1{"type":"atis-latch","atis":"","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:33:26.028Z","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","content":"Review"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:33:26.034Z","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}4{"parentUuid":null,"isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":"Review"},"uuid":"7f096273-5c6a-4ba6-b3c6-0429f1053497","timestamp":"2026-10-30T05:33:26.039Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","timestamp":"2026-10-30T05:33:26.054Z","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/RT0007\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":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"59df9926-f723-4bc4-b915-67981543a076","timestamp":"2026-10-30T05:33:26.054Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"bba8354a01dd7ecffb54ccebe3716d07f93e34901a568c1929d22daa0b39d475"}8{"parentUuid":"7f096273-5c6a-4ba6-b3c6-0429f1053497","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"9105e8c4-7f31-46c7-acc3-33439a0d35d1","timestamp":"2026-10-30T05:33:26.045Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"9105e8c4-7f31-46c7-acc3-33439a0d35d1","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"af3c6366-e1ef-4826-98b6-da583ed9270b","timestamp":"2026-10-30T05:33:26.045Z","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/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"af3c6366-e1ef-4826-98b6-da583ed9270b","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":"50378051-14d2-4f53-8d1b-f7d7f6d68348","timestamp":"2026-10-30T05:33:26.046Z","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/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}12{"parentUuid":"50378051-14d2-4f53-8d1b-f7d7f6d68348","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmRPwzUttvqHcsjDPg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Kaz3JgTyaV3eZFRrn857kB","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json"},"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":76,"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":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsmR8pYLDYgREoyyQFz","requestRef":"59df9926-f723-4bc4-b915-67981543a076","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"04ac6761-5752-436c-a3a3-eac0ab01d647","timestamp":"2026-10-30T05:33:27.734Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"04ac6761-5752-436c-a3a3-eac0ab01d647","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Kaz3JgTyaV3eZFRrn857kB","type":"tool_result","content":"# T3-synthesis — Does generative-AI assistance shorten the time workers need to complete their tasks? A small evidence synthesis\n\n## Scientific question\nFive accessible primary studies report how access to a generative-AI assistant changed the performance of workers (software developers, IT administrators, security analysts) on their tasks. They report their effects under different definitions: a regression coefficient on log time-on-task, a percentage change in completion time, a percentage difference in mean task duration holding accuracy constant, a percentage time saving per processed item with a p-value, and a difference-in-differences coefficient on output counts around the withdrawal of access. This is a complete, bounded evidence-synthesis project: extraction with locators → harmonisation onto one stated definition → pooled estimates with heterogeneity → forest plot → an appropriately limited synthesis. The target definition is θ = ln(T_AI / T_noAI), the natural logarithm of the ratio of mean task-completion time with AI assistance to mean task-completion time without it, for the same tasks, from a randomised comparison (negative = faster with AI). The estimands are: the five extracted values exactly as printed; the harmonised θ and its standard error for every study where both can be obtained from the printed quantities under the conventions below; the inverse-variance fixed-effect and DerSimonian–Laird random-effects pooled θ over the poolable studies, with Q, I² and τ²; and the synthesis conclusion that these numbers support.\n\n## Inputs\n- `data/studies.json` — the five items {\"id\", \"source\", \"short\", \"extract\"}: `extract` names the printed quantity to take from each source (which table/row/column or sentence).\n- `data/sources/arxiv-2410.12944v3.txt` — Paradis et al. (2024), *How much does AI impact development speed? An enterprise-based randomized controlled trial* (Google), CC BY 4.0: abstract, analytic approach, results Sections VI-B/VI-C with Table III (OLS on logged time on task; coefficients with standard errors in parentheses; the four model columns are collapsed into one line per row, see the extract's editorial note).\n- `data/sources/arxiv-2507.09089v2.txt` — Becker et al. (2025), *Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity* (METR), CC BY 4.0: abstract, effect-estimation section, opening of the results, Appendix D (regression, confidence intervals, conversion to speedup).\n- `data/sources/arxiv-2411.01067v2.txt` — Bono & Xu (2024), *Randomized Controlled Trials for Security Copilot for IT Administrators* (Microsoft), CC BY 4.0: abstract, RCT protocol, results on speed with Table 3 (task durations in minutes, holding accuracy constant; significance by asterisks only), Appendix B (how time savings are computed and bootstrapped).\n- `data/sources/arxiv-2511.13860v1.txt` — Bono (2025), *Randomized Controlled Trials for Phishing Triage Agent* (Microsoft), CC BY 4.0: abstract, methodology (three arms), results Sections 3.1 (true positives per analyst minute, Table 1) and 3.3 (Table 3, time per email with % time savings and p-values), Appendix B.\n- `data/sources/arxiv-2304.09339v1.txt` — Kreitmeir & Raschky (2023), *The Unintended Consequences of Censoring Digital Technology – Evidence from Italy's ChatGPT Ban*, CC BY 4.0: abstract, outcome definitions (Section 3.1), Section 4 with Table 1 (difference-in-differences coefficients, standard errors in parentheses).\n- `data/README.md` — provenance, retrieval times, licences, SHA-256 of the extracts.\n\n## Information-availability rules\n- The extracts are the only admissible evidence. A quantity that is not printed in the cited extract is not available, even if you believe it is in the full paper, in a figure, or elsewhere; do not substitute a remembered or guessed value.\n- Harmonisation conventions (state the one you apply in `transformation`):\n - a coefficient b on an AI indicator in a regression whose dependent variable is the natural log of completion time gives θ = b with SE(θ) = SE(b); a 95% confidence interval [L, U] on that scale gives SE = (U − L)/(2 × 1.96);\n - a percentage change in time c (e.g. \"+19%\" means c = 0.19, \"−29.79%\" means c = −0.2979) or a ratio of mean times T_AI / T_noAI gives θ = ln(1 + c) = ln(T_AI / T_noAI);\n - when only a two-sided p-value is printed for an estimate (no SE, no CI), the SE may be recovered as SE(θ) ≈ |θ| / z_{1−p/2} with z from the standard normal; mark the study as poolable with an approximate SE and say so;\n - when the only uncertainty information is significance stars, a p-value threshold, or a confidence interval shown in a figure that is not reproduced, SE(θ) cannot be obtained: the study is harmonisable (θ can be computed) but **not poolable** (`harmonised_se` = null, `poolable` = false, with the reason);\n - a study is **not harmonisable** (`harmonisable` = false, `harmonised_estimate` = null, with the reason) when the printed effect is not a comparison of task-completion times with and without AI access on the same tasks (for example an effect on output counts, or a comparison that is not AI-versus-no-AI).\n- Pooling: inverse-variance fixed effect and DerSimonian–Laird random effects over the poolable studies only, on the θ scale, with 95% intervals using 1.96; Q with k − 1 degrees of freedom; I² = max(0, (Q − df)/Q) × 100; τ² = max(0, (Q − df)/C) with C = Σw − Σw²/Σw. `heterogeneity_interpretation` is \"low\" if I² < 25, \"moderate\" if 25 ≤ I² < 50, \"substantial\" if I² ≥ 50. `pooled_significant_5pct` is true only if the random-effects 95% interval excludes 0.\n- `feasibility` refers to the project as a whole: the project is complete when every item has either harmonised values or an explicit, justified statement of what cannot be obtained, and the pooled estimates are computed over the poolable items.\n\n## Required outputs\n- `out/table1.csv` — the extraction table, one row per study (5 rows): `study`, `estimate_as_printed`, `uncertainty_as_printed`, `sample_as_printed`, `definition`, `locator`, `harmonised_estimate`, `harmonised_se`, `harmonisable`, `poolable`, `transformation`, `reason_if_not`.\n- `out/figure1.png` — a forest plot of the harmonised estimates (all harmonisable studies; those without an SE shown as points without intervals) with the pooled random-effects estimate.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T3-synthesis\" |\n| `target_definition` | string | — | the harmonisation target in your words |\n| `items` | object | — | {\"S1\": {...}, …, \"S5\": {...}} with, for each study: `estimate_as_printed` (string, the printed numbers with their printed unit/sign), `uncertainty_as_printed` (string: SE, CI, p-value, stars, or \"none printed\"), `sample_as_printed` (string), `definition` (string), `locator` (string: source id, table/section, row, column), `harmonisable` (boolean), `harmonised_estimate` (number or null, θ), `harmonised_se` (number or null), `poolable` (boolean), `transformation` (string, the formula with the printed inputs), `reason_if_not` (string or null) |\n| `k_extracted` | integer | — | number of items with an extracted printed value |\n| `k_harmonised` | integer | — | number of items with a non-null `harmonised_estimate` |\n| `k_pooled` | integer | — | number of items entering the pooled estimates |\n| `fe_estimate`, `fe_se`, `fe_ci_low`, `fe_ci_high` | number | log ratio | fixed-effect pooled θ, its SE and 95% interval |\n| `re_estimate`, `re_se`, `re_ci_low`, `re_ci_high` | number | log ratio | random-effects pooled θ, its SE and 95% interval |\n| `q_stat` | number | — | Cochran's Q |\n| `i2` | number | percent | I² |\n| `tau2` | number | — | DerSimonian–Laird τ² |\n| `heterogeneity_interpretation` | string | — | \"low\", \"moderate\" or \"substantial\" (rule above) |\n| `pooled_significant_5pct` | boolean | — | random-effects interval excludes 0 |\n| `pooled_pct_change_re` | number | percent | 100 × (exp(re_estimate) − 1) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" — refers to the project as a whole |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the inputs (rendering defects, internal inconsistencies of a source, ambiguous units, …) and how handled; empty list if none |\n| `n_input_rows` | object | lines / items | {file name: number of lines} for every file under `data/` that you read (text files: lines as reported by `wc -l`; `studies.json`: number of items) |\n| `n_analysed` | integer or null | — | number of studies assessed (5) |\n| `random_seed` | integer or null | — | null (no randomness) |\n\n- `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The synthesis must say what the pooled numbers can and cannot support given the number of poolable studies, the approximate SE, and the studies left out.\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/` only, deterministically; the script must print the source lines it relies on.\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- Report printed numbers exactly as printed (same sign, same decimals); transformations are applied only in the harmonised columns.\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 248\ndrwxr-xr-x@ 11 simon-pierreboucher staff 352 oct. 30 01:33 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:30 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 17539 oct. 30 01:32 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 2868 oct. 30 01:33 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 412 oct. 30 01:30 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 68212 oct. 30 01:32 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 7221 oct. 30 01:33 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 9990 oct. 30 01:32 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:33 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 01:32 state\n-rw-r--r--@ 1 simon-pierreboucher staff 4218 oct. 30 01:32 table1.csv\n{\n \"task_id\": \"T3-synthesis\",\n \"target_definition\": \"theta = ln(T_AI / T_noAI): natural log of the ratio of mean task-completion time with access to a generative-AI assistant to mean completion time without it, for the same tasks, from a randomised comparison; negative values mean faster with AI.\",\n \"items\": {\n \"S1\": {\n \"estimate_as_printed\": \"-0.24 (ExpCon, Model 2, LogToT; marker '.'); text: beta_1=-0.24, effect of AI = 21%\",\n \"uncertainty_as_printed\": \"SE (0.14); 95% CI = [-0.51, 0.03]; p=0.086\",\n \"sample_as_printed\": \"Table III: n = 96 (Section VI-B: N=47 AI, N=46 no-AI)\",\n \"definition\": \"OLS coefficient of the experimental condition (AI vs no-AI, randomised) on the natural log of time on task, controlling for developer-level factors (Model 2)\",\n \"locator\": \"arxiv-2410.12944v3; Table III (L76-L78), row ExpCon, column (2) 'Dev'; Section VI-C (L58) for CI and p\",\n \"harmonisable\": true,\n \"harmonised_estimate\": -0.24,\n \"harmonised_se\": 0.14,\n \"poolable\": true,\n \"transformation\": \"log-time coefficient: theta = b = -0.24; SE(theta) = SE(b) = 0.14 (printed SE used; CI-based SE = (0.03 - (-0.51))/3.92 = 0.1378 used only as sensitivity)\",\n \"reason_if_not\": null\n },\n \"S2\": {\n \"estimate_as_printed\": \"19% more time on average (AI allowed increases completion time by 19%)\",\n \"uncertainty_as_printed\": \"none printed (confidence interval shown only in Figure 1 / Figure 15, not reproduced in the extract)\",\n \"sample_as_printed\": \"16 developers, 246 tasks; 136 issues AI-allowed, 110 issues AI-disallowed\",\n \"definition\": \"S = E[time with AI allowed]/E[time AI disallowed] - 1, estimated as exp(beta)-1 from OLS of log implementation time on AI indicator and log forecast time (issue-level randomisation)\",\n \"locator\": \"arxiv-2507.09089v2; Section 3 Results (L62); abstract (L34); estimator in Section 2.3 (L45) and Appendix D.1-D.3\",\n \"harmonisable\": true,\n \"harmonised_estimate\": 0.17395330712343798,\n \"harmonised_se\": null,\n \"poolable\": false,\n \"transformation\": \"percentage change: c = +0.19; theta = ln(1 + 0.19) = 0.173953 (equals the regression beta since S = exp(beta) - 1)\",\n \"reason_if_not\": \"Not poolable: no SE, CI or p-value is printed in the extract; the confidence interval appears only in a figure that is not reproduced, so SE(theta) cannot be obtained.\"\n },\n \"S3\": {\n \"estimate_as_printed\": \"Treatment 44.29 min, Control 63.10 min (Overall 53.84); Improvement -29.79%***\",\n \"uncertainty_as_printed\": \"significance stars only (***; per the paper's scheme 0<p<=0.01); no SE or CI printed\",\n \"sample_as_printed\": \"181 subjects completed the task satisfactorily (one subject dropped)\",\n \"definition\": \"Percentage difference in mean task duration (minutes), Copilot (treatment) vs control without Copilot, holding accuracy constant (control duration predicted at treatment accuracy; Appendix B), randomised\",\n \"locator\": \"arxiv-2411.01067v2; Section 4.2, Table 3 (L51-L55), row 'Aggregate Results / All Content', columns Treatment, Control, Improvement\",\n \"harmonisable\": true,\n \"harmonised_estimate\": -0.353679434958934,\n \"harmonised_se\": null,\n \"poolable\": false,\n \"transformation\": \"percentage change: c = -0.2979; theta = ln(1 + (-0.2979)) = -0.353679 (ratio of displayed means ln(44.29/63.10) = -0.353962, sensitivity only)\",\n \"reason_if_not\": \"Not poolable: uncertainty is printed only as significance stars (p<=0.01); SE(theta) cannot be recovered from a threshold.\"\n },\n \"S4\": {\n \"estimate_as_printed\": \"Aware 50.5, Control 56.9 (row labels: Time per Email (s)); % Time Savings 11.1\",\n \"uncertainty_as_printed\": \"p-value 0.471\",\n \"sample_as_printed\": \"Aware N=56, Control N=52 (of 167 analysts in three arms; 13 low-scoring responses filtered)\",\n \"definition\": \"Percentage time saving per processed email (Full Corpus, whole 25-email queue without resolve-benign protocol), Aware arm (agent verdicts, rationale, agent-ordered queue) vs Control (random order, no AI), randomised\",\n \"locator\": \"arxiv-2511.13860v1; Section 3.3, Table 3 (L86-L96), column 'Full Corpus', rows Aware/Control Time per Email, % Time Savings, p-value\",\n \"harmonisable\": true,\n \"harmonised_estimate\": -0.11765804346823246,\n \"harmonised_se\": 0.1632205919720678,\n \"poolable\": true,\n \"transformation\": \"percentage time saving 11.1% -> c = -0.111; theta = ln(1 + (-0.111)) = -0.117658; APPROXIMATE SE from two-sided p: SE = |theta|/z_(1-0.471/2) = 0.117658/0.720853 = 0.163221 (ratio of displayed means ln(50.5/56.9) = -0.119322, sensitivity only)\",\n \"reason_if_not\": null\n },\n \"S5\": {\n \"estimate_as_printed\": \"-0.278 (Treat x Post, Output, panel A, column (3))\",\n \"uncertainty_as_printed\": \"SE (0.295) (clustered at user level)\",\n \"sample_as_printed\": \"N = 18332 (user-day observations, users with affiliation)\",\n \"definition\": \"Difference-in-differences coefficient (Italy vs Austria/France, post vs pre ChatGPT ban) on an aggregate count of GitHub Output events (Push, Pull Requests, comments, Create, Issues)\",\n \"locator\": \"arxiv-2304.09339v1; Section 4, Table 1 (L80-L88), panel A 'Pre 27/28.03 - Post 03/04.04', row Treat x Post, column (3) Output (users with affiliation)\",\n \"harmonisable\": false,\n \"harmonised_estimate\": null,\n \"harmonised_se\": null,\n \"poolable\": false,\n \"transformation\": \"none: no transformation maps an effect on output counts onto ln(T_AI/T_noAI)\",\n \"reason_if_not\": \"Not harmonisable: the effect is on output counts (GitHub events) around the withdrawal of ChatGPT access in a non-randomised difference-in-differences design, not a comparison of task-completion times with and without AI on the same tasks.\"\n }\n },\n \"k_extracted\": 5,\n \"k_harmonised\": 4,\n \"k_pooled\": 2,\n \"pooled_study_ids\": [\n \"S1\",\n \"S4\"\n ],\n \"fe_estimate\": -0.18814332871148873,\n \"fe_se\": 0.10626483095451474,\n \"fe_ci_low\": -0.39642239738233764,\n \"fe_ci_high\": 0.02013573995936016,\n \"re_estimate\": -0.18814332871148873,\n \"re_se\": 0.10626483095451474,\n \"re_ci_low\": -0.39642239738233764,\n \"re_ci_high\": 0.02013573995936016,\n \"q_stat\": 0.3236860522786328,\n \"q_df\": 1,\n \"i2\": 0.0,\n \"tau2\": 0.0,\n \"heterogeneity_interpretation\": \"low\",\n \"pooled_significant_5pct\": false,\n \"pooled_pct_change_re\": -17.15040485348688,\n \"pooled_pct_change_re_ci_low\": -32.72775202989503,\n \"pooled_pct_change_re_ci_high\": 2.0339831514392115,\n \"baseline_unweighted_mean_theta_harmonised\": -0.13434604282593213,\n \"baseline_unweighted_mean_theta_pooled\": -0.17882902173411622,\n \"sensitivity_ci_se_s1_re_estimate\": -0.1891067723193802,\n \"sensitivity_ci_se_s1_re_se\": 0.10527305720065441,\n \"sensitivity_ratio_s4_theta\": -0.11932200485097105,\n \"sensitivity_ratio_s4_re_estimate\": -0.18967451746361488,\n \"sensitivity_ratio_s4_re_se\": 0.10689411567852646,\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"S1 (Paradis): Table III states n = 96, while Section VI-B reports N=47 (AI) + N=46 (no-AI) = 93 completed tasks.\",\n \"handling\": \"Both sample statements recorded in sample_as_printed; coefficient and SE taken from Table III as designated; no effect on theta.\"\n },\n {\n \"issue\": \"S1 (Paradis): Section VI-B says the AI group (Mean LogToT=4.6) was faster than the no-AI group (Mean LogToT=4.3), which contradicts the raw means (96 vs 114 min); the log means appear swapped.\",\n \"handling\": \"Not used; harmonisation relies on the Model 2 regression coefficient designated in studies.json.\"\n },\n {\n \"issue\": \"S1 (Paradis): printed SE 0.14 and printed 95% CI [-0.51, 0.03] imply slightly different SEs (0.14 vs 0.1378); '21% faster' denotes a 21% reduction in time (1-exp(beta)).\",\n \"handling\": \"Printed SE used (convention for a coefficient with SE); CI-based SE reported as sensitivity_ci_se_s1_* keys.\"\n },\n {\n \"issue\": \"S2 (Becker): the confidence interval for the 19% estimate is shown only in Figure 1/Figure 15, which are not reproduced in the extract.\",\n \"handling\": \"No SE imputed; S2 harmonised (theta = ln 1.19) but not poolable.\"\n },\n {\n \"issue\": \"S3 (Bono & Xu): uncertainty only as significance stars with a non-standard scheme (* 0.05<p<=0.1, ** 0.01<p<=0.05, *** p<=0.01); displayed minutes give 44.29/63.10-1 = -29.81% vs printed -29.79%; control subjects could use other AI tools (25% did).\",\n \"handling\": \"Printed -29.79% used for theta; S3 not poolable; contamination noted as a limitation.\"\n },\n {\n \"issue\": \"S4 (Bono): printed % Time Savings 11.1 does not equal 1-50.5/56.9 = 11.25% (Malicious and Non-Malicious columns also do not reproduce from displayed times); row labels say seconds per email, but Full Corpus values (50.5, 56.9) are inconsistent with the per-email Malicious/Non-Malicious values (2.8/1.9, 1.8/2.4), so the unit of the Full Corpus column is ambiguous.\",\n \"handling\": \"Printed % saving (11.1) used for theta (unit-free); ratio of displayed means used as sensitivity (sensitivity_ratio_s4_* keys); SE recovered approximately from p = 0.471.\"\n },\n {\n \"issue\": \"S4 (Bono): the Aware arm differs from Control by both agent verdicts/rationales and agent-prioritised queue ordering; only a p-value is printed.\",\n \"handling\": \"Treated as AI vs no-AI; SE flagged as approximate.\"\n },\n {\n \"issue\": \"S5 (Kreitmeir & Raschky): table notes print '** p<0.5' (presumably 0.05); row label rendered as '\\\\times TreatPost'; date line under the author block is a rendering artefact; whether Output is logged is ambiguous in Section 3.1.\",\n \"handling\": \"Values copied verbatim; S5 not harmonisable regardless of these issues.\"\n },\n {\n \"issue\": \"Stray 'p<', 'p=' and footnote-number lines in the extracts.\",\n \"handling\": \"Ignored as rendering artefacts per data/README.md.\"\n }\n ],\n \"n_input_rows\": {\n \"studies.json\": 5,\n \"README.md\": 17,\n \"sources/arxiv-2304.09339v1.txt\": 108,\n \"sources/arxiv-2410.12944v3.txt\": 112,\n \"sources/arxiv-2411.01067v2.txt\": 109,\n \"sources/arxiv-2507.09089v2.txt\": 132,\n \"sources/arxiv-2511.13860v1.txt\": 162\n },\n \"n_analysed\": 5,\n \"random_seed\": null\n}[\n {\"id\":\"C1\",\"text\":\"Of the five studies, five printed values were extracted, four could be harmonised to theta = ln(T_AI/T_noAI), and two (S1, S4) could be pooled; S5 measures output counts in a DiD and is not harmonisable.\",\"results_keys\":[\"k_extracted\",\"k_harmonised\",\"k_pooled\",\"items\"],\"status\":\"supported\",\"caveat\":\"Poolability limited by what the extracts print; S2 and S3 uncertainty exists in the full papers but is not admissible here.\"},\n {\"id\":\"C2\",\"text\":\"Harmonised estimates: S1 -0.240, S2 +0.174, S3 -0.354, S4 -0.118 (log time ratio).\",\"results_keys\":[\"items\"],\"status\":\"supported\",\"caveat\":\"S3 and S4 use the printed percentages, which differ slightly from ratios of displayed means.\"},\n {\"id\":\"C3\",\"text\":\"The pooled random-effects estimate over S1 and S4 is theta = -0.188 (about 17% shorter completion time), 95% CI [-0.396, 0.020], equal to the fixed-effect estimate.\",\"results_keys\":[\"re_estimate\",\"re_se\",\"re_ci_low\",\"re_ci_high\",\"fe_estimate\",\"fe_ci_low\",\"fe_ci_high\",\"pooled_pct_change_re\"],\"status\":\"supported\",\"caveat\":\"k = 2; S4 SE approximated from a p-value.\"},\n {\"id\":\"C4\",\"text\":\"The pooled effect is not statistically significant at the 5% level; the evidence does not establish that AI assistance shortens task time.\",\"results_keys\":[\"pooled_significant_5pct\",\"re_ci_low\",\"re_ci_high\"],\"status\":\"supported\",\"caveat\":\"Absence of significance with k=2 is not evidence of no effect.\"},\n {\"id\":\"C5\",\"text\":\"Measured heterogeneity among the pooled studies is low (Q = 0.324, I2 = 0%, tau2 = 0), but this reflects k = 2 and the excluded studies' estimates (+0.174, -0.354) suggest substantive heterogeneity not captured by the pooled analysis.\",\"results_keys\":[\"q_stat\",\"i2\",\"tau2\",\"heterogeneity_interpretation\",\"items\"],\"status\":\"supported\",\"caveat\":\"Heterogeneity of excluded studies is qualitative only; cannot be quantified without SEs.\"},\n {\"id\":\"C6\",\"text\":\"The pooled result is robust to using the CI-derived SE for S1 and the displayed-means ratio for S4.\",\"results_keys\":[\"sensitivity_ci_se_s1_re_estimate\",\"sensitivity_ci_se_s1_re_se\",\"sensitivity_ratio_s4_re_estimate\",\"sensitivity_ratio_s4_re_se\",\"sensitivity_ratio_s4_theta\"],\"status\":\"supported\",\"caveat\":\"Only two small perturbations examined.\"},\n {\"id\":\"C7\",\"text\":\"Baseline unweighted means of theta are -0.179 (pooled studies) and -0.134 (all harmonised studies).\",\"results_keys\":[\"baseline_unweighted_mean_theta_pooled\",\"baseline_unweighted_mean_theta_harmonised\"],\"status\":\"supported\",\"caveat\":\"Unweighted means ignore precision; descriptive only.\"},\n {\"id\":\"C8\",\"text\":\"The project is complete in the TASK sense: every item has harmonised values or a justified statement of what cannot be obtained.\",\"results_keys\":[\"feasibility\",\"feasibility_reason\",\"data_issues\"],\"status\":\"supported\",\"caveat\":\"Completeness of the project does not imply strength of evidence.\"}\n]","is_error":false}]},"uuid":"3328b947-c9d1-4333-8843-9776df9b770d","timestamp":"2026-10-30T05:33:27.818Z","toolUseResult":{"stdout":"# T3-synthesis — Does generative-AI assistance shorten the time workers need to complete their tasks? A small evidence synthesis\n\n## Scientific question\nFive accessible primary studies report how access to a generative-AI assistant changed the performance of workers (software developers, IT administrators, security analysts) on their tasks. They report their effects under different definitions: a regression coefficient on log time-on-task, a percentage change in completion time, a percentage difference in mean task duration holding accuracy constant, a percentage time saving per processed item with a p-value, and a difference-in-differences coefficient on output counts around the withdrawal of access. This is a complete, bounded evidence-synthesis project: extraction with locators → harmonisation onto one stated definition → pooled estimates with heterogeneity → forest plot → an appropriately limited synthesis. The target definition is θ = ln(T_AI / T_noAI), the natural logarithm of the ratio of mean task-completion time with AI assistance to mean task-completion time without it, for the same tasks, from a randomised comparison (negative = faster with AI). The estimands are: the five extracted values exactly as printed; the harmonised θ and its standard error for every study where both can be obtained from the printed quantities under the conventions below; the inverse-variance fixed-effect and DerSimonian–Laird random-effects pooled θ over the poolable studies, with Q, I² and τ²; and the synthesis conclusion that these numbers support.\n\n## Inputs\n- `data/studies.json` — the five items {\"id\", \"source\", \"short\", \"extract\"}: `extract` names the printed quantity to take from each source (which table/row/column or sentence).\n- `data/sources/arxiv-2410.12944v3.txt` — Paradis et al. (2024), *How much does AI impact development speed? An enterprise-based randomized controlled trial* (Google), CC BY 4.0: abstract, analytic approach, results Sections VI-B/VI-C with Table III (OLS on logged time on task; coefficients with standard errors in parentheses; the four model columns are collapsed into one line per row, see the extract's editorial note).\n- `data/sources/arxiv-2507.09089v2.txt` — Becker et al. (2025), *Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity* (METR), CC BY 4.0: abstract, effect-estimation section, opening of the results, Appendix D (regression, confidence intervals, conversion to speedup).\n- `data/sources/arxiv-2411.01067v2.txt` — Bono & Xu (2024), *Randomized Controlled Trials for Security Copilot for IT Administrators* (Microsoft), CC BY 4.0: abstract, RCT protocol, results on speed with Table 3 (task durations in minutes, holding accuracy constant; significance by asterisks only), Appendix B (how time savings are computed and bootstrapped).\n- `data/sources/arxiv-2511.13860v1.txt` — Bono (2025), *Randomized Controlled Trials for Phishing Triage Agent* (Microsoft), CC BY 4.0: abstract, methodology (three arms), results Sections 3.1 (true positives per analyst minute, Table 1) and 3.3 (Table 3, time per email with % time savings and p-values), Appendix B.\n- `data/sources/arxiv-2304.09339v1.txt` — Kreitmeir & Raschky (2023), *The Unintended Consequences of Censoring Digital Technology – Evidence from Italy's ChatGPT Ban*, CC BY 4.0: abstract, outcome definitions (Section 3.1), Section 4 with Table 1 (difference-in-differences coefficients, standard errors in parentheses).\n- `data/README.md` — provenance, retrieval times, licences, SHA-256 of the extracts.\n\n## Information-availability rules\n- The extracts are the only admissible evidence. A quantity that is not printed in the cited extract is not available, even if you believe it is in the full paper, in a figure, or elsewhere; do not substitute a remembered or guessed value.\n- Harmonisation conventions (state the one you apply in `transformation`):\n - a coefficient b on an AI indicator in a regression whose dependent variable is the natural log of completion time gives θ = b with SE(θ) = SE(b); a 95% confidence interval [L, U] on that scale gives SE = (U − L)/(2 × 1.96);\n - a percentage change in time c (e.g. \"+19%\" means c = 0.19, \"−29.79%\" means c = −0.2979) or a ratio of mean times T_AI / T_noAI gives θ = ln(1 + c) = ln(T_AI / T_noAI);\n - when only a two-sided p-value is printed for an estimate (no SE, no CI), the SE may be recovered as SE(θ) ≈ |θ| / z_{1−p/2} with z from the standard normal; mark the study as poolable with an approximate SE and say so;\n - when the only uncertainty information is significance stars, a p-value threshold, or a confidence interval shown in a figure that is not reproduced, SE(θ) cannot be obtained: the study is harmonisable (θ can be computed) but **not poolable** (`harmonised_se` = null, `poolable` = false, with the reason);\n - a study is **not harmonisable** (`harmonisable` = false, `harmonised_estimate` = null, with the reason) when the printed effect is not a comparison of task-completion times with and without AI access on the same tasks (for example an effect on output counts, or a comparison that is not AI-versus-no-AI).\n- Pooling: inverse-variance fixed effect and DerSimonian–Laird random effects over the poolable studies only, on the θ scale, with 95% intervals using 1.96; Q with k − 1 degrees of freedom; I² = max(0, (Q − df)/Q) × 100; τ² = max(0, (Q − df)/C) with C = Σw − Σw²/Σw. `heterogeneity_interpretation` is \"low\" if I² < 25, \"moderate\" if 25 ≤ I² < 50, \"substantial\" if I² ≥ 50. `pooled_significant_5pct` is true only if the random-effects 95% interval excludes 0.\n- `feasibility` refers to the project as a whole: the project is complete when every item has either harmonised values or an explicit, justified statement of what cannot be obtained, and the pooled estimates are computed over the poolable items.\n\n## Required outputs\n- `out/table1.csv` — the extraction table, one row per study (5 rows): `study`, `estimate_as_printed`, `uncertainty_as_printed`, `sample_as_printed`, `definition`, `locator`, `harmonised_estimate`, `harmonised_se`, `harmonisable`, `poolable`, `transformation`, `reason_if_not`.\n- `out/figure1.png` — a forest plot of the harmonised estimates (all harmonisable studies; those without an SE shown as points without intervals) with the pooled random-effects estimate.\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T3-synthesis\" |\n| `target_definition` | string | — | the harmonisation target in your words |\n| `items` | object | — | {\"S1\": {...}, …, \"S5\": {...}} with, for each study: `estimate_as_printed` (string, the printed numbers with their printed unit/sign), `uncertainty_as_printed` (string: SE, CI, p-value, stars, or \"none printed\"), `sample_as_printed` (string), `definition` (string), `locator` (string: source id, table/section, row, column), `harmonisable` (boolean), `harmonised_estimate` (number or null, θ), `harmonised_se` (number or null), `poolable` (boolean), `transformation` (string, the formula with the printed inputs), `reason_if_not` (string or null) |\n| `k_extracted` | integer | — | number of items with an extracted printed value |\n| `k_harmonised` | integer | — | number of items with a non-null `harmonised_estimate` |\n| `k_pooled` | integer | — | number of items entering the pooled estimates |\n| `fe_estimate`, `fe_se`, `fe_ci_low`, `fe_ci_high` | number | log ratio | fixed-effect pooled θ, its SE and 95% interval |\n| `re_estimate`, `re_se`, `re_ci_low`, `re_ci_high` | number | log ratio | random-effects pooled θ, its SE and 95% interval |\n| `q_stat` | number | — | Cochran's Q |\n| `i2` | number | percent | I² |\n| `tau2` | number | — | DerSimonian–Laird τ² |\n| `heterogeneity_interpretation` | string | — | \"low\", \"moderate\" or \"substantial\" (rule above) |\n| `pooled_significant_5pct` | boolean | — | random-effects interval excludes 0 |\n| `pooled_pct_change_re` | number | percent | 100 × (exp(re_estimate) − 1) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" — refers to the project as a whole |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | problems detected in the inputs (rendering defects, internal inconsistencies of a source, ambiguous units, …) and how handled; empty list if none |\n| `n_input_rows` | object | lines / items | {file name: number of lines} for every file under `data/` that you read (text files: lines as reported by `wc -l`; `studies.json`: number of items) |\n| `n_analysed` | integer or null | — | number of studies assessed (5) |\n| `random_seed` | integer or null | — | null (no randomness) |\n\n- `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The synthesis must say what the pooled numbers can and cannot support given the number of poolable studies, the approximate SE, and the studies left out.\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/` only, deterministically; the script must print the source lines it relies on.