1{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:05:49.014Z","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:05:49.021Z","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}4{"parentUuid":null,"isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":"Begin"},"uuid":"eb4e4e90-0d42-48ea-98fa-7e60db0638f9","timestamp":"2026-10-30T04:05:49.026Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","timestamp":"2026-10-30T04:05:49.042Z","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/RC0015\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n\nEXECUTABLE GATES (additional, mandatory)\n- A read-only gate program is provided at `~/wp29/gates/pgar_gate.py`. Run it from the workspace root as `~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .` It checks the output contract of `TASK.md` (required files, keys, types, finite values, report sections, the claims ledger, the phase ledger, the exclusion ledger) and reproducibility (it re-runs `out/analysis.py` in a temporary copy and compares the regenerated `out/results.json` with yours). It never checks scientific correctness and it contains no reference answers.\n- You must run the gate at the end of P4 and again at the end of P5, and record each run's receipt (the gate writes `out/state/gate_receipts/<timestamp>.json`) in `out/state/phases.json`. You may not declare the task complete while the latest gate receipt reports `\"passed\": false`. Fix the reported problems and re-run the gate.\n- The controller will run the same gate after your session ends. If it fails, you will be resumed with the gate output and asked to fix the problems; each such cycle consumes your remaining budget.\n\nSEPARATE REVIEW (additional)\n- After the gate passes, a separate reviewer session that has not seen your work in progress will examine `TASK.md` and everything under `out/` and may return a list of issues (file `out/review/review.json`). You will then be resumed once to address them: fix what is justified, explain in `out/report.md` (Limitations and open issues) what you disagree with, re-run the gate, and update `out/claims.json` and `out/state/phases.json`. The reviewer has no reference answers; its role is to challenge unsupported claims, violated information rules, unverified computations, and inconsistencies between your report and your results.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"40d5e9ca-05d4-416e-9aaf-81f05d4cc49a","timestamp":"2026-10-30T04:05:49.042Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"bde8457663ea503dc3334e84fcfb8628fc1ab5761bbfdc2312f845a8ee6cb0c9"}8{"parentUuid":"eb4e4e90-0d42-48ea-98fa-7e60db0638f9","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"37413d2e-6d72-4900-98a9-35fa14a62f48","timestamp":"2026-10-30T04:05:49.033Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"37413d2e-6d72-4900-98a9-35fa14a62f48","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"cd0075cc-59e3-4564-be3a-f841bbdc779d","timestamp":"2026-10-30T04:05:49.033Z","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/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"cd0075cc-59e3-4564-be3a-f841bbdc779d","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":"92a9df6c-7a60-44f5-b5bf-691b051f3820","timestamp":"2026-10-30T04:05:49.034Z","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/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}12{"parentUuid":"92a9df6c-7a60-44f5-b5bf-691b051f3820","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm5yxDkf4N1pVKihnC9","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":139,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":439,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm5yc8XqiCjf4dFmby6","requestRef":"40d5e9ca-05d4-416e-9aaf-81f05d4cc49a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"966882db-d8fc-4c19-a81b-93e83592ff0f","timestamp":"2026-10-30T04:05:51.095Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"966882db-d8fc-4c19-a81b-93e83592ff0f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm5yxDkf4N1pVKihnC9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0174KJYGu8YaKMaHSs8RUHxF","name":"Bash","input":{"command":"cat TASK.md; ls -laR | head -50; ls out/state 2>/dev/null && cat out/state/log.md","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2811,"cache_read_input_tokens":1504,"output_tokens":139,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2811},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm5yc8XqiCjf4dFmby6","requestRef":"40d5e9ca-05d4-416e-9aaf-81f05d4cc49a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3b37d7a7-8bec-4aec-a4ae-10593b8013a3","timestamp":"2026-10-30T04:05:51.760Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"3b37d7a7-8bec-4aec-a4ae-10593b8013a3","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 .\ndrwxr-xr-x 24 simon-pierreboucher staff 768 oct. 30 00:05 ..\n-rw-r--r-- 1 simon-pierreboucher staff 419 oct. 29 23:43 bundle.json\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 data\n-rw-r--r-- 1 simon-pierreboucher staff 2302 oct. 29 23:43 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 5597 oct. 29 23:43 TASK.md\n\n./data:\ntotal 64\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 ..\n-rw-r--r-- 1 simon-pierreboucher staff 31657 oct. 29 23:43 firms.csv","is_error":true,"tool_use_id":"toolu_0174KJYGu8YaKMaHSs8RUHxF"}]},"uuid":"82d90a72-64c7-44ff-ab02-dd9fde4afdd4","timestamp":"2026-10-30T04:05:51.829Z","toolUseResult":"Error: Exit code 1\n# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 .\ndrwxr-xr-x 24 simon-pierreboucher staff 768 oct. 30 00:05 ..\n-rw-r--r-- 1 simon-pierreboucher staff 419 oct. 29 23:43 bundle.json\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 data\n-rw-r--r-- 1 simon-pierreboucher staff 2302 oct. 29 23:43 gate_spec.json\n-rw-r--r-- 1 simon-pierreboucher staff 5597 oct. 29 23:43 TASK.md\n\n./data:\ntotal 64\ndrwxr-xr-x 3 simon-pierreboucher staff 96 oct. 29 23:31 .\ndrwxr-xr-x 6 simon-pierreboucher staff 192 oct. 29 23:43 ..\n-rw-r--r-- 1 simon-pierreboucher staff 31657 oct. 29 23:43 firms.csv","sandboxed":false,"sourceToolAssistantUUID":"3b37d7a7-8bec-4aec-a4ae-10593b8013a3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"7c91a732005d411e808bae7d6e08e43b54827a1ddc05fe1d4ac422bd018cd0a7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_0174KJYGu8YaKMaHSs8RUHxF","name":"Bash","input":{"command":"cat TASK.md; ls -laR | head -50; ls out/state 2>/dev/null && cat out/state/log.md","description":"Read task and list workspace"}}]}}16{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"b5206f4a-ddfb-4317-8dd7-667c36d0ad88","timestamp":"2026-10-30T04:05:51.834Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"40d5e9ca-05d4-416e-9aaf-81f05d4cc49a","keep":2,"tail":["7c91a732005d411e808bae7d6e08e43b54827a1ddc05fe1d4ac422bd018cd0a7","68e1294277c1a3cef0920db1ed31d70915afbfddee5dbb71bc3e8a73b11d30c3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"493a5cf6ecabc9ec921505ba61f83eb96983ddc5f1a00af5650d92783f3b7b82"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"82d90a72-64c7-44ff-ab02-dd9fde4afdd4","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}18{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}19{"parentUuid":"82d90a72-64c7-44ff-ab02-dd9fde4afdd4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm68rzpFQKWmGsires2","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Hp28bDqk6pmN85VXMC4gKP","name":"Bash","input":{"command":"cat gate_spec.json bundle.json; head -5 data/firms.csv; shasum -a 256 data/firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('data/firms.csv'); print(d.shape); print(d.describe().T); print(d.isna().sum()); print(d.duplicated().sum(), d.firm_id.duplicated().sum()); print(d.corr()); print(d.dtypes)\"","description":"Inspect gate spec and data"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2485,"cache_read_input_tokens":4315,"output_tokens":238,"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":2485},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXm68XQSW9MdeqLWJ91J","requestRef":"b5206f4a-ddfb-4317-8dd7-667c36d0ad88","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"36a3583d-cec0-4228-a28a-cb2de326e104","timestamp":"2026-10-30T04:05:54.239Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"36a3583d-cec0-4228-a28a-cb2de326e104","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Hp28bDqk6pmN85VXMC4gKP","type":"tool_result","content":"{\n \"task_id\": \"F6-conf-04\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"naive_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"skill_index_coefficient\": {\n \"type\": \"number\",\n \"nullable\": true\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\"\n ],\n \"ci_pairs\": [\n [\n \"naive_estimate\",\n \"naive_ci_low\",\n \"naive_ci_high\"\n ],\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}{\n \"task_id\": \"F6-conf-04\",\n \"family\": \"F6\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:43:29.620094+00:00\",\n \"files\": {\n \"TASK.md\": \"f91b6d78e16573314371e5761a0e79c69721af82a9454655f56a864b34006c6e\",\n \"data/firms.csv\": \"34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df\",\n \"gate_spec.json\": \"7233dd8b32d0b3680b8275042673b5278441b86744044bd806094c4af34bd87f\"\n }\n}firm_id,skill_index,training_hours,productivity_growth\n1748,-2.0128,12.679,12.167\n1202,0.0756,20.0,7.3943\n1860,1.0082,21.618,3.9187\n1341,-1.6259,8.305,13.8987\n34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df data/firms.csv\n(1200, 4)\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\n firm_id skill_index training_hours productivity_growth\nfirm_id 1.000000 0.047429 0.054160 -0.030509\nskill_index 0.047429 1.000000 0.693530 -0.786787\ntraining_hours 0.054160 0.693530 1.000000 -0.277219\nproductivity_growth -0.030509 -0.786787 -0.277219 1.000000\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object","is_error":false}]},"uuid":"6e21b40c-dae1-4b57-9fb1-9089d5f7945e","timestamp":"2026-10-30T04:05:54.522Z","toolUseResult":{"stdout":"{\n \"task_id\": \"F6-conf-04\",\n \"required_files\": [\n \"out/results.json\",\n \"out/report.md\",\n \"out/analysis.py\",\n \"out/claims.json\",\n \"out/figure1.png\",\n \"out/table1.csv\"\n ],\n \"results_keys\": {\n \"task_id\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility\": {\n \"type\": \"string\",\n \"nullable\": false\n },\n \"feasibility_reason\": {\n \"type\": \"string\",\n \"nullable\": true\n },\n \"data_issues\": {\n \"type\": \"array\",\n \"nullable\": false\n },\n \"n_input_rows\": {\n \"type\": \"object\",\n \"nullable\": false\n },\n \"n_analysed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"random_seed\": {\n \"type\": \"integer\",\n \"nullable\": true\n },\n \"naive_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"naive_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"baseline_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"model_metric\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_estimate\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_se\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_low\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"effect_ci_high\": {\n \"type\": \"number\",\n \"nullable\": false\n },\n \"skill_index_coefficient\": {\n \"type\": \"number\",\n \"nullable\": true\n },\n \"conclusion\": {\n \"type\": \"string\",\n \"nullable\": false\n }\n },\n \"report_sections\": [\n \"Question\",\n \"Data and exclusions\",\n \"Method\",\n \"Results\",\n \"Uncertainty\",\n \"Limitations and open issues\"\n ],\n \"family_checks\": [\n \"ci_contains_estimate\",\n \"positive_se\",\n \"claims_reference_existing_keys\",\n \"phase_ledger_consistent\",\n \"exclusion_ledger_sums\"\n ],\n \"ci_pairs\": [\n [\n \"naive_estimate\",\n \"naive_ci_low\",\n \"naive_ci_high\"\n ],\n [\n \"effect_estimate\",\n \"effect_ci_low\",\n \"effect_ci_high\"\n ]\n ],\n \"positive_keys\": [\n \"effect_se\",\n \"baseline_metric\",\n \"model_metric\"\n ],\n \"chronology_pairs\": [],\n \"analysis_timeout_s\": 300,\n \"reproducibility_tolerance_rel\": 1e-06\n}{\n \"task_id\": \"F6-conf-04\",\n \"family\": \"F6\",\n \"split\": \"conf\",\n \"version\": \"1.0\",\n \"created_utc\": \"2026-10-30T03:43:29.620094+00:00\",\n \"files\": {\n \"TASK.md\": \"f91b6d78e16573314371e5761a0e79c69721af82a9454655f56a864b34006c6e\",\n \"data/firms.csv\": \"34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df\",\n \"gate_spec.json\": \"7233dd8b32d0b3680b8275042673b5278441b86744044bd806094c4af34bd87f\"\n }\n}firm_id,skill_index,training_hours,productivity_growth\n1748,-2.0128,12.679,12.167\n1202,0.0756,20.0,7.3943\n1860,1.0082,21.618,3.9187\n1341,-1.6259,8.305,13.8987\n34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df data/firms.csv\n(1200, 4)\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id 0\nskill_index 0\ntraining_hours 0\nproductivity_growth 0\ndtype: int64\n0 0\n firm_id skill_index training_hours productivity_growth\nfirm_id 1.000000 0.047429 0.054160 -0.030509\nskill_index 0.047429 1.000000 0.693530 -0.786787\ntraining_hours 0.054160 0.693530 1.000000 -0.277219\nproductivity_growth -0.030509 -0.786787 -0.277219 1.000000\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"36a3583d-cec0-4228-a28a-cb2de326e104","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"9d29417f12dd7cc0e09417ea01c12a0a09037f41add5ad458351818bdf937a02","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Hp28bDqk6pmN85VXMC4gKP","name":"Bash","input":{"command":"cat gate_spec.json bundle.json; head -5 data/firms.csv; shasum -a 256 data/firms.csv; ~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('data/firms.csv'); print(d.shape); print(d.describe().T); print(d.isna().sum()); print(d.duplicated().sum(), d.firm_id.duplicated().sum()); print(d.corr()); print(d.dtypes)\"","description":"Inspect gate spec and data"}}]}}22{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"754b76c7-5f13-443c-a1b5-56ab7a61995c","timestamp":"2026-10-30T04:05:54.526Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"b5206f4a-ddfb-4317-8dd7-667c36d0ad88","keep":4,"tail":["9d29417f12dd7cc0e09417ea01c12a0a09037f41add5ad458351818bdf937a02","7018ab96a920a43e39d4239003474b7415d286fe24b3ec29e7c5b65bb540fae9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"89a2d0956a92c9dcef5d06817c1583a861c2a0d328cf7e57eccd022d9897d137"}23{"parentUuid":"6e21b40c-dae1-4b57-9fb1-9089d5f7945e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm6LL4suD6c7BzRg9WJ","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":1951,"cache_read_input_tokens":6800,"output_tokens":521,"output_tokens_details":{"thinking_tokens":52},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1951},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":420,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm6L3D7nAoZ3UEv8uy8","requestRef":"754b76c7-5f13-443c-a1b5-56ab7a61995c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"32439540-9203-4231-a3f8-95911293cd5c","timestamp":"2026-10-30T04:05:56.021Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"32439540-9203-4231-a3f8-95911293cd5c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm6LL4suD6c7BzRg9WJ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JDHyp92drPuHczYquM9ME2","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd; pd.set_option('display.width',200); d=pd.read_csv('data/firms.csv'); print(d.describe().T.to_string()); print((d.training_hours<0).sum(), (d.training_hours==0).sum()); print(d.training_hours.value_counts().head(8)); print(d.productivity_growth.value_counts().head(5)); print(d.skill_index.value_counts().head(5))\nimport statsmodels.formula.api as smf\nfor f in ['productivity_growth~training_hours','productivity_growth~training_hours+skill_index','productivity_growth~training_hours*skill_index','productivity_growth~training_hours+skill_index+I(skill_index**2)']:\n m=smf.ols(f,d).fit(cov_type='HC1'); print(f); print(m.params.round(4).to_dict(), m.bse.round(4).to_dict())\nd2=d[d.training_hours!=20.0]; m=smf.ols('productivity_growth~training_hours+skill_index',d2).fit(cov_type='HC1'); print(len(d2), m.params.to_dict())\n\"","description":"Further data checks and candidate models"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1951,"cache_read_input_tokens":6800,"output_tokens":521,"output_tokens_details":{"thinking_tokens":52},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1951},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm6L3D7nAoZ3UEv8uy8","requestRef":"754b76c7-5f13-443c-a1b5-56ab7a61995c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4cf1b55b-fc38-4682-abc3-3667d6d19d9f","timestamp":"2026-10-30T04:05:59.035Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"4cf1b55b-fc38-4682-abc3-3667d6d19d9f","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JDHyp92drPuHczYquM9ME2","type":"tool_result","content":" count mean std min 25% 50% 75% max\nfirm_id 1200.0 1600.500000 346.554469 1001.0000 1300.750000 1600.50000 1900.250 2200.0000\nskill_index 1200.0 -0.001467 0.994503 -3.8279 -0.642375 0.01025 0.680 2.9623\ntraining_hours 1200.0 19.945735 8.243620 -7.5850 14.580750 19.67650 25.502 51.7700\nproductivity_growth 1200.0 7.083012 4.020107 -4.0380 4.444350 7.06140 9.987 19.3889\n12 0\ntraining_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\n29.737 2\n30.812 2\n14.113 2\nName: count, dtype: int64\nproductivity_growth\n8.9942 2\n11.4315 2\n10.5167 2\n4.4570 2\n4.3872 1\nName: count, dtype: int64\nskill_index\n-1.2509 2\n-0.5832 2\n 0.1411 2\n 0.5076 2\n-1.1683 2\nName: count, dtype: int64\nproductivity_growth~training_hours\n{'Intercept': 9.7795, 'training_hours': -0.1352} {'Intercept': 0.3028, 'training_hours': 0.0139}\nproductivity_growth~training_hours+skill_index\n{'Intercept': 2.0454, 'training_hours': 0.2522, 'skill_index': -4.6304} {'Intercept': 0.2006, 'training_hours': 0.0095, 'skill_index': 0.0781}\nproductivity_growth~training_hours*skill_index\n{'Intercept': 2.036, 'training_hours': 0.2521, 'skill_index': -4.6674, 'training_hours:skill_index': 0.0019} {'Intercept': 0.2024, 'training_hours': 0.0095, 'skill_index': 0.1317, 'training_hours:skill_index': 0.0054}\nproductivity_growth~training_hours+skill_index+I(skill_index**2)\n{'Intercept': 2.0535, 'training_hours': 0.2523, 'skill_index': -4.6315, 'I(skill_index ** 2)': -0.0088} {'Intercept': 0.2032, 'training_hours': 0.0095, 'skill_index': 0.0783, 'I(skill_index ** 2)': 0.0371}\n1199 {'Intercept': 2.0447515401183836, 'training_hours': 0.25223051778360633, 'skill_index': -4.630513593839779}","is_error":false}]},"uuid":"57ce4c4c-21ab-4409-bb82-27883ae88993","timestamp":"2026-10-30T04:05:59.746Z","toolUseResult":{"stdout":" count mean std min 25% 50% 75% max\nfirm_id 1200.0 1600.500000 346.554469 1001.0000 1300.750000 1600.50000 1900.250 2200.0000\nskill_index 1200.0 -0.001467 0.994503 -3.8279 -0.642375 0.01025 0.680 2.9623\ntraining_hours 1200.0 19.945735 8.243620 -7.5850 14.580750 19.67650 25.502 51.7700\nproductivity_growth 1200.0 7.083012 4.020107 -4.0380 4.444350 7.06140 9.987 19.3889\n12 0\ntraining_hours\n26.584 2\n19.412 2\n26.494 2\n30.526 2\n10.148 2\n29.737 2\n30.812 2\n14.113 2\nName: count, dtype: int64\nproductivity_growth\n8.9942 2\n11.4315 2\n10.5167 2\n4.4570 2\n4.3872 1\nName: count, dtype: int64\nskill_index\n-1.2509 2\n-0.5832 2\n 0.1411 2\n 0.5076 2\n-1.1683 2\nName: count, dtype: int64\nproductivity_growth~training_hours\n{'Intercept': 9.7795, 'training_hours': -0.1352} {'Intercept': 0.3028, 'training_hours': 0.0139}\nproductivity_growth~training_hours+skill_index\n{'Intercept': 2.0454, 'training_hours': 0.2522, 'skill_index': -4.6304} {'Intercept': 0.2006, 'training_hours': 0.0095, 'skill_index': 0.0781}\nproductivity_growth~training_hours*skill_index\n{'Intercept': 2.036, 'training_hours': 0.2521, 'skill_index': -4.6674, 'training_hours:skill_index': 0.0019} {'Intercept': 0.2024, 'training_hours': 0.0095, 'skill_index': 0.1317, 'training_hours:skill_index': 0.0054}\nproductivity_growth~training_hours+skill_index+I(skill_index**2)\n{'Intercept': 2.0535, 'training_hours': 0.2523, 'skill_index': -4.6315, 'I(skill_index ** 2)': -0.0088} {'Intercept': 0.2032, 'training_hours': 0.0095, 'skill_index': 0.0783, 'I(skill_index ** 2)': 0.0371}\n1199 {'Intercept': 2.0447515401183836, 'training_hours': 0.25223051778360633, 'skill_index': -4.630513593839779}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4cf1b55b-fc38-4682-abc3-3667d6d19d9f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"266da04a32fa3fdfc34ac2a440683e2b49a55aff6c580a8d951600aafafa76b0","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JDHyp92drPuHczYquM9ME2","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd; pd.set_option('display.width',200); d=pd.read_csv('data/firms.csv'); print(d.describe().T.to_string()); print((d.training_hours<0).sum(), (d.training_hours==0).sum()); print(d.training_hours.value_counts().head(8)); print(d.productivity_growth.value_counts().head(5)); print(d.skill_index.value_counts().head(5))\nimport statsmodels.formula.api as smf\nfor f in ['productivity_growth~training_hours','productivity_growth~training_hours+skill_index','productivity_growth~training_hours*skill_index','productivity_growth~training_hours+skill_index+I(skill_index**2)']:\n m=smf.ols(f,d).fit(cov_type='HC1'); print(f); print(m.params.round(4).to_dict(), m.bse.round(4).to_dict())\nd2=d[d.training_hours!=20.0]; m=smf.ols('productivity_growth~training_hours+skill_index',d2).fit(cov_type='HC1'); print(len(d2), m.params.to_dict())\n\"","description":"Further data checks and candidate models"}}]}}27{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"346fe960-cf7e-4a9c-858d-8c72b5b5dd02","timestamp":"2026-10-30T04:05:59.749Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"754b76c7-5f13-443c-a1b5-56ab7a61995c","keep":6,"tail":["266da04a32fa3fdfc34ac2a440683e2b49a55aff6c580a8d951600aafafa76b0","bca2ddb847fb1924ac799efdd6c0aa9e69914829cf3125b1b7717aa6a6e2699f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b46775b08dde5c36900ea4d700a52dba6c68100f3227f289d52a2acf33af939e"}28{"parentUuid":"57ce4c4c-21ab-4409-bb82-27883ae88993","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm6ie1AmS4iZQzJrLCb","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":1408,"cache_read_input_tokens":8751,"output_tokens":359,"output_tokens_details":{"thinking_tokens":120},"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":1408},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":756,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm6iN7zraZETc6BNcUn","requestRef":"346fe960-cf7e-4a9c-858d-8c72b5b5dd02","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f4be0a6d-7dd1-4d93-9deb-3bbc8170809c","timestamp":"2026-10-30T04:06:01.749Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}29{"parentUuid":"f4be0a6d-7dd1-4d93-9deb-3bbc8170809c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm6ie1AmS4iZQzJrLCb","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KE48UenaVLCoXBb1skM48q","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('data/firms.csv'); print(d[d.training_hours<0].to_string())\nimport statsmodels.formula.api as smf\nd2=d[d.training_hours>=0]; m=smf.ols('productivity_growth~training_hours+skill_index',d2).fit(cov_type='HC1'); print(len(d2), m.params.to_dict(), m.bse.to_dict())\n\"","description":"Inspect negative training rows"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1408,"cache_read_input_tokens":8751,"output_tokens":359,"output_tokens_details":{"thinking_tokens":120},"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":1408},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm6iN7zraZETc6BNcUn","requestRef":"346fe960-cf7e-4a9c-858d-8c72b5b5dd02","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"89dc9fe5-521a-4dcb-8530-b901348f2d18","timestamp":"2026-10-30T04:06:03.186Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}30{"parentUuid":"89dc9fe5-521a-4dcb-8530-b901348f2d18","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KE48UenaVLCoXBb1skM48q","type":"tool_result","content":" firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\n1188 {'Intercept': 2.0132168180283085, 'training_hours': 0.25353820594501253, 'skill_index': -4.624620879345756} {'Intercept': 0.20848243162917732, 'training_hours': 0.009812212326345536, 'skill_index': 0.07816357249116873}","is_error":false}]},"uuid":"d15c7f3e-ceb4-4bf8-91ad-adf5de8f918a","timestamp":"2026-10-30T04:06:03.878Z","toolUseResult":{"stdout":" firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\n1188 {'Intercept': 2.0132168180283085, 'training_hours': 0.25353820594501253, 'skill_index': -4.624620879345756} {'Intercept': 0.20848243162917732, 'training_hours': 0.009812212326345536, 'skill_index': 0.07816357249116873}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"89dc9fe5-521a-4dcb-8530-b901348f2d18","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}31{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"3704e5d402bcdbf304e961f11f63c2de45399592c896ffc9a94fb64d6b2dc36c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQStggKEAgTGAI4AUIIdGhpbmtpbmcSDKLEwt8MBGIQRkh0lRoMhUW5flOXwDsiiOJsIjCtwUtEqYd+CSm+t4eae2hhRO1mR+QV3e4OooB/0Q9+TURGK+llow4aJN/gkJFby9Uq0weLsw+cm/nMXT6Em2WfgD43/Jg6e3+MZP6TNOI8eze2W6YWevzaqzCl/YUrywKnRhAxdtVqka3xqiQvj8hZo3snvl/fOFPxbEnK9MSiYH5dCXuZmdWuvKyuOr3jxMfsGx/9kqIDp6jG+2AmuZyDc48fTAWBBH59V97WFs96SnQjWcsvvDQyzXHOO4AJNHyYrEmjX4tsyAH5pSiEKqHsCmR9qFqXyQf+j2UK5cp0sODVg5oi7xDXdw6ENp9UUOYAS9l9v8R/wcYuZ1lGoAAj6EuZKiKjHbDOHyw8Fhing+VZcCWgfCOqAtkshj1dWoUMIYmRXLD8RPl0mZ8HsmRghjlpbH0rt57lO3WI3qMKSE7HuuoE5GkPJvcmu5f98iLwEHVcfKrx2TG5sy8CyjqlmCRmFa9+4DJHMNOb3Ht1Hhxp8W5Zk3ydgTnWRKvINqDGGwTVUr2tSTfUqK/04jha/luO+rqPWnanzz19PDegYWJE9fogLjFoqfsIYH64inhd8PHnWbjdngOhhOzu8RlnwjfzFeK7C6oQJYmgkoMkN9mUZmrRdtUyrzAvCwaxAG68qukdXjd9bLlp8LaqlqtoMXBvY/AjGwGcdOWB1sL2JUIS7Yw1q6W8+ZAF6azC399Xqwb76blZVGWbDVCjJP2syUOtEbz+PFPoP3BGPs1SrV5w3LNHQ0jfDz936XKxNPe/2OnPQsyZpeOrGSqx9XeUgQG5kx0rAUWHPOWd8iCqbkqfUdlUsUIoaHQYJm26j3uVXHB3X4zV+DQ1iXVCXgAcE7iZJK1Kn8kGhs6eIYE21Q6Ur915XaBwkvcUqvX71pQD1fB01ak+V4vyhtRFpVVIKAa2jFDOT50ng+yNwsodX/sy35vIWG6tmAGrd+qe5JSle8kU/qtKwapQD9UHhTcLa21TqHfoBLTJElTnkd+sFL/fBWuhr1sYRt7JY9NnBLxRbOcw+ZLNt6Ynt7V27TMuaKHINybnqyNmBeYOKGHl36+SEpSahKwsQsEFpJsMvw0Kq3creg7o4s1XPG2ptnZOBwLQ1RUArY+8Ob3mbyppLcE+HHCeEDZ0/UEFfOk2hhaUrUUPCKLk1DAAsK8EYdl2ZnheBPxrmH5MGfShh7VPt1wFVJbBYRLj+Gk19FoFR4CmsKLIRfj5ZJR/yO3QMtLsd8tkFUSOewzEuQnH1fmsc4fnSFxN/5pwp81txHGh78U3j40o7EbBu40MgLnx73oTFZn5ZAyLj/gdRpJjHE28TgoD9kW8ATy8R8joz/d5OWOxkVLlm16f26cBrxDM91S5L6cv0FqmGAE="},{"type":"tool_use","id":"toolu_01KE48UenaVLCoXBb1skM48q","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd; d=pd.read_csv('data/firms.csv'); print(d[d.training_hours<0].to_string())\nimport statsmodels.formula.api as smf\nd2=d[d.training_hours>=0]; m=smf.ols('productivity_growth~training_hours+skill_index',d2).fit(cov_type='HC1'); print(len(d2), m.params.to_dict(), m.bse.to_dict())\n\"","description":"Inspect negative training rows"}}]}}32{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"4669229b-4d73-4b2f-a1e5-b2a653e6b1fb","timestamp":"2026-10-30T04:06:03.882Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"346fe960-cf7e-4a9c-858d-8c72b5b5dd02","keep":8,"tail":["3704e5d402bcdbf304e961f11f63c2de45399592c896ffc9a94fb64d6b2dc36c","e08dc69d18e1876a8aaa26891c688aa900a93d616f7082291667fb54ced5699c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"307e70f68b28575dc298dd222d38eb1aa231e1bc31fb7b827706172076a2df1d"}33{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d15c7f3e-ceb4-4bf8-91ad-adf5de8f918a","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}34{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}35{"parentUuid":"d15c7f3e-ceb4-4bf8-91ad-adf5de8f918a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm72EQvXMnBqP7vbnK7","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":747,"cache_read_input_tokens":10159,"output_tokens":1575,"output_tokens_details":{"thinking_tokens":105},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":747},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":810,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXm723FnMoK8uYkuDZ3f","requestRef":"4669229b-4d73-4b2f-a1e5-b2a653e6b1fb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f8fb5a8a-d01b-4ccf-845c-603542c23653","timestamp":"2026-10-30T04:06:05.928Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"f8fb5a8a-d01b-4ccf-845c-603542c23653","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm72EQvXMnBqP7vbnK7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CEr8sBugM95CEiTLE8uCRc","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — F6-conf-04\n**Question**: causal effect of one extra training hour per employee (programme year) on next-year productivity growth (pp/hour), simulated firm data.\n**Estimand**: linear homogeneous coefficient beta on training_hours, identified under selection on observables given skill_index (pre-programme, measured year before) — i.e. no unobserved confounders, correct linear functional form, overlap.\n**Baseline**: OLS productivity_growth ~ 1 + training_hours (unadjusted), with 95% CI and RMSE sqrt(mean(e^2)).\n**Main model**: OLS productivity_growth ~ 1 + training_hours + skill_index (skill_index is pre-treatment, so a valid confounder control, not a mediator/collider). HC1 robust SE.\n**Outputs**: out/results.json (naive_estimate, naive_ci_low/high, baseline_metric, model_metric, effect_estimate, effect_se, effect_ci_low/high, skill_index_coefficient, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (model, estimate, se, ci_low, ci_high), out/report.md (6 sections), out/analysis.py, out/claims.json.\n**Info rules**: only data/firms.csv; unadjusted model = intercept + training_hours only. All variables are pre-treatment or treatment/outcome in correct temporal order.\n**Invalidating**: missing confounder column (would make premise_invalid) — not the case; unobserved confounding; nonlinearity; impossible values.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully; contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > log.md <<'EOF'\n- 2026-10-30 P0 passed: contract written.\n- 2026-10-30 P1 audit: 12 rows with negative training_hours found (physically impossible); decision: exclude in main analysis, report sensitivity including them.\nEOF\ncat > data_audit.md <<'EOF'\n# Data audit (P1)\n- File: data/firms.csv, SHA-256 34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df (matches bundle.json)\n- 1200 data rows, 4 columns: firm_id (int, 1001–2200, unique), skill_index (float, standardised, mean -0.001, sd 0.99, range -3.83..2.96), training_hours (float, hours/employee, mean 19.95, sd 8.24, range -7.585..51.77), productivity_growth (float, %, mean 7.08, sd 4.02, range -4.04..19.39).\n- Missing values: none. Duplicate rows: 0. Duplicate firm_id: 0. A few repeated values per column (max count 2) — consistent with rounding, not an anomaly.\n- **Anomaly**: 12 rows with training_hours < 0 (min -7.585). Hours of training cannot be negative; all 12 have low skill_index (-3.0..-1.0). Handling: excluded from main estimate (exclusions.csv); sensitivity analysis including them reported. No zero values.\n- Correlations: corr(skill, training)=0.69, corr(skill, growth)=-0.79, corr(training, growth)=-0.28 → strong confounding by skill_index expected to bias the unadjusted slope downward.\n- Information availability: skill_index measured before programme (pre-treatment) → legitimate control. No violating inputs.\nEOF","description":"Write P0/P1 state files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":747,"cache_read_input_tokens":10159,"output_tokens":1575,"output_tokens_details":{"thinking_tokens":105},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":747},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm723FnMoK8uYkuDZ3f","requestRef":"4669229b-4d73-4b2f-a1e5-b2a653e6b1fb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ba739c30-1399-45ab-9d8d-d442a1426ff2","timestamp":"2026-10-30T04:06:18.285Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"ba739c30-1399-45ab-9d8d-d442a1426ff2","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CEr8sBugM95CEiTLE8uCRc","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"9e683248-4e39-4cc9-8c15-69c94b6eb260","timestamp":"2026-10-30T04:06:18.311Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ba739c30-1399-45ab-9d8d-d442a1426ff2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015/out/state","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"d9dd757547a5057671d0206de1ca377971a145335e6538b09b94b1b96fdadd26","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01CEr8sBugM95CEiTLE8uCRc","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract (P0) — F6-conf-04\n**Question**: causal effect of one extra training hour per employee (programme year) on next-year productivity growth (pp/hour), simulated firm data.\n**Estimand**: linear homogeneous coefficient beta on training_hours, identified under selection on observables given skill_index (pre-programme, measured year before) — i.e. no unobserved confounders, correct linear functional form, overlap.\n**Baseline**: OLS productivity_growth ~ 1 + training_hours (unadjusted), with 95% CI and RMSE sqrt(mean(e^2)).\n**Main model**: OLS productivity_growth ~ 1 + training_hours + skill_index (skill_index is pre-treatment, so a valid confounder control, not a mediator/collider). HC1 robust SE.\n**Outputs**: out/results.json (naive_estimate, naive_ci_low/high, baseline_metric, model_metric, effect_estimate, effect_se, effect_ci_low/high, skill_index_coefficient, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (model, estimate, se, ci_low, ci_high), out/report.md (6 sections), out/analysis.py, out/claims.json.\n**Info rules**: only data/firms.csv; unadjusted model = intercept + training_hours only. All variables are pre-treatment or treatment/outcome in correct temporal order.\n**Invalidating**: missing confounder column (would make premise_invalid) — not the case; unobserved confounding; nonlinearity; impossible values.\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully; contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n\"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > log.md <<'EOF'\n- 2026-10-30 P0 passed: contract written.\n- 2026-10-30 P1 audit: 12 rows with negative training_hours found (physically impossible); decision: exclude in main analysis, report sensitivity including them.\nEOF\ncat > data_audit.md <<'EOF'\n# Data audit (P1)\n- File: data/firms.csv, SHA-256 34aa682e59ef64cfc56931ea33bb809797cd53eca83edfe370c31aeaa8e8b7df (matches bundle.json)\n- 1200 data rows, 4 columns: firm_id (int, 1001–2200, unique), skill_index (float, standardised, mean -0.001, sd 0.99, range -3.83..2.96), training_hours (float, hours/employee, mean 19.95, sd 8.24, range -7.585..51.77), productivity_growth (float, %, mean 7.08, sd 4.02, range -4.04..19.39).\n- Missing values: none. Duplicate rows: 0. Duplicate firm_id: 0. A few repeated values per column (max count 2) — consistent with rounding, not an anomaly.\n- **Anomaly**: 12 rows with training_hours < 0 (min -7.585). Hours of training cannot be negative; all 12 have low skill_index (-3.0..-1.0). Handling: excluded from main estimate (exclusions.csv); sensitivity analysis including them reported. No zero values.\n- Correlations: corr(skill, training)=0.69, corr(skill, growth)=-0.79, corr(training, growth)=-0.28 → strong confounding by skill_index expected to bias the unadjusted slope downward.\n- Information availability: skill_index measured before programme (pre-treatment) → legitimate control. No violating inputs.\nEOF","description":"Write P0/P1 state files"}}]}}39{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"c5e56b48-6b4b-44ed-954b-076094c39e69","timestamp":"2026-10-30T04:06:18.315Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"4669229b-4d73-4b2f-a1e5-b2a653e6b1fb","keep":10,"tail":["d9dd757547a5057671d0206de1ca377971a145335e6538b09b94b1b96fdadd26","a94913076b09c78ba273375e9f63b98c01e4554107317c9b6c7b69b71c67bf76"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a7579ffccb5bb6fd8f6f09bdde34fdfce1c574e0b04d7ba61350ac759ac8c3ef"}40{"parentUuid":"9e683248-4e39-4cc9-8c15-69c94b6eb260","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm861uCFWTmUYW3qjtt","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LJ2Xf5vgyMFJTYVq4fF4JW","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# --- exclusions ---\nexcl = []\nd = raw.dropna()\nexcl.append((\"1\", \"drop rows with missing values\", n_raw, len(d), \"none expected; complete-case\"))\nn0 = len(d)\nd = d[d[\"training_hours\"] >= 0].copy()\nexcl.append((\"2\", \"drop training_hours < 0\", n0, len(d), \"negative hours of training are physically impossible\"))\npd.DataFrame([dict(step=s, rule=r, n_before=a, n_after=b, n_removed=a - b, rationale=why)\n for s, r, a, b, why in excl]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nn_neg = int((raw[\"training_hours\"] < 0).sum())\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs\n\ndef fit(formula, data):\n m = smf.ols(formula, data).fit(cov_type=COV)\n ci = m.conf_int(0.05)\n rmse = float(np.sqrt(np.mean(m.resid ** 2)))\n return m, ci, rmse\n\nnaive, naive_ci, naive_rmse = fit(\"productivity_growth ~ training_hours\", d)\nadj, adj_ci, adj_rmse = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity analyses (not the main estimate)\nsens_all, sens_all_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\nsens_int, sens_int_ci, _ = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nsens_q, sens_q_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\nadj_conv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\nb = float(adj.params[\"training_hours\"]); lo, hi = map(float, adj_ci.loc[\"training_hours\"])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nrows = []\ndef addrow(name, m, ci):\n rows.append(dict(model=name, estimate=float(m.params[\"training_hours\"]), se=float(m.bse[\"training_hours\"]),\n ci_low=float(ci.loc[\"training_hours\", 0]), ci_high=float(ci.loc[\"training_hours\", 1])))\naddrow(\"unadjusted (growth ~ hours)\", naive, naive_ci)\naddrow(\"adjusted (growth ~ hours + skill) [main]\", adj, adj_ci)\naddrow(\"sensitivity: adjusted, incl. negative-hours rows\", sens_all, sens_all_ci)\naddrow(\"sensitivity: adjusted + hours x skill (coef at skill=0)\", sens_int, sens_int_ci)\naddrow(\"sensitivity: adjusted + skill^2\", sens_q, sens_q_ci)\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nresults = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": [\n {\"issue\": f\"{n_neg} rows have negative training_hours (physically impossible; all low skill_index)\",\n \"handling\": \"excluded from main estimate; sensitivity estimate including them reported in table1.csv\"},\n ],\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(len(d)),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_ci_low\": float(naive_ci.loc[\"training_hours\", 0]),\n \"naive_ci_high\": float(naive_ci.loc[\"training_hours\", 1]),\n \"baseline_metric\": naive_rmse,\n \"model_metric\": adj_rmse,\n \"effect_estimate\": b,\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo,\n \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"conclusion\": conclusion,\n \"se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_se_conventional\": float(adj_conv.bse[\"training_hours\"]),\n \"sensitivity_incl_negative_hours_estimate\": float(sens_all.params[\"training_hours\"]),\n \"sensitivity_interaction_term\": float(sens_int.params[\"training_hours:skill_index\"]),\n \"sensitivity_interaction_term_p\": float(sens_int.pvalues[\"training_hours:skill_index\"]),\n \"sensitivity_skill_sq_estimate\": float(sens_q.params[\"training_hours\"]),\n \"corr_skill_training\": float(d[\"skill_index\"].corr(d[\"training_hours\"])),\n \"adjusted_r2\": float(adj.rsquared),\n \"naive_r2\": float(naive.rsquared),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(results, f, indent=2)\n\n# --- figure ---\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d[\"training_hours\"], d[\"productivity_growth\"], s=8, alpha=0.35, color=\"grey\", label=\"firms\")\nx = np.linspace(d[\"training_hours\"].min(), d[\"training_hours\"].max(), 100)\nax.plot(x, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * x, color=\"tab:red\",\n label=f\"unadjusted: slope {results['naive_estimate']:.3f}\")\nsm = d[\"skill_index\"].mean()\nax.plot(x, adj.params[\"Intercept\"] + b * x + adj.params[\"skill_index\"] * sm, color=\"tab:blue\",\n label=f\"adjusted for skill (at mean skill): slope {b:.3f}\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours (simulated data)\")\nax.legend()\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: results[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_se\",\n \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && cat out/results.json","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1590,"cache_read_input_tokens":10906,"output_tokens":2641,"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":1590},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXm85kXDaS4JniFakGwf","requestRef":"c5e56b48-6b4b-44ed-954b-076094c39e69","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f4e416f3-015b-40d2-b638-8e43da0b0aa9","timestamp":"2026-10-30T04:06:37.683Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015/out/state","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"f4e416f3-015b-40d2-b638-8e43da0b0aa9","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0015/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01LJ2Xf5vgyMFJTYVq4fF4JW"}]},"uuid":"04f87bc1-3287-4a03-8e68-029a5146a049","timestamp":"2026-10-30T04:06:37.721Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0015/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"f4e416f3-015b-40d2-b638-8e43da0b0aa9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015/out/state","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}42{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"9e3c1a239c92a3132dc5f9c3bffd121f034823deb45aa427b205642755b70166","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01LJ2Xf5vgyMFJTYVq4fF4JW","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# --- exclusions ---\nexcl = []\nd = raw.dropna()\nexcl.append((\"1\", \"drop rows with missing values\", n_raw, len(d), \"none expected; complete-case\"))\nn0 = len(d)\nd = d[d[\"training_hours\"] >= 0].copy()\nexcl.append((\"2\", \"drop training_hours < 0\", n0, len(d), \"negative hours of training are physically impossible\"))\npd.DataFrame([dict(step=s, rule=r, n_before=a, n_after=b, n_removed=a - b, rationale=why)\n for s, r, a, b, why in excl]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nn_neg = int((raw[\"training_hours\"] < 0).sum())\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs\n\ndef fit(formula, data):\n m = smf.ols(formula, data).fit(cov_type=COV)\n ci = m.conf_int(0.05)\n rmse = float(np.sqrt(np.mean(m.resid ** 2)))\n return m, ci, rmse\n\nnaive, naive_ci, naive_rmse = fit(\"productivity_growth ~ training_hours\", d)\nadj, adj_ci, adj_rmse = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity analyses (not the main estimate)\nsens_all, sens_all_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\nsens_int, sens_int_ci, _ = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nsens_q, sens_q_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\nadj_conv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\nb = float(adj.params[\"training_hours\"]); lo, hi = map(float, adj_ci.loc[\"training_hours\"])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nrows = []\ndef addrow(name, m, ci):\n rows.append(dict(model=name, estimate=float(m.params[\"training_hours\"]), se=float(m.bse[\"training_hours\"]),\n ci_low=float(ci.loc[\"training_hours\", 0]), ci_high=float(ci.loc[\"training_hours\", 1])))\naddrow(\"unadjusted (growth ~ hours)\", naive, naive_ci)\naddrow(\"adjusted (growth ~ hours + skill) [main]\", adj, adj_ci)\naddrow(\"sensitivity: adjusted, incl. negative-hours rows\", sens_all, sens_all_ci)\naddrow(\"sensitivity: adjusted + hours x skill (coef at skill=0)\", sens_int, sens_int_ci)\naddrow(\"sensitivity: adjusted + skill^2\", sens_q, sens_q_ci)\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nresults = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": [\n {\"issue\": f\"{n_neg} rows have negative training_hours (physically impossible; all low skill_index)\",\n \"handling\": \"excluded from main estimate; sensitivity estimate including them reported in table1.csv\"},\n ],\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(len(d)),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_ci_low\": float(naive_ci.loc[\"training_hours\", 0]),\n \"naive_ci_high\": float(naive_ci.loc[\"training_hours\", 1]),\n \"baseline_metric\": naive_rmse,\n \"model_metric\": adj_rmse,\n \"effect_estimate\": b,\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo,\n \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"conclusion\": conclusion,\n \"se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_se_conventional\": float(adj_conv.bse[\"training_hours\"]),\n \"sensitivity_incl_negative_hours_estimate\": float(sens_all.params[\"training_hours\"]),\n \"sensitivity_interaction_term\": float(sens_int.params[\"training_hours:skill_index\"]),\n \"sensitivity_interaction_term_p\": float(sens_int.pvalues[\"training_hours:skill_index\"]),\n \"sensitivity_skill_sq_estimate\": float(sens_q.params[\"training_hours\"]),\n \"corr_skill_training\": float(d[\"skill_index\"].corr(d[\"training_hours\"])),\n \"adjusted_r2\": float(adj.rsquared),\n \"naive_r2\": float(naive.rsquared),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(results, f, indent=2)\n\n# --- figure ---\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d[\"training_hours\"], d[\"productivity_growth\"], s=8, alpha=0.35, color=\"grey\", label=\"firms\")\nx = np.linspace(d[\"training_hours\"].min(), d[\"training_hours\"].max(), 100)\nax.plot(x, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * x, color=\"tab:red\",\n label=f\"unadjusted: slope {results['naive_estimate']:.3f}\")\nsm = d[\"skill_index\"].mean()\nax.plot(x, adj.params[\"Intercept\"] + b * x + adj.params[\"skill_index\"] * sm, color=\"tab:blue\",\n label=f\"adjusted for skill (at mean skill): slope {b:.3f}\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours (simulated data)\")\nax.legend()\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: results[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_se\",\n \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && cat out/results.json","description":"Write and run analysis script"}}]}}43{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"d690e03c-ef34-4f9c-b2f8-4d0a012331c9","timestamp":"2026-10-30T04:06:37.725Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"c5e56b48-6b4b-44ed-954b-076094c39e69","keep":12,"tail":["9e3c1a239c92a3132dc5f9c3bffd121f034823deb45aa427b205642755b70166","d4efdd1c831654f90184b9cfd13470404a77607a6c4039948c478a967005915c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"82f05a446ad4bf0a10ee58c73f3e8d52ca1cb2daed17d5377a0520e65649ec5f"}44{"parentUuid":"04f87bc1-3287-4a03-8e68-029a5146a049","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm9Wz6kxKyB5PqdAWDx","type":"message","role":"assistant","content":[{"type":"text","text":"The shell is still in out/state; rerunning from the workspace root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2803,"cache_read_input_tokens":12496,"output_tokens":129,"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":2803},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXm9WijKCTXarD6BBMZz","requestRef":"d690e03c-ef34-4f9c-b2f8-4d0a012331c9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2a6b7599-3d61-4dc5-a57d-1efcc848c49e","timestamp":"2026-10-30T04:06:39.704Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015/out/state","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}45{"parentUuid":"2a6b7599-3d61-4dc5-a57d-1efcc848c49e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm9Wz6kxKyB5PqdAWDx","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BXYYcSFmZ9XhqHBtR9PHmq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0015 && ls out/state","description":"Return to workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2803,"cache_read_input_tokens":12496,"output_tokens":129,"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":2803},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXm9WijKCTXarD6BBMZz","requestRef":"d690e03c-ef34-4f9c-b2f8-4d0a012331c9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fe4e5b99-3b7b-4ca4-ac85-937a9dfdfde4","timestamp":"2026-10-30T04:06:40.251Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015/out/state","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}46{"parentUuid":"fe4e5b99-3b7b-4ca4-ac85-937a9dfdfde4","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BXYYcSFmZ9XhqHBtR9PHmq","type":"tool_result","content":"contract.md\ndata_audit.md\nlog.md\nphases.json","is_error":false}]},"uuid":"2fe31d22-c41f-464d-928d-b11c2cde9bfe","timestamp":"2026-10-30T04:06:40.265Z","toolUseResult":{"stdout":"contract.md\ndata_audit.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fe4e5b99-3b7b-4ca4-ac85-937a9dfdfde4","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}47{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"6b0ad9826623623e7b1308137e041f45baff2f3479a4fac71ab3d9ec840fef4b","message":{"role":"assistant","content":[{"type":"text","text":"The shell is still in out/state; rerunning from the workspace root."},{"type":"tool_use","id":"toolu_01BXYYcSFmZ9XhqHBtR9PHmq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0015 && ls out/state","description":"Return to workspace root"}}]}}48{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"c0ecbf0e-4f9a-4e15-8a4e-e0d1c6df9c28","timestamp":"2026-10-30T04:06:40.268Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"d690e03c-ef34-4f9c-b2f8-4d0a012331c9","keep":14,"tail":["6b0ad9826623623e7b1308137e041f45baff2f3479a4fac71ab3d9ec840fef4b","7cd2349120bed51b0b3b397706235c6c35e7ae81e53b3f473a46ad9ccafb047f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"48acf29f3a256e2032e38bbfc70c90d50d1fc3fbdab09de9b748a0694a1589bb"}49{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2fe31d22-c41f-464d-928d-b11c2cde9bfe","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}50{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}51{"parentUuid":"2fe31d22-c41f-464d-928d-b11c2cde9bfe","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXm9hswqWG851YKC9ZFy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019JAwdrArih3jm1kRF4Q1qk","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# --- exclusions ---\nexcl = []\nd = raw.dropna()\nexcl.append((\"1\", \"drop rows with missing values\", n_raw, len(d), \"none expected; complete-case\"))\nn0 = len(d)\nd = d[d[\"training_hours\"] >= 0].copy()\nexcl.append((\"2\", \"drop training_hours < 0\", n0, len(d), \"negative hours of training are physically impossible\"))\npd.DataFrame([dict(step=s, rule=r, n_before=a, n_after=b, n_removed=a - b, rationale=why)\n for s, r, a, b, why in excl]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nn_neg = int((raw[\"training_hours\"] < 0).sum())\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs\n\ndef fit(formula, data):\n m = smf.ols(formula, data).fit(cov_type=COV)\n ci = m.conf_int(0.05)\n rmse = float(np.sqrt(np.mean(m.resid ** 2)))\n return m, ci, rmse\n\nnaive, naive_ci, naive_rmse = fit(\"productivity_growth ~ training_hours\", d)\nadj, adj_ci, adj_rmse = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity analyses (not the main estimate)\nsens_all, sens_all_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\nsens_int, sens_int_ci, _ = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nsens_q, sens_q_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\nadj_conv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\nb = float(adj.params[\"training_hours\"]); lo, hi = map(float, adj_ci.loc[\"training_hours\"])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nrows = []\ndef addrow(name, m, ci):\n rows.append(dict(model=name, estimate=float(m.params[\"training_hours\"]), se=float(m.bse[\"training_hours\"]),\n ci_low=float(ci.loc[\"training_hours\", 0]), ci_high=float(ci.loc[\"training_hours\", 1])))\naddrow(\"unadjusted (growth ~ hours)\", naive, naive_ci)\naddrow(\"adjusted (growth ~ hours + skill) [main]\", adj, adj_ci)\naddrow(\"sensitivity: adjusted, incl. negative-hours rows\", sens_all, sens_all_ci)\naddrow(\"sensitivity: adjusted + hours x skill (coef at skill=0)\", sens_int, sens_int_ci)\naddrow(\"sensitivity: adjusted + skill^2\", sens_q, sens_q_ci)\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nresults = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": [\n {\"issue\": f\"{n_neg} rows have negative training_hours (physically impossible; all low skill_index)\",\n \"handling\": \"excluded from main estimate; sensitivity estimate including them reported in table1.csv\"},\n ],\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(len(d)),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_ci_low\": float(naive_ci.loc[\"training_hours\", 0]),\n \"naive_ci_high\": float(naive_ci.loc[\"training_hours\", 1]),\n \"baseline_metric\": naive_rmse,\n \"model_metric\": adj_rmse,\n \"effect_estimate\": b,\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo,\n \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"conclusion\": conclusion,\n \"se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_se_conventional\": float(adj_conv.bse[\"training_hours\"]),\n \"sensitivity_incl_negative_hours_estimate\": float(sens_all.params[\"training_hours\"]),\n \"sensitivity_interaction_term\": float(sens_int.params[\"training_hours:skill_index\"]),\n \"sensitivity_interaction_term_p\": float(sens_int.pvalues[\"training_hours:skill_index\"]),\n \"sensitivity_skill_sq_estimate\": float(sens_q.params[\"training_hours\"]),\n \"corr_skill_training\": float(d[\"skill_index\"].corr(d[\"training_hours\"])),\n \"adjusted_r2\": float(adj.rsquared),\n \"naive_r2\": float(naive.rsquared),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(results, f, indent=2)\n\n# --- figure ---\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d[\"training_hours\"], d[\"productivity_growth\"], s=8, alpha=0.35, color=\"grey\", label=\"firms\")\nx = np.linspace(d[\"training_hours\"].min(), d[\"training_hours\"].max(), 100)\nax.plot(x, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * x, color=\"tab:red\",\n label=f\"unadjusted: slope {results['naive_estimate']:.3f}\")\nsm = d[\"skill_index\"].mean()\nax.plot(x, adj.params[\"Intercept\"] + b * x + adj.params[\"skill_index\"] * sm, color=\"tab:blue\",\n label=f\"adjusted for skill (at mean skill): slope {b:.3f}\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours (simulated data)\")\nax.legend()\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: results[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_se\",\n \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && cat out/results.json","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":154,"cache_read_input_tokens":15299,"output_tokens":2670,"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":154},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXm9hbaXF76rX84VtGJE","requestRef":"c0ecbf0e-4f9a-4e15-8a4e-e0d1c6df9c28","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9a88b400-253d-43f7-9563-656d2d9d771d","timestamp":"2026-10-30T04:06:57.812Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}52{"parentUuid":"9a88b400-253d-43f7-9563-656d2d9d771d","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019JAwdrArih3jm1kRF4Q1qk","type":"tool_result","content":"{\n \"naive_estimate\": -0.13169790632300882,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"conclusion\": \"positive_effect\",\n \"n_analysed\": 1188\n}\nmodel,estimate,se,ci_low,ci_high\nunadjusted (growth ~ hours),-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\nadjusted (growth ~ hours + skill) [main],0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\n\"sensitivity: adjusted, incl. negative-hours rows\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\nsensitivity: adjusted + hours x skill (coef at skill=0),0.2535986940513955,0.009917283395566277,0.23416117577160853,0.2730362123311825\nsensitivity: adjusted + skill^2,0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values,1200,1200,0,none expected; complete-case\n2,drop training_hours < 0,1200,1188,12,negative hours of training are physically impossible\n{\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 rows have negative training_hours (physically impossible; all low skill_index)\",\n \"handling\": \"excluded from main estimate; sensitivity estimate including them reported in table1.csv\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null,\n \"naive_estimate\": -0.13169790632300882,\n \"naive_ci_low\": -0.1603518326928757,\n \"naive_ci_high\": -0.10304397995314195,\n \"baseline_metric\": 3.8601022336733584,\n \"model_metric\": 1.9758571828823268,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"skill_index_coefficient\": -4.624620879345756,\n \"conclusion\": \"positive_effect\",\n \"se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_se_conventional\": 0.0098410870694658,\n \"sensitivity_incl_negative_hours_estimate\": 0.25222449623309495,\n \"sensitivity_interaction_term\": -0.00032835690944043455,\n \"sensitivity_interaction_term_p\": 0.9564572077696775,\n \"sensitivity_skill_sq_estimate\": 0.25383792381516485,\n \"corr_skill_training\": 0.6775720280598007,\n \"adjusted_r2\": 0.7558650404794334,\n \"naive_r2\": 0.06821334219243413\n}","is_error":false}]},"uuid":"c2066528-e989-40d5-9cdc-597ad9d981e3","timestamp":"2026-10-30T04:06:58.854Z","toolUseResult":{"stdout":"{\n \"naive_estimate\": -0.13169790632300882,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"conclusion\": \"positive_effect\",\n \"n_analysed\": 1188\n}\nmodel,estimate,se,ci_low,ci_high\nunadjusted (growth ~ hours),-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\nadjusted (growth ~ hours + skill) [main],0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\n\"sensitivity: adjusted, incl. negative-hours rows\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\nsensitivity: adjusted + hours x skill (coef at skill=0),0.2535986940513955,0.009917283395566277,0.23416117577160853,0.2730362123311825\nsensitivity: adjusted + skill^2,0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values,1200,1200,0,none expected; complete-case\n2,drop training_hours < 0,1200,1188,12,negative hours of training are physically impossible\n{\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 rows have negative training_hours (physically impossible; all low skill_index)\",\n \"handling\": \"excluded from main estimate; sensitivity estimate including them reported in table1.csv\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null,\n \"naive_estimate\": -0.13169790632300882,\n \"naive_ci_low\": -0.1603518326928757,\n \"naive_ci_high\": -0.10304397995314195,\n \"baseline_metric\": 3.8601022336733584,\n \"model_metric\": 1.9758571828823268,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"skill_index_coefficient\": -4.624620879345756,\n \"conclusion\": \"positive_effect\",\n \"se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_se_conventional\": 0.0098410870694658,\n \"sensitivity_incl_negative_hours_estimate\": 0.25222449623309495,\n \"sensitivity_interaction_term\": -0.00032835690944043455,\n \"sensitivity_interaction_term_p\": 0.9564572077696775,\n \"sensitivity_skill_sq_estimate\": 0.25383792381516485,\n \"corr_skill_training\": 0.6775720280598007,\n \"adjusted_r2\": 0.7558650404794334,\n \"naive_r2\": 0.06821334219243413\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"9a88b400-253d-43f7-9563-656d2d9d771d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}53{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"86a3c4f2a132f2db8831deadd89431eae020643bf227d561681be403cde9f95e","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_019JAwdrArih3jm1kRF4Q1qk","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# --- exclusions ---\nexcl = []\nd = raw.dropna()\nexcl.append((\"1\", \"drop rows with missing values\", n_raw, len(d), \"none expected; complete-case\"))\nn0 = len(d)\nd = d[d[\"training_hours\"] >= 0].copy()\nexcl.append((\"2\", \"drop training_hours < 0\", n0, len(d), \"negative hours of training are physically impossible\"))\npd.DataFrame([dict(step=s, rule=r, n_before=a, n_after=b, n_removed=a - b, rationale=why)\n for s, r, a, b, why in excl]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nn_neg = int((raw[\"training_hours\"] < 0).sum())\n\nCOV = \"HC1\" # heteroskedasticity-robust SEs\n\ndef fit(formula, data):\n m = smf.ols(formula, data).fit(cov_type=COV)\n ci = m.conf_int(0.05)\n rmse = float(np.sqrt(np.mean(m.resid ** 2)))\n return m, ci, rmse\n\nnaive, naive_ci, naive_rmse = fit(\"productivity_growth ~ training_hours\", d)\nadj, adj_ci, adj_rmse = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity analyses (not the main estimate)\nsens_all, sens_all_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\nsens_int, sens_int_ci, _ = fit(\"productivity_growth ~ training_hours * skill_index\", d)\nsens_q, sens_q_ci, _ = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\nadj_conv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\nb = float(adj.params[\"training_hours\"]); lo, hi = map(float, adj_ci.loc[\"training_hours\"])\nconclusion = \"positive_effect\" if lo > 0 else (\"negative_effect\" if hi < 0 else \"no_detectable_effect\")\n\nrows = []\ndef addrow(name, m, ci):\n rows.append(dict(model=name, estimate=float(m.params[\"training_hours\"]), se=float(m.bse[\"training_hours\"]),\n ci_low=float(ci.loc[\"training_hours\", 0]), ci_high=float(ci.loc[\"training_hours\", 1])))\naddrow(\"unadjusted (growth ~ hours)\", naive, naive_ci)\naddrow(\"adjusted (growth ~ hours + skill) [main]\", adj, adj_ci)\naddrow(\"sensitivity: adjusted, incl. negative-hours rows\", sens_all, sens_all_ci)\naddrow(\"sensitivity: adjusted + hours x skill (coef at skill=0)\", sens_int, sens_int_ci)\naddrow(\"sensitivity: adjusted + skill^2\", sens_q, sens_q_ci)\npd.DataFrame(rows).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nresults = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": [\n {\"issue\": f\"{n_neg} rows have negative training_hours (physically impossible; all low skill_index)\",\n \"handling\": \"excluded from main estimate; sensitivity estimate including them reported in table1.csv\"},\n ],\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(len(d)),\n \"random_seed\": None,\n \"naive_estimate\": float(naive.params[\"training_hours\"]),\n \"naive_ci_low\": float(naive_ci.loc[\"training_hours\", 0]),\n \"naive_ci_high\": float(naive_ci.loc[\"training_hours\", 1]),\n \"baseline_metric\": naive_rmse,\n \"model_metric\": adj_rmse,\n \"effect_estimate\": b,\n \"effect_se\": float(adj.bse[\"training_hours\"]),\n \"effect_ci_low\": lo,\n \"effect_ci_high\": hi,\n \"skill_index_coefficient\": float(adj.params[\"skill_index\"]),\n \"conclusion\": conclusion,\n \"se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_se_conventional\": float(adj_conv.bse[\"training_hours\"]),\n \"sensitivity_incl_negative_hours_estimate\": float(sens_all.params[\"training_hours\"]),\n \"sensitivity_interaction_term\": float(sens_int.params[\"training_hours:skill_index\"]),\n \"sensitivity_interaction_term_p\": float(sens_int.pvalues[\"training_hours:skill_index\"]),\n \"sensitivity_skill_sq_estimate\": float(sens_q.params[\"training_hours\"]),\n \"corr_skill_training\": float(d[\"skill_index\"].corr(d[\"training_hours\"])),\n \"adjusted_r2\": float(adj.rsquared),\n \"naive_r2\": float(naive.rsquared),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(results, f, indent=2)\n\n# --- figure ---\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d[\"training_hours\"], d[\"productivity_growth\"], s=8, alpha=0.35, color=\"grey\", label=\"firms\")\nx = np.linspace(d[\"training_hours\"].min(), d[\"training_hours\"].max(), 100)\nax.plot(x, naive.params[\"Intercept\"] + naive.params[\"training_hours\"] * x, color=\"tab:red\",\n label=f\"unadjusted: slope {results['naive_estimate']:.3f}\")\nsm = d[\"skill_index\"].mean()\nax.plot(x, adj.params[\"Intercept\"] + b * x + adj.params[\"skill_index\"] * sm, color=\"tab:blue\",\n label=f\"adjusted for skill (at mean skill): slope {b:.3f}\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours (simulated data)\")\nax.legend()\nfig.tight_layout()\nfig.savefig(f\"{OUT}/figure1.png\", dpi=120)\n\nprint(json.dumps({k: results[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_se\",\n \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv && cat out/results.json","description":"Write and run analysis script"}}]}}54{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"64f9613e-2fd6-4e03-ab8b-610b4489b335","timestamp":"2026-10-30T04:06:58.858Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"c0ecbf0e-4f9a-4e15-8a4e-e0d1c6df9c28","keep":16,"tail":["86a3c4f2a132f2db8831deadd89431eae020643bf227d561681be403cde9f95e","fed231a127518e07294e1e68c4e4934b7a8f33b7e17ea8ec154ad02079ba2108"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"fae2138505ecee96a45950b6b975f88f1a3703f1a61d7dbfd42a25840a267c14"}55{"parentUuid":"c2066528-e989-40d5-9cdc-597ad9d981e3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmB5cg9jcRWPsFszDvw","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":3775,"cache_read_input_tokens":15453,"output_tokens":587,"output_tokens_details":{"thinking_tokens":111},"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":3775},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":953,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmB5KZxz8XnLrRVH4Yq","requestRef":"64f9613e-2fd6-4e03-ab8b-610b4489b335","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7ef49fe2-71d3-4cbb-85df-cb57622a6f52","timestamp":"2026-10-30T04:07:01.244Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}56{"parentUuid":"7ef49fe2-71d3-4cbb-85df-cb57622a6f52","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmB5cg9jcRWPsFszDvw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SQxomHrjUtxYriUSpY9xsj","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('sens_all, sens_all_ci, _ = fit(','naive_all, _, _ = fit(\"productivity_growth ~ training_hours\", raw)\\nsens_all, sens_all_ci, _ = fit(')\ns=s.replace(' \"sensitivity_incl_negative_hours_estimate\"',' \"naive_incl_negative_hours_estimate\": float(naive_all.params[\"training_hours\"]),\\n \"sensitivity_incl_negative_hours_estimate\"')\nopen(p,'w').write(s)\nEOF\ncp out/results.json /tmp/r1.json; rm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r2.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r2.json && echo IDENTICAL; grep naive_incl out/results.json; ls out","description":"Add key, rerun from clean state and compare"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3775,"cache_read_input_tokens":15453,"output_tokens":587,"output_tokens_details":{"thinking_tokens":111},"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":3775},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmB5KZxz8XnLrRVH4Yq","requestRef":"64f9613e-2fd6-4e03-ab8b-610b4489b335","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4e8ba4ff-0da3-4c7a-ab79-048961beae10","timestamp":"2026-10-30T04:07:04.454Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}57{"parentUuid":"4e8ba4ff-0da3-4c7a-ab79-048961beae10","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SQxomHrjUtxYriUSpY9xsj","type":"tool_result","content":"IDENTICAL\n \"naive_incl_negative_hours_estimate\": -0.13518960504279864,\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv","is_error":false}]},"uuid":"fef6f1c7-5f2e-40be-81ff-00bdf47aba22","timestamp":"2026-10-30T04:07:06.433Z","toolUseResult":{"stdout":"IDENTICAL\n \"naive_incl_negative_hours_estimate\": -0.13518960504279864,\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4e8ba4ff-0da3-4c7a-ab79-048961beae10","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}58{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"1ba82adb127ce4b5b538beb4940879b6cfee5e51772b629370eb42d7b1e7a277","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01SQxomHrjUtxYriUSpY9xsj","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\np='out/analysis.py'; s=open(p).read()\ns=s.replace('sens_all, sens_all_ci, _ = fit(','naive_all, _, _ = fit(\"productivity_growth ~ training_hours\", raw)\\nsens_all, sens_all_ci, _ = fit(')\ns=s.replace(' \"sensitivity_incl_negative_hours_estimate\"',' \"naive_incl_negative_hours_estimate\": float(naive_all.params[\"training_hours\"]),\\n \"sensitivity_incl_negative_hours_estimate\"')\nopen(p,'w').write(s)\nEOF\ncp out/results.json /tmp/r1.json; rm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cp out/results.json /tmp/r2.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r2.json && echo IDENTICAL; grep naive_incl out/results.json; ls out","description":"Add key, rerun from clean state and compare"}}]}}59{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"30219a49-2412-4c8e-97a5-aeaccee63f8a","timestamp":"2026-10-30T04:07:06.436Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"64f9613e-2fd6-4e03-ab8b-610b4489b335","keep":18,"tail":["1ba82adb127ce4b5b538beb4940879b6cfee5e51772b629370eb42d7b1e7a277","54da2e3f06eb90dcef42797b44511c44655ff58ad7d3c1da3d8d7854702dfea0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e8d0ac7bc44aecffc9286aed80206b6c7ffec3034b51afa3c0e976654c773895"}60{"type":"tools-used","tools":["Bash","Read"],"sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}61{"parentUuid":"fef6f1c7-5f2e-40be-81ff-00bdf47aba22","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBdfzRhzMmsoB1NwH4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015u8KBi9AMeH6ugi33jnAHK","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0015/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":660,"cache_read_input_tokens":19228,"output_tokens":1232,"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":660},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmBdV5q5E12hHYeDvbn","requestRef":"30219a49-2412-4c8e-97a5-aeaccee63f8a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"52ab6d02-a728-4725-a923-f83ac392b97e","timestamp":"2026-10-30T04:07:09.051Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}62{"parentUuid":"52ab6d02-a728-4725-a923-f83ac392b97e","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015u8KBi9AMeH6ugi33jnAHK","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"iVBORw0KGgoAAAANSUhEUgAAA0gAAAJYCAYAAABYRsb0AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAASdAAAEnQB3mYfeAABAABJREFUeJzsnQeYHWXVgE82u9n03jc9pJNKl957FQQVRUBRQEX0V5Ffpagoor+giIpSBBug9Cq994QE0khPdtN73c1u9v7P+2XPMncyt8+te97nmWzu3LkzX5uZc75TvlaRSCQihmEYhmEYhmEYhpRZGxiGYRiGYRiGYezGFCTDMAzDMAzDMIwmTEEyDMMwDMMwDMNowhQkwzAMwzAMwzCMJkxBMgzDMAzDMAzDaMIUJMMwDMMwDMMwjCZMQTIMwzAMwzAMw2jCFCTDMAzDMAzDMIwmTEEyDMMwDMMwDMNowhQkwzAMwzAMwzCMJkxBMgzDMAzDMAzDaMIUJMMwDMMwDMMwjCZMQTIMwzAMwzAMw2jCFCTDMAzDMAzDMIwmTEEyDMMwDMMwDMNowhQkwzAMwzAMwzCMJkxBMgzDMAzDMAzDaMIUJMMwDMMwDMMwjCZMQTIMwzAMwzAMw2jCFCTDyAGLFy+WVq1ayZe+9KWCam/KdMQRR2R0DurEeaijkR2GDBniNiM5rr32WjcmX3rppYyajN9zHs5XSNh4ELnmmmukbdu2smzZsrTakOcefVtoFGPfhnW/wd133+3Oxd9C4sEHH3Tlev755/NdFCNHmIJklBQ8wLxb69atpWfPnnLUUUfJP/7xD2lp5OtlW6gKYaFSqMJaGNhYMMIGpeimm26SSy65RAYOHGgNnKXJr2ImTKUNzjzzTJkyZYp8+9vflsbGxlDOaRQ25fkugGFka3YR6uvrZc6cOfLII4/Iiy++KO+995783//9nzV6E7Nnz5b27dtn1B4///nP5aqrrpKqqiprV6Mg+PrXvy7nnXeeDBo0KKPz7L///u4eYZLFKBx+8pOfSF1dnXzve99L+xz33HOPbN++PdRyGaULytb3v/99Offcc+Vf//qXfO5zn8t3kYwsYwqSUZL4XWIwix977LFy8803yze/+c2ic2HIFqNHj874HP369XObYRQKKDRhKDVMHoRxjxjhsWnTJvn73/8uRx99tAwYMCDt82SqPBstj9NOO026du0qt912mylILQBzsTNaBLxMEXQikYi8++67e5jgcb874IADpGPHjlHK04oVK+Tyyy93+9q0aSO9evWSs846S95///3A62zZssWZ4Hlx4x/PNbFYxTLJx3OtiueLXV1d7RS9ESNGSLt27aR79+5utpuZVW/sxJIlS9zmdTv0ur353TC+9rWvuX1Y3IJ4++233fdnn312zBgk2nXo0KHu/3/961+jrk1dnnnmGff/Cy+8MPAazAyrgMv/kwGBCfcH2qJ3797yhS98QZYvXx7Yvt64knfeeUdOPvlk137eOnDdX/ziFzJ+/HgnJHfu3FkOPfRQuf/++6POtXXrVjcuDj744Kj9O3bscP3POe+9996o7/7whz+4/XfeeWez+9nLL7/svvO2VZB7zLZt2+S73/2uE+4qKytlr732khtvvNGN62RgPFLetWvXBn7Pubj2rbfe2rxvxowZ8tnPftbdA1yTe4C2/ta3vuUstPFINBaS7Q+sv7hTjR071vUF/bz33nvLddddJ7W1tUm712i7Un/Oh2JPncaNGyd33XVX0jFIOq4aGhrkhhtucPch58Hdi1nmnTt3ZjxOkyHV8cD4Peyww6RLly6uDIxvLMBB91k8F62guEOvK+XHH3/sZtqpY1lZWXM/LFy40LU75dTnFmXgubNu3bqk6vzPf/7TWX44fxCPPvqoe95r3/bv318OP/xwJ9R6SfRswNvghBNOcG3VrVs3+fSnP90c70Q9sFByL1CPI488UqZPnx7a8z1IKcSlEFdx3i36LkJgf/PNNwPPCzxXvPecfxzzPOdZ3rdvX3dOxu9Xv/pVNyaD4L1Hm3Tq1Mndh8ccc8we10+W+fPnyznnnOPatkOHDvKpT31KnnjiiZjHp/IM4FnFfqBvvG2gMEbxfNh3331dWzJWBg8e7K7B+zUInulnnHGGvP76684zxShtzIJktBhUaPC/sH7961/Ls88+K6eeeqp7mPIygkWLFskhhxziXha8mBASeUE+8MAD7kH+n//8R0455ZTm8yBk8GJGAZs4caJ8/vOfl40bNzqlRQXgMODFffzxx8v69eudsIPChsAwa9Ys9wL80Y9+5F4QuBliMQOEWWXSpEkxz33BBRfIn/70J+d+cvrpp+/xPUIuxIstQiