/8eEydOxLp16zB8+PAmfS3JZoqJicG7776rgj3Sl+mxxx7D/PnzoTlPk0Dp3ySZSZ999hlSUlJUmTwpx7d69WqMHz++zvHSr0mCaNOmTcOLL76IsrIyDBw4UB1/2WWXNen8yXHtydiDWRtmISkvST92cfTFmDNiDkK9Qm16bo7O16NxH0uBXvX3YiMiIjqv0gLg1GZDn6WUBFlNMX+sR4A2U0mXtRTSrVkCSzrlVeX4+MDHeHv32yipLNGPT+o6CU8OehL+7k3v8UREtpVTWKZ2BkvPJUvBpX7R/qqnwYQ+kWgfxP54RHThDmcfxrT100x6PEpVFlnPqNNbOu+sabng3FOWXziwk+nmG99w/riIHDi4tGpvCjbWUxZPZVb3jUTnUGYnUjMFmvbt24e//e1v+vsS9OnTpw/++usvFWzSkeDOiBEjMG/ePPz8889N+lrSX+mpp55Sl/okJRmCAcaBJslgaoyePXuqABm17V0//979b7Xrp0oaoktgxNUX04ZNwzWx13A3sRWM6hKCLSeyG3z85b04eSUiokYqLwFObzUsmpzZAVRZyKh18wE6jjQsnIT3ATTOLfKWJ2QkqKbcR3IM/bJi/WPVQtCg8EEtcg5EZP3FmzWyeJOgXbyRnqO1xbXTBpdkAYfBJSKylsqqSvz3wH/xxq43UFEz7/F29caMYTMM6xmFmTXlgmvmSFmGYFQdvlGG+ZFswgnowB8WkYNicInsMtCUn58Pf3/tzsri4mIcPXoUy5cvNwkyCclseuihh1RJOiJHsC9zn8piOp57XD82ut1oPD/ieYR7M9hhDRn5pfh+Vz0N1WvxcNVg0qBoq3xtIiJqxSrLgbO7DBlLp+KBylLzxzq7Ax2GGXoIRA0AnF1b9HQLygrw+s7X8fnhz/XlbNw0bpjSdwom95kMN2dm8xK1tobZfdr5YWJclAoudQhm5hIRWb8Er/Ri2pm+Uz82OHwwFg6ZhqjME8CaGdo5Uto+yy/iFazNVNLNkYI7N2tWt915uZvpfQnKiZyTpo89bdggRGTPdJtfpGwvM5fILgNN0dHROHJE+6Hq6uqqso7c3d3NHivjVVXarBAie1VWWYb/7PkPPtj3ASqrK/W7fqQnwvVdrmcWk5Wk5BbjjvficSKzsMHPmX9tH/h7tuziHxEROQCZX6btNezGPbkJKCswf6zGBWg3yLAjN3oo4OoBW5B+or+f+h2L4xcjvdjQ82BoxFDMHj4bMf4xNjkvImq8vJJy/KaCSyn462iG2eBSr0g/feZSTIg332Yiapa5xXfHvsOLW19EUUWRGnN1csbjvr1wV3ISNPHDgZpqLXW4+wExow1zJOm5dJ42FW2Km5f2vXPie0KOGVzacNR8ZrWUxZOekFfFRSKWZfHIloEmKZu3bNkyPPHEEwgLC8OVV16Jf//737jxxhvh4mL4ckVFRfjggw8QFxdn7VMgspqDWQcxc+NMHM05qh8bHjkc80fOR6RPJN9pK0nOLsLt729Bcnaxut8t3Ac3D26Pl9ccRklFldlMJgky3TykPX8GRESkbU6dcbgmsPQnkLQBKDln4Z1xAiL7GXbjdhgOuNu+rnhKQQoWxS/CutPr9GMB7gF4evDTuLbztdzYQuQA8iW4dLAmuHQkE2WVdeexXLwhopaSVZyFeZvmYu3pP/Vj3cvKsSg9Bd3KE+s+wcUT6DjCEFiK6Ac4W33Z0HExU4kc1Lki6QmZVm/ZXs5PyBqs/htj5syZ+PrrrzFkyBA899xzmDJlirpIf6PbbrsNEREROH36ND755BOcOXNGHUtkb6Tx9vsJ7+PdhHdRUa2tXezp4qkWe27qdhMXe6woMbMQd7y3BWdztQ3Oe0f54eP7hyHI2w03DWqPr3aexpLVh1TAycNFg2ev7IFJA6Ph78VMJiKiNh1YykkyZCzJpdCQAVSH7MDVLZpIvyWvINgL6ZGw4tAK1S+huEK74UJIcEnmHXWachORXSkorcDvB9OwMiEFfx7JQJmZTVLdw31V5pLsDO4SZvvANhG1YpUVQOoerNv3CeamrkU2tFVZnKqrcV9uHh7NyYW+AK/GFWg/1DBHkgxvF/MViYjIAYNL+9Owaq/l4FJPyayOi2DmEtlvoCkwMBB//vkn7rjjDvzjH/9QC/KSqpuRkYGFCxeqY+S+r68v/vOf/+C6666z9ikQXRBpuC29mA5mH9SPDYkYorKYon3ZD8iajqbl4/b341VvJtG/fQD+O3movhyeBJPuH90JH29OQlJWESL8PTB5dCerngMRETmIvLNAolFz6txTlo8N7GRYNJFeAr722Utxf9Z+zNs0z2TO0dGvI+YMn4OhkUNtem5EZFmhBJcOpaueS2sPmw8uSYa+6rnUNwJdwnz5dhJR85ULzjionx8VntyIJT7O+NrXENRuV16BhRlZGFRWblouuP1wbfk3ImoVGFwiW2uWHNgOHTpg/fr1+Ouvv/Dzzz/j8OHDyM/Ph6enp+rhNHToUBVgCggIaI4vT9TkHcXL9y3HW3veUreFh7MHnhj0BG7rcRs0rLtrVfvP5uKuZVuRXVim7g/tFIQP7h0CH3em5hMRkazkZgFJRoGlLEMZ2zp8I7Vl8NTCyRggoINdv4VF5UUqg+mzQ5+hqqYvgovGBff3uR9T+k6BuzN3ExPZm6IyyVyS4FIK1h5OR6mZ4FLnUG9c3VeCS5HoFs7gEpHycreGvREsS9YwktWddbymVLDMk9YDRZnqoV3ubpgRGozTrobqHzdUuOLZqCvhPeYSbVa3hz//YRK1weCS9Fya0CeCPZeoWTXriu5FF12kLkT27sS5E5i5YSb2Ze3Tjw0IG4AXRr2ADn72vVjliHYnn8Pdy+KRV6IN6I3uEoL37h4MTzdnW58aERHZSkkucHKTIWspba/lY72CtZlKuj5LwZ0BJyc4gnXJ67AwfiFSC1P1YwPDBmLuiLmIDYi16bkRUd3g0tpDGVi19yz+OJSOkvK6waVYCS7FRWJi3yiVxSQVPYioHuVFgGyykI2crsymaZBzyablgvPPmr6lAN4K9McH/n6oqvkMCnLxxtyh03BJV1YRImqtwaWVe1OwyUJwqZeUxasp29spxNsm50ltD1MHqE2rrKrERwc+wpu73kRZlTazRnYRPzbgMdzZ8044axj4sLZtSdm4b/k2Vc9eXNIjDG/dMRAernyviYjalLIiIHmLYdHk7C7twpM57n5AzGhDcCmsF6DRwJGkF6Xjxa0v4teTv+rHfN188dSgp3B91+uZOU1kJ4rLKrHucLpavPnjYDqKy7X9TYzJgs3VNYs30jybwSWiRmQqLR0AZJ8AgmKBqbv41plTkG4aWMpJtPg+HQtqj+mBPjhUVagfuzj6YswdORchniF8f4laiZzCMvxyIBWr9qYyuERtL9BUUFCA77//Hlu2bEFycjKKiorg5+eHHj164KqrrsLIkSOb60sTNUhSbhJmbZyFPRl79GN9Q/piwegFiPXnjuLmIDst7v/vdv0f7JK2+/qtA+Dm4liLhURE1AQVZcCZ7YZFk9PbgErtJo86XDyBjiMMPQQi+gHOLg67qeWLI1/g9Z2vo7DcsAh0Vaer8MyQZ7gIRGQHSsoluCSZSyn4/WAaisrqBpc6Bnup4JL0XeoZyeASEVlRcQ6QtNEwR5KeS5Z4h6m5UVXMGHxSfQ6vH/oYZTVBJk8XTzw35Dnc0PUGBsCJWgEGl8jRNMtf7CtWrMBjjz2GnJwcVEv9WEg1Eyf97cWLF+Piiy/GRx99hHbt2jXHKRBZJL0QPj34qVrwKa0sVWOuGlc82v9R3NP7HtUjgaxPatk/+PEOfbPkv/WPwis39YOLM4NMRER25+1RQGGG6Vihtv4/ck6a9lvwDgUe3lj3NaoqgZTdhkWTU1u05XLM0bgC7YcaAkvSqNrF8fsUHc4+jPmb5yMhM0E/Fu0TjdnDZ2NkO266IrJ1cOnPIxmq55IElwrNBJc6BHmpsjMT4yLRO8qPC7dEZB2lBdp5kfRZkjlSimx+rVv6SvEI0GZ163pRhnZHSmGq2jS7NXWr/rD+of2xaPQitPdrz58SkQNjcIkcmdVX1H/++Wfceeed6N27N55++ml4eXnhjz/+wOrVq/HWW28hMjISq1atwrJlyzBu3Dhs375dZToRtYTkvGQ1IduZvlM/1iu4FxaOWogugV34Q2gmq/el4rEVO1FeqZ083zK4PRbdEAdnDWvYExHZJQkyFaSZf6y60vxjVVXaHbi6wJLszC3NNf8a0pchaoAhsNR+OODWevo0FFcU4+09b+Oj/R+hUt4vmXQ7uagNLQ/2e1DtOCailldaUYm/jmRiVcJZ/HYwXV/K2Vh0oKcKLl0dF4U+7RhcIiIrKC/RZnLr5kiS4V1V9/NHcfUGOo40yuqOA2pK+svm7ZUnVmJx/GLkl+erMdkoK5tm7+t9H0v/Ezl4cGllQgo2H88y23NJNrxIyV7Z/BLDnkvUVgJNkq00YMAAxMfHw9lZ+8tw6tSpeO6557Bw4UIcP34cEyZMwL333ouxY8fixRdfxKJFi6x9GkR1spg+P/w5/m/H/6nFH92E7KG+D2Fy3GSV0UTN44c9Z/Hk57tRWfOL8u4RHfH8Nb2hYZCJiKh1kCylL+8FEtcDRTVZT+aE9zEsmsgCioc/WqMNZzbghS0v4EzBGf1Yv9B+mDNiDroFGmWCEVGLBZc2HJXgUgp+PZCGfDPBpXYBnvqeS32j/Zm5REQXprJc23tSl7GUvBWoKDF/rLN7TVZ3TcZSu4GAc931iXMl57BgywL8cvIX/Vhn/85YPGYxegb35E+MyAGDS2v2S8+lFGw6nqVfMzPG4BKhrQeadu/ejfnz5+uDTDr33XcflixZgj179qBfv34YPHiwCjZ98803DDRRs5KFnrkb5yI+NV4/1j2wOxaOXojuQd357jejL7cn47mvE6D7ffn3i2IxfUIP/vFORNSalOYD+7+tOx7cxRBYihkDeLfuhtSZxZn419Z/4eekn/VjPq4+eGLgE7ip+03QSBYXEbUIKdW88Vim2hksO4TzS+oGl6L8PbRl8fpGoR+DS0R0ISSrO22vIWPp5CagrMD8sU7OQPRgwxwpeijg6nHeTSxzNs5BRrGhrPHdve7G1IFT4S6BKiJqVcElmZ9c1YeZS+R4rB5oqpJfsPUoKDD8sh00aBCWL19u7VMg0qeVf3X0K7y87WUUVWh7Qjg7OWNK3yn4e9zf4WpmlxBZzydbTmLWd/v096de0gVPXt6NQSYiotbKv33Nbtwx2sCSf7s2kzX99dGvVdZ0fpm2jI24ouMVmDZ0GkK9Qm16fkRtKrh0XJu59Mv+VOSZCS5F+ntoy870jUT/6ABm2BNR00j/8cwjNYGlP4GkDUBxjoWDnYDIvjWBpbFAh+GAu2+DvkxReRFe3fGqqs6iE+EdoUr/D40cyp8ekQPIlrJ45wkuSalemZ8wuESOzuqBJslW+uSTT/DYY4+ZZDVJQEmj0aBbN0PJkNzcXNXDicjaUgtTMXfTXGw6u0k/1iWgi8pikp5M1LyWbUjEgpUH9PefGd8dj45jDywiolbJ3Q948C8gMAZwalu9947lHMP8LfOxK32XfizKOwozh8/ERdEX2fTciNqC8soqtWgjPZfW7E9DbnF5nWPC/dzV4o2UxhvQPpDBJSJqmpwkQ8aSXCz1shShPYzKBY8CvIIa/eUSMhIwY8MMnMw7qR+7JvYaTBs2DX5u7HNO1FqCS9JzqWOwt03Ok8juA01PPPEEbrnlFpWtdPvtt6tA0h9//IHvv/8eN9xwA0JDDbs6t27dih49elj7FKiNZzF9d+w7/Gvbv1BQrs2ek1I1k/tMxsP9Hoabs5utT7HV+/faY1iy5rD+/uyre+H+0Z1sek5ERNSMXD2BoLb1OV9SUYJ3E97F8v3LUVHTzFuypu/seSce6f8IvFy5kYqouVRUVmHzCQkupWD1/lScK6obXArzdddnLg3qwOASETVBXgqQtN7QZ+ncKcvHymYbXcaSZHX7hjf5LS+vKsd7Ce+peUZldaUa83f3x5zhc3BFzBVNfl0iav7gkpTF+4nBJWrDrB5ouummm3DixAnMnTsX06ZN049ffvnleP/9902O7dq1qwpKEVlDelE65m2eh79O/6Uf6+TfSaWVx4XG8U1ugSDfq78ewRt/HNOPLby+D+4Y1rHRrzVk4W8m97MLStV1cnaRyWPbZl52QedMRETUWFtStmDB5gU4lW9YcOod3BtzR8xlM26iZgwuxSdmq55Lq/elIMdMcClUgkt9IlTPpcEdGVwiokYqzKoJLNVkLGUdtXysb6RpH8rAxv/Na05ibiKmr5+O/Vn79WOj2o3CgpELWIqXyIGDSxPjonBVXAQzl6jVs3qgSTz33HO47777sGnTJpSWlqJ3797o06dPnePmz5/fHF+e2mCAY+WJlVi8dbG+N4ITnHBP73vwaP9H4eFSf2NNss7PYNFPB/He+kR1X+ME/OvGfrhxULRV3l5PNxdUVVdD08ZKMhERkf3ILslWfR9/PPGjfszLxUs14r61+61w1hhKRhPRhZPFmvgTWVi5NwVr9qUiq7CszjEhPm6Y0EebuTQkJgjOMgklImqIkjzg5CZDYCltr+VjPYO0PSh1WUvBXaxaLlj+nl5xaIXq91hSWaLGPJw98PTgp3Fz95vZ55jIDoNLklktGdbmgktx7fy1PZcYXKI2plkCTSIsLAzXXXddc708kZJZnKl2Ff+R/If+Heno1xEvjHoB/cP6811qAVVV1Zj7w358vEVbO1r+wH/tlv64pl9Uk1+TmUpERGRvZXlf2fEKcktz9eOXtL8E04dNV025icg6ZLFma2I2Vu09i9X7UpFZUDe4FOzthitV5lIkhnUKZnCJiBqmrAhIjjcEls7uAmpK05ntPym9lXRZS2G9AI2m2SqzzN4426S/dFxIHBaNXoQY/5hm+ZpE1DhZBaWqF6RkLp0vuCQ9lzoEs4w2tU3NFmgiam6rE1djYfxCnCs9px+T3giys9jTxZM/gBYgv1ynf5OAL7afVvddnZ3w5u0DMb43F92IiMjxSQmb+ZvnY3vadv1YmFcYZgybgUs7XGrTcyNqTfPJ7UkSXErBT3sluKQtmWwsqCa4dHVcJIZ2CoKLc/Ms+BJRK1JRBpzZYQgsnd4KVNYNXiuyftBhuCFjKbIf4Nz8y2Wrk1arjbN5ZXn6fo8P9nsQU+KmwEXD5ToiW2JwiajxbPabKysrC//+979VCvDs2bNtdRrkoKVrFm5ZiF9O/qIfi/aJxvxR8zEkYohNz62t1cp/6ss9+H73WXXf3UWDd+4ahIu7h9n61IiI6EJ5h9YdK8zU7vx1cga8Q+o/1sGVVZZh2d5leG/ve6opt64s7+09b8djAx6Dt6u3rU+RyOEz4refzMGqhLP4eV8q0vPrBpcCvVy1mUtxURgey+ASEZ3vg6USSNljCCyd2gyUF5k/VuMKRA8xZCxFDwZc3FvsLZbA0qL4RVh1YpV+LMYvBovHLEafkLptJ4jIvoJLklV9VR9mLhHZTaApMzMTzz//PANN1Ci/nfwNC7YsUMEmnVu634J/DvonvFyZmtpSyiqqMHXFLqzen6rue7o6Y9k9gzGyi9HCIxEROa6HN9YdWzoAyD6hbXg9dRdaq22p21QWU1Jekn6sR1APzB0xl4s/RBcYXNp5KgcrE1Lw874UpOXVDS75e7riyt7asngjOgfDlZlLRGRJdTWQftAQWEraABiVuDXhpAEi+xsCS5K95GabTSNbUrZg1oZZSCtK04/d1uM2PDnoSVZmIbJhcEnK9m45kW02uNQ3uqbnEoNLRPYZaIqMjMTy5ctt9eXJwZwrOYfFWxfjp8Sf9GOR3pEqi2l45HCbnltbU1JeiUc+3Yk/DqWr+z7uLvjwviEYHBNk61MjIiJqMum/9Mr2V/DtsW/1Y1KK99H+j+KOnnewhA1RE4NLu5LPqYbZsjs4NU/b5N6Yn4eLKrsswaVRXUIYXCJqTd4eBRRm1M2QFjkngZe7mWZIm9voYhxYkg0viX8Cieu1waWimtcyJ6y3IbDUcSTgGQBbKqkowes7X8cnBz8xnKJnGBaMWoCR7Uba9NyI2mJwSTZOy9yEwSWiVhBo8vPzwz333GOrL08OZF3yOszbPA+ZxYZJ5KSuk/D04Kfh4+Zj03Nra4rKKvD3j3Zgw7FM/a7TjyYPRb/2tp20ExERNVV1dTVWnliJl7e/bJIxfVH0RZg5bCaifKL45hI18v/UbqPg0tncusElX+PgUucQuLmw5xJRqyRBpgJD5o4JKcdr6TGd3NOGjCW55J2xfGxwF21QKWaM9uJjP6V9D2QdwPT103Ei94R+7MqYKzFr+Cz4u/vb9NyI2mJwafPxLJhJXFKZSxMlcykuEu2DWDWJqLHYXZDsltQtfmnrS/jh+A8mDbjnj5yPUe1G2fTc2qL8knLc/+F2bE3K1jdl/uT+YegV5WfrUyMiImqSU3mnVEleKWOjE+IZgmlDp+GKjleoEs9E1LDg0p7TuWrxRgJMZ84V1znG190Fl/cOx9U1mUvuLs58a4nIVEEGkGQUWJIMJkv8ooHYsYbgkn87u3s3K6oq8MG+D/D27rdRUV2hxnzdfDFr2CxcFXuVrU+PqNVrSHCpn64sHoNLRI4daMrPz0dOTg46dOhgy9MgO7ThzAbM3TQX6UXa8mzib53/hmeHPgs/NwY2WlpuUTnuWb5V7U4VYb7u+PSBYega7tvi50JERHShyivL8eH+D/FOwjsordT2iXGCE27ufjMeH/i4WgQiovMHl/aeyVWBpVV7U3A6p25wSUosX94rXO0OHtONwSUiqkdRFvByF8uPS2k9XSk8uQR2Aux4Q4hsZpmxYQb2ZOzRjw2LHIYXRr2ACO8Im54bUWuWqXoupar5yZYTDC4RtZlA09KlSzFnzhxUVlba8jTIjhSUFajSNV8f/dpkZ/HzI57H2PZjbXpubVV2YRnufD8eB1Ly1P0ofw98OmU4OoXYpnkqERHRhdiVvgvzN8/HsXPH9GNdArpg7oi56B/Wn28u0XmCS/vP5mGlCi6dRXJ23eCSt5uzNrjUNwpjuobAw5WZS0TUAFXajB89D39tppIusBTaw64DS8afk18d/QpLti1BcYX2M9Ld2R1PDHwCt/e8HRonlgolao7g0up9up5LDC4R2QpL55Hd2Hx2M+ZsmoPUwlT92NWxV6vyNaxbbBvp+SUqyHQkrUDd7xDkpTKZWKuWiIgcsSTvaztew5dHvtSPycLPQ/0ewj2974GrxtWm50dkz4umsuFIl7l0MquozjFebs64rKcElyIxtlsog0tE1AROQJdLDYGliL6AxrEC1dJXWiqz/HX6L/1Yz6CeWDxmMToHdLbpuRG11eCSzE0m9GHPJSKHDDT99ZfhF+r5JCYmWvvLkwMqKi/CqztexeeHP9ePBXkEYc7wObi046U2Pbe2LCW3GHe8F48TmYXqfmyoNz57YDgi/D1sfWpERESNWiRfk7QGL259EVklWfrxkVEjVRPu9r7t+W4Smfl/czAlX9tzaW8KEmvmg8Y8XZ1xac8w1XPp4u5hDC4R0YXxCQXuNFQ2cTS/n/wd8zbPQ05pjrovmUv397kfD/d7GK7O3MxCZM3gkmx+iU+0EFxqH4CJcREMLhG1hkDTxRdf3ODGyfIHDJsst23bUrdh9sbZOFNwRj82PmY8Zg6biUCPQJueW1uWnF2E29/foi+H0iPCFx/fPwyhvu62PjUiIqIGO51/GgvjF6rej8abWZ4d8iyu6nQV56FEtf42O5yWr81cSkjRbzYy5uGqwaU9tJlL47qHwdPNsbINiMie2X9ZPEvl/2Uzy/fHv9ePySaWRaMXsSQvkRUwuETkOKweaHJ3d0evXr1w++23n/fY33//HWvWrLH2KZCDZDG9vvN1fHboM/1YgHsAZg6fiStjrrTpubV1JzIKcMf78UjJLVH3+7Tzw8eThyHQ283Wp0ZERNQg5VXl+OTAJ3hr91soqdT+PhOTuk7Ck4OeZEleIiNH0vK1PZcSzuJ4hvng0iU9wjAxLgrjeoTCy43V14mIxPbU7Zi5YSbOFp7VvyE3dbsJTw9+Gl6uXnyTiJooI78Uq/en4qfzZC5dHReJCXERiA7k/zcie2D1vxLi4uJQVVWFp5566rzHlpSUMNDURptwz9owC6fyT+nHLu1wqSpfE+IZYtNza+tkoUGCTPJLXQzoEIAP7xsKf0+m+hMRkWPYm7FXla45nHNYPxbrH4s5I+ZgUPggm54bkb04KplLUhYvIQVH07W9OI25u2hUxpJkLkmQydudwSUiIp2yyjK8uetNfLj/Q1RDuwIe7BGM+aPm46Loi/hGETUBg0tEjs/qfzEMHDgQH374IcrLy+HqysVpMiipKFGTsY8OfKSfjPm5+WHGsBksX2MH9p3Jxd0fbEV2YZm6P7RTED64dwh8uLBAREQOUrpm6a6l+N+h/+nnGW4aN0zpOwWT+0yGmzMzc9uiIQt/a9Bx22ZehtbuWHqBtudSQooqkVebm4sGF3cLVcGlS3uGcw5IRGTG4ezDmL5hOo7mHDXZOCsbWqQ8LxE1PrgkWdVbE7PNZi71Vz2XmLlE1CYDTTfeeCNKS0uRmZmJyMjIeo+99tprER0dbe1TIDuUkJGgUsqT8pL0Y2Ojx2LuiLkI9Qq16bkRsOtUDu75YCvySirU2zGmawjevWsw6+4TEZFD9JX5/dTvWBy/GOnF6frxoRFDMXv4bMT4x9j0/Mi+FJdVoqq6GhonpzYxz5GSyKrn0t4UHEo1E1xy1uCibqG4WgWXwuDrwY2CRGRF3mb+1i/MBKorASdnwDuk/mPtSGVVpdo0+8auN1SJXuHt6o3pQ6fj2s7Xsu8jUQOl55dgzb5UNTdhcImodbF6oOmyyy5Tl4aW2ZMLWc+4L8Y16Li1N69tsZRy6Y+wfP9yVFVXqTFfV188N/Q5TsbshPxin/zhNhSUaoNMl/UMw5u3D4SHa+tffCEionq83K3uwpDIOWn62NNHbPY2phamYmH8QqxLXmfS81F6I3DRh8xlKl28ZC2SsooQE+yFdc80bN7saBIzC1XmkvRdOpiSV+dxV2cnjDXKXPJjcImImsvDG+uOLR0AZJ8AAjsCU3c5xHt/puAMZqyfgZ3pO/VjUo534eiFaOfTzqbnRtSagkuy8WVCXCTaBXja4jSJ6AKx2HYrV1xRrHb6OsmuTZeW/aDen7Vf9WI6du6YfmxU1Cg8P/J5RHhHtOi5kHkbj2Xigf9uR3F5pbp/VVwEXrtlgCqdQkREZMLNC5BNI04au9hV/Nmhz9SuYpnr6EhwSYJMgR6BNj0/opZ2MqtQ33Np/1nzwaUxXUNV6ZnLeoWz/yYRUQPIWsr3x7/Hi1tfRGF5ofbzVOOKqQOm4q5ed8FZw82ZRA0JLsUnZqPaTHBJ+oJry+IxuETUGjDQ1MrUzlSa+M1EnMo/hQ6+HbDqhlUtcg7lleV4J+EdvL/3fVRKSnxNSvkzg5/BDV1vYEq5nVh7KB0PfrIDZRXaTLPrB7TDkhv7wsXZ9guIRERke+M6NGyHbsvkSBscyDqAeZvnqWudjn4dMWf4HAyNHNrCZ0NkO6eyirTBpb1nse9M3eCSi8YJo7uGqAWcK3pFwN+LZfGIiBoquyQb8zfPV+V5dboFdsOi0YvQPag730iieoJLklW9NYnBJaK2ptkDTcXFxViyZAnuvvtuxMSY1sjfu3cvvv32W8yZM6e5T4NasDGm9GI6nHNYPzYsYhjmj5qPKJ8o/hzsxOp9qXhsxU6UV2q3lNw6pD0WXh8HZ42TrU+NiIjslC2zpEVReRHe3P0mPj34qb4cr4vGBff3uR9T+k6Bu7N7i58TUUtLzi5SZfEkwJRwOtdscGlUl5rgUu9wBHi58YdERNRIfyb/ibmb5iKrJEvdd4IT7u1zL/7R/x9wc+bnals1ZOFvTSrb2xaCS7LGJFnVDC4RtW3NHmgqKirCvHnzMHr06DqBpoSEBPUYA02OT5phLtu7DO/seQcV1dpeP7II9dSgp3BT95ugsYMyO6T1/e4z+OcXe1BZUxT33pExmHN1L2gYZCIiIjvLkjZe8JFeTCmFKfqxgWEDMXfEXMQGxLbouRC1tDPnivFTQgpW7k3BnuRzdR6XjUIjOwervgaSuRTozUVQIqKmbmpZsn0JvjrylX5MejC9MOoFDI4YzDeVTBSXVaKquhoa2YTl1rbKKDK4REQ2K50nu1+p9TqacxSzNs4yKWEzOHywymJq79vepudGpr7Ynoznvk7Q18Z9cGwspl3Zg+UMiYjILqUXpau+CL+e/FU/5uvmqzayXN/1em5koVbrrASXajKXdp2qG1yS/UEjO4dgYt9IjO8dgSAGl4iILsju9N2YsWEGkvOT9WPXdbkOzw15Dj5uPnx3qU6m0sVL1iIpqwgxwV5Y98y4Vv8ONSS4NLBDAK6Ki1SXqICWr4BARLbFHk3UZBVVFfhw/4d4a/dbKqNJeDh74IlBT+C2Hrdx8cfOfLw5CbO/36+///ilXfHEZV0ZZCIiIrtTWVWJL498idd3vo6C8gL9+FWdrsIzQ55BiGeITc+PqDmk5EpwSRZwzmKnheDS8NhgfXApxIflIomIrNFj+u09b2PZvmX60ryB7oGYO3IuLu1wKd9gatN0wSXpubSNwSUiOg8GmqhJTpw7obKY9mbu1Y/1D+2PBaMWIMbftEQi2d7760/ghVUH9fefu7IHHr64s03PiYiIyFK/R2m+nZCZoB+L9onG7OGzMbLdSL5p1Kqk5ZVoM5cSUrD9ZE6dx50kuNQpGFf1jcSVvSMQ6svgEhGRtRw/dxzT10/HwWzD38pjo8fi+ZHPc1MLtVnpeSX4WTKX9tYfXJrYNwoT+kQwc4mImj/QNHnyZHVdWlqqrpcsWYJPPvlE3ZYm0suWLWuuL03NvMP4k4OfYOnOpSirKlNjbho3TB04FXf2vBPOmrZVl9YRvPnHUbz8yxH9/bnX9MJ9ozrZ9JyIiIhqK64oxn/2/Acf7f9I3+/RxckF9/S+Bw/2e1D1fiRqVQs4sjv4ZN0FHAkuDY0JUj2XxveJQJivh61OlYioVZLMpU8PforXdrymX9eQeYaUybuh6w2s+kFtDoNLRGTXgaY//vhD/XKuqtKmHu/evRuHDh1St2WcHM/JvJOYvXE2dqXv0o/FhcThhdEvINafjbjtjfRGe+WXI3hz7TF1X/7bLbwuDrcP62DrUyMiIjKx8cxGLNiyAGcKzujH+oX2w5wRc9AtsBvfLWoVpWfW1JSeMdfXQOZpQzoGqbJ4sjs4zI/BJSJqHcZ9Uat3jW8F4N0O0FQARo+tvXlti5xPamEqZm2YhfjUeJM5x+LRi9Hejz2mqe0438YXMahjoOq3xMwlIrJpoCkpKUldZ2ZmIiwsDJ9++ikuueSS5vpy1My7fVYcWqF2+5RUlqgxV40rHun/CO7tfS9cNKzAaI9BpoWrDuL9DYn6mv5LbuyHSYOibX1qREREepnFmfjXtn/h58Sf9WM+rj54YuATuKn7Tez3SA4tI78Uq/en4qeEFMQnZqHKzALOkBjdAk4kIvwZXCKi1q/YCajWOKkAu2cL/428KnEVFm1ZhPzyfH3mtKxr3NfnPq5rUJvA4BIRNadmjxAwe8mxJecnqyymHWk79GM9g3pi4eiF6BrY1abnRuZVVVVjzg/78MmWU+q+i8YJr93aH1f3jeJbRkREdrOJ5Zuj3+DVHa8iv0y72COu6HgFpg2dhlCvUJueH1FTZRVog0uyO3jLCfPBJdkdPFGCS3ERiPRnSUgiat1qZypN/CAOp5w16FAJrGqhLKbc0lyVOb0maY1+rLN/Zywaswi9gnu1yDkQ2bIf5M97U/DT3tR6M5c4NyGiC8VUFLK4APTl4S/xyo5XVM8E9Y/FyUX1SLg/7n6V0UT2p7KqGs99nYCvdpxW992cNXjz9gG4oneErU+NiIhI33h7/ub52Jm+U/+ORHlHYebwmbgo+iK+S+RwsgvLsKYmuLT5RJaaj9U2QJpmx0Wq7KWoAAaXiIhasjzvnI1zkF6crh+T/tKPD3wcHi7MJKW2G1warCuLx40vRGQlDDRRHWcLzmLOpjmITzHULJb+CJLF1COoB98xO1VeWYV/frEHP+45q+67u2jw7t2DMbYbd4UTEZHtlVaW4t2Ed/HBvg9QUVWhxpydnNVij5St8XL1svUpEjVYji64tDcFm46bDy71ax+Aq2sWcKID+e+biKglyYbZV7e/iv8d/p9+LNwrXPWYHh45nD8MarXBJZmbbD+Zw+ASEbW+QJOrqyvGjh2LwMDAOo+Fh4fjoou4c9VeSM1iKWOzZPsSFJYX6heAHoh7AA/2fRCuzsxislelFZWYumIX1uxPU/e93Jzx/j2DMbJziK1PjYiICFtStmDB5gU4la8t6yp6B/fG3BFz0TO4J98hcgjnisrwy/40rJTg0rFMVJgJLvWN9tdnLrUPYnCJiAgvdzN9EwKcAWcXQDadGD/29BGrvVn7Mvdh+vrpSMrT9g4XV8dejenDpsPPzY8/FGo1UnNL8PM+yVxicImI2kCgyc/PD2vXmq+7e9lll6kL2V5qYSqe3/Q8Np7daFKzWLKYeof0tum5Uf1Kyivx8Cc7sPZwhrrv6+6CDycPwaCOQXzriIjIprJLsvHK9lfww/Ef9GNeLl6YOnAqbu1+K5w1zjY9P2o7covK8eWOZLUgI+R62YZE3DgwGv5ervU+75cD2sylDUfNB5fi2vljYt9IXNUnEh2CGVwiIqqXk5PptRWVV5Xj/YT38U7CO6isrlRjEliaPWI2roy5kj8YalPBJZmbTOgTiQh/logkopbB0nltnGQxyeLPS1tfQn65thm3xkmD+3rfp8rYuDm72foUqR5FZRV44L/bVckW4e/pio/vH4q+0QF834iIyKbzi++Pf6+CTOdKz+nHx7UfhxnDZiDCm70DqeV8sS0Zc77fh5KKKv2Y3F6w8gCWrD6E+X/rg5uHtNc/lltcjt8OpKng0vqjGSivrLuC0zvKTy3gSPZSx2DvFvteiIgcTu1MpW8mApLhHNgJuH+V1b5MUm4SZmyYgb2Ze/Vjo6JGYf6o+QjzCrPa1yGydXBpW1KO2WOGxNT0XGJwiYhshIGmNiyjKEM14153ep1+LMYvRtUs7hfaz6bnRueXX1KOyR9u008ygr3d8MkDw9AzkqUAiIjIdhJzE7FgywJsS92mH5MFHgkwXdrhUv5oqMWDTM9+nWDxcQk4yeOSIe7r6YJVCSn460gmyioNQSkdmWNdLZlLcZHoFMLgEhGRvWxu+fzw52pzS0mlNmvVw9kDTw1+Crd0vwVOzZA5RdSSwSWZm0jmUm3yT1sylxhcIiJ7wUBTK59wFZQX6G8bj/+U+BMWxS9CXlmeGnOCE+7udTf+MeAf8HBhWq29kzIudy/fij3J2l3iYb7u+GzKMHQJ87X1qRERURtVVlmGZfuW4b2E91TpGt384vaet+Mf/f8BHzcfW58itcH5kmQyNcScH/abHe8R4asPLsWG8t8wEZE9SS9Kx5yNc0xaAPQJ7oNFYxahk38nm54bUVODS5K1pCuLZym4JBnVE+IiEe7H9Tsish8MNLVi8anxqjeCKK0sVddZxVlql/Hvp37XH9fBt4PKYhoQNsBm50oNl1VQiruWbcWBFG2QsF2AJz59YBhiuLOWiIhsZHvqdszfMl9lM+n0COqBuSPmok9IH/5cyCa+2nnapFxeQ3UP99X2XIqLRJcwBpeIiOzRmqQ1am0jtzRX3Xd2csaDfR/EA30fgKvGcu89IkcMLg3pGISr4iIYXCIiu8ZAUyslWUtv735bfz+3LBerE1erLKacUsMvrjt63oGpA6bCy5WNix1Bel4J7ng/HkfTtZlqHYO9VJApOpA/PyIiavksaVnceXXHq/jm6Df6MU8XTzza/1E1x3DRcKpJtvPrgdRGHR8d6Inl9w5B13BmiBMR2SupyiLrGqtOrDJpAbBo9CLEhcbZ9NyIGioltxg/701V/SB3MLhERK0E//pvxdlMO9N36u9LRtMzfz2jv9/Opx0WjFqAIRFDbHSG1FhnzxWrIFNiZqG63znUG58+MBwR/kyVJiKils2SlmDTqsRVWLJtiX5cjGk3BjOHz1TzDCJbyy+paNTx/p6uDDIREdmx+JR4zNwwE2lFafqxW7vfin8O/qfa6ELUUqV5v9yRrDKRhFwv25CIGwdGw9/LcjYdg0tE1Nox0NQGsplqk4aY/xz0T2YxOZDk7CLc9t4WnM4p1vcL+OSBYQjxcbf1qRERURubV5wrPYe///J3bEndoh8L8QzBtKHTcEXHK9h0m+yGr0fj/tTx82CpJSIieySbXF7f+To+PvCxfizUM1Rtnh3VbpRNz43ali+2Jav+j8aleeX2gpUHsGT1Icz/Wx/cPKS9SXDpp72pqixefZlLUrL3yj4R7LlERA6tWQNNWVlZSE9PR8+ePfVjiYmJePXVV5GdnY27774b48ePb85TaJNqZzMZkwDTfX3ua/FzoqY7kVGA29+LR2qedrdMXDt/fDR5KAK93fi2EhFRi88ryqrK9EEmJzjh5u43Y+rAqfBz8+NPg+zK5b0isOVEdiOOD2/W8yEiosY7mHUQ09dPx/Hc4/ox2dgye/hsBHgE8C2lFg0yPft1gsXHJeAkj58rLoOzRlN/cCkmCBPjGFwiotalWQNNjz/+OI4cOYKtW7eq+wUFBRgzZgzOnj2r7n/++ef4448/cNFFFzXnabQp58tmWpe8Dvf2vpe7jR3E4dR8VS4vs6BU3R/YIQAfTh7KHbdERGTzeUVn/854fuTz6B/Wnz8NsktX943EC6sOwKitmEUerhpMGhTdEqdFREQNUFlVieX7l+Pfu/+NiiptKVRfV1/MGD4DEztN5JoGtXi5PMlkaohFPx2qN7g0oU8EwvzYAoGIWp9mDTRt3rwZd911l/6+BJYkyPTTTz+hf//+uPzyy/Gvf/2LgSYrqi+bSchjW1O3YljkMGt+WWoG+87k4q5l8cgpKlf3h8cGYdk9Q+DtzoqXRERk+3nFM0OeYZCJ7FZVVTXm/9iwIJOYf20f1aOJiIhsLzkvGTM2zMDujN36sWERw/DC6BcQ4R1h03OjtumrnadNyuU1hC64JBtfruzN4BIRtX6a5nzxtLQ0tG9vqE36888/Y/DgwbjyyisRERGBe++9F7t27Wry61dVVeH//u//0KNHD3h4eKiv9dRTT6GwsLBBz5cMq0WLFiEuLg6+vr4ICQnByJEj8eGHH6odvMbkXJ2cnMxevvrqKzhCNpPOW7vfqvP9kX3ZeSpH9WTSBZku6haK5fcOZZCJiIjsZl7xbsK7nE+Q3Vr400Gs2puibnu7OcPNRWMxk+lfk/qa9FMgIiLbzT2+OvIVJv04SR9kctO44bkhz+HdK95lkIls5tcDqY06vlOIN+KnX4ovHhyBu0fEMIOJiNqEZk2NcHV1RXFxsf7+n3/+qQI2OgEBAaqPU1M9+eSTWLp0Ka6//noVYDp48KC6L8Gr3377DRqNpt4g1YQJE7Bp0ybcc889eOyxx1BUVIQVK1bgvvvuU6/10ksv1Xnexx8bmk/qDB06FI6QzaTDrCb7Fn8iC5M/3IbCskp1/7Ke4fj3HQPg7uJs61MjIqI2hFnS5KjeX38CyzYk6gNJnzwwDLEhPmo3sjTqlh3JHi4aPHtlD0waGA1/L2YyERG1VCCpoLxAf9tYZnEmnt/0PP48/ad+rGdQTywesxidAzrzB0Q2lV+iLd/YUF5uzgwuEVGb06yBpm7duuHrr7/Go48+ih9//BHZ2dm49NJL9Y8nJycjKCioSa+9f/9+vPHGG7jhhhvU19Dp1KkTpk6div/973+4/fbbLT4/Pj4eGzZswBNPPKGyonQeeeQRlSH1zjvvmA003XnnnbBXXxz+osHHfn74c5bPs0MbjmbigY+2oaRcm5It9Xtfu7U/XJ2bNfmQiIioyVnSQyOGsk8C2Y1VCSkqm0lonIA3bhuIAR0C1f37R3fCx5uTkJRVhAh/D0we3cnGZ0tE1PY2sWSXZKvbpZXaPsTi91O/Y96mecgpzVH3NU4a3N/nfjzc72G4OnMzANmer0fjlk/9PPjvlojanmZdvZYAk2QxBQYG4sYbb0RsbKxJoGn9+vWqbF1TSOaRLIJIoMjYlClT4OXlhU8++aTe5+fl5anrqKgok3E3NzdVQs/b29vs8+RrynMlI8re3Nr9VoR4hphcZIIm5Np4XI4l+/L7wTRM/q8hyHTDgHZ4nUEmIiJygCxpInvJCn/y8936vkzz/9YHl/cKt/VpERGRmU0suWW5yC/Nx+yNs/HE2if0Qab/Z+8+wKMqugaOn/RGCL333ntCUymCIAgiCEjvYMOGYkGlCBbUVwEREYTQQUQRBRVREJWS0HvvvYQa0pPvOZNv1wQSSNklyeb/e551d+7e3Ts7idnLPXPmFMtRTGa1niUv1HmBIBMyjZZVUlcbjPMPANmRXTOaevfubWa4Ll26VPz8/OStt94yy+kpXTLv6tWrJoMoLYKDg83SeLcvW6e1mmrVqmWevxt9nS7dN378eClVqpTUr1/fLJ03a9Ys2bx5s3z11VdJvk4/x40bN0xA6qGHHpKxY8ea12YGAYUDZHWX1Ym2tf2+rZy4ccKcrC3vuDzD+oa7+2XnWXlh4VaJiom/MtItoISM61BNnHUqLgAA9xlZ0shqDp6/IYNmb5LImPgJO882LSs9G5TM6G4BAJKZxKIZTe2XtpdL4Zes2zqV7yTD/YeLt5s344ZM5eFKBWTsz3skJdXOddneTnWL3YdeAUA2CTTFxMTI6dOnpW3bttKrV687ns+bN68J6KTVmTNnTOaRh4fHHc8VLVrU1F6KjIw0AaGkaJbVsmXLZODAgdKlSxfrdl9fX7MUX4cOHRLtX6hQIVMTqm7duibbafv27fL555/Lgw8+KCtWrJAWLVqkqN+6XOCpU6cSbdu5c2cKPzUc0Y/bTssr326XmNj4U5a+jUrJyHZVWIYIAJBh5xOa+bz1wtZE23Spm9i4WJMlncfzv6WPyZJGRjt/PVz6zgyW6/9fP0Gzwl9rVTGjuwUAWcL9uEaR3JK8liCTnleMaTRGmhRvYtPjArYQHhUjr3y7LUVBJjWmfTXx82LpPADZj90CTVFRUWapvA8++EBee+01m7+/Zh8lFWSyZDVZ9kku0KRy5Mgh1apVk/bt20ujRo1MDanJkyeb2k4//vijtGzZ0rrvhx9+mOi1GojS/TR76plnnpGDBw+mqN/ffPONjB49OoWfEo7u2+CT8vr3O6xLvDzdpKy83roiQSYAQIaeT5AljaziRniUCTKdvhpm2g+UyycfdqrBuRQApND9uEZxtyV5a+WvJROaT0g0iQXILHRC8AsLtsqWE1dNO18Od7kRHi0R0bFJZjJpkKmLf/EM6CkAOHCgSYM9d6t1lF5ah+nChQtJPhceHm7dJzk6Q0eDS5999pk8/fTT1u3dunUzwSet9XT48GFxcXFJ9j3Kly9vsqECAwPlwIEDUqFChXv2e8CAAdKqVas7+jJkyJB7vhaOZfb6Y/Luj7ut7ZdbVJAXHi7HhREAwD1xPgGIREbHyjNzt8jes/G1VysV8pUpPeuIu6tdy9ACgEOx9zlFctlMFpopndsjt02OBdiS/u6O/mm3rNxz3hpk+v6ZxiZb6bstp+TjX/dJeHSseLo6y/DWlaRTnWLi500mE4Dsy641mtq0aSM///xzmusw3U2RIkVkz549EhERcUdmky7Zp0Guu2UzaYBJA1KdO3dOtF2DU7rc3xdffCHHjh2TsmXL3rUfWt9JXbp0KUWBpuLFi5sbsrdpa4/IuBV7re03Hq1kspkAAEgJzieQ3enFnze+3yH/HIpfdqmIn6fM6h8gvp5c4AGAzHROcbdsJqXPBZ0LkvqFM0fta8Bi6tojMnv9cfPYy81FvunjLyXyxk9oH/BAaZmz/pgcu3xLCvl5Sv8HSjNwALI9u073Gz9+vJw9e1b69OljZsRYMo1swd/fX2JjYyUoKCjRdj3Gtm3bpF69end9vQajLLWkbhcdHZ3o/m4sS+YVLFgwVf1H9jXpj4OJgkyj2lUhyAQAAJAKn648IN9viT+fz+npKoH9A6RgzvjlswEAmcO9spksvtz2pdkXyEy1tD/8ZZ957OLsJF/2qCM1i+fK6G4BQPYNNBUoUEB27Nghc+bMMbWMdBk9XYou4c3VNW1JVV27djVLjH3++eeJtk+bNs3UZurRo4d1my6Bt29f/BeERZUqVcy9LnuX0NWrV019pty5c0u5cuXMttDQ0CSDZFu3bpXFixdL5cqV75n5BOiJ88e/7ZNPfz9gBsPJSeSDjtWlb2NmvgAAAKTUvI3H5YvVh8xjdxdn+bp3PalQ0JcBBIBM5l7ZTLdnNQGZwbpDl+TVxdut7XEdqkmzSgUytE8AINl96bzevXvbrd5M9erV5bnnnjNL3HXs2NEs07d3716ZOHGiNGnSRLp3727d9+GHH5bjx48nmiHz0ksvyezZs+WNN94w2VaNGzeWkJAQE6jSLKzJkydb6zNp1tKjjz4qHTp0MHWZNGC2fft2mTFjhtnn66+/tstnhOPQ3733ft4rM/49atrOTiKfdqkpT9QultFdAwAAyDJW7Tkv7yzdZW3/r2tNaVAmb4b2CQCQtG/3f5vioVm0fxHL5yHD7Tt3XYbM2SxRMfHXD194uLw8FVAio7sFAFmCXQNNt2cL2ZpmM2mNJA30LF++3NRlGjp0qIwZM0acne+erFWyZEmz7J7u+8cff8jChQvFy8vLZF59+umnJnhlUahQIWnRooWsXr1a5s2bJ2FhYVK4cGGTVfXmm29KpUqV7Po5kbXFxsbJ2z/ukvkbT5i2q7OTTHiqtrStUTijuwYAAJBlbD1xRZ5fsEVi/3/u2NttK8tjNYpkdLcAAMl4quJTsvXC1kTbQsJDJDYuVpydnCWPZ55E+wIZ6czVMOk7I1huRMSX0ehct5i83KI8PxQAyAyBJnvTbKJhw4aZ290cO3Ysye263N2sWbPueRwNNOnyf0BqxcTGyfDvdsiSLaesy7vo2r4tqlDTCwAAIKWOXQqVAbM2SXhUrGn3b1xaBj5YhgEEgEwsoHCArO6yOtG2tt+3lRM3TkixHMVkecflGdY3IKFrYVHSd2aQnLseXzbjoQr55f2O1e22ShMAOKL7Fmi6efOmqX8UGxv/j8OESpQgDRWOJyomVl5etE1+3nHWtD3dnOXrXvXMCQsAAABS5tLNCOkzM0hCQiNNu031QiabCQAAIL0iomNkyJxNcuD8TdOuVjSnmSDs5mLXsvYA4HDsHmjSJenGjh1r6iclJyYmxt7dAO77icrQ+Vtl5Z7zpu3t7iIz+vpTQwAAACAVbkVGy4DAYDl++ZZp+5fKLf/rUkucteAlAABAOksdvLp4h2w4EmLaxXJ7mWs3OTyy9AJQAJAh7BqeX7p0qXTv3l2io6NlyJAhEhcXJ926dZPOnTuLm5ub1K1bV9599117dgG478KjYmTw7M3WIJOvh6vMGVCfIBMAAEAqRMfEmok7209dM+2y+X1kWu964unmwjgCAIB0++jXffLT9jPmcS5vNwnsFyAFfD0ZWQBIA7uG6D/55BOpXLmybN682Syd99VXX0n//v2lefPmsmvXLmncuLGMGDHCnl0A7qvQiGgZOGuTrD9y2XqiMqd/falezI+fBAAAQArpBLV3ftwtf+y7YNr5fT3MxZ9c3u6pGkP/casStUNuRpj7kyG3Ej0XPKIFPxsAALKRwH+PytS1R8xjd1dnmd67npQrkCOjuwUAWZZdM5p27Nghffr0EU9PT3F2dk60TF61atVk8ODB8sEHH9izC8B9cz08SvrMCLIGmfLlcJeFgxsQZAIAAEilyasPyYKgE+axj7uLzOzrL8XzeKd7HL3cXc2SxnoPAACyp193nZXRP+8xj52cRCY+VUvqlcqT0d0CgCzNrv/C0qBS3rx5zWMvLy9zf+1a/NIXqmLFijJlyhR7dgG4L67eijRBJsvSLgVzesi8gQ2YDQMAAJBK320+JZ+sPGAeuzo7yZSedaVa0bRlh5OpBAAAEtp0LEReXLhN4uLi2yMfqyKtqxVmkAAgMweaihUrJsePH7cGmgoUKGCW0XvyySfNtv3794uPj489u5DtNPu2WaJ2SHh8QcNTN08lem51l9X3vW+O6vLNCOn5TZDsPXvdtIvm8pL5g+pLybz8bgMAAKTG2gMX5Y0lO6ztDzvVkIcq5GcQAQBAuh2+eFMGzt4kEdGxpj34oTLSt3FpRhYAMnugqVGjRrJq1SoZM2aMabdv314+//xzE3SKjY2VyZMnS7t27ezZhWzPy9XLrHHvpLnAsLkL18Ol+/SNcujCTdMumddb5g9qYIJNAAAASLndZ67JM3M3S3Rs/BTjYS0ryJN1izGEAAAg3S7cCDcr0Vy9FWXa7WoWkTdaV2JkASArBJqeffZZ+eGHHyQsLMwEl8aNGydBQUEyatQo83zVqlXlk08+sWcXsh0yle6f01fDpMe0DXLs8i3TLpvfxwSZCub0vI+9AADAPsiSxv106sot6TszWEIj4+u5dgsoIc83L8cPAQAApNvNiGjpHxgsp66EmXaDMnnkk841xNmZSdkAkCUCTf7+/uZmkT9/ftm2bZvs2LFDXFxcpHLlyuLs7GzPLgB2ceLyLek2bYMJNqlKhXxl7sD6ki+HByMOAHBIZEnDnrUuNch08UaEaT9cqYC893hVMvIBAEC6RcXEynPztsiu0/HlDioUzCFTe9UTD1eXVL2P/7hVidohN+PPW06G3Er0HPUhAWRXdg00JadGjRoZcVjAJnSZvB7TN8j56/EnFTWK+cns/gGSy9udEQYAOAyypHE/hEfFyODZm63LENcs5ieTutcWVxcmowEAgPTRUhIjftgpfx24aNqFcnpKYL8A8fNyS/fQerm7SmxcnDhTqgIA7l+g6cyZM/LTTz/JkSNHTLtMmTLy2GOPSdGiRe/H4QGb2XfuuvScvlEu3Yw07bolc8vMfv6S0zP9JykAAADZSWxsnLzy7TYJOhZirXX5TV9/8XbPkLlwAADAwXy+6qB8u+mUeezr4SqB/f2lSBprapOpBAB3Z/d/xb333nsyduxYiY6ONjMJLIYOHSojRoyQkSNH2rsLgE3sOn1Nen6z0Vo4smGZvDK9Tz3x8eBiCAAAQGqNXb5XVuw8Zx7n8XGXWf0CWIYYAADYxKLgEzLhj4PmsZuLk0ztVVcqFcrJ6AKAndh1TYovvvjCBJJq1aol8+bNM/WZ9KaPdduYMWPMPkBmt/n4FVOTyRJkalIhv8lkIsgEAACQetP/PiIz/j1qHnu6Ocs3fepJqXw+DCUAAEi31fsuyFs/7LK2P+lcUxqVy8fIAoAd2TUVY9KkSRIQECD//POPuLq6JqrR9OSTT0rjxo3NPs8//7w9uwGky4Yjl2VAYLCERsaYdssqBeWL7rVTXTgSAAAAIj/vOGOymZSzk8ikbnWkdoncDA0AAEi3HaeuyrPztkhMbPyqSq+3riSP16J0BwBk6UDTiRMn5Nlnn00UZLJwc3OTHj16yBtvvGHPLgDpsvbARRk8Z5OER8Wa9mM1CstnXWuJGwWqAQAAUm3jkcvyyqLt1vaYx6uZSTwAAMfU7Ntmidoh4fF1+U7dPJXoudVdVt/3vsHxnLh8S/oHBktYVPxE4d4NS8rTTcpkdLcAIFuwa6CpRIkScuPGjWSf1+d0HyAzWrXnvJkFExkTH2TqVKeYjH+yhrjo1FsAAACkyoHzN2TQ7E3Wc6vnmpWVng1KMooAkI14uXqZ+t1OTvy7GrYVEhopfWYGyaWbkab9SJWCMrJdVX7XAMARAk26JN748eNlwIABUrhw4UTPnT59Wr766isympAprdh5Vl5YsFWi/z/Vunv9EjL28WriTJAJAAAg1c5fD5e+M4Lkeni0aXesXVRefaQiIwkADo5MJdwPYZExMnBWsBy9FGradUrkkondajNRGACyaqBp9uzZidp+fn5SsGBBqVSpkvTs2dPcq71798q8efOkQoUKkjNnTlt2AUi3H7aekmHfbpf/jzFJv8al5N3HqjALBgAAIA1uhEdJnxlBcuZauGk/UC6ffNipBudWAAAg3bQW04sLt8qWE1dNu3Q+H5nex1883airDQD3k00DTX379jX/YNQ06NtNmTLljm2bN2+Wfv36Se/evW3ZDSDNFgadkDd/2CmWX+Fnm5aV11pV5EIIAABAGkRGx8ozc7fIvnPxy2lXLpxTpvSsI+6uzownAABIF73+OPqn3bJyz3nTzpfDXWb1C5A8Pu6MLABk5UDT6tUUb0TWNWvdMRm5bLe1/UrLCjK0eTmCTAAAAGm8+PPGkh3yz6FLpl3Ez1MC+/mLr6cb4wkAANJt6tojMnv9cfPY291FZvT1lxJ5vRlZAMjqgaYmTZrY8u2A+2bqX4flg1/2Wdtvtakkgx8qy08AAAAgjT5ZuV++33raPM7p6Sqz+gdIwZyejCcAAEi3H7edlg///zqOi7OTTO5eR2oUy8XIAoAjBJqArDjTduIfh+SzVQes28Y8XlV6NyyVof0CAADIyuZuOC6TVx82j91dnGVa73pSvqBvRncLAAA4gHWHLsmri7db2+M6VJNmlQpkaJ8AILsj0IRsHWQa/9t+mbIm/iKIk5PIhx2rS1f/EhndNQAAgCzr9z3n5d0fd1nb/+taU+qXyZuhfQIAAI5h79nrMmTOZomKiS+u/cLD5eWpAK7jAEBGI9CEbFwwco8ErjtmTbP+tHNN6VC7aEZ3DQAAIMvacuKKDF2wRWLjr/3I220ry2M1imR0twAAgAM4czVM+s0MlhsR0abduW4xeblF+YzuFgCAQBOyo9jYOBmxdJcsCDph2q7OTjKpW215tHrhjO4aAABAlnX0UqgMnLVJwqNiTbt/49Iy8MEyGd0tAADgAK6FRUnfmUFy7nq4aTepkF/e71hdnHR5GgBAhiOjCdlKdEysDF+yQ77fctpaM2BKzzrycOWCGd01AACALOvSzQhz8SckNNK021YvbLKZAAAA0isiOkaGzNkkB87fNO1qRXPKlz3qiJuLM4MLAJkEgSZkG1ExsfLSom2yfMdZ0/Z0iy9M/WD5/BndNQAAgCzrVmS0DAgMluOXb5l2QKk88mmXmuLszAxjAACQ/lVpXl28QzYcCTHtYrm9ZEZff/Hx4JImAGQm/FVGtpn98vz8raY4tfJxdzEnJhSmBgAASF+2uJ5jbT91zbTLFcghX/euK55uLgwrAABIt49+3Sc/bT9jHufydpNZ/QOkgK8nIwsAmYxdc0zDwsJk7dq15pYU3X7w4EF7dgGQsMgYGTR7szXI5OvpKnMG1ifIBAAAkA5xcXHyzo+75M99F0y7gK+HBPbzl1ze7owrAABIt8B/j8rUtUfMYw9XZ5neu56UzZ+DkQWA7BZoOnHihDRt2lSaN2+e5PP6XOXKlaV///5y9mz8cmaALYVGREu/wCBZe+Ciaef2dpMFgxpInRK5GWgAAIB0mLz6kCwIOmnNFp/Zz1+K5fZmTAEAQLr9uuusjP55j3ns5CQy4alaUq9UHkYWALLj0nl+fn7Su3dvcdJvhCToczdv3pSffvpJvv32W/MYsJXr4VHSb2awbD5+xbTz5fCQeQPrS8VCvgwyAABAOny3+ZR8svKAeezq7CRTetaVqkX8GFMAAJBum46FyIsLt0lcXHx75GNVpHW1wowsAGTXQFOhQoUkMDAw2ectz+myG5s3b7ZnV5DNXL0VKb1nBMmO/68XUCinp8wbVJ8UawAAgHTSTPE3luywtj/sVEMeqpCfcQUAAOl26MJNGTh7k0REx5r2kIfKSN/GpRlZAMjOgaaU0oynevXqZXQ34CAu3YyQntM3yr5zN0y7WG4vmT+wgZTIy1IuAAAA6bHr9DV5Zu5miY6Nn2L86iMV5Mm6xRhUAACQbhduhEvfmUFy9VaUaberWUReb12JkQWA7F6jySI6OlquX79u7gF7On89XLpOXW8NMpXK6y3fDmlIkAkAACCdTl25Jf0CgyU0Msa0uwWUkOealWNcAQBAut2MiJb+gcFy6kqYaTcok0c+6VxDnJ2TLscBAMgmgaaFCxfKY489JgULFhQPDw/JnTu3ude2bl+wYIG9Do1sfPGjy9T1cvhiqGmXL5DDBJmK5PLK6K4BAABk+WWJ+8wIkos3Ikz74UoF5L3HqyZbixUAACClomJi5dl5W2TX6eumXbGgr0ztVU88XF0YRADIrkvn3bp1S9q3by9//vmneHt7S61ataRp06bi6ekp4eHhcvr0aVmzZo388ssvMn36dPnpp5/MfkB6HL8cKt2nbZTTV+NnvlQunFPmDgiQvDk8GFgAAIB0CI+KkUGzN1kn89Qsnksmda8tri73ZXEEAADgwLRu+1vf7zQ1IC01tmf28xc/L7eM7hoAICMDTe+++66sXbtWJk6cKIMGDTJZTLeLiIiQr7/+WoYNGyYjR46Ujz/+2NbdQDYrFNl92ga58P8zbGsW85PZ/euLnzcnJQAAAOkRGxsnr3y7TYKPXTHtknm95Zs+9cTbPVOUegUAAFncZ6sOyuLNp8xjXw9XCezvz8o0AJAF2Xwa4rfffisvvPCCPP/880kGmZRuHzp0qLnpEntAWu09e93UZLIEmfxL5Za5AwkyAQAA2MLY5Xtlxc5z5nEeH3eZ1S9A8pExDgAAbGBh0AmZ+MdB89jNxUmm9qorlQrlZGwBIAuy+VTEixcvSuXKlVO0b5UqVeTSpUu27gKyiZ2nrkmvGRvl6q0o025UNq9MZ4YtAACATUz/+4jM+Peoeezp5mwymUrl82F0AQBAuq3ed0FGLN1lbX/SuaY0KpePkQWALMrmGU2lSpWSX3/9NUX7rlixwuwPpNbm4yFmuTxLkKlpxfwyo68/y7gAAADYwE/bz5hsJuXsJPJFtzpSu0RuxhYAAKTbjlNX5dl5WyQmNs6033i0kjxeqygjCwBZmM0DTYMHD5YlS5ZIly5dZN26dRIVFR8IsND2v//+K507d5alS5ea/YHUWH/4svT6JkhuRESb9iNVCpr0ak83FwYSAAAgnTYcuSzDvt1ubb/XoZq0qFKQcQUAAOl24vIt6R8YLGFRMabdu2FJGfJQGUYWALI4my+d99JLL8mxY8fkiy++MAEnZ2dnyZcvn6nLFBERYZbKi42NNfs+99xzZn8gpf46cFEGz94kEdHxv0PtahaR/3WpKW4uNo+ZAgAAZDsHzt8w51qRMf9/vt6srPSoXzKjuwUAABxASGik9JkZJJduRlonDo9sV1WcnJwyumsAgMwWaNIvhwkTJsiQIUNk/vz5smnTJjlz5ozcunVLcubMKTVr1hR/f3/p2rWrVKtWzdaHhwP7fc95eW7eFuuFjyfrFpOPOtUQF13PBQAAAOly7lq49J0RJNfD47PGO9YpKq8+UpFRBQAA6RYWGSMDZgXL0Uuhpl2nRC6Z2K0213QAwEHYPNBkUaVKFRk7dqy93h7ZzPIdZ+XFhVsl+v/X7+3ZoISMaV9NnAkyAQAApNuN8CjpOzNIzlwLN+0HyuWTDzvWYIYxAABIN63F9MLCrbL1xFXTLpPPR6b38acEAgA4ELsFmgBb+X7LKXl18Xb5/xiTDHigtLzdtjIXPgAAAGwgMjpWnp67Wfadu2HalQvnlCk964i7K0sTAwCA9ImLi5NRy3abVWpUvhzuEtgvQPL4uDO0AOBA7BZoOnnypCxatEiCg4Pl9OnTZuk8b29vKVq0qFk6r0uXLlKiRAl7HR4OYkHQCXnrh50S9/9BpueblZNhj1QgyAQAAGCjiz+vL9kh/x66bNpFc3lJYD9/8fV0Y3wBAEC6ffXXEZmz4bh57O3uIjP6+kuJvN6MLAA4GLsEmsaMGSPvv/++REZGmoBAvnz5xNPT0wSc1q9fL4sXL5YRI0bIm2++KaNGjbJHF+AAAv89KqN+2mNtv/pIBXm+efkM7RMAAIAj+fi3/fLD1tPmcU5PVxNkKpjTM6O7BQAAHMDSraflo1/3mcdaX3tyjzpSo1iujO4WAMAObL4exldffWWCR4899pisXbtWwsLC5Pz583L8+HFzr+2//vrLPP/ee+/JlClTbN0FOICv/jqcKMikS+URZAIAALAdnV385ZrD5rG7i7NM611Pyhf0ZYgBAEC6/Xvokrz23XZr+/0nqkmzigUYWQBwUDYPNH3xxRfSsWNH+e677+SBBx4Qd/fEa65q+8EHH5QlS5bI448/LpMnT7Z1F5DFl2/57PcD8uEv8TNe1HuPV5WBD5bJ0H4BAAA4kpW7z8nIH3dZ2591rSX1y+TN0D4BAADHsPfsdXl6zmaJiomvg/Diw+Wlqz/lMwDAkdk80HT48GF59NFHU7Rv27Ztzf6AJcj04a/7ZMIfB03byUlkfKca0qthKQYIAADARracuCIvLNwqsXH/ZY63rVGY8QUAAOl25mqY9J0ZJDciok27S71i8lILyiAAgKOzeY2mvHnzyr59/2Wj3M3evXvN/kBsbJyM+XmPBK47Zl27939dasrjtYoyOAAAADZy9FKoDJy1ScKjYk17wAOlyRwHAAA2cS0sygSZzl+PMO0mFfLLuCeqm/rtAADHZvOMpieeeEImTpwoX375pURGRia5T1RUlFkyb9KkSWaZPWRvGmQasXSnNcjk5uIkk7vXJsgEAABgQ5duRkifGUESEhp/jt62emEZ0aYyYwwAANItIjpGBs/eJAfO3zTtakVzypc96oibi80vPQIAskNG07hx42Tjxo3y/PPPy+uvvy61a9eWokWLioeHh0RERMjp06dl69atEhoaKnXr1pWxY8faugvIQqJjYmX4dzvk+62nTdvd1Vm+6llHmlcqmNFdAwAAcBi3IqNlQGCwnAi5ZdoBpfLIp11qirMzM4wBAED6JxC/uniHbDwaYtrFcnvJjL7+4uNh88uOAIBMyuZ/8XPmzCn//vuvTJs2TebPny+bN2+Wf/75x/q8l5eX1KlTR7p16yaDBg0SNzc3W3cBWURUTKy8tHCbLN951rQ93Zxlem9/eaB8vozuGgAAgENN7Hl+/lbZfuqaaZcrkEO+7l1XPN1cMrprAADAAWi97Z+2nzGPc3m7yaz+AVLA1zOjuwUAuI/sMrVAg0fPPvusucXFxcmVK1fk1q1b4u3tLblz52ZtVkh4VIw8P3+LrNp7wYyGj7uLzOwXIAGl8zA6AAAANqLn4u/8uEv+3Bd/zlXA10MC+/lLLm93xhgAAKTbzH+Pytdrj5jHHq7O8k2felI2fw5GFgCyGbvnsGrBvzx58pgboMIiY2TwnE3y98FLpp3T09XMdqldIjcDBAAAYENf/HlIFgSdNI9zeLjKzH7+Uiy3N2MMAADS7ZedZ2XMz3vMYycnkQlP1Za6Jbn+BwDZkV0DTZs2bZLg4GBTl8mS0aT1murVqyf+/v72PDQyqZsR0TJwVrBsOBK/bm9ubzeZM6C+VCvql9FdAwAAcCiLN52UT38/YB67OjvJlJ51pGoRzrkAAED6bToWIi8u2iZxcfHtUe2qSutqhRhaAMim7BJo+vPPP+W5556TAwcOmOU6kspyqlChgkyaNElatGhhjy4gE7oeHiV9ZwTJlhNXTTtfDg+ZP6i+VCjom9FdAwAAcCh/Hbgob36/09r+qFMNebB8/gztEwAAcAyHLtyUAbM2SWR0rGkPaVJG+jQqldHdAgA4UqBp9erV0rp1aylSpIiMHj1aGjRoYLKYPD09JTw83GQ3rV+/XqZPny5t2rSR3377TZo1a2brbiCTuRIaKb1nBMnO0/FFqAv7ecq8gfWlDOv2AgAA2NSu09fk2bmbJTo2fsLXa60qSqe6xRhlAACQbhduhEufGUFyLSzKtNvXLCKvt6rEyAJANuds6zccOXKkVK9eXXbv3i1vv/22yViqXLmylC5d2txr+5133jHPV61aVUaNGpXmY8XGxspnn30mlSpVMoGs4sWLy7BhwyQ0NDRFr79586a8//77pr++vr6SL18+adSokQQGBiaZibVx40bTf903Z86cJqC2bdu2NPc/u7h4I0K6TdtgDTIVy+0l3w5pSJAJAADAxk6G3JJ+gcESGhlj2t3rl5Bnm5ZlnAEAgE3KIfSbGSynr4aZdsMyeeXjzjXE2dmJ0QWAbM7mgaYtW7bIoEGDxMfH56775ciRQwYPHiybN29O87FefvlleeWVV6RKlSpmGb7OnTvLxIkTpV27diYIdTf6/KOPPmqCXlov6tNPPzWBsZiYGOnXr5+88cYbifbfsGGDNGnSRI4ePSpjxowx2VoHDx6UBx98UHbu/G9ZEiR27lq4dP16vew7d8O0S+fzkcVPN5TieShCDQAAYEtXb0VK35lBZpKPalG5gIxpX9UsWw0AAJAeUTGx8uy8LbL7zHXTrljQV77qVVc8XF0YWACA7ZfOc3d3l+vX47907kX30/3TQjOiNLjUsWNHWbJkiXW7Zk698MILsnDhQunevXuyr9fspH/++UdeeuklkxVl8eyzz5oMqalTp8pHH31k3a7vqX1du3atWQpQdenSxWRpaRbVypUr0/Q5HNmpK7ek+7SNciLklmlXKJhD5g6sLwV8PTO6awAAAA4lPCpGBs7aJIcvxmf21yyeSyZ2qy2uLjafVwYAALIZXfVHaz+uPXDRtAvl9JTA/v7i5+WW0V0DAGQSNv+X50MPPWQCN/fK8tHndT/NEkqLBQsWmC86DRQlpNlU3t7eMnfu3Lu+3hIM01pSCWkwSZfQS5iRdejQIQkODjYZU5Ygk9LHum3VqlVy7ty5NH0OR3XsUqh0+Wq9NchUpXBOWTi4IUEmAAAAG4uJjZOXF22TTcevmHbJvN7yTZ964u1u8zllAAAgG/ps1UH5bvMp89jXw9UEmQr7eWV0twAAmYjN//U5fvx4adiwodSpU0eaNWsmDRo0MAEZDw8PiYiIkNOnT8v69etlzZo14ufnJx9++GGajqOBH2dnZwkICEi0XWs11apVyzx/N/q6XLlymf6WKlVK6tevL7du3ZJZs2aZ5fy++uqrRMdS+rlup59vxowZ5jVt27ZN02dxNIcu3DCZTBf+f9kWnVE7u1+A+Hkz0wUAAMCWdOLVez/vkV92xU96yuPjLrP6BUi+HB4MNAAASLcFQSdk4h8HzWM3FyeZ2ruuVCqUk5EFANg30FShQgUTmNEaRz/99JPJ9rmdBp2eeOIJ+eCDD6Rs2bQVJz5z5ozJPNL3up0GttatWyeRkZHJLs2XO3duWbZsmQwcONAsgWfh6+trluLr0KFDomNZ3jepYykNoKXEyZMn5dSp+FkgFo5U42nPmevS65uNcjk00rT9S+WWGX39xdeTIBMAALbi6OcTSLnpfx+VwHXHzGNPN2eTyVQq391rpQIAYME5Be7mz33n5e2lu6ztTzrXlEZl8zFoAIA72GU9jTJlysi3335rMoR27NhhAjX6WJe006XqqlevnmhpurTQ90sqyGTJarLsc7caUDly5JBq1apJ+/btpVGjRhISEiKTJ082tZ1+/PFHadmypfV9VFLHS3islPjmm29k9OjR4oh2nLoqvb4JkmthUabduFxemdabZVsAALA1Rz6fQMot235Gxq3Yax47O4l80a2O1C6RmyEEAKQY5xRIzvaTV+W5eVvNEr3qzUcryeO17pyADQCAsuvC7RpY0qXl7PXeFy5cSPK58PBw6z7J0Vm/GlzSOlFPP/20dXu3bt1M8ElrPR0+fFhcXFys76NL/6XlWAkNGDBAWrVqdUdfhgwZIrbgP+7ODLKkBI9oIba06ViI9JsZLDciok27eaUC8mWPOuLp5mLT4wAAAPufTyDzW3/4srz67XZr+70O1aRFlYIZ2icAQNbDOQWScvxyqPQPDJawqBjT7tOwpAx+qAyDBQBIVpatEKyZUXv27DHBn9szjXQZO11W727ZTBpg0iBR586dE23XgJHWWvriiy/k2LFjZmk/PZblfW9n2ZbUsnpJKV68uLndL2GRMRIbFyfOTk7i5W6foM+6w5dk4KxNcisy/gSkddVCMrFbbXF3dbbL8QAAyO7u9/kEMpcD52/I4DmbJDIm1rSfb1ZOetQvmdHdAgBkQZxT4HaXb0ZI35nB1pIIraoWlHfbVRUnJycGCwBwfwNNGvzR9Otdu3ZJwYIFzVJ05cuXv2M/rd/0/vvvy59//pnqY/j7+8vKlSslKChIHnzwQet2DR5t27ZNHnroobu+3hIgiomJD44kFB0dnehej6XWr19vajoltGHDBvNlW7duXckMbs9Uavrxajl2+ZaUyusta15rZvPjrdl/QYbM2SwR0fEXOh6vVUQ+7VxTXF0IMgEAANjauWvh0mdGkNwIjz9P7VinqAx7pAIDDQAAbDJZeeDsTXL0Uqhp1y2ZWyY8VVtcdI1eAADuwubRAK1VpMvlDR06VL766itTP0CXohs/fvwd+54/f17++uuvNB2na9euJsDz+eefJ9o+bdo004cePXpYt+kSePv27Uu0X5UqVcx9YGBgou1Xr1419Zly584t5cqVM9v0vl69erJ48WJTb8pCH+u25s2bS6FChSS7Wbn7nAye/V+QqUu9YvK/LrUIMgEAANjB9fAo6TszSM5ei1+6+cHy+eTDjjWYYQwAANJNazG9sHCrbD1x1bTL5POR6b3rURIBAJAxGU0a+Nm+fbuMGDHCBINOnjwp7733nrz55ptmKbovv/zSJsepXr26PPfcc2aJu44dO0qbNm1k7969MnHiRGnSpInJorJ4+OGH5fjx4xIXF1/AUL300ksye/ZseeONN0xNg8aNG0tISIgJVJ09e1YmT55s6jNZTJgwQZo1a2aypzSIpiZNmiSxsbHy6aefSnbz844z8tLCbRL9/0UhezUoKaPbVxVnZrkAAADYXGR0rDwzd7PsO3fDtKsUzmnqYbJUMQAASC+9XjZy2S75fc95086Xw0Nm9Q+Q3D7Jl6QAAMCugSbN8NEAkwaXlGYzabHqF1980QRvoqKiTDDHVkGtUqVKyddffy3Lly83dZk0CDRmzBhxdr57slbJkiXNsnu67x9//CELFy4ULy8vqVWrlgkcafAqoUaNGsmaNWvk7bffNjfNptJt+nlr1qwp2cmSzafkte+2y//HmGTQg6XlrTaVmU0LAABgp4s/w7/bLv8eumzaRXN5ycx+/uLr6cZ4AwCAdJvy12GZu+GEeezt7iIz+/pL8TzejCwAIOMCTbpM3TPPPJNomwZ9NPsnV65cMm7cOJMFpDWc0kszjoYNG2Zud6OZVEkpW7aszJo1K8XHa9iwoQlKZWfzNh6XET/ssraHNi8nr7SsQJAJAADATsb/tl+Wbotfvjmnp6sE9vOXgjk9GW8AAJBuP2w9JeN/3W8eay2myT3qSPVifowsACBjA02enp4maykpmuWkwSHNItJgk9Y2QtYx45+jMubnPdb2a60qynPN4utYAQAAwPbmrD8mU9YcNo/dXZxleh9/KV/Ql6EGAADp9u+hSzL8ux3W9gdPVJdmFQswsgCAjA80aZbQhg0bTP2kpIwaNcrca7BJl6JD1vDlmkPWGS7q7baVZeCDZTK0TwAAAI5s5e5zMnLZbvPYyUnks661JKB0nozuFgAAcAB7zlyXIXM2S1RMfF2El1qUly7+xTO6WwCALOruhYzSoGXLlrJs2TK5cSO+UHFywSa9HT9+3NaHhx1qAvzv9wOJgkzvdahGkAkAAMCONh+/IkMXbLXWxHy7bRVpW6MwYw4AANLt9NUw6RcYJDcjok27a73i8uLD5RlZAEDmyWjq1auXWTrv4MGDUqdOnWT3e/fddyVv3ryyadMmW3cBNgwyffjLPpm69ohpOzuJfNSphnSuxwwXAAAAezly8aYMnBUsEdGxpj3ggdLmBgAAkF7XbkVJ3xlBcv56hGk3rZhfxj5RjdrbAIDMFWgqX768fPDBBynaN7nl9ZDxYmPjZPRPu2XW+uPWgpC6XEv7mkUyumsAAAAO6+KNCOkzM0iu3IqveapZTCPaVM7obgEAAAcQER0jg+dskoMXbpp29aJ+Mrl7HXFzsfmCRwCAbMbmgSZkfTGxcTLih52yMPikabu5OMmkbnWkdbVCGd01AAAAhxUaES0DZgXLyZAw09Z6TJ92rinOmlYOAACQzgnFw77dLhuPhph28TxeMqOvv/h4cGkQAJB+zvdj+bUTJ05IZGSkacfGxiZqI3OJjomVYd9uswaZPFyd5eve9QgyAQAA2Pkc7Pn5W2THqWumXa5ADpnWq554urkw7gAAIN0++GWv/LzjrHmc29tNZvULkPy+HowsACBrBJpCQkKkdOnS8s8//5j2xYsXE7WReURGx5qi00u3nTFtLzcXmdnXX5pVLJDRXQMAAHBYOjHr7aW7ZPX+i6ZdwNdDZvUPED9vt4zuGgAAcAAz/jkq0/4+ap1QPL2Pv5TJnyOjuwUAcCCu9+sfz3drI+OFR8XIc/O2yB/7Lph2Dg9XmdnPX/xL5cnorgEAADi0SX8esmaTW87BiubyyuhuAQAAB/DLzrPy3vI95rGTk8jEbrWlbsncGd0tAICDYSFWSFhkfDHIvw9eMqOR09NVZg+oL7WK52J0AAAA7OjbTSflf78fiD8xd3aSKT3rSNUifow5AABIt+BjIfLiom1ime89un1VaVWV+tsAANsj0JTN3YyIlv6BwRL0/8Ug8/i4y5wBAVzgAAAAsLO/DlyUN7/faW2Pf7KGPFg+P+MOAADS7dCFGzJw1iZTJkE93aSs9G5YipEFANgFgaZs7FpYlPSdGSRbT1w1bS0COX9gfSlf0DejuwYAAODQdp2+Js/M3SwxsfFTjF9rVVE61imW0d0CAAAO4ML1cOkzI9hc91EdahWR4a0qZnS3AAAOjEBTNhUSGim9vtkou89cN+0ifp4yb1ADKZ3PJ6O7BgAA4NBOhtySvjOD5VZkjGn3qF9Cnm1aNqO7BQAAHGTlmn6BwXL6aphpNyqbV8Y/WVOcnZ0yumsAAAdGoCkbungjQnpO3yj7z98w7eJ5vGT+wAZSPI93RncNAADAoV0JjZQ+M4Pk0s0I025RuYCpl+Ck1bkBAADSISom1mRMWyYVVyrkK1/1qivurs6MKwDArgg0ZTNnr4VJj2kb5cilUNMuk89H5g2qL4X9vDK6awAAAA4tPCpGBs7eJEcuxp+H1SqeSyZ1qyOuLlz8AQAA6RMXFydvLNkpfx+8ZNqF/TxlZj9/yenpxtACAOyOQJODunYrShZvPinnroWbtt5/unK/fL/llJy+Gr+tQsEcMndgfSng65nBvQUAAHBsWovppYXbZPPxK6ZdKq+3fNOnnni5u2R01wAAgAP47PcDsmTLKfPY19NVAvsFMKkYAHDfEGhyQN8Gn5R3f9wl4dGx1m36eNKfh6ztqkVyypwB9SWPj3sG9RIAACD7zDB+7+c98uvuc6ad18ddZvUPkLw5PDK6awAAwAHM33hCJv7/NR93F2eZ2quuVCzkm9HdAgBkIwSaHDDINHzJjnvu17lecYJMAAAA98G0v49I4Lpj5rGnm7N809dfSub1YewBAEC6/bH3vLy9dKe1/XHnGtKobD5GFgDgWIGmPHnyyNGjR6VQoUKmnT9//kRt2Ha5PM1kSokPf9krT9QqKn7erNULAABgL8u2n5H3V+wzj52dRCZ3r2NqMwEAAKTX9pNX5fn5WyU2Lr795qOV5PFaRRlYAMB9Z/fKw05OTlKyZEnx8IhfGsTZ2TlRG7bz3ZZTiZbLu5vwqFjr2r0AAACwvfWHL8ur3263tt/rUE0erlyQoQYAAOl2/HKo9A8MlrCoGNPu26iUDH6oDCMLAHDMQNO9/P333xndBYfx+55zqdz/vN36AgAAkJ3tP3dDBs/ZJJEx8ZOAnm9WTnrUL5nR3QIAAA7g8s0I6TMjSC6HRpp2q6oF5Z3HqpjJ3gAAZKtA07p166Rly5bStGnTjOqCw7kRHp2q/a+HR9mtLwAAANnV2Wth0ndmkPXcrGOdojLskQoZ3S0AAOAAwiJjZMCsTXLs8i3Trlsyt0x4qra46Bq9AAA4Uo2mgwcPyhdffGHutUZTr169pFWrVua5Xbt2yauvviq///67mWnRtWtXe3QhW/L1TN2PM6cn9ZkAAABsSSfy9JsZLGevhZv2g+XzyYcdazDDGAAApFtMbJwMXbBVtp28atpl8vvI9N71xNPNhdEFADhWoGn37t3SqFEjuXHjhnXbggULZPbs2RITEyODBg2SuLg4E3x66623pEIFZnfaSssqhWTDkZBU7E+NAAAAAFuJjI6Vp+dsln3n4s+DqxTOKV/2qCPurhm+WjUAAMji9FrayGW7ZNXe+DII+XJ4yKx+AZLbxz2juwYAgO2XznvvvfckIiJCJkyYYLKXli5dKiVKlJDXX39dhgwZIi1atJA9e/ZIYGAgQSYbe7JOMfFM4YUMTzdn6VS3mK27AAAAkC3FxsbJ8O+2y7rDl027aC4vmdnPX3zJIAcAADYw5a/DMnfDCfPY291FZvb1l+J5vBlbAIBjZjT9/fff0r9/fxk6dKhpV6lSRWJjY6Vjx47y2GOPybJly2x9SPw/P283GfN4NRm+ZMc9x2RM+2ri58XSeQAAALbw8cr9snTbGfM4p6erzOrvLwVzejK4AAAg3b7fckrG/7rfPNZaTJoxXb2YHyMLAHDcjKaLFy9K3bp1E22rV6+eue/du7etD4fbdPEvLuM71Ug2s0kzmfR53Q8AAADpN2f9MZmy5rB5rMvkTe/jL+UK+DK0AAAg3f45eEmGf/ffhOIPOlaXphULMLIAAMfOaIqOjhYvL69E2yztPHny2PpwSIIGkVpVLSTfbTklH/+6T8KjY03gaXjrStKpTjGT+QQAAID0+233OXl32W7z2MlJ5POutSSgNOe8AAAg/facuS5Pz90s0bFxpv1yiwrSpR4ThwEAmY9dKhM76b+yU7EdtqfBpAEPlJZCfvFLtuh9/wdKE2QCAACwkc3Hr8gLC7ZKXPy1H3m7bRVpU70w4wsAANLt9NUw6RcYJDcjok37Kf/i8sLD5RhZAED2yGhSAwYMkCFDhtyxXWs0ubi43BF8unbtmj26AQAAANjFkYs3ZeCsYImIjjXtgQ+UNpN8AAAA0uvarSjpOyNIzl+PMO1mFfPL2A7VmMANAMg+gaaHHnqILz4AAAA4rIs3IqTPzCC5civKtNvWKCxvtamc0d0CAAAOICI6RgbN2SQHL9w07epF/eSL7nXE1cUuixIBAJA5A01r1qyx9VsCAAAAmUJoRLT0DwyWkyFhpq31mD7tXFOcnVkiGgAApE9sbJy88u12CToaYtrF83jJjL7+4uNhlwWJAACwGaZDAAAAACkQHRMrz8/fIjtPxy/7XL5ADpnWq554uiVeGhoAACAtPvhlryzfcdY8zu3tJrP6BUh+Xw8GEwCQ6RFoAgAAAO4hLi5O3l66S1bvv2jaBXw9JLB/gPh5uzF2AAAg3Wb8c1Sm/X3UPPZwdZbpffylTP4cjCwAIPsFmh588EFZu3Ztql/3559/ygMPPGDLrgAAAAA2M/GPQ7Iw+KR5nMPDVQL7BUjRXF6MMAAASLcVO8/Ke8v3mMe6Gu/EbrWlbsncjCwAIHsGmooUKSJNmzaVunXrysSJE+XgwYPJ7rtnzx755JNPpGbNmtKyZUspUaKELbsCAAAA2MS3m07KZ6sOmMeuzk7yVc+6UqVITkYXAACkm9ZjemnRNomLi2+Pal9VWlUtxMgCALIUm1YTXLRokbzwwgsyZswYefnll80tV65cUrp0acmTJ49ZciQkJEQOHz4sN27cECcnJ2nVqpVMnTpVGjRoYMuuAAAAAOm2Zv8FefP7ndb2+CdryAPl8zGyAAAg3Q5duCGDZm+SyOhY0366SVnp3bAUIwsAyN6BJtW4cWP57bffTDBp8eLFZik9zV7au3evCSzlz5/fLLGnmU+dOnWSUqX4AgUAAEDms+v0NXl23haJiY2fYvxaq4rSsU6xjO4WAABwABeuh0ufGcFyLSzKtDvUKiLDW1XM6G4BAJA5Ak0WZcuWlTfeeMPcAAAAgKzkZMgt6TszWG5Fxph2j/ol5NmmZTO6WwAAwAHcjIg25xmnr4aZdqOyeWX8kzXFWQs0AQCQ3Ws0AQAAAFndldBI6TMzSC7djDDtFpULypjHq5nsfAAAgPSIiomVZ+Zulj1nr5t2pUK+8lWvuuLuyiU6AEDWxbcYAAAA8P/Co2Jk4OxNcuRiqGnXKp5LJnWrLS7MMAYAAOmktcvfWLJT/j54ybQL+3nKzH7+ktPTjbEFAGRpBJoAAAAAEVOL6cWFW2Xz8StmPErl9ZZv+tQTL3cXxgcAAKTb/34/IEu2nDKPfT1dJbBfgBT282JkAQBZHoEmAAAAZHs6w/i9n/fIb7vPm7HI6+Mus/oHSN4cHtl+bAAAQPrN33hCJv15yDx2d3GWr3vVk4qFfBlaAIBDINAEAACAbG/a30ckcN0xMw5ebi4yo6+/lMzrk+3HBQAApN8fe8/L20t3WtufdKkpDcvmZWgBAA6DQBMAAACytR+3nZb3V+wzj7UU0xfda0vN4rkyulsAAMABbDt5VZ6fv1Vi4+Lbb7WpJO1rFsnobgEAYFOutn07AEB2FB4eLhcuXJDIyEiz/BSQnTg7O0vOnDklX7584uTklNHdQSqtO3xJXl283doe26G6PFy5IOMIAADS7dilUBkQGCxhUTGm3bdRKRn0YBlGFgDgcOye0RQTEyOzZ8+Wnj17SsuWLWXr1q1m+5UrV8z206dP27sLAAA70r/nR48eldDQUImOjibQhGxFA6saYL106ZJcvnw5o7uDVNp37roMmbNZomLiA+RDm5eT7vVLMI4AACDdLt+MkL4zg+RyaKRpt65aSN55rAoTkwAADsmuGU23bt2SRx55RNatWyc+Pj6mrRcklc78feONN6R///4yduxYe3YjW/EftypRO+RmhLk/GXIr0XPBI1rc974BcEyWv+tFixYVX19f/uGEbEcDTYcPH5Zr166ZrCZkDWevhUm/mcFyIzzatDvVKSavtKyQ0d0CAAAOICwyRgbM2iTHLt8y7Xolc8vnT9USF12jFwAAB2TXjKZRo0bJpk2b5IcffpAjR44kmuXu4uIiHTt2lN9++82eXcj2vNxdxdvdxdwDgL0yV/Vvuk4gYNkwZEfu7u7m/4HY2NiM7gpS6Hp4lAkynb0WbtoPls8nH3aqzt8wAACQbtExsTJ0wRZTm0mVye8j03rXE083F0YXAOCw7Bp9WLx4sQwePFgef/zxJJeTKVeunCxatMieXch2yFQCkBEIMCG74/+BrCMyOlaGzN4s+87dMO0qhXPKlJ51xc3F7itKAwAAB6cTrEcu2y2r9l4w7fy+HjKrX4Dk9nHP6K4BAGBXdv0X9ZkzZ6RmzZrJPu/t7S03bsT/Ix8AAACwp9jYOHntu+2y/kj8BKiiubwksJ+/5PAg8xsAAKTfl2sOy7yNJ8xjH3cXmdnXX4rn8WZoAQAOz66Bprx588rp06eTfX737t1SpEgRe3YBAIBMLTAw0G7ZMPq++v4A4o3/bb/8uO2Meezn5Saz+vtLgZyeDA8AAEi377ecko9/228eay2mL3vWlWpF/RhZAEC2YNdA08MPPywzZ86UW7fiix8mdPToUZkxY4a0bt3anl0AACBT69q1q5w9ezbDjq/H7tKli6mxpTd9fP78+Xu+bvr06VK9enWTnVyiRAlTlzFhjaJjx46ZQNftN90PyAiz1x+Tr/46bB67uzrL9D71pFwBX34YAAAg3f4+eFGGf7fD2v6wY3VpUiE/IwsAyDbsuk7IyJEjpV69euLv7y/dunUzF5h+/fVX+f333+Wrr74SDw8PefPNN+3ZBQAAMjUvLy9zywgaGHrsscfM45UrV5r7Z599Vtq1aycbNmwQZ+ek56NMmzZNnn/+efNd3qRJE5OhPGjQIImKipJx48Yl2nfJkiXSqFEjaztHjhx2/UxAUn7ddc7US1CaQPh511riXyoPgwUAANJt95lr8szcLRIdG2far7SsIJ3rFWdkAQDZil0zmsqVKyd//PGHuLq6yrvvvmuKIn7yySfy0UcfSfHixc1zeg8AQEbp27evNG3a1ARPSpYsabJ62rdvf0dWz6xZs6RKlSri7u4uxYoVkxEjRkh0dPQd76PBF30fHx8f6dy5s9y8eVOWLl1qXqtBlkcffTTRe9++dN6aNWusEzMeeughkzGkr/3ll18S9eftt9+WqlWrmuMULVpUevbsmaJMpIRWrVolW7ZskdmzZ0uDBg3Mbc6cORIcHCx//vlnsq/TsejVq5f069dPypQpYwJTr7/+unz++ecSGhqaaN88efJIoUKFrDcCTbjfNh8PkRcXbpW4+Gs/8k7bKtKmemF+EAAAIN1OXw2TfjOD5WZE/L8LugUUl6HNyzGyAIBsx66BJlW3bl3Zvn277NixQxYtWiQLFy6UzZs3m3bNmjXtfXgAAO5p69atJrCyfPlyE+DR761XX33V+rxu79+/vwmu7Nq1S/73v//Jl19+Ke+8806i99GgjQaKVqxYIcuWLTOBnE6dOsmUKVNk3rx55hj79u1L9N7J0cDNW2+9Zfqi2cG6xN6VK1esz2tWsL6vZhPpd+uBAwdM9nBq/Pvvv2bChwasLPSxBtL++eefZF8XHh4unp6J69poVpYulbtp06ZE23XM8uXLZz6DjptmPQH3y+GLN2XArE0SER2/rOPAB0pL/wdK8wMAAADpdu1WlPSZESQXbkSYdrOK+eW9x6vZrf4qAADZdum8hKpVq2ZuAIDso3DhpLMGNKtH6/RZav3cHrBJatm1hg0bmro/t6tcubI1+0YDOy1atEh1P93c3ExNQUvwZPDgwfLFF19Yn//www/liSeesC73WqFCBVPbSINBmrFrWfpO30czlPR9NGCjGU36+XTfggULmn10iblJkybds0+asWSpY/jBBx+YTKOgoCBp1aqV2ZZwzEqVKmX6W79+fTlz5owUKVIkRZ9b+6VZRrfTbXerG6U/P/0MGvx64IEHTPDss88+M8/p8ZVmLo0fP14aN25sxmft2rWmzxrU088C2NuFG+HSd2aQXL0VH9xsW6OwvNWmMgMPAADSLTwqRgbN2SSHLtw07RrF/OSL7nXE1cXu87kBAMjegSYAADKrihUrJsrQ0UBNwmXoNGvoySefTPQarU0UEREhhw4dkurVq5ttlSpVSvQ+GmjTmyXIZNmWkiXuatWqlag/KuHrfvzxRxPcOXjwoFy/ft3UW1IajEtpoCmtNAh28eJFefjhh81xc+XKJS+++KIJulnqOmkW02uvvWZ9Te3atc0ygBrE08CdLvcH2EtoRLQMCNwkJ0PCTDugdB75tHNNcXZmhjEAAEif2Ng4GbZ4uwQdDTHtEnm85Zs+/uLjwSU2AED2ZddvQb3YdK+UYZ3lXKJECXnkkUdk+PDhdr84BgC4f+6WFWMxcOBAc7uX9evX33OftGQzWTKREtLvLq0raIv3Set7J3yd5bvUEkzauHGjdOzY0QRyNGiTO3duE2DSDKjIyMgU91eDXrpU4O00oJVcNppl2T6tRaVZVOfOnTOBtN9//908V7Zs2WRfZ8lOO378OIEm2E1UTKw8N3+L7Dx9zbTLF8gh03rVE083F0YdAACk2/sr9sryHfH/zsnt7SaB/fwlv68HIwsAyNbsmtPbu3dvM8tbL6jpLO/HH3/c3HTmuG6rUaOGWX7H1dVVJk6caGY7HzlyxJ5dAgAg1XQZvL///jvRtr/++ssEXMqVu//FfrV+kmYRaZCpQYMG5ntVAz6ppcvanTx5Uvbu3WvdtmfPHrNNl8S7F/3+1npOGhSbP3++lC5dWurUqZPs/lrDSulrAHvQ88u3f9gla/ZfNO2COT0ksH+A+HknDvgCAACkxTf/HJXp/xw1jz1cneWbvv5SJn8OBhMAkO3ZPdB09OhRUxRdlx36/vvvzU0vYv3888/mueeee0527NghP/30k1y9etUsu5NSOrNblw2yLFWkBc2HDRsmoaGh93ztqFGjzAzx5G63z0C/2/6ffPJJmsYHAJA1aG2mH374wQR2Dhw4IN9++62MHj1aXn75ZWt9pvtJv/dCQkLk66+/Nt+lixcvlrFjx6b6fTQDTAND+n2tWVJ608f+/v7SvHlz6366RJ6lPpXSSSFai0rHYvPmzfLss8/KokWL5Msvv7QunafPay0m/f7X5QW1BtZLL71kliDUTGbAHib8cVAWbTppHufwcJWZfQOkaK77//8oAABwPCt2npWxy/eYx7oa76RutaVOidwZ3S0AABx/6Tyt4TBkyBBrMfOE2rRpYwqi64UrXQ6pbdu20q9fP1NzIqX0Ap9mQmmBdg0w6YxsbWuhcS0Ib7nYlRRdciipWega9Pr444+lXbt2Sb5OA1tadyKhunXrprjPAICsR7+zZsyYYQJNOiEif/788vTTT8uYMWMypD/6nTly5Ehz09pI9evXlwkTJpjtqaHfkzrx44UXXrAuO6jf2ZMmTUr0HXr48GEzmSNh1sjkyZPNZBGdcKGBqT/++EMeeuihRO89fvx4EwjT/TXb6fXXXzf9Bezh2+CT8vmqg+axq7OTfNWzrlQpkpPBBgAA6ab1mF5atE0sK2CPfryaPFK1ECMLAMD9CDRt27ZNevXqlezzZcqUMbOfLXTpPJ3xnBI6Q1ovhGnAaMmSJdbteiFLL5gtXLhQunfvnuzrddk+vd1OA2NqwIABSb6uQ4cOUqpUqRT1EQCQ+Wnmze369u1rbgn16dPH3FLzPpoNq7e7vfft7aZNmyZZw+n2bUm99+37pKQWlNZi0oyou9H6TwlpHabg4OC7vkYzo/QG3A+r91+QN3/YaW2Pf7KGPFA+8cQgAACAtDh04YYMmr1JIqPj66U+07Ss9GpQksEEAOB+LZ2n9SN0hnNyNOsoZ87/Zppeu3ZN/Pz8UvTeCxYsMBfQdBmehDRLytvbW+bOnZvq/uqSexqg0toRSWVhWVy/fl2io6NT/f4AAACwrZ2nrslz87ZITGx8YPW1VhWlYx3qgAEAgPQ7fz1c+swIlmthUab9RO2iMrxVRYYWAID7GWh66qmnTE0LXV5o//79EhMTY+oq6WPdtnTpUunWrZt1/9WrV0uVKlVS9N46k1qX5QkICEi0XWs11apV654zrZOiM7o1iKQzy11cXJLcR7OgNBimx2nUqJH88ssvqT4OAAAA0u9kyC3pFxgstyJjTLtngxLybNOyDC0AAEi3G+FR0m9msJy+GmbajcvllY861TBLRwMAgPu4dN64ceNMUEmLlU+bNs1a70GDTZqN1KpVK7OPCg8PN0vnPfjggyl67zNnzphaSR4eHnc8V7RoUVm3bp1ERkaKu7t7ivv7zTffmBOG/v37J5mdNXjwYBNcyp07t/lcn3/+uamHoXU7bl9iKTknT56UU6dOJdq2c+d/S70AAABwPnFvV0Ijpc+MILl0M8K0W1QuKKPbV+PiDwAAqcA1iqRFxcTKs/O2yJ6z1027UiFfmdKzrri72nW+NgAAWZZdA01eXl6yfPlyWbFihSk2rgXBldY4ateunSmubqEZQu+//36K3/vWrVtJBpks72XZJ6WBJg0c/fPPP/Lwww+bOk+3u32JPqUBqWrVqsnLL78sTz75pOTIkSNFwazRo0enqE8AAACcT9wpPCpGBswKliOXQk27VvFcMqlbbXFxZoYxAACpwTWKO+nE6NeX7JC/D14y7SJ+nhLYL0ByerrxywUAQEYEmiw0oJQwqGQLWofpwoULST6n2VGWfVJzcqUGDhyY4tfkzZvXLAGoxdg1g+qRRx6552sGDBhgMrluz2gaMmRIio8LAACyt+x8PqG1mF5cuFW2nLhq2qXyess3feqJl3vSyx4DAIDkZedziuT87/cD8v2W0+axr6erBPYPkEJ+8ROaAQBABgaa7KFIkSKyZ88eiYiIuCOz6fTp02ZZvZRmM0VHR8vs2bNN4OiJJ55IVT80O0tduhQ/0+Veihcvbm4AAABplV3PJ3SG8Zifdstvu8+bdl4fd5nVP0Dy5kg6yx0AANxddj2nSM68jcdl0p+HzGN3F2eZ1rueVCjom9HdAgAg07N7oEmDOEuXLpWNGzfKlStXTH2mhLQmkiWbKDX8/f1l5cqVEhQUlKiuk2Yzbdu2TR566KEUv9dPP/0k58+flxdffDHZ5fiSc/DgQXNfsGDBVL0OAAAAqfP12iMya/1x89jLzUVm9PWXknl9GEYAAJBuf+w9L+8s3WVtf9qlpjQok5eRBQAgowNNISEh0qxZM9m1a5eZgapBJb1XlsdpDTR17drV1HT6/PPPEwWapk2bZmoz9ejRw7rt8OHDEhUVJZUqVUryvSzH15Tx5IJloaGh4ufnd0fRzClTpphMqEaNGqX6MwAAACBlftx2Wj74ZZ95rKWYJveoLTWL52L4AABAum07eVWen79VYuMvWcmINpWlXc0ijCwAAClk10DT22+/Lfv27ZPp06dL06ZNpWzZsvLbb79JiRIl5L333jPZQNpOi+rVq8tzzz0nX3zxhXTs2NHUgNq7d69MnDhRmjRpIt27d7fu+/DDD8vx48etQa6Ezpw5I7/++qsEBASY90zKzZs3pXTp0tKhQwepXLmy5M6dW/bv328+lz63YMEC8fLyStPnAAAAwN2tO3xJXl283doe90R1aV6JbHIAAJB+xy6FyoDAYAmLijHtfo1LycAHSzO0AABklkDT8uXLpXfv3tKvXz+5fPmy2ebi4iIVK1aUuXPnmuDTm2++abKC0kKzmbRG0tdff22OpXWZhg4dKmPGjBFnZ+cUvUdgYKDExMTIwIEDk91Hg0idOnUyy//pMoAaXNJjtWjRQoYPH26CVAAAALC9feeuy5DZmyUqJn7C0AvNy0m3gBIMNQAASLfLNyOk78wguRwaadqPViskb7etYlbfAQAAKZeyaEwanTt3ztRSUq6urtYaShaaIbRs2bI0v78GrYYNG2ayiyIiIuT06dPyv//9T3LkyJFov2PHjiWZzaTeeust89ygQYOSPY7WbdLspZ07d5o6U7oM39mzZ+W7774jyAQADmDEiBFSqFAh8w9KncSQEqNGjTKTHRJOXMjof5DqBI6+ffta2/pYtwFZ1dlrYdJ3RrDciIg27SfrFpOXW1bI6G4BAAAHEBYZI/1nbZJjl2+Ztn+p3PJZ11riomv0AgCAzBNoypMnj6ltpHx9fcXNzc3UNbLQtgZuAADIKJqtqjX/Jk+ebCYRDB48OEWve/XVVyU4OFgyswkTJsj3339/346nwTbNWtYJGno/e/bse75Gl7bt1q2bCfR5e3ub5W63b99uk/dG1nYtLMoEmc5dj5+k9GD5fPJBx+oZHtAFAABZX3RMrAxdsEW2n7xq2mXz+8i03vXE080lo7sGAECWZNdAU4UKFWTPnj3xB3J2ltq1a5sLRZp9dOvWLXORqEyZMvbsAgAAd6X1ApXW+7MEO1JCs2fz589v89GNjIxftsMW/Pz8zKSP+0GXlh0wYIAJ1GmgSO916dyffvop2dfouUDLli3l0qVLsmLFCtmyZYupidi8eXM5f/58ut4bWVtEdIwMmbNJ9p+/YdpVCueUKT3ripuLXU9dAQBANqCr2ry7bLes2nvBtPP7ekhgvwDJ5e2e0V0DACDLsuu/1h955BGzvJwGltQrr7xiZo7rRa8CBQrIpk2b5OWXX7ZnFwAASJYuLderVy/rhAjNlNDlVjXg0aZNGylYsKD4+PhIzZo1ZcGCBXddOu92SS2lp++t29asWWPdpu3PPvtMevbsKbly5TI1AdXmzZulVatWJiNYA1pPPPGEHD16NFU/zduXzrP0+ccff5RKlSqZz6bPW4JtFmk59vjx403fdUlbfW+91+DdRx99lOxr1q1bZ449c+ZMqVOnjnnd1KlTzXNffvllut4bWVdsbJy8tniHbDgSYtpFc3lJYD9/yeFh19KiAAAgm/hyzWGZv/GEeezj7iIz+/pL8Twpm2wGAAAyINCk9Y+0TpMuc6O6dOliAk968erRRx+V+fPnmxnKAABk1NJylppMumye3ooXLy7Xr1+Xzp07yx9//GEyaHr37m0CQX/99Zdd+jFmzBipW7eumYDxySefmGzgJk2aSIMGDczyfKtXrza1Dlu0aCFhYWHpOtaFCxdkypQpMm/ePBPouXbtmvTv39/6fFqOrVlYum/r1q0Tbdd2UFCQqW2YFEvdRk9Pz0T1F93d3WXt2rXpem9kXR/9tk+WbT9jHvt5ucms/v5SIOd/vyMAAABptWTzKfn4t/3msauzk8mYrlbUjwEFACAzB5p0lrYlyGShM5C1XsTixYula9eu9jw8ACCjFS6s6a3/tbdsid/2+uv/bZs+PX7bokX/bXvuufhtCTNtGjYUKV/+v/bly/H7JPwuWbUq1UvL6U3psnl600CHZvno0mzVqlWTcuXKmQwanSShwRl7aNeuncnw1WNp/SHN4NGMqtGjR5sMHu3H3LlzTSBs+fLl6TqWBndmzZplAluaqaW1pv79919r0Cctx9al76Kjo834JaRtDQTp80nRYJZmcWkfNLinGdDjxo0zk1TOnDmTrvdG1jRr3TGZ+tcR89jd1Vmm96kn5Qr4ZnS3AACAA/j74EV5fckOa1trPz5UwfZLYQMAkB3ZbQ2Smzdvmot3ukzPO++8Y6/DAABgc5cvXzbfX6tWrTJBDw1oaBCkWbNmdhnt+vXrJ2prBo8uKad1oBLSYNDty9ylVuHChc2SgBZFihQx69RrplOJEiXseuzb5cuXz0w+efrpp805gwb5NFNJA11HjsQHG5Bx/MelLHAbPKKFTY73665zMuqn3eaxrjo5oWst8S91f2qMAQAAx7b7zDV5Zu4WiY6NM+1XWlaQzvWKZ3S3AABwGHYLNOkFKp2lrLWYAADZ1Nmzidt16ty5beDA+FtCkyfH3xJavz5xO2/eO9+rhW0uePfp00cOHz4s77//vpQtW1a8vb3lxRdflNDQ0BS/h9Z8UhrEsdRqSm6ZN62VlFBsbKx0795d3n777Tv21TqH6eHm5paobembHjOtx9aAkS6vp0G5hM6fP2+Op88nR4N3+/fvlytXrphj582bVwICAsy4p/e9YVthkTESGxcnzk5O4uXuYtP33nw8RF5cuFXi4q/9yDttq8ij1Qvb9BgAACB7OnXllvSbGSw3I6JNu1tAcRnavFxGdwsAAIdi16rKevFI61kMGTLEnocBAMCm9LtLg0xPPPGEacfExMiBAwekaNGiKX4Py0QLXQLO8rotunRgCtSrV0927NghZcqUsQas7pe0HFtrKvn7+8tvv/2WqN7Tr7/+aoJGtwe3kpI7d25zr0GnzZs3y3RdUtFG7420uT1TqenHq+XY5VtSKq+3rHnNdtl9hy/elAGzNklEdHywc9CDpaX/A6Vt9v4AACD7unYrSvrODJYLNyJMu3mlAvLe49Wsk60AAIBt2PXq1ccffyz//POPjBw50tReAAAgK9DaRAsWLJDt27fLzp07pW/fvmZpudTQIIivr6+8+eabZsk5DYyMHTs2Ra996623zGt69OghQUFBcvToUVm9erW89NJLNl++zlbHHj58uHz33Xfy2WefmWCR3i9ZskReT1CP64cffjBje/r0aeu22bNnmxpRulSe7t+iRQt56KGHpHfv3ql6b2RNF26ES58ZQXL1Vny232M1Csubj1bO6G4BAAAHEB4VI4Nmb5JDF26ado1ifvJF99ri6nJ/J3IBAJAd2PXb9eGHHzY1HfTCms5U1sLdOkM64c2yNA4AAJlFYGCgyeZp2LChqRlUoUIFa3ZTSukycxqs0ppHNWrUMN+F48ePT9FrK1euLOvWrZNbt25Jq1atTHvQoEFm6T5L5o+9pPXYHTp0kG+++UamTJki1atXN/czZ86Udu3aWfe5du2aCRQlXEJQlyjs0qWLCUC98sorZtm+5cuXm3pNqXlvZD2hEdHSPzBYTl0JM+36pfPIp11qirMzM4wBAED6xMbGybBvt0vQsRDTLpHHW2b09Rdvd7su7AMAQLblFKfFI+ykadOmKUpH1pnS2dn69eulUaNG5sKeXtQEgKzEkuVSvnz5jO4KkGn/P7gf3/X2PoYtl86LiomVgbM2yV8HLpp2hYI5ZPGQRuLnzVKIAADcjSOcU9wP7/28R77556h5nNvbTb5/trGUzpe4LioAANnVejt819t1KseaNWvs+fYAAADIYnSO04gfdlqDTAVzesjMfgEEmQAAcED+41alqTZkekz/+4g1yOTp5izf9PUnyAQAgJ2RMwwAAID75vNVB+XbTafM4xwerjKzb4AUzeXFTwAAgGwgLDJGYuPixNnJSbzc/1sq2VaW7zgr41bsNY91Nd5J3epInRL2XXoaAADcp0DT2rVrZeXKlXL+/HkZNmyYqcNw8+ZN2bJli6lbkStXLn4WAAAADm5R8AmZ8Ef8MoOuzk4ytVddqVIkZ0Z3CwAA2MntmUq2XIr3dhuPXJaXF20TS4GI0Y9Xk5ZVCtr0GAAAIGnOYkcxMTHStWtXadasmbz//vsyY8YMOXPmjHnO1dXVFPf+8ssv7dkFAAAAZAKr912Qt37YZW1/3LmGNC6XL0P7BAAAHMPB8zdk0OxNEhkTa9rPNi0rvRqUzOhuAQCQbdg10PTRRx/JkiVL5H//+5/s3bvXrMlv4enpKU888YSsWLHCnl0AAABABttx6qo8O2+LxMTGnwsOb11RnqhdLKO7BQAAHMD56+HSd2awXA+PNu0naheV11pVzOhuAQCQrdg10DR79mzp3bu3vPjii5Iv350zVitXriyHDx+2ZxcAAACQgU5cviX9A4MlLCrGtHs2KCHPNCnLzwQAAKTbjfAoE2Q6fTXMtBuXyysfdaohTk5OjC4AAI4SaDp27Jg0bNgw2ee1NtOVK1fs2QUAAABkkJDQSOkzM0gu3Yw0ba2TMLp9NS7+AACAdIuMjpVn5m6RvWevm3alQr4ypWddcXe166UuAACQBFexI19fXwkJCUn2+UOHDkn+/Pnt2QUAQCbnP25VmgoJA8jcwiJjZOCsYDl6KdS0a5fIJROfqi0uzswwBgAA6aOlGd74fof8c+iSaRfx85TAfgGS09ONoQUAIAPYdZrHAw88IHPnzk1Um8lCM5lmzJghzZo1s2cXAABZ8OJ0aES0uQeQNWktphcXbpUtJ66adul8PvJNH3/xcnfJ6K4BAAAH8OnKA/L9ltPmcU5PVwnsHyCF/DwzulsAAGRbdg00jRgxQg4ePCjNmzeXn3/+2Wzbvn27TJ06VerUqSOhoaHyxhtv2LMLAIBMTjOV9Lbq5SYy5KEyEh0TK7ciY8z9003Kmu3ZJZspNjZW6tWrJ/PmzUvR/v/8848UL15cbt26Zfe+ASmlE4xG/7RbVu45b9r5crhLYD9/yePjziACAIB0m7fxuHyx+pB57O7iLF/3ricVCvoysgAAOGqgSS+WLVmyRPbt2yf9+vUz21599VV55plnJCwsTH744QepUqWKPbsAAMgCvg0+KfXfXyVjl++V8OhYs03v3/t5j9muz9uTfie9//77UqtWLfHx8TE1BPU77NNPP5UbN26YfUaNGmXqylhuBQsWlNatW0tQUNAd73fgwAFp1aqVeHt7S968eWXw4MFy8+bNe/Zj9uzZEh4eLt27d09x5nC1atXkk08+ScOnBuxj6tojMnv9cfPYy83FZDKVzOvDcAMAgHRbtee8vLN0l7X9aZea0qBMXkYWAABHrtGk2rZtK8eOHZPff/9d9u7da2a5li9f3noBDgCQvWkQafiSHck+rwEny/Nd/Ivb/PgaSGratKmcOnVKRo8eLfXr1zeBJs3AnTx5sgkU9e3b1+xbrFgxCQ4ONt9l586dk7Fjx5pg0/79+601BzWg9PDDD5sA0L///muWiu3fv795j+++++6ufdHA1qsapzYAADdlSURBVKBBg0wgK6V0f53AoRnC7u5kjCBj/bjttHz4yz7zWGsxTe5RW2oWz8WPBQAApNvWE1fk+QVbJPb/qzO83baytKtZhJEFACA7BJqUh4eHPPbYY+YGAIDFtVtR8u6P/81IvJt3l+2SVlULiZ+3bQv8vv3227Jnzx5zK126tHW7Pu7QoYMJFFm4uLhIoUKFzOPChQvLyJEj5fvvv5cNGzZIu3btzPb58+fLhQsXzH3u3LnNNg1Y6XfgoUOHpFy5ckn2Y9u2bbJr1y554oknrNs0i0qDX7dr0qSJrFmzxjxu06aNXL16VVauXMn3LDLUukOX5NXF263tsR2qSfNKBTO0TwAAwDEcuxQqA2ZtkvCo+NUP+jUuJQMe+O/cHQAAOPDSeVqHaeLEiXLp0iV7HgYAkEV9t+WUdam8e9F/VC7Zcsqmx9fMpLlz50qPHj0SBZkSsgSLksqEmj59unmcMJNIs5g0Kyrh6x555BFxdnY2NZWS89dff5nl+EqUKGHdpsvNnj171nrT4JJmA2vtQwtPT0+pWbOmrF69OpWfHrCdfeeuy5A5myUqJn6K8QvNy0m3gP9+lwEAANLq0s0I6TMzSEJCI027TfVC8k7bKqlaBQAAAGThjCad0f3SSy/Ja6+9Jo8++qj07t3bzPh2c7PtbHQAQObTY/oGOX0l7K77nLsWnqr3HP/rPpm9/tg99yua20vmDWxwz/0uXrwoISEhKa4XeOLECcmRI4d5HBoaau4bNGhglsqz0ICQJevJQr/38uTJY55LztGjR6Vo0aKJtumxLMfTvuoSfB07dpR333030X66pN+RI0dS9BkAWztzNUz6zgiWGxHRpv1k3WLycssKDDQAAEi3W5HRMiAwWI5fvmXa/qVyy/+61BJnZ4JMAABkm0DTyZMnZdWqVaa4+dKlS+Wnn34yM7yfeuop6dOnj/j7+9vz8ACADKRBpmP//w9CW9HsJ1u/Z2oUKVLEZBVFR0ebzKX33ntP5syZI66u6f86DQsLM9lJSQkPD5fHH39cSpYsKd98880dz+vrNGAG3G/XwqKk78wgOXc9Pmj8UIX88kHH6swwBgAA6RYdEytD52+V7aeumXbZ/D4yrXc98XRzYXQBAMhOgSZNY27ZsqW56cxvLYKuQaevvvpKpkyZIhUqVDABJy1gDgBwLJpVdC+a0ZTSpfOUp6uzFPLztMmxVf78+U2mkdZnSgkNKFlqLFWqVElu3rxpAkBbt261Lp+ntZs0OymhqKgoEwjS5+7Wl6SCRbq8n2YEX7t2TVasWJFomT4LfZ2+HrifIqJjZMicTXLg/E3Trlokp3zZo464udh1ZWYAAJAN6Dnwu8t2yx/7Lph2fl8PCewXILm87zwXBgAADh5oSsjHx8cElfR26tQpMwP8o48+MkXYCTQBgONJydJ13/xzVN77OWVBHjW8dSXpb8OivzohQuszTZs2TUaMGJFknaarV69Krly5knz9M888Ix9//LFMmjRJhg0bZrY1btxYFi5cmOh1v//+u8TGxsoDDzxw17qG+l6avZQws0m/I7W20/r165Ptx86dO2X48OGp/vxAWsXGxsmri3fIhiPxwdGiubxkZl9/yeFx304tAQCAA/tyzWGZv/GEeezj7mLOM4rn8c7obgEAgGTc9ymnWkNCi6fr0j/Xr18XFxdSngEgu3qyTjGTpZQSnm7O0qluMZv3YezYsSY7SWstTZ06VbZt2ybHjh0zy722atXKLP2aHM0uevnll+WDDz4w32mqe/fuUqBAAXOv76VL7T3//PPSqVMnazZUUpo1aybOzs4moGQxa9Ys+fzzz833poeHh5w7d87cEmY+HTx4UM6cOSNt2rSx2ZgACV27FSXT/z5iramm9z2mb5Sftp8xbT8vN5nVP0AK5Lx3tiEAAMC9LNl8Sj7+bb957OrsJFN61pVqRf0YOAAAsnugSZf7+frrr81M7vLly8uYMWNMcfNPP/3U1HECAGRPft5uMubxainad0z7auaCtq3lzJnT1FsaOnSoTJ48WRo2bCi1atUy31WtW7eWJ5988q6vHzx4sMTExJhsJKXfb1qfUOs4NWrUSDp27CgPP/ywBAYG3vV9tIZht27dzBKzFqtXr5bIyEhp27atWXbPctP3tNAMYX1//X4FbO3b4JNS//1VMnb5Xusyl3q//shl89jF2Umm96kn5QrkYPABAEC6/X3wory+ZIe1/WGnGqYGJAAAyNzsur7Jzz//bC6Y6b0uBaQzvF988UWzfF7NmjXteWgAQBbRxb+4uX/3x11J1mvSTCYNMln2swdvb2+zlKvekjNq1Chzu52vr69cuXIl0baKFSvKypUrU90PPb4uoTd69GgpUaKECU7dLUB148YNk4X1ww8/pPpYQEqCTMMTXOhJSkxsnBy9GCr+pfIwoAAAIF12n7kmz8zdItGxcaY9rGUFedIOKxoAAIAsFmhq3769WeqnXbt2JrikM8NZKg8AkJD/uFXm3sfTVVyiYiQ0Isb6nI+Hi3i6ucjHK/fbNdCUWZQpU8bUi9Kl+zTQlJLlaMeNG2cypwBbL5enwd+UeHfZLmlVtZDJUAQAAEiLU1duSb+ZwXIzItq0uwWUkOebJ7/sNAAAyEaBpi+//FKeeuqpZIuXAwBg4ezkJN7uruIkThIbF2faXu7Zr45f586dU7yvZgeTIQx7+G7LqSQzDJMSHhUrS7ackv4PlOaHAQAAUu3qrUjpOzNYLtyIMO2HKxWQ9x6vKk5OTowmAABZhF0DTU8//bQ93x4A4ACCR7TI6C4AuM3ve86lakx+33OeQBMAAEi18KgYGTx7sxy6cNO0axbzk0nda4ury30pKQ4AALJCoEnFxsbKrFmzTP0IXeLHsjSQFjLv3bu3ODtz8gAAAJCZ3AiPX7Ympa6HR9mtLwAAwDGW5V28+aScuxZu2no//e8jEnQ0RIKOhZhtJfN6yzd9/c0qBwAAIGux67d3WFiYtGnTRtauXWtSngsXLmy2r1ixQpYvXy6zZ882jz09Pe3ZDQAAAKSCr2fqThFzelKfCQAAJO3b4JOm9mPCZXn18djle63tPD7uMqtfgOTL4cEwAgCQBdk1nWjs2LHy119/ybBhw+TixYty8uRJc7t06ZK8+uqrsmbNGlPEHAAAAJlHyyqFUrl/Qbv1BQAAZO0g0/AlO+5Z+7FbQHEplc/nvvULAABkoUDTokWLpEuXLjJ+/HjJnTu3dXuuXLnko48+Ms8tWLDAnl0AAABAKj1Zp5h4uqbsNNHTzVk61S3GGAMAgDuWy9NMppT45p+jZn8AAJA12XXpvFOnTpnMpeQ0adJEli5das8uAAAyu08qpGy/Vw/YuycA/p+ft5uMebyamYF8L2PaVxM/L5bOAwAAiX235dQ9M5kswqNiZcmWU9L/gdIMIwAAWZBdM5o0c+nQoUPJPq/P6T4AAFhF3RKJvBl/DyDDdPEvLuM71Ug2s0kzmfR53Q8AAOB2v+85l6pB+X3PeQYRAIAsyq6BppYtW8rkyZPlt99+u+O5lStXypQpU6RVq1b27AIAIDOb0vjObZEaaAqNv7/Xvg4mNjZW6tWrJ/PmzZOsIiYmRipVqiTLli3L6K7ADjSItPGtFvLOY1WsASe9f/exKrLxzRYEmQAAQLJuhEenanSuh7N0HgAAWZVdA01jx44VX19fadOmjblw1qdPH3PTx48++qh5bsyYMfbsAgAgMwu9KHLzfOJbXEz8c3qfcLvuaydhYWHy/vvvS61atcTHx8dk2+p31aeffio3btww+4waNUqcnJyst4IFC0rr1q0lKCgo0XudPXtWevToIVWrVhVXV1dp2rRpivsxe/ZsCQ8Pl+7du1u36bECAwPT/Nm0Py+//LJUrFhRvLy8JG/evFKnTh155513zBK39/LSSy9J/fr1xdvb2/Tldi4uLjJ69GgZNmyYCTrBMZfRG/BAaSnk52naeq/L2uh2AACA5Ph6pq5aQ05Pzi0AAMiq7BpoKlmypGzatEmeeuopOXDggMyZM8fcDh48KN26dZPg4GCzDwAAGUUDSQ888IBMmDBBnn76afnnn39k69at8vbbb8uvv/4qS5Ysse5brFgxE7g5c+aMeU6DUhpsunjxvyBYRESE5MmTR1555RVp0aJFqvqiga1BgwYlGdBJi927d0uNGjXkzz//lPfee898727ZskU+/vhjOX/+vLm/Fw0eaeDr2WefTXafJ554Qq5cuSI//fSTTfoNAACArK9llUKp3L+g3foCAADsK3XTS9KgRIkSZgmguLg464W4/Pnz2+wiGgAA6aEBpT179phb6dL/FR/Wxx06dDABlITZO4UKxf+DuXDhwjJy5Ej5/vvvZcOGDdKuXTuzvVSpUjJp0iTz+O+//5Zjx46lqB/btm2TXbt2maCNhb6X6tevn7mpo0ePWrffjX7v9uzZ0/RTJ324uf03Q1QneTz88MNmn3uxfJa7ZVW5u7tL27ZtZe7cuWbMAAAAgCfrFJOPf90n4dGx9xwMrf3YqW4xBg0AgCzKrhlNCWlgqUCBAuZGkAkAkBlooEWDI7rUXcIgU0K5c+dONhNq+vTp1kBLev31119mOT6doGGhGUjq888/N5lUeitevHiK3m/Hjh0mePX6668nCjIlZMvvY11eb/Xq1TZ7PwAAAGRtuszumMerpWjfMe2riZ8XS+cBAJBV2TWjafLkyfLDDz/IqlWrknz+kUcekU6dOsmQIUPs2Q0AQEaY1V7k2sm77xN6KeXvp/tOrJ2yff2Ki/RZds/dNNM2JCREqlSpkqK3PXHihOTIkSO+O6Gh5r5BgwYmOyi9NFOpaNGiibZpBrDy8/OzZlKl1P79+8195cqVE22vWbOmHD582JrZpMvr2YIuK6hjee3aNdNfAAAAoIt//CSpd3/clWRmk2YyaZDJsh8AAMia7Bpo0mV2tJh6cipUqCAzZswg0AQAjkiDTCFHbPd+cTG2fb80KFKkiKxZs0aio6Pl33//NXWPtPagq2v6v07DwsLE09NT7E3rKEVGRsrEiRNl2bJl1gBawmDbgw8+KL/88kuq3tfSd/0cBJoAAABgoUGkVlULyXdbTlmX0vN0dZbhrStJpzrFTOYTAADI2uwaaDp48KC1pkRSqlatKvPnz7dnFwAAGUWziu7lyvH4AFJKOLmI5C5pu2P/f8ZQnjx5TH2mlNCAUrly5czjSpUqyc2bN+Xxxx+XrVu3pnv5PO2LZgTZSsWKFc29frY6depYt1uW5tPPnTCApsvsWXh5eaX6eNp3XYovb9686ew5AAAAHI0GkwY8UFrmrD8mxy7fkkJ+ntL/gaSXrgYAAFmPXQNNUVFREh4enuzz+tzdngcAZGEpWLpOPqkgcvN8yt7PJ5/IC1vFljQwovWZpk2bJiNGjEiyTtPVq1clV65cSb7+mWeekY8//lgmTZokw4YNS1dfNBik76Xfiwkzm7S+UkxMCoNxCdSoUcPcPvjgA+natWuydZpuD6Cl1c6dO82yfHc7DgAAAAAAAByPsz3fXJfG+/3335N9fuXKlVK2bFl7dgEAgLsaO3asyU7SWktTp041mT3Hjh0zS8y1atVKli5dmuxrNYvp5ZdfNsGc69evW7fre+hNs3w068nS1iXrktOsWTNxdnaW9evXJ9qu35Na6/D06dNy6dIliY29c2375IJos2bNkrNnz5og1qJFi0w9Jq3P9PPPP8uKFSvExcXlnu9z6NAh03ddXu/2z5aQLinYtm3bFPUNAAAAAAAAjsOugaZu3bqZYNI777yT6OKaZjqNHDnSPNe9e3d7dgEAgLvKmTOnqbc0dOhQmTx5sjRs2FBq1aolY8aMkdatW8uTTz5519cPHjzYZBxpNpJF7dq1zU2DVZs3b7a2z5w5k+z75M6d23xvzp49O9H2CRMmmGwhDTjp8nqWgE/Tpk3N7W70c+zYscPs9/bbb0vdunWlWrVq8sYbb8gDDzwgf/zxxz1/OwYOHGj6rt/bCT+bpb6T0uDVxo0bZdCgQfd8PwAAAAAAADgWuy6dp7O8tZj4uHHjZMqUKWbGuNq3b5+ZCa3FxtO71BAAIAvzyX/nttBL8XWbtCaTLpd3t31txNvb2wRi9JacUaNGmdvtfH195cqVK4m2xcXFpakfenzNPho9erS1ltIjjzwiu3btumPfI0eOmKX77qVYsWJmab+00kyle9Eg24ABA6RkyRTW0AIAAAAAAIDDsGtGk9Zp0KylDz/80Fzo0mLpeitevLiMHz/eLAWU3uLpAIAs7Jl/7bNvFlWmTBlTL0qX7rsbzVLSOk6ZYbKGZnPp97pOKgEAAAAAAED2Y9eMJkuwafjw4eYGAMA9uXuLxMWKONl1LkSm1blz53vuU6NGDTlw4IBkBlrnacSIERndDQAAAAAAADhqoAkAgLt6NXMETAAAAAAAAACkXvacLg4AAAAAAAAAAIB0I9AEAAAAAAAAAACANCHQBAAAAAAAAAAAgDQh0AQAAAAAAAAAAIA0cU3byzKH2NhYmTBhgkydOlWOHTsm+fPnly5dusiYMWPEx8fnrq8dNWqUjB49OtnnXV1dJSoqKtG2/fv3y+uvvy5//fWXREZGSp06dcx7NG/e3GafCQCym2bfNkvRfqu7rLZ7XwAAAAAAAABko0DTyy+/LBMnTpQnnnhChg0bJnv37jXtrVu3yqpVq8TZOfmErY4dO0q5cuXu2L5jxw75+OOPpV27dom2Hz58WBo1amQCUMOHDxc/Pz+ZNm2atGrVSn755Rdp0aKFXT4jAGQ3YdFhEhcXJ05OTuLl6pXR3QEAAAAAAADgiIGm3bt3y6RJk0zAaMmSJdbtpUuXlhdeeEEWLlwo3bt3T/b1NWrUMLfbDRkyxNwPGDAg0fY333xTrl69Kps3b5ZatWqZbb1795aqVavKc889J/v27TMXRQEAqZMwU0kDTE2/bSoh4SFSPEdxWdFpBcOZSfTt29dkD69Zs0ayAs1cDgwMNH0GAAAAAACA/WTZGk0LFiwwFyRfeumlRNsHDRok3t7eMnfu3FS/Z2hoqAlQFStWTFq3bp1o+7Jly6Rp06bWIJPKkSOHDBw4UA4cOCDBwcHp/EQAgI3nNpogk4qIibD7gMyYMcNkqupEgoQaN25sJg+cPXs20XbNYn3kkUcSbfv111/l0UcflXz58omnp6dUqFDBTFbQCRFKAx36XpabHq948eLy9NNPy7Vr1+7ZR32NBkxSElhJeJyCBQua77KgoKAUjgaQmP+4VYluJ0Nume16n3A7AAAAAADI3rJsoEkDO7o0XkBAQKLtepFPg0FpCfwsXrxYrl+/bmZtu7i4JFpOLyIiQho2bHjHaxo0aGDtDwAg7XTywJRtU6zta5HXzDZ7evjhhyUmJkZWr/4vq+rGjRsmOFOiRAmzDKuF1ub7559/Ei2VOm7cOGnbtq2UKlVKvvvuO1PLb/bs2ZInTx559dVXEx1Ls281cKWBJ1169aeffjIZuLakEyX0GGfOnDEBMK1XqMGmixcv2vQ42d3tNRyzCy93V/F2dzH3AAAAAAAAWT7QpBfRdPa4h4fHHc8VLVpULl26ZC4KpsY333xjZoH379//jmNZ3jepY6nTp0+n6BgnT56U9evXJ7rt3LkzVf0EAEfNZtpyYYu1rRlNQefsm41TsmRJU68vYUBp7dq15m+7Lo+acLv+vb5165Y10LRlyxZ55513TLBpypQpJutV308nIGitv/nz5yc6lgafChUqZM2afeqpp2TTpk137Z8GsFS/fv2smUp3WwpOJ0noMQoXLiy1a9eWkSNHypUrV2TDhg2JMoJ14kSuXLkkd+7c0rx5c7MsbEIhISHStWtXE6jSzKi33347yaCfZgHrcXSSh352rZ2oWcAWOnFDx+Wrr74yz+v7de7cWW7evClLly6VKlWqmOxgzQg7f/689XVHjx6VJ5980vwcvLy8pHLlyqYG4+190J/Pgw8+aDKZtXZikyZNTE3FhH788UepVKmSObb25eDBg4me18+umWq+vr6SP39+U/dRj2+h2WQ67n/99ZfUrVtX3N3dzXtmtPtxPhE8okWi267RrWTPmNbmPuF2AACQdXGNAgAA2EKWnZKqF/uSCjIpveBl2UcvCKWEzkLXmeo6u13rPN1+LJXU8RIeK6XBrNGjR6doXwDIrtlMFl9u+1ICCgXYtQae/t3/448/rG19rNs0ANOrV69E2/PmzWsCK2rOnDkmCPLKK68k+b4axEnOkSNHTMZRo0aN7to3zZYtUKCAfP755ybwozQYkhKamTV9+nTzOOF3YXh4uLz11lsmeBMWFmaCYhpo0WVgNRimdOm/7du3m4CKBq0++OADs4RsnTp1EgVgNLA0YcIEs9SgTrh4/vnn5dy5cyaYZaEBOQ1+rVixwjynAaROnTqZ5+bNm2eyg/SzaQaYjqnSQJQGhTTAlTNnThPk0XqIGkzq06ePNcik/R46dKh88cUX5jv633//TZRtdOHCBRME1OPokoUa+NLJJH///bd5fs+ePSY4NWzYMPM5oqOjzXe0BhN37dplfr4W+nP+6KOPpEyZMiZoldE4nwAAAJxTAACAzCLLBpp09rJeQEqKXkSz7JOaCzZKay4ldSyly+el91h68U4vjCWkM5CHDBmS4r4CQFYwcOVAOXszcY2j5IRHh8uFsDv/pmuGU4vFLcTTNT6on1KFcxSW6Y/EB1nuRYMKU6dOlVOnTplsoz///FOGDx9usn4uX74s+/btMxkxul2DT5agl05QKFu2bIonNGjWjmYcaTBDv080wPG///3vrq+xBJU0wKLBmns5ceKEyRBSlswizbDSwJmFZkclNHPmTBMU08BX9+7d5dChQybbSANDluwtrWV1+yQMrQml2Vya+aV0LDTgo59r0qRJJutYubm5maCUTsyoWrWqyWjSAJgu8afZUpb6ivoai+rVq5ubhQZ3NOimASNLoEkDQvp9qkE4C/053f4dPWvWLOtxNJilwUPdrv0ZP368tGnTJtEEEK3xqOOxfPlyExSz0ICc/vwzC84nAAAA5xQAACCzyLKBpiJFipiZyHqx7vZMI51VrRe4UnrxTy/6aU0NnamuS+YkdSzL+97Osi2pZfWSogXg9QYAjk6DTCdunEj3+yQVgLIlDR5ozT/NkHnsscdM8F+3aSBCg026XQNQWrdJAylppcGV+vXrS2xsrBw/flxGjBghjz/+uHl/Pb4GYXS7hWb1pJZ+X61Zs8Z8r2l2z3vvvWeyhDSbJ2HdwTFjxphMI11mVvujWbmWJfn0u1UlzLbS71N/f3+5evWqaWvNJ+2rZgJpUM7CsrSdLk9nCTRp8MeS/as0Q0pvluCPZVvCpfM002rs2LEmi0qXr9Xvel0O17KUoGXJOw103c3tx9Hx0T7qRBWtwaXBK+2rJThnoYGo25fY059dZsL5BAAA4JwCAABkFlk20KQXvFauXGku/Gl9hoQXh7Zt2yYPPfRQit9LC7LrBa4XX3wxyeXxdFa1btf6B7ez1L2oV69emj8LADgizSpKTzZTQgW8CqQqqymlx1a6XFytWrXM0nianaqBEUv2ULNmzcx2zajRJdksGT6qYsWKZkk3DYCkZGKDTkjQelCqQoUKJrihwRwNDGlgSzOIEi77lhYaULIcQz+HBqs0mLV161bTRw0otWzZ0gRNNPCln1O3a9ZTauoaanBKaUaWvl9Sn9VCM5oS0oywpLYlrL/02muvyZIlS+TTTz+11nHSjKLffvstFaOR9LET9l/vNYtLl+i7nWUZQYvMsFweAABAVuM/7r+apyrkZvxKMSdDbiV6jrqPAABkbVk20KT1HN5//32zZE7CQNO0adPMhbQePXpYt2lhcL14d/uSOrcvm6fL0CRFL3C1a9dOvv/+e1OzombNmma7XsDTC3Xly5eXgIAAG39CAMjaUrJ0nQYX+v7a956BpmK+xSSwdaDdajVpAEkzfzTQlHCZOQ00aTClZMmSZuk4DThZ9OzZ03wH6fNvvPHGHe955cqVu9ZpsmQZWWr86TGSC5bExMSk6XM988wzJkCjy9Jp9tHevXtNNo9mAlmWptNMJl0i0EIDO2rdunVmuT+lQSjN/tHvO6VZQppRo8sH6jFsTQN4GgDSm4XWkEqobt268vvvv5s6UWmlk0Q0w0t/rppVBgAAAPvycneV2Lg4cbZjDVYAAHD/ZdlAk14g08LguoxRx44dTY0FvYA2ceJEUx8i4cUpvWioS/wknC1toUvyaF0KDRQlrAdxOy2ErrPaH3nkEXNRS4uTa1BLl87TOg72LFQPAI5q47mNpg7Tveg+QeeCpH5h+yxfpt8TWq9nwYIFJuBkoZk/OlFBaxQ99dRTdwQ6tLaPLoGntZF0AoQu7aYZsjoxQQMYmqVkERISIufOnbMunadLzmnAJuESdUnR2ke6vF7r1q1Ndq1m2qQ0KKLZSvqdpd9hWgdJ+6fL2Ol3px5fvwP13svLy/oazYhq3769DB06VL7++muT9fThhx/KjRs3Er23Bqv69+9vXXZWA2Jaz+rnn38234/poRNDNNtY6znlypXLTAjRpf4SBu7eeecdEwh76aWXTD8smce63KFmm6XEW2+9Zb7/dXKKjpPWxNLA248//mjOMSyBNQAAAKQNmUoAAGQPWXr6rs4k/+STT2T37t3mgtDChQvNhTG9yJXSi3BaoFxnig8cOPCu++mFN613ocsL6QU3LSiuy+hokEqLkQMAUu/b/d+meN9F+xfZbYg1M1YDFZpdpJMVLDR40rhxYxNkSbhsnsW7775r6ggdOXLEBFs0wKFBC80Q0mXfEurUqZOpGaT1nnRfrWGkAaTbl2i73YQJE0zdKA04aSBEg1qpMXjwYPM9p5lNGhSaP3++Wa5PM5eGDBlisrEKFCiQ6DUaWKtTp47J5tXx0KXwbq9h2KtXL/nuu+9MME2DNZodNHLkyBTXLLzX97t+7+qY689GM6r0ez4hnfihx964caMJCGofZs2adcdyeXdTuXJlk7mlP3f9Lte2BuRCQ0Pvmo0GAAAAAACA/zjFJZXmg/tKZ2DrjHa92KUzsQEgKzl48KC5T0v2R9DZIHn979cTbQsJD5HYuFhxdnKWPJ7/BWE+evAjCSjMMqXImv8f3I/ves4nAABwfJxTAACAzHg+kaUzmgAAWVtqAkcEmQAAAAAAAIDMJ8vWaAIAOCYvVy9TU4/adwAAAAAAAEDmR6AJAJChVndZzU8AAAAAAAAAyKJYOg8AAAAAAAAAAABpQqAJAJBuutQdkJ3x/wAAAAAAAMiuCDQBANL3ReLsLLGxsVxoR7YOMun/A9QVAwAAAAAA2RGBJgBAunh4eJgL7WfOnCHYhGzp+vXr5nff3d09o7sCAAAAAABw37ne/0MCABxJoUKFJDIy0lxsv3HjhslwIrMD2YUGmGJiYszjAgUKZHR3AAAAAAAA7jsymgAA6eLq6iolSpQQX19fcXNzI8iEbEWDqprVpwFXT0/PjO4OAAAAAADAfUdGEwAg/V8mrq5SrFgxRhIAAAAAAADIZshoAgAAAAAAAAAAQJoQaAIAAAAAAAAAAECaEGgCAAAAAAAAAABAmhBoAgAAAAAAAAAAQJq4pu1lsKXQ0FBzv3PnTgYWAAAHZPmOt3zn2wPnEwAAOD7OKQAAQGY8nyDQlAkcOXLE3A8ZMiSjuwIAAO7Dd74935vzCQAAHB/nFAAAIDOdTzjFxcXF2ezdkCZnzpyRn3/+WcqUKSM+Pj42j07qBaepU6dK9erV+QkhS+L3GEBW/1ujs4T0BO6xxx6TIkWKSFY7n1D8LYYj4PcYQFb/W5PVzyn4OwxHwe8ygKz8dybUDucTZDRlAvrDHDx4sF2Pob+MDRs2tOsxAHvj9xjA/ZBV/9bcj/OJrDw+QEL8HgO4H7Lq3xquUQCO//85gKyjehb5O+Oc0R0AAAAAAAAAAABA1kSgCQAAAAAAAAAAAGlCoAkAAAAAAAAAAABpQqDJwRUrVkxGjhxp7oGsit9jAPytyXj8LYYj4PcYAH9rMhZ/h+Eo+F0GwN+ZxJzi4uLibtsGAAAAAAAAAAAA3BMZTQAAAAAAAAAAAEgTAk0AAAAAAAAAAABIEwJNAAAAAAAAAAAASBMCTQAAAAAAAAAAAEgTAk0AAAAAAAAAAABIEwJNAAAAAAAAAAAASBMCTQ7IyckpyVuOHDkyumtAkj744APp3LmzlClTxvyulipV6q4jtXHjRmnRooX4+vpKzpw5pXXr1rJt2zZGF0Cy9u/fLz169JDKlSuLn5+feHt7S6VKleSVV16Rs2fPJrl/hw4dJHfu3OLj4yMPPvig/Pnnn9luhDmnQFbDOQUAe+J8Iu04p0BWwvkEAHvb74DXKJzi4uLiMroTsP0JnP6yDR48ONF2Nzc36dq1K8ONTPk7mydPHqlTp45s3rzZBI+OHTuW5L4bNmyQpk2bStGiReX5558327744gu5cOGCrFu3TqpXr36few8gK/jjjz9k3Lhx0qBBAylWrJi4urrKzp07ZebMmeZvjgarCxQoYPY9fPiwBAQEmH1eeuklc9I3bdo02bVrl/zyyy8m0J1dcE6BrIZzCgD2xPlE2nFOgayE8wkA9vaHA16jINDkoF+Iffr0kcDAwIzuCpAiR44cMdlMqlq1anLz5s1kA036h3Xfvn2yd+9eE2xSp0+fNjMA9I/zypUrGXUAKbZ48WLp0qWLfPTRRzJ8+HCzTdtLliwxge9atWqZbfp3qWrVquLp6Wn+Bul3bXbAOQWyGs4pAGQEzifujXMKZCWcTwDIKIuz8DUKls5zYJGRkeaXDsjsLEGmezl06JAEBwebZfYsQSalj3XbqlWr5Ny5c3bsKQBHU7JkSXN/5coVcx8aGirLli0zmZOWEzily88OHDhQDhw4YP4OZTecUyCr4JwCQEbgfCLlOKdAVsD5BICMUjILX6Mg0OSgvvvuO7O2o9aw0TS7oUOHyrVr1zK6W0C6WP5wNmzY8I7nNJtJVwLV6D4AJCc8PFwuXbokp06dMhmQQ4YMMdvbtGlj7nfs2CERERHJ/p1J+Lcou+CcAo6IcwoA6cH5RNpwTgFHw/kEgPQKd6BrFK4Z3QHYni4tptkd5cqVk+vXr8uKFStMDZu//vrL1LDRiCeQFZ05c8bcJ8xmski4jB4AJGf69Olm8oVFqVKlZO7cuaa2IX9n7sQ5BRwV5xQA0oPzidTjnAKOiPMJAOk13YGuURBockAbN25M1O7du7fUqFFDRowYIRMmTDD3QFZ069Ytc+/h4XHHc7omacJ9ACApHTp0kEqVKpmlZbdu3WpS0HX2EH9nksY5BRwV5xQA0oPzidTjnAKOiPMJAOnVwYGuUbB0Xjbx2muvibu7uyxfvjyjuwKkmS4HqTRlNKlU04T7AEBSihUrJi1atDAnc6NHj5ZZs2aZApsffPABf2dSiHMKOALOKQCkB+cTtsE5BbI6zicApFcxB7pGQaApm3Bzc5MiRYokiogCWY3+DieXEmrZllQqKQAkRzN+a9euLV9++SV/Z1KIcwo4As4pANgS5xNpwzkFsjrOJwDYWo0sfI2CQFM2oRFOLSpWsGDBjO4KkGb+/v7mfv369Xc8t2HDBnFycpK6desywgBSJSwsTEJCQszj6tWrm5T05P7OqHr16mXrEeacAo6AcwoAtsb5ROpxToGsjvMJAPYQlkWvURBocjCXL19Ocvs777wj0dHR0q5du/veJ8BWypUrZ/54Ll682FoMT+lj3da8eXMpVKgQAw7gDufOnUtyVFavXi27du2SBg0amHaOHDnMd+WaNWtk+/bt1v10vWQt0lm+fHlTzDo74JwCjoxzCgBpwflE2nBOAUfF+QSAtDrngNconOLi4uIyuhOwnZdfftlEM5s1ayYlSpQwv3QrVqwwv6T169c3915eXgw5MpU5c+bI8ePHzeNJkyZJZGSkDBs2zLRLliwpvXr1su67bt068/uta5gOHTrU+prz58/Lv//+KzVr1sygTwEgM3viiSfk7NmzJiCtf1d0Bu3mzZtl4cKFZj1jPWmrVauW2ffQoUPmRE2Xc9Hv1Zw5c8q0adNk586dptZhq1atJDvgnAJZEecUAOyJ84m04ZwCWQ3nEwDs7QlHvEahgSY4jqVLl8Y98sgjcUWKFInz8PCI8/b2jqtZs2bcuHHj4sLCwjK6e0CSmjRpogHvJG/63O3WrVsX17x58zgfH5+4HDlymN/5zZs3M7oAkrVo0aK4tm3bxhUrVsx8P3p6esZVrFgx7vnnn487fvz4Hfvv2bMnrn379nF+fn5xXl5ecY0bN477/fffs9UIc06BrIhzCgD2xPlE2nBOgayG8wkA9rbIAa9RkNEEAAAAAAAAAACANKFGEwAAAAAAAAAAANKEQBMAAAAAAAAAAADShEATAAAAAAAAAAAA0oRAEwAAAAAAAAAAANKEQBMAAAAAAAAAAADShEATAAAAAAAAAAAA0oRAEwAAAAAAAAAAANKEQBMAAAAAAAAAAADShEATAAAAAAAAAAAA0oRAEwAAAAAAAAAAANKEQBOATO3YsWPi5OQko0aNkqzo0qVL0rt3bylSpIj5HE2bNk33e65Zs8a8V2BgoE36CABAdsA5xZ04pwAAgHMKrlMAsAVXm7wLACBJw4YNk0WLFsmIESOkTJkyUrBgwSwzUnrxSW8vvfSS5MqVSzKzw4cPy6RJk2TVqlVy4sQJCQ8Pl3z58kmtWrWkXbt2Jtjn4+OT0d0EACDNOKe4PzinAAA4Os4p7g/OKZDdEGgCADv6/fffpVWrVvLuu+9muXHWINPo0aOlb9++mTrQpJldTz/9tLi6ukqXLl3MY29vbzl37pysXbtWnn/+eVm6dKn89ttvGd1VAADSjHMK++OcAgCQHXBOYX+cUyA7ItAEAAlERUVJTEyMeHp62mRcNNiRJ08exvg2OsYREREmIJQef/zxhwwYMECqVasmK1askKJFiyZ6/q233pIjR46YrDIAAO4nzinuD84pAACOjnOK+4NzCiB9qNEEZHM6y0Lr/fz555/yySefSNmyZcXDw0MqVKggs2bNSnFtA92mz+k+FpoJo9suX75sHutSZr6+vtKhQwcTgFFff/21VK5c2QR2KlWqJD/++GOyfV2wYIHUqFHD7FuiRAlzzOjo6Dv2O3v2rDzzzDNmH3d3d1MfafDgwXLhwoUk+7x792555ZVXpFixYua9N2zYcNcxCw0NlTfffNM6VoUKFTJLsx0/fvyO946LizPjqI9TUldJ9582bZrUr19fcuTIYW7Vq1e/Z0aU5eeoWUi30/WWS5UqlWjbunXr5NFHHzV918+sAZo2bdpYP7v+vDSbSZUuXdra/4Q/+2vXrsnrr78u5cqVM+OQP39+6datmwnsJNU3XdbuvffeM+Omx/z2229T1Je7GT58uLnX97o9yGShSxbqzwsAYF+cU3BOwTkFAIBzCq5T3H5uyHWKO3GdAo6IjCYA1syPsLAwGTJkiAkaTJkyxQQbNIjQuHHjdI1S69atTRBnzJgxcujQIZk4caI88cQT0rFjRxNo0owUvTCh25988kk5cOCACW4ktGzZMhPAeO6550xAQtsaCNHgzsyZM637aX2ehg0bSmRkpHlfDWroMfXzrF69WjZt2iR+fn6J3rtHjx7i5eVl1inWk6DChQvfdSaRLoX377//mr7qaw4ePGjef+XKleb99bPqZ9Ox69Wrlzz44IMm0KUaNWp017HS/efNm2cCTVrXSZes27dvn3z33Xdm/Gxh//790rJlSzOOL774oqkbdf78efnnn39k+/bt0qBBA/N7cP36dfnhhx/ks88+M0FCpYE+S5BJP4uOd//+/aVq1aomwPfll1+avus4lCxZMtFxX331VTN+gwYNkpw5c0rFihVT1JfkHD16VLZs2SIPPfSQeS8AQObAOQXnFJxTAAA4p+A6RWpwnQJwAHEAsrWZM2fG6Z+CWrVqxUVERFi3nzp1Ks7d3T3uqaeesm47evSo2XfkyJF3vI9u0+d0H4s+ffqYbc8++2yifV9++WWzvXjx4nHXrl2zbt++fbvZ/sYbb9xxTGdn57jNmzdbt8fGxsZ16NDBPLd+/Xrr9vbt28flz58/7uTJk4mOGRwcHOfi4pKo75Y+N2nSJC4qKipF4/X111+b17z22muJtv/8889me8+ePRNt1206DimxaNEi63vExMQkei5he/Xq1WY//dnd/nPU526nn69kyZLW9oQJE8y+GzduvGt/kvqZWrzwwgtxnp6ecdu2bUu0/dixY3G+vr6JPrOlbxUqVIgLDQ1NtH9K+5KUZcuWmddqX26nx7l48WKim/7OAADsh3MKzimSwzkFAIBzCq5TJMR1Cq5TwPGwdB4A49lnnzXLzFnoMmS6fJ5m66TXSy+9lKitGT5Kl5vTzBYLzZbRdlLH1KyXOnXqWNuaeWRZNk2zbixZNj///LO0b9/eZEhdunTJetOl4zTDSLOOkuqfq2vKEjz1WM7Ozncsxda2bVupVauWWfovNjZW0kIzmZQuYajHSOj2dnpYMrq0r+Hh4al+vcbPtK+aSaS/JwnH2cfHx2QhJTXOupzh7TWZ0tMXzbhSCX+HLHSpQV3KL+FNl3AEANgf5xScU6QU5xQAAM4puE6huE4BZH0EmgBY14e9Xd68eW1ycf72986dO7e5v315PMtzSR1T6zjdrkqVKubeUhNIU601yPPNN9/cEWTQmz6vy7LdTgNqKaXLtWnNJ8tnSEiXj7tx44YJuKSFBth02T5dPs6ennrqKWnRooW8//77kidPHmnevLl89NFHiWpM3c3FixfNz0iDSUmN8++//57icU5PXywBJkvAKSFd+k/7obdHHnkkRZ8LAGAbnFOkDOcUnFMAADin4DpFPK5TAFkfNZoAGC4uLkmORPzqb/9lESUnOjo61e+dkmOmhuV1PXv2lD59+iS5j9Ziut3tWTZZUWp+NlqDSwMwQUFB8ttvv8natWtNBtCoUaNk/vz5pn5WSsZZA0Svv/56ivuY1Dinpy/VqlUz99u2bbvjufLly5ubmjt3bor7CABIP84psjbOKRLjnAIAMg7nFFkb5xSJcU4BR0egCUCKacaJCgkJueM5S1aRvezdu/eObXv27Ek0c1qXxtMTmcjISBMEsQc91q+//ipXr16VXLly3dEfzbLJly9fmt5bM350CTnNBkptVtPdfjY6Y9rNze2O7QEBAeamTp48KbVr15a3337bGtxJ7qRQs5b0s2smka3G+V59SYpmxOlyilpwXGeBVaxY0SZ9AQDYH+cUnFMozikAAJxTpB/XKTinADIDls4DkGK+vr5SqFAh+fPPPxNlHWmQaenSpXYdSc162bJli7Wtxx8/frx53KFDB+tSf23atJHvv/9eNmzYcMd76Gt02bf00GPp8nwffvhhou2//PKLbN261dSHSms9pR49eph7rT11e52ne2V5WZalW7VqVaLtCxYskDNnziTaltTSfsWKFTMXexIGqnLkyJFk8Eo/n/ZVs5C+++67JPtz4cKFu/Y3tX1Jji6zp7p06XLH50xvhhwAwH44p+CcQnFOAQDgnILrFIrrFEDWR0YTgFR5/vnnTabJo48+aoIuenH/q6++MsuYBQcH2200a9asaer3PPfcc6aOkWb+aFClV69e0rBhQ+t+U6ZMkQceeEAeeugh6d27t8mM0aCNBsP0NbpNl2VLq759+8qsWbNMgOPYsWPmOIcOHZIvv/zSZCFpraG06ty5s3Tt2lVmz55t6jVp0EprQR04cMAsK7dr165kX6vZPJpdNHXqVBNYqVWrlllS7ocffjCZXlFRUdZ9x44da+orPfbYYyYrSPf/6aefZN++fSbIZdGgQQNzr8vjaWDJ09PT/Jz1Nm7cOPn3339NgEdvuq+7u7uprbRixQqpW7euBAYG3vMzp7QvydHPrDW5tCaTBtt0DPXYukyfZobpUnz6/vo7o/0HAGQenFNwTsE5BQCAcwquUyiuUwAOIA5AtjZz5kxN94hbvXr1Hc81adIkrmTJkom2RUVFxb322mtxhQoVivPw8IirXbt23LJly+JGjhxp3ufo0aPWffv06WO23U6Ppdv12LfT4+lxLfT9dF99//nz58dVr149zt3dPa5YsWJx77zzTlxkZOQd73Hx4sW4V199Na58+fKmj35+fnHVqlWLe+GFF+J2795t3S+pPqfEzZs3495444240qVLx7m5ucXlz58/rmfPnnHHjh27Y199fx2HlIqJiYn74osvzLh6eXnF5ciRw3zmUaNG3XP8zp49G/fkk0/G+fr6xvn4+MS1bt06bs+ePXf8HPX1Xbp0Mds8PT3jcufOHRcQEBA3bdq0uNjY2ETv+dFHH5nP6erqav05WISGhsaNGTPGjK2+j/a1UqVKcQMHDozbsGFDin7HUtOXuzl06JD5+VapUsV8dv25FC5c2IzBlClTzM8MAGBfnFNwTsE5BQCAcwquUyTEdQquUyD7cNL/ZHSwCwAAAAAAAAAAAFkPNZoAAAAAAAAAAACQJgSaAAAAAAAAAAAAkCYEmgAAAAAAAAAAAJAmBJoAAAAAAAAAAACQJgSaAAAAAAAAAAAAkCYEmgAAAAAAAAAAAJAmBJoAAAAAAAAAAACQJgSaAAAAAAAAAAAAkCYEmgAAAAAAAAAAAJAmBJoAAAAAAAAAAACQJgSaAAAAAAAAAAAAkCYEmgAAAAAAAAAAAJAmBJoAAAAAAAAAAACQJgSaAAAAAAAAAAAAkCYEmgAAAAAAAAAAAJAmBJoAAAAAAAAAAACQJgSaAOD/2rNjAgAAAIRB9k9th91QgwEAAAAAUIgmAAAAAAAAEtEEAAAAAABAIpoAAAAAAABIRBMAAAAAAACJaAIAAAAAACARTQAAAAAAAKw45z1l1BlUObcAAAAASUVORK5CYII=","type":"image/png","originalSize":79877,"dimensions":{"originalWidth":1690,"originalHeight":546,"displayWidth":1690,"displayHeight":546}}},"sourceToolAssistantUUID":"971d056b-7d16-4690-84fa-4a6d9a56434c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}46{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"2bdbc2cbc8d06e70e85447f5d7aa5095f1103578c1cbf1f574a09c0ec62d74d4","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Y4qcpvhwWcY1kU8FwAGxmL","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0020/out/figure1.png"}}]}}47{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"29ecb313-aab9-4c33-b3c1-ee0831bab72f","timestamp":"2026-10-30T05:42:06.031Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"d74ef049-7d00-4a54-bae5-56df02e952d6","keep":12,"tail":["2bdbc2cbc8d06e70e85447f5d7aa5095f1103578c1cbf1f574a09c0ec62d74d4","f31e69cc1a9df277ee08956be897cd4d65ced8b97e17e3e71dcade05483f6768"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"79d3798355915024374807f64a89cac5860e700e52a368569daec99d12b49a29"}48{"type":"last-prompt","lastPrompt":"Review","leafUuid":"fdd21124-cae9-4b06-b340-0d1188d44549","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}49{"type":"atis-latch","atis":"","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}50{"parentUuid":"fdd21124-cae9-4b06-b340-0d1188d44549","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRkg8HQp9HxJ4FHU25","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":1385,"cache_read_input_tokens":24642,"output_tokens":1682,"output_tokens_details":{"thinking_tokens":433},"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":1385},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4188,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtRkQ1X7HajWu2rdfoL","requestRef":"29ecb313-aab9-4c33-b3c1-ee0831bab72f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"604341d6-0b4d-4bdc-9c53-43114ba8130e","timestamp":"2026-10-30T05:42:11.863Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}51{"parentUuid":"604341d6-0b4d-4bdc-9c53-43114ba8130e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtRkg8HQp9HxJ4FHU25","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SJJtT5EZmRxxtWRnwR9A1z","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"claims.json C6 / report.md Results\",\n \"issue\": \"The claim that WCB beats CR1 at G=10 with ICC>0 is marked 'supported', but the caveat only compares the gap to the SEs of the individual coverages and says it was 'not formally tested'. The code already computes paired differences on shared replications. When I re-ran it, the paired WCB-CR1 differences were 0.014 (SE 0.0039) for C5 and 0.026 (SE 0.0043) for C6. That support is stronger than the caveat says, but it is not reported.\",\n \"suggested_fix\": \"Report the paired MC SE for the G=10 WCB-CR1 differences, as is already done for the G=5 ranking, and update the C6 caveat.\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"report.md Results (variance bias bullet)\",\n \"issue\": \"The statement that the unbalanced cluster sizes make the bias 'much worse than the balanced-cluster factor (G-1)/G' is not backed by any balanced-design computation in the deliverables. It is plausible but untested here.\",\n \"suggested_fix\": \"Either add the closed-form E[V_CR0]/Var(ybar) for a balanced design of the same N and G, or label the statement as an interpretation.\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"report.md / claims.json C4 ('most at small G and high ICC')\",\n \"issue\": \"In the MC estimates the bias is not monotone in ICC at G=10: CR0 is 0.762 at ICC=0.2 and 0.774 at ICC=0.5. My closed-form check gives 0.760 and 0.754, so the reversal is MC noise. The ICC=0.2 and ICC=0.5 values are also close at G=5 and G=30, so the ICC part of the claim is weaker than the G part.