\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- Report printed numbers exactly as printed (same sign, same decimals); transformations are applied only in the harmonised columns.\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 248\ndrwxr-xr-x@ 11 simon-pierreboucher staff 352 oct. 30 01:33 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 01:30 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 17539 oct. 30 01:32 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 2868 oct. 30 01:33 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 412 oct. 30 01:30 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 68212 oct. 30 01:32 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 7221 oct. 30 01:33 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 9990 oct. 30 01:32 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 01:33 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 01:32 state\n-rw-r--r--@ 1 simon-pierreboucher staff 4218 oct. 30 01:32 table1.csv\n{\n \"task_id\": \"T3-synthesis\",\n \"target_definition\": \"theta = ln(T_AI / T_noAI): natural log of the ratio of mean task-completion time with access to a generative-AI assistant to mean completion time without it, for the same tasks, from a randomised comparison; negative values mean faster with AI.\",\n \"items\": {\n \"S1\": {\n \"estimate_as_printed\": \"-0.24 (ExpCon, Model 2, LogToT; marker '.'); text: beta_1=-0.24, effect of AI = 21%\",\n \"uncertainty_as_printed\": \"SE (0.14); 95% CI = [-0.51, 0.03]; p=0.086\",\n \"sample_as_printed\": \"Table III: n = 96 (Section VI-B: N=47 AI, N=46 no-AI)\",\n \"definition\": \"OLS coefficient of the experimental condition (AI vs no-AI, randomised) on the natural log of time on task, controlling for developer-level factors (Model 2)\",\n \"locator\": \"arxiv-2410.12944v3; Table III (L76-L78), row ExpCon, column (2) 'Dev'; Section VI-C (L58) for CI and p\",\n \"harmonisable\": true,\n \"harmonised_estimate\": -0.24,\n \"harmonised_se\": 0.14,\n \"poolable\": true,\n \"transformation\": \"log-time coefficient: theta = b = -0.24; SE(theta) = SE(b) = 0.14 (printed SE used; CI-based SE = (0.03 - (-0.51))/3.92 = 0.1378 used only as sensitivity)\",\n \"reason_if_not\": null\n },\n \"S2\": {\n \"estimate_as_printed\": \"19% more time on average (AI allowed increases completion time by 19%)\",\n \"uncertainty_as_printed\": \"none printed (confidence interval shown only in Figure 1 / Figure 15, not reproduced in the extract)\",\n \"sample_as_printed\": \"16 developers, 246 tasks; 136 issues AI-allowed, 110 issues AI-disallowed\",\n \"definition\": \"S = E[time with AI allowed]/E[time AI disallowed] - 1, estimated as exp(beta)-1 from OLS of log implementation time on AI indicator and log forecast time (issue-level randomisation)\",\n \"locator\": \"arxiv-2507.09089v2; Section 3 Results (L62); abstract (L34); estimator in Section 2.3 (L45) and Appendix D.1-D.3\",\n \"harmonisable\": true,\n \"harmonised_estimate\": 0.17395330712343798,\n \"harmonised_se\": null,\n \"poolable\": false,\n \"transformation\": \"percentage change: c = +0.19; theta = ln(1 + 0.19) = 0.173953 (equals the regression beta since S = exp(beta) - 1)\",\n \"reason_if_not\": \"Not poolable: no SE, CI or p-value is printed in the extract; the confidence interval appears only in a figure that is not reproduced, so SE(theta) cannot be obtained.\"\n },\n \"S3\": {\n \"estimate_as_printed\": \"Treatment 44.29 min, Control 63.10 min (Overall 53.84); Improvement -29.79%***\",\n \"uncertainty_as_printed\": \"significance stars only (***; per the paper's scheme 0<p<=0.01); no SE or CI printed\",\n \"sample_as_printed\": \"181 subjects completed the task satisfactorily (one subject dropped)\",\n \"definition\": \"Percentage difference in mean task duration (minutes), Copilot (treatment) vs control without Copilot, holding accuracy constant (control duration predicted at treatment accuracy; Appendix B), randomised\",\n \"locator\": \"arxiv-2411.01067v2; Section 4.2, Table 3 (L51-L55), row 'Aggregate Results / All Content', columns Treatment, Control, Improvement\",\n \"harmonisable\": true,\n \"harmonised_estimate\": -0.353679434958934,\n \"harmonised_se\": null,\n \"poolable\": false,\n \"transformation\": \"percentage change: c = -0.2979; theta = ln(1 + (-0.2979)) = -0.353679 (ratio of displayed means ln(44.29/63.10) = -0.353962, sensitivity only)\",\n \"reason_if_not\": \"Not poolable: uncertainty is printed only as significance stars (p<=0.01); SE(theta) cannot be recovered from a threshold.\"\n },\n \"S4\": {\n \"estimate_as_printed\": \"Aware 50.5, Control 56.9 (row labels: Time per Email (s)); % Time Savings 11.1\",\n \"uncertainty_as_printed\": \"p-value 0.471\",\n \"sample_as_printed\": \"Aware N=56, Control N=52 (of 167 analysts in three arms; 13 low-scoring responses filtered)\",\n \"definition\": \"Percentage time saving per processed email (Full Corpus, whole 25-email queue without resolve-benign protocol), Aware arm (agent verdicts, rationale, agent-ordered queue) vs Control (random order, no AI), randomised\",\n \"locator\": \"arxiv-2511.13860v1; Section 3.3, Table 3 (L86-L96), column 'Full Corpus', rows Aware/Control Time per Email, % Time Savings, p-value\",\n \"harmonisable\": true,\n \"harmonised_estimate\": -0.11765804346823246,\n \"harmonised_se\": 0.1632205919720678,\n \"poolable\": true,\n \"transformation\": \"percentage time saving 11.1% -> c = -0.111; theta = ln(1 + (-0.111)) = -0.117658; APPROXIMATE SE from two-sided p: SE = |theta|/z_(1-0.471/2) = 0.117658/0.720853 = 0.163221 (ratio of displayed means ln(50.5/56.9) = -0.119322, sensitivity only)\",\n \"reason_if_not\": null\n },\n \"S5\": {\n \"estimate_as_printed\": \"-0.278 (Treat x Post, Output, panel A, column (3))\",\n \"uncertainty_as_printed\": \"SE (0.295) (clustered at user level)\",\n \"sample_as_printed\": \"N = 18332 (user-day observations, users with affiliation)\",\n \"definition\": \"Difference-in-differences coefficient (Italy vs Austria/France, post vs pre ChatGPT ban) on an aggregate count of GitHub Output events (Push, Pull Requests, comments, Create, Issues)\",\n \"locator\": \"arxiv-2304.09339v1; Section 4, Table 1 (L80-L88), panel A 'Pre 27/28.03 - Post 03/04.04', row Treat x Post, column (3) Output (users with affiliation)\",\n \"harmonisable\": false,\n \"harmonised_estimate\": null,\n \"harmonised_se\": null,\n \"poolable\": false,\n \"transformation\": \"none: no transformation maps an effect on output counts onto ln(T_AI/T_noAI)\",\n \"reason_if_not\": \"Not harmonisable: the effect is on output counts (GitHub events) around the withdrawal of ChatGPT access in a non-randomised difference-in-differences design, not a comparison of task-completion times with and without AI on the same tasks.\"\n }\n },\n \"k_extracted\": 5,\n \"k_harmonised\": 4,\n \"k_pooled\": 2,\n \"pooled_study_ids\": [\n \"S1\",\n \"S4\"\n ],\n \"fe_estimate\": -0.18814332871148873,\n \"fe_se\": 0.10626483095451474,\n \"fe_ci_low\": -0.39642239738233764,\n \"fe_ci_high\": 0.02013573995936016,\n \"re_estimate\": -0.18814332871148873,\n \"re_se\": 0.10626483095451474,\n \"re_ci_low\": -0.39642239738233764,\n \"re_ci_high\": 0.02013573995936016,\n \"q_stat\": 0.3236860522786328,\n \"q_df\": 1,\n \"i2\": 0.0,\n \"tau2\": 0.0,\n \"heterogeneity_interpretation\": \"low\",\n \"pooled_significant_5pct\": false,\n \"pooled_pct_change_re\": -17.15040485348688,\n \"pooled_pct_change_re_ci_low\": -32.72775202989503,\n \"pooled_pct_change_re_ci_high\": 2.0339831514392115,\n \"baseline_unweighted_mean_theta_harmonised\": -0.13434604282593213,\n \"baseline_unweighted_mean_theta_pooled\": -0.17882902173411622,\n \"sensitivity_ci_se_s1_re_estimate\": -0.1891067723193802,\n \"sensitivity_ci_se_s1_re_se\": 0.10527305720065441,\n \"sensitivity_ratio_s4_theta\": -0.11932200485097105,\n \"sensitivity_ratio_s4_re_estimate\": -0.18967451746361488,\n \"sensitivity_ratio_s4_re_se\": 0.10689411567852646,\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"S1 (Paradis): Table III states n = 96, while Section VI-B reports N=47 (AI) + N=46 (no-AI) = 93 completed tasks.\",\n \"handling\": \"Both sample statements recorded in sample_as_printed; coefficient and SE taken from Table III as designated; no effect on theta.\"\n },\n {\n \"issue\": \"S1 (Paradis): Section VI-B says the AI group (Mean LogToT=4.6) was faster than the no-AI group (Mean LogToT=4.3), which contradicts the raw means (96 vs 114 min); the log means appear swapped.\",\n \"handling\": \"Not used; harmonisation relies on the Model 2 regression coefficient designated in studies.json.\"\n },\n {\n \"issue\": \"S1 (Paradis): printed SE 0.14 and printed 95% CI [-0.51, 0.03] imply slightly different SEs (0.14 vs 0.1378); '21% faster' denotes a 21% reduction in time (1-exp(beta)).\",\n \"handling\": \"Printed SE used (convention for a coefficient with SE); CI-based SE reported as sensitivity_ci_se_s1_* keys.\"\n },\n {\n \"issue\": \"S2 (Becker): the confidence interval for the 19% estimate is shown only in Figure 1/Figure 15, which are not reproduced in the extract.\",\n \"handling\": \"No SE imputed; S2 harmonised (theta = ln 1.19) but not poolable.\"\n },\n {\n \"issue\": \"S3 (Bono & Xu): uncertainty only as significance stars with a non-standard scheme (* 0.05<p<=0.1, ** 0.01<p<=0.05, *** p<=0.01); displayed minutes give 44.29/63.10-1 = -29.81% vs printed -29.79%; control subjects could use other AI tools (25% did).\",\n \"handling\": \"Printed -29.79% used for theta; S3 not poolable; contamination noted as a limitation.\"\n },\n {\n \"issue\": \"S4 (Bono): printed % Time Savings 11.1 does not equal 1-50.5/56.9 = 11.25% (Malicious and Non-Malicious columns also do not reproduce from displayed times); row labels say seconds per email, but Full Corpus values (50.5, 56.9) are inconsistent with the per-email Malicious/Non-Malicious values (2.8/1.9, 1.8/2.4), so the unit of the Full Corpus column is ambiguous.\",\n \"handling\": \"Printed % saving (11.1) used for theta (unit-free); ratio of displayed means used as sensitivity (sensitivity_ratio_s4_* keys); SE recovered approximately from p = 0.471.\"\n },\n {\n \"issue\": \"S4 (Bono): the Aware arm differs from Control by both agent verdicts/rationales and agent-prioritised queue ordering; only a p-value is printed.\",\n \"handling\": \"Treated as AI vs no-AI; SE flagged as approximate.\"\n },\n {\n \"issue\": \"S5 (Kreitmeir & Raschky): table notes print '** p<0.5' (presumably 0.05); row label rendered as '\\\\times TreatPost'; date line under the author block is a rendering artefact; whether Output is logged is ambiguous in Section 3.1.\",\n \"handling\": \"Values copied verbatim; S5 not harmonisable regardless of these issues.\"\n },\n {\n \"issue\": \"Stray 'p<', 'p=' and footnote-number lines in the extracts.\",\n \"handling\": \"Ignored as rendering artefacts per data/README.md.\"\n }\n ],\n \"n_input_rows\": {\n \"studies.json\": 5,\n \"README.md\": 17,\n \"sources/arxiv-2304.09339v1.txt\": 108,\n \"sources/arxiv-2410.12944v3.txt\": 112,\n \"sources/arxiv-2411.01067v2.txt\": 109,\n \"sources/arxiv-2507.09089v2.txt\": 132,\n \"sources/arxiv-2511.13860v1.txt\": 162\n },\n \"n_analysed\": 5,\n \"random_seed\": null\n}[\n {\"id\":\"C1\",\"text\":\"Of the five studies, five printed values were extracted, four could be harmonised to theta = ln(T_AI/T_noAI), and two (S1, S4) could be pooled; S5 measures output counts in a DiD and is not harmonisable.\",\"results_keys\":[\"k_extracted\",\"k_harmonised\",\"k_pooled\",\"items\"],\"status\":\"supported\",\"caveat\":\"Poolability limited by what the extracts print; S2 and S3 uncertainty exists in the full papers but is not admissible here.\"},\n {\"id\":\"C2\",\"text\":\"Harmonised estimates: S1 -0.240, S2 +0.174, S3 -0.354, S4 -0.118 (log time ratio).\",\"results_keys\":[\"items\"],\"status\":\"supported\",\"caveat\":\"S3 and S4 use the printed percentages, which differ slightly from ratios of displayed means.\"},\n {\"id\":\"C3\",\"text\":\"The pooled random-effects estimate over S1 and S4 is theta = -0.188 (about 17% shorter completion time), 95% CI [-0.396, 0.020], equal to the fixed-effect estimate.\",\"results_keys\":[\"re_estimate\",\"re_se\",\"re_ci_low\",\"re_ci_high\",\"fe_estimate\",\"fe_ci_low\",\"fe_ci_high\",\"pooled_pct_change_re\"],\"status\":\"supported\",\"caveat\":\"k = 2; S4 SE approximated from a p-value.\"},\n {\"id\":\"C4\",\"text\":\"The pooled effect is not statistically significant at the 5% level; the evidence does not establish that AI assistance shortens task time.\",\"results_keys\":[\"pooled_significant_5pct\",\"re_ci_low\",\"re_ci_high\"],\"status\":\"supported\",\"caveat\":\"Absence of significance with k=2 is not evidence of no effect.\"},\n {\"id\":\"C5\",\"text\":\"Measured heterogeneity among the pooled studies is low (Q = 0.324, I2 = 0%, tau2 = 0), but this reflects k = 2 and the excluded studies' estimates (+0.174, -0.354) suggest substantive heterogeneity not captured by the pooled analysis.\",\"results_keys\":[\"q_stat\",\"i2\",\"tau2\",\"heterogeneity_interpretation\",\"items\"],\"status\":\"supported\",\"caveat\":\"Heterogeneity of excluded studies is qualitative only; cannot be quantified without SEs.\"},\n {\"id\":\"C6\",\"text\":\"The pooled result is robust to using the CI-derived SE for S1 and the displayed-means ratio for S4.\",\"results_keys\":[\"sensitivity_ci_se_s1_re_estimate\",\"sensitivity_ci_se_s1_re_se\",\"sensitivity_ratio_s4_re_estimate\",\"sensitivity_ratio_s4_re_se\",\"sensitivity_ratio_s4_theta\"],\"status\":\"supported\",\"caveat\":\"Only two small perturbations examined.\"},\n {\"id\":\"C7\",\"text\":\"Baseline unweighted means of theta are -0.179 (pooled studies) and -0.134 (all harmonised studies).\",\"results_keys\":[\"baseline_unweighted_mean_theta_pooled\",\"baseline_unweighted_mean_theta_harmonised\"],\"status\":\"supported\",\"caveat\":\"Unweighted means ignore precision; descriptive only.\"},\n {\"id\":\"C8\",\"text\":\"The project is complete in the TASK sense: every item has harmonised values or a justified statement of what cannot be obtained.\",\"results_keys\":[\"feasibility\",\"feasibility_reason\",\"data_issues\"],\"status\":\"supported\",\"caveat\":\"Completeness of the project does not imply strength of evidence.\"}\n]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"04ac6761-5752-436c-a3a3-eac0ab01d647","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}14{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"97234788196cfc40b4f0fe3237661314dfff3ec1bc59233b807af536ea0a5ffe","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Kaz3JgTyaV3eZFRrn857kB","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json"}}]}}15{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"86c44e83-536b-4847-b1be-9cd4e2a824b7","timestamp":"2026-10-30T05:33:27.823Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"59df9926-f723-4bc4-b915-67981543a076","keep":2,"tail":["97234788196cfc40b4f0fe3237661314dfff3ec1bc59233b807af536ea0a5ffe","ee96a1d0af04d7bca847bbe5439c056cce1d4c1c2cce3257cd88c991bd007bcd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"682c141a80e77131872f7a14512023898c8ba04d4851e428011133609e0d9b9c"}16{"type":"last-prompt","lastPrompt":"Review","leafUuid":"3328b947-c9d1-4333-8843-9776df9b770d","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}17{"type":"atis-latch","atis":"","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}18{"parentUuid":"3328b947-c9d1-4333-8843-9776df9b770d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmYnD58H86YjGb6Nf5","type":"message","role":"assistant","content":[{"type":"text","text":"Now check the sources and code."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":10080,"cache_read_input_tokens":2220,"output_tokens":197,"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":10080},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsmYcYC31vUFPM5NJsJ","requestRef":"86c44e83-536b-4847-b1be-9cd4e2a824b7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9bdfef95-8d2f-496d-805c-6d84658846d8","timestamp":"2026-10-30T05:33:32.332Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}19{"parentUuid":"9bdfef95-8d2f-496d-805c-6d84658846d8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmYnD58H86YjGb6Nf5","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NW3KwhUb57V9oYKUPqfEYG","name":"Bash","input":{"command":"cat data/studies.json; cat out/report.md; cat out/exclusions.csv; ls out/state"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":10080,"cache_read_input_tokens":2220,"output_tokens":197,"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":10080},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsmYcYC31vUFPM5NJsJ","requestRef":"86c44e83-536b-4847-b1be-9cd4e2a824b7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a7c79a46-d6d6-4a49-9be4-7a04bf17a5a4","timestamp":"2026-10-30T05:33:32.881Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"a7c79a46-d6d6-4a49-9be4-7a04bf17a5a4","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01NW3KwhUb57V9oYKUPqfEYG","type":"tool_result","content":"[\n {\"id\": \"S1\", \"source\": \"arxiv-2410.12944v3\", \"short\": \"Paradis et al. (2024), Google enterprise RCT, 96 developers, one complex coding task\",\n \"extract\": \"the coefficient on the experimental condition (ExpCon) in Model 2 of Table III (logged time on task, developer-level covariates), its standard error, and the 95% confidence interval and p-value quoted for it in Section VI-C\"},\n {\"id\": \"S2\", \"source\": \"arxiv-2507.09089v2\", \"short\": \"Becker et al. (2025), METR field RCT, experienced open-source developers, real issues\",\n \"extract\": \"the headline regression-based estimate of the percentage change in issue completion time when AI is allowed, as stated in Section 3 (with the estimator defined in Sections 2.3 and D.1-D.3), together with whatever uncertainty is printed for it in the extract\"},\n {\"id\": \"S3\", \"source\": \"arxiv-2411.01067v2\", \"short\": \"Bono and Xu (2024), Microsoft Security Copilot RCT, IT administrators\",\n \"extract\": \"the aggregate 'All Content' row of Table 3 (task duration in minutes, holding accuracy constant): the treatment and control durations and the printed improvement, together with whatever uncertainty is printed for it\"},\n {\"id\": \"S4\", \"source\": \"arxiv-2511.13860v1\", \"short\": \"Bono (2025), Microsoft phishing-triage agent RCT, security analysts\",\n \"extract\": \"the 'Full Corpus' column of Table 3 (time per email): the Aware and Control times, the printed % time savings and its p-value\"},\n {\"id\": \"S5\", \"source\": \"arxiv-2304.09339v1\", \"short\": \"Kreitmeir and Raschky (2023), difference-in-differences around Italy's ChatGPT ban, GitHub users\",\n \"extract\": \"the Treat x Post coefficient and standard error for the Output measure (column 3) in panel A of Table 1 (users with affiliation), and its sample size\"}\n]\n# T3-synthesis — Does generative-AI assistance shorten task-completion time?\n\n## Question\nDoes access to a generative-AI assistant change the time workers need to finish their tasks? Target quantity (`target_definition`): θ = ln(T_AI / T_noAI), the log ratio of mean completion time with vs without AI, same tasks, randomised comparison (negative = faster with AI). Five primary studies were assessed (`n_analysed` = 5); only the provided extracts were used as evidence.\n\n## Data and exclusions\nInputs: `data/studies.json` (5 items) and five arXiv text extracts (line counts in `n_input_rows`); all SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Table 1 (`out/table1.csv`, mirrored in `items`) gives the printed values verbatim with locators:\n\n| study | printed estimate | printed uncertainty | θ | SE(θ) | poolable |\n|---|---|---|---|---|---|\n| S1 Paradis et al. 2024 (Google RCT) | ExpCon Model 2 = −0.24 (log time) | SE (0.14); 95% CI [−0.51, 0.03]; p=0.086 | −0.240 | 0.140 | yes |\n| S2 Becker et al. 2025 (METR RCT) | 19% more time | none printed (CI only in a figure) | 0.174 | — | no |\n| S3 Bono & Xu 2024 (Copilot RCT) | 44.29 vs 63.10 min, −29.79%*** | stars only | −0.354 | — | no |\n| S4 Bono 2025 (phishing agent RCT) | 50.5 vs 56.9, 11.1% time savings | p = 0.471 | −0.118 | 0.163 (approx.) | yes |\n| S5 Kreitmeir & Raschky 2023 (DiD) | −0.278 on Output | SE (0.295), N=18332 | — | — | not harmonisable |\n\n(Values from `items.S1`…`items.S5`.) Exclusion ledger (`out/exclusions.csv`): 5 extracted (`k_extracted` = 5) → 4 harmonisable (`k_harmonised` = 4; S5 removed: its outcome is GitHub output counts around the ChatGPT ban in a non-randomised DiD, not completion time) → 2 poolable (`k_pooled` = 2; S2 removed because its uncertainty appears only in a figure that is not reproduced; S3 removed because only significance stars are printed).\n\nData issues detected in the sources (`data_issues`) include: S1 sample stated as n = 96 in Table III but 47 + 46 = 93 in the text, and log-time means that look swapped relative to the raw means; S3's displayed minutes give −29.81% vs the printed −29.79%; S4's printed 11.1% saving does not equal 1 − 50.5/56.9 = 11.25%, and the \"(s) per email\" units of its Full Corpus column cannot be reconciled with the other columns; S5's table note prints \"** p<0.5\". None of these changes the printed headline quantities used.\n\n## Method\nHarmonisation followed the TASK conventions (formula and inputs in each `items.*.transformation`):\n- S1: coefficient on log time → θ = b = −0.24, SE = printed 0.14.\n- S2: +19% → θ = ln(1.19). This equals the regression β, because the paper defines S = exp(β) − 1.\n- S3: −29.79% → θ = ln(1 − 0.2979).\n- S4: 11.1% time saving → c = −0.111, θ = ln(0.889). The SE is **approximate**, recovered from the two-sided p = 0.471 as |θ|/z₀.₇₆₄₅.\n- S5: not harmonisable.\n\nPooling over S1 and S4 used inverse-variance fixed effect and DerSimonian–Laird random effects on the θ scale, with 1.96-based 95% intervals, Q on k−1 = 1 df, and I² and τ² as defined in TASK.md. As a baseline (P2), I computed unweighted means of θ. `out/analysis.py` regenerates everything deterministically (`random_seed` = null) and prints the source lines it parses.\n\n## Results\n- Harmonised θ per study: S1 −0.240, S2 +0.174, S3 −0.354, S4 −0.118 (`items.*.harmonised_estimate`). Three point estimates indicate less time with AI, and the METR study indicates more (+19%).\n- Fixed effect (k = 2): θ = −0.188, SE 0.106, 95% CI [−0.396, 0.020] (`fe_estimate`, `fe_se`, `fe_ci_low`, `fe_ci_high`).\n- Random effects (DL): θ = −0.188, SE 0.106, 95% CI [−0.396, 0.020] (`re_estimate`, `re_se`, `re_ci_low`, `re_ci_high`). This corresponds to a 17.2% shorter completion time (`pooled_pct_change_re` = −17.15), with an interval from −32.7% to +2.0% (`pooled_pct_change_re_ci_low`, `pooled_pct_change_re_ci_high`).\n- Heterogeneity: Q = 0.324 (`q_stat`), I² = 0% (`i2`), τ² = 0 (`tau2`), labelled \"low\" (`heterogeneity_interpretation`).\n- The pooled estimate is **not** significant at 5%: the RE interval includes 0 (`pooled_significant_5pct` = false).\n- Baselines: the unweighted mean of the two pooled θ is −0.179 (`baseline_unweighted_mean_theta_pooled`), and the unweighted mean of all four harmonised θ is −0.134 (`baseline_unweighted_mean_theta_harmonised`).\n- Forest plot: `out/figure1.png`.\n\n**Synthesis.** The two poolable RCTs point toward shorter completion times with AI (about −17%), but the pooled interval includes no effect. The evidence therefore does not establish that AI assistance shortens task time. The data are also compatible with no change, or with a small slowdown.\n\n## Uncertainty\n- The pooled interval rests on only two studies. One of them (S4) has an SE back-calculated from a p-value, which assumes normality on the θ scale even though the paper's test was on its own scale.\n- With k = 2, Q has 1 df. The finding τ² = 0 / I² = 0 reflects very low power to detect heterogeneity, not evidence of homogeneity.\n- RE = FE here only because τ² was truncated at 0.\n- Sensitivity checks:\n - Using S1's CI-derived SE (0.1378) instead of the printed 0.14 gives RE −0.189 (SE 0.105) (`sensitivity_ci_se_s1_re_estimate`, `sensitivity_ci_se_s1_re_se`).\n - Using S4's ratio of displayed means (θ = −0.119, `sensitivity_ratio_s4_theta`) gives RE −0.190 (SE 0.107) (`sensitivity_ratio_s4_re_estimate`, `sensitivity_ratio_s4_re_se`).\n - Neither change alters the conclusion.\n\n## Limitations and open issues\n- **The pooled estimate is not a summary of the evidence base.** It leaves out S2 (+19%, the only study of experienced developers on their own real issues) and S3 (−35%), solely because their uncertainty is not printed in the extracts. Adding S2 would pull the pooled estimate toward zero, and adding S3 would pull it away from zero; neither direction can be quantified legitimately. The four harmonised point estimates range from −0.354 to +0.174, which points to real heterogeneity that k = 2 cannot detect.\n- **The studies are not comparable.** They differ in population (Google engineers; open-source maintainers; Upwork IT administrators; security analysts), task (one lab coding task; real issues; admin scenarios; email triage), and the AI arm itself:\n - S4's Aware arm also has an agent-prioritised queue.\n - S3's control group partly used other AI tools.\n - S3 holds accuracy constant via a model-based adjustment.\n - S1 and S2 condition on covariates.\n- **The SEs are uncertain.** The S4 SE is approximate. For S1, the reported sample size is internally inconsistent (93 vs 96).\n- **S5 is excluded by design.** It measures output counts after AI withdrawal, a different construct. Its estimate (−0.278, SE 0.295) is reported but not harmonised.\n- **Feasibility.** I set `feasibility` to \"complete\" (`feasibility_reason` = null): every item has harmonised values or a justified statement of what cannot be obtained, and the pooled estimates were computed over the poolable items, as TASK.md defines it. \"Complete\" refers to the project, not to the strength of the evidence, which is weak.\nstep,rule,n_before,n_after,n_removed,rationale\n1,extracted printed value available,5,5,0,All five extracts print the designated quantity\n2,harmonisable onto theta=ln(T_AI/T_noAI),5,4,1,S5 is a DiD effect on GitHub output counts around a ban - not task completion time AI vs no-AI\n3,poolable (SE obtainable from printed quantities),4,2,2,S2 uncertainty only in a non-reproduced figure; S3 significance stars only\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","is_error":false}]},"uuid":"9f848149-8cca-4d0b-bfb0-ee8e386356e5","timestamp":"2026-10-30T05:33:32.909Z","toolUseResult":{"stdout":"[\n {\"id\": \"S1\", \"source\": \"arxiv-2410.12944v3\", \"short\": \"Paradis et al. (2024), Google enterprise RCT, 96 developers, one complex coding task\",\n \"extract\": \"the coefficient on the experimental condition (ExpCon) in Model 2 of Table III (logged time on task, developer-level covariates), its standard error, and the 95% confidence interval and p-value quoted for it in Section VI-C\"},\n {\"id\": \"S2\", \"source\": \"arxiv-2507.09089v2\", \"short\": \"Becker et al. (2025), METR field RCT, experienced open-source developers, real issues\",\n \"extract\": \"the headline regression-based estimate of the percentage change in issue completion time when AI is allowed, as stated in Section 3 (with the estimator defined in Sections 2.3 and D.1-D.3), together with whatever uncertainty is printed for it in the extract\"},\n {\"id\": \"S3\", \"source\": \"arxiv-2411.01067v2\", \"short\": \"Bono and Xu (2024), Microsoft Security Copilot RCT, IT administrators\",\n \"extract\": \"the aggregate 'All Content' row of Table 3 (task duration in minutes, holding accuracy constant): the treatment and control durations and the printed improvement, together with whatever uncertainty is printed for it\"},\n {\"id\": \"S4\", \"source\": \"arxiv-2511.13860v1\", \"short\": \"Bono (2025), Microsoft phishing-triage agent RCT, security analysts\",\n \"extract\": \"the 'Full Corpus' column of Table 3 (time per email): the Aware and Control times, the printed % time savings and its p-value\"},\n {\"id\": \"S5\", \"source\": \"arxiv-2304.09339v1\", \"short\": \"Kreitmeir and Raschky (2023), difference-in-differences around Italy's ChatGPT ban, GitHub users\",\n \"extract\": \"the Treat x Post coefficient and standard error for the Output measure (column 3) in panel A of Table 1 (users with affiliation), and its sample size\"}\n]\n# T3-synthesis — Does generative-AI assistance shorten task-completion time?\n\n## Question\nDoes access to a generative-AI assistant change the time workers need to finish their tasks? Target quantity (`target_definition`): θ = ln(T_AI / T_noAI), the log ratio of mean completion time with vs without AI, same tasks, randomised comparison (negative = faster with AI). Five primary studies were assessed (`n_analysed` = 5); only the provided extracts were used as evidence.\n\n## Data and exclusions\nInputs: `data/studies.json` (5 items) and five arXiv text extracts (line counts in `n_input_rows`); all SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Table 1 (`out/table1.csv`, mirrored in `items`) gives the printed values verbatim with locators:\n\n| study | printed estimate | printed uncertainty | θ | SE(θ) | poolable |\n|---|---|---|---|---|---|\n| S1 Paradis et al. 2024 (Google RCT) | ExpCon Model 2 = −0.24 (log time) | SE (0.14); 95% CI [−0.51, 0.03]; p=0.086 | −0.240 | 0.140 | yes |\n| S2 Becker et al. 2025 (METR RCT) | 19% more time | none printed (CI only in a figure) | 0.174 | — | no |\n| S3 Bono & Xu 2024 (Copilot RCT) | 44.29 vs 63.10 min, −29.79%*** | stars only | −0.354 | — | no |\n| S4 Bono 2025 (phishing agent RCT) | 50.5 vs 56.9, 11.1% time savings | p = 0.471 | −0.118 | 0.163 (approx.) | yes |\n| S5 Kreitmeir & Raschky 2023 (DiD) | −0.278 on Output | SE (0.295), N=18332 | — | — | not harmonisable |\n\n(Values from `items.S1`…`items.S5`.) Exclusion ledger (`out/exclusions.csv`): 5 extracted (`k_extracted` = 5) → 4 harmonisable (`k_harmonised` = 4; S5 removed: its outcome is GitHub output counts around the ChatGPT ban in a non-randomised DiD, not completion time) → 2 poolable (`k_pooled` = 2; S2 removed because its uncertainty appears only in a figure that is not reproduced; S3 removed because only significance stars are printed).\n\nData issues detected in the sources (`data_issues`) include: S1 sample stated as n = 96 in Table III but 47 + 46 = 93 in the text, and log-time means that look swapped relative to the raw means; S3's displayed minutes give −29.81% vs the printed −29.79%; S4's printed 11.1% saving does not equal 1 − 50.5/56.9 = 11.25%, and the \"(s) per email\" units of its Full Corpus column cannot be reconciled with the other columns; S5's table note prints \"** p<0.5\". None of these changes the printed headline quantities used.\n\n## Method\nHarmonisation followed the TASK conventions (formula and inputs in each `items.*.transformation`):\n- S1: coefficient on log time → θ = b = −0.24, SE = printed 0.14.\n- S2: +19% → θ = ln(1.19). This equals the regression β, because the paper defines S = exp(β) − 1.\n- S3: −29.79% → θ = ln(1 − 0.2979).\n- S4: 11.1% time saving → c = −0.111, θ = ln(0.889). The SE is **approximate**, recovered from the two-sided p = 0.471 as |θ|/z₀.₇₆₄₅.\n- S5: not harmonisable.\n\nPooling over S1 and S4 used inverse-variance fixed effect and DerSimonian–Laird random effects on the θ scale, with 1.96-based 95% intervals, Q on k−1 = 1 df, and I² and τ² as defined in TASK.md. As a baseline (P2), I computed unweighted means of θ. `out/analysis.py` regenerates everything deterministically (`random_seed` = null) and prints the source lines it parses.\n\n## Results\n- Harmonised θ per study: S1 −0.240, S2 +0.174, S3 −0.354, S4 −0.118 (`items.*.harmonised_estimate`). Three point estimates indicate less time with AI, and the METR study indicates more (+19%).\n- Fixed effect (k = 2): θ = −0.188, SE 0.106, 95% CI [−0.396, 0.020] (`fe_estimate`, `fe_se`, `fe_ci_low`, `fe_ci_high`).\n- Random effects (DL): θ = −0.188, SE 0.106, 95% CI [−0.396, 0.020] (`re_estimate`, `re_se`, `re_ci_low`, `re_ci_high`). This corresponds to a 17.2% shorter completion time (`pooled_pct_change_re` = −17.15), with an interval from −32.7% to +2.0% (`pooled_pct_change_re_ci_low`, `pooled_pct_change_re_ci_high`).\n- Heterogeneity: Q = 0.324 (`q_stat`), I² = 0% (`i2`), τ² = 0 (`tau2`), labelled \"low\" (`heterogeneity_interpretation`).\n- The pooled estimate is **not** significant at 5%: the RE interval includes 0 (`pooled_significant_5pct` = false).\n- Baselines: the unweighted mean of the two pooled θ is −0.179 (`baseline_unweighted_mean_theta_pooled`), and the unweighted mean of all four harmonised θ is −0.134 (`baseline_unweighted_mean_theta_harmonised`).\n- Forest plot: `out/figure1.png`.\n\n**Synthesis.** The two poolable RCTs point toward shorter completion times with AI (about −17%), but the pooled interval includes no effect. The evidence therefore does not establish that AI assistance shortens task time. The data are also compatible with no change, or with a small slowdown.\n\n## Uncertainty\n- The pooled interval rests on only two studies. One of them (S4) has an SE back-calculated from a p-value, which assumes normality on the θ scale even though the paper's test was on its own scale.\n- With k = 2, Q has 1 df. The finding τ² = 0 / I² = 0 reflects very low power to detect heterogeneity, not evidence of homogeneity.\n- RE = FE here only because τ² was truncated at 0.\n- Sensitivity checks:\n - Using S1's CI-derived SE (0.1378) instead of the printed 0.14 gives RE −0.189 (SE 0.105) (`sensitivity_ci_se_s1_re_estimate`, `sensitivity_ci_se_s1_re_se`).\n - Using S4's ratio of displayed means (θ = −0.119, `sensitivity_ratio_s4_theta`) gives RE −0.190 (SE 0.107) (`sensitivity_ratio_s4_re_estimate`, `sensitivity_ratio_s4_re_se`).\n - Neither change alters the conclusion.\n\n## Limitations and open issues\n- **The pooled estimate is not a summary of the evidence base.** It leaves out S2 (+19%, the only study of experienced developers on their own real issues) and S3 (−35%), solely because their uncertainty is not printed in the extracts. Adding S2 would pull the pooled estimate toward zero, and adding S3 would pull it away from zero; neither direction can be quantified legitimately. The four harmonised point estimates range from −0.354 to +0.174, which points to real heterogeneity that k = 2 cannot detect.\n- **The studies are not comparable.** They differ in population (Google engineers; open-source maintainers; Upwork IT administrators; security analysts), task (one lab coding task; real issues; admin scenarios; email triage), and the AI arm itself:\n - S4's Aware arm also has an agent-prioritised queue.\n - S3's control group partly used other AI tools.\n - S3 holds accuracy constant via a model-based adjustment.\n - S1 and S2 condition on covariates.\n- **The SEs are uncertain.** The S4 SE is approximate. For S1, the reported sample size is internally inconsistent (93 vs 96).\n- **S5 is excluded by design.** It measures output counts after AI withdrawal, a different construct. Its estimate (−0.278, SE 0.295) is reported but not harmonised.\n- **Feasibility.** I set `feasibility` to \"complete\" (`feasibility_reason` = null): every item has harmonised values or a justified statement of what cannot be obtained, and the pooled estimates were computed over the poolable items, as TASK.md defines it. \"Complete\" refers to the project, not to the strength of the evidence, which is weak.\nstep,rule,n_before,n_after,n_removed,rationale\n1,extracted printed value available,5,5,0,All five extracts print the designated quantity\n2,harmonisable onto theta=ln(T_AI/T_noAI),5,4,1,S5 is a DiD effect on GitHub output counts around a ban - not task completion time AI vs no-AI\n3,poolable (SE obtainable from printed quantities),4,2,2,S2 uncertainty only in a non-reproduced figure; S3 significance stars only\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a7c79a46-d6d6-4a49-9be4-7a04bf17a5a4","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}21{"parentUuid":"9f848149-8cca-4d0b-bfb0-ee8e386356e5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmYnD58H86YjGb6Nf5","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_017uD1visC1WeR1xRQ2UPFdf","name":"Bash","input":{"command":"sed -n 40,100p data/sources/arxiv-2410.12944v3.txt; echo ----; sed -n 40,110p data/sources/arxiv-2511.13860v1.txt"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":10080,"cache_read_input_tokens":2220,"output_tokens":197,"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":10080},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsmYcYC31vUFPM5NJsJ","requestRef":"86c44e83-536b-4847-b1be-9cd4e2a824b7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ab5fed8d-a825-40a9-8543-c72e23e7149c","timestamp":"2026-10-30T05:33:33.472Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}22{"parentUuid":"ab5fed8d-a825-40a9-8543-c72e23e7149c","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_017uD1visC1WeR1xRQ2UPFdf","type":"tool_result","content":"Finally, to explore interaction effects between experimental condition and developer-level factors, we ran three separate linear regressions with interaction effects, one for each covariate: average hours coded daily, level (seniority), and frequency of use of AI tooling.\n\nTo identify the best model, we used adjusted R^{2} values and model-level p values.\n\n### VI-B RQ1: Impact of AI tools on developer task speed\n\nFigure 7 shows the time distribution by experimental condition in a box and whisker plot.\nOn average, developers who were exposed to AI features completed the task in 96 min ( N=47,SE=9.3 ), compared to 114 min ( N=46,SE=8.1 ) for developers in the no-AI condition. We conducted a Student’s t-test on log time on task to assess the main effect impact of the experimental condition assignment (AI vs no-AI exposure). Results of this analysis indicated that developers who were in the AI exposure condition (Mean LogToT=4.6 ) were significantly faster at completing the task ( t(83.6)=2.11,p=.038 ), compared to those who were in the no-AI exposure condition (Mean LogToT=4.3 ).\n\np<\n\n### VI-C RQ2: Impact of covariates on main effect\n\nTable III summarizes the regression findings. When controlling for other factors in our theoretical framework, we find that estimates for the impact of the experimental condition on logged time on task range between -0.30 to -0.24 ( \\beta_{1} for ExpCon for Models 1-3 in Table III), suggesting a relatively consistent and negative downward pressure on time on task. Controlling for the developer- and task-level factors described in our theoretical framework (see Section IV-B), we found that this main effect was robust to covariates, making developers between 21% and 26% faster.^2^2\n2\n\nFrom Model 2, where \\beta_{1}=-0.24 , and therefore the effect of AI =(1-exp(\\beta_{1}))*100=21\\% (with 95% CI = [-0.51, 0.03]). Similarly, 26% from Model 3, where \\beta_{1}=-0.30 .\nHowever, our confidence intervals are large, and as a result the estimate is not statistically significant at the p<0.05 level (estimate of experimental condition on best-fit Model 2, \\beta_{1}=-0.24; 95\\%CI = [-0.51,0.03] , p=0.086 , NS). Our second hypothesis is therefore only partially supported.\n\nControlling for experimental condition and other model covariates, average programming hours per day was significantly associated with time spent on task, with participants reporting five or more hours of development work per day being 32% ( \\beta=-0.38 ) faster than participants reporting zero to four hours of development work per day. Similarly, higher levels of seniority were also associated with a decrease in time on task, with one increased level (from 4 to 5, or 5 to 6, for example) being associated with a 15% ( \\beta=-0.16 ) decrease in time spent on task.\n\nOther covariates were not significantly associated with time spent on task. As seen in Table III, the best fit model was Model 2 with developer-level factors only, as evidenced by higher adjusted R^{2} and lower p -value. While the total variance accounted for by Model 2 was low, the model was statistically significant ( p=0.011 ), suggesting an adequate fit to our data.\n\np=\n\nTABLE III: Summaries of regressions using LogToT as the dependent variable, n = 96. Unstandardized estimates provided, along with standard error of the mean (in parentheses).\n\nComplete Dev Task Interaction | | | |\n\n(1) (2) (3) (4) | | | |\n\n5.36*** 5.41*** 4.55*** 4.66*** Constant | | | |\n\n(0.42) (0.37) (0.19) (0.11) | | | |\n\n-0.25. -0.24. -0.30* -0.14 ExpCon | | | |\n\n(0.14) (0.14) (0.14) (0.17) | | | |\n\n-0.38* -0.38* -0.16 AvgProgHrsDay | | | |\n\n(0.15) (0.15) (0.22) | | | |\n\n-0.16. -0.16* Level | | | |\n\n(0.08) (0.08) | | | |\n\n-0.01 0.00 NbrHighFreqAreas | | | |\n\n(0.03) (0.03) | | | |\n\n0.02 0.06 TopLangCpp | | | |\n\n(0.15) (0.15) | | | |\n\n0.05 0.02 DataLogExp | | | |\n\n(0.09) (0.09) | | | |\n\n-0.29 EC:APHD | | | |\n----\n\nOur subjects are 167 external security analysts.^1^1\n1\n\nWe filter out 13 subject responses that scored less than 40% – significantly below guessing percentage. These included three in the Aware group, six in the Blind group, and four in the Control group. This step does not affect our qualitative results. Their task is to triage a 25-email queue. The queue comes from an original corpus of 93 randomly selected emails reported by Microsoft employees. Through an in-depth analysis by expert graders and security researchers, we arrived at our ground truth of 82 non-malicious and 11 malicious emails.\n\nOn this corpus, the agent’s precision and recall were both 100%. The agent’s accuracy is very good, but it is not always perfect. It will occasionally have false negative (FN) and false positive (FP) verdicts. However, without FNs and FPs in our corpus, we cannot measure the effect of the agent on analyst trust and diligence. Hence, we create synthetic false positives (SFPs) and synthetic false negatives (SFNs). We create SFNs from each of the malicious emails by changing the agent verdict and swapping the justification for a generic justification of a non-malicious verdict that fits the content of the malicious email. For example, for a malicious email impersonating Microsoft 365, we used the justification from a non-malicious email from Microsoft 365. We create fake false negatives (SFNs) with a similar technique, e.g., by using the justification from a non-malicious email from Microsoft 365 for a malicious email impersonating Microsoft 365. In both cases, we ensure no details in the fake justification are in obvious conflict with the SFN and SFP emails. Using this method, we ended up with five SFPs and 10 SFNs.\n\nTo construct each subject’s 25 email queue, we randomly select four malicious emails, 19 non-malicious emails, one SFN, and one SFP. This sampling scheme mimics agent precision and recall of 80%, which aligns closely to Microsoft’s internal measurements on large random samples. It also includes 20% malicious samples.^2^2\n2\n\nOur results are not sensitive to this malicious percentage, since we calculate the time to triage for TP, TN, SFP, and SFN for all groups separately. We need only that the malicious percentage does not dramatically affect the expectations of the Control group, which 20% should not do. For the Aware and Blind groups, we randomly order the four malicious and one SFP at the front of the queue, i.e., in positions one through five. We then randomly order the 19 non-malicious and one SFN in queue positions six through 25. This implies agent accuracy with precision=recall=0.8. Each email is presented as a timed, forced-choice classification: Malicious vs. Non-Malicious. Responses are final (no backtracking).\n\nTo reduce the importance of learning effects and to control for the heterogeneous beliefs of subjects using the agent for the first time, we calibrate our Aware group’s beliefs about the agent’s accuracy with the following information: “On a very large sample, the agent’s accuracy is approximately as follows: Malicious verdicts are 80% correct; Not Malicious verdicts are 95% correct.”\n\nFor each email in the queue, subjects have a link to a read-only OneDrive folder with the email’s artifacts, including a screenshot (annotated with primary URL), EML and HTML text, URL list, URL detonation screenshots, and sanitized attachments.^3^3\n\n## 3 Results\n\nThe results show that the agent offers dramatic improvements in both productivity and protection. These improvements are driven by both the agent’s ability to prioritize the queue as well as its verdicts and explanations. In addition, the agent’s accuracy and its effect on analyst accuracy both strongly support implementing the resolve-benign protocol.\n\n### 3.1 Productivity Gains: True Positives per Analyst Minute\n\nThe Aware group identifies 6.5 times as many TPs per analyst minute (550% productivity gain) on the corpus ground truth. This number reflects the resolve-benign protocol.\nUnder the pessimistic counterfactual, analysts identify 3.1 times as many TPs per minute. At a high malicious rate of 30%, we still find an effect of 2.0-2.6 times. These measurements are all statistically significant above the 99% level. Figure 1 illustrates the relationship between the malicious rate and the agent’s productivity gain (as a factor improvement) for both the case where agent precision = 1.0 and the case where agent precision = 0.8. The shaded region is the 99% confidence interval for the case where agent precision = 0.8.\n\nFigure 1: Factor Increase in TPs per unit of Analyst Time\n\nNext, by applying the resolve-benign protocol to the Blind group’s responses, we measure how much of this gain is due to the resolve-benign protocol versus the subject being aware of the agent, including its verdicts and explanations. We find that the resolve-benign protocol, which dramatically reduces the number of non-malicious emails for review, is the biggest factor driving the productivity gain, accounting for between 79-84% of the total agent-driven productivity gain. As precision decreases, the information conveyed in the agent’s verdicts and explanations becomes relatively more important. However, even when the agent’s precision is maximized, the information conveyed in the agent’s verdicts and explanations remains relatively important, about 13-17% of the total improvement.\n\nTable 1: Productivity Improvements by Agent Feature\n\nScenario | Factor Increase | Resolve-Benign (%) | Agent Awareness (%)\n\nCorpus ground truth | 6.53 | 83 | 17\n\nAccuracy counterfactual | 5.04 | 78 | 22\n\nMalicious rate counterfactual | 3.97 | 87 | 13\n\nPessimistic counterfactual | 3.07 | 83 | 17\n\n### 3.3 Behavior: Effect of Agent on Analyst Behavior\n\nNext, we look at subject behavior across the entire queue, not just the agent-prioritized portion, i.e., this is how analysts would perform if we removed the resolve-benign protocol. First, we find that the Aware group spends 53% more time per malicious email. They spend marginally less on non-malicious email, and the overall time is roughly the same. This indicates they are utilizing the agent to help optimize their time and attention.\n\nTable 3: Comparison of Email Processing Times\n\nMetric | Malicious | Non-Malicious | Full Corpus\n\nAware Time per Email (s) | 2.8 | 1.8 | 50.5\n\nControl Time per Email (s) | 1.9 | 2.4 | 56.9\n\n% Time Savings | -52.9 | 23.6 | 11.1\n\np-value | 0.006 | 0.126 | 0.471\n\nWe also find that the Aware group is no more likely to confirm the agent’s TPs or miss the agent’s SFPs, which are precisely the samples the Aware group would see under the resolve-benign protocol. Taken together with the evidence that Aware subjects spend more time on malicious emails, this means they are not rubber-stamping the agent’s malicious verdicts. Rather, they use the agent’s insights to guide their own investigation.\n\nHowever, we do find they are more likely to confirm agent TNs by 21 percentage points and more likely to miss agent SFNs by 29 percentage points. This lends further support to the use of the resolve-benign protocol. In addition to the productivity gains documented above, the protection benefit of having analysts spend time on emails the agent has already classified as non-malicious is minimal because analysts are likely to agree with the agent anyway.\n\n## Appendix B TP per Analyst Minute\n\nLet p denote the malicious email rate in the corpus. We define the following parameters and variables:\n\n### B.1 Control Group Performance\n\nFor the control group, the expected time to process an email is:\n\n\\mathbb{E}[T_{c}]=p\\cdot\\bar{T}_{c,m}+(1-p)\\cdot\\bar{T}_{c,b} | |","is_error":false}]},"uuid":"8c501f0b-fc98-4158-be34-d0e970edf595","timestamp":"2026-10-30T05:33:33.497Z","toolUseResult":{"stdout":"Finally, to explore interaction effects between experimental condition and developer-level factors, we ran three separate linear regressions with interaction effects, one for each covariate: average hours coded daily, level (seniority), and frequency of use of AI tooling.\n\nTo identify the best model, we used adjusted R^{2} values and model-level p values.\n\n### VI-B RQ1: Impact of AI tools on developer task speed\n\nFigure 7 shows the time distribution by experimental condition in a box and whisker plot.\nOn average, developers who were exposed to AI features completed the task in 96 min ( N=47,SE=9.3 ), compared to 114 min ( N=46,SE=8.1 ) for developers in the no-AI condition. We conducted a Student’s t-test on log time on task to assess the main effect impact of the experimental condition assignment (AI vs no-AI exposure). Results of this analysis indicated that developers who were in the AI exposure condition (Mean LogToT=4.6 ) were significantly faster at completing the task ( t(83.6)=2.11,p=.038 ), compared to those who were in the no-AI exposure condition (Mean LogToT=4.3 ).\n\np<\n\n### VI-C RQ2: Impact of covariates on main effect\n\nTable III summarizes the regression findings. When controlling for other factors in our theoretical framework, we find that estimates for the impact of the experimental condition on logged time on task range between -0.30 to -0.24 ( \\beta_{1} for ExpCon for Models 1-3 in Table III), suggesting a relatively consistent and negative downward pressure on time on task. Controlling for the developer- and task-level factors described in our theoretical framework (see Section IV-B), we found that this main effect was robust to covariates, making developers between 21% and 26% faster.^2^2\n2\n\nFrom Model 2, where \\beta_{1}=-0.24 , and therefore the effect of AI =(1-exp(\\beta_{1}))*100=21\\% (with 95% CI = [-0.51, 0.03]). Similarly, 26% from Model 3, where \\beta_{1}=-0.30 .\nHowever, our confidence intervals are large, and as a result the estimate is not statistically significant at the p<0.05 level (estimate of experimental condition on best-fit Model 2, \\beta_{1}=-0.24; 95\\%CI = [-0.51,0.03] , p=0.086 , NS). Our second hypothesis is therefore only partially supported.\n\nControlling for experimental condition and other model covariates, average programming hours per day was significantly associated with time spent on task, with participants reporting five or more hours of development work per day being 32% ( \\beta=-0.38 ) faster than participants reporting zero to four hours of development work per day. Similarly, higher levels of seniority were also associated with a decrease in time on task, with one increased level (from 4 to 5, or 5 to 6, for example) being associated with a 15% ( \\beta=-0.16 ) decrease in time spent on task.\n\nOther covariates were not significantly associated with time spent on task. As seen in Table III, the best fit model was Model 2 with developer-level factors only, as evidenced by higher adjusted R^{2} and lower p -value. While the total variance accounted for by Model 2 was low, the model was statistically significant ( p=0.011 ), suggesting an adequate fit to our data.\n\np=\n\nTABLE III: Summaries of regressions using LogToT as the dependent variable, n = 96. Unstandardized estimates provided, along with standard error of the mean (in parentheses).\n\nComplete Dev Task Interaction | | | |\n\n(1) (2) (3) (4) | | | |\n\n5.36*** 5.41*** 4.55*** 4.66*** Constant | | | |\n\n(0.42) (0.37) (0.19) (0.11) | | | |\n\n-0.25. -0.24. -0.30* -0.14 ExpCon | | | |\n\n(0.14) (0.14) (0.14) (0.17) | | | |\n\n-0.38* -0.38* -0.16 AvgProgHrsDay | | | |\n\n(0.15) (0.15) (0.22) | | | |\n\n-0.16. -0.16* Level | | | |\n\n(0.08) (0.08) | | | |\n\n-0.01 0.00 NbrHighFreqAreas | | | |\n\n(0.03) (0.03) | | | |\n\n0.02 0.06 TopLangCpp | | | |\n\n(0.15) (0.15) | | | |\n\n0.05 0.02 DataLogExp | | | |\n\n(0.09) (0.09) | | | |\n\n-0.29 EC:APHD | | | |\n----\n\nOur subjects are 167 external security analysts.^1^1\n1\n\nWe filter out 13 subject responses that scored less than 40% – significantly below guessing percentage. These included three in the Aware group, six in the Blind group, and four in the Control group. This step does not affect our qualitative results. Their task is to triage a 25-email queue. The queue comes from an original corpus of 93 randomly selected emails reported by Microsoft employees. Through an in-depth analysis by expert graders and security researchers, we arrived at our ground truth of 82 non-malicious and 11 malicious emails.\n\nOn this corpus, the agent’s precision and recall were both 100%. The agent’s accuracy is very good, but it is not always perfect. It will occasionally have false negative (FN) and false positive (FP) verdicts. However, without FNs and FPs in our corpus, we cannot measure the effect of the agent on analyst trust and diligence. Hence, we create synthetic false positives (SFPs) and synthetic false negatives (SFNs). We create SFNs from each of the malicious emails by changing the agent verdict and swapping the justification for a generic justification of a non-malicious verdict that fits the content of the malicious email. For example, for a malicious email impersonating Microsoft 365, we used the justification from a non-malicious email from Microsoft 365. We create fake false negatives (SFNs) with a similar technique, e.g., by using the justification from a non-malicious email from Microsoft 365 for a malicious email impersonating Microsoft 365. In both cases, we ensure no details in the fake justification are in obvious conflict with the SFN and SFP emails. Using this method, we ended up with five SFPs and 10 SFNs.\n\nTo construct each subject’s 25 email queue, we randomly select four malicious emails, 19 non-malicious emails, one SFN, and one SFP. This sampling scheme mimics agent precision and recall of 80%, which aligns closely to Microsoft’s internal measurements on large random samples. It also includes 20% malicious samples.^2^2\n2\n\nOur results are not sensitive to this malicious percentage, since we calculate the time to triage for TP, TN, SFP, and SFN for all groups separately. We need only that the malicious percentage does not dramatically affect the expectations of the Control group, which 20% should not do. For the Aware and Blind groups, we randomly order the four malicious and one SFP at the front of the queue, i.e., in positions one through five. We then randomly order the 19 non-malicious and one SFN in queue positions six through 25. This implies agent accuracy with precision=recall=0.8. Each email is presented as a timed, forced-choice classification: Malicious vs. Non-Malicious. Responses are final (no backtracking).\n\nTo reduce the importance of learning effects and to control for the heterogeneous beliefs of subjects using the agent for the first time, we calibrate our Aware group’s beliefs about the agent’s accuracy with the following information: “On a very large sample, the agent’s accuracy is approximately as follows: Malicious verdicts are 80% correct; Not Malicious verdicts are 95% correct.”\n\nFor each email in the queue, subjects have a link to a read-only OneDrive folder with the email’s artifacts, including a screenshot (annotated with primary URL), EML and HTML text, URL list, URL detonation screenshots, and sanitized attachments.^3^3\n\n## 3 Results\n\nThe results show that the agent offers dramatic improvements in both productivity and protection. These improvements are driven by both the agent’s ability to prioritize the queue as well as its verdicts and explanations. In addition, the agent’s accuracy and its effect on analyst accuracy both strongly support implementing the resolve-benign protocol.\n\n### 3.1 Productivity Gains: True Positives per Analyst Minute\n\nThe Aware group identifies 6.5 times as many TPs per analyst minute (550% productivity gain) on the corpus ground truth. This number reflects the resolve-benign protocol.\nUnder the pessimistic counterfactual, analysts identify 3.1 times as many TPs per minute. At a high malicious rate of 30%, we still find an effect of 2.0-2.6 times. These measurements are all statistically significant above the 99% level. Figure 1 illustrates the relationship between the malicious rate and the agent’s productivity gain (as a factor improvement) for both the case where agent precision = 1.0 and the case where agent precision = 0.8. The shaded region is the 99% confidence interval for the case where agent precision = 0.8.\n\nFigure 1: Factor Increase in TPs per unit of Analyst Time\n\nNext, by applying the resolve-benign protocol to the Blind group’s responses, we measure how much of this gain is due to the resolve-benign protocol versus the subject being aware of the agent, including its verdicts and explanations. We find that the resolve-benign protocol, which dramatically reduces the number of non-malicious emails for review, is the biggest factor driving the productivity gain, accounting for between 79-84% of the total agent-driven productivity gain. As precision decreases, the information conveyed in the agent’s verdicts and explanations becomes relatively more important. However, even when the agent’s precision is maximized, the information conveyed in the agent’s verdicts and explanations remains relatively important, about 13-17% of the total improvement.\n\nTable 1: Productivity Improvements by Agent Feature\n\nScenario | Factor Increase | Resolve-Benign (%) | Agent Awareness (%)\n\nCorpus ground truth | 6.53 | 83 | 17\n\nAccuracy counterfactual | 5.04 | 78 | 22\n\nMalicious rate counterfactual | 3.97 | 87 | 13\n\nPessimistic counterfactual | 3.07 | 83 | 17\n\n### 3.3 Behavior: Effect of Agent on Analyst Behavior\n\nNext, we look at subject behavior across the entire queue, not just the agent-prioritized portion, i.e., this is how analysts would perform if we removed the resolve-benign protocol. First, we find that the Aware group spends 53% more time per malicious email. They spend marginally less on non-malicious email, and the overall time is roughly the same. This indicates they are utilizing the agent to help optimize their time and attention.\n\nTable 3: Comparison of Email Processing Times\n\nMetric | Malicious | Non-Malicious | Full Corpus\n\nAware Time per Email (s) | 2.8 | 1.8 | 50.5\n\nControl Time per Email (s) | 1.9 | 2.4 | 56.9\n\n% Time Savings | -52.9 | 23.6 | 11.1\n\np-value | 0.006 | 0.126 | 0.471\n\nWe also find that the Aware group is no more likely to confirm the agent’s TPs or miss the agent’s SFPs, which are precisely the samples the Aware group would see under the resolve-benign protocol. Taken together with the evidence that Aware subjects spend more time on malicious emails, this means they are not rubber-stamping the agent’s malicious verdicts. Rather, they use the agent’s insights to guide their own investigation.\n\nHowever, we do find they are more likely to confirm agent TNs by 21 percentage points and more likely to miss agent SFNs by 29 percentage points. This lends further support to the use of the resolve-benign protocol. In addition to the productivity gains documented above, the protection benefit of having analysts spend time on emails the agent has already classified as non-malicious is minimal because analysts are likely to agree with the agent anyway.\n\n## Appendix B TP per Analyst Minute\n\nLet p denote the malicious email rate in the corpus. We define the following parameters and variables:\n\n### B.1 Control Group Performance\n\nFor the control group, the expected time to process an email is:\n\n\\mathbb{E}[T_{c}]=p\\cdot\\bar{T}_{c,m}+(1-p)\\cdot\\bar{T}_{c,b} | |","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ab5fed8d-a825-40a9-8543-c72e23e7149c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}23{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"2d189cd8b67e023b5d3726cd200ed0b2137ea587a96b739c3c40c6ac48550110","message":{"role":"assistant","content":[{"type":"text","text":"Now check the sources and code."},{"type":"tool_use","id":"toolu_01NW3KwhUb57V9oYKUPqfEYG","name":"Bash","input":{"command":"cat data/studies.json; cat out/report.md; cat out/exclusions.csv; ls out/state"}},{"type":"tool_use","id":"toolu_017uD1visC1WeR1xRQ2UPFdf","name":"Bash","input":{"command":"sed -n 40,100p data/sources/arxiv-2410.12944v3.txt; echo ----; sed -n 40,110p data/sources/arxiv-2511.13860v1.txt"}}]}}24{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"46a0392dc48e0721bc08a8c505782a9ca0ad5498befb2ba778dc06d996ab836b","message":{"role":"user","content":[{"tool_use_id":"toolu_01NW3KwhUb57V9oYKUPqfEYG","type":"tool_result","content":"[\n {\"id\": \"S1\", \"source\": \"arxiv-2410.12944v3\", \"short\": \"Paradis et al. (2024), Google enterprise RCT, 96 developers, one complex coding task\",\n \"extract\": \"the coefficient on the experimental condition (ExpCon) in Model 2 of Table III (logged time on task, developer-level covariates), its standard error, and the 95% confidence interval and p-value quoted for it in Section VI-C\"},\n {\"id\": \"S2\", \"source\": \"arxiv-2507.09089v2\", \"short\": \"Becker et al. (2025), METR field RCT, experienced open-source developers, real issues\",\n \"extract\": \"the headline regression-based estimate of the percentage change in issue completion time when AI is allowed, as stated in Section 3 (with the estimator defined in Sections 2.3 and D.1-D.3), together with whatever uncertainty is printed for it in the extract\"},\n {\"id\": \"S3\", \"source\": \"arxiv-2411.01067v2\", \"short\": \"Bono and Xu (2024), Microsoft Security Copilot RCT, IT administrators\",\n \"extract\": \"the aggregate 'All Content' row of Table 3 (task duration in minutes, holding accuracy constant): the treatment and control durations and the printed improvement, together with whatever uncertainty is printed for it\"},\n {\"id\": \"S4\", \"source\": \"arxiv-2511.13860v1\", \"short\": \"Bono (2025), Microsoft phishing-triage agent RCT, security analysts\",\n \"extract\": \"the 'Full Corpus' column of Table 3 (time per email): the Aware and Control times, the printed % time savings and its p-value\"},\n {\"id\": \"S5\", \"source\": \"arxiv-2304.09339v1\", \"short\": \"Kreitmeir and Raschky (2023), difference-in-differences around Italy's ChatGPT ban, GitHub users\",\n \"extract\": \"the Treat x Post coefficient and standard error for the Output measure (column 3) in panel A of Table 1 (users with affiliation), and its sample size\"}\n]\n# T3-synthesis — Does generative-AI assistance shorten task-completion time?\n\n## Question\nDoes access to a generative-AI assistant change the time workers need to finish their tasks? Target quantity (`target_definition`): θ = ln(T_AI / T_noAI), the log ratio of mean completion time with vs without AI, same tasks, randomised comparison (negative = faster with AI). Five primary studies were assessed (`n_analysed` = 5); only the provided extracts were used as evidence.\n\n## Data and exclusions\nInputs: `data/studies.json` (5 items) and five arXiv text extracts (line counts in `n_input_rows`); all SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). Table 1 (`out/table1.csv`, mirrored in `items`) gives the printed values verbatim with locators:\n\n| study | printed estimate | printed uncertainty | θ | SE(θ) | poolable |\n|---|---|---|---|---|---|\n| S1 Paradis et al. 2024 (Google RCT) | ExpCon Model 2 = −0.24 (log time) | SE (0.14); 95% CI [−0.51, 0.03]; p=0.086 | −0.240 | 0.140 | yes |\n| S2 Becker et al. 2025 (METR RCT) | 19% more time | none printed (CI only in a figure) | 0.174 | — | no |\n| S3 Bono & Xu 2024 (Copilot RCT) | 44.29 vs 63.10 min, −29.79%*** | stars only | −0.354 | — | no |\n| S4 Bono 2025 (phishing agent RCT) | 50.5 vs 56.9, 11.1% time savings | p = 0.471 | −0.118 | 0.163 (approx.) | yes |\n| S5 Kreitmeir & Raschky 2023 (DiD) | −0.278 on Output | SE (0.295), N=18332 | — | — | not harmonisable |\n\n(Values from `items.S1`…`items.S5`.) Exclusion ledger (`out/exclusions.csv`): 5 extracted (`k_extracted` = 5) → 4 harmonisable (`k_harmonised` = 4; S5 removed: its outcome is GitHub output counts around the ChatGPT ban in a non-randomised DiD, not completion time) → 2 poolable (`k_pooled` = 2; S2 removed because its uncertainty appears only in a figure that is not reproduced; S3 removed because only significance stars are printed).\n\nData issues detected in the sources (`data_issues`) include: S1 sample stated as n = 96 in Table III but 47 + 46 = 93 in the text, and log-time means that look swapped relative to the raw means; S3's displayed minutes give −29.81% vs the printed −29.79%; S4's printed 11.1% saving does not equal 1 − 50.5/56.9 = 11.25%, and the \"(s) per email\" units of its Full Corpus column cannot be reconciled with the other columns; S5's table note prints \"** p<0.5\". None of these changes the printed headline quantities used.\n\n## Method\nHarmonisation followed the TASK conventions (formula and inputs in each `items.*.transformation`):\n- S1: coefficient on log time → θ = b = −0.24, SE = printed 0.14.\n- S2: +19% → θ = ln(1.19). This equals the regression β, because the paper defines S = exp(β) − 1.\n- S3: −29.79% → θ = ln(1 − 0.2979).\n- S4: 11.1% time saving → c = −0.111, θ = ln(0.889). The SE is **approximate**, recovered from the two-sided p = 0.471 as |θ|/z₀.₇₆₄₅.\n- S5: not harmonisable.\n\nPooling over S1 and S4 used inverse-variance fixed effect and DerSimonian–Laird random effects on the θ scale, with 1.96-based 95% intervals, Q on k−1 = 1 df, and I² and τ² as defined in TASK.md. As a baseline (P2), I computed unweighted means of θ. `out/analysis.py` regenerates everything deterministically (`random_seed` = null) and prints the source lines it parses.\n\n## Results\n- Harmonised θ per study: S1 −0.240, S2 +0.174, S3 −0.354, S4 −0.118 (`items.*.harmonised_estimate`). Three point estimates indicate less time with AI, and the METR study indicates more (+19%).\n- Fixed effect (k = 2): θ = −0.188, SE 0.106, 95% CI [−0.396, 0.020] (`fe_estimate`, `fe_se`, `fe_ci_low`, `fe_ci_high`).\n- Random effects (DL): θ = −0.188, SE 0.106, 95% CI [−0.396, 0.020] (`re_estimate`, `re_se`, `re_ci_low`, `re_ci_high`). This corresponds to a 17.2% shorter completion time (`pooled_pct_change_re` = −17.15), with an interval from −32.7% to +2.0% (`pooled_pct_change_re_ci_low`, `pooled_pct_change_re_ci_high`).\n- Heterogeneity: Q = 0.324 (`q_stat`), I² = 0% (`i2`), τ² = 0 (`tau2`), labelled \"low\" (`heterogeneity_interpretation`).\n- The pooled estimate is **not** significant at 5%: the RE interval includes 0 (`pooled_significant_5pct` = false).\n- Baselines: the unweighted mean of the two pooled θ is −0.179 (`baseline_unweighted_mean_theta_pooled`), and the unweighted mean of all four harmonised θ is −0.134 (`baseline_unweighted_mean_theta_harmonised`).\n- Forest plot: `out/figure1.png`.\n\n**Synthesis.** The two poolable RCTs point toward shorter completion times with AI (about −17%), but the pooled interval includes no effect. The evidence therefore does not establish that AI assistance shortens task time. The data are also compatible with no change, or with a small slowdown.\n\n## Uncertainty\n- The pooled interval rests on only two studies. One of them (S4) has an SE back-calculated from a p-value, which assumes normality on the θ scale even though the paper's test was on its own scale.\n- With k = 2, Q has 1 df. The finding τ² = 0 / I² = 0 reflects very low power to detect heterogeneity, not evidence of homogeneity.\n- RE = FE here only because τ² was truncated at 0.\n- Sensitivity checks:\n - Using S1's CI-derived SE (0.1378) instead of the printed 0.14 gives RE −0.189 (SE 0.105) (`sensitivity_ci_se_s1_re_estimate`, `sensitivity_ci_se_s1_re_se`).\n - Using S4's ratio of displayed means (θ = −0.119, `sensitivity_ratio_s4_theta`) gives RE −0.190 (SE 0.107) (`sensitivity_ratio_s4_re_estimate`, `sensitivity_ratio_s4_re_se`).\n - Neither change alters the conclusion.\n\n## Limitations and open issues\n- **The pooled estimate is not a summary of the evidence base.** It leaves out S2 (+19%, the only study of experienced developers on their own real issues) and S3 (−35%), solely because their uncertainty is not printed in the extracts. Adding S2 would pull the pooled estimate toward zero, and adding S3 would pull it away from zero; neither direction can be quantified legitimately. The four harmonised point estimates range from −0.354 to +0.174, which points to real heterogeneity that k = 2 cannot detect.\n- **The studies are not comparable.** They differ in population (Google engineers; open-source maintainers; Upwork IT administrators; security analysts), task (one lab coding task; real issues; admin scenarios; email triage), and the AI arm itself:\n - S4's Aware arm also has an agent-prioritised queue.\n - S3's control group partly used other AI tools.\n - S3 holds accuracy constant via a model-based adjustment.\n - S1 and S2 condition on covariates.\n- **The SEs are uncertain.** The S4 SE is approximate. For S1, the reported sample size is internally inconsistent (93 vs 96).\n- **S5 is excluded by design.** It measures output counts after AI withdrawal, a different construct. Its estimate (−0.278, SE 0.295) is reported but not harmonised.\n- **Feasibility.** I set `feasibility` to \"complete\" (`feasibility_reason` = null): every item has harmonised values or a justified statement of what cannot be obtained, and the pooled estimates were computed over the poolable items, as TASK.md defines it. \"Complete\" refers to the project, not to the strength of the evidence, which is weak.\nstep,rule,n_before,n_after,n_removed,rationale\n1,extracted printed value available,5,5,0,All five extracts print the designated quantity\n2,harmonisable onto theta=ln(T_AI/T_noAI),5,4,1,S5 is a DiD effect on GitHub output counts around a ban - not task completion time AI vs no-AI\n3,poolable (SE obtainable from printed quantities),4,2,2,S2 uncertainty only in a non-reproduced figure; S3 significance stars only\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","is_error":false},{"tool_use_id":"toolu_017uD1visC1WeR1xRQ2UPFdf","type":"tool_result","content":"Finally, to explore interaction effects between experimental condition and developer-level factors, we ran three separate linear regressions with interaction effects, one for each covariate: average hours coded daily, level (seniority), and frequency of use of AI tooling.\n\nTo identify the best model, we used adjusted R^{2} values and model-level p values.\n\n### VI-B RQ1: Impact of AI tools on developer task speed\n\nFigure 7 shows the time distribution by experimental condition in a box and whisker plot.\nOn average, developers who were exposed to AI features completed the task in 96 min ( N=47,SE=9.3 ), compared to 114 min ( N=46,SE=8.1 ) for developers in the no-AI condition. We conducted a Student’s t-test on log time on task to assess the main effect impact of the experimental condition assignment (AI vs no-AI exposure). Results of this analysis indicated that developers who were in the AI exposure condition (Mean LogToT=4.6 ) were significantly faster at completing the task ( t(83.6)=2.11,p=.038 ), compared to those who were in the no-AI exposure condition (Mean LogToT=4.3 ).\n\np<\n\n### VI-C RQ2: Impact of covariates on main effect\n\nTable III summarizes the regression findings. When controlling for other factors in our theoretical framework, we find that estimates for the impact of the experimental condition on logged time on task range between -0.30 to -0.24 ( \\beta_{1} for ExpCon for Models 1-3 in Table III), suggesting a relatively consistent and negative downward pressure on time on task. Controlling for the developer- and task-level factors described in our theoretical framework (see Section IV-B), we found that this main effect was robust to covariates, making developers between 21% and 26% faster.^2^2\n2\n\nFrom Model 2, where \\beta_{1}=-0.24 , and therefore the effect of AI =(1-exp(\\beta_{1}))*100=21\\% (with 95% CI = [-0.51, 0.03]). Similarly, 26% from Model 3, where \\beta_{1}=-0.30 .\nHowever, our confidence intervals are large, and as a result the estimate is not statistically significant at the p<0.05 level (estimate of experimental condition on best-fit Model 2, \\beta_{1}=-0.24; 95\\%CI = [-0.51,0.03] , p=0.086 , NS). Our second hypothesis is therefore only partially supported.\n\nControlling for experimental condition and other model covariates, average programming hours per day was significantly associated with time spent on task, with participants reporting five or more hours of development work per day being 32% ( \\beta=-0.38 ) faster than participants reporting zero to four hours of development work per day. Similarly, higher levels of seniority were also associated with a decrease in time on task, with one increased level (from 4 to 5, or 5 to 6, for example) being associated with a 15% ( \\beta=-0.16 ) decrease in time spent on task.\n\nOther covariates were not significantly associated with time spent on task. As seen in Table III, the best fit model was Model 2 with developer-level factors only, as evidenced by higher adjusted R^{2} and lower p -value. While the total variance accounted for by Model 2 was low, the model was statistically significant ( p=0.011 ), suggesting an adequate fit to our data.\n\np=\n\nTABLE III: Summaries of regressions using LogToT as the dependent variable, n = 96. Unstandardized estimates provided, along with standard error of the mean (in parentheses).\n\nComplete Dev Task Interaction | | | |\n\n(1) (2) (3) (4) | | | |\n\n5.36*** 5.41*** 4.55*** 4.66*** Constant | | | |\n\n(0.42) (0.37) (0.19) (0.11) | | | |\n\n-0.25. -0.24. -0.30* -0.14 ExpCon | | | |\n\n(0.14) (0.14) (0.14) (0.17) | | | |\n\n-0.38* -0.38* -0.16 AvgProgHrsDay | | | |\n\n(0.15) (0.15) (0.22) | | | |\n\n-0.16. -0.16* Level | | | |\n\n(0.08) (0.08) | | | |\n\n-0.01 0.00 NbrHighFreqAreas | | | |\n\n(0.03) (0.03) | | | |\n\n0.02 0.06 TopLangCpp | | | |\n\n(0.15) (0.15) | | | |\n\n0.05 0.02 DataLogExp | | | |\n\n(0.09) (0.09) | | | |\n\n-0.29 EC:APHD | | | |\n----\n\nOur subjects are 167 external security analysts.^1^1\n1\n\nWe filter out 13 subject responses that scored less than 40% – significantly below guessing percentage. These included three in the Aware group, six in the Blind group, and four in the Control group. This step does not affect our qualitative results. Their task is to triage a 25-email queue. The queue comes from an original corpus of 93 randomly selected emails reported by Microsoft employees. Through an in-depth analysis by expert graders and security researchers, we arrived at our ground truth of 82 non-malicious and 11 malicious emails.\n\nOn this corpus, the agent’s precision and recall were both 100%. The agent’s accuracy is very good, but it is not always perfect. It will occasionally have false negative (FN) and false positive (FP) verdicts. However, without FNs and FPs in our corpus, we cannot measure the effect of the agent on analyst trust and diligence. Hence, we create synthetic false positives (SFPs) and synthetic false negatives (SFNs). We create SFNs from each of the malicious emails by changing the agent verdict and swapping the justification for a generic justification of a non-malicious verdict that fits the content of the malicious email. For example, for a malicious email impersonating Microsoft 365, we used the justification from a non-malicious email from Microsoft 365. We create fake false negatives (SFNs) with a similar technique, e.g., by using the justification from a non-malicious email from Microsoft 365 for a malicious email impersonating Microsoft 365. In both cases, we ensure no details in the fake justification are in obvious conflict with the SFN and SFP emails. Using this method, we ended up with five SFPs and 10 SFNs.\n\nTo construct each subject’s 25 email queue, we randomly select four malicious emails, 19 non-malicious emails, one SFN, and one SFP. This sampling scheme mimics agent precision and recall of 80%, which aligns closely to Microsoft’s internal measurements on large random samples. It also includes 20% malicious samples.^2^2\n2\n\nOur results are not sensitive to this malicious percentage, since we calculate the time to triage for TP, TN, SFP, and SFN for all groups separately. We need only that the malicious percentage does not dramatically affect the expectations of the Control group, which 20% should not do. For the Aware and Blind groups, we randomly order the four malicious and one SFP at the front of the queue, i.e., in positions one through five. We then randomly order the 19 non-malicious and one SFN in queue positions six through 25. This implies agent accuracy with precision=recall=0.8. Each email is presented as a timed, forced-choice classification: Malicious vs. Non-Malicious. Responses are final (no backtracking).\n\nTo reduce the importance of learning effects and to control for the heterogeneous beliefs of subjects using the agent for the first time, we calibrate our Aware group’s beliefs about the agent’s accuracy with the following information: “On a very large sample, the agent’s accuracy is approximately as follows: Malicious verdicts are 80% correct; Not Malicious verdicts are 95% correct.”\n\nFor each email in the queue, subjects have a link to a read-only OneDrive folder with the email’s artifacts, including a screenshot (annotated with primary URL), EML and HTML text, URL list, URL detonation screenshots, and sanitized attachments.^3^3\n\n## 3 Results\n\nThe results show that the agent offers dramatic improvements in both productivity and protection. These improvements are driven by both the agent’s ability to prioritize the queue as well as its verdicts and explanations. In addition, the agent’s accuracy and its effect on analyst accuracy both strongly support implementing the resolve-benign protocol.\n\n### 3.1 Productivity Gains: True Positives per Analyst Minute\n\nThe Aware group identifies 6.5 times as many TPs per analyst minute (550% productivity gain) on the corpus ground truth. This number reflects the resolve-benign protocol.\nUnder the pessimistic counterfactual, analysts identify 3.1 times as many TPs per minute. At a high malicious rate of 30%, we still find an effect of 2.0-2.6 times. These measurements are all statistically significant above the 99% level. Figure 1 illustrates the relationship between the malicious rate and the agent’s productivity gain (as a factor improvement) for both the case where agent precision = 1.0 and the case where agent precision = 0.8. The shaded region is the 99% confidence interval for the case where agent precision = 0.8.\n\nFigure 1: Factor Increase in TPs per unit of Analyst Time\n\nNext, by applying the resolve-benign protocol to the Blind group’s responses, we measure how much of this gain is due to the resolve-benign protocol versus the subject being aware of the agent, including its verdicts and explanations. We find that the resolve-benign protocol, which dramatically reduces the number of non-malicious emails for review, is the biggest factor driving the productivity gain, accounting for between 79-84% of the total agent-driven productivity gain. As precision decreases, the information conveyed in the agent’s verdicts and explanations becomes relatively more important. However, even when the agent’s precision is maximized, the information conveyed in the agent’s verdicts and explanations remains relatively important, about 13-17% of the total improvement.\n\nTable 1: Productivity Improvements by Agent Feature\n\nScenario | Factor Increase | Resolve-Benign (%) | Agent Awareness (%)\n\nCorpus ground truth | 6.53 | 83 | 17\n\nAccuracy counterfactual | 5.04 | 78 | 22\n\nMalicious rate counterfactual | 3.97 | 87 | 13\n\nPessimistic counterfactual | 3.07 | 83 | 17\n\n### 3.3 Behavior: Effect of Agent on Analyst Behavior\n\nNext, we look at subject behavior across the entire queue, not just the agent-prioritized portion, i.e., this is how analysts would perform if we removed the resolve-benign protocol. First, we find that the Aware group spends 53% more time per malicious email. They spend marginally less on non-malicious email, and the overall time is roughly the same. This indicates they are utilizing the agent to help optimize their time and attention.\n\nTable 3: Comparison of Email Processing Times\n\nMetric | Malicious | Non-Malicious | Full Corpus\n\nAware Time per Email (s) | 2.8 | 1.8 | 50.5\n\nControl Time per Email (s) | 1.9 | 2.4 | 56.9\n\n% Time Savings | -52.9 | 23.6 | 11.1\n\np-value | 0.006 | 0.126 | 0.471\n\nWe also find that the Aware group is no more likely to confirm the agent’s TPs or miss the agent’s SFPs, which are precisely the samples the Aware group would see under the resolve-benign protocol. Taken together with the evidence that Aware subjects spend more time on malicious emails, this means they are not rubber-stamping the agent’s malicious verdicts. Rather, they use the agent’s insights to guide their own investigation.\n\nHowever, we do find they are more likely to confirm agent TNs by 21 percentage points and more likely to miss agent SFNs by 29 percentage points. This lends further support to the use of the resolve-benign protocol. In addition to the productivity gains documented above, the protection benefit of having analysts spend time on emails the agent has already classified as non-malicious is minimal because analysts are likely to agree with the agent anyway.\n\n## Appendix B TP per Analyst Minute\n\nLet p denote the malicious email rate in the corpus. We define the following parameters and variables:\n\n### B.1 Control Group Performance\n\nFor the control group, the expected time to process an email is:\n\n\\mathbb{E}[T_{c}]=p\\cdot\\bar{T}_{c,m}+(1-p)\\cdot\\bar{T}_{c,b} | |","is_error":false}]}}25{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"345117ec-9bfb-4d68-b902-092040d7d3bc","timestamp":"2026-10-30T05:33:33.500Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"86c44e83-536b-4847-b1be-9cd4e2a824b7","keep":4,"tail":["2d189cd8b67e023b5d3726cd200ed0b2137ea587a96b739c3c40c6ac48550110","46a0392dc48e0721bc08a8c505782a9ca0ad5498befb2ba778dc06d996ab836b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"bdc84c03fbcc07ccc5b8c381dd8eb667e3a553d2478f595fb52d4bf48a8097c6"}26{"type":"last-prompt","lastPrompt":"Review","leafUuid":"8c501f0b-fc98-4158-be34-d0e970edf595","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}27{"type":"atis-latch","atis":"","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}28{"parentUuid":"8c501f0b-fc98-4158-be34-d0e970edf595","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmyBeMEruYHiW6Vhcg","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":8378,"cache_read_input_tokens":12300,"output_tokens":237,"output_tokens_details":{"thinking_tokens":38},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":8378},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":147,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsmxtnjVk1inEmbXQNK","requestRef":"345117ec-9bfb-4d68-b902-092040d7d3bc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4dabb7d9-13d1-426a-a187-859e2af707d5","timestamp":"2026-10-30T05:33:36.397Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"4dabb7d9-13d1-426a-a187-859e2af707d5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmyBeMEruYHiW6Vhcg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01VNXm4S94wkHfiRhkG167Ai","name":"Bash","input":{"command":"grep -n \"N=\\|N =\\|56\\|52\" data/sources/arxiv-2511.13860v1.txt | head -20; grep -n \"19%\\|246\\|136\\|110\" data/sources/arxiv-2507.09089v2.txt | head; grep -n -i \"confidence\\|CI\" data/sources/arxiv-2507.09089v2.txt | head -20; sed -n 45,60p data/sources/arxiv-2411.01067v2.txt"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":8378,"cache_read_input_tokens":12300,"output_tokens":237,"output_tokens_details":{"thinking_tokens":38},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":8378},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsmxtnjVk1inEmbXQNK","requestRef":"345117ec-9bfb-4d68-b902-092040d7d3bc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"30232d00-55aa-4409-a043-b857de4eb6f6","timestamp":"2026-10-30T05:33:37.699Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"30232d00-55aa-4409-a043-b857de4eb6f6","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01VNXm4S94wkHfiRhkG167Ai","type":"tool_result","content":"5:Retrieved: https://arxiv.org/html/2511.13860 on 2026-10-30T04:20:39Z (SHA-256 of the retrieved HTML: 9a25378878d5735130154b510c032744445d4089e70415e3f1c3b2ca066b984a)\n31:Control ( N{=}52 ): Random queue order, no references to AI.\n35:Aware ( N{=}56 ): Queue ordered by the agent’s verdicts; participants see the agent’s decision, a brief rationale, and an accuracy calibration.\n92:Control Time per Email (s) | 1.9 | 2.4 | 56.9\n94:% Time Savings | -52.9 | 23.6 | 11.1\n30:16 developers with moderate AI experience complete 246 tasks in mature projects on which they have an average of 5 years of prior experience.\n34:Surprisingly, we find that allowing AI actually increases completion time by 19%—AI tooling slowed developers down.\n62:Developers complete 136 issues with AI-allowed and 110 issues with AI-disallowed. Section G.7 shows the number of issues completed across repositories and developers, respectively. We find that when developers use AI tools, they implement issues in 19% more time on average (Figure 1), and nearly all quantiles of observed implementation time see AI-allowed issues taking longer (Figure 5). That is, developers are slower when using AI is allowed. Colloquially, we refer to this result that issues with AI-allowed take longer than issues with AI-disallowed as slowdown.\n68:Before developers complete each issue, they forecast how long they expect them to take with and without AI assistance. On average, they forecast speedup of 24%. Interestingly, after the experiment they post-hoc estimate that they were sped-up by 20% when using AI is allowed—after they used AI assistance, they estimate similar speedup as before, despite the fact that they are in fact slowed down by 19% (Figure 1).\n72:The raw percentage difference in implementation times between AI-allowed and AI-disallowed issues is 34%, which is larger in absolute value than the 19% slowdown estimated using the regression specified in Section D.1. This is true because AI-allowed issues ended up being slightly more difficult than AI-disallowed issues after randomization, as measured by the forecasted AI-disallowed times (not statistically significant; see Table 4). Our regression accounts for this, while this simple ratio estimator does not. See Figure 13 for results implied by alternative estimators..\n7:Extract contents: title, authors and abstract; Section 2.3 'Effect Estimation'; the opening of Section 3 'Results' and Section 3.1 'Forecasts' (figure captions included as text); Appendix D.1 'Regression', D.2 'Confidence intervals' and D.3 'Converting to speedup'.\n8:Omitted: Sections 1, 2.1-2.2, 2.4, 3.2-3.3, 4-5, Appendices A-C, D.4-D.5, E-G, Tables 1-8, all figures (including Figure 1, which displays the confidence interval of the main estimate graphically), the references.\n9:Rendering note: converted from the HTML rendering to plain text. Tables are rendered one row per line with \" | \" separating cells; in regression tables the line following a coefficient row holds the standard errors in parentheses, exactly as printed. Mathematical expressions appear as LaTeX source; non-breaking spaces were replaced by ordinary spaces. Figures are not reproduced: a value that appears only in a figure is not in this extract. No numbers were altered.\n52:We use the total implementation time (including both pre- and post-pull request review time) developers self-report spending on each issue to estimate the percentage change in issue completion time due to AI. A small number of issues do not end up getting reviewed/merged for various reasons—we impute the post-review implementation time of these issues with the mean post-review time per treatment condition. Section C.3.4 shows that our results are robust to the specific imputation method used.\n54:We estimate S via a log-linear regression for total implementation time, incorporating estimates of issue difficulty to reduce noise in our estimate. We also use adapted versions of this regression when examining how performance varies in different subsets of the data (to efficiently account for any post-randomization issue difficulty imbalances that may be more pronounced within subsets). See Appendix D for details of the regression approach used.\n58:Figure 4: Left: Raw average forecasted implementation times. Right: Raw average observed implementation times. The ratio of observed implementation times gives a more extreme slowdown estimate than regression-based estimates (Section D.1) because AI-allowed issues are forecasted (importantly, before treatment assignment) by developers to take slightly longer, which the regression corrects for. Both: Section D.5 describes confidence intervals around ratios of average times.\n72:The raw percentage difference in implementation times between AI-allowed and AI-disallowed issues is 34%, which is larger in absolute value than the 19% slowdown estimated using the regression specified in Section D.1. This is true because AI-allowed issues ended up being slightly more difficult than AI-disallowed issues after randomization, as measured by the forecasted AI-disallowed times (not statistically significant; see Table 4). Our regression accounts for this, while this simple ratio estimator does not. See Figure 13 for results implied by alternative estimators..\n86:We include forecasts as a control variable because they serve as a proxy for issue difficulty and are highly predictive of completion times. This substantially increases our statistical power without introducing bias, as forecasts were elicited prior to treatment assignment and thus cannot be affected by treatment status.^18^18\n89:We do not generally include developer fixed effects because they explain minimal variation in the outcome conditional on forecasts. Section C.3.5 displays estimates from a regression specification including developer fixed effects.\n91:Figure 14: Regression diagnostics associated with the regression specification in equation (1).\n93:Figure 14displays regression diagnostics associated with this specification.\n95:#### D.2 Confidence intervals\n97:By default, we report 95% confidence intervals using HC3 standard errors.^19^19\n100:Given that our sampling of developers is non-random and treatment is assigned at the issue level, Abadie et al. [2022] do not necessarily recommend developer-level clustering even if residuals are correlated within-developer. If we are willing to treat developer sampling as random then clustering is appropriate. Figure 15 displays 95% confidence intervals from alternative uncertainty estimation procedures. Standard errors clustered at the developer level and bias-corrected cluster-robust standard errors give similar results; a hierarchical bootstrap resampling developers and then issues within developers yields somewhat wider confidence intervals.\n102:Figure 15: Speedup calculated using the regression specification in equation (1) and alternative uncertainty estimation procedures. CR2 and CR3 standard errors are bias-corrected cluster-robust standard errors Colin Cameron and Miller [2015], Bell and Mccaffrey [2002]. Two-stage bootstrap resamples developers, then issues within developers.\n126:Then under standard regularity assumptions (which our diagnostics suggest hold) our OLS estimator \\hat{\\beta} is normally distributed \\mathcal{N}(\\beta,\\sigma^{2}) for some \\sigma which we can estimate using it’s standard error \\text{SE}[\\hat{\\beta}] . This lets us construct a 95% confidence interval for \\beta in the usual way:\n128:\\text{CI}_{95\\%}=\\left[\\hat{\\beta}-1.96\\cdot\\text{SE}[\\hat{\\beta}],\\hat{\\beta}+1.96\\cdot\\text{SE}[\\hat{\\beta}]\\right] | | | (6)\n130:As \\text{S}=\\exp(\\beta)-1 is a monotonic function of \\beta we can construct a confidence interval for S by simply applying the function to the endpoints of \\beta ’s confidence interval:\n132:\\text{CI}_{95\\%}=\\left[e^{\\hat{\\beta}-1.96\\cdot\\text{SE}[\\hat{\\beta}]}-1,e^{\\hat{\\beta}+1.96\\cdot\\text{SE}[\\hat{\\beta}]}-1\\right] | | | (7)\nThe results answer RQ1 in the affirmative: Copilot does offer speed and accuracy improvements in common IT scenarios. Across all tasks, we measure a 34.53%*** increase in accuracy and a 29.79%*** reduction in task completion time. In the subsections on accuracy and speed below, we present detailed results answering RQ1-RQ4.\n\n### 4.2 Speed\n\nWe measure statistically significant time savings in all scenarios. Table 3 summarizes these results by task type and scenario. The “Aggregate Results, All Content (Holding accuracy constant)” numbers represent our headline speed improvements, a 29.79%*** time savings for Copilot users. We also note that Copilot generally involves greater latency than typical page-loading in the admin centers, which is common among GAI tools. This necessarily slowed the Copilot users. Product improvements should reduce this latency and further increase the time savings for users with Copilot.\n\n| Overall | Treatment | Control | Improvement\n\nAggregate Results | | | |\n\nAll Content | 53.84 | 44.29 | 63.10 | -29.79%***\n\nSATA | 17.81 | 15.25 | 20.14 | -24.28%***\n\nMC | 10.91 | 12.02 | 9.60 | 25.13%***","is_error":false}]},"uuid":"1ddb9db0-cc30-4b26-aa0d-e7144bbdff86","timestamp":"2026-10-30T05:33:37.734Z","toolUseResult":{"stdout":"5:Retrieved: https://arxiv.org/html/2511.13860 on 2026-10-30T04:20:39Z (SHA-256 of the retrieved HTML: 9a25378878d5735130154b510c032744445d4089e70415e3f1c3b2ca066b984a)\n31:Control ( N{=}52 ): Random queue order, no references to AI.\n35:Aware ( N{=}56 ): Queue ordered by the agent’s verdicts; participants see the agent’s decision, a brief rationale, and an accuracy calibration.\n92:Control Time per Email (s) | 1.9 | 2.4 | 56.9\n94:% Time Savings | -52.9 | 23.6 | 11.1\n30:16 developers with moderate AI experience complete 246 tasks in mature projects on which they have an average of 5 years of prior experience.\n34:Surprisingly, we find that allowing AI actually increases completion time by 19%—AI tooling slowed developers down.\n62:Developers complete 136 issues with AI-allowed and 110 issues with AI-disallowed. Section G.7 shows the number of issues completed across repositories and developers, respectively. We find that when developers use AI tools, they implement issues in 19% more time on average (Figure 1), and nearly all quantiles of observed implementation time see AI-allowed issues taking longer (Figure 5). That is, developers are slower when using AI is allowed. Colloquially, we refer to this result that issues with AI-allowed take longer than issues with AI-disallowed as slowdown.\n68:Before developers complete each issue, they forecast how long they expect them to take with and without AI assistance. On average, they forecast speedup of 24%. Interestingly, after the experiment they post-hoc estimate that they were sped-up by 20% when using AI is allowed—after they used AI assistance, they estimate similar speedup as before, despite the fact that they are in fact slowed down by 19% (Figure 1).\n72:The raw percentage difference in implementation times between AI-allowed and AI-disallowed issues is 34%, which is larger in absolute value than the 19% slowdown estimated using the regression specified in Section D.1. This is true because AI-allowed issues ended up being slightly more difficult than AI-disallowed issues after randomization, as measured by the forecasted AI-disallowed times (not statistically significant; see Table 4). Our regression accounts for this, while this simple ratio estimator does not. See Figure 13 for results implied by alternative estimators..\n7:Extract contents: title, authors and abstract; Section 2.3 'Effect Estimation'; the opening of Section 3 'Results' and Section 3.1 'Forecasts' (figure captions included as text); Appendix D.1 'Regression', D.2 'Confidence intervals' and D.3 'Converting to speedup'.\n8:Omitted: Sections 1, 2.1-2.2, 2.4, 3.2-3.3, 4-5, Appendices A-C, D.4-D.5, E-G, Tables 1-8, all figures (including Figure 1, which displays the confidence interval of the main estimate graphically), the references.\n9:Rendering note: converted from the HTML rendering to plain text. Tables are rendered one row per line with \" | \" separating cells; in regression tables the line following a coefficient row holds the standard errors in parentheses, exactly as printed. Mathematical expressions appear as LaTeX source; non-breaking spaces were replaced by ordinary spaces. Figures are not reproduced: a value that appears only in a figure is not in this extract. No numbers were altered.\n52:We use the total implementation time (including both pre- and post-pull request review time) developers self-report spending on each issue to estimate the percentage change in issue completion time due to AI. A small number of issues do not end up getting reviewed/merged for various reasons—we impute the post-review implementation time of these issues with the mean post-review time per treatment condition. Section C.3.4 shows that our results are robust to the specific imputation method used.\n54:We estimate S via a log-linear regression for total implementation time, incorporating estimates of issue difficulty to reduce noise in our estimate. We also use adapted versions of this regression when examining how performance varies in different subsets of the data (to efficiently account for any post-randomization issue difficulty imbalances that may be more pronounced within subsets). See Appendix D for details of the regression approach used.\n58:Figure 4: Left: Raw average forecasted implementation times. Right: Raw average observed implementation times. The ratio of observed implementation times gives a more extreme slowdown estimate than regression-based estimates (Section D.1) because AI-allowed issues are forecasted (importantly, before treatment assignment) by developers to take slightly longer, which the regression corrects for. Both: Section D.5 describes confidence intervals around ratios of average times.\n72:The raw percentage difference in implementation times between AI-allowed and AI-disallowed issues is 34%, which is larger in absolute value than the 19% slowdown estimated using the regression specified in Section D.1. This is true because AI-allowed issues ended up being slightly more difficult than AI-disallowed issues after randomization, as measured by the forecasted AI-disallowed times (not statistically significant; see Table 4). Our regression accounts for this, while this simple ratio estimator does not. See Figure 13 for results implied by alternative estimators..\n86:We include forecasts as a control variable because they serve as a proxy for issue difficulty and are highly predictive of completion times. This substantially increases our statistical power without introducing bias, as forecasts were elicited prior to treatment assignment and thus cannot be affected by treatment status.^18^18\n89:We do not generally include developer fixed effects because they explain minimal variation in the outcome conditional on forecasts. Section C.3.5 displays estimates from a regression specification including developer fixed effects.\n91:Figure 14: Regression diagnostics associated with the regression specification in equation (1).\n93:Figure 14displays regression diagnostics associated with this specification.\n95:#### D.2 Confidence intervals\n97:By default, we report 95% confidence intervals using HC3 standard errors.^19^19\n100:Given that our sampling of developers is non-random and treatment is assigned at the issue level, Abadie et al. [2022] do not necessarily recommend developer-level clustering even if residuals are correlated within-developer. If we are willing to treat developer sampling as random then clustering is appropriate. Figure 15 displays 95% confidence intervals from alternative uncertainty estimation procedures. Standard errors clustered at the developer level and bias-corrected cluster-robust standard errors give similar results; a hierarchical bootstrap resampling developers and then issues within developers yields somewhat wider confidence intervals.\n102:Figure 15: Speedup calculated using the regression specification in equation (1) and alternative uncertainty estimation procedures. CR2 and CR3 standard errors are bias-corrected cluster-robust standard errors Colin Cameron and Miller [2015], Bell and Mccaffrey [2002]. Two-stage bootstrap resamples developers, then issues within developers.\n126:Then under standard regularity assumptions (which our diagnostics suggest hold) our OLS estimator \\hat{\\beta} is normally distributed \\mathcal{N}(\\beta,\\sigma^{2}) for some \\sigma which we can estimate using it’s standard error \\text{SE}[\\hat{\\beta}] . This lets us construct a 95% confidence interval for \\beta in the usual way:\n128:\\text{CI}_{95\\%}=\\left[\\hat{\\beta}-1.96\\cdot\\text{SE}[\\hat{\\beta}],\\hat{\\beta}+1.96\\cdot\\text{SE}[\\hat{\\beta}]\\right] | | | (6)\n130:As \\text{S}=\\exp(\\beta)-1 is a monotonic function of \\beta we can construct a confidence interval for S by simply applying the function to the endpoints of \\beta ’s confidence interval:\n132:\\text{CI}_{95\\%}=\\left[e^{\\hat{\\beta}-1.96\\cdot\\text{SE}[\\hat{\\beta}]}-1,e^{\\hat{\\beta}+1.96\\cdot\\text{SE}[\\hat{\\beta}]}-1\\right] | | | (7)\nThe results answer RQ1 in the affirmative: Copilot does offer speed and accuracy improvements in common IT scenarios. Across all tasks, we measure a 34.53%*** increase in accuracy and a 29.79%*** reduction in task completion time. In the subsections on accuracy and speed below, we present detailed results answering RQ1-RQ4.\n\n### 4.2 Speed\n\nWe measure statistically significant time savings in all scenarios. Table 3 summarizes these results by task type and scenario. The “Aggregate Results, All Content (Holding accuracy constant)” numbers represent our headline speed improvements, a 29.79%*** time savings for Copilot users. We also note that Copilot generally involves greater latency than typical page-loading in the admin centers, which is common among GAI tools. This necessarily slowed the Copilot users. Product improvements should reduce this latency and further increase the time savings for users with Copilot.\n\n| Overall | Treatment | Control | Improvement\n\nAggregate Results | | | |\n\nAll Content | 53.84 | 44.29 | 63.10 | -29.79%***\n\nSATA | 17.81 | 15.25 | 20.14 | -24.28%***\n\nMC | 10.91 | 12.02 | 9.60 | 25.13%***","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"30232d00-55aa-4409-a043-b857de4eb6f6","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"8c80cb46d852963e530083531b0e7e6b1b22ccae51419a154d537fb881e50056","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS1AUKEAgTGAI4AUIIdGhpbmtpbmcSDKN6oQHNT0MmlEDnpRoMa6YZ1zFagQqtm66jIjA6UTs+a5L6RFv53Dj70MhJk0Vkd+kVWPhlkajhcFGhMBfDEv8Kjm2we1Igx/jUw9Iq8QQntIq8dMpo8rhz+i2VPM9/z7qQgQu+M2myq/gHWEarg3INlyyqGnscCDovtW3aHm5/toKlFTesDXG39VQfZtXV+gP5l23GCQafL3pNv1PL+0dPJ+hI3NHO21LXpDV3iHTYacBv6TkiRqZVCPHvuv5trTRIiahrYnd7R/8sQr0zwXxCySezZ2twk/ynQAWiBjF3USutPbfRfuwAgcjYSiBtB/cakJG0kHoULyJ3SeSqqizXTBKaxfksn90HXvBHq5bIoTnn+EF2szwmKx7dcg7WyIOQJJOLjU0B3ePL0IV6ZIeZuf/71OIApQ7hVMI9li/Q6MeIeM8uBIFp9ecn1OO7cl2dUcWLzbW//ZCCabhFOhpexzffKpnrTZXDRDMMejf5YBal0ff0GD+n+XHqWuLtyeIDkdaxO535Hj9zrdJIL2wgtduI3+Rh9KrMO/IOQStixpxMawxB1N6QDJTaHzZukKukerbYA/nTJXHUQ1gD6nLrDxtxhoUL5kTunTPI8/KSx+Y625HaVmmJXfTdXNQgJT9kn2jWyCjQVl+zwz5VKd9PpIGsIzRyYk7bybVZ9WnyI1Fz2a/LroocV4V/irsY5bdmCxDLv74Y3K6r/JGR6TfVo0u6cztqTmBx80L7puhwaa77FNsAbPGCkMo5p7yODBqCQsXmUAkoHttKMxBSwERYQeHvYIL0Yha/mmvf/jEiUkOQyY8yo0LgfYdtKM7mtsFRjb5mgWKBULbjKq/zy1rsXK8Dj5I3Z7CuUJ3t9Uvgvh5txVaXQLOvS77G7DVDGW9QcbBz0ojEz6wsA+Ru3jTHDe676MY58wnS/gbEFJ8OGAE="},{"type":"tool_use","id":"toolu_01VNXm4S94wkHfiRhkG167Ai","name":"Bash","input":{"command":"grep -n \"N=\\|N =\\|56\\|52\" data/sources/arxiv-2511.13860v1.txt | head -20; grep -n \"19%\\|246\\|136\\|110\" data/sources/arxiv-2507.09089v2.txt | head; grep -n -i \"confidence\\|CI\" data/sources/arxiv-2507.09089v2.txt | head -20; sed -n 45,60p data/sources/arxiv-2411.01067v2.txt"}}]}}32{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"b8a5740c-8f84-4835-9af1-0f3b23a56b0d","timestamp":"2026-10-30T05:33:37.738Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"345117ec-9bfb-4d68-b902-092040d7d3bc","keep":6,"tail":["8c80cb46d852963e530083531b0e7e6b1b22ccae51419a154d537fb881e50056","0c70f02bc7eef361a25321a8e25c67401778214190bdc07342352a90775fccbd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9d0c362348a4a72e389458ae5729c1e5f4ff07dcfc19b2d871f2e57d209c4cf0"}33{"parentUuid":"1ddb9db0-cc30-4b26-aa0d-e7144bbdff86","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnHFqcUCcCemyh4bkE","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":3467,"cache_read_input_tokens":20678,"output_tokens":487,"output_tokens_details":{"thinking_tokens":177},"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":3467},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1213,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsnGzD1Znt5L28L725L","requestRef":"b8a5740c-8f84-4835-9af1-0f3b23a56b0d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f38addd7-617f-4271-8611-f4b67d9e1bdc","timestamp":"2026-10-30T05:33:40.362Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}34{"parentUuid":"f38addd7-617f-4271-8611-f4b67d9e1bdc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnHFqcUCcCemyh4bkE","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019VgPgW8sKpyhCwWe5XnQ7J","name":"Bash","input":{"command":"rm -rf /tmp/rt7 && mkdir /tmp/rt7 && cp -r data out /tmp/rt7/ && cd /tmp/rt7 && ~/wp29/venv/bin/python out/analysis.py > run.log 2>&1; echo $?; tail -5 run.log; ~/wp29/venv/bin/python -c \"\nimport json\na=json.load(open('/tmp/rt7/out/results.json'));b=json.load(open('/Users/simon-pierreboucher/wp29/runs/RT0007/out/results.json'))\nprint(a==b)\n\"; diff out/table1.csv ~/wp29/runs/RT0007/out/table1.csv && echo same; grep -n \"open(\\|read\\|http\\|import\" out/analysis.py | head -30"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3467,"cache_read_input_tokens":20678,"output_tokens":487,"output_tokens_details":{"thinking_tokens":177},"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":3467},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsnGzD1Znt5L28L725L","requestRef":"b8a5740c-8f84-4835-9af1-0f3b23a56b0d","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c0f59299-e521-4b80-9f1a-3c5ecb561cbc","timestamp":"2026-10-30T05:33:42.503Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}35{"parentUuid":"c0f59299-e521-4b80-9f1a-3c5ecb561cbc","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019VgPgW8sKpyhCwWe5XnQ7J","type":"tool_result","content":"0\nS2 theta = 0.17395330712343798 SE = None poolable = False\nS3 theta = -0.353679434958934 SE = None poolable = False\nS4 theta = -0.11765804346823246 SE = 0.1632205919720678 poolable = True\nS5 theta = None SE = None poolable = False\nFE -0.1881 (SE 0.1063); RE -0.1881 (SE 0.1063) [-0.3964, 0.0201]; Q=0.3237, I2=0.00%, tau2=0.0000; pct change RE -17.15%\nTrue\nsame\n4:import json, math, os, re, csv\n5:import numpy as np\n6:from scipy.stats import norm\n7:import matplotlib\n9:import matplotlib.pyplot as plt\n16: with open(os.path.join(D, \"sources\", src + \".txt\"), encoding=\"utf-8\") as fh:\n17: return fh.read().split(\"\\n\")\n28:studies = json.load(open(os.path.join(D, \"studies.json\"), encoding=\"utf-8\"))\n35: with open(os.path.join(D, fn), \"rb\") as fh:\n36: n_input_rows[fn] = fh.read().count(b\"\\n\")\n214:with open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n219:with open(os.path.join(OUT, \"table1.csv\"), \"w\", newline=\"\") as fh:\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0007","is_error":false}]},"uuid":"07bcf6be-bba3-4b38-ad23-e6acffe35e3c","timestamp":"2026-10-30T05:33:43.374Z","toolUseResult":{"stdout":"0\nS2 theta = 0.17395330712343798 SE = None poolable = False\nS3 theta = -0.353679434958934 SE = None poolable = False\nS4 theta = -0.11765804346823246 SE = 0.1632205919720678 poolable = True\nS5 theta = None SE = None poolable = False\nFE -0.1881 (SE 0.1063); RE -0.1881 (SE 0.1063) [-0.3964, 0.0201]; Q=0.3237, I2=0.00%, tau2=0.0000; pct change RE -17.15%\nTrue\nsame\n4:import json, math, os, re, csv\n5:import numpy as np\n6:from scipy.stats import norm\n7:import matplotlib\n9:import matplotlib.pyplot as plt\n16: with open(os.path.join(D, \"sources\", src + \".txt\"), encoding=\"utf-8\") as fh:\n17: return fh.read().split(\"\\n\")\n28:studies = json.load(open(os.path.join(D, \"studies.json\"), encoding=\"utf-8\"))\n35: with open(os.path.join(D, fn), \"rb\") as fh:\n36: n_input_rows[fn] = fh.read().count(b\"\\n\")\n214:with open(os.path.join(OUT, \"results.json\"), \"w\") as fh:\n219:with open(os.path.join(OUT, \"table1.csv\"), \"w\", newline=\"\") as fh:","stderr":"\nShell cwd was reset to /Users/simon-pierreboucher/wp29/runs/RT0007","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c0f59299-e521-4b80-9f1a-3c5ecb561cbc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}36{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"2aa943bbe06bcb5dbc895a00ba12d6db56c6c904b315a7c6b3742514c0a34e19","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_019VgPgW8sKpyhCwWe5XnQ7J","name":"Bash","input":{"command":"rm -rf /tmp/rt7 && mkdir /tmp/rt7 && cp -r data out /tmp/rt7/ && cd /tmp/rt7 && ~/wp29/venv/bin/python out/analysis.py > run.log 2>&1; echo $?; tail -5 run.log; ~/wp29/venv/bin/python -c \"\nimport json\na=json.load(open('/tmp/rt7/out/results.json'));b=json.load(open('/Users/simon-pierreboucher/wp29/runs/RT0007/out/results.json'))\nprint(a==b)\n\"; diff out/table1.csv ~/wp29/runs/RT0007/out/table1.csv && echo same; grep -n \"open(\\|read\\|http\\|import\" out/analysis.py | head -30"}}]}}37{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"051b46b6-8e7c-423e-bef1-cdfc13992d65","timestamp":"2026-10-30T05:33:43.378Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"b8a5740c-8f84-4835-9af1-0f3b23a56b0d","keep":8,"tail":["2aa943bbe06bcb5dbc895a00ba12d6db56c6c904b315a7c6b3742514c0a34e19","a38533c8b489b1181be02574e564e822643e3b75ed1d6ce1cfb02e44aa117685"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b0b9c3ca8c1a08a21d0bde7647dc254745fa4e95b4b5ab110c4b22c8798e55d3"}38{"type":"last-prompt","lastPrompt":"Review","leafUuid":"07bcf6be-bba3-4b38-ad23-e6acffe35e3c","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}39{"type":"atis-latch","atis":"","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}40{"parentUuid":"07bcf6be-bba3-4b38-ad23-e6acffe35e3c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnhPADqxnkTPA5kqPi","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":991,"cache_read_input_tokens":24145,"output_tokens":301,"output_tokens_details":{"thinking_tokens":59},"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":991},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":405,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsnh7nahMC9Ho1BP5H3","requestRef":"051b46b6-8e7c-423e-bef1-cdfc13992d65","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c65f048e-face-4e58-abad-50d02c700166","timestamp":"2026-10-30T05:33:47.569Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"c65f048e-face-4e58-abad-50d02c700166","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnhPADqxnkTPA5kqPi","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01AhFQpWktsW2fsJ2TvYSLHe","name":"Bash","input":{"command":"sed -n 40,140p out/analysis.py; cd data && wc -l README.md sources/*; cd ..; ~/wp29/venv/bin/python -c \"\nimport numpy as np\nfrom scipy.stats import norm\nt=np.array([-0.24,np.log(1-0.111)]);z=norm.ppf(1-0.471/2);s=np.array([0.14,abs(t[1])/z]);w=1/s**2\nfe=(w*t).sum()/w.sum();print(fe,1/np.sqrt(w.sum()),((t-fe)**2*w).sum())\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":991,"cache_read_input_tokens":24145,"output_tokens":301,"output_tokens_details":{"thinking_tokens":59},"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":991},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsnh7nahMC9Ho1BP5H3","requestRef":"051b46b6-8e7c-423e-bef1-cdfc13992d65","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3a511544-8135-4eda-9287-9d651b0adff7","timestamp":"2026-10-30T05:33:49.291Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"3a511544-8135-4eda-9287-9d651b0adff7","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01AhFQpWktsW2fsJ2TvYSLHe","type":"tool_result","content":"# ---------------- S1 Paradis et al. ----------------\nsrc = \"arxiv-2410.12944v3\"\nln_tab, row = find(src, r\"ExpCon \\|\")\nln_se, _ = find(src, r\"^\\(\", ln_tab) # next SE line after the ExpCon row\nse_line = lines_of(src)[ln_se - 1]\ncoefs = re.findall(r\"-?\\d+\\.\\d+\", row.split(\"ExpCon\")[0])\nses = re.findall(r\"\\((\\d+\\.\\d+)\\)\", se_line)\nb_print, se_print = coefs[1], ses[1] # Model 2 = second column\nln_ci, ci_line = find(src, r\"best-fit Model 2\")\nm = re.search(r\"CI = \\[(-?\\d+\\.\\d+),\\s*(-?\\d+\\.\\d+)\\]\\s*,\\s*p=(\\d?\\.\\d+)\", ci_line)\nci_l, ci_u, p1 = m.group(1), m.group(2), m.group(3)\nfind(src, r\"TABLE III\")\nln_n, nline = find(src, r\"completed the task in 96 min\")\nb1, se1 = float(b_print), float(se_print)\nse1_ci = (float(ci_u) - float(ci_l)) / (2 * Z)\nitems[\"S1\"] = dict(\n estimate_as_printed=f\"{b_print} (ExpCon, Model 2, LogToT; marker '.'); text: beta_1=-0.24, effect of AI = 21%\",\n uncertainty_as_printed=f\"SE ({se_print}); 95% CI = [{ci_l}, {ci_u}]; p={p1}\",\n sample_as_printed=\"Table III: n = 96 (Section VI-B: N=47 AI, N=46 no-AI)\",\n definition=\"OLS coefficient of the experimental condition (AI vs no-AI, randomised) on the natural log of time on task, controlling for developer-level factors (Model 2)\",\n locator=f\"{src}; Table III (L{ln_tab}-L{ln_se}), row ExpCon, column (2) 'Dev'; Section VI-C (L{ln_ci}) for CI and p\",\n harmonisable=True, harmonised_estimate=b1, harmonised_se=se1, poolable=True,\n transformation=f\"log-time coefficient: theta = b = {b_print}; SE(theta) = SE(b) = {se_print} (printed SE used; CI-based SE = ({ci_u} - ({ci_l}))/3.92 = {se1_ci:.4f} used only as sensitivity)\",\n reason_if_not=None)\n\n# ---------------- S2 Becker et al. ----------------\nsrc = \"arxiv-2507.09089v2\"\nln_a, _ = find(src, r\"increases completion time by 19%\")\nln_r, rline = find(src, r\"implement issues in 19% more time on average\")\nln_s, _ = find(src, r\"S=\\\\frac\")\nln_c, _ = find(src, r\"Developers complete 136 issues\")\nfind(src, r\"^Omitted:.*Figure 1\")\nc2 = float(re.search(r\"(\\d+)% more time\", rline).group(1)) / 100\nth2 = math.log(1 + c2)\nitems[\"S2\"] = dict(\n estimate_as_printed=\"19% more time on average (AI allowed increases completion time by 19%)\",\n uncertainty_as_printed=\"none printed (confidence interval shown only in Figure 1 / Figure 15, not reproduced in the extract)\",\n sample_as_printed=\"16 developers, 246 tasks; 136 issues AI-allowed, 110 issues AI-disallowed\",\n definition=\"S = E[time with AI allowed]/E[time AI disallowed] - 1, estimated as exp(beta)-1 from OLS of log implementation time on AI indicator and log forecast time (issue-level randomisation)\",\n locator=f\"{src}; Section 3 Results (L{ln_r}); abstract (L{ln_a}); estimator in Section 2.3 (L{ln_s}) and Appendix D.1-D.3\",\n harmonisable=True, harmonised_estimate=th2, harmonised_se=None, poolable=False,\n transformation=f\"percentage change: c = +0.19; theta = ln(1 + 0.19) = {th2:.6f} (equals the regression beta since S = exp(beta) - 1)\",\n reason_if_not=\"Not poolable: no SE, CI or p-value is printed in the extract; the confidence interval appears only in a figure that is not reproduced, so SE(theta) cannot be obtained.\")\n\n# ---------------- S3 Bono & Xu ----------------\nsrc = \"arxiv-2411.01067v2\"\nln_h, _ = find(src, r\"\\| Overall \\| Treatment \\| Control \\| Improvement\")\nln_row, row3 = find(src, r\"^All Content \\|\", ln_h)\ncells = [c.strip() for c in row3.split(\"|\")]\nov, tr, co, imp = cells[1], cells[2], cells[3], cells[4]\nfind(src, r\"Table 3: Comparison of task duration\")\nfind(src, r\"We had 181 subjects\")\nfind(src, r\"^Editorial note\")\nc3 = float(re.match(r\"(-?\\d+\\.\\d+)%\", imp).group(1)) / 100\nth3 = math.log(1 + c3)\nitems[\"S3\"] = dict(\n estimate_as_printed=f\"Treatment {tr} min, Control {co} min (Overall {ov}); Improvement {imp}\",\n uncertainty_as_printed=\"significance stars only (***; per the paper's scheme 0<p<=0.01); no SE or CI printed\",\n sample_as_printed=\"181 subjects completed the task satisfactorily (one subject dropped)\",\n definition=\"Percentage difference in mean task duration (minutes), Copilot (treatment) vs control without Copilot, holding accuracy constant (control duration predicted at treatment accuracy; Appendix B), randomised\",\n locator=f\"{src}; Section 4.2, Table 3 (L{ln_h}-L{ln_row}), row 'Aggregate Results / All Content', columns Treatment, Control, Improvement\",\n harmonisable=True, harmonised_estimate=th3, harmonised_se=None, poolable=False,\n transformation=f\"percentage change: c = {c3}; theta = ln(1 + ({c3})) = {th3:.6f} (ratio of displayed means ln({tr}/{co}) = {math.log(float(tr)/float(co)):.6f}, sensitivity only)\",\n reason_if_not=\"Not poolable: uncertainty is printed only as significance stars (p<=0.01); SE(theta) cannot be recovered from a threshold.\")\n\n# ---------------- S4 Bono ----------------\nsrc = \"arxiv-2511.13860v1\"\nln_t3, _ = find(src, r\"^Table 3: Comparison of Email Processing Times\")\nln_aw, aw = find(src, r\"^Aware Time per Email\", ln_t3)\nln_co, cw = find(src, r\"^Control Time per Email\", ln_t3)\nln_ts, ts = find(src, r\"^% Time Savings\", ln_t3)\nln_p, pv = find(src, r\"^p-value\", ln_t3)\nfind(src, r\"Control \\( N\\{=\\}52\")\nfind(src, r\"Aware \\( N\\{=\\}56\")\nlast = lambda s: s.split(\"|\")[-1].strip()\naw4, co4, sav4, p4 = last(aw), last(cw), last(ts), last(pv)\nc4 = -float(sav4) / 100\nth4 = math.log(1 + c4)\nz4 = norm.ppf(1 - float(p4) / 2)\nse4 = abs(th4) / z4\nitems[\"S4\"] = dict(\n estimate_as_printed=f\"Aware {aw4}, Control {co4} (row labels: Time per Email (s)); % Time Savings {sav4}\",\n uncertainty_as_printed=f\"p-value {p4}\",\n sample_as_printed=\"Aware N=56, Control N=52 (of 167 analysts in three arms; 13 low-scoring responses filtered)\",\n definition=\"Percentage time saving per processed email (Full Corpus, whole 25-email queue without resolve-benign protocol), Aware arm (agent verdicts, rationale, agent-ordered queue) vs Control (random order, no AI), randomised\",\n locator=f\"{src}; Section 3.3, Table 3 (L{ln_t3}-L{ln_p}), column 'Full Corpus', rows Aware/Control Time per Email, % Time Savings, p-value\",\n harmonisable=True, harmonised_estimate=th4, harmonised_se=se4, poolable=True,\n transformation=f\"percentage time saving {sav4}% -> c = {c4}; theta = ln(1 + ({c4})) = {th4:.6f}; APPROXIMATE SE from two-sided p: SE = |theta|/z_(1-{p4}/2) = {abs(th4):.6f}/{z4:.6f} = {se4:.6f} (ratio of displayed means ln({aw4}/{co4}) = {math.log(float(aw4)/float(co4)):.6f}, sensitivity only)\",\n reason_if_not=None)\n\n# ---------------- S5 Kreitmeir & Raschky ----------------\nsrc = \"arxiv-2304.09339v1\"\nln_tp, tp = find(src, r\"TreatPost \\|\")\nln_tse, tse = find(src, r\"^\\| \\(\", ln_tp)\nln_N, nl = find(src, r\"^N \\|\", ln_tp)\nfind(src, r\"aggregate Output measure\")\nb5 = [c.strip() for c in tp.split(\"|\")][3]\ns5 = [c.strip() for c in tse.split(\"|\")][3]\nn5 = [c.strip() for c in nl.split(\"|\")][3]\nitems[\"S5\"] = dict(\n 17 README.md\n 108 sources/arxiv-2304.09339v1.txt\n 112 sources/arxiv-2410.12944v3.txt\n 109 sources/arxiv-2411.01067v2.txt\n 132 sources/arxiv-2507.09089v2.txt\n 162 sources/arxiv-2511.13860v1.txt\n 640 total\n-0.18814332871148873 0.10626483095451474 0.3236860522786328","is_error":false}]},"uuid":"bd192d83-77d3-4dbc-b97d-1cc904c3cec3","timestamp":"2026-10-30T05:33:49.787Z","toolUseResult":{"stdout":"# ---------------- S1 Paradis et al. ----------------\nsrc = \"arxiv-2410.12944v3\"\nln_tab, row = find(src, r\"ExpCon \\|\")\nln_se, _ = find(src, r\"^\\(\", ln_tab) # next SE line after the ExpCon row\nse_line = lines_of(src)[ln_se - 1]\ncoefs = re.findall(r\"-?\\d+\\.\\d+\", row.split(\"ExpCon\")[0])\nses = re.findall(r\"\\((\\d+\\.\\d+)\\)\", se_line)\nb_print, se_print = coefs[1], ses[1] # Model 2 = second column\nln_ci, ci_line = find(src, r\"best-fit Model 2\")\nm = re.search(r\"CI = \\[(-?\\d+\\.\\d+),\\s*(-?\\d+\\.\\d+)\\]\\s*,\\s*p=(\\d?\\.\\d+)\", ci_line)\nci_l, ci_u, p1 = m.group(1), m.group(2), m.group(3)\nfind(src, r\"TABLE III\")\nln_n, nline = find(src, r\"completed the task in 96 min\")\nb1, se1 = float(b_print), float(se_print)\nse1_ci = (float(ci_u) - float(ci_l)) / (2 * Z)\nitems[\"S1\"] = dict(\n estimate_as_printed=f\"{b_print} (ExpCon, Model 2, LogToT; marker '.'); text: beta_1=-0.24, effect of AI = 21%\",\n uncertainty_as_printed=f\"SE ({se_print}); 95% CI = [{ci_l}, {ci_u}]; p={p1}\",\n sample_as_printed=\"Table III: n = 96 (Section VI-B: N=47 AI, N=46 no-AI)\",\n definition=\"OLS coefficient of the experimental condition (AI vs no-AI, randomised) on the natural log of time on task, controlling for developer-level factors (Model 2)\",\n locator=f\"{src}; Table III (L{ln_tab}-L{ln_se}), row ExpCon, column (2) 'Dev'; Section VI-C (L{ln_ci}) for CI and p\",\n harmonisable=True, harmonised_estimate=b1, harmonised_se=se1, poolable=True,\n transformation=f\"log-time coefficient: theta = b = {b_print}; SE(theta) = SE(b) = {se_print} (printed SE used; CI-based SE = ({ci_u} - ({ci_l}))/3.92 = {se1_ci:.4f} used only as sensitivity)\",\n reason_if_not=None)\n\n# ---------------- S2 Becker et al. ----------------\nsrc = \"arxiv-2507.09089v2\"\nln_a, _ = find(src, r\"increases completion time by 19%\")\nln_r, rline = find(src, r\"implement issues in 19% more time on average\")\nln_s, _ = find(src, r\"S=\\\\frac\")\nln_c, _ = find(src, r\"Developers complete 136 issues\")\nfind(src, r\"^Omitted:.*Figure 1\")\nc2 = float(re.search(r\"(\\d+)% more time\", rline).group(1)) / 100\nth2 = math.log(1 + c2)\nitems[\"S2\"] = dict(\n estimate_as_printed=\"19% more time on average (AI allowed increases completion time by 19%)\",\n uncertainty_as_printed=\"none printed (confidence interval shown only in Figure 1 / Figure 15, not reproduced in the extract)\",\n sample_as_printed=\"16 developers, 246 tasks; 136 issues AI-allowed, 110 issues AI-disallowed\",\n definition=\"S = E[time with AI allowed]/E[time AI disallowed] - 1, estimated as exp(beta)-1 from OLS of log implementation time on AI indicator and log forecast time (issue-level randomisation)\",\n locator=f\"{src}; Section 3 Results (L{ln_r}); abstract (L{ln_a}); estimator in Section 2.3 (L{ln_s}) and Appendix D.1-D.3\",\n harmonisable=True, harmonised_estimate=th2, harmonised_se=None, poolable=False,\n transformation=f\"percentage change: c = +0.19; theta = ln(1 + 0.19) = {th2:.6f} (equals the regression beta since S = exp(beta) - 1)\",\n reason_if_not=\"Not poolable: no SE, CI or p-value is printed in the extract; the confidence interval appears only in a figure that is not reproduced, so SE(theta) cannot be obtained.\")\n\n# ---------------- S3 Bono & Xu ----------------\nsrc = \"arxiv-2411.01067v2\"\nln_h, _ = find(src, r\"\\| Overall \\| Treatment \\| Control \\| Improvement\")\nln_row, row3 = find(src, r\"^All Content \\|\", ln_h)\ncells = [c.strip() for c in row3.split(\"|\")]\nov, tr, co, imp = cells[1], cells[2], cells[3], cells[4]\nfind(src, r\"Table 3: Comparison of task duration\")\nfind(src, r\"We had 181 subjects\")\nfind(src, r\"^Editorial note\")\nc3 = float(re.match(r\"(-?\\d+\\.\\d+)%\", imp).group(1)) / 100\nth3 = math.log(1 + c3)\nitems[\"S3\"] = dict(\n estimate_as_printed=f\"Treatment {tr} min, Control {co} min (Overall {ov}); Improvement {imp}\",\n uncertainty_as_printed=\"significance stars only (***; per the paper's scheme 0<p<=0.01); no SE or CI printed\",\n sample_as_printed=\"181 subjects completed the task satisfactorily (one subject dropped)\",\n definition=\"Percentage difference in mean task duration (minutes), Copilot (treatment) vs control without Copilot, holding accuracy constant (control duration predicted at treatment accuracy; Appendix B), randomised\",\n locator=f\"{src}; Section 4.2, Table 3 (L{ln_h}-L{ln_row}), row 'Aggregate Results / All Content', columns Treatment, Control, Improvement\",\n harmonisable=True, harmonised_estimate=th3, harmonised_se=None, poolable=False,\n transformation=f\"percentage change: c = {c3}; theta = ln(1 + ({c3})) = {th3:.6f} (ratio of displayed means ln({tr}/{co}) = {math.log(float(tr)/float(co)):.6f}, sensitivity only)\",\n reason_if_not=\"Not poolable: uncertainty is printed only as significance stars (p<=0.01); SE(theta) cannot be recovered from a threshold.\")\n\n# ---------------- S4 Bono ----------------\nsrc = \"arxiv-2511.13860v1\"\nln_t3, _ = find(src, r\"^Table 3: Comparison of Email Processing Times\")\nln_aw, aw = find(src, r\"^Aware Time per Email\", ln_t3)\nln_co, cw = find(src, r\"^Control Time per Email\", ln_t3)\nln_ts, ts = find(src, r\"^% Time Savings\", ln_t3)\nln_p, pv = find(src, r\"^p-value\", ln_t3)\nfind(src, r\"Control \\( N\\{=\\}52\")\nfind(src, r\"Aware \\( N\\{=\\}56\")\nlast = lambda s: s.split(\"|\")[-1].strip()\naw4, co4, sav4, p4 = last(aw), last(cw), last(ts), last(pv)\nc4 = -float(sav4) / 100\nth4 = math.log(1 + c4)\nz4 = norm.ppf(1 - float(p4) / 2)\nse4 = abs(th4) / z4\nitems[\"S4\"] = dict(\n estimate_as_printed=f\"Aware {aw4}, Control {co4} (row labels: Time per Email (s)); % Time Savings {sav4}\",\n uncertainty_as_printed=f\"p-value {p4}\",\n sample_as_printed=\"Aware N=56, Control N=52 (of 167 analysts in three arms; 13 low-scoring responses filtered)\",\n definition=\"Percentage time saving per processed email (Full Corpus, whole 25-email queue without resolve-benign protocol), Aware arm (agent verdicts, rationale, agent-ordered queue) vs Control (random order, no AI), randomised\",\n locator=f\"{src}; Section 3.3, Table 3 (L{ln_t3}-L{ln_p}), column 'Full Corpus', rows Aware/Control Time per Email, % Time Savings, p-value\",\n harmonisable=True, harmonised_estimate=th4, harmonised_se=se4, poolable=True,\n transformation=f\"percentage time saving {sav4}% -> c = {c4}; theta = ln(1 + ({c4})) = {th4:.6f}; APPROXIMATE SE from two-sided p: SE = |theta|/z_(1-{p4}/2) = {abs(th4):.6f}/{z4:.6f} = {se4:.6f} (ratio of displayed means ln({aw4}/{co4}) = {math.log(float(aw4)/float(co4)):.6f}, sensitivity only)\",\n reason_if_not=None)\n\n# ---------------- S5 Kreitmeir & Raschky ----------------\nsrc = \"arxiv-2304.09339v1\"\nln_tp, tp = find(src, r\"TreatPost \\|\")\nln_tse, tse = find(src, r\"^\\| \\(\", ln_tp)\nln_N, nl = find(src, r\"^N \\|\", ln_tp)\nfind(src, r\"aggregate Output measure\")\nb5 = [c.strip() for c in tp.split(\"|\")][3]\ns5 = [c.strip() for c in tse.split(\"|\")][3]\nn5 = [c.strip() for c in nl.split(\"|\")][3]\nitems[\"S5\"] = dict(\n 17 README.md\n 108 sources/arxiv-2304.09339v1.txt\n 112 sources/arxiv-2410.12944v3.txt\n 109 sources/arxiv-2411.01067v2.txt\n 132 sources/arxiv-2507.09089v2.txt\n 162 sources/arxiv-2511.13860v1.txt\n 640 total\n-0.18814332871148873 0.10626483095451474 0.3236860522786328","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3a511544-8135-4eda-9287-9d651b0adff7","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}43{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"00eabbfc1a8703765cc9d4e26aaea6ede76f3430b044cfe38372ad9552e69150","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01AhFQpWktsW2fsJ2TvYSLHe","name":"Bash","input":{"command":"sed -n 40,140p out/analysis.py; cd data && wc -l README.md sources/*; cd ..; ~/wp29/venv/bin/python -c \"\nimport numpy as np\nfrom scipy.stats import norm\nt=np.array([-0.24,np.log(1-0.111)]);z=norm.ppf(1-0.471/2);s=np.array([0.14,abs(t[1])/z]);w=1/s**2\nfe=(w*t).sum()/w.sum();print(fe,1/np.sqrt(w.sum()),((t-fe)**2*w).sum())\""}}]}}44{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"378f9b99-7bc4-4104-9916-169079deda29","timestamp":"2026-10-30T05:33:49.791Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"051b46b6-8e7c-423e-bef1-cdfc13992d65","keep":10,"tail":["00eabbfc1a8703765cc9d4e26aaea6ede76f3430b044cfe38372ad9552e69150","8f97d77ce0f0e2808112af8619d25ff53132a2734de282257952a6a2211df9e9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"73c5cb0a231b7731b72d056e54a0bacd1b78800c37438dce04ec130092ab0e67"}45{"type":"tools-used","tools":["Bash","Read"],"sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}46{"parentUuid":"bd192d83-77d3-4dbc-b97d-1cc904c3cec3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoAixi526WutQwCeGo","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":3840,"cache_read_input_tokens":25136,"output_tokens":211,"output_tokens_details":{"thinking_tokens":19},"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":3840},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":308,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsoAY3N4Lb28i48iSAM","requestRef":"378f9b99-7bc4-4104-9916-169079deda29","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d11e818e-b3e6-4235-946d-bb358d532042","timestamp":"2026-10-30T05:33:51.553Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}47{"parentUuid":"d11e818e-b3e6-4235-946d-bb358d532042","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoAixi526WutQwCeGo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QZQBspfEfFTKnFXt4GY2m5","name":"Bash","input":{"command":"sed -n 76,92p data/sources/arxiv-2304.09339v1.txt; grep -n \"181\\|stars\\|0<p\" data/sources/arxiv-2411.01067v2.txt | head"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3840,"cache_read_input_tokens":25136,"output_tokens":211,"output_tokens_details":{"thinking_tokens":19},"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":3840},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsoAY3N4Lb28i48iSAM","requestRef":"378f9b99-7bc4-4104-9916-169079deda29","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2a37614f-1f69-4591-9f4c-79f3d17d7d30","timestamp":"2026-10-30T05:33:52.101Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"2a37614f-1f69-4591-9f4c-79f3d17d7d30","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QZQBspfEfFTKnFXt4GY2m5","type":"tool_result","content":"| (1) | (2) | (3) | (4) | (5) | (6) | (7) | (8)\n\n| A: Pre 27/28.03 - Post 03/04.04 | | | | | | |\n\n\\times TreatPost | 0.115 | -0.012** | -0.278 | -0.227 | 0.005 | -0.003 | 0.188 | 0.192\n\n| (0.109) | (0.005) | (0.295) | (0.207) | (0.120) | (0.005) | (0.221) | (0.189)\n\nPost | 0.052 | 0.002 | 0.453*** | 0.323*** | -0.013 | 0.002 | 0.040 | 0.051\n\n| (0.053) | (0.002) | (0.123) | (0.094) | (0.060) | (0.002) | (0.119) | (0.101)\n\nN | 18332 | 18332 | 18332 | 18332 | 14496 | 14496 | 14496 | 14496\n\n| B: Pre 27/28/29.03 - Post 05/06/11.04 | | | | | | |\n\n\\times TreatPost | 0.048 | -0.003 | 0.135 | 0.073 | 0.003 | 0.000 | 0.067 | 0.058\n10:Editorial note: the paper marks significance with asterisks only (defined in the methodology as * 0.05<p<=0.1, ** 0.01<p<=0.05, *** 0<p<=0.01); no standard errors or confidence intervals are printed for the time-savings estimates.\n38:We had 181 subjects complete the task satisfactorily.^3^3","is_error":false}]},"uuid":"a8b2f7c4-2285-40f4-bbcc-1780ef302c1a","timestamp":"2026-10-30T05:33:52.131Z","toolUseResult":{"stdout":"| (1) | (2) | (3) | (4) | (5) | (6) | (7) | (8)\n\n| A: Pre 27/28.03 - Post 03/04.04 | | | | | | |\n\n\\times TreatPost | 0.115 | -0.012** | -0.278 | -0.227 | 0.005 | -0.003 | 0.188 | 0.192\n\n| (0.109) | (0.005) | (0.295) | (0.207) | (0.120) | (0.005) | (0.221) | (0.189)\n\nPost | 0.052 | 0.002 | 0.453*** | 0.323*** | -0.013 | 0.002 | 0.040 | 0.051\n\n| (0.053) | (0.002) | (0.123) | (0.094) | (0.060) | (0.002) | (0.119) | (0.101)\n\nN | 18332 | 18332 | 18332 | 18332 | 14496 | 14496 | 14496 | 14496\n\n| B: Pre 27/28/29.03 - Post 05/06/11.04 | | | | | | |\n\n\\times TreatPost | 0.048 | -0.003 | 0.135 | 0.073 | 0.003 | 0.000 | 0.067 | 0.058\n10:Editorial note: the paper marks significance with asterisks only (defined in the methodology as * 0.05<p<=0.1, ** 0.01<p<=0.05, *** 0<p<=0.01); no standard errors or confidence intervals are printed for the time-savings estimates.\n38:We had 181 subjects complete the task satisfactorily.^3^3","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2a37614f-1f69-4591-9f4c-79f3d17d7d30","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"a8b2f7c4-2285-40f4-bbcc-1780ef302c1a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoAixi526WutQwCeGo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JmykRwUdKcdZzWMoVXpeHk","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0007/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":3840,"cache_read_input_tokens":25136,"output_tokens":211,"output_tokens_details":{"thinking_tokens":19},"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":3840},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXsoAY3N4Lb28i48iSAM","requestRef":"378f9b99-7bc4-4104-9916-169079deda29","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cfd86899-b902-406c-aa1a-3f1e8c1ced64","timestamp":"2026-10-30T05:33:52.544Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}50{"parentUuid":"cfd86899-b902-406c-aa1a-3f1e8c1ced64","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JmykRwUdKcdZzWMoVXpeHk","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"775d5bd3-03e6-4736-8eb2-4031206c0bac","timestamp":"2026-10-30T05:33:52.553Z","toolUseResult":{"type":"image","file":{"base64":"iVBORw0KGgoAAAANSUhEUgAABLAAAAJ2CAYAAABPQHtcAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAXEgAAFxIBZ5/SUgABAABJREFUeJzs3QWUHNX2uO0KBPcEd0KwBJfgDgnukuAuwSH4xQl6cQjuFuSiwYI7hOAOIbiEQHCX+tZ7fv8zX01N9Uz39EymZ/I+azVDuqu7y7qqzq599umUpmmaSJIkSZIkSTVqvLaeAUmSJEmSJKkxBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmmYAS5IkSZIkSTXNAJYkSZIkSZJqmgEsSZIkSZIk1TQDWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmmYAS5IkSZIkSTXNAJYkSZIkSZJqmgEsSZIkSZIk1TQDWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmmYAS5IkSZIkSTXNAJYkSe3Qsccem3Tq1Cn56KOPklrw2GOPhflhvlRslVVWSeacc84Ovd9ccsklSY8ePZKJJ544fA/7BT7++ONk0003TWaYYYbwPOtiXPH6668nvXv3Trp27RqWfYcddmjrWdI46qqrrgr7IH/1/+O43JrHpNb+/JbAOcFzuNoDA1iSpJq6eCr1qPWLvyzmlXmude1tvaq2EazafffdkzRNkwMOOCA55phj6gJ222+/fXLHHXcka6+9dni+NYM48VhSC4Giv//+O9lkk02SJ598Mtliiy3Csm+00UZlv3/vvfcOyzLrrLMm//77b8npmGaZZZZpobnW2FBL+6nGjRs48QZGvLEgtUed23oGJEnK6tmzZ7LZZps1WCltnbkiVeuaa65J/vrrrw67IocOHRr+kt2x9NJL1z3/xx9/JE888UTSp0+fcS7zY+TIkcmIESOSPfbYI7nwwgsreu+ff/6Z3HjjjaHB+fnnnycPPfRQyOSS1L48/PDDyQQTTJDUsllmmSV5++23k2mnnbatZ0VqlAEsSVJNWXDBBWv+LqbUHLPPPnuHXnFfffVV+Es3waxRo0aFrKz88+OCUuukHHfffXcyZsyYZL/99kvOOeec5OqrrzaAJbVDc889d1LrCLDNP//8bT0bUpPsQihJapduuOGG0GVmsskmS6accspk5ZVXTu67774G09E9gwwGsiBOOOGEcCHZuXPnepkg9957b7L66qsnU089dTLJJJMkSy65ZHL99dc3+Kxvv/02Ofjgg5N55503TDfNNNMkCy+8cHLIIYfUTcN3Pf7443X/Hx9NZZ5ka5OQdbHQQguFOkJzzTVXcuqppzbafSjrhx9+SAYMGBDeN9FEEyUzzzxzsvPOO4cMjnx3BzCv2flsidpIdJdaYYUVkkknnTSZccYZk4MOOqhB5tHo0aOT448/PmzD6aabLswr6/Woo45Kfv/998IMPB7ffPNNstNOO4WAwHjjjRfmN7vu/ve//yWLLbZY2D7du3dPrrjiivB+PpP1Qlcs1utKK62UvPnmmy2yb5Flc/LJJ9etc/aJIUOGlFUDq5x9Kvr000+TXXfdNZltttnC9xAQo6se2zzvp59+Svbdd9+w/tkOyy67bMgCaE4XuHPPPTesUz5nqqmmCt0Ahw0b1mB/uvLKK8O/WQ/8O9Z9mWOOOcLzBGCKfg9vvfVW0q9fvzCvLBfbjSA2mVtF83PeeeclSy21VDL55JOH+WHeYtCbz+X789+X7dLLetxtt92Sbt26hX2BjAM+77///W9F2Warrrpq2D/YT3r16pVce+219aZh+dl3cNxxx9XNR7ndd5h/9vHDDjssWW655ZLbb789+fHHH5OWqMnFvsHNgjj/LD/fVwr7P9lfXbp0CfvpPPPMk/Tv3z8EJ7PYlttss0047rAt2Vc333zz5IUXXqg3HYE5jgscj5mObc/v+osvvij8btb19NNPH7YXv+ENNtggeeaZZ+pNxzGb3y3zyL7KfrfllluGrJKWOnbmu19/9tlnYfk4d0wxxRShztuXX37Z5HeVs58+/fTTyS677JLMN9989Y5F99xzT+FnVrP8L774YvgdsM9yriwHvyMyC3kP62ummWZK1llnneTBBx+sNx3blOMWGT5Mx/Qct7777ruSXSpfe+21sL+xTtnuBx54YPjt5+vsEXDhd1GqG/8vv/yS7LPPPnXHQc5LrNdylXPM5djD/pn/nWeP9aVqYPG7WG+99cJxn98Vx36C1fnzffYcR1fsxRdfPCw/88O5pxx8P/MH5jfOZ+zCWqoGVtzXP/nkk5Adz7yyj9EtnPMMbrvttmSJJZYIy8CyXnTRRYXzUMnvXioplSSpBnz44Ycpp6Utt9yyyWmPP/74MO2ss86a7r///ulee+2VTjvttGmnTp3Syy+/vN6022+/fZi2d+/e6YwzzpjuvPPO4T333ntveP30008Pr88+++zprrvumu6zzz5p9+7dw3OnnHJK3ef8+++/6eKLLx6+Y+21104POeSQdO+9907XXHPNdPLJJ6+b7phjjknnmGOO8H7+Pz5efvnlRpfpyiuvDO9Za6210kkmmSTdaaed0oMPPjidZ555wvPMVxafyfOst+jnn39OF1poofD8qquumh522GHpRhttFOZ55plnTj/99NO6dR3fz7xm5/O7776rtz1WXnnltByPPvpo3fxPPPHE6cYbb5weeOCB6SKLLBKeP+CAA+pNf99994XlXG+99dJ99903vL788suHaVm/ecwn24/lW3DBBdP99tsvrKPPP/+8bt3xWWyL7bbbLmwb9gmev/POO8Nnzj///OG7Nt100/D8nHPOmf71119V71sbbLBBWL+77bZbuvvuu6dTTjllOv7446cvvvhivelZlyxHpfsU3nrrrXS66aZLJ5hggnSzzTZLBwwYENY137/YYoulv/32W920f//9d7rCCiuE15ZddtmwH2yxxRbphBNOGD47v9+U8s8//4RlY/oll1yybp1PPfXU6UQTTZQ+/vjj9fanuK2Zjn+fddZZYdvwb57n9fzv4bHHHksnnXTSdLLJJku33nrr9KCDDqrbD9ZZZ52wjrLLxXritXnnnTd8LvtNnz590s6dO4dp+Nyi7+MRfyOzzTZbWI/sB6ybPfbYI11xxRXTBRZYIC3HVVddFbZZly5d0j333DPMA8cPvvPoo4+um47lj/sI2z7ORznrftSoUWGZVl999fDv888/P3zOZZddVjg9ry299NJlzf+hhx6azjDDDOFYyzGGZSg65kUDBw4Mr3Xt2jXdZZddwvs333zzsJ/zu48eeuih8JuO+yjrluXndxbXP7788svwfaxDtjH7MttivPHGC+vx66+/rpv2jjvuCN89yyyzhO3EZ2677bbhd3TyySfXTXfOOeeE6Thecqzkt9SvX790+umnT2+88cYm10m5x87s+l544YXDsi233HLhWBf3zSWWWKLeflukqf0UbB8+n98F65zjy0wzzRTmKb9M5S5/PFbyN3riiSfCtpxvvvnSTz75JC3Ha6+9FvaHuA1ZX5xbe/ToEbZ5xPGZY2k8TjId+zT/7tmzZ/rjjz/WTRvPOfwWp5pqqnA8Z70yHc/z/+yfHI/5Lo61HDc41r799tv15o/fWzyXsE7Yzzl2sX9y7HrmmWfqTc/+lD/XlXvM5TdQ9Dvn99/Y5z/44IPhmMzxL57vOQbxOZzDsuJ2Yx2yDGxbzk9zzz13eJ7t3xQ+I64X5jfO5+23315v/Wf3wey+zm9zlVVWCduBYw3Pb7LJJmH/4nzF75J9j3XGayxfViW/e6kxBrAkSTUhXjxxsZq9mM8HVt55551wwcOF25gxY+rez4U3F9RcDH7zzTd1z8cLy27duqVfffVVve989dVXw2etscYa6S+//FL3/K+//hoaJTQgY8OFaYsCMch+H+JFYiXiBSoXd08//XS9eaGBw/OvvPJKowGsI488MjxHECBr0KBB4XmCGFmNBaiaG8DiMWTIkLrnf//999CooaHB/0fffvtt+sMPPzT4nJNOOil8BoGNrBgU3HDDDdM///yzcN3RMGE7ZRuJPE9jiEZpNsgTG48333xz3XPN3bcIjGWff/LJJ8PzNLIaC2BVsk8RQOL784HQ2HDNNuYvueSSwkbQ1VdfXbeNygmixKAJ+1W2Qf7RRx+FIBaNrezzcX3kPzvuS9mGLdgfCEwQmPz444/rvcY64T3ZxvcZZ5xRF+QmmJX12WefNfl9IJhZqsGXX+dFOA7RWCN4xXqIvv/++xBUY/954403Gvwu8o3Cppx55pnhfTFoSuOO4xGN+2oDWBzT8oHbGBxk2QjmRMOHDw/HHvbx0aNH13sP07Hc8ThFUIzfIO/JB0K/+OKLun8TDGA9EcQu2jYEJiIC4TTy841b9juOIREBBfYl5iOL5Yzz2JjmHDt5EHTI4jfP8xwDmtLYfgr2r3wgjPPUoosums4111z1ni93+fMBrHgjgXMMQdNyME8xWH333Xc3eJ2gVUTwjenOO++8etMQYON5/ubXB4+LL7643jITROTGCMHnbJCN4AvT9+/fv/AczHxm18lTTz0V9mduHGQVBZgqOeY29TvPfz6/N54jOJa90fHHH3+E3zifFW+yZbcbv4Xs9ByPODdxzipHvG7IBp6jxgJYPA4//PB680+glnVJkLTovEuQKquS373UGANYkqSakL14LXrERnG8ACvKRDjuuOMaXPzGRjUNkTyya3gtf/cWBGF47dxzz60XbKCh05RqAlhF2Uc33XRTeI27140FsLggpgGab7DRgOTOJw3gbOO0sQAVQSLWSz6wUEq8gF9ttdVKbhfu2jeFwFHRRXQMYHFXvNS6IzskL2aW0HDJ4t/5jJnm7lvXXHNNg+lpYOYbSaUCWE3tUy+88EKYjiyMPLYtDYjsd/E9NBTygSQangQiyg1gEUym4ZgPFoG75/ltWmkA65ZbbgnPX3jhhQ0+n8wMGkfc4Y/IEKGxzZ38xpQTwLr00kvT5oj72n/+858Gr8UAYbah19wAFg1vgkHZ3zLHBtbJBx98UFUAq5TbbrutQeOWRiXPsd4aQ6CxVDA2iyAJ+2apTFuCBjTIswEsgt/xBkYpBHD4zREAaI7mHDuZPnvjA2QlZs8b1QSwmgpuZn9n5S5/NoB16623hoAIWZpNrd+sZ599NnwG26YxBKjZh8kiyx9D+H1zY4GMsvz6IGMqH7jj2M5rJ554YoPtwzKstNJKhedgzp15MVOOGxalAkyVHnMrDWDF6bfZZpsG08Z9iCyr/HYjUytvxx13DK9ls9laOoA1xRRTNAiOsi0aO++SVdXc373UGIu4S5JqCjU7Bg8eXPJ1amNgxRVXbPBarDfz6quvNniNmhF51PGhHlbR91GjCe+++274S80NHieddFKYh/XXXz/UhaAWTEui1k0e9Yuyy16E2jgff/xxmJa6QFnU0aH2B7VNqFFDvZvWKui6yCKLNHiOWjL4/vvv6z1///33h3ofw4cPD7UxsnU/iurIUF9jgQUWKPnd1A/Jo8YGy51/jeeRrb3R3H2r1DI3VQun3H0q1pv64IMPCgc4YB+O+2lcDurR5OttUcuE/eudd95JmkLtGPYVapVQOy6P18D3Uq+tOeJyUX+naLnY3nG5fv755/D/7Ltx2zUHtc+oqUP9pkceeSTU82KdU+OmHM3dRyrxyiuvhM/YeOON6/2Wt9pqq1APippJsZZNc/zzzz/JxRdfHEbFZDuybv+vnfp/svstv02sscYajX5mJdPxO6f2W9E2//XXX8Nr1LqjJhP1pahxxD629dZbh1qFyy+/fKhnlMV0RxxxRPidU09ttdVWCyNhTjjhhE2uj+YeO/md5uej1LGuOajbd+aZZya33HJL8v7774ffZBbbKf7GK13+m266KdSqYp+96667Qo2trFhbMGvRRRdNNtpoo7K3Nb9X6tixXscff/x6r1Hbitp11IPjXEsdxIhtna0Fhvibzx/H2T78nkvVUCp1PuV3xG+Z+mJFKj3mVqqx4wj7N59fybkm7nOs19bAvs7xuJxtEl977rnnmv27lxpjAEuS1K7EIsZFo3rF54oKHXORm0cRWQrDNtYYjI0GLigfffTR5D//+U8oFM4IYSDIc8oppyQbbrhh0hKyF/L5eW+sgHNj6yX7fEsUgW4MhYbzWHex4ZwtlE6DlGVba621QoFfitKC7VFUwLto3WQVXbzHhlP+tfh8trh8c/etUsucXd4i5e5TsdjxrbfeGh5NYR5j4fRyfgdFaAwR1KDhXs7voznicl122WVNfn4smhwba81FsW2Kfx955JFhfTNgAghMECwgWNGY5u4jlYjF1AlYZRE8IGBC4IlGYL6RX64999wzufTSS8N+RrCD3xX7IkELvjv722O9E9TJB2ryyt0+cZs/9NBD4dHYdqchy/wRpDjrrLOS0047LQxowXGC59lebE9Q6J75vPDCC8O64cHvkiLoBIgpGN3Sx85yj3XNxe+fwQIojk3BbApnc9wiwHnnnXfW206VLv/zzz8f5pEgVD54BfaF/O+eeWAfLHdbV7Jes8f2So7j8bX8ICHVnk8rPeZWqrF1w/J07dq1onNNS+1zpTRnm8Si+8353UuNcRRCSVK7Ei/g8qNfZZ8rusgrauxx4cWFPRd+/69bfYNHHFktXvgyAhJ3jMkaITPl66+/DiPzVJt1kc/8yuI7Si1XOesl+3xjnzE2nXjiiaEBxEiAjN5GwIZGF43rUprbYG/tfasa5exTsYFw3XXXldxPsxk0zGPRfpTdl5oSv5MGbmPfSaO2ueJ3PPXUUyU//8MPP6xbJrTEaFVklZF1SdYfI5Ix4uMbb7yRrLvuuk1mzbX2PkKjj+BuzKrJjk7H+iJTgeDCE0880azP/+qrr0LAkKAxvz0ysfgt8tsjGy2PoAgBC763MTFzqantE7c539nYfpUNwJKVSzYH+y7ZSGTMcVxmJMmI9UNWHSMsMmogQT6yGwlyMbJpY2rx2EkGEMErRsAje+WCCy4Ixwa2U8zIzap0+QcOHBhGoiNr6/zzz2/wOus4v01iRla527oW1mtzz6eVHnMr1di64XqEbKRaOVe3hOb87qVSDGBJktqVmEJPozfvySefrDdNU8i64C42d7QrQUYAXRLJnKELHI1OusNlX0d+KOxy5IeGx7PPPhv+NtZVi4tdupPQgMkO8R3ng4Y6d2pp1GQbPc2Zx5YwcuTI0BDL322tZIjzWt63KtXYPhW7LZE1UQ66dBCIIdCRRQOhaP8qtT/NO++8oasLXZlaQyXLRQOI7j4Emko1iCv9/dFNli5GZPXQkCfjoanAUGvvI/fee29oYPMZO++8c4PHJptsUi9Lq1LsE+wHBOviemrst7fkkkuGv41lTVQ6HcedcvflLI4VBHbvueee0KWJv0VBBALj2267begiOvnkk9dlNrbksbMlNLafcnzEBhts0OC1po6R5Sw/3cF4nu5q++67b8jIK1e525rfKzeIOH/ls4Potsp5l67OTWXWVqO559NKj7mVnvMbO44wfxz/W+NcU821STWq+d1LeQawJEntSuxSQsZOtrHBXWca/nR12XTTTcv6rN133z181l577RXueOa9/fbbdXdrafh98sknDaaJr2e7aNDVI85TpQhaZC+6f/vtt9AFhIs/lr0x22yzTWgYcHc9i4wLaqjQ+M12F2E+S80jXTKolVS0zC2BmkMvvfRSWL6IoAuBhI6wb5Wj3H1qmWWWCfVnLrroolAzJo/ASzYIS9dMGijHHHNMvenIdCun/lVENhzzctBBB9XrDgICB83NAorojkQDlrvyBKaKsif4DUZk3LC/7Lfffg0axNlskGmmmSb8Ldq3qWNEnZVyfselunURFCAj5tNPP623DVgO9h/Wf3PFLJczzjgj/G7zD2oX0e2Ibk1NZUUVibW+8kEQMpzIBMyjCxrHnkMPPbTBMZLvj78T1gvzNWjQoJBJmMW+SOZXDK4QlCF4cv311zf4PoKlsf5QbODnG9vsAxznqO8UszKL9kXm7c8//2xymzbn2NkSGttPS22n2267rTAg1ZzlZ3kImBKs2WOPPcLxoRwcjwiSU5tsyJAhDV6Pv0W+lyxCjnNk+mVxTqObMoG21nTyySfXO8ewPjnHUn+rsRqPlR5zKz3n01WZbCMyQbPZ25x3uYmB1lg31VybVKPS373UGGtgSZLaFbJCaJjz4A4qd+S56ONCkAYWd5KpH1EOMl6oq3LwwQeHz6VbDQ0HMjxoUNN1g7uhdPPiYpXvImuIQuJ8B0VcuSCj4ZatV0P3C2oacfHeu3fv0NDi4q2o2Glenz59Qrctgil8xx133BEaUPvss0+Td2Spg0JtlNNPPz00IiniS8CCz+ACkkZxVnY+WZc0vvkeuohwgctyUuS36AK+WjSYBgwYEBoSZIPQnYvGEEVtqymOWyv7VjnK3adopNOtjC4/FGdm/1hwwQXDvJGpwfahsUNjCzvttFPoQsSDGlYULmc69oM111wzFG8uB5kZjz/+eAhKxILPNLoJ3HAnnYZqNdlZZIGwbtn+7AfrrLNOyNr46aefwnzz3ccff3xd4X4CV8wHQRzWHV3e2GdZZw888EBdHRyytagbxHphXcw111xhHdIwpFsWwRj2M7Y32Td8Fu/nezgGNIaaS3S52nHHHcM89+3bNzTUCSgRjDz66KOTnj17Nmt9sI+RVcQxiG1dhEwg9gtqQhHMIPBSCWrNrbfeemG9E1QieMG+QSFvnicokc+coOsa645tQyCH/ZSi5xTCZnqOI2xLultxnGN/JjjZvXv3EBikzhv7ZyzeTDCDQCLzzr7FtqJmDoEOthnHrZh9uPfee4fPIFOI7cj+xjoi2J0tBs33Ml+9evUKgQGCN+zvBHAOOOCAJtdLpcfOltDYfsr3E0AhO5CungRb+Mt6IVjIvGY1d/nZ//lMiuOzT7Mvb7HFFk3OO8Eu9lG+l98t5zaO4dx84bwaA7HMP8vHduS3y2+M8yr/z+8kBmtaCwFyzpvsj/y+qHnH+bio22RWpcdctg/HbD6fGm18L8cKlrsI+zvBUY597NscR9h+nAP5bWy33XaFXXqrFQea4EYR+xPBeNYPA4i0tkp+91KjGh2jUJKksSQO4VxqmOW86667Lu3Vq1c66aSThuHMV1xxxfSee+5pMB1DlOeHHM975JFH0vXWWy+ddtpp0wkmmCCdddZZ09VXXz294IIL6oZO//TTT9NDDjmkbrjniSeeOAwVvffee4fXsv7888903333DUOEM3R0HLa83OHNb7jhhnTBBRcMQ5Az/PbJJ58chu4uGg47v1wMh37ggQeG97EsM844YxhmOz+P+Oyzz9INN9wwnXrqqdNOnTrV+7y4PbJDfzemsWHE47Jlh+5meRgOft55560bav3II48Mw8AXDS3P8vBoat3lxeHUKxnCviX2Lb43P7/55yrZp/Dll1+m++23Xzr33HOHoeO7dOmSLrLIIumAAQPSt956q960DKnO50w33XTpJJNMki6zzDLpQw89VHK/KYXtdOmll6bLLrtsGEqdeezWrVu6+eabp7feemtZ66OxdY33338/3XnnndPZZpst7LPM81JLLRXm9eOPP27w22K/YbmZl6mmmipdbLHF0uOPP77edG+88Ub4DbP9+O64D7Ce9tlnn3ThhRcO+z3beP7550+POOKI9Ntvv03Ldf/994ftyeezftmG11xzTUW/i7zzzjsvTHvYYYc1Ot0rr7wSpmP5Iv699NJLlzXv33//fbrnnnums8wyS1iHrMurrrqqbl6Lfkd33nlnuuqqq4Z9gOWdZ5550r322isdNWpUvelee+21dIsttgjbkH2UYyn/Hj58eIN5OOqoo9IePXqEeZhyyinD//fv3z8dNmxY3XQ33nhjuskmm4TjA9Pxufweb7rppnqfN2jQoHSdddYJ38f3cuzt06dPOnTo0LRclRw7Sx0b475ezvZubD/F559/nvbr1y+dfvrp08kmmyz8BocMGVJ4PC13+UsdK0ePHp327Nkz7dy5c3r77beXNe8fffRR+N3OPPPMYX3xneuuu244zmSxHLvsskt4nelmn332dP/990/HjBlT9nEiHreyy9zYuSEe9zl/s5/OMMMMYf9Zbrnl0ieffLLwM4q2ZyXH3CeeeCJsI44pfHd2nkp9/vPPPx+2G8cxzoOc988666wG5/vGznGVHtMvuuiidL755gvbIru+S+27pfb15px3y/3dS43pxH8aD3FJkqTWxh1r7oBTnHiHHXZwhUuS1AxkBZLBaTNX6nisgSVJkiRJkqSaZgBLkiRJkiRJNc0AliRJkiRJkmqaNbAkSZIkSZJU08zAkiRJkiRJUk0zgCVJkiRJkqSaZgBLkiRJkiRJNc0AliRJNeiPP/5I5phjjmTfffdt61mpSccee2zSqVOn5LHHHmvrWalZrJ8ddtih5rYF88T0qk1sR7YP21UNXXXVVRUfe+acc87wGJeWuaNq7nF11KhRySSTTJKcffbZrTJf0rjCAJYkSTXoggsuSL766qvkkEMOafDarbfemqyxxhpJly5dkgknnDCZccYZk169eiUHHXRQ8tZbb9WbdpVVVgkX3EWPww47LKkF7b1xp/bhxRdfTLbccstklllmSSaYYIKka9euyYILLpjsvPPOyf333183XZqmyb333pvstttuSc+ePZPJJ588mWKKKZJll102ueKKK8LrLaGS3/GJJ56YrL766smss86aTDzxxMlMM80Uftv/+9//Wmx+NG4E/eI5oa2CYPwdF80wwwzJLrvskpx00knJTz/91NazI7Vbndt6BiRJUn1//vlncsoppySbbbZZaLBmHX744eG1KaecMll//fWT2WabLfn5559D45w7uzRse/To0WCVHnPMMQ2eW2GFFVz1Hdjbb7+dTDXVVG09GzXhnnvuSTbaaKMQ7FlrrbWSBRZYIDz/5ptvJoMHDw7ZETwfsx/XXXfdZNJJJw1Bo/XWWy/5/vvvk9tuuy0Eu5555pnksssuq2p+Kv0dX3zxxeFYwDxON910yZgxY5IhQ4aEY8Q+++yTnHvuuVWuIZVr4403TpZZZplk9tlnH2dW2ri4zK3hgAMOSM4///zkwgsvLLw5JalpBrAkSaoxd9xxRzJ69Oikb9++9Z4fOXJkctppp4WuhcOGDUumn376eq9/8cUXybffflv4me0hM0Ata/7553eV/j977713+Pv4448nyy+/fL318ssvvyQvv/xy3b/HH3/85OSTT0769+8fAkwRmRNLLbVUcvnll4dMChr0zdGc3/H7778fMq/y87300ksn5513XjJgwACDC2MJQeFxLTA8Li5za+jWrVvdMcQAltQ8diGUJKnGXHPNNSH7o0+fPvWeHz58ePLvv/+Gu+H5Ri9mnnnmZKGFFmrx+fnoo4/q6n6QscJ80a2Krk877bRTYXcIslhOOOGEEESh4U3WyBZbbJG88847DT73448/Do9s98ZKaq1ceumlIaNmookmSuadd97QzSvv9ddfD/XE6DJGUGKyySYLDYmrr7660eUlsMHy0niba6656tVw+uCDD5KBAweG59leBBPIzgHLs/nmm4d1RPezbbbZJvnhhx+atZ7yXS3JBiKAMu2004bvXXPNNQunL6rVQtc0AqNkUrC+6Nay4oorNujWc8MNN4SMJYIsTMf+RrZPvmtbHplA88wzT1gWtkklmUq//vprcvzxx4fMI95PFz/W4Xvvvddg2m+++SYsc9E6zfv666/DNmXb54NXYF/IZiPSvZDutdngFZgfuhXiqaeeSpqrOb/jfPAqznfv3r3D/3/44Ydlffd9992XrLrqquF7+UyyujbYYIO6/TbvySefDOuG/YwujnRv/OuvvxpMx3YgiMZvgf2FZSBb7fPPP6833XzzzVeX/RaRdca+ynonKBf99ttv4bPY76L42yMISJAxft/CCy8cMtLKsfvuu4fPIOsuYntMPfXU4fkHHnig3vT8Pvhdxq6a+XpQ3BxgneK4446rO4YVdYsu97cbf4MESdnO7Isrr7xy2H5FXQJLdcHmeV6PmC+CuPH/46Opbn1FNbCy3Sab2k/YbjvuuGP4f/7G783OG5599tmwP/JbY//kN3vOOec06Cabrbs3aNCgcMygGy7Pb7vttuG1ESNGFC7LkksuGdbn77//Hv7NsYHf++KLL55MM800oU4Vv78zzzwz7BflKPe4ik022SQc055//vmyPltSfWZgSZJUQ7hgpjGw2GKLhQvyLIIhMRujUtdff30IqhCIWW655cLnV4pGMo0U6vTsscceyXPPPZdceeWVdd2rsstAt6gHH3wwWWKJJZL9998/+eyzz5Kbb745NA5pQC266KKhwUjXxljUlumicmtinXXWWckTTzwRgi00Bm+55ZbQcKaBSEMou/x8Pw2mddZZJ3TXYv5oWFFr7NBDD23w2aznlVZaKQSmaPRmG9dxfl977bXQxYzPo8FJF6+nn346WXvttZPu3buHxhrBAb4f1113XcXrKd+9lOWkcUhDjQABtZRiQ5jGbil8Ng1ivpf1RWOLQNBLL72U3HTTTfWCXTRACW5Qo4nG+yeffBIyA5lXAjAEqfLIKmKf6NevX9h3WY5dd901+fHHH5MDDzywyeAVQQAykmios/4IPLE9H3roodCwzWaU0Q2HYAH7X1MFldnnyaois4lt2Ng6agpBFnTu3PxL6Gp+x/ngJw145oXAUFPuvPPOsN2pAbbpppuG3x/7D78fHhwXsmhgn3rqqWFb7LnnnsnDDz8cGvUEE/gbsU5prBMkZhvSkGdfZNtQW4zPiV2h2bYEnNm2MXgXAyp///13+K2wL4Ntzv7Oe4q6YrEf8tsjWHHjjTeGZWP/IRDRGD7vkksuCctMgBSvvPJKXTCU5+PNA4IcfGb8niIcUwiCEAzns2NQhvXb3N8uQe2jjz46rDeCpryH3yhdWwkKc+OgOTjeElThXJDtVp4/zlSinP2EbcN5gn1www03rPu+7HGe5dt6661DEIljN38feeSRcFxk/dDtLo8gJt/P9GwjMpw4P3GcpWvwf/7zn3rT85sjYLrddtvVBYXZRy+66KLQXZj9l3XNOZhjINMXfW9zj6uImZuPPvpoOLdIqlAqSZJqxuuvv86t5nTvvfdu8NqPP/6YzjLLLOH1ddddN73uuuvSjz/+uNHPW3nllcP0+cc666yTjhkzpqx5+vDDD+ved/7559c9/++//6Zrrrlm2qlTp/STTz6pe/7SSy8N02622WZhmujee+8Nz/fq1ave588xxxzhUYljjjkmfNa0004b5i8aOXJkOsEEE6Srr756vek//fTT9K+//qr33N9//52uvfba6eSTT57+/PPPhct72mmnNfju7bffPrzWo0ePeuvwrLPOCs9PNdVU6eGHH17ve5ZYYom0c+fO6RdffFHVeuL5vn37hs+MTjjhhPD8tddeW296nmNeo3POOSc8d+eddzZYpm+++abev1mPee+88046xRRTpDvssEPhtph00knT999/v+750aNHpzPPPHM68cQTp6NGjWqw/rIGDBgQnrvkkkvqPT98+PCwPfv06VP4nVdeeWVajg022CBMv+CCC6bnnXde+J39888/aSWYftFFFw2f88orr6TN1ZzfcTRw4MD06KOPTvv375/ONddc4TNOPfXUst678cYbpxNOOGH69ddf13uefe/bb7+t+/ejjz5at/8PGTKk7vnff/897POTTTZZ+P/oyCOPDNMedNBB9T530KBB4fktttii7jn2UZ675ZZb6p7bcMMN08UWWyydcsopw2flt3F2Xcd9Z/7556+3zz755JPh+Z133rnJ9cCxgGn32muver/d8ccfP11hhRXS5ZdfvsG6OPvss+ueY5/jOV7LT8c8F6nkt8vvbLzxxkvnnnvuescXjrFdu3YNv7PssnOML3X85HleLzonVKKxZS53P4mfUfSb/eqrr8L0/D6z+yLriuMj73v22Wcb7BtTTz11+t5779X7rD///DOsJ+Yh77jjjgvvu+++++qe+/LLL9PffvutwbS77bZbOLdlzy/VHlfj75/p119//QavSWqaXQglSaoh3M1FUdciuqKR6UT2C0Wp6ZZGFy+665DpQzZQHneEyeYhy4gsIe5Wc6ecUdbIlKkEGUXUBYrISGAeuKYngyHi7jevcXc8m7XA98Ysm6JuYc1Bt8DsXXy6FJEllq1pBDIZ8lkzZOWQIcR6eeGFFxp8NuuVTI9SjjjiiJAlEMVsDu7EH3XUUfW+h+5iZJhkuws1dz2R6cRnRmQTIL/MpdDNJ48uO1mxu2QWWT7MF5kDRbbffvuwj0Rkwe23334hi+X2228vOT///PNPyMohG4HtkUVmGhkbQ4cOrdddkK5C7HflDmfP55Pp8sYbb4Si53QRIkOGrI277767rM9gO7GfkyWyyCKLJM3VnN9xtg4X3SzpNvXpp58m//3vfyuqpUMGWcwii9j3YlZY1mqrrRYyfiK6RjGKIxlX2f2S/Zguxdl9HmQtsj+wrDF7MWZTxawrtiHZLnwXv9v4fJyG31dRt2h+e9l9lveyz5bzG+BYQKZO/rvICiKTh2MB3Rez81mUBdYc5fx2ySbjGEKh/+zxhUL/HO/IVmT0yVpR7n7SmGuvvTZMf/rpp9fbF1lXsX4j2Zh5ZKfls0HZvzkW060v/1ti3ZJRSmZpRJfHoi66ZBmzf5bbnb2c42r8/dNNMZ7rJVXGAJYkSTWE0cWQbbhk0T2CIAhdK2gwEuygixbdQqjtQReNLLpfUCeHmhx0UeH9NNgJFhDYIkhSLhqS+W40NLpB95CIRgONgmwwI4oNwVdffTVpCUWBBOYpOz8xSEKjn+4b1D8Zb7zxwrJQjwRffvllg8+hrk5jXcV4PYtlBg0qGihFr9GNrZr1xH5BQza/vMgvcx7BGhpqBDUJFNEgpCtXEbo3Eaxk3miQxpo1d911V+G6Qr4LGpZddtm6ZS3l3XffDcEpthGN1fyDdUZDspoudwSECYLRzY1GMnXG+D0QQCJo0VQQiO6QdOnq2bNncsEFFyTVqvR3HBFsZT3RpZOA2pFHHhkCYOWgUU+QgN8xNX/oDkowpNLfVnZfY57pjsZn5ot88xsjsETgNtZOY98l4BwDQwQUOeaxv9Ndl+MRwSO62xFs5/18Trnz1tRvIOK7qOdHsfwYRIvzwHfTfTF2JyTQmf+tN0e5v934W6FbZmsfP1tCOftJU+J5iO6H+d8/XbPjcSKvVHfReHOGgFVE8JnfHL+D/HGd76DrJ9sonhviZ5c63jXnuBrxPaUGXJHUOGtgSZJUQ2LgIxaYLcIFNpkwsXAwDS5qjXDHnqwH7oY3FnjhrjZ3/mkgUrOIxnQ58kWtEb+HRnVEo5aMkiIE0uI0LaHUPOWL71KbhSwc6ijRuOEuPNPF2jXUE8oryoLL30nPipkV+eezr2ULGzdnPZW7DYqQdUJ9LmrfkPFALR0aamRQUCiZ4Ayo38I+QZFrMhUI8JBhw35HHaxSjWfWaal12Nj2/u6778JfahrxKCVfg6w5KArNAwQuYgYUmUylMqsI+DIN64+gT0uNxtbc3zHvIxBC0XT2J7KRaDxni50XYb/nvdSNIxOIukU0vHme783XbCpnX4vbNe6v5ezHBGEYqIIGPIEs5ikWSmcdcEwii4ZAVqnMp1Lz1tRvIDsPBAsJUBFwZl54jow/9nXmi3kikEVtpKIgWqUqOX6WWqctffxsCdUck/LHAH6Hlfz+Sx2j2Xb8RqhBRaAX1MTCVltt1SCrkUAwx2IyZbmpQA0/gm8cF4vODc05rmaxbzd1fpFUzAwsSZJqSAwCxEyscnCxTUYF2QMEHcrJVKF7V0sFBYoaNNkRvrLi80WNntZC90kaFRRYJ+vi4osvTk488cRwd5/Ml1JKFW1uz+uJrAICMjQYyXagmwxdZChsH7tNMYojWU8EGShwTHCDbmusr5lmmqnkZ48ePbrBczETobHliAE/RmcjqFTq0VLduLLbl+wJujny+UUj8ZGlSMYGGSWsr8aWv1rN+R0TXAEZROWgaxcBolggn6wTiq3H0RUrFbdrJfsxyxezngggkd1E8IzgEd2wCB7xfJy2NcTPjd8Vg2gEXsga5PnYlbC15qE567RofTLvZLkVqaVAV2PiMYBudaV+/0Vdl0sdo3mefZ2BR9jfeT8BLIJU2UxR1tspp5wSAtdvv/12OPYR0OJYV0kX+3KOqxHzQsZpUcBfUtMMYEmSVEMYDpyL7+Z0lyJzoNygVMx0KZUBVA0aAwSNPvjggwavxYZ2NtOFBli5w5U3B1lWNBrIaMlnUnDnvK1Uup5aOtOPDAG6VVJHii5psevSyJEjw9/sKI4xK5CRtUopCgDFrlhFdYyiBRZYIOy7BAz+r0by2FXqd0MDlIwM6tjQKGV0sbacnyKxe1OloyISwCZjiwy0WIurOeueQApdAumama1RBn7T/L6YN45rUQxEsn4JHsV/k3VFcIHgEQ+CGk2NKNhcZM1QCyt+F/tn7LbN/JCdSpfT7Pw2Jh5XWuI4Fn/zTz31VFnHBYJ/BCTz2U507YyZTa01r5Vo7HuXWmqp8Jf13lJiphXdCDkOsT4YITMb9CLb9KeffgqZpvlu3805NzR2XI1GjBgR1kFjx0RJpRnAkiSphlDAlm5uRV2paOBTq4NuNkWvcYeaBmXsIsXd7KI6G1yYn3feeWFaspJaWizsTreMbKOYBiGBALqnzTvvvPWWmYZE0XK1hFh3Jt8g4c78JZdckrSVStdTtQg+UUOpVOYUta5KrS/mj65tjdV2oSsmjbOIbXruueeGbmqx1lgRAhc777xz6JpINkQ+kEKWRH7bkSFBQ5RuYE0hEEQ3oqLGPL+Pyy+/PPz/8ssvX2/fWH/99UMQhW0x99xzN/odzAfzEwtON6bS3zHF2lmXeXRxit9HnbumEBDJBw/IDmGfIPuruRmH7Md8xsCBA+s9T9YjgXi2PfXGItblLLPMEtYBGUXZABHZTqx7gqEEs7IFz1sa30Vw4aGHHmowDwRrCUIQTCwniBYLj1M7rlqxqye/hWxQkM+mSxpZaptuumnd82Su0ZU0W++Jf9PFtLXntRKNfS8DQBD8oRYdQZ88gk/ciKjEYostFs6l1K9joAHks6rIguL4RIAre9yh+HzsethSx9V8va+iGmeSmmYNLEmSagyZL9SnoftDdjQ4Lvyp07P33nuHrj9kTnDXncK0dPWicUqjK46oRBCMC3YaZ2Qc0IikmPJ9990XGoZ0HSoafaxajKRGdw3qj5DNQzcngmn8m4Y5XfiyWJYXX3wxdOei0UrGxrbbbtti2WE0lvls5omMJ+72M18UJOf5xkbIa02Vrqdq0SWQoAL7A0EE9hMCBQSHqMPEKGwxIEHjjcAD3XCo+UTmB/PIe7Ojt2XxGkE39jkCIjQc6Yp4xhlnNFnvhW47ZF9Qz4nlpxsX+ysNVwIvzEN2BMfY2Cwn8yjWiSLYQ1Fwuqyx7ASG6PZDNyu2RSw4T/ddupbSKO3Tp09d7Zz8PsujOfNT6e+Y3waZIzR42W5k3DDvQ4YMCfNOpgfz2RS+jwAkgTqOKwRpyLwii6ucwFspdHuk6DzF8ZlXBohgWaiXRtdLtn8eQSICLgTNsl302Icolh//vzXx+QTRYhH5iH2YdU8AgsBgOduUQAn1qVgm3ktXU7YT67xSBK2pp8SDLB0y5diH2Q8JuFLLLzu6HfsuNc122mmnUKON7yXoyu+nqMsr+xyjGNI1luXjt8o5pyUK1TeGATQI5lCDjWAy5x6O8Rzr2U84H/H/ZGSSLcs+yrZhX+I4df3119cbcbYcHItYj6wzsgDzGa2cB+m6fP7554fzAsdBjlmcGxi1tJxzQ7nH1YiBG1jn5QSdJRVIJUlSTXnvvfdoDacnnXRSved//PHH9Jprrkn79euXzj///OkUU0yRTjjhhOlss82WbrnllunTTz/d4HO23377dIEFFkinmmqqdIIJJkhnmWWWtG/fvunw4cPLnp8PP/wwzA+flffoo4+G16688sp6z//222/pcccdl84777xhHrt27Zputtlm6VtvvdXgM77//vt02223Taeddtq0U6dO4fP43MYcc8wxJadjPvOXOHzHnnvuGZZ/4oknThdZZJH0qquuKpz/xpY3+/lMl8fzK6+8coPn+fxq19Mcc8wRHkWK5jf/3LPPPpvusssuYX+YfPLJ0ymnnDJdeOGF01NPPTX95Zdf6r33+eefD8vBPjbNNNOkG264YfrOO+8UrtvstjjnnHPS7t27h2WZb7750ksvvbTk+sv7/fff09NPPz1dbLHF0kknnTSdbLLJwnph+oceeqjetJtuumk6ySSTpN98803alH/++Se955570r322itddNFFw37WuXPn8HeNNdZIr7vuuvTff/9tsP0be7DMWQcddFDYd998880m56fS3/HHH3+c7rfffmHeu3TpUjfvvXv3TgcPHpyW68Ybb0w32WSTdM455wy/gemmmy5dccUV05tuuqnedPE3kV/G7H6c/91999136YEHHhj2T44zM844Y7rjjjumn376aeG8XHTRReFzFlxwwQb7APPGa0899VRFvz3211K/jyLsz3wW22306NH1XltllVXCayeeeGLZ6+CJJ55Il1122bDv8np2Xir97YL9slevXuHz+L2yrdiPi/B7XX755dOJJpoo7Bu77757+sMPP4TvzB+P/vzzz3TfffdNZ5pppnS88cYrPC6Vs8zN2U9uu+22cOxlPouOlS+++GL4DbD/xP2I5TrttNPqbaPGjv9F51IeJ5xwQuE07HNHHnlkOtdcc4X54rh1xhlnpCNHjixcvmqOq3/88Uc69dRTp1tssUWj8y2ptE78pyiwJUmS2g53oMl4IWOqtYuJS+0NmSWMvHfhhRcmtYDsLTJfyG6UpCJkpZLVSkYr2aCSKmcAS5KkGvTKK6+E2itc8NKFRNL/IbDbvXv30LWoJWuENRdd8ejiSJc+uh1JUqm6XHRp51ghqXmsgSVJUg2ibgZ1O0oNjy6Nq6jnNrZHUGsMNW/++OOPtp4NSTWM+nMbbrhhg0LykipjBpYkSZIkSZJq2nhtPQOSJEmSJElSYwxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmmYAS5IkSZIkSTXNAJYkSZIkSZJqmgEsSZIkSZIk1bTObT0DklSNGWecMfnll1+S2Wef3RUpSZIkSW3gk08+SSabbLLkq6++arXvMANLUrtG8Oqvv/5q69mQpHHaDz/8EB6SJGnc9Ndff4W2WWsyA0tSuxYzr9588822nhVJkiRJGif17Nmz1b/DDCxJkiRJkiTVNANYkiRJqsqwYcPCQ5IkqbUYwJIkSVJVhg8fHh6SJEmtxQCWJEmSJEmSapoBLEmSJEmSJNU0A1iSJEmSJEmqaQawJEmSJEmSVNM6t/UMSJIkqX3r1q1bW8+CJEnq4AxgSZIkqSprrbWWa1CSJLUquxBKkiRJkiSpphnAkiRJUlXuv//+8JDUfnz00UdJp06d6h633nprW8+SWsArr7zidlWH1WECWI8++miy6aabJrPMMksy4YQTJtNMM00y33zzJZtvvnly/vnnJz/88EO96T/99NNk0KBByQ477JAssMACyXjjjRd+6I899lizvn/OOeesd6DgMeWUUyZLLbVU8t///jf5888/k/aGdVO0TuKyjssn+lVWWaVFP/f4448P++Drr79e99xff/2VDB06NNl7772TBRdcMJl00kmTSSaZJOyvAwYMSEaPHt3oZ959993JyiuvHPZDHszzPffcUzjtxx9/nJx33nmhC8iMM86YTDDBBMm0004b/n3XXXeVvRzvv/9+mEfW0RprrNHg9d9++y2ZaaaZknXWWafsz5SkvDRNk19++aVZD96rljdy5MjwkDq677//Ptltt92S6aabLplsssmSVVddNXnppZeafN+///6bXHXVVckGG2yQzDbbbOG9XN+deOKJye+//97oe5966qm69sU333zT4PXPP/882WKLLZKpp546XPNtuOGGFf0eWZ5rr7026dWrV6uug2z7Iv+Yf/75G0w7cODAsL5mmGGGMM2xxx5b1nesueaaYXquoatRzXLi7bffDtfSk08+edKlS5dk2223bXD9/sUXXyTbbLNNaLdOMcUUYRuyHa6++uomz1ellnOOOeYI2/OII46ocIml2tchamDR+D/mmGPC/9O4X3rppUMD/N13301uu+22cDdhySWXTJZZZpm69/zvf/9LDjjggBafF4JoHKQ44BDsePbZZ5Phw4eHYMKDDz4YgmtqWQRmHn/88eTDDz8MwbX2ZtSoUcnpp5+ebLbZZslCCy1U9zzL1KdPn/D/LNfaa68dglrsU2eccUZy/fXXh+AiJ7y8s88+O+zfnTt3DoGkiSaaKATD1ltvvRCoyp/ott566+Tpp58O0/E7IYjFhc8DDzwQHnzWmWee2eSycJL/448/Sr5OcOuQQw5JDjzwwOSRRx5JVltttQrXliQlya+//hrOtc3x888/h4aIJFWKINS6666bvPrqq8nBBx8cbvZxQ5xr0RdffDGZZ555Gj1u7bjjjuE6a4899kimn376cE1HG+bhhx8O10VFN4j5zn322ScctwjCFx3TCKxws56ABW2gs846K9zEJBOna9euTS7XsssuG4Iorb0OIq43L7vssnrPTTXVVA2m+89//hOuSRdbbLFwPVoO2n6s12pVu5yfffZZstJKK4XlOumkk8J2IqmBm9XDhg2raxMSkGRa2gGzzz57uNanzUigj7Ys7610OUnkYHvSTij1fqndStu54cOHp506dUonmGCC9Pbbb2/w+pdffpmefvrp6dtvv13v+TvvvDPdf//90+uvvz5977330t69exPiTh999NFmzcccc8wR3v/hhx/We/7ll19Op5pqqvDaeeedl7Yn22+/feE6GTFiRIP12ZZWXnnlwnXfGvgOvovvbCn77rtv+MyXXnqp3vMPP/xwusUWW6TPP/98vee///77tE+fPuE9yy67bIPPe+edd9Lxxx8/nWiiidJnnnmm7vl333037dq1a9q5c+f0/fffr/eeLbfcMuyfP/74Y73nhwwZEqbnux544IFGl+Oyyy4L0+22227h7+qrr1443a+//ppOPfXUaa9evdKW0KNHj/CQWtrPP/8c9mUe/L9qc9tU+nBbto4LLrggPJq7Hd0uag9uuummsL/ecsstdc99/fXX4bqmX79+jb73jz/+SJ9++ukGzx933HHhMx988MHC91144YXh+m2//fYL040ePbre66eeemp4ftiwYXXPcZ3OteDhhx9e1nXtlVdemY6NdRDbF5NNNllZ3xWv7VlmvvOYY45pdPrffvstnXPOOdPjjz8+TL/XXnulzVXtcu65557pJJNMkn788cd1z7GN+cyLL764yfevt956YT39/fffzV5O2nD5ZZBa09hol7X7LoREn8l2Im12o402avA6UXu6W+XTUklH5e7EVlttFSLordUlbtFFFw3ZJrjjjjuSjmDuuecuTPNV5bgbR4owKeTcXcoiO+mmm25qkM7NnZwrrrgi/D93Xuj+l3XOOeck//zzT7i7xx21aN55502OPPLI5O+//w7TZA0ePDhkZZG6nMWdp5122in8/4033thoFhl3p0hl7tevX6PLTBYWmYrcfXr55ZcbnVaSJKlW0KuD7mybbLJJ3XN0L6MdcueddzaahU7GzXLLLdfg+Y033riuu1nemDFjQhYSvU3oWlZqnihZwiPiOn311VdPbr755qSW1kEW16o//vhjo9NU2rPitNNOC5lTtP3aejnp7UPPB7KqInpFcD1eznZh2WknFJWhacnllNqbdh/Aiv2IOaDUqhiYoO4W6Od++eWXh/7p3bp1Cw16TkqkmRJIaKoeFSm0pArzHp6jfzaefPLJEIRYeOGFQ+oon8sJ7LDDDqubpgjBEAJtTE/Aj+/66quvSk5fqgbWG2+8EdJVWaaJJ544bBM+d//990++/PLLstcXAUmCJQRwWA4+i66h9HvnQJ6vR0VXO8w111z1+tKXo7nrrKXccsstIeW7qaBP3swzz1y3z9N3PivWuSIVOS8+R5fWci2yyCKF35O13377hfpWpFaXg8AxLrnkkrLnQ5IkqS1x423xxRcPdUuzuNnINep7771X8WfGa266qOUdddRR4dp89913L3wvQYzXXnstlErJY54++OCD5KeffkpqbR0wHbW6uClLbai99tordLGrxieffJKccsopyamnnhqu59tyOalJ9vXXX5fcLkU3cLmOpjsh7Rtubl955ZXhRnR+WVp6OaX2pt0HsCiCGKPcHChqUTxx0N8bHJh22WWXUBuLYBCBLAI9zz33XAhkNFag8IYbbgi1kOgDz1/utsRgDRkwBMY4mHHXhQd3NjjArbDCCoUnBgI1O++8c/LWW2+FABqP++67L9QR465PuegLzrxQl4ksHpaJPv704ybbhz7c5eBETD0mAhwvvPBCWC8U/GZ5jzvuuBC44wAP6p9sv/324e4IyOrh3/FRjuass5Y0ZMiQ8LfSovAE17777rvw/1zYZJ/nxIZ8Rlf8vXCBRNZWU3e9olgENPs9Wffee2/IFKPuQvfu3cv6TO5AUqOhVFF5SVL7QkOtqLEmdSTckGUwmrz4XGM3+0ohm4ZgDtf1WQSmLr744lCDdPzxxy98L9fqZAK19Dy15jpgOuqhEqDhhjW9YrgBSrFzegk010EHHRSuffv27Zu09XLGG/el3h+3WxbtJW5Oc0OeZALaUUWJDS29nFJ70+6LuBPsOPnkk0N2E41n0jwJPCyxxBIhq6bUAX9sitkuzA84OFGcj2BJNlOIIuRkHZ1wwgnhwFWUNnvppZeGg9mWW27Z4DWKQBIYyBZB5OC47777hkwXToBHH3103WsEzDhpMj2jOMaAB0EbAlCVZOmce+65IbOM4oQcWLPeeeedwsKMRShOzsmMgA5/Y9CE9Nn+/fuHYBOBLO48EIhhNBempQsb311pqnGl66ylkQFGofWiYFNjLrjggnCSp+g7J7ooBq/IJitVpHjWWWcNd3gIYmWLxhchIHbNNdeE/2efyCOwyHahkPyhhx5a9vyTVcfvgcAn+312GaRaxG+BgLxqQ1Eh43K5LVsH3WLi+h0b21FqC9xEjTek89c18fVKUGD7oYceCgGcfBdBrkUJavXu3bvR+UFLzlNrrwPabVkEYmKZC7rtNScwQzuGZIbnn38+qYXlLHe7ZF8niYGbAPQu4gY3bZv8d7TGckrtTbsPYNFdjUALo3oQxCLlkgc4EXAwIP22KALemugGRzDhwgsvDAEnAlUx/ZfRQOgDnUcjnoP3rrvuGpaJEUfyqElUFLxC/s4NODAyIh3dBOmvnQ3GMG/MJ92/sgEUMpsYqY66TOUONx67chYtV7n1sgjIEFAj8MI6i5lVsW4A80TGDoElTvj5lN7mqHSdtSQyBjk5sd0rSQEm7Zghl0GmWFbMGJt00klLvj8GtspJKaeOFtuWu0CxRkMWdRkIhHFCrXSETfYLAliMkFNOAKtnz56Fz5MeT102qTUR+FXH4LaU1BhumuZ7IXDzmZviXK8V1T7iJi4quZ4je53rKHpC7Lnnng1ee+aZZ0J5jsbE72upeRrb6yBitGvaawTzKg1g0X4g2LftttvWqwNWrWqWsznbZY455ggP0H5lZG/aVfRiYdrWWk6pvWn3ASyQyTRixIgQ3Bg6dGgoDk3aLXcBCdIQqX7iiSdClkhrK2qI07AnILLiiivWe/6pp54KNa3oJ83BjGBRTDl9//33Cz+fNNvG8FkEv8h6oosYXfLiPOQ/k+wfFJ0oevToEWofEVwoBxlvdD2kDzvBFbLgyCyqxEsvvRQygygEng1eRRy8+R62M8vSUtuzknXWkmKXV7KlykXAiyxD9hdqixUF4FoKwTEuoKhNQNfQfF0xusCSebfddttV3AUSfG42+ClJar9iLcfGBvyQ2gMCR5SsyCJbnCx/bogX1XWNz1GjtBz0xOD6iRvTF110UWGJi8033zxci1J6JJvdyA17Akx8F9dS3HhtiXka2+sgf43PDf5KypdE9BQgyEN3y7iuIm7W8tz000/f6M3dItUsZ0ycKPX+uN0aQ91aet7Qhu3Tp0+rLafU3nSIABY4wJMhErNEOMiTxUNdHgIFFOrmZNHaqMNEBhONff6SZcI8ZQ9yFO0mCPHII4+U/JxS2THZkSzy6O5GTatyu7nEvtsx2p/HSarcABYn2hiQ44THslN4kBMz3SHL6UIYD8Zsp6aKsBPoaokAVqXrrCWxHyA/8l9j+wT1wFhPXNTQ3TKP9Y5ssftSXTYa+97rrrsuOfzww0O2FgFDMh2zuAtEpiBZjnTdbA7qPVTS3eTNN9+sKDNLkjT2VHIzRqpl3MDNtxliSQtqs3IDmJud2Z4AdOkicBC70jaGaWkb0F2M0eiKbvgSpKLuLY88CovHm8zMA+UguKlY9D1cv5V7nTk210HRNS7X9s0ZlIseL1zHL7/88g1eI+jD4/bbby8crb4x1SznLLPMEpalaLuQaMFnNyV2H4zthdZaTqm96TABrDwa1nR/InBE7R66ONGob+2odDl1mKgVRPBq5ZVXDvWc6KrH/JKWSwYZUfZSXfdiv+k86llRe4pAEUUAyYjhRBOj+6yHSkYCbE4wgmV6+umnQzYTgSz+zcmPvu6cAOaZZ55GPyNmPlHLrOjgnMVdmmq19TqLQb1yuvKRcUX2HVlq1EIgwFTUhTIGOCnwTqCqqA7WZ5991mjgkn73dMmlyPptt90Wug8WfQYXTqwvgmlZMSBF98CYmcX+kBdPyKWGhZZqCft8qbpyGvs4vjW3K6DbsnVce+214W8cYKS1t6PUmsHYopIYMSuGOk1cH8WRnQm8MKr0+uuvXy+rhhIHyJY5ePvtt8PNXdoKXG+V6oZGICKPG/NkxhOoyP5umA9uxhIsiQMpkKnDdfiAAQNqah1wPUsQJh9Uo/4vbR8KuVeKniRFASGChNz45YYrg1NVqtptTVIDZW0IRsZBxx5++OEweiFdJiN6IhQF7qj7yw19ApatuZxSe9NhA1gRRdHxzz//hIZ1LaRVclIiWHXXXXfVZaHkR3xrzmdi4MCBDUbgI4Ifh+jNp7eSzUMNowUWWKDB6zxfCQ6ydB3kATLf6OZGdwJqe3GXqTHxZEzWGsXZW1tz1llLIs0XTaVLk+1E3TOCQBSc50Raqt4UwSCCWNyloVZW3BYRJ1FOvgSv8vseHn/88RCQ4iKCu36NFQ4F66jUeuL3xueVEhs5zbnbJo1t/LYMYNUOAuzN5bZsHXHQnEpuSlSzHaW2QCCDG3vc6GMEbwYUogA77QxuSudLnGR7GHDDkpvUXP/QcyE/EjPBD3ovoCiLJvaKoHwE3xsxmA5dzQiMEbDid0UPA8px5AdWaut1wDUjdXfpchxr5D7wwANhRGuCV/kBgwiM0x6JPQvoThfrwFILiutZPqdUvV1Ku+TXJTdXuT5tqs5vNcsJegER7KJnCvWGqVN7+umnh4w5PjOiHUICAMvPNTztAsrfMBo79ZDjCN+VLqfUUbX7ABYHn8a6m1EbCzT4swf7tsSJi+BBUQChqSBPY5+JojuZHDyLDtLU5OJAy3cyGl8W9aDK7T7YWIDm2GOPDQGspopQgoKEZCVxUuHgHWskNSUGcyoderc566wlsX7IYCKoVCo7kHngJEewk7suXOw01YjmAobab9w1ygeweA7cOcoju4ssLwpOUsCeO0elcOew1PqJ3Ug5mVOMsxTuQqKcNGpJkqRaCNQSbCEARR1Qbnhy/cqN16ZKW3z77bfhmg9kTOVxMzUGsCpBNhPXXmT1ENyhRwNBmrPOOqtVbhJWsw4IcK+33nqhhwbZSQSDCNAwOBPBt3zvArKQsjdD6VHDA1zjlupN0BgCSbE7ZGstJ8i6Yt4PPPDAsL1pr3CNTgmQbPYWz5HBxbU32VhxpO4rr7yywQ12Sf/XQG7XjjzyyHTAgAHpiBEjGrz22Wefpb169aKVnW622WaNfk6fPn3CdI8++miz5mOOOeYI7//www+bnLZnz55h2sGDB9d7/swzzwzP89h+++3rvca/G5u/008/Pby+/vrrp3/++Wfd82+++WY644wz1n1u1tNPPx2em3rqqdNXXnml7vmff/45XWONNerek//OuKxZF154YTpy5MgG83XWWWeFaXv37p2WY+DAgWH6lVdeOf3ggw8Kt+k111xTuG6GDBmSVqI564ztG+cvb7755gsP5rFcm2++efi8p556qvD1fffdN7w+//zzp19//XVZn/nOO++k448/fjrRRBOlzz77bN3z7733Xtq1a9e0c+fO6fvvv9/gPdNNN134rnPPPTetBvsLn7P66quXnOa3335LJ5hggnS22WZLq9WjR4/wkFoax8J4HOD/VZvbptKH27J1XHDBBeHR3O3odpHGvnhde95556WjR49O//jjjw69GX788cdwHXz++eenHdnff/8dtucdd9wRtu8tt9zS1rOkcUSPsdAua/cZWETRqV9E7SmK6TF6HpFralxQZI9+1kT2GQUwi9pGseB7zDiKabgxM4qIOEO6tjSKY2+zzTahL/MFF1wQMoBeffXVMA/cPeGOSaXI0iGiT/0p7gpwh4AsJiL/pJRSMDDfJZDuaNztYN0xPd0tYwYUdwbI0uHzysEIKgwBzPqnOyIFKVkelovtcfTRR5f1Odyh4H2kDPM5pBmTFstoK/TnJ4WXuxKkDUdkDXEXZ6uttgpd3mJtqcsuu6zF11ljmD9UUhCefYxsL+6c5et+3XnnneGOT7yLwx2gUussm1LMspCizB0fsuwY1ZG7PtRX4+4RnxnTkSP2xdgHn9pVFN7P4zuK7hg2B6nSrCeWX6pVZDu2diam1FE01eW8iL8xqTbQVY0H16Sx3lNHRBdECqxTL6oje/3110MbSuqQ0naO6PK1116bbrPNNulCCy1Ul2HSpUuXdPnll09PO+20wrt68Y5DY498FlRLZWDhnnvuSZdZZpl0iimmCBlQZDw99thjddkrlWZg4dNPP0232mqrdJZZZkknnnjidIEFFkhPOeWUEIUvypqKLr300nThhRcOGTvTTz99WJeff/55ye8s+qy77ror3WmnnUJ2Gcsz6aSTpvPOO2+6yy67hOyeSt15553puuuuG+aHTB3+LrHEEukhhxySvvjii4WZXkR7WYaizKmWWmeNZWDF7y13H8Cvv/6aTjXVVIWR6iuvvLKsbIJS+wTbZMUVV0wnn3zy8OD/77777sJp47I29iha5uZmYLGvME3RtqyUGVjSuOfff/8N5/bmPHivJOn/MuIffPDBuseoUaNcLR3ATz/95HZVmxgb7bJO/Ketg2jSuIysOzIEGT1miSWWSDo6ssAY4ZGMSbIkq9WzZ8/w980332yBuZMkSZIk1WK7rH6lPEljHV1KJ5988uTkk08eJ9Y+3U0ZoXBcWV5JGhcwOhcPSZKk1mIAS2pjjEZIfavbbrst9Fnv6NlXp512WhgCmpprkiRJkiSVwwCWVAMocs+wxwsttFDSkU0yySRhAAWGJZYkSZIkqVwGsCRJkiRJklTTDGBJkiRJkiSpphnAkiRJkiRJUk3r3NYzIEmSpPatb9++bT0LkiSpgzOAJUmSpKp06dLFNShJklqVXQglSZJUlTFjxoSHJElSazGAJUmSpKoMHjw4PCRJklqLASxJkiRJkiTVNANYkiRJkiRJqmkGsCRJkiRJklTTDGBJkiRJkiSpphnAkiRJkiRJUk3r3NYzIEmSpPatf//+bT0LkiSpgzMDS5IkSZIkSTXNAJYkSZKqMmLEiPCQJElqLXYhlCRJUlWGDh0a/nbv3t01KUmSWoUZWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNs4i7JEmSqjLNNNO4BiVJUqsygCVJkqSq9OvXzzUoSZJalV0IJUmSJEmSVNMMYEmSJKkqw4YNCw9JkqTWYgBLkiRJVRk+fHh4SJIktRYDWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJN69zWMyBJkqT2rVu3bm09C5IkqYMzgCVJkqSqrLXWWq5BSZLUquxCKEmSJEmSpJpmAEuSJElVuf/++8NDkiSptdiFUJIkSVUZOXKka1CSJLUqM7AkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmmYRd0mSJFVlySWXdA1KkqRWZQBLkiRJVenVq5drUJIktSq7EEqSJEmSJKmmGcCSJElSVW688cbwkCRJai12IZQkSVJVvvvuO9egJElqVWZgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmmYAS5IkSZIkSTXNIu6SJEmqSu/evV2DkiSpVRnAkiRJUlW6d+/uGpQkSa3KLoSSJEmSJEmqaQawJEmSVJVBgwaFhyRJUmsxgCVJkiRJkqSaZgBLkiRJkiRJNc0AliRJkiRJkmqaASxJkiRJkiTVNANYkiRJkiRJqmmd23oGJEmS1L717du3rWdBkiR1cAawJEmSVJUuXbq4BiVJUquyC6EkSZKqMmbMmPCQJElqLQawJEmSVJXBgweHhyRJUmsxgCVJkiRJkqSaZgBLkiRJkiRJNc0AliRJkiRJkmqaASxJkiRJkiTVNANYkiRJkiRJqmmd23oGJEmS1L7179+/rWdBkiR1cGZgSZIkSZIkqaYZwJIkSVJVRowYER6SJEmtxS6EkiRJqsrQoUPD3+7du7smJUlSqzADS5IkSZIkSTXNAJYkSZIkSZJqmgEsSZIkSZIk1TQDWJIkSZIkSappFnGXJElSVaaZZhrXoCRJalUGsCRJklSVfv36uQYlSVKrsguhJEmSJEmSapoBLEmSJFVl2LBh4SFJktRaDGBJkiSpKsOHDw8PSZKk1mIAS5IkSZIkSTXNAJYkSZIkdXD//vtvsuCCCyYDBw5s61nRWHTssccmnTp1atHPXGWVVcIjeuutt5LOnTsnb7zxRot+jzTOBLAeffTRZNNNN01mmWWWZMIJJwzDO88333zJ5ptvnpx//vnJDz/8UO9g/uSTTyaHHHJIssQSSyRTTDFFMtFEEyVzzz13ssceeyQffvhhxd8/55xzhgNF9jH++OMn008/fbL22msn99xzT9IWrrrqqjAvHMjU/BMA67Gl/P3332Hf7NWrV73nR40alVx++eXJxhtvnMw666xhP5566qmTlVdeObn66quTNE1LfuZvv/2WHH300cm8886bTDzxxMnMM8+c7LTTTsnnn3/eYNrm7v+PPfZYg308+1hmmWUavOeOO+4Ir918883NWleSJEljwx9//JEceuih4RpqkkkmSZZeeunkwQcfLOu97777bnLAAQckyy23XLgO49rno48+qvhaqrFA06677hqmWW+99cpephtvvDH59NNPk7333jtpC0899VRoB9E+Y73MPvvsyfrrr5/ccMMN9aZrbJ1wbVoLfv3119AuYBsqSXr06JGsu+66of0htabOSQd0/PHHJ8ccc0z4/wUWWCCccCaYYIJwMrntttuSW2+9NVlyySXrGtgjR45MVlpppfD/M844Y7LaaquFYBPFSC+++OJwUL333nuTFVZYoeJ5IYg2+eST1x3o3n777eT+++8Pj5NPPjk57LDDWnTZxzVcDMw111whqNNeTyDsY++9916DoOZBBx2UXH/99eFuBvsr+x8BKE7+TzzxRDJkyJBk8ODBYV/N+v3338M+/NxzzyUzzTRTsuGGG4b1dOWVV4b38Hy3bt3qpq92/yfQVfQaz+cxL4ssskhyxBFHhMAcv0tJkjoSbkBddtllyeOPP5789NNP4cYQmQo777xzMsMMM7T17KlMO+ywQ2gz7L///sk888wTbl6us8464SZ5U22CZ599Njn33HNDo562yCuvvFI4Ha9de+21DZ7nuaFDhya9e/cufB/15pgfgkCVOP3005O+ffsmU001VTK23XLLLcmWW26ZLLroosl+++0Xkgu4Sco17aWXXppstdVW9aZfc801k+22267B53BzthbQrjvuuOPC/2czkcZlBBf5jXzwwQeF7QCpRaQdzPDhw9NOnTqlE0wwQXr77bc3eP3LL79MTz/99PTtt9+ue27EiBHpmmuumT788MPpv//+W/f877//nu6www6kuaSzzz57+ueff5Y9H3PMMUd434cfftjgtQsuuCC8xjx+9dVX6dh05ZVXhu8+5phj0o6A9cvyrLzyymPl+1hvfB/rsSWwj00//fTpwgsv3OC1fffdNx04cGD69ddf13t+2LBh6ZRTThnm4+KLL27wviOPPDK8tuyyy6Y//fRT3fNnnHFG4bpq7v7/6KOPhte23377ipb5xhtvDO8bNGhQ2hJ69OgRHpKktnPfffeFx7js119/TXfddddwfcd5Lv/g+d122y397bff2npW1YTnn38+bDPaDBHbbe655w7XV0359ttv0x9//DH8P59Rqk1QSvfu3dN55pmn8DWu1ZiHnXbaKbQ31l133bI+86WXXgrz8dBDD6VtgWu1nj17pn/88UeD10aNGlXv38znXnvtlday0aNHt5s2VWy/tCTaE/k2BW2FaaaZJj3qqKNa9LvUfvQYC+2yDteFkAwrjntbbLFFstFGGzV4nQyTAQMGJPPPP3/dc0SIuctB5km2fzDdqAYNGhTuUnzyySfJM8880yLz2L9//2S22WZL/vrrr3CHRuMu7ux9/fXXhXeYzjnnnJCpNN1009V7fqmllqrL3CMVPOvPP/8MXWRxwQUX1GX/4cADD0wWXnjhcEf4xRdfbLP9nyws7kZfdNFFLfJ5kqS2t9Zaa4XHuIqu+3SNIpOE67tll102ufDCC0PXef6S9c/zl1xySVhPTK/avj4jG3233Xare45sJ7LouHanG15junTpEq51moMM+BEjRiRbb7114etkZ1FnqNI6VuyLlKOIWff58hh8J1lnlKvg2m/HHXcMWUb5shcnnHBCuHbkOpGSKVyr0t2yKWTlcA3LPORRYqU5mL933nkn+eabb5qcliwp6n9Rq2nVVVdNJp100tCV8bTTTmswLdfmMWOS7U7vAcp3RPRsiNfnZGHF7o2NlWiJZVzIONt9992Trl27JlNOOWVoA3z33XcNpucavGfPnmE90411r732Sr7//vvCzDZKgNDNddppp0222WabwpIhRa677rq697LPkp1XtG9z3GKbMx0lTyg9UoSeFaznO++8s6zvl5qjwwWwRo8eHf7mG/3NxQ81pqp+8cUXSUuJB2pOBHk8x8UOFz8c2JgH0m3PPvvswunxyy+/JKeeemroasZ7JptsshCk42BH97RynHHGGcl4440X3pc9eMW+8hy4OIhzgKO/fVFAI/bl5wT41VdfJbvsskuo30Q3OOa/HGPGjEkOP/zwkHbNsnMSJbhC97csThJ0HwRBmWz/eL6/KXS1o8YUARW61PFdnLQ5sdM1b2ygiwHzywmjEpxIi/bJp59+OtR3Y1sttthiDd632Wabhb933313m+3/fCbB5ddeey15/vnnW+QzJUlqS3SJ4lqEazBuCnGNRHcarjH4S9CD53md6eiWptr18ssvh+sftldWrFdaqktgS6B8BIoCWHRJpS4XQSNuyleCfZIATqnyDdz85/MpccL/E3CJXeQiruupcbT44osnZ511VijhwfTlXMfOMcccycMPP5x89tlnZc0v1+kEpvIPbtZmg310w4w3b5tCoIgAMtfRtHto87A+77vvvrppCC4ThCFQyDag2yVtEdoW3FyO7UzaaqAkBtPy2GSTTZqcB9pUlJShHUPwiu3NdXG2ti2v0YYjcMV8UpKGsh50KSUQHrGN2FYEW9kO1EUjmYMurkXBriwCoHw/3WPPPPPMcExi+9AOyr6XthIBN/Y3gn3LL798ssEGG5QM4hIQI8D6448/NrkupGZJO5jjjz8+pEjONttsDdJRm+Off/4JXbz4zEceeaRFuhD+8MMP6RRTTBFef+ONNxqkn6+66qrhtS5duoSuXeuvv37dPGywwQZhnrK++OKLkJLL66RtMv1mm22WLr744ul4442XnnXWWU12ITz88MPD80suuWRIiY2eeeaZ8Jm8Nt9886WbbLJJuuKKK6adO3dOxx9//HTw4MGF3crWWWeddNZZZ01nnHHGMC/rrbdeYXe3vHfffTdsOz5jzjnnTDfccMN0tdVWSyeddNIGqdx0Ed10003D8zPMMEPoyhYfl156aZPfRTdS3jvzzDOHdb7llluGVNiY+l+UEtySXQjZD1iHpVLEG3PeeeeF+VhppZXqPc+25vnNN9+88H1DhgwJr2+88cZV7/9xWy+33HLpYYcdFrpNsB/dc889DfbRvMsvvzy8tyVSjO1CKEltb1zuQkh5injtMHTo0Ean5fW2KiOh8nFdzfVn3ptvvhm230UXXVT2Z1XShfDvv/8O17S9evUqfH3AgAHpXHPNFco8oJIuhFyXc91c6tqWLolZXCt27dq17t+vvPJKmG6XXXZpME/ltJPitd+EE04Yrru5BnzyyScLrxmLuuDGB6Uo8tei5XTj4xqfaa+55pq65+jOSFslu17OPvvsMN11111Xr2sc3TYnn3zyuq6hlXYhjG2wJZZYol5ZjtNOOy08f+edd4Z/UzqEddS7d+966+b8888P011xxRV188Q1+oILLlivW3K81j/66KNLdiH86KOPQhuEUiVZr7/+emjjxefjdyy66KL1un5ecsklJUu43HDDDeE1uuFq3NNjLHQh7HABrA8++CCdZJJJwg+HIFEMZtDvm5NCpTh48VnTTTdd3cmiuQEsglMvvvhiOCDFYFRe//79w2sEU77//vu65zlYEhTitQsvvLDee1ZfffXw/BZbbFGv5hH4/ldffbVkAIsDI/UYeI6TSTwoxwDLTDPNFA5w2YM4XnjhhRDY4kCerdEUTyQxSFJJnQe2z0ILLRTey8E8e9B+//33wwmbeeHg2hI1sL755pv0wQcfrFf3CSNHjgzBM4J/+YuNlgxgcaHPZ2211VYVvY+TyQILLBDeS12rrAMOOCA8z98i8eKD4Ga1+392W+cfbMf33nuv5OeyDYsCcM1hAEuS2h71PXmMi0488cRwTltmmWXKmn7ppZcO0+cbj6od3bp1S9dee+3CdgbbLntzuCUDWA888ECY9pxzzim8yUvg89Zbb617rpIAFu2jfPApe21LjdWsM888MzxPewAnnXRS+Pdbb73VIIDL8wcddFCT83D//feHdlC2Thzr+umnn643Hc9zE5vr9PyjuYFf2gq0W/LX/bTHFltssbp/M38EtfKBtVjD9e67764qgJW/oU/bjaDR7rvvXi8AdO+999abjgASNXBjsI0kg1I1Zeeff/4QKCsVwGLbUjOa9hXLkX3QxlhjjTXqfUc+YEtbZKqppipsf8X2DTe0Ne7pYQ2sytEVjO5R1JgiDZb+yqRTkupKv2DqT3355ZdlfRapkTHFm5EN6YNcKbq4xW5t9LUmrZLRS0gNvfnmmxv0t6Z2AvPOiHHZEULoR08KJ/3GY8pqTJ0l3ZMuiXRHy9Y8An3TqXtUhBRcUn7p10zqKumz2f76V1xxRVhXrIN8GjNdFY866qjk559/Dv2n81hX5513XkWjo7DdXn/99ZAme/DBB4fujFH37t1DCu0///wT1lFLoO/5GmusUa/uU9xmRx55ZPLvv/+W3dWuOehCh/nmm6+i97HeST1mPvNDCbM9wL5WhK6l4LdR7f7P/sl2YlTDb7/9NjzYF6nzwXYkzZnujEViDbpKUvCpA1D0oKaCJElthS6B2H777cuaPpY5aK+jJ48LKHdQVNeJbm3x9dZAdzK6gzFaX1E31eWWWy5cJzdXtpta3uyzz17v34wSiFif6eOPPw7X5lyTZ9G1jBIcvN6UPn36JA888EDookYtKLrJ8T5Kk9AOyqIECdfp+Uc1I3nymfnrfpYzW4OK+aFbXbYdAroqxterwWdn0XZj1HDqamU/P98+oA1IOze+Xmq6eJ3d2Hy+//77YV9gXugOmX3QxojbIn5Gfp7phpod0bxoH8uvZ6mldE46oNVXXz0UIrznnntCvQGCPAQLOFgS/Pnf//4XDpqNBQ6oKUU/ZvpaE9zJBwrKxUkmBpWoX0W/b+og0NeYQNVOO+1UNy0XMvRrpm920YmREwQHEIID9M9mmoceeii81q9fv4qKRbJ8nCwefPDBcCFF8IsTZhbrDqX6c6+44orhL+s3j4AhhRErUc33VeOpp54K656Ch1yYcOCNQU4O8K0lnhziBUI5qM1F/3MCgzfccEPJQFW1ytn/qbGVr7NFrTLWJ8UxKfBIAUrqmeVRE439lf7xBFKLCnpKktQexJtCNELLEWsXlXMzSW2DbVlUCDteH1KbqKVxbX/77bcXBmkeeeSR5P777w/1jWKgI7YteB/PUaM2X7Mrf+O2qFh4lG8HlAp6tURggutXrut5kGBArS1upJcbBG6ucpexo+MmPduRdV60TvIJEZWI+xjbVWoNHTKABRrEFNXjAYJXNP4pekjggAJ6BG+KEETafPPNk+HDh4cieAQKmuu///1vyILK4iRDgTxGt+A1Gv3xeZBh1FSWEYXOCRDFAnoU7a5ELAi/zjrrhEyropNRnB+K9TWmaOSP/F2ccsTvI9ur1Mgrpb6vOcgOIkjDRUEprXlxGbOTyg08Mp8EG7kjxOiDZDqVOuHkR43JBqaa+s5q939OhBTEJIDFXbaiABa4yGL98tssZ/SZN998s/B5srAkSWor8ZxaboY/g9xk36faw+BJ9JjgRls2KBQHn+H1lnbXXXeF66Kia2BGgy51k5dAG1n5FFVvbHAAsnI+/PDDZs8fRdgJfHBzN2YjYdSoUeFajtebg14dlfx+WhvLQeIDy5rNwmK0w/h6NYE81h83erO9J1h22mTZz3/33XfrZTlxw5ftR4AzP11sS0Y819j2oN1I0I79Jg7WVCR+BvOc/Q7aCsxLHFQqi+dZb419rlSNDhvAyiO1lSwS7pgwIgwnJRr5+QwWDlZE/4lIc3KiC1lLpwkTtKKBTxDt3HPPrTsg8N3ge4sOCFnN6c6YxVDPZKGR9URGWhydLivOD6/FrmeNdQfLqqTrYP77yEBrLD24pSL6bAOCQoygwp0fRmZhPyEAw3ohzbk178jELqLlBMleeOGFsN9y8qIrKVlRRWLgsNQIL/H5Uie1ltr/Y6pxYxcjMYDHOpckqb3iOoKbopStKCdjn5HDwEhnqk1c+3ITmjIbAwYMCM/RpZASH0svvXToRZENLtGmKLoerkTMrI8337NoK5CdlbfbbruFazpKXyy00EKNfj6jm59yyilhOZrTjiDAQiIAN8EZES+iVwnWXXfdRt9PmQl6yeTde++9zSqp0VpYTtoBN910U+jhAm76UxqFG8X83hHbkE2N9pfHPrXjjjvWjQZJ7yA+n7YZCFCRiEEbkTZRDJRx/c+1c1zPBP64AXzRRReFHj1xm3INTzdARosshUAoN5hp/1AKJhuMo+1DogQZe3wH3Qr5DuY59pjgGFZquV988cVwczlbCkdqSeNMACuKwSJqKfHDywew9tlnn5DdQtSY7JHWalwT8c53UaNfNsh64SBZjngCrbQOEF38ONlRp4iDM5Hy/F0d5ocI/mGHHRZqd7W2uPwM0VtN//5ycSFAsIo7XvmU65EjR7b698esI04SjXnrrbfCSY07NNxd4wRSSgx8vvTSS4Wvx+dL1UVrqf0/pg+XCnxy54blYb3bfVCS2r+YRTEuIqOehiA1IQlkrbnmmiWn5XWyeGi88j7VJoJUZKPTyKfnBnWfCFDSW4BAQtZ2220X6qBlb3oSaIjX8k8//XT4e/7554frKh7cxM7iWpDAQ7b0SP4GZVHvBjKuuOlb6sZmFjdCTzjhhDCvXP9XimtMbnISgKENRSCHsh6sF74/m1VU6vtp/6y//vohA4heAZRC4WbpUkstFZ7Peu+99wrr7LK88TdGCRC+95hjjgn1hVsCQUECdPR6IBhD4sGtt94atiPBu5g5yQ3eHj16hEAX18104eRmOI/GcDOaQN4WW2wR2lmU26Dtt8EGG4TXCRjF4BIBLJ6P07GettlmmzAdx5BTTz01tAvYFrTnyIY755xzwjwfcMABJeeB9X/iiSeG72GfZvuxXGRP0T5iHRC45TuYbvfddw9taGqzMQ2B3KIaWFzfs39Rc1pqNWkHkx9ZIu/ll1+uG8I1OxwojjzyyPDa7LPPnn788cdVzUfRKIRZ5513Xng9O0zuZ599FkbZYwS87PCqjWGIUj6HIU7zIxAWyY9CyOgSjNbIaCB33HFHvWlPOeWUMC3rpVxxZDpGf6zU4MGDw3u33nrrst/z+eefh/csv/zyFX8fy8xIikUYkbFoOVpyFEJGYuGz+vXrV3Ia9p9ZZpklTHfsscc2+Zns04wKwvTs63kLL7xweG348OENXmvJ/f/ggw8On7XzzjsXvv7aa685CqEkqcPYddddw3mNUcKGDh1aOA3P8zrTMQK0ahsjaQ8YMCCMSDfRRBOlSy21VLh2y2MktnyTKo6SXfSgjZDHKG+8dtddd1U0j5WMQhivA/PXZvHalhHoitoM2bbMX3/9lR533HFhZHCuo2ebbbb08MMPL2ukdkbx69u3bzr33HOHEREnnnjiMGIZ15/ZUdBRat3lRx5nRMCiUfKK8L6ePXs2eJ5r/fw2GTVqVLrjjjum0047bWgzMrp20bU/7ShG+2OapkYkjOvz8ccfD7//OJo77Z5vv/22wfTnn39+GE2Q9TzDDDOke+65Z/rdd981mO6mm24Koyiyj3bp0iV8Hm3KrPwohNH//ve/dIUVVkgnm2yy8OD79tprrzDiZRYjHbLN+Y4ll1wyfeKJJ8L6zI9CGEcgZHRDjZt6jIVRCDtcAIuDICebESNGNHiNHzMBI35Ym222WeFQsZyk3nvvvarno7EAFs9xwC8KSsQLIIZILRomlgNCdvjcbLCFQMjPP//c4LsIFpQKYIGhazmAcvDNnjg5SBIY48DJkK/54WQ5iXEif/3111skgMXnscPz/uOPP77ByZDg5FNPPRUe2YAN88d2+/vvvyv6Pk5ifBeBs6J9oZIA1m233ZbON9986bbbblv293OyJmDZvXv3wtc5ec4zzzxlD02cD0Qtt9xy9faHM844o8GJv5r9nyGkP/nkkwbbiIsIhgNmeN6iQBkuu+yy8H1HHXVU2h4OlJIkNebXX3+tC2TwWGaZZdILL7wwvf3228PfpZdeul4DnOCINLZdc8014cZ1USCkPeKG6ayzzlpWAK2txTbYCy+8kHZUG264YbrRRhu19WyoDY2NdlmH60JItyRSJ+m3TjonqZ3UY6L2DynbpDaSBkwKaPTKK68kBx10UPh/UlsHDhxY+Nl0bSPFsxKkXxaNQkj6aK9eveq+N2LeSeWkLhWjjVCHiJRh0mzpSsboiqTgZrvYXXvttSEVla5fdPtiHukHTbdClu2MM85otF88Q/KStkyaKn3+GeGE/tWkON95550hpZfUUVJISYtl1DwKkNIdjRRiUk2bSpctByPT3XHHHaH2FP22SbWmqxtd7SjczrKQxk03ulhYnu5nzDfpx6Q20zWS53i9sa52IG2WNNy+ffsmF1xwQejC+Oqrr4YijaTd8j3lIlWc9N44slA5SNVl9BXSn9kvYhfKiHVOF1O6ubL8cdjtfD0w9vWs//znPyEl+5lnngm1qPgOhsFl/yctmaL9Wc3d//kNsX+zznkfIzgyQmYs3kjf/VJdT+PQ4U3VS5AktQ9cgyDWjBnX0J2Iaym6dNG9hu6EPLLojsO1Cdd6zakVKlWLAvF0O+O6l1Ii7R01jY866qiqawOretTdGjJkSGhXSK0q7WBIf7322mvTbbbZJqR7du3aNWSDkFJJN7PTTjutQZZSzBpq6lFJt7GYgZV9kJFC6jh35ch4yXdhjMgkuvrqq9PVVlstzDcZRjPPPHO67LLLhrTdfFpnzOYha4nUYNJyyagiDXTvvfeul8ZZlIEVkdJK+ijpoaSARl9++WV6yCGHhIylSSedNDxI/yXKftVVV9XrulhNBlb0/fffpyeeeGK6+OKLh+UgxZhulX369EkvuOCCBinOZCqR+UT2EBlNlXz/PffcE7YHd6OmnnrqdI011kgfe+yxkstRKgMrrtei7KbGXH/99eF97Jd52Tu5laShxzvBZDexncisY93ssMMO6aefftpg2ubu/+eee2663nrrhZRi9hu+h/nhtzds2LCSy8y8sV3ZV1uCGViS1PY4P/NQGjLoBw4cmK655prhGoO//Lsos17SuGFcyMCSeoyFDKxO/Kd1Q2SSSmEkGEaPIcuMIXvHlbv0W221VShGueeee1b9eYx0gjfffLMF5k6S1Bwc02HxXklqiJH7yMBkZPFxedALdWw9x0K7bLxW+2RJTSLlme6SdL0j7bajI15O6jqjnzj6kiRJksYFlALhOtjglVQdA1hSG2OoWuq1MVxuR0dNNeqMnXTSSaFWmSRJkiRJ5ehwRdyl9obi9RSAHxdstNFG4e6TJEmSJEmVMIAlSZKkqvTu3ds1KEmSWpUBLEmSJFWle/furkFJktSqrIElSZIkSZKkmmYAS5IkSVUZNGhQeEiSJLUWA1iSJEmSJEmqaQawJEmSJEmSVNMMYEmSJEmSJKmmGcCSJEmSJElSTTOAJUmSJEmSpJrWua1nQJIkSe1b375923oWJElSB2cAS5IkSVXp0qWLa1CSJLUquxBKkiSpKmPGjAkPSZKk1mIAS5IkSVUZPHhweEiSJLUWA1iSJEmSJEmqaQawJEmSJEmSVNMMYEmSJEmSJKmmGcCSJEmSJElSTTOAJUmSJEmSpJrWua1nQJIkSe1b//7923oWJElSB2cGliRJkiRJkmqaASxJkiRVZcSIEeEhSZLUWuxCKEmSpKoMHTo0/O3evbtrUpIktQozsCRJkiRJklTTDGBJkiRJkiSpphnAkiRJkiRJUk0zgCVJkiRJkqSaZhF3SZIkVWWaaaZxDUqSpFZlAEuSJElV6devn2tQkiS1KrsQSpIkSZIkqaYZwJIkSVJVhg0bFh6SJEmtxQCWJEmSqjJ8+PDwkCRJai0GsCRJkiRJklTTDGBJkiRJkiSpphnAkiRJkiRJUk0zgCVJkiRJkqSa1rmtZ0CSJEntW7du3dp6FiRJUgdnAEuSJElVWWuttVyDkiSpVdmFUJIkSZIkSTXNAJYkSZKqcv/994eHJElSa7ELoSRJkqoycuRI16AkSWpVZmBJkiRJkiSpphnAkiRJkiRJUk0zgCVJkiRJkqSaZgBLkiRJkiRJNc0i7pIkSarKkksu6RqUJEmtygCWJEmSqtKrVy/XoCRJalV2IZQkSZIkSVJNM4AlSZKkqtx4443hIUmS1FrsQihJkqSqfPfdd65BSZLUqszAkiRJkiRJUk0zgCVJkiRJkqSaZgBLkiRJkiRJNc0AliRJkiRJkmqaRdwlSZJUld69e7sGJUlSqzKAJUmSpKp0797dNShJklqVXQglSZIkSZJU0wxgSZIkqSqDBg0KD0mSpNZiAEuSJEmSJEk1zQCWJEmSJEmSapoBLEmSJEmSJNU0A1iSJEmSJEmqaQawJEmSJEmSVNM6t/UMSJIkqX3r27dvW8+CJEnq4AxgSZIkqSpdunRxDUqSpFZlF0JJkiRVZcyYMeEhSZLUWgxgSZIkqSqDBw8OD0mSpNZiAEuSJEmSJEk1zQCWJEmSJEmSapoBLEmSJEmSJNU0A1iSJEmSJEmqaQawJEmSJEmSVNM6t/UMSJIkqX3r379/W8+CJEnq4MzAkiRJkiRJUk0zgCVJkqSqjBgxIjwkSZJai10IJUmSVJWhQ4eGv927d3dNSpKkVmEGliRJkiRJkmqaASxJkiRJkiTVNANYkiRJkiRJqmkGsCRJkiRJklTTLOIuSZKkqkwzzTSuQUmS1KrMwJIkSVJV+vXrFx6S2p+ff/45mX766ZPrr7++rWdFY9EOO+yQzDnnnC36mXwenxvdf//9yeSTT56MHj26Rb9H464OF8B69NFHk0033TSZZZZZkgknnDDcEZxvvvmSzTffPDn//POTH374od70d911V7L99tsnCy20UDLttNMmE0wwQTiAr7POOsmQIUOa9aPt1KlTvcf4448fPnPttddO7rnnnhZcWoF1XO7B99tvvw3bYrzxxkueeeaZwmn+/vvvZJFFFgmfe8UVV7T6Sh4xYkTYVw8++OB6z7/zzjvJqaeemqy66qp1++aMM86YbLLJJsmTTz7Z6Gd+9tlnyY477pjMPPPMycQTT5zMO++8yTHHHJP8/vvvDab99ddfkzvuuCPZeeedw2+F6SebbLKwDo4//vhwUVOuNdZYo26/Zx7y9t9//2SSSSZJPvnkk7I/U5IkqVZ8//33yW677ZZMN9104XqJ67SXXnqprPdeeumlycorr5zMMMMMyUQTTZTMNddc4Xrto48+ajBtvj0RH6ecckqj37HmmmuG6fbee++yl+mcc85JpphiiqRv375JW7j77rvDeuEafdJJJ026deuWbLHFFiH4EbGOSq2TctbL2PLFF18kxx57bPLKK6+09azUhLXWWivp3r17cvLJJ7f1rKiD6JSmaZp0EDS2aaRjgQUWSOaff/7Q6H/33XeT119/Pfn333+TZ599NllmmWXq3rPZZpslt912W9KzZ89k9tlnDwdvDpDPP/98eP3www9PTjrppLLngUDKxx9/HIJoRJtjgODtt99O3njjjfBvfsCHHXZYCy/9uIuT1hxzzFF48i/C3aVtttkm6dGjR/Lyyy+H4FEW2+eII44IFySPPPJI0toIrt53333Jhx9+GC6GollnnTX5/PPPw37EPtulS5fkrbfeCvsRy3zmmWeGgFBRQGzZZZdNvvnmm2TBBRcMyzl8+PBk5MiRyfLLL588/PDD4aIpuuyyy5Jdd9217nfDe3788ccQ4Pvpp5/C7+jxxx8PFxWNueqqq8JFGPPGYeXTTz8Ny5D15ZdfhosSlvmaa65pgbWXhN8u3nzzzRb5PElJMmrUqHBs4LfPcYBz4yqrrBIC3TS8pLxhw4aFv7169XLlqMOiLbHiiismr776arjxyA3GQYMGhWueF198MZlnnnkafX///v1Du4Ab59xk59qPoNY///wTPpMbjxHXUwSjtttuu3qfsdhii9Vd++TRpmH6X375Jdlrr73Czfum/PXXX+HG/wEHHBDaPWPbf//737AuCWBtuOGGIYDFtexDDz0UbqZyfQmu8wn4kelJokFeY+tlbOKae6mllkquvPLKeplItYj5e+yxx8puQ5XbFuZ6IW43XHjhhcmAAQOSr776KlxPqOPqOTbaZWkHMXz48LRTp07pBBNMkN5+++0NXv/yyy/T008/PX377bfrPf/SSy+l33zzTYPpn3vuuXTyyScPn/naa6+VPR9zzDEHAcH0ww8/bPDaBRdcEF5jHr/66quyP1ONY52y3ivRp0+f8L7jjjuu3vPvv/9+OvHEE4fHe++91+qr/sUXXwzzse+++zZ4bfXVV0+vueaa9Lfffqv3/EUXXRTeM/7446dvvvlmg/ctv/zyDT7zr7/+SjfeeOPw/DHHHFNv+quuuirdbbfd0rfeeqve81988UW62GKLhff069ev0eX4+uuv0y5duqS9e/eu+w18+umnhdPuvvvu4XdVNO/N0aNHj/CQVL1ff/013XXXXcN5it9x/sHzHC/yxyWJaxweUkd20003hWPhLbfcUu8aaOqpp27yWqmxNgyfefLJJ9d7nuf22muvsj+H4/Kcc86ZHn/88RW997bbbgvTjxgxIh3buD6dcsop0zXXXLPw9VGjRtX9P20r5pP2XC174YUXwnxeeeWVaa3bfvvtK25DNYXP43Pz25F2y+WXX96i36XaMzbaZR2mCyF3HDjWk2660UYbNXidrldEfskmyUfru3bt2mD6pZdeOtlyyy3DZ9ItsSVw12W22WYLdzrIBFPbueiii0LaN9l1ZOhFpITTze7oo49u8i5aS+COBPJ318Cdp2233TZ06cvafffdk969e4e7dbfcckuDO+BPP/10yJY67bTT6p7v3Llz+C4yEs8999zQTTKiC+3FF18csq+yZppppuSCCy6o+339+eefJZeDTDDuKHIXsilkv/G7YhtIqh2//fZb6OpONgDnKTI5OW7QxZi/ZILy/CWXXBK6BDC9JI1Lbr311pCFSjmHiOx52h933nln8scff1T8mbEMBl0Ti3CsLSoBkcd1HxlitHcqwTGeeZh77rkbZOfQC4DeALSt+H+Wlc/nGjSLjK+DDjootHPI8qckBZlVTXX0obcAWf/0ECjSVPZ/KZSMoRRHvnRMEZZ9vfXWS5566qmQQcp1N70FinoK0JuBXgT0iiBTjPNitjwM2UxkXyH2SuCRzUbKo7sh0zC/7EdTTjllaJvut99+DbY71+8nnHBC2FasZ+adXiNF+x3X5GTDMB2ZfWTkldrHstiHzj777PBe1gX7O22P7777rt50bNsTTzwx9LZgXdBzpVTWDdtx4YUXDr8RqVodJoAVC8Nlu2BVi8Y+8l3MqhEPxNkAQrY+Eym0BE44YHBwpJEwdOjQRms/cRKhVhJ1jjhIcfI49NBDS55ESXPmQES3O6ZnnjgRv/DCCxUtCwfB8847L+nTp0/dZ3HAZZ4ffPDBwveQUsp8k6rKCZMDP4EklpWU4KK6SRgzZkzoyx9rOtEtjv76ze0By3qjyynriKAVn3P55ZeHYCUH2Hw9qngiZ945OVVbiwvUlho8eHDY3ksssURF809KdexnnxVPouuvv369boLgBETaOycgTtKVfA/rif2zCPUJbrjhhuTII49scPFThIsUuuted911ZV2QSRo7uFimyyAXz5x36Ea8xx57hC4d/OXGC8/zOtMVdWGWpI6M0hOLL754qKWaReCDG3nvvfdeWZ/DNdXXX38dupsR6MDqq6/eYDoCH1wnUz+Ua1+ut4pQW5QaULQHmLYSHOtZpiK0MbjO5/qegBTd/M4444xwIyPiGnqDDTZIzjrrrNAGoMQFASyupQ888MBGv5s2CPNLDSyu9cvBeibwlX9k21a33357uDHL33LQZZGyMnTZZPno3sl1fzYgQ9f65ZZbLnnggQdCUsLAgQPDdSzLHr+H76R9AdoX1157bXistNJKTc4DwSs+j1ImdJHkhjOfkbXLLruEm+xsL9Y324Pp87XLCIoRsKLdxPJQ2oab1dwA50ZUY2gjsu24Xqetxf5J+RX2g+x7mY+jjjoqtBVOP/30EPTj8wlmFqGtU6r+sFSRtIOI6bKzzTZbvXTT5qLb4DTTTBO6S1SSUttYF8IffvghnWKKKcLrb7zxRr3XPvvss7Rbt27htdlnnz3dcsst09VWWy2kW/LcmWeeWbLr3BZbbBG6O6633nrhMdVUU4XXtt5668LlmnbaacPr8803X9q3b990ueWWC//u3LlzevPNN5e9rPfdd194H+nKpP4yz8suu2zoHsajKE105ZVXDu85+OCDw7Ktssoq6WabbRa2G8/PM888oQtL1pgxY9IFFlggvD7jjDOG5V1jjTXC/O69997N6kKIv//+O11iiSXC+9l/2N7jjTde+vzzzxdOTzos0z766KOFr1c6H0OGDAnvobtOpTbddNPw3qOPPrre8xtuuGF4vlQ3jgEDBoTXzznnnLK+5/XXX6/rNvT77783eP3nn38O23/++edP//jjj/BcU10Ise2224ZpHn744bRadiGUqkc3+9htcOjQoY1Oy+t2h1eeXQg1LphsssnSnXbaqcHz99xzTzgu3n///WV9zkQTTVTXNbtr167pueee22Aars/PPvvs9M4770wvvPDCdMEFFwzTDxo0qMG0XEszfVRuF0K68HHNftBBB5W87uUaOYvyElw/R3fccUeY7sQTT2wwT3x2U+0ormV5P+t27bXXTgcOHBhKbOTFLoSlHs8++2zdtHTfK7cbX7xufeKJJ+p1C2UbZdfL/vvvH6Z78skn65776aef0rnmmitcC//zzz/N6kJIaQ+m32CDDeo9379///D8q6++Gv79yiuvhH/vsssuhdf2jzzySN28TzjhhKGsR5wnnH/++WG6K664omQXQpaNaa6//vp638F+nX0+fse6666b/vvvv3XTHXHEEWG6fBdCnHTSSeG1lminq3aNjXZZhwlgffDBB+kkk0wSfhgEifjhXHrppaHGFYGKptx1113hPVtttVW6wgorhEAGBy7qA1WiKIBFQIYDMQeSogMUCDzxGt8fAwHxQDLppJOGYM/LL79c7z3xgE1wh8ZHNHLkyNAXP9+fnQPMQgstFJ4/5JBD6h1wbr311rDMBMKofVQOvid7sohY53w/fdo5sBcFsFimZ555pu75X375pS6Qlg987bHHHuH5tdZaK0wXEWhifpsbwALrlEBYXJf77bdfyWlbOoB16KGHhvdccsklFc0z2zRe+FA3ISvWrOJipwgXQrx+4IEHlvVdnCSZfv311y98nc/h9ccee6zuuXICWOedd15hAK45DGBJ1aPhwW9ymWWWKWv6pZdeOkxPQ0OCASyNC7hW3nPPPRs8zw05jolFdXiLEGy499570zPOOCNcu+XrXxWhfUAQi2vs7M1ePotA0bBhwyoOYBFMKAo+Za97CVZkUWOVm74RdRFpp/z444/1pqONwPu55mvKDTfcUNf+itfkrJdsfdYYwOL7HnzwwQYPEgWag+vWogb3wgsvHOrHRvPOO2/aq1evBtOx7ZgvbvpWE8B64IEH6j1P3eZsbbQYAMrXrKUNyPMx2Ma65N/sX/n9h7YZN8FLBbDYtiRCsM1Hjx5d70GbKwbP4nfkA7a8r1QAiyAsr7VUDVzVJmtgVYC0RdJP6T7HiElXX311GFmNFEtGCCHVkxHQSmHkD95Dai7dq+h+Rfc4ahA1B6NkxH7P9AsmbZLuaaR03nzzzQ36Uw8ZMiT0Lec7s10WV1hhhdB1gxTeWI8ojxRTanxlv5s6Q3jyySfrnqfrG6Mx0n2LPsvMW0RqKf3b6dZ2xRVXlL2M2REds3XFSFulT3up+mGMdEJ9lYh1FNOMn3jiibrnSUNlu5CqzUgqTJdN1+Z7qrHooosmq622Wvh/usWwXsaW1157LfwlzbpcpEeT0kyXPmq05bsesv2QXU9ZpKGD30hT7r333tCtkq609LfPY8hoUoupoUUKcyViLbpKhhimL37R44MPPqjouyU1RJdA8HsuRxxZqVSXao17uA7jIbV31PxktLTsI9Z8ortbUYmOWBKh3O571Aui5iDXvtQzPe6445ocMZD2AeU0KOHBiIfxunDfffcN7ZVYe6k5SpXkoGxHvjwL3euy9ZAYfZ2uavnR5WJtVV5vCmVEaLPwuXRV32qrrUJ3TUpi5MtNUHpjjTXWaPDgOr65aBvlFS1n0TV7JcvZmHztXcpy0P6JIwTy+fy7e/fu9aajDTj11FPXfX/8m59X9h+O0Y3N5/vvvx/qhtG1k+2efdDGoNtr9jvy88x0rLfG9rFs+1Nqjs5JB0LfcfowUweIgx8FrQkScKCnAO3//ve/EBwpOvj85z//CQ8OknwG09Pv+K677grvq7QOFgEhAlLx5EJtJ+qH0C+cINtOO+1UN22sR0S/cWpB5XFS4n3ZYFREcIGTYB71sJAN2sX308c61vfKfw/Fuou+pxRO6A8//HDo08x3xZM6B8Ds3zz6SJczz5ygKV5JsKqovhInPPr7NxfrPtbrIuDGfpMtzNma4kmg1IG+CBcpzDMnoHIKpjcXhSRjsXX6tcdaWNntTj98TpjURKhU3M9j7TpJbSsGtRm8oRzxpkk5wXCNG7iGkToCrmnz19YffvhhqHPKMbLohnh8jkBOpbi+5eYvdYYIUDWGNgRivSgKjTMYEfWNYqAj4vjMcwQjSt3Y5HqMgEK+QHc0/vjjJ2MTQSjqUPGgrcJN7Oeff77iG6WVKrWcza212xJKBXpaMwBEAXf2F/bFItXUmo77GIklUjU6VAALBJo23njj8ADBKwplM0IDAQNODKUKjMc7DQsuuGDIduJgRkYUD0bWqASN+nxBb04iFPHbeeedw2sx8ycW4i5VADw+zyggRY2IooNuvAuSvUtUzfcUISjHqB1kr5VSqnHDiBWVzDNF4hub5+beYYsF3MnQIyBEgIiTZv4uUmuII6OU+10UiySwSjF2CkgWBTtj0JQCl0ViYcXGvpPtT0OEEw13BinsnMfoJNwZI0OrOSeieJesnNFQolIjm5CFJak68ZjQWKZyFhkJ2fdJUkfBTbt8WyEG7cnc50YvDf1sIXeCLASJ4s3YSnGztpwRDOm1kQ0kULydwtpFo/gR3OJBgfGiEdrjKNUE0AjQNRfX6IyczTV/9pzAzdD4enMsueSSIYBV7nmptbEc2ZHLSy1ncwNM3PSnd0tEQgX7WWzr8Pn8m+myI4dTXJ7r6fj98S/zms2Kpd3DdiZbrRT2BbYl+1Nj2YTxO5iX7HdwY7pUMJTvps3QkgOuadzUYUYhLIUMEbrgxeFL6dJWqnGfF7sPttSQnxyAGB0wdvsrV2MHwvwoKNWo9IBLBg7BK7LNOHFz8CQzh4AQd4Iau3PRkvPdXCeddFLy9ttvhyAcAUvSlQneEOysFCeUSk011VRlZzBcdNFFIUOQ9zDqXz59OJ8CXWo0x/h8qYsJ7uiRHUdqMKOOlMquorsu+wsXFowsmX3Ehi3DDPNv5rdU8I7fp6S2F+9u85suRzyn8huXwLG+6HgvtTdkxue7p3GDG4xUR8CAHgsRI+DRDTA/AjQlDrJlDuiRUdS4p8cIJT4I2ERFGepcL3IDkSBALCHB6HMEqPIPMJId/7/00ks3uryU9GA0xObie7j+z3eBZJQ8rhXpKlkKbTJ6qBS57777Ki610ZpYTrZVdn65McyIjLTxGCUyW66jkpu0yJeKIYECcf3x/WAfyKKXDtZdd93wl/2VhA7amtl2GDeduf6O0xWhlw7bsqh0CPtvXCa+gww55jH7Hfl5y6JXTbZ8jNRcHS4Dq5SY7cSPkh9fqVTarJhZ0pLdnGJkPdu1LqYbl+qTHFOCZ5lllqq+uyW/hwM2d6fIBrrpppsaZIHFO0TVit1ZSs1zc/ubE7hi2FkylmJXPE60nCz5N8FLui1mxW6ksc5U1qefflrxPJCii6aGDSaDkFpf7LN0j+XuX2N3DQm4Up+qSHx+4YUXbvAay8VJ8q233grdKC+99NJGg5qcsLL1yvKee+65erVysuIFnHdhpNpAZjA1WPjdcmwnE7UUXuemBRevvE9qyfO+VMsIYFH/lZt8XC/RVuC6kfYFx9B8aZPs9TXXWXQBpIYp2eMEOghcXXnlleEG5VFHHVUvmHHHHXeEoBg3J8lCokYtGVfXXntt3TUpNUVjXdGiNkepzKusDTfcMHzme++916wMMuaRLpdHHnlkWFauRSnJwfXo/vvvX1gCJBvAWm655cI6Jfuf9UM7jWUn0435p3tl/lr2uuuua/BZfE8MkHCThW3Eui26Dm2Oww47LLnxxhvDtTI9NugJwU0fMosoNxNvzjMf3KDl5jMZaWxngojZ7KoifM4GG2wQ1gNBMpaRm+uxjAd/qVNJwIx1xI0nAmrMA+spdnvl2vrwww8P+yOfxWeSjcV+Sp20WCe5CJ+5++67hzYSdWq5qc25nnYrQVpq3/Ib4DsGDBgQpiMRgOAaPTNoRxX1zKAXFGV9qq1dLAVpB5EdUa/UaHMsLkN+Zkf5a0wcgpUhQqsZhbBo9LXsKBaMoBhHT/zuu+8avCcOj5ofNrWxUe/ivDOyRXaUEp5jqNeikRkZ7rbUSCR5n3/+eZh20UUXbfDan3/+GUbqyH9/dhTCovUTRxdhmohRDBldktFNWE95hx9+eMWj/7GvLL/88uF9jMqXddlll4XnF1lkkTC0cNEwv4wYk8eIl5XOx2GHHRbec/HFF5echmGZGdqe/TY/OkkRRmbkM6effvr0999/r/faV199FT6LkWPYRllMu9pqq4X39unTp+zfSJFyRiFkuGhHIZRqy6677hp+l4xSNHTo0MJpeJ7X40hQUuQohBpXjBkzJt15553Trl27hlG1uW5l5Lmi66HsdSHXVox2zeh2HEe5JuN1Pit/Xcyxds0110xnnHHGMB0jDzKaOaMdlqPcUQjjfE077bTpCSecUO95RpKbbLLJSo6al8X1+gEHHJDOPPPMYX7nmWee9PTTT2+yfca1NtfQG220UVgXjLLNOmUEQt6fvR6N7YRSj+zId7G9lR8lrwjfW9TWY7tm2ySgLUJ7ie0x8cQTh/bckCFDGryX0cAZjS2OdN7YiIRxfTK6IJ9Ne5Br9b333jv97bffGqyv4447Lp1rrrnCep5tttlCWyh/zY/zzz8/nX/++cN0M8wwQxg9M9/OzI9CGDFC+hJLLBHaYMwPo9gzgn12pPp//vknzMtMM80UpltllVXSN954I3xefhRCRiBku+ZHqlTH06NHj8JRPVtShwlgHXnkkSHQM2LEiAavffbZZ+EAw8GBA0N2qE9+oL/88kuD93DimG666cJ7br311hYJYPEcBxpeP/bYY+u9xoGT57fbbrt6wYVnnnkmnDwI4BCEqyaAxUmEAxDPH3HEEfVOKrfddlsYupYhUrMHp1I4gDLMKgfmp556qu55AmOcwOLJpNoAFmgk8fw666xTb9hgLhY4qFYaOBo0aFB4z1JLLRUOvlmsk5VWWim8ftpppxUOkdy9e/f0m2++qXue7cLBu9L5IDhVFJiMWK+cEFjH5Q7LjBic4yIpu7022WSTwm3CNmOYYF5bccUVC38PLR3A2mabbcI05V6ItfWBUhoXcHyNx2geyyyzTLjo5PjD36WXXrruNabLX1hr3GYAS2q/jj/++BAUKbrB3R5tvvnm4Tq/PYgBrNGjR6cdFQkP+++/f1vPhsaCsdEu6zBdCEnLJa2Rmj2kv9IPmf7q1PyhqwMFDqkblO2bSzc4iniT3kpfcgqL8xwptLEg3wEHHBBqPFWKtMqiUQgpoEfXtHxReGpGrbjiiqHYIsOZkwJL10WGKCct+Ywzzmi061g56A7GqBKkmFL/iX7xfCbpyE8//XQo5Ej/6HJGoWLaQw45JKQLk25KF01SaVnX1AYgRTTfl7u5SE9lndx7770hLZdC+HRBe+SRR0KaayXfQ1F4UoCZf7rI5WtxsY7YFqTpHnvssaGOUyyeyHpjWZkX9i8KHFL3gGUmlbjS0fhYDvaRUsPQk5JLUU9Sjkml5pG3wgorhFpkWaRLs//we2AdMa8vvPBC6N5BmjZpxVnULIj1Ekj7paB9EZavJUYOIfbKOiS9mvmRVBso2Er6P+dEjiN0J4xdgSO6EtAtg+NLrAkjSWrfaO9Qz4iyFVtvvXXSnnGdybV1UTdDjX3URqQLIgNQSS0i7SCIWl977bUhs4MsI9J6yVzp0qVLyEghm+bnn3+u9x4yTXiezB6yRsh2IXWVLnZ9+/ZNH3300WZnn2QfnTp1CqnC3M0+88wzS3bPIqvnoIMOSueee+7QZSymC5fqOlZpBlb08ccfh64iZIORVkraMKm7dD+r1NVXXx3SfEkLZZ1vuOGG6auvvlry+5uTgRXXDamvpFKzjUiJ/e9//xsypirJfGI5mZ402HLuhqy11lr1nv/+++/TPfbYI6TiMh89e/YMmQmoNAMr22Vn2LBhDV5rLE26KF0665NPPkl32GGHsL7Yl8gaO+qoowozJuKyNvUo1S220gysJ554Iry+zz77pC3BDCyp5dHleODAgaELC+cu/vJvnpeKmIElSZUbFzKwNO7oMRYysDrxn5YJhUmqFAUSKU65995714020tGRNUf2G4VLKWJarfgZb775ZgvMnSSpOSgmjPwAKJKk0ujxQcF1et60RE8HqS2NjXaZASypjTFkLaMLMvpIHJmwo2IUnW7duoWumXSXbQkGsCRJkiSpbY2Ndln9AkCSxjpqfFGj7bTTTuvwa//UU08Nf0888cS2nhVJkiRJUjtiBpakds0MLElqezfeeGP4269fv7aeFUmS1EHbZR1mFEJJkiS1DUYHliRJak12IZQkSZIkSVJNM4AlSZIkSZKkmmYAS5IkSZIkSTXNAJYkSZIkSZJqmkXcJUmSVJXevXu7BiVJUqsygCVJkqSqdO/e3TUoSZJalV0IJUmSJEmSVNMMYEmSJKkqgwYNCg9JkqTWYgBLkiRJkiRJNc0AliRJkiRJkmqaASxJkiRJkiTVNANYkiRJkiRJqmkGsCRJkiRJklTTOrf1DEiSJKl969u3b1vPgiRJ6uAMYEmSJKkqXbp0cQ1KkqRWZRdCSZIkVWXMmDHhIUmS1FoMYEmSJKkqgwcPDg9JkqTWYgBLkiRJkiRJNc0AliRJkiRJkmqaASxJkiRJkiTVNANYkiRJkiRJqmkGsCRJkiRJklTTOrf1DEiSJKl969+/f1vPgiRJ6uDMwJIkSZIkSVJNM4AlSZKkqowYMSI8JEmSWotdCCVJklSVoUOHhr/du3d3TUqSpFZhBpYkSZIkSZJqmgEsSZIkSZIk1TQDWJIkSZIkSappBrAkSZIkSZJU0yziLkmSpKpMM800rkFJktSqDGBJkiSpKv369XMNSpKkVmUXQkmSJEmSJNU0A1iSJEmqyrBhw8JDkiSptRjAkiRJUlWGDx8eHpIkSa3FAJYkSZIkSZJqmgEsSZIkSZIk1TQDWJIkSZIkSappBrAkSZIkSZJU0zq39QxIkiSpfevWrVtbz4IkSergDGBJkiSpKmuttZZrUJIktSq7EEqSJEmSJKmmGcCSJElSVe6///7wkCRJai12IZQkSVJVRo4c6RqUJEmtygwsSZIkSZIk1TQDWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaZZxF2SJElVWXLJJV2DkiSpVRnAkiRJUlV69erlGpQkSa3KLoSSJEmSJEmqaQawJEmSVJUbb7wxPCRJklqLXQglSZJUle+++841KEmSWpUZWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNs4i7JEmSqtK7d2/XoCRJalUGsCRJklSV7t27uwYlSVKrsguhJEmSJEmSapoBLEmSJFVl0KBB4SFJktRaDGBJkiRJkiSpphnAkiRJkiRJUk0zgCVJkiRJkqSaZgBLkiRJkiRJNc0AliRJkiRJkmpa57aeAUmSJLVvffv2betZkCRJHZwBLEmSJFWlS5curkFJktSq7EIoSZKkqowZMyY8JEmSWosBLEmSJFVl8ODB4SFJktRaDGBJkiRJkiSpphnAkiRJkiRJUk0zgCVJkiRJkqSaZgBLkiRJkiRJNc0AliRJkiRJkmpa57aeAUmSJLVv/fv3b+tZkCRJHZwZWJIkSZIkSappBrAkSZJUlREjRoSHJElSazGAJUmSpKoMHTo0PCS1L506dap7/Pe//23r2VELmXrqqeu26957713We4YNG5ZMOOGEyccff+x2GEvuv//+ZPLJJ09Gjx7tOi+TASzV8+ijjyabbrppMssss4QD2DTTTJPMN998yeabb56cf/75yQ8//NDkGltjjTXqDpifffZZRWt4zjnnrHci5TH++OMn008/fbL22msn99xzT4fbYn///XdYx7169ar3/KhRo5LLL7882XjjjZNZZ501bA9ORiuvvHJy9dVXJ2malvzM3377LTn66KOTeeedN5l44omTmWeeOdlpp52Szz//vMG0//77b/Lkk08mhxxySLLEEkskU0wxRTLRRBMlc889d7LHHnskH374YeF3PPbYYw22VfaxzDLLNHjPHXfcEV67+eabm7WuJKkj4Pj9yy+/NOvR2LFfUuv7/vvvk9122y2ZbrrpkskmmyxZddVVk5deeqnsAAH14rjemmCCCcI1USkXXnhhuP6effbZw3Q77LBDyWlffPHFZL311ktmnHHG0BheeOGFk3PPPTf5559/ypovrjWvvfbaZN111y1r+j/++CM59NBDw/XlJJNMkiy99NLJgw8+mDTHmmuuWRhk4Vp25513ThZccMFkqqmmCsu1yCKLJOecc07y119/tfg6aOnlvO2225Itt9wy6datWzLppJOGa/2DDjoo7D9F7rrrrmTxxRcP1+1s82OOOSa0EbIefvjhcD3P9T2fyWfvsssuyZdfftng8y655JKwTStx5JFHJv369UvmmGOOit43LiHQtN9++yXzzz9/2Cdoo9KGYz/5+eef66bj91qqjcQ2jtZaa62ke/fuycknn9xGS9T+WMRddY4//vhwsMQCCywQDtKcXN99991wEL711luTJZdcsjAwEV111VXh4MqPs5qLbIJonHzw66+/Jm+//XaIUPPgB37YYYd1mC138cUXJ++9916D4Bwnueuvvz7p3LlzWO8rrLBCCEA99dRTyRNPPJEMGTIkGTx4cAjwZf3+++/Jaqutljz33HPJTDPNlGy44YbJRx99lFx55ZXhPTzPCS8aOXJkstJKK4X/56TPe/lMLrKYtxtuuCG59957w/cXIdBV9BrP5zEvXHwcccQR4WKJ/UuSxjWc1+I5rlJcINNoljT2cdOPIM+rr76aHHzwwcm0006bDBo0KFlllVVCAGWeeeZp9P1cT1122WUhuMK1GNd/pZx66qnJTz/9FBrHRQGKiO9dbrnlwnfTiCawcd9994VG9gcffBACPk1hfrbZZpukXDTOaRfsv//+4Xu5/l9nnXXCjfBS14tFaF88++yzha8RwHrzzTfD53KDe7zxxkueeeaZ5IADDkief/75cH3akuugpZeTICeBL9YrAanXX389JAOwDxDwJPgRMa8bbbRR2I/OO++8MO2JJ56YfP311yGQGbFsY8aMCYFN5odreD6T6/tXXnklXMdHW2yxRfi77bbblrWsvP+hhx4K61jFWPe0yX788ccQSCSI9e233yavvfZa2E577rlnvXM7CQH83vPybbfdd989GTBgQHLccceFRAI1IZXSNB0+fHjaqVOndIIJJkhvv/32Buvkyy+/TE8//fT07bffLrm+vv7667RLly5p79690znmmIPoVfrpp59WtH7j+z788MMGr11wwQXhNebxq6++6hDb7ffff0+nn376dOGFF27w2r777psOHDgwrNesYcOGpVNOOWVYFxdffHGD9x155JHhtWWXXTb96aef6p4/44wzwvMrr7xyvelHjBiRrrnmmunDDz+c/vvvv/XmbYcddgjvmX322dM///yz3vseffTR8Nr2229f0TLfeOON4X2DBg1KW0KPHj3CQ+oofv755/Ab4cH/q2Nv40oftbpPcI7mocr5m28/brrppvA7vOWWW+qe4zpt6qmnTvv169fk+7l+/fXXX8P/77XXXuGzSvnoo4/qrssmm2yyktdbu+66azrhhBOm3377bb3nV1pppXC92BTm4ZhjjknL9fzzz4f30C6Ifvvtt3TuuecO157l4j1zzjlnevzxx4fPY32UY++99w7T0zZpqXXQGsvJdXLe1VdfHT7z0ksvrfc817GLLLJI+tdff9W7nqdtlm17Pf744+k///xT7708x2cyfZFy1y3tDq73s22BWvTLL7+02XefdtppYX0+/fTTDV774Ycfwv4R8Xvld1uOUaNGpeOPP356+eWXp+1dj7HQLrMLoerugHCMI1rPHYA8IvpEhok0l8LdCe4qcyeqNZByPdtss4W04VJ3a9ob7upwd2W77bZr8Bp3i8hUIkU9a6mllqrLQLvxxhvrvfbnn3+GOzG44IIL6t0FOPDAA8MdtscffzzcqcpmSlG3hMyrbCo7dw3YlqRtf/LJJy12R4YsLO4uXHTRRS3yeZIkSWPrum2GGWZINtlkk7rnuE7j+vnOO+8MXc4aw3uzmTeNoRtXY10MI7JB6JJEmYkssvDL/a5K1wEZJGQYRXw/3f24Pv/000/L+pzTTjstZLTRvqgE2VjIdsVrjXVQ7XKSTZVH7wPQsyR66623woPvoddFtt1D24z5iOgxQSZaFs916dKl3mc2B2U+8m0BsF+TdUg2WSwxcsIJJzTomsny0t0zZsOx3ueaa64G1/uxBMlNN90U2jm0Mckq3mCDDRqs0+xnspxk1vEe0H5iW/CbYrvQw4MSKxGv89vkM7K9ghhshO+je2elyOZjnyjqjTTllFPW6xpYCboh0kZjXatpBrAUxMJx+WBJuejaRyovfaeLuo61FH7gyPcJBymcpHOTUssBhIM5/YpLFZXl4MlJkAMwadr0J+fATJCMFN1SFyEcXEn15MKC6ZknLmReeOGFipeHtFLmo2/fvhW9j4M0vvjii3rPP/3006FOGdtgscUWa/C+zTbbLPy9++67y/oeTj6sl6Lvai4+kyAp6bakgEuS2j9qZvKQOrKXX3451CnKBxHo5sdN3Ma6BLYWGugEcLg2JYhBAW6CBtycPvzww1tlHXBtSIM9K9ZypStaU7gxesopp4Tr76YCTNyc/eabb8L19+233x4KzXMNTt2g1lwHLbGceV999VX4S9fT7PeArmlZBIyogRtfb6xbOY/sZ1aKEiVsE/btPLpNckOcG+HcXKd+G3V2i8q5fPfdd6GLJdMQoGT+6VZ3xRVXNJh24MCBoXwKba5999031BajjjJdR/PtO+ogL7roosnZZ58das4xDducGl9bb711cvrpp4cb7nT5jN1FaZ/RrY8b93TLBAFTpuFGenMSLtjvaDdWUluMfTf/YF/NY53ZfbNMrZrfpXYjpu/ONttsIY2x0tR3UoDnn3/+9I8//gjPtUYXQlIzp5hiivD6G2+8Ue+1zz77LO3WrVtdd7ctt9wyXW211UI6Js+deeaZDT6P5/m+LbbYIp188snT9dZbLzymmmqq8NrWW2/d4D2vvfZaOu2004bX55tvvrRv377pcsstF/7duXPn9Oabby57WVke5m+eeeZJK3XeeeeF7yQ1Ouuss84Kz2+++eaF7xsyZEh4feONNy7re0hTposj73nkkUcKuxCy/IcddlhI3z788MPTe+65p0F6cx4psrz3qKOOSqtlF0J1NHYn6vg6YhdCNZ+/+faDLkE77bRTg+e59uH3ef/995f9WU11Icx/b6kuhH///XfoVkeJjXic4PrywgsvLOuzK+1C2LNnz3CNnffmm2+Gz7roooua/IzNNtssXD+W080tlp6IjyWXXDJcj7fkOmit5czbeeedw3y99957dc/RRZHP++STTxpMv9RSS6XLLLNMo595wgknhPdTCqS5XQgfeuihMN3dd9/d4LXY5TVr9913TyeddNJQbiSiRAmfQcmSiHbhoosuGtoSsRRJbD/MMsss6Y8//lg3LW0onj/nnHMafGZ+XZ999tnh+euuu67uOT6frp206bKfS9de5pV1Htf1HXfckTYHXYCnm2668Bm0e/fYY4/0hhtuSL///vsG0/J7LXUe79OnT4PpTzrppPBape3wWjM22mUWcVdA9Jri6Nzd4I4GGUUUJyQaTEpjvthcFlF4ioSTEspIeS2NKDt3U7iDQjFLUkx79uxZbxpGy6OQ4VZbbRWKlcf5oOB5nz59QmYWEXui91ncoSEd9f33368rfMioe9yBoIA6xfRiRhnnANYTkXNG7OPOUUyz/d///hfSxynox3ojZbkpRNmJ4tMlsBJ0oYx3DeiOl8XdE3DHo0h8vtzhcemiGFNwSQcutRz5OwYLLbRQWCelipnGu1fcFZFUGl0kikZbUvvGaILN5T7R8VSzP2js4pqU7Pu82HUonz0yNnCNzrUq17sU92ZeuH7bZ599wrVtUWmQtlwHFEDnGrHcLHyu38nO4djHQFEU0M//ZlpjHbT0tqanCqOL04bIXh/Hzyn1XUXZOhGDOtFWoQ1C97/mIssJRVm02Qw52mH0UFlxxRXDQE/vvPNOXa8Q0AWSLLiI9hj/JguLboDZrneUT8kWLKeXCO0nityTkRWxXnbcccd688Q0bFdGTIwYGIr38RztC0akBKVVaKPy+WRIUtQ+334qF90V2f8Y+IxsQLL8eLCc//nPf8Ij2wWT7VfU66UoWy6ue9qZsceRSmjV8JjaFaLvZGDlo8QUptxzzz3TL774osF7XnzxxXAnIX9XqNoMrKIHd1WOPfbYetF+fPDBB+F1Iu754o048MADw+u77LJLvefj5z744IMlC0ReeeWVdc+RgVSqoDk22WST8PqJJ55Y1rKeeuqpYfrjjjsurcShhx4a3jfXXHM1KGRIFlRjhRzff//98Ho5WV/cCYrZZkV3sF566aX04IMPTp977rmw3nlw94c7RbyHrLyiOxKgSCXTVFJYM0b084+JJprIIu7qUKrJzvHhOmirfYBMAR7ug9WtRzPs2h5ZIxQIzz7I8KnVDKyTTz45nXHGGesN3INVVlklnXnmmesVBi83A4vlza+D2Muimswk5mXBBRdMt9tuuwbzUG4RdwY44po/W8S92nXQ2hlYTzzxRDrxxBOHzJv8vDQ3A4vi7gyeRYZTNuMor5x1GwcnePLJJxu8Rq+XjTbaqG4AqeyDAvLZbCnaSHm0DZiWTLpsBtYVV1zRYNoVV1wx9HDJfiY9bPKYhmnzXnnllfDZ559/fr3nGXSB52eYYYb0u+++S1sCxe7ffffd9Nxzzw3ZZPni/JUUcQeDW/EZb731Vtqe9bCIu8am1VdfPRS2o784GU1kIRFJ544HfYjJXnr33Xfrpid7aJdddgkFE+mP3pI23XTTZPvttw8Psp5WXnnlENE+88wzQ2ZUFllWoN4Vda/y4vCxTz75ZIPXiNZzZycv1n3KDlsc389dDt5XyfcUIbMJldQMGTx4cOhTTkSfOzlkj7UG7myRhcddAO5asT/kUWOLeVl66aXDeufB3R+2B3dmyMor1b+c/Yq7LtxVoraBJKl9I5u40oxiqRaRVU4mSPYRi0vz/9lrwyg+R92isY1rLa6/sgP3gB4L1C/leqxSLG9+HcRs+2rWwTXXXBPaEmTlMF/xEbN7+H9qiTWGTBpqPmULXrfGOmipbU3GDvNBMXIKsmcLtcfvyX5u/ruKvoft07t371D3iWykbCZTc3Tt2rWuhlUWbUDaYDHriGwisuGoXRZrSrW2lhiI4IEHHqhbvs8++6wF5ur/ainTXiTLj0w46uLl26iViOu+mlpm4wq7EKoeUiAZISOOksGBi6AJIz4QcNl7773DgQsU0qOwIOmwLf1jIyAWRxmJOPkwAgUjTvBaTJWNxcXz00fxeQoU5pF+WtQ9Mp4IsoXcq/meIhRbz35XUx555JFQeJADJGnRRSNgxBN3qZN/TLlu7DvprkT69fDhw0N3SAJllWB9UpCRQB4njFLFMymKycUK+1g5qbJvvvlm4fP57qSSJEnNRZeoeK0bxTIT3Mzl+oaGe7aQO93huKkYb4COTaNGjWowIhxi9/OigY+awvLm10HsKsY6oBsgNyGzBc5jl8B8uY58qQvma/nlly8MbvGga1ZjXf5il7t4Hd1a66Ca5cyOWscNdq5zCTTlA2zZz+G6O5bYiO0Ogi3ZURBjdz+CV7RR6FJZTtmSpsRR5imjkkXXO76P5AbaYFF+uuw809ZglL8oDmyQbz9RviWLZDESKShdU04xdQaDyv8O6dIYX88ONMagWXTdJMBEcgTbMB9IrEa3bt1CQkJRELJcrFPa080dUG1cYgBLjSK7iuwbov/0F+ZATnCEkzRReKLPDFnKCadolA0CIfRdZqQKDuDV4MBHYIQg2rnnnlt2X+/GhiDOjyJTjXKGOs7irgkI4jSFEQ5Z/2QrETAsdWKfffbZw99Sdxfi89kDexYnAg7s9913Xzihso2bc+cj9u1v7EAeLzzyQx5Lqv+bzV4IqmPgAr9UrcL2uk/EUZnyd/DVuvuDWh4NUUZDK5X9QxYNDfo4sjPZ6rfcckuy/vrr16tjRPACrTk6NwiaEWwi0BAzaQjm3HzzzeGGZXO+n0z/xtYBN5ovueSSZMCAAeE5ginUoCUrn9G8swEr2g0xQMKo20WBH26cM3rdrrvuGj4jrleWJ399TTAiP2pfa6yDapYztoUINNHW4IZuqcAEN2J5H99DZlq8sU7vF5Y97mfxWMF64mY5bbJStWYrNcsss4TlIYiWFefl/3oi/h/aIqV6WBAopDYWIxbGafk3y05d5SzajtzkjjfV+V3RbqCt1xTWAaPM33TTTXV1sPhuRhskSEjWGLhJTm8hAoMnnXRS6HXDiIb8PzWcozg6IO2oxnq3EPgiky5/Dh42bFjY94oCs+WiRtiyyy7b7PePSwxgqSwxWMTJgINB/HFzQCNtspTnnnsu/CVzqCXMNddcDaL2MbW2VGHymDbMwbkaLf09MetozJgxjU731ltvhYMt6dJnnXVWg0KGRXfHXnrppcLX4/Ol7m6QBkt2FxcCnGybG1yKDZhSjSzuiLE83NFqjcL/UkfBb7AWgxWqTlE39Pa+T8SGjjclxu7+oLGLYAIZ8FyLcX1GxgSNea6PKaadL82BbPc1riFjsDcGC0488cS6m4uxHAW4iUjXrXjdRMZJnJYuafFajpvE22yzTQiqkK3DjUeu5WgQM31L7198DzeoCT7QO4PBn7iZzXJykzWLQt0U1I4BEAI12SBP/ho/e4P2uuuuCwWyeY4MF274cm1KoIpgYfZGdiXrgDYJ80vGS6leFdUuJ7hxzwBTZP5QXiOWPInFwNdcc826f59++ulhmxLwIsj3xhtvhOLjBF8WWGCBuukoq0KwhEGjGOCKR0TgppqC/dwoJ/uNZYhBQwZwIqDLzW0KpPM8+292OfNtJboXso5oSxBgeuWVV0JwLr8fUnqEnh78lsigo2cP65ggZlPYxgTG2JZsY7YjAbCnn346fE4Miu23334hsPTQQw+FcxTbhHXKPsHyxnYT65rfL0HBVVZZpeT3suxkcRFwJSBHG4ZtcMUVV4SgLz2WsgiqsR8X4TPiuZz9i9/3Xnvt1eSyyyLuyhSia8zLL78cCstNOOGEdUUcG1NtEfcPP/yw8PXzzjsvvN6rV68GRdynmGKKwsJ8AwYMKFnEne8rQvH2fFHLWMSd4uSxmGd+SOBKirhT6JPpGd61FNZDLAxIAfumsG2mmmqqMD3bLG/hhRcOrw0fPrzBaxR+j0XqP/7447QaFHfnsxguuAjDH/P6SiutlLaHYoFSWxVxt6Bzx1RNof5a3ScuuOCC8FDl/M23L2PGjAnXN127dk0nnXTSUGj6hRdeaDAd15j568xYwLrowedkUQS61LTZQYbiNSXvZ/AdrtUXWmihsouMFxVxb8pvv/0Wrq8pnM5gOhQbLypgzzyV09wsKjTOOt18883DdSnfQUHsxRdfPD3zzDMLi7KXuw423XTTdJJJJimrmHc1y9nYcTy/rXH77beHgux8z6yzzpr+5z//aTBoVGODXZVq05RbIJ/BmYoKuT/99NOhkDzrjIL4hxxySPrAAw+Eadmfs+uAwve0MZZddtlQtJ55yhdUj78Biroffvjh6fTTTx8+e911123Q/oifWWTUqFHpjjvuWG97Z38Xd955Z/ieM844o977KHjPfC2yyCJ165f9P788pdovtHHYDymg37lz53SmmWYK+ynrr9zfb76ty2BZHEsaK8bfXvQYC+0yRyFUXfCCA/SIESMarJHPPvssBIz4sRGkKUdrBLB4Lo6SmA/mcNDjeUY1yR7sn3nmmXDCY6TEfECn0gAWQT4Ojjx/xBFH1Av63Xbbbel4440XRkUpGq2xCAcp5qt79+4lD8yMFsj3HXTQQWm5YiBqueWWq9fQ4QBe6qTJxQCvcYJ+7733yvqes846q8GIKawTLhY4oHfq1KkwUIbLLrssfN9RRx2VVssAljoaG7MdX0cMYN13333hocr5m1db4rhCo3z06NHpr7/+2uE3BgET2jwdHaODs00rGeGRURe32WabZn1fY8GmogAWIwPq/xC43H///TvE6ugxFgJYdiFUQHeuc845J/T1JuWzR48eIRWSWhv09yV1mbRO0jLHBvqax0KHpF8yH88++2zoS00/5oMOOqje9KSRMvId/alJ4aUP8ejRo0PxQdK6zzjjjLKKLTaGtFnSRuk/Td9p0mz5TPq9k7JKMUBSisstpkh6K/PMPLJ8+foX9IOnqyTdNemXXdQNk9T1/AiQ//nPf0KqLKPF0Dee7yBlne1IH3TSXLNI7Y3rk/TtgQMHFs4vKbek+kbsC2wnRqvkfb///nvy+uuvh5Rs+vtTpyzf3z1imbHuuuuWta6kcQkp5aXS86VaVW2dy3GZv3m1NbqwxUes99QRMSAQReDLqbPU3tHtMlvovhy0b2g30MWuVL1ctSyKzNPeiyMlqmkGsFQX9KAYIj8e+tszwgoHPWoUETCin3D//v3HWt2N//3vf/UCRwR7CJRsscUWoX9wvm4SdacodH7yyScnd9xxRyiuSeCH+gMEZ+hT3hIWWmihUEeKAzsHHPpbU4ydPuf0kc+OHlIO+nkTzKGf/sEHH1xYR4qikPS5L8LJJR/AIvBIH27WBSMIsj7oZ04A7IQTTmgQKKOmWWwsEyTkUYQ+4dkAFuuVAopcDFAHgiAnwTtqENBPvtRw6lw4ME/UboiFOiVpXML5iRtHzX2vJLWU7GiDbTGK4thEwXRGFRwX3HnnnXWjMGYLzjeG63KSBTR2b/4093pgXNWJNKy2nglpXMVoJgShKOhO8b5xAcG6rbbaKhQ93XPPPVvkYgQE0iRJbYObOjATS5LGPdzopscIBegbw417erMwcmd2hEV1DD3HQrvMDCypDTHcMsO4klU2ZMiQZL311uvQ24N4OaOTMJzxzjvv3NazI0lqIYy2JUkaN8XyIOUEusyfUTXGq+rdkqrGULCkbOeHX+6o6cx0UaWPfb4bqCRJkiRJpZiBJbUxir+/++67ybiAWmHedZEkSZIkVcoMLEmSJEmSJNU0A1iSJEmSJEmqaXYhlCRJUlWWXHJJ16AkSWpVBrAkSZJUlV69erkGJUlSq7ILoSRJkiRJkmqaASxJkiRV5cYbbwwPSZKk1mIXQkmSJFXlu+++cw1KkqRWZQaWJEmSJEmSapoBLEmSJEmSJNU0A1iSJEmSJEmqaQawJEmSJEmSVNMs4i5JkqSq9O7d2zUoSZJalQEsSZIkVaV79+6uQUmS1KrsQihJkiRJkqSaZgBLkiRJVRk0aFB4SJIktRYDWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmta5rWdAkiRJ7Vvfvn3behYkSVIHZwBLkiRJVenSpYtrUJIktSq7EEqSJKkqY8aMCQ9JkqTWYgBLkiRJVRk8eHB4SJIktRYDWJIkSZIkSappBrAkSZIkSZJU0wxgSZIkSZIkqaYZwJIkSZIkSVJNM4AlSZIkSZKkmta5rWdAkiRJ7Vv//v3behYkSVIHZwaWJEmSJEmSapoBLEmSJFVlxIgR4SFJktRa7EIoSZKkqgwdOjT87d69u2tSkiS1CjOwJEmSJEmSVNMMYEmSJEmSJKmmGcCSJEmSJElSTTOAJUmSJEmSpJpmEXdJkiRVZZpppnENSpKkVmUAS5IkSVXp16+fa1CSJLUquxBKkiRJkiSpphnAkiRJUlWGDRsWHpIkSa3FAJYkSZKqMnz48PCQJElqLQawJEmSJEmSVNMMYEmSJEmSJKmmGcCSJEmSJElSTTOAJUmSJEmSpJrWua1nQJIkSe1bt27d2noWJElSB2cAS5IkSVVZa621XIOSJKlV2YVQkiRJkiRJNc0AliRJkqpy//33h4ckSVJrsQuhJEmSqjJy5EjXoCRJalVmYEmSJEmSJKmmGcCSJEmSJElSTTOAJUmSJEmSpJpmAEuSJEmSJEk1zSLukiRJqsqSSy7pGpQkSa3KAJYkSZKq0qtXL9egJElqVXYhlCRJkiRJUk0zgCVJkqSq3HjjjeEhSZLUWuxCKEmSpKp89913rkFJktSqzMCSJEmSJElSTTOAJUmSJEmSpJpmAEuSJKmED0b/nLz22ffJv/+mriNJkqQ2ZA0sSZKk/+eff9PkxY+/Sx56e1Ty0FujkpHf/BKen2HKiZLVF5ghWXOBGZJl5+6aTDzB+K4zSZKkscgAliRJGqf98sffyZPvj04efOvr5JF3RiXf/fpXg2lG/fhHcsPzn4THpBOOn6w4z7TJmj1mTFadb7qk6+QTJeO63r17t/UsSJKkDs4AliRJGud89cPv/5dl9fao5JkR3yZ//vNv2e/99c9/kgfeHBUe43VKkiXmmCZZY4EZkjV6zJDMPd3kybioe/fubT0LkiSpgzOAJUmSOrw0TZO3vvwxeeitr0PQ6vXPf2iRz6U01gsffRceJ9/3TtJt2slCIIuA1uKzT510Ht9yo5IkSS3BAJYkSeqQ/vz73+S5kd/W1bP64offW/07qZl1yRMjw2OaSSdIVp1/+lA3a8V5p0smn6jjXnYNGjQo/O3fv39bz4okSeqgOu6VlCRJGud8/+ufyWPvjk4efHtU8vi7o/+/9s4DTIoi/cNFRnKOknMQDKACKgpiFhRzRPH0Ts+IOSCGEyNmPZU7UU4RFAEDIgKiguEUQckSRUlLlJx3/s9bXu2/d7ZndmZ20u783udpV7qnU1V1dX+/+r6vzPY9+1N2LeTSGjNzlV1Klyhuujav/meoYZvapk7lsim7LiGEEEKIwogELCGEEEIUalZs3GEmzf8znxWhfMwkmG6QYwthjeW+cXPNIfUr/y9vVi3Ttm4lU6xYsVRfohBCCCFEWiMBSwghhBCFiuzsgPlp5R9/ilbzs8ziddtNYYMcXCzPTF5k6lUum5M36+im1U3pksqbJYQQQggRjAQsIYQQQqQ9u/YeMNOXbLCC1ZSFWWbD9r2mqEBuruHfrrALebK6t6pp82Yd36qmqVKudKovTwghhBAiLZCAJYQQQoi0ZN223ebzBX/OGjht8QazZ3+2KeqQs2v87DV2KVG8mOncuKr1zOrVtrZpVL18qi9PCCGEECJlFAswr7QQQhRS2rVrZ//Omzcv1ZcihCggfJIsytpuBSvCA3/6/Q+VqYcWtSrkhBoe1qCKKV48ffJmbdq0yf6tVq1aqi9FCCGEEEXULpMHlhBCCCFSxr4D2eaHXzeZyfP/9LT6bdNO1UYIyPXF8s8vlpoaFUqbnq1JAl/bHNO8hjmodImUlpuEKyGEEEIkGglYQgghhEgqW3fvM1/+st4KVlMXrjNbd+9XDUQJOcBGzfjdLmVKFjfHtqhhPbN6tKllalUsm/TylAeWEEIIIRKNBCwhhBBCJJyVm3faBOyTF6wz3y3baPZnK4NBvCA3GOXKAoc2qGJzZiFotaxdwRQrlvhQw5EjR9q/1113XcLPJYQQQojMRAKWEEIIIeJOdnbAzF29xYpWkxasMwvWbFUpJwlyh7E8OfEX07BaOStkndi2luncuJopVaK46kEIIYQQhRIJWEIIIYSIC7v3HTDfLt1oJi3IMlMWZJmsrXtUsimGnGKvf73cLpXKljQntK5lBa3urWqaSmVLpfryhBBCCCEiRgKWEEIIIWJm4/Y95vOFfyZgn7Z4g9m594BKM00h19gHP622S8nixczRTaubE9vUMj3b1DYNqpVL9eUJIYQQQoRFfuRCCCGEiIql67ebV79cas795zem0yOTze2jZ5uJ87IkXhUiyEE2fckG88BH882xT0w1pzz7lRny2S9m9so/bPinECK5fP/996Z06dJmxYoVOesaN25szjjjjJRXxV133WWOOuqoVF9GoeH444+3uQdZ0qH+RHw49NBDVa+ZIGC5h9ctxYsXN1WqVDHHHnus+de//mUCgUDKOpVff/01oed54IEH7HneeOONiH7P9QSXV5kyZUytWrXMEUccYf7617+aSZMmhSwztz8vu0yBe01Gctp04McffzQnnXSSfX5c+3BteMeOHebGG280DRo0MCVLlrTbaH9CCBEP9h/INt8v32QGf7LA9HjqC9NzyJfm0QkLzYwVm00KXuMiASxcu8288PkS0/vFr02Xx6aYe8bOsTNEEhYqRKbBt7v3e5xvq/r165srrrjCrFq1KqxgEby0bt06onPee++95qKLLjKNGjUyyeD33383Dz74oDnyyCNN1apVTY0aNex9TJ48Oc9vb775ZvPzzz+bDz/8MGHX8+9//9u0adPGlC1b1rRo0cK88MILEe23fft2M2jQIHPKKaeYatWq5Wt7vfvuu+boo4+239PVq1c33bt3N+PHj8/zuzVr1phrrrnGNGnSxBx00EGmWbNmZsCAAWbjxo0RXRf1/p///MfcdtttJtFlMG/ePHPeeeeZpk2bmnLlytm6PO6448xHH33k+/sXX3zRngc7k3bNfWFL+LF06VJz8cUXW3uUcuC6aKsFIdb7hD179pg777zT1KtXz14Pwir2sZedO3eal156ydpNdevWNRUrVjSHHXaY+ec//2kOHMj7TsvOzjZPPPGErWuuqUOHDuadd97J87vBgwfbOqV8RQaEEPbr18/+pdHwIHz99ddm+vTpZsqUKb4NJJMpX768Offcc3PK648//jBz5841r732ml0Qs0aMGGFatmyZ6ksVSWLbtm2md+/e9mXKxwVCFS/oChUq2O1333237fybN29uzj//fDuCxyhBMuBj7s033zRTp0611yaEKBps37PfTFu03uazQsjYvHNfqi9JJAlyl4347292KVe6hDm2RQ2bN6tH61qmeoUyvvto9kFRFHnooYesUbt7927z3XffWWEE+4XvcgxdLwcffLB59NFH8xyjcuXK+Z7np59+ssLRN998Y5LFBx98YB5//HFz1llnWTtt//79Zvjw4aZXr17m9ddfN1deeWXOb+vUqWP69OljnnrqKfs9Gm9effVV87e//c2cc845VkyZNm2aHZhFiECsCMeGDRtsPTVs2NB07NjRfPHFFyF/y7cyxz399NPNY489ZuuVOsVL6v333zd9+/bNEcW6dOliRR36Nr67EfAQfvjeZVAZp4xw1K5d21x66aVJKQO89rAVqEeEHfbhfqgrjosQ5+BYiDXYmjfddJOZP3++LRdEsIkTJ+Zpl3zbI3LdeuutVvD77bffrPgZKwW5T2d3jB492oqqiF/U32mnnWbr5ZhjjrG/WbZsmbnhhhtMz5497TkqVapk74265DnGbvGCIEd7uPrqq03nzp3ts4Foh6114YUX5vyO88B9990X8/2LglMskGAXKOcdE3walFIaAZ0l6nAy3St5EL/88kuzfPnyhHor4QHDyMawYcPsw5YfeNPwkmTkxc87jI6Th/Dzzz+3neIPP/xgO9RI9y+KUH902qnw5Esm1Dmd8GWXXWY/LoLhpc0LfN26dTmiVrJItYDVrl07+5cXrxCiYKzZsstMWfBnPqtvlmw0ew9kq0hFDnzSHdGwqjmxbW0raDWvldz3jRDJAqMYAYdv7U6dOuUKpUP0GTVqlB0wdPD9w3cYwlYsICSMGzcuJ5rC+53bvn178/HHH5t4w3cT9oTXmwTvFgZAEXCCRQoEEbx8lixZYj194sWuXbusPYNXlPc+EX8oE64DD7FQcM2bN2+2ItuMGTOsABHK9mLwH8+r//73vznlvHXrVivQ9OjRwwoXgKPAJZdcYq8HscuBpxdi2cyZM61HTyjc93A4MS2eZeAHThA4PSDSLVy40K5jIBybAU8/rz2BMIfgg4fdmWeemeOVhCCIYwXf+Hg7FZSC3idhtnhcPfnkkzmebdwfzwgeYk4A5lnMysrKsREc/fv3t21j8eLFdtAf8KjEfkbkoxwAuxLPPLQCnskSJUrkOk4in8vCTrsk2GUpy4GFuo8xDjRYkT90Ip999pl1h+Sh5GUnMoOVK1fav6E+GNhOx51s8UoIUbjhI23e6i3mucmLzZkvTDddHv3c3Ddurvnil/USr4RPezE2bPSxCQvNiU9/acNJCSslvPSXRYutYStEUYYUKEA0STzBFkJAiSQtBoOGhDTefvvtBTY0g0OhCCnDwYDvSjx6vJx44on2rxN5HIgiCCT79sXmpYs4QlhesBfn3//+d+sB5RfeF3zNiFeRgFjF97K3nPHO4fvZK9DwO0Dg80I4GsRDzIlnGfiB6IJYRCSP49tvv7XOI16vInD/HjlyZM46bE4EWUQ77hcPKb/wu2TeJ55X3JfXowxPyKuuusremxNdadfB4hWcffbZ9u+CBQty1tGeabvea6J9XHvttfY54LgivUhpEnenXAcr/MSW4gJIh0IcL3GouOSisPrBA/Xwww9bJZQHDFdd4n69D2GkbNq0yYZjtW3bNudYvFDCKayo1biZcq24VuISuWjRIpMIeGhRh3mweNnhxpkIXC6tvXv32pEG4rh5QeBmDNQF8cu4EyOqUFaMaIQrd0ZCOC6jEV999ZUtV2KSqWdGN3BhDaXW49rp4pKJQacz5drC8cknn1ihFCWf/Vq1amVHzrwduV++MtyCTz31VHs/xNIzwuYEJDrXO+64w5YNx6TN0ZnGYjQSOksZuOsjFpzroD073EicC8HFo8/lVKA8Xc4FjocnmjfnQkHbNc8lLr2MVrEPZcEoJNfgXuycx7nhnnDCCbnO77wAuba3337bPtN8CHCvvFD5ECI+XQiRXPbuzzZfLVpv7v9grun22Ofm9Oenm2cmLzJzVm1RVYioWLZhh3ntq2Xm/Fe/Na+9M9YMf+9DM2HOGht+KkRRxH3b+HmJYNzj+RG8hMot5MADhO/5ww8/PN/zk0oEzzC+Z/FCceCB5Hfu4MX7jRmKtWvXWpuGxQvfjnyDkwbGC9+XfMP65QaLhFmzZtm/Xk83wHuIMD23PR7w3fzpp5/akDnqEuEN8WTLli25HAOwZzg36wg5ww7ArnjkkUesLRRpXrNklwFtjXpGYH3mmWfMhAkTbASH11vNT4BzdY0N5HC50LD/uC48sfgdYhd2RSruk+3YJdiOXsjj5kIe82vb4BVuOSb3Rhv2O2Y8258oZDmw/HDKPg+Gg0TldM4YuRjYPCgIHvfcc48NNeRh8naoHAPDmQeuZs2aNhSRh5eQK2JqUU2fe+65iK4H0QmjGsMdgeLkk0+2x6fjwp3S667oeOWVV6xCi8HOqAzKPL+n0TsXzHhDvC8POm6yhEI6T7Z4g+sonTRiE26UCIkIdECn/5e//MXGWSMMcb90CrhuUu68EEIlEaceqRM6L0Z56Gx4KeDOi9LvHUVBpKIeOCYfCwhddL7UBR1KqNBBBE/aDCNUXDsdFS9c3L7Hjh1r7yl4VAW4BuKyEaY4Ly7C7733ng3fxG0VQQyhiBcbLwjKH4GLFwS/j7RccZVFwGLEh3Lg3qhPxCGORZvn5cJ2xCtGtbl+vPBcbisEIV6gtFVEJG/utIK2a8qbuHnEPvbhdwiJrl4RLrkOro1cELwoOa637pw3GIIfORN4zik36oK2Mnv2bHtffDgIIRLLHzv3Wq+qSfOzzJeL1ktgEHHnQHbAbN29z1z79kxTukRx06VZ9f+FGtYydSvH11tBiGSBsMH3HgO3fCPyncb3jF/qE76RsEWCwbbBXgiFC+9ioDYczz//vM37w8BycA4enAK8sxeGggHgcJP88F02ZswYGyoYHDYFDFqHGnCOFTy4OBeeUV7I54rdsXr16ridizKkPhmgZQG+S8nJjDOCgwFf7FG+j73r+e5lErJ4E68yIE8VOaYAQYicXi4sDrDZAJsC+9n73Q9eEZIwO8DOIUE+QiX2EDYWNgXf/9FOpFXQ+2R/5wXnxa0Ltz825bPPPmufM8JMvcfEJgy+l0iOKTJMwEJ4cN4fCCMutprOAlEEAx6hxr08eFHwoNx///3WGHYgUiBe8RDiAohHj3sZIFzQUSE65Jdji1ETjH8eSBLb0QG45Hx05oTtMdrBA4y4AbwobrnlFlOqVCkryjgBAzdERkfeeustkygQDxA8vC6Q8Yay4CX9yy+/2NhwL7ygyWOGqu994IkVRnjEIw4PIb8cY3Qe1LXz5qLsL7jgArvu5Zdfti9mB6MHdKq8mDmfE9CoE+rXr1MhXwEvdgQUBE837S/CF2IfghSiiZ/nFB8YzFCBiOXqEpGN43Tt2tUKNCQGRCwCvNAQ8piVIlIBa8iQIVa8YhSIv070oWPFfZVj8oFEMkFeqniFsfCyocz8PjwQsNxvC9quGVXBixDxCnGLvGveRJWIwjyjwPmoZwQsjhOcA4sPPka5eC556Xk/znBhlluuEIlj1R+7rDcM+ax++HWzFRiESAbkTkMoZRk4zphD6le2ObNOaV/HtKrz53eaEIUBFzbn4LuW73sStgfDtqFDh+ZZ7/dbL25Wu3C5f/iGc8m3/UIH8XRnoDE/wuWuwjsL4YoBVL5B/eAagz1S3HdqrHDdCBh+4NAQyX1FCk4QiDjUCbYhA7rYGgg92BsuLxJg+zBAjx1AfmG2Y1fyve21ReNBvMoAgZPvfuwjZlvEDvBGrODlh13EgD73h/2MLYkzBvas9zzkQQPEHmfTYh9QhohZiH7Bz0ei75PtXscX775ueyiuv/56K74SpoiDQzyOKTIkhJAHCUWXJGoYrzQYN8sFnYIbHXDilXNZJdQIoQRV2YUS4mmFsY9xjfDhxCvAM8WNTkTigYUANWfOHPtg8mLwGux0ZogOXLv3xcQMHVwLifC84gUdAOcMdr2NJ871EZfhRILKHixeAUISnVawWo1AQbgfXkahpm6lvJx4BSjxdISAZ5QX6hUofydeuToZOHCg7/EZaeD8JCN04hXQ1tjGixkvLL8ZNPBqcuKVq0uO40RRxC0nXgHiDXVBW44k9h/Rho8PjkGopddjiQ4dsYd1CLncQ0GJpV0zsrR+/XorajHyFDzLCiNRwSMnoSDUEOEQl/PgkUVeHi6XRCQQy+63xDsPhRBFhZemLjH/GL/AfLdsk8QrkVIITyVM9Z6xc1QTolCB/cEAKoOeCBl47/gZu8C3Hd/GwUuk4Wahogrw9ke8YgmV96pbt26+5w5eQglYfAsSGoaBz726gUq/a4zW68bBtyUe+G5xAgnf5aHSgmBnxTPfFAId4ZoIbgg92KA4TXB+7BcHg8YIXIQMEkaI3cI3M7bl008/HbMXWqLLgLZGPV9++eXWUYTjE0XhbVs4DBDRgS3Otznb8bLCWcCbS9edE7vNC7PzQSwzZhb0PtnuwiCD9/VeczAMyGPr4GDhZhIs6DFFBghYLi8ORiuxq3QcCE54oGDcYvwT0gTM+hAMXlosPIguvhXPK1RR1GS/l4MLraMTyk8MIFEduOlTg3GGNmFkwe6WwYnwALEF75ZE4TqiWF8ikcCx8wuDxCvuH//4h1XueQkg6ODh5HU9DcavXGgTzo3TwQuGBbHE6+bqCO5Qg+vFrx1xLM5PewiO4Q91be5lz8iau06v+MaoDO2Xj5r8ICSR3+HN5RfCSCdJeCjCZKjyi4ZY2rWLecflvaBQ3oxy8czioYX3mhAiOZQpmdI0l0LkoazapChk4IGDIMBAIDlv8VbHgHfCQzxwA7ShBqUZrMNriBzBRDpEIoyEWkJd99VXX20FD+wzIilCwTUGJ36PFDx5CMtyi/Ni4v8R0JhJ2wtCB95pocS0aOEblPxXpMjwQo5XBrC9dgEOE3ynB+dqYl9ssFjEm1SUASIdkSne3Mw4JmC/sQ7HAfJ7MbjOwL7XznHnDLZX3CB2LE4UBb1P9vfaig63zm9/2jTiLw4KwaG37pg8G8ECcrhjigwJIXRJqPHmIPHaIYccYo1q5y5Lo6Xx0il6PVy8ICAQhuTic134mF+YGpCEG+8tQhB5yLwePKGSMiJ6+AkfDq9I4c6PgBHqehOFuw463URBBxVqlIkypf7INRaK4NlLwrlSO+85rwKeX/lSt9RxcFL2/NqFW++XbNLP28yNRvht8273U+9DtTNG8/ITH6ljF6seK7G0a+eZhrAcDwhvROTFXZmF+iT8k3Uky4+UUNOx+s0yIoQwZuDpbU2fQ+ubyfOzbBjhwrX+fbIQ8WBbwP97oX6Vg0yvtrXt0rlx4r5ZhEg0DFoSmcCgKh79DMzFAzcIH0qcwjbCKwqRhdQdiA/BRjXCSKw5sPDqGjZsmE3xEWpw2ME14r0TC8Fhjm6A2OV2JTWK1zuGfzPg7LYXFGZwB7+Z9BiIJkrC+9tQvwPvb9O5DNy5sNuCIdrJRTzhUYZggyOCgwF1vJaC7SVnZ/nle8uPgt4n25nJkAgPbyJ38tN5j+8gvRCpXrBZQ00cxT5EnxBKSe6z/I4pMkjAKkhstCMWb6NI93EeWoRN+XnGOGIddYg3Lv7c+6DFGxf76wdKNuIVQgT5mhiRQkzi5Y7XDyGVoVyhg0PSkk24NhHu2uJx3a6dEb6Hu3c4wgmu0Z4vle2akTzybTGyx8gXrtrDhw+3CyOascziKITIn+LFi5lDG1Sxy20ntzK/bdxphSyW/y5XWKGIL1P2/n/qh44H/5nziiTuretUTKi3uBDJhFyfeGUh9pBvKNy3cqQwQMrszBjxoWDwFw95POfJ7YvnjPc7MdYcWIRW4QVETmHvLHx+IIKQtoGoCy8IH2xj4JPUG6EI9d3LdyID8qTp8Ioa/Jt0LEzg5HCzKTZs2DDqVC18e/MtP2rUKBtl4PolPJCI3kAgdOCJhD3DN6s3vyuRQ0C4XSwkqgzwaApO74HYxrc20R3h7EVsBSZc4ljeNCpM2ESbQNxE2HJ2kEtiTzuMloLeJx5ltFeXYN85EHCNpI3hOXLwjDBYzgRSPB+h7Djuk5zWpK1xCe+xYcmLzLNJ1IxIL1I6C6EXOmFyALnpZv28sJw3ifOEcaMPoUYc6EzxzuHBDZcY0esVhEqLUR0JuByS4Jzz+3UMkYyExAKhZQhYPIg8lKmAHFKIVbhTB09lGq8wMTf7Q6hyRH0P9r5y7YIRolD1EtyOkolrZ4y2xUPUjfR80bRrOn/yffGRgqdkPKCN4HLv4uYJFyYPAXH4zEAZHI8uhIg/DauXM/2PaWKXLTv3mS8WrTOTF6wzXyxcZ7btiW00WQgoXbK4OaZ5DSta9WxTy9SuVHCjXoh0BY8lvmH4jvMa/NgdoSZwYvbpcGBE820dLscUAgyiCoIKA8UMJLtv8PwGRf3gfAgXeOG0adMmz7UjUHgHPxHQuD6u1Qt5bPG259s7lugT7DRyEzHBEuXqZh/neshB5Y02QWBg4BwvHK+wxHpsAucdRA5YhCkgly1RG3gMkfcJAQZPNrxyiBZBuED8c/l4XcJvRBFSqbA/0QPkIkPAoly8OXbjQUHLAEEOuwi7EPuGkDhEG77nyd3lzW2FKEV+JzyLELlGjBhhU4lQh4hFDnLykheMCdQYCCcPGJFQeGXhqeedyY9ngVQyTuxK1H1S7uxHXSHa8Uxw3dh25MV2YAMS7smzhOjl0tsEpyZythJiNGIu5cF9jRs3zl4XZeg3G6dILWkjYKHYH3300VYtJbn1VVddlWv73Llz7UPDA+hc+XBt5EEgFxaijjfxO7iOmE49P+8ZOiMaPp15pIY+oyAo88zyEBwKxUxuLv9QPMGdlU6VFwgPZH4zmyQKQjJ5aQaLV0B5xANeFogphLTx0sDbywvtJFS98BLlJUMnGZwjYOLEibZDi+VlX1DoFHmJcj+0kUSGgMbarsn1QIgjoxveZPuhcLOJRONOzbNOjjpc8Xm2JWAJkVwqlytlwwtZ9u7PNj/8uslMmp9lF2YvFCI/qpUvbXq0rmVDA49tUcPM/WmmMWatqV3p/w0gIYoiCB94G+EJQu4oZ+AimLj8u9EKWAgrGOzkYfJ6AgXDwOKECRPstxriCp7tsSaZxq4CbCi/60Y48ApYiABcW7xSTHhhFm5sQcQWBsf5/md2wPy8whzUhXfAe8yYMXZxZc+3t/P0IQSSb2MnWPFtjqeS1ymAFB7Yl+RMwp5EEGKAHK8fRJVEUJAyYDZ37on7Iy0PqVmwk0ndEZzzC+8xPAidVxIehcwo6JdvmPvHCYRJphB5vKKWF5dbzTkfJOo+gbpiIi9ywmGPIkQR5eGtP+xAFzaJWOYXSusELGDWTe6T3GeIcWgK1LsbeBfpRbFAqDiveJ3gf6MIkZyGUCJUVUQZDHzn5oo6TifNultvvTXX1KWIOcS0YqhjpDvPLRLTIXjQ4fBweJORo+JyLO9IAcY3HRoxwA899JAdkfDmf/Im7HPCB/szYoHrJV4kbipR1Fs8XnjAID812oF6zGwQCDfOS8jL7NmzrYsjIy50ELgae2Pg89s/2noLdxxCBslJhIhEp+mgAxowYEBO3jOvlxFlgEoePGoS7pwIHLg10wkjCDrBBy8vOioXl+1tX4wiMFMeYicdskvASI41ZuXAdTg4dI18ALyQ/OrKlSvtCcEyGL/2FI7Bgwfbzp/jMZNlsDs390Qdez8m3MiGX+6CUGUXa7tGWOPFjTeke6F4RwPxnuKanauyKzs+vIJfEiTh516Y3cTr6s3IDy9KjsXIT345F8LhcmCFypElhIgc+gRyZbm8WT+vzJs3Q2QuzWqWt2GBvdrUNoc1rGpKFC+WZ9ZgjBMhRPTgFcR3PYZ5uoE9xbcw3/3BHljC+NoG2IPkYGKg12/AvyjBdz42iHdSqKIIXn7YVkwg54QzkXy7LG08sACPomuuucZ6fiCQECeL0YtogOcMXhsY4V4QODCC8RjBqEYUIAQRoxkj+cYbb8x3Jj1gdkTcBXFlRFXGGKdhYqRjyDOLGq6KGPTO0KcjRz1GRGM/BBWUaa4HRZik2ajb0cL5nIiCxxUKMo3AheYxUoDRH2pWBGLRKatQoFp7Y4xjgVELRjSILUZARHRkJAdXVUQ2yikeIFiOHz/ejkjhJkqbINYZYYoXPaNeiCReGEnA8wqRCCGLlwg5njgG3lyo6qES+SUDkn5STnygIIAyEkJbQmAjJBWxibYXahQvGmJp14iEjLIxYkNdPv/887bN4V5NgkPyWRHC6gQsni+eS0aleA5dPi1GfRDDEN4QthASaSc8n4hmPNOsCzVDohAi+SBWt6lbyS439GxhsrbuNlMWEGqYZaYv2WC9tUTmgD7VqXE1K1gRGti05v+HoQgh4gsDnEQRMLt3qAmMUgUeO3h/SbyKHL51CVvE5irKQgcDX9jqocJnixLYlM5z0evBJZJLWglYgOse7qkkTsOrBZUTV1XcFjGmg91kcZHkdwhJeNbgbYXSjWHMKGA0nh0IGxjmGPm4nSJEcX5EKUQGDHoUZi8Y5sQa43rIbAUkc0TI4t+hQtzyAwMfTyXAxRK3V2KSEfcQ+fD0CpcQFSHEzZzgB8JBQUGcw9USoQgRZM6cObbMGYGlI4uXgEVd4nnFyxwxkJh2hDvaAt5I3uleveC1hecR18H0sYgvlCEeSAhI+eVESyS46+KdR10i1nJ9M2fOtNeEGy25FbxebQUllnbtOmim1cU9HREMjzaENsQqr/s43nG8tHgGqSuXRBS3Y37HegRHhDlGZvCS5DjUEW061EyXQojUQy6ji49qaJede/ebaYs32DDDzxeuM5t27E315YkEUK50CdO9ZU2bz4oQwarl/wwTF0IkFvL78A2fjmDXiMjh2xdnhlhn6ytMYJMyGJ4JoFMQGZYJ9ZrRIYRCCJFIFEIoRPI5kB0ws37bbCYxq+H8LLN0/Q5VQyGmTqWy5sS2taxodXTT6qZsqeiT1iqEUAghhMhs2mVaCKEQQggh0h9yHxFaxnL3qW3MsvXbbaghgtaMXzeZbA2NpT3t6lWyghVJ2Pn/cJ7dQgghhBDpgAQsIYQQQhQIciOxXH1cU7N5x14bYkjerC8XrTc79x5Q6aYBpUoUs95VCFY929Q29avENnNZKIInJBFCCCGEiDcKIRRCFGoUQihE+rJ73wHz3bKNVsyaPH+dWbt1d6ovKaOofFApm8cKT6vjWtYwFcuWSvUlCSGEEKKI0k4hhEIIIYQorJBL6fhWtezycJ+Ambd6q00Cj6DF/4v406h6OTtr4Ilta5tOjaqakiWKq5iFEEIIUSRQCKEQQgghEg45ltrXr2yXW3q1NKv+2GWmLMiyghZeWvsOKHFWbOVqzGENqljBCuGqea0KKclnxYy1cMoppyT93EIIIYTIDCRgCSGEECLpkIPp8i6N7bJt9z7z1aIN1jOL/Flbdu1TjYShbKni5tgWNa1gdULrWqZmxTIpL69ly5al+hKEEEIIUcSRgCWEEEKIlEJuptM71LXL/gPZZsaKzWby/Cw7q+GKjTtVO8ZYkerENn/ms+rWvIYNzxRCCCGEyCQkYAkhhBAibSBnE7Plsdx7ehuzdP12M2n+OjNp/loz6/c/TCCDIg1b1a5oTmxby/RqW8d0qF/ZFC+e/NBAIYQQQoh0QQKWEEIIIdIScjk1r1XRLtce38ys37bHTF24znpmTVu83uzel22KEiWKFzNHNalmvaxYGlYvl+pLEkIIIYRIGyRgCSGEEKLQhNGd37mBXXbvO2C+XvJn3qzJC9ZZcaswUrFMSXN8a0IDa5njW9YylcuVSvUlCSGEEEKkJRKwhBBCCFHoIAdUzza17fJIdsDMXrXFhhlOnr/O/JK1zaR7Avtebf/0sjqySTVTumRxU9jp1KlTqi9BCCGEEEWcYoFAJmWTEEIUNdq1a2f/zps3L9WXIoRIE37buPN/nllZ5r/LN5kD2an/1Ol4cOU/QwPb1jat61S04ZFCCCGEEEWFdkmwy+SBJYQQQogiBbmj+h/TxC5bdu4zXyxaZ8MMv1i4zmzbsz8p14BX1THNa1jRqmebWqZ2pbJJOa8QQgghRFFFApYQQgghiizklOpzaH277N2fbb5fvsl6Zk2an2VW/bErrueqVr606WHzWdU2x7aoYcqXyZzPrHfeecf+veiii1J9KUIIIYQoomTOl5UQQgghMhrrFdWihl0GndnWLFy7zUye/2eo4c8rt8R0zGY1y9uwwF5tapvDGla1MwlmIps3b071JQghhBCiiCMBSwghhBAZBzmo2tStZJcberYwWVt3mykLCDXMMtOXbLDeWn6gT3VqVM2c2PZPT6umNSsk/dqFEEIIITIRCVhCCCGEyHjIUXXxUQ3tsmPPfjNt8QYrZn2+cJ3Zve+A6d6yphWsTmhdy4YKCiGEEEKI5CIBSwghhBDCA7mrTmlfxy7MYLg/O9uUKVlCZSSEEEIIkUIkYAkhhBBChICcViWKS7wSQgghhEg1ErCEEEIIIUSBOOmkk1SCQgghhEgoErCEEEIIIUSBaN68uUpQCCGEEAmleGIPL4QQQgghhBBCCCFEwZCAJYQQQgghCsTLL79sFyGEEEKIRCEBSwghhBBCCCGEEEKkNRKwhBBCCCGEEEIIIURaIwFLCCGEEEIIIYQQQqQ1ErCEEEIIIYQQQgghRFojAUsIIYQQQgghhBBCpDUlU30BQgghhBCicHPhhRem+hKEEEIIUcSRgCWEEEIIIQpEtWrVVIJCCCGESCgKIRRCCCGEEAVi06ZNdhFCCCGESBQSsIQQQgghRIEYOXKkXYQQQgghEoUELCGEEEIIIYQQQgiR1kjAEkIIIYQQQgghhBBpjQQsIYQQQgghhBBCCJHWSMASQgghhBBCCCGEEGlNsUAgEEj1RQghRKxUrFjR7Nu3zzRr1kyFKIQQKcLNQFitWjXVgRBCCJGBLF261JQqVcps27YtYeeQB5YQolBTvnx521FmykuBRaQe1UX6oLpIDzZv3mwXkXr0TKQPqov0QXWRPqguim5dlCpVytpmiUQeWEIIUUho166d/Ttv3rxUX0rGo7pIH1QX6YHqIX1QXaQPqov0QXWRPqgu0od2hdC2kAeWEEIIIYQQQgghhEhrJGAJIYQQQgghhBBCiLRGApYQQgghhBBCCCGESGskYAkhhBBCCCGEEEKItEYClhBCCCGEEEIIIYRIazQLoRBCCCGEEEIIIYRIa+SBJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIdIaCVhCCCGEEEIIIYQQIq2RgCWEEEIIIYQQQggh0hoJWEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgiRQr7++mtz2mmnmWrVqpkKFSqYI4880gwfPjzq4zRu3NgUK1Ys7NK0adNc+/z6669hf1+nTh2TScSrLt54442w5XrhhReG3HfevHnmvPPOMzVr1jQHHXSQOeSQQ8yzzz5rsrOzTSYRr7r48ccfzQMPPGC6du1qqlSpYkqXLm0aNGhgLr30UjN79mzffTLtudi1a5e5//77TcuWLU3ZsmVNvXr1TP/+/c2qVauiPtbmzZvNTTfdZBo1amTKlClj/958883mjz/+CLnPgQMHzDPPPGPbOm2etn/++eebBQsWmEwjHnVBWY8YMcJcdNFFpkmTJrbNV6xY0Rx11FHmueeeM/v27fPd74orrgjb7l955RWTKcTrmcjvvbxw4ULf/fRMxLcu8nsnuyX4HaNnIve79LHHHjN9+/Y1Bx98cE6ZxYreFamviz8K8buiZMLPIIQQwpf333/fXHDBBVacOO6440yNGjXMlClTTL9+/axx/dRTT0Vccueee67ZsGGD77Yvv/zSGuXHHnus7/batWubU045Jc/6ypUrZ0zNxbMuHB07djSHHnponvV8HPjx7bffmp49e9oPdgQbjJ+vvvrK3HLLLeabb74xo0aNKtAHY6bVxf79+02nTp3s/yOEIWKVL1/ezJo1y7z99tvmvffes395djL1udi9e7fp0aOH+e6770zdunVNnz59bF8xbNgw8/HHH9v1wcJ3KOh/unTpYpYsWWL3Oeuss6wgy4fwhAkTbPumHrxQxwi2Y8eOtQLj6aefbo8zevRoM378eDN16lT7LGQC8aoLno9HHnnE9hX0P/Q369evt6Lw999/b8t24sSJply5cr77n3zyyb4ibatWrUwmEM9nwkHf5YdfX6JnIv510bx585B1sGXLFjNu3Dj7/8ccc4zvbzL9mYCHH37YfPDBB3E5lt4V6VEXTxXmd0VACCFE0tm4cWOgUqVKAbrh999/P2f92rVrA82bN7frp06dWuDzHDhwIFC3bl17vEmTJuXatnz5cru+e/fugUwm3nUxbNgwu8+gQYMi3mfv3r2BJk2a2P2efvrpnPXbtm0LdOnSxa7nuEWdeNbFvn37Ap07dw6MGzcusH///lzPxL333muPVbFixcD69esz9rlw5UAbo605hgwZEnUZXHLJJXafvn372rJ33HDDDXZ9v3798uwzdOhQu61Fixa2jh2jR4+266lz77GKMvGqi8GDBwfuuOOOwIoVK3KtX7RoUaBhw4b2WHfffXee/aifeL13CjPxfCYaNWpk94kGPROJqYtQvPzyy/ZY3bp1y7NNz8T/89hjjwUGDhwY+PDDDwNr1qwJlClTJuq27dC7Ij3qYnAhfldIwBJCiBTw+OOP2xdAnz598mwbM2aM3XbGGWcU+DyfffaZPVb9+vWt4Z6phnoy6yIWAWvUqFF2n44dO+bZ9uOPP9pt7du3DxR1kvVcZGdnB1q1amWP98Ybb2Tkc7Fnz55A5cqV7b3OnDkzz/YOHTrYbTNmzMj3WKtXrw4UL148ULp06VxCFOzevTtQs2bNQIkSJQJZWVm5trVp08aeY+zYsXmO2bt3b7sNMauoE8+6CMeIESPscRo3bpyWRklRq4dYBCw9E4mpi1B07drVHueVV17Js03PRGhiFU30rog/ZQogJhbWd4VyYAkhRAogPAb8wpcIoyHXw+TJk60LfUF466237N+LL77YFC+uLj+VdRHrNRx++OE2TGLu3Lk2fKIok6y6wGW+Q4cO9v9Xr15tMhHCBAifadasmTnssMPybHd18NFHH+V7rE8//dSGPhGmTOilF3JhnXnmmTavzyeffJKzfvny5TbPFXmvqNuCnL+wE8+6yC+sOZPbfLrUQyj0TCS3LihvwvPJ/UPePZF49K4oHHRM83eFcmAJIUQK+Pnnn3PEiWD4mGrfvr2ZMWOGWbRoUY6hHS3kUiK3DJC0OhRZWVlm0KBBZs2aNTYnB3HwvXv3tteRCSSqLki0efvtt5utW7faPAHk8ujevXvU1+DWL1u2zOaAIjdWUSUZz4WD8oRQSdmL+nMRSZuDUMnuoz3W66+/nutYbh/qtFSpUgU6f2EnnnVRkDYPY8aMsXnoEBxJ7Iv42Lp1a5MJJKoennzySbN06VIr5rZr186cffbZdrKCUOfXM5GcZ8IN8CGgV61aNeTvMvmZiDd6VxQOlqX5u0IClhBCJBkEDUYWgRlE/GA9hvqKFStiNtRJTLpt2za7f7hjMBPSQw89lGtdw4YNbZLrop5AOZF1QZJZFgdljIBFMvZgL5Xffvst32sArqGokqznAqZPn24FRsQov0TtmfBcxLPNxXIstfnE1EU4SKgPJMMOxQsvvJDr33feeae59tpr7b4lSxZtsyFR9XDHHXfk+jcTc1DOzKaXjPMXRpJRFk7Auuyyy8L+LpOfiXijd0Xh4Lk0f1conkQIIZLM9u3bc/4/1OwezJYGCFCx8p///CfsxxmjwbxsvvjiC+ttgoDATGGnnXaa/chghpGi/qGciLpgtqQHHnjAznaHILN27Vrz4Ycf2pEpZoQ844wz7IiV33Uksj2kO8l6LmjnznDEkKS+MvG5iGebi+VYavOJqYtQMLU54bfM9njXXXfl2U6YFr/Bu3Hnzp12BP6ll16yv3/55ZetN2lRJ971gMcmXgr0F5QpYeADBgwwe/bsMX/5y1/yzCSmZyJ5ZcEsa7R1Zkb1C2EGPRPxR++K9OeVQvCukGwshBAxQAgA+VuiYfjw4Unz3Fi3bp2ZNGmSzXtF/is/MNx52Xg5+uijbR6iSy65xIwYMcIMHjzYvPrqqyadSbe6QOBgcVSqVMm6Vp9wwgnmiCOOsB5E7777rrnoootMUSPd6iIYhEPa9uLFi+05gz2sitJzIYRj2rRp5qabbrK53wjlrFevXp7CYbsXQkKuu+466zVKuNaLL75oxZcGDRqoYCPk+eefz/VvwgeHDBliBzOuueYa67EQzsNBJA7nfUXuq1Bh4XomRKYxrZC8KyRgCSFEjMk/f/nll6j2YaQCKlSokGsdAkcwO3bssH8rVqwYU/2MHDnS7N+/3/Tq1cv3BZQf99xzjzXUJ06caNKddK8LB+e68cYbzfXXX2/L1StgsW3z5s0515Woa0g06V4XeFYR1tmqVSsrSEWbz6owPRf54co7Hm0ulmPF8/yFnUSWBV4/iCR79+61ggoiczQguuBJNHr0aDNlyhRzxRVXmKJKstrkVVddZe677z7bVzIxh8trqGciOXXBtxGh/JGED2b6MxFv9K5IX+YWoneFQgiFECIGfvrpJ+asjWo5/vjj7b4Y5iSFhpUrV/oe361v1KhRgUYXwyVvD0eLFi3sXxJYpzvpXheRlCu5lZJ1DZlaF7jCDx061I4K4p1Yo0aNIv1c5Ec821wsxyoqbT4eJKosEJRPOukkK44T1nzDDTfEdH1Fqd2HI1ltEs9oZtcLLlM9E8mpi88++8x6qTO7b9euXU0sZMozEW/0rkhPlheyd4UELCGESOEUtTNnzsyzbd++fXYkpGzZsqZly5ZRH5u49B9++MHmjujbt29M18dLzJtnoiiTyLqItFzDXYN3fUFn3svUunjiiSfM448/bmrVqmXFq1hd24vScxHPNhfLsdw+1Cl1W5DzF3YS8fxjQOCBy19CPphRM1aKUrsPRzL7Yb8y1TORnLoo6ABfJj0T8UbvivRjTWF8VwSEEEIknccffzxAF9ynT58828aMGWO3nXHGGTEde+DAgXb/Sy65JObre+mll+wxevbsGSjqJLIugjnvvPPs8R5++OFc60eNGmXXd+zYMc8+M2fOtNvat28fKOokoi5ee+01u1+VKlUCs2bNKtD1FaXnYs+ePYHKlSvb+/Erlw4dOthtM2bMyPdYq1evDhQvXjxQunTpQFZWVq5tu3fvDtSsWTNQokSJPNvatGljzzF27Ng8x+zdu7fdNnr06EBRJ551AZs2bQoccsghdp8rr7wykJ2dHfO1UX8NGjSwx5o2bVqgKBPvegjF3LlzA8WKFQuUK1fOntOLnonE1sW2bdtsubPvokWLYqq/THomQlGmTBl7/9Gid0X61EVhfldIwBJCiBSwcePGQKVKlWxH//777+esx8Br3ry5XT916tQ8+7Vq1couK1euDHnspk2b2v0//fTTfA37BQsW5FnP9VSsWNEeA9GgqBPvuhg8eHBg/fr1udbt3bs38MADD9hjHXTQQXn2YXuTJk3s9qeffjpn/fbt2wNdunSx64cNGxYo6sS7Lt577z0rrFSoUCHwzTffRHQNmfRc3HvvvfZ+unbtatuaY8iQIXZ99+7dc/3+hRdesOV811135TkWgjn7nHPOOYF9+/blrL/xxhvt+n79+uXZZ+jQoXZbixYtcolblDXrqXPvsYoy8aqLHTt25PQZ559/fmD//v35npv2Pnz4cGuAeFm3bl3grLPOyhHXC2LcZFo9jB8/PjBlypQ8x//5559zRCqejWD0TMS/Lry8+eabdt+jjz46bDvQM1Ew0UTvivSvix2F+F0hAUsIIVIEngUY14zEnnDCCYFzzz3XeonwAhgwYIDvPmxjWb58ue/2r7/+2m6vU6dOvi8jPv74LSOZnLtv376B1q1b55zj9ttvD2QK8awL1vFB0a1bt8CFF14YOO200wL16tWz68uWLZtLmAmuO8QtfnfUUUfZD4q6devaf3M9mWA8xrMuEETwCGI9I4wIKH5LsPdPJj0Xu3btsm2N+6Kt0ebcv/GaWrp0aa7fDxo0KKQYhWjbrFkzu52/F1xwgfUadAIV4mQwBw4cCJx99tn2N1WrVrXlffzxx9u651n47rvvAplCvOri5ptvtuvxeLv44otDtnsviMKuDnr16mX3ox6cYHvwwQcHfvnll0AmEK96cOsbNWpkvQl5Fxx55JGBkiVL2vWU786dO/OcX89E/OvCC+2b3+BNGw49E7n5+OOPbdm7hT7afau4hd9EUhd6V6RHXdxciN8VErCEECKFTJ8+PXDKKadYAx239k6dOgXeeOONkL/PT8C69tpr7fZbbrkl33O/9dZb1mDEywGvl1KlSlmhBYN90qRJgUwjXnVx//332xd7w4YNrRGOaEUZ//Wvfw0sXLgw39ASPFiqV69u92vXrp31yMKoySTiURf8v1sfbuHjLpOfC4xowo4RnRD8EL+vuOKKwO+//57nt/kZiIhUN9xwgw0j4Fj8xctk8+bNIc+P0I5HBW2dNk/bp/znzZsXyDTiURf8O5J272XVqlXWmMErhXPS5vFaPPzww+15CDPJJOJRD3h89u/f34rntGmEq2rVqlljDy+rcANMeibiWxfe8DWMddr3hg0bwrYBPRO5wQM8vz7F6yWud0X610W/QvyuKMZ/EptlSwghhBBCCCGEEEKI2NEshEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIdIaCVhCCCGEEEIIIYQQIq2RgCWEEEIIIYQQQggh0hoJWEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIdIaCVhCCCGEEEIIIYQQIq2RgCWEEEIkmGLFipnGjRurnKPg119/teV2/PHHx7Xc+vfvb8qXL2/WrVuXUzfRLPGox7Zt29pjNWvWLOzv3njjDfu7K664IqbzXH311Xb/5cuXhy3jaJZ410eiWLNmjSlZsqS9Zuo8HJQvv6O8vZx11lmmdu3aZvv27SaZLFmyxJQuXdrcfvvtJpNx7f+BBx4wmcb69evN5ZdfburWrWtKlCjh2z5F5MTSdyfqHeR44okncvrVr776Kuxv3e+C+7iDDjrIXHfddQm5PiHSlZKpvgAhhBCiMMNHbpMmTUz37t3NF198kdJr4QO3UaNG9ppEXubMmWPefPNNc+utt5patWrZdf369cvzu+nTp5ulS5eajh07mkMPPTTXtho1ahSoaH/88UezYMEC+//Lli0z33zzjenatWvcqysQCJjx48eb9u3b2/bpR4UKFXzv/9NPPzVZWVmmW7dupnnz5rm2tW7d2hQGRowYYQ4cOGD///333zcvv/yyKVu2bFTHuP/++80RRxxhDc2HHnrIJIu7777bClh33HGHKcogHPI8Tp06tdAIo8niqquuMh999JHp0KGD6dmzpxVjg5/FRIBY+OCDD5phw4bFLJwXFnhfn3DCCbYPTIU4+J///Cfn/9966y1z3HHHRbU/4uY111xj+7abb77ZtGzZMgFXKUT6IQFLCCGEEBnBfffdZ70Zbrvttpx1foYLhhsCFh448fb+cEYLxgcj6Pw7EQLWDz/8YI8fzghFjPO7f8QEBKy//OUvhdaIDS7nDz74wFxwwQVRHePwww83J598shkyZIi56aabTPXq1U2imTlzphk9erS58cYbTc2aNU0mc/bZZ5ujjz66wKJxYWPv3r3mk08+sR5Ds2bNMsWLK2CmoDBoUKpUKZMu/PTTT2bu3LnWwxNvu/fee8+88MILpkyZMlEdB5H7xRdfNAMHDjSjRo1K2PUKkU6oRxRCCCFEkef33383H3/8sRUknPdVssEj6J133rH/P3z4cOsx9+6771qDNd7gvQG9e/c2mQaG4c8//2waNGhgHn300TzeDtFw6aWXmp07d1pPoWTwz3/+0/4lfCzTqVy5svX4yzQBa+3atbavwJtW4lV8oB3lF7KdTFx/xCABAwZ//PFHTp8dDfXr17deZGPHjrWDDkJkAhKwhBBCiBjBO8eFZ3355Ze5cgX5ea5glDz++OPW1Z+RVgzsO++80+zZs8f3+BjOGOCHHXaYDfdiwSMh2Jh2uWJgxYoVIXMWMerLiC1hUXh3cA1Nmza1OTRWr15d6PLi/Pbbb+biiy+290IukE6dOoU0Al5//XWTnZ1tLrroIpMqPvvsM5t766ijjjInnniiOfbYY82mTZtsqF+8+fDDD61Qd+SRR5pUgyeJa5//+te/bFgU9VWnTh3z17/+1RpvfmzcuNHmgWrRooUN/6tWrZo55ZRTbDlGYhzSNs455xxTrlw5M3HiROvpEC144XGtQ4cONYmGXFsjR46098szGipXF6FP5Mzp0aOHqVixoqlUqZI5/fTTzfz580Mem7BQfuN97gcMGGDL2I8NGzaYa6+91tSrV8/eP6GoL730kg1N9csntHv3bvPvf//b9OnTxx6bfapUqWLDorinYDiG68cwwL19lguB9suBhSDLugkTJvheN30sXi2EYAbfG144lCH9LmXA7y688EIzb948ky5QrghXwe8Ub3nTX5DXrU2bNrbuyelHuPPgwYNDvkvw6OrVq5cVPLh36vWYY46x4YLec7t/X3nllbnqJDg8/r///a8577zzrIcjZX3wwQdbMYY+ORjqz+Xw+v77780ZZ5xhvRlZxzsplhxUhHazDYHZC+2TNk7bcyHEEFyGtAPaHdAOvffq53W7a9cuc9ddd9m6ofwI5+RdzvkKMpDB9bt7iFVkp5/bt2+fcqSJzCEghBBCiJgYO3Zs4JxzzuELNlC7du1Av379cpahQ4fm/I7tjRo1Cpx//vmBChUqBM444wy7VK5c2W675JJL8hw7Kysr0KFDB7u9Tp06gdNOOy1w6qmn5uxz/fXX5/x22rRp9pysL1++fK7rePTRR3N+d8EFFwRKliwZOPzwwwNnnXWWXRo3bmz3q1u3bmDVqlVp0xKWL19ur6t79+651g8bNsyu595q1aoVaNasmb2vLl262PXFixcPTJw4Mc/xOnXqZLdHco+uLAcNGhTXe7rooovscV944QX779dee83+u2/fvr6/995rNKxYscLu179//5iukzJnf84fD2j7HO/2228PlC5dOnDSSScFzj77bFt/rD/22GMD2dnZufZZuXJloGnTpnZ7w4YNbR336NEjUKJECbvu6aef9j3XgQMHAvXr17e/mTNnjl138cUX238///zzYes71P1yfWxfunRpIJF8/PHH9jxXX3112OscMGCALYejjjrK9iktW7a066tXrx5Ys2ZNnv3uvPNOu52y79atW+Dcc88NtGjRwq7j+Vm7dm2u369fvz5ne7169ew5evXqFShVqlTgpptuyunPvCxYsCDn9yeccIKtL9oR+/g9S9wL52bbySefnKvP4vze9u/dd+TIkXbdpZde6ltGEyZMsNvPPPPMPH11mTJl7LZDDz3UlgHlV6xYsUC5cuUCX375ZSAduPXWW33fKax3sL5SpUqBrl272rqh/KpWrWr34RnZv39/rmO++OKLdhtt5rjjjrP9EPV58MEH2/Xec3fs2NGuo51464T6dbz00ku2n2WhDM8777ycd1XNmjUD8+fPz3V+6o9tV155pW0P7dq1C1x44YX2Wn7++eew5UE7o9527dqVs27jxo223jgm9+Bl9uzZdv3pp5+ea31wm+X9TLm5Z8B7r7QV7zuId8sxxxwTqFatmu2r2a9s2bJ227333huIFt5P7HvEEUfYf2/ZsiVw0EEH2bLZsGGD7z78PpTZTr/k+lEhMgEJWEIIIUQChBa/j882bdrkMjCXLVsWqFKlit22ZMmSXPsgWLEeg3H37t056zE2nRiDsRZ8nmDD0svnn3+ex1jF4H/wwQdzDIxo7zvaJV4CFgsGF9fveOaZZ3w/5Ldt22aNN4zrSEiEgLV161ZrpCAgOgN98+bN1jhj2bRpU9wELAQy9nOGWLoIWAixCxcuzFlPOTRv3txumzJlSq59EHhZj/i0Z8+eXGItggP1OWvWrDznmjx5st0PQ9zxySef2HWdO3eOScCinbH99ddfDyQSJzQhbIa7ToQDb90iWDjRY+DAgbn2effdd+369u3bBxYvXpyzHsHw/vvvt9sQm7xcddVVdn3v3r1zCQc//vhjjoAe3M9geE+aNCmPEEkfh0jONfNM+93P1KlTfe/XT8DauXNnoGLFinYgYMeOHXn2QdhiH4QuB+dF2GcfrtELfSjCQYMGDXK1s3B4+6BIl3Dvh2jfKePGjbPlENy/uGfmzTffzLUNARjB54cffsi1nroKLnsnNoV6Fr799lv77CESz5gxI9e2f/3rX3ZfRC2/Y7I8/vjjgWi4/PLL87SRMWPG2HUIYfz1tmtEatY9+eSTuY7j12Y5Zrj+1fuOoy4QmhyUJeVAX8T7JRpcG+V95UCIZB3ioB/5vT9r1KiRR+gToqiiEEIhhBAiSTz//PM2bMpB+KELH5g2bVrOesIqCPno3Lmzefrpp3MldiXs5bXXXsuVLydSCJlgfy/kWGG2NUJLCDuLFDeDXbRLvKDsCJnx5oi5/vrrTdWqVc13332XK68UoVWEbbRq1cqkCmbCIwyFHFwupw9hLoR1EfZDLqx4QRglIXcnnXSSSScefvjhXHVAOfztb3+z/++dRp7ZGclXRhsjsTEhSg7CntiH+iSkLRgXhuMNLSJ0inBKEtv/8ssvUV+3m3kxXLhTPJg9e7b9m187JQyW0EYHExMwc2FwOcIjjzxi/xKy5J3FzoVKEYpF0nhCBl0Y49tvv22P+dxzz+WauZGk9jxjfhASRlisCxX1Pqf33nuvDd+NJcdPMIQm9u3b115ncH9FyPW4ceNsWKU399uzzz5rduzYYcOxuUYvhKQSKkmOvEhDeSnHaPs9zhMvCNOkHLxwz88884z9fyYs8ELoLH0NIdZeQoXnheOxxx6zz94rr7ySJ8yVmRMpd8ILST4fzCGHHGJDgqPBXZ83hNH9P++tUNuYFThe8I559dVXbbimg7I89dRTbZubMWNGxMeiHZKviufLG85e0DBC+gzeI26GWyGKMpqFUAghhEgCzIDkcm54cVNfM1Oaw+X4wUj1S+LrcmKRTyRayAuD4Ueia3IPuTwh5NBgGzmZyDWUH6FmsEsWGDZeYQOYah6DmZncuBfyswB5pwBxK1UwTTpcdtlludbz7zFjxljDhXxQBWXbtm3WiMNQJ/dTOuEnqPm1/+nTp9u/GP1+bZEyQ9j1ir6AQEhZ8syQF8bbLjAWEWQo53/84x9RXbe7hlhyaEVDpO000nLkeCSzJ6cWOayCQcDo1q2bFeZ+/PFHK67yl3xW5NoLznMFzOToRDE/qDva36pVq+xxcB5x17R48WITDy655BKbt2jEiBE2h5UD4QZhC8HIK/C4/hThyw9y0TG4QH/KzIf5gYjKkkooSwY5lixZYkURBEKXjym4nBGaqBcEJvKetWvXLqZzco4pU6bYfoW2Eqoseb9QlrynvJD7KljgzA8nRAWLVOT/QixjcId/k3+L+0fARWhCbI0X5L3yE5X9nrn8QLyivujbvINJ/Jt3KoMv1KlXbE6nPkqIdEAClhBCCJEE8Lxi1DUYRs7Bm3zXJTHGc4ElFBiI0YAXxjXXXGONvHACSCQCVqohabAffuW5ZcuWXNuSDcb81KlTrWEVPCvgaaedZsv7m2++McuXL8+ZFCBWSFaO91k6zj7oV2d+9eUmFPATULzrKVcveN/QfhHvSFLtBQ8HBCy8i/AEi8aQdp4XoZLNx4tI22mk5ej6EQSN/O7XeWA5Y5xE5340bNgw5LUjEH3++echz0HdxAOS1yNOk5jeK7hTt07g8uLKAS/TSMognUGkue2226y3VagE4sHljKcigyFMZMGCcIIwRH2de+65vu+lUOXj3h3Bgwd+v4207YSDCQHYD2GH9x0eT3PmzLFec3gHIrSS7B4YlOG89KmR3lO83zX54ech6ga4EIepKwY7/BLJp0MfJUQ6IAFLCCGESALRTIfOSDcwyh+vqb+ZndDNjEhIDaFrGHTOU6Fr167m22+/jXhWJQwFDKloiZfXVjTlWbly5bga0NGCYe3qlHC2YJz3BIbLwIEDC3QuvB8QK/B2SDeiqbNwhBJjnHFImKCfh4yb4Q5vFDxFohWWCMNKJJG200jL0bU5xPNQHjMON/NdrDCbKuIVwggz2eHxRXkhJOABxfljmbHND46J5xUiznvvvWc9F+mPEG8RthC4/MohvxBmZgeNBNoPs2lGG4bKLHYFZdSoUdb7EIGR++/SpYuddQ8BBOEaj6TgcmbWT8KoEfzw2sJjiZBlFvbn3/kJUiwj5c4AAAnUSURBVN5yxPuX2T3D4efl5Q1HjQbaFM82ItbmzZvt/bnQQv4iYOG1lIjwwXj2W4jDeLABdRecAsB5T8UiYCWrjxIiHZCAJYQQQqQZbsSXUfNbb701LsfEcMHAQXS66aab8mwn71A0MBJPGE+0pCLskPxHgLdGKsMHt27dar7++uuwvyuIgEU4KPVM+Ex+3ibpjPOeQnT1w8+jhnC5SZMm2f8nnxFLKDCGoxGwMJoBoaAwtVPXj0QT7uvCbkOVX6j1Lq8PAqo3V1AsfUsk4GWFCIA4jICFGLN//34rbAV731AOS5cuNUOGDLG5ugoKYkm0fR+iSjwELMoZED8YhIi0nBGPeJ+43Gnz5s2zYbYMWiDGXXfddfmem3bEcRB0hg0bFnU4YKw4AQuByj2LXgELwZRtTsCKNq9XsiDk1YXsE6obCtoqHrkMKqVbHyVEOqAk7kIIIUQBcCPXGE/xwnnpOGMlUhiFD3Ud7gPXLxyCvCFZWVlRnYswrv/NZhzVkgrwBiAPUiwJvAsKOYgIeSFsh7oJVS6EDi5atMgmQI4VjB5yf5155pmmMOO8p/AY8QuJcYKgV4QiPJbyJSQqVBkTogl47UQT9uMSI5PwPJF07NjR/o1XO+VZx/MH7xvaViSQLwmRgsTUv/32W57toSYboH9BuAoWr8LtU5C+k+vk3vCG4jpDhQ8WpD8NBZ6s0fZ73hxOBSFcPx7NRBD0iX//+99zQu8iqRP6UMQhhHjnSZQMvIncWbh2J9QQQojXGSHavMcI6wtOLp/Md3c4XL/FBBWh2onzvIo2mfvChQttOZAbTIiijgQsIYQQogAwKo1wxKipG10tKISyYHThrYORgcHgJ4xg4Ad7riBE+Rn9LuEsH9EkkXWQR8jNBFdUKV++vE0oTAhHcN6kROMMkfPPPz9sXhaXjNoZObHgZnlLx/xX0ea9wbuEUDq8BZlgwIHHCN4nlKUzwL3l7J3Zy090JWSK5wMjMlLcZAnxDk0KxglyzJYYL/DoI/SLkC+/WRQRPIcOHZrzb8LDEIEw6il7r9BHn8OskH7QvyCuEOLmBS8pxIVwnnaxCnZcJ0Y/swsi3iJo+YkXeLESKo33KUn+g+EemYlx5cqVJt1x/Tgz0XoHBJjQ4Mknn8zze3JGkaA++J1Am3DvD2++s/zqhJyMeGBdeeWVvqIcnrnk2WJChXhBGD2CHc8+gwFeDyuXB4t6JYyUSQkizX9V0PYXDYiEPH/kaws3O6zrvxAjvTPphoNvD57jI488MuYwTSEKExKwhBBCiALAKC4zCK1du9Z6UFx++eV2RiRCLAoCQgaiy8svv2zz0zCDIQYbuY1Iaos3SLCAhXCB4UkIGUliuQ5n1LCNkWs8K5jhCE8VjoVBxKxn0YQrFEZcuE28PCEiAUGTsJH8hBXv9pEjR+YSbKKB8C0MveDZvwojTFuPV9rw4cPtLHqUD8nZEXkQYJ944okcjyg8pAjJwfuHBM6RlHOkHg4Y5DwziCMIa4nkuOOOswJSPNsoYWL33HOPNaARd1gQU8877zzbT+AZePvtt+fa57HHHrN9BEnxEQ8QV+njOnfunJN8Ojhn0t13323/8lvug/PS3yAa3XLLLb7XhqcgYWj8htA2+isWjPFI7w1eeeWVkN5XwL3gocdzhZBHe6I/pC1wrYQVUh6FIYn7jTfeaAV53gvkGXP3gLjqNxCBCIIQSXgq4i2/pwwQc/FI4y8TezgQVxBBEB5PPfVUO3MhdeJEHrwjSTTOYADvpEMOOcQej3pHSGJAh32i8XCMBO6Pe/Hmv3LwbzehSTThg9w7+cF4vhF/EOW4V/rReOP6G967DHiFgvcxzyVhxISDR4LrL4JDSoUoqkjAEkIIIQoIOUQuu+wya3ghWPz73//OmRkpVjA48Cpg9Lxt27Zm1qxZ1ktg9uzZ1pBGmApOoo4nwvXXX29FLDwhuI7x48fnGJyM0rvZm/BAwfC/4YYbbO6gcB/VRYH+/fvbkXknKCUDwmww9JznTzgwBDH4MaKDhclIYKY5jMzCHj7oIL8Vnkh4zxC6hIcFIlXPnj1tsu4BAwbkMQ7PPvvsfD0QnCccxmEkQglGPsbx1VdfbRIN4hUCAzmW4umF9cgjj9j+CKEBoR1hCq8oBFb6g2CDHRGCvofcUvyG3xOmR59zxx132N8E55JCPKKvQcTA02TChAnWw4XE7qE8AhHTEOrp30j0Tn/FEulkC/SD3ufKCVp+9OnTx/ad5HpCNKPP43rJncYzg8cL15HuIHAguHDN9BXUHSIrgq+fBxZtCsGJ35MknN9TJwxakDuKZ8pbl9TZBx98YOuR8Ey8qagTNzslIJRxDSTFp654l/BMch20A/7tJiSIF06You6CPSG9olW0+a/ef/99K56SPwyxnHudOXOmiSd4u0U6kBGLyM6xeX+7SVqEKOoUC6QqIYUQQgghRBJB4MC4IhE1M7MVJUhQjaCJMIPnhIgPzJ7n8izFIwF4fiD+4EGHEB0qXC+V4CGIgY2IETyLmhAiuRD2ioc2nl3B4btCFFXkgSWEEEKIjODhhx+2o+FPPfWUKWqQx4YEwD169Ej1pRQZ8MTAMwgvsGSIV0BYJOFseL7gHZQq/GZJQ1xz4YYulFAIkTrwuiMn2UMPPaRqEBmDPLCEEEIIkTEQSshINTPSEaYpRCgILSJxNEmSCcVKFpyP2cTId5QqsZVQTLwUuQ5yi/G8IGohAKerd5gQmQRhnYTRkruLnGhCZAoSsIQQQgghIoRwMnKeRSqAsBQlyIfEEgkkRCbpsyh8kB+JcFRyAzGDHQIe3mHUaahk6UIIIUSiKZnwMwghhBBCFBFIsP3mm29G9FuStxc1AYswskjvn4TKErAKJ4MGDbKLEEIIkU7IA0sIIYQQQgghhBBCpDVK4i6EEEIIIYQQQggh0hoJWEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIdIaCVhCCCGEEEIIIYQQIq2RgCWEEEIIIYQQQggh0hoJWEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIdIaCVhCCCGEEEIIIYQQIq2RgCWEEEIIIYQQQggh0hoJWEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIdIaCVhCCCGEEEIIIYQQIq2RgCWEEEIIIYQQQggh0hoJWEIIIYQQQgghhBAirZGAJYQQQgghhBBCCCHSGglYQgghhBBCCCGEECKtkYAlhBBCCCGEEEIIIUw6839VrrYuyVP4jQAAAABJRU5ErkJggg==","type":"image/png","originalSize":68212,"dimensions":{"originalWidth":1200,"originalHeight":630,"displayWidth":1200,"displayHeight":630}}},"sourceToolAssistantUUID":"cfd86899-b902-406c-aa1a-3f1e8c1ced64","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}51{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"36b69b41d56ea4fe912570b2960a4bf598f6fb64c8d375c305ff8c294aec6a23","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01QZQBspfEfFTKnFXt4GY2m5","name":"Bash","input":{"command":"sed -n 76,92p data/sources/arxiv-2304.09339v1.txt; grep -n \"181\\|stars\\|0<p\" data/sources/arxiv-2411.01067v2.txt | head"}},{"type":"tool_use","id":"toolu_01JmykRwUdKcdZzWMoVXpeHk","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0007/out/figure1.png"}}]}}52{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"206a7d734fa3d06844f93eaf2919302a13b683ff960dde52f404ded0e816590a","message":{"role":"user","content":[{"tool_use_id":"toolu_01QZQBspfEfFTKnFXt4GY2m5","type":"tool_result","content":"| (1) | (2) | (3) | (4) | (5) | (6) | (7) | (8)\n\n| A: Pre 27/28.03 - Post 03/04.04 | | | | | | |\n\n\\times TreatPost | 0.115 | -0.012** | -0.278 | -0.227 | 0.005 | -0.003 | 0.188 | 0.192\n\n| (0.109) | (0.005) | (0.295) | (0.207) | (0.120) | (0.005) | (0.221) | (0.189)\n\nPost | 0.052 | 0.002 | 0.453*** | 0.323*** | -0.013 | 0.002 | 0.040 | 0.051\n\n| (0.053) | (0.002) | (0.123) | (0.094) | (0.060) | (0.002) | (0.119) | (0.101)\n\nN | 18332 | 18332 | 18332 | 18332 | 14496 | 14496 | 14496 | 14496\n\n| B: Pre 27/28/29.03 - Post 05/06/11.04 | | | | | | |\n\n\\times TreatPost | 0.048 | -0.003 | 0.135 | 0.073 | 0.003 | 0.000 | 0.067 | 0.058\n10:Editorial note: the paper marks significance with asterisks only (defined in the methodology as * 0.05<p<=0.1, ** 0.01<p<=0.05, *** 0<p<=0.01); no standard errors or confidence intervals are printed for the time-savings estimates.\n38:We had 181 subjects complete the task satisfactorily.^3^3","is_error":false},{"tool_use_id":"toolu_01JmykRwUdKcdZzWMoVXpeHk","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]}}53{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"a6fe518a-dd75-4624-94c3-f9e3312903cf","timestamp":"2026-10-30T05:33:52.557Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"378f9b99-7bc4-4104-9916-169079deda29","keep":12,"tail":["36b69b41d56ea4fe912570b2960a4bf598f6fb64c8d375c305ff8c294aec6a23","206a7d734fa3d06844f93eaf2919302a13b683ff960dde52f404ded0e816590a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"dd2236e3e5413192e56696302bdc3f6cacc0ba3c5e0e20a568529fcc50ccd968"}54{"type":"last-prompt","lastPrompt":"Review","leafUuid":"775d5bd3-03e6-4736-8eb2-4031206c0bac","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}55{"type":"atis-latch","atis":"","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}56{"parentUuid":"775d5bd3-03e6-4736-8eb2-4031206c0bac","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoNgoGMeyUUVENcA5W","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSkQ0KEAgTGAI4AUIIdGhpbmtpbmcSDOl2iqwJaaUDworBahoMWyZ1mLP1JxJyLi0KIjAPWQyI32I6LQwTBkXxC4AJY8A88HFt2VxcHJIubLGXHx2aLey40v361TQ0XweN46Iqrgy8nbf04CXT30RkGj8FhKtG4bmdwiVvTtWeRoNM+zSw7CdQBbXAx8BhNtNDImbbHlMjUQAo7ObDdcsGuXvaTQ8ZglKSexniQFsUSXnjWNSpalJiP/QpnxkrdmaCEnAB3fKmJWvRt3b3Kank3QjAVmlkhJ0ukJXIqSzzC/wqTX2olGsrPdLXOZcurj4X1zr/RISKu84fJVZnMiOJHXiaH2Bo3UCon/eq6/6mt8rzC48D/NEZfDn14SwlOYCzC8kUoYNm8HY81s+SbeLAbMmy5ryD2ZHm8prk+wko8+gdlSzqRND3AHiEnD89eEXHciQWqYU5cpzko0C0MSpbdBQ2d3nuCc1V4oDhugFg0FK1g9zQjjYEpABbAMqNSlyhd+pqkPIG5PZRvMX2+l5t2g1jT+NzBThWywIUQKPIVxZspuPYlQOI1Tpe5YLpnEXLGAAGQFqM8NKRQcYCDSz/+2A3Gfg5QZgzzDKrUf81+g5c9aqDe5KqEe9mGNlbVVLmti5V1SXyc4h5rDm3guoW/ot8pMG7PKBl49FZ8GMWrw2/p4uT4AEcbaqyiQYXfdrAq5/jmjZpTZk09T6iTp5VUDoD5JAy/g9iH+fzTVDwSLwg0R1E2gKK59zFc9I5FKeTShlAMRtSnVdcHdEx1kvQ9SXoCbP5/eEiFKq+D/kqS7OkMME9H3Wy3sbpsjBSy3UYhgjCcE//2UaH/Pj8g22JiCBvc0AdY+RcH87AAAvUh7+Df0Y2zkpRieL7bN6PRAVcOxbhPGHDYfvBbABW8vc28nNTOzMjNxvdvuyQV3PGXbOGzZ998iFUrAgGfWtXpAIcxglaN6CiqNRWkM0el9i7zDeTdsOuj14K91MlEmPRnWEAT5/YTmX3no0G0FrafzbEJ1AqDtuSZL0679hN2Bl/F5iRhZArFtc7M4tr2z+73Q4z+j0DNLa9T4tYuJvTU28uWHxjuWMdZSO40VKB9hipf4P95k41G5EIrIpWXkifjcvU5JKWcjBjbFwAovf6CoUiDg68grQK12lrdpf8pDGa/t2KpGeBdRTYi3Xfz17n4ZivanjuPhl67fUXQv+rAQuYJH381cH636TwEZzkS0xPgf0YVVRjYiqfxhVXMMUCf7IPrz9AbdlbfWWVBODOwxBY0+2URhLxoXDU6fcEWdisqI474+K5CqgPGmg7Zqi4f8OeKLgpUAKn6w4SufZD54LfOwmhfuqivtKzMlb4Y42p6tsXpEga7MfM3VtsUclHKhVvzwd575jyKboKRkGtuS8VuguONWbjasvy2lPBkWziXaFo4VUk6oxGw0dmuZt8eIfmFj/5zOlLbVn+Hbk/g7fPA6rjhW8FRzRPhZqv1AnJ8d6ib7GgFIF+wwwfEhl3DRSLVa5b8fz16wr7ti86pnSaqbtcYXty2kFnNwrV8f+BzJSLt/iBDYmWwp5HvdGWui5sffMW8mMYXAMlSapJQm68BhDO9GVrbwjBktKpAVD4nIn/2qxG7kN+etWBRN97pwYmKeGTjLOJJ3lcKhNAvQ7UqSB9FOrL9q25YWMTC24VNweLgDQZQs/k5bNwuYt9pSqfJPf6htwUQwyZvsoAzMpIWigVtB88v8Zhs2QOQWAQAQ9ISWWy3TH/sGthOt6aixRxRiWR7r0tOz423otwzzH0sEBOqnSvALBZXfb7DLfffcRzAvcMYujrQWflbMA0f7Zd8HIq6PpG5a1Ry3WuWPd1Xc4DgPNfFoF8lJmWiluad308SCzuyGV3C9eiVxQSobgdLlEoicwrLBCXI/lTEpVjx90hxaJhdFGl+jg3n0yvSZu5TlerMJq5PhMVl1ZORGIEnCg3Lx3rKyu63XER5wY6QH64kN1WWGRSc1ZMFQQ8AuntozY3UiNRDLjafmgdluctFRCuX5zU59Pn5xjv3QmESn6azyBoDpQWx0jnlf1tLuA6e/X+eVXuteOLvmYZPqH8fL2V2R5XDC3GQ0vD3zM0qKqTHi1SGdDkD20O5cQ4HFnr+Ui/ssconwPHIMuadUqNEFkSJ9JPIfTn+2wW9ouRmiCz08sLWf9suOYrU7KQx09VP6Som4GEc+wcwM57yEl8xRNfJfmfFX93lZO3KS1w5pNjGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1781,"cache_read_input_tokens":28976,"output_tokens":1597,"output_tokens_details":{"thinking_tokens":412},"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":1781},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3393,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsoNMwasCCiYSFXS7by","requestRef":"a6fe518a-dd75-4624-94c3-f9e3312903cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"37a10967-4f7c-4ef5-a38e-895cd997467b","timestamp":"2026-10-30T05:33:58.005Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}57{"parentUuid":"37a10967-4f7c-4ef5-a38e-895cd997467b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoNgoGMeyUUVENcA5W","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01U25zrBzToCiy5XFYKEFs88","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\"id\": \"R1\", \"severity\": \"minor\", \"location\": \"out/report.md (Limitations) and claims.json C5\",\n \"issue\": \"The report says the four harmonised point estimates (-0.354 to +0.174) 'point to real heterogeneity', and C5 calls it 'substantive heterogeneity'. S2 and S3 have no SE, so the spread cannot be compared with sampling error. The claim is stronger than the evidence, although the caveat on C5 partly acknowledges this.\",\n \"suggested_fix\": \"Reword to: the point estimates differ widely and even disagree in sign, but without SEs for S2 and S3 we cannot tell whether this is heterogeneity beyond chance.\"},\n {\"id\": \"R2\", \"severity\": \"minor\", \"location\": \"results.json data_issues (S1 LogToT)\",\n \"issue\": \"The data issue says the S1 log-time means 'appear swapped'. But exp(4.6)≈99 and exp(4.3)≈74 do not match the raw means of 96 and 114 min in either order, so 'swapped' does not fully explain the inconsistency. The value is not used, so nothing downstream changes.\",\n \"suggested_fix\": \"Describe it as an internal inconsistency rather than a swap.\"},\n {\"id\": \"R3\", \"severity\": \"minor\", \"location\": \"items.S4.sample_as_printed\",\n \"issue\": \"The extract prints Aware N=56 and Control N=52, plus a separate filter that removed 13 responses (3 Aware, 4 Control). It is unclear whether the arm Ns are counted before or after the filter, and the field does not flag this.\",\n \"suggested_fix\": \"Add a note that it is ambiguous whether the arm Ns are before or after filtering.\"},\n {\"id\": \"R4\", \"severity\": \"minor\", \"location\": \"out/analysis.py (S1–S3 printed strings)\",\n \"issue\": \"Some '*_as_printed' and sample strings are hard-coded rather than parsed. The script does locate the source lines with find() and prints them, and the strings match the extracts verbatim, so the outputs are correct.\",\n \"suggested_fix\": \"Optionally build these strings from the parsed lines.\"}\n ],\n \"summary\": \"I re-ran analysis.py in a scratch copy and it reproduced results.json and table1.csv exactly. All required keys are present. I checked the extracted values against the sources and they match: S1 -0.24 (0.14), CI [-0.51, 0.03], p=0.086; S2 +19%; S3 -29.79%***; S4 11.1%, p=0.471; S5 -0.278 (0.295), N=18332. The harmonisation follows the TASK conventions: S2 and S3 are harmonisable but not poolable, S4 uses an approximate SE recovered from the p-value, and S5 is not harmonisable. I recomputed the FE/DL pooling (θ=-0.188, SE 0.106, Q=0.324, I²=0, τ²=0) and it is correct. The line counts match wc -l. No inadmissible inputs are used. Claims are appropriately hedged (not significant, k=2, studies left out); only minor wording and documentation issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1781,"cache_read_input_tokens":28976,"output_tokens":1597,"output_tokens_details":{"thinking_tokens":412},"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":1781},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsoNMwasCCiYSFXS7by","requestRef":"a6fe518a-dd75-4624-94c3-f9e3312903cf","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"29750203-3f81-439b-bb3d-e71c324e5275","timestamp":"2026-10-30T05:34:07.797Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"29750203-3f81-439b-bb3d-e71c324e5275","isSidechain":false,"promptId":"70f16b8b-6490-4d54-b724-cb2421938c90","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01U25zrBzToCiy5XFYKEFs88","type":"tool_result","content":"ok","is_error":false}]},"uuid":"f89eaf2d-56c6-416b-9f7f-a6c118fc3e10","timestamp":"2026-10-30T05:34:07.866Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"29750203-3f81-439b-bb3d-e71c324e5275","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}59{"type":"api-request-blob","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","hash":"e8837d523fd51b3b6a7fda73fbdee6498b499362b718da3105d3ae22ebb64d90","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01U25zrBzToCiy5XFYKEFs88","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\"id\": \"R1\", \"severity\": \"minor\", \"location\": \"out/report.md (Limitations) and claims.json C5\",\n \"issue\": \"The report says the four harmonised point estimates (-0.354 to +0.174) 'point to real heterogeneity', and C5 calls it 'substantive heterogeneity'. S2 and S3 have no SE, so the spread cannot be compared with sampling error. The claim is stronger than the evidence, although the caveat on C5 partly acknowledges this.\",\n \"suggested_fix\": \"Reword to: the point estimates differ widely and even disagree in sign, but without SEs for S2 and S3 we cannot tell whether this is heterogeneity beyond chance.\"},\n {\"id\": \"R2\", \"severity\": \"minor\", \"location\": \"results.json data_issues (S1 LogToT)\",\n \"issue\": \"The data issue says the S1 log-time means 'appear swapped'. But exp(4.6)≈99 and exp(4.3)≈74 do not match the raw means of 96 and 114 min in either order, so 'swapped' does not fully explain the inconsistency. The value is not used, so nothing downstream changes.\",\n \"suggested_fix\": \"Describe it as an internal inconsistency rather than a swap.\"},\n {\"id\": \"R3\", \"severity\": \"minor\", \"location\": \"items.S4.sample_as_printed\",\n \"issue\": \"The extract prints Aware N=56 and Control N=52, plus a separate filter that removed 13 responses (3 Aware, 4 Control). It is unclear whether the arm Ns are counted before or after the filter, and the field does not flag this.\",\n \"suggested_fix\": \"Add a note that it is ambiguous whether the arm Ns are before or after filtering.\"},\n {\"id\": \"R4\", \"severity\": \"minor\", \"location\": \"out/analysis.py (S1–S3 printed strings)\",\n \"issue\": \"Some '*_as_printed' and sample strings are hard-coded rather than parsed. The script does locate the source lines with find() and prints them, and the strings match the extracts verbatim, so the outputs are correct.\",\n \"suggested_fix\": \"Optionally build these strings from the parsed lines.\"}\n ],\n \"summary\": \"I re-ran analysis.py in a scratch copy and it reproduced results.json and table1.csv exactly. All required keys are present. I checked the extracted values against the sources and they match: S1 -0.24 (0.14), CI [-0.51, 0.03], p=0.086; S2 +19%; S3 -29.79%***; S4 11.1%, p=0.471; S5 -0.278 (0.295), N=18332. The harmonisation follows the TASK conventions: S2 and S3 are harmonisable but not poolable, S4 uses an approximate SE recovered from the p-value, and S5 is not harmonisable. I recomputed the FE/DL pooling (θ=-0.188, SE 0.106, Q=0.324, I²=0, τ²=0) and it is correct. The line counts match wc -l. No inadmissible inputs are used. Claims are appropriately hedged (not significant, k=2, studies left out); only minor wording and documentation issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok"}}]}}60{"type":"api-request","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","id":"e1dc70c7-fa8a-426d-9e4a-bbc253644083","timestamp":"2026-10-30T05:34:07.870Z","version":"2.1.314","querySource":"sdk","shapeHash":"883ce76a7368e6eb9e4ee123c527ab854b646b6506d697a9b136e23e21866251","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":"a6fe518a-dd75-4624-94c3-f9e3312903cf","keep":14,"tail":["e8837d523fd51b3b6a7fda73fbdee6498b499362b718da3105d3ae22ebb64d90","e11b3358fd613741baa96ed64efafe4b9cf0de39672dcb1956f69be5a3cc12f0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d35778acf7fb78ee43b1898315519157cd819987145fd6f453f226cb0ac3a5e1"}61{"parentUuid":"f89eaf2d-56c6-416b-9f7f-a6c118fc3e10","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspW9ncJLGRnudp8DXM","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":1604,"cache_read_input_tokens":30757,"output_tokens":808,"output_tokens_details":{"thinking_tokens":36},"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":1604},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6393,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXspVt9tSxdgmD8A2CDi","requestRef":"e1dc70c7-fa8a-426d-9e4a-bbc253644083","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a2a0b21f-efe5-4350-80ad-773d36067618","timestamp":"2026-10-30T05:34:16.320Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"a2a0b21f-efe5-4350-80ad-773d36067618","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspW9ncJLGRnudp8DXM","type":"message","role":"assistant","content":[{"type":"text","text":"My verdict is **accept**: I found no critical or major issues. The review is saved to `out/review/review.json`.\n\nI re-ran `out/analysis.py` on a scratch copy and it produced `results.json` and `table1.csv` exactly as submitted. Every required key is present.\n\n- **Extraction:** all five values match the source extracts exactly as printed, with correct locators. They are S1 −0.24 (0.14), CI [−0.51, 0.03], p=0.086; S2 +19%; S3 −29.79%***; S4 11.1% saving, p=0.471; and S5 −0.278 (0.295), N=18332.\n- **Harmonisation:** the classification follows the task's rules.\n - S2 can be converted to θ but not pooled, because its uncertainty only appears in a figure that isn't in the extract.\n - S3 can be converted but not pooled, because it only prints significance stars.\n - S4 is pooled with a standard error worked back from its p-value, and both the report and the table say that this standard error is approximate.\n - S5 is correctly left out: it measures output counts in a non-randomised design, not completion time.\n- **Pooling:** my own calculation gives the same results, both fixed-effect and random-effects. The pooled θ is −0.188 (SE 0.106, 95% CI [−0.396, 0.020]), with Q=0.324, I²=0 and τ²=0. The line counts match `wc -l`. The code reads only `data/` and uses nothing forbidden. The forest plot is correct.\n- **Claims:** the report correctly says the pooled effect is not significant and rests on only two studies. It also says that studies S2 and S3 are left out and that heterogeneity can't really be measured with two studies.\n\nThere are four minor issues:\n1. The report's \"real heterogeneity\" and the \"substantive heterogeneity\" in claim C5 are worded too strongly, since S2 and S3 have no standard errors to compare against.\n2. A data note says S1's log-time means \"appear swapped\", but they don't match the raw means in either order.\n3. S4's sample field doesn't flag that it's unclear whether the group sizes (56 and 52) are counted before or after 13 low-scoring responses were filtered out.\n4. Some \"as printed\" strings are typed into the code rather than read from the sources, though they match the extracts word for word."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1604,"cache_read_input_tokens":30757,"output_tokens":808,"output_tokens_details":{"thinking_tokens":36},"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":1604},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXspVt9tSxdgmD8A2CDi","requestRef":"e1dc70c7-fa8a-426d-9e4a-bbc253644083","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"78958b31-74e6-4c49-84ab-1ec90c799421","timestamp":"2026-10-30T05:34:16.791Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0007","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","version":"2.1.314","gitBranch":"HEAD"}63{"type":"last-prompt","lastPrompt":"Review","leafUuid":"78958b31-74e6-4c49-84ab-1ec90c799421","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c"}64{"type":"cost-state","sessionId":"d1775679-df86-4a2f-8c11-41b77d7a730c","totalCostUSD":0.26178019999999996,"totalAPIDuration":49186,"totalAPIDurationWithoutRetries":49182,"totalToolDuration":1588,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":50912,"startTime":1793338405887,"modelUsage":{"claude-opus-5-5":{"inputTokens":18,"outputTokens":3914,"thinkingTokens":741,"cacheReadInputTokens":145716,"cacheCreationInputTokens":30857,"cacheCreationEphemeral5mInputTokens":30857,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.26178019999999996}},"hasUnknownModelCost":false}65