\",\n \"suggested_fix\": \"Say that the bias is driven mainly by G, that the ICC effect is small beyond ICC=0.2, and note the non-monotone MC estimate at G=10.\"\n }\n ],\n \"summary\": \"Re-running analysis.py in a scratch copy took about 2 s and reproduced results.json and table1.csv exactly. All required keys are present with the correct counts (27/27/18) and are consistent: 11 failure cells, 5 nominal-consistent cells, best_procedure_small_G=cr1, n_analysed=18000. The code follows the specified DGP, CR0/CR1 formulas, t_{G-1} critical value and unrestricted Rademacher WCB-t, with the correct bootstrap residual cluster sums. It uses the design seeds, R=2000 and B=399, and reads only design.csv. My own closed-form E[V_CR0]/Var(ybar) matches the MC relative bias, including the disclosed 2.46-SE deviation in G5_icc0.2. The claims are supported, there is an i.i.d. baseline, the Monte Carlo uncertainty and the classifications near the threshold are discussed, and the limitations cover distributions, heterogeneity, regressors and weights. Only minor wording and reporting issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON and validate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1385,"cache_read_input_tokens":24642,"output_tokens":1682,"output_tokens_details":{"thinking_tokens":433},"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":1385},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtRkQ1X7HajWu2rdfoL","requestRef":"29ecb313-aab9-4c33-b3c1-ee0831bab72f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2c5de747-bbd9-4cc1-9a10-b7d6a2fa54d1","timestamp":"2026-10-30T05:42:22.156Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}52{"parentUuid":"2c5de747-bbd9-4cc1-9a10-b7d6a2fa54d1","isSidechain":false,"promptId":"e88a3209-a74e-4912-8dc4-143ee450d1c1","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SJJtT5EZmRxxtWRnwR9A1z","type":"tool_result","content":"ok","is_error":false}]},"uuid":"f68ab463-1eb2-4af9-a416-bba14ea073c9","timestamp":"2026-10-30T05:42:22.236Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2c5de747-bbd9-4cc1-9a10-b7d6a2fa54d1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}53{"type":"api-request-blob","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","hash":"daf58fc2e06a80188d64de2683119af4ffb354ce0090acde1b8fdf5a30b349aa","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01SJJtT5EZmRxxtWRnwR9A1z","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\n \"id\": \"R1\",\n \"severity\": \"minor\",\n \"location\": \"claims.json C6 / report.md Results\",\n \"issue\": \"The claim that WCB beats CR1 at G=10 with ICC>0 is marked 'supported', but the caveat only compares the gap to the SEs of the individual coverages and says it was 'not formally tested'. The code already computes paired differences on shared replications. When I re-ran it, the paired WCB-CR1 differences were 0.014 (SE 0.0039) for C5 and 0.026 (SE 0.0043) for C6. That support is stronger than the caveat says, but it is not reported.\",\n \"suggested_fix\": \"Report the paired MC SE for the G=10 WCB-CR1 differences, as is already done for the G=5 ranking, and update the C6 caveat.\"\n },\n {\n \"id\": \"R2\",\n \"severity\": \"minor\",\n \"location\": \"report.md Results (variance bias bullet)\",\n \"issue\": \"The statement that the unbalanced cluster sizes make the bias 'much worse than the balanced-cluster factor (G-1)/G' is not backed by any balanced-design computation in the deliverables. It is plausible but untested here.\",\n \"suggested_fix\": \"Either add the closed-form E[V_CR0]/Var(ybar) for a balanced design of the same N and G, or label the statement as an interpretation.\"\n },\n {\n \"id\": \"R3\",\n \"severity\": \"minor\",\n \"location\": \"report.md / claims.json C4 ('most at small G and high ICC')\",\n \"issue\": \"In the MC estimates the bias is not monotone in ICC at G=10: CR0 is 0.762 at ICC=0.2 and 0.774 at ICC=0.5. My closed-form check gives 0.760 and 0.754, so the reversal is MC noise. The ICC=0.2 and ICC=0.5 values are also close at G=5 and G=30, so the ICC part of the claim is weaker than the G part.\",\n \"suggested_fix\": \"Say that the bias is driven mainly by G, that the ICC effect is small beyond ICC=0.2, and note the non-monotone MC estimate at G=10.\"\n }\n ],\n \"summary\": \"Re-running analysis.py in a scratch copy took about 2 s and reproduced results.json and table1.csv exactly. All required keys are present with the correct counts (27/27/18) and are consistent: 11 failure cells, 5 nominal-consistent cells, best_procedure_small_G=cr1, n_analysed=18000. The code follows the specified DGP, CR0/CR1 formulas, t_{G-1} critical value and unrestricted Rademacher WCB-t, with the correct bootstrap residual cluster sums. It uses the design seeds, R=2000 and B=399, and reads only design.csv. My own closed-form E[V_CR0]/Var(ybar) matches the MC relative bias, including the disclosed 2.46-SE deviation in G5_icc0.2. The claims are supported, there is an i.i.d. baseline, the Monte Carlo uncertainty and the classifications near the threshold are discussed, and the limitations cover distributions, heterogeneity, regressors and weights. Only minor wording and reporting issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON and validate"}}]}}54{"type":"api-request","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","id":"5a7b5197-ab9c-44e4-98ee-cf1166049fb7","timestamp":"2026-10-30T05:42:22.239Z","version":"2.1.314","querySource":"sdk","shapeHash":"740433175d8979a2c632c93a17b2bb3d45f0fa2b84e9918d91c8b3153051c068","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":"29ecb313-aab9-4c33-b3c1-ee0831bab72f","keep":14,"tail":["daf58fc2e06a80188d64de2683119af4ffb354ce0090acde1b8fdf5a30b349aa","fb3cb07943f01eec0810f700841dede7f8ec43c14df68231952b9beb99617cda"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4309f7290633bac4d6d15f2eabc39e05f042c57d6d144fe4c06f58e6774ee29c"}55{"parentUuid":"f68ab463-1eb2-4af9-a416-bba14ea073c9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtSwxZUxdZ8MMgxtvne","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":1689,"cache_read_input_tokens":26027,"output_tokens":732,"output_tokens_details":{"thinking_tokens":5},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1689},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":7025,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXtSwghQAifgYta5ZnMA","requestRef":"5a7b5197-ab9c-44e4-98ee-cf1166049fb7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a08d41df-5d3e-4a5e-a56e-f82b328ec6c2","timestamp":"2026-10-30T05:42:30.589Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}56{"parentUuid":"a08d41df-5d3e-4a5e-a56e-f82b328ec6c2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXtSwxZUxdZ8MMgxtvne","type":"message","role":"assistant","content":[{"type":"text","text":"I recommend **accepting** the submission. There are no critical or major issues, only three minor ones; the review is saved at `out/review/review.json`.\n\nI re-ran `out/analysis.py` in a scratch copy. It finished in about 2 seconds and reproduced `results.json` and `table1.csv` exactly. Every required key is there: 27 coverage values and 27 Monte Carlo standard errors, 18 variance-bias values, 11 failure cells, 5 cells consistent with 95% coverage, and 18,000 replications in total. The best procedure at five clusters is CR1, under the task's highest-average-coverage rule. Reading the code, it follows the task's rules exactly: the specified way of simulating the data, the CR0 and CR1 formulas, the Student t critical value, and the wild cluster bootstrap with ±1 weights. It uses the seeds, replication count and bootstrap count from `design.csv` and reads no other input. I worked out the expected CR0 variance ratio exactly and it matches the simulated values; the one 2.46-SE gap, in the five-cluster, ICC 0.2 cell, is disclosed in the report. The report includes a naive baseline interval, discusses Monte Carlo error and which classifications sit close to the 0.90 line, and is honest about what the design does not cover.\n\nThe three minor issues:\n- **Claim C6 is better supported than stated.** At ten clusters with ICC > 0, I computed paired standard errors for the bootstrap-minus-CR1 coverage gap: 0.014 ± 0.0039 and 0.026 ± 0.0043. These should be reported instead of \"not formally tested.\"\n- **The balanced-cluster comparison is unchecked.** Nothing in the deliverables backs the statement that unequal cluster sizes make the variance bias \"much worse\" than with equal sizes.\n- **The ICC part of claim C4 is overstated.** At ten clusters the simulated bias is slightly smaller at ICC 0.5 than at 0.2, the reverse of the claim, though my exact calculation shows this is noise. Overall the bias depends mainly on the number of clusters and changes little between ICC 0.2 and 0.5."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1689,"cache_read_input_tokens":26027,"output_tokens":732,"output_tokens_details":{"thinking_tokens":5},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1689},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXtSwghQAifgYta5ZnMA","requestRef":"5a7b5197-ab9c-44e4-98ee-cf1166049fb7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"86c0a7d1-5ea5-4ddf-a4c6-8078f22667de","timestamp":"2026-10-30T05:42:30.600Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0020","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","version":"2.1.314","gitBranch":"HEAD"}57{"type":"last-prompt","lastPrompt":"Review","leafUuid":"86c0a7d1-5ea5-4ddf-a4c6-8078f22667de","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982"}58{"type":"cost-state","sessionId":"b4971e4f-33c0-4444-94a5-dee52138a982","totalCostUSD":0.25606700000000004,"totalAPIDuration":64392,"totalAPIDurationWithoutRetries":64387,"totalToolDuration":3326,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":67854,"startTime":1793338882766,"modelUsage":{"claude-opus-5-5":{"inputTokens":18,"outputTokens":4919,"thinkingTokens":1594,"cacheReadInputTokens":132775,"cacheCreationInputTokens":26212,"cacheCreationEphemeral5mInputTokens":26212,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.25606700000000004}},"hasUnknownModelCost":false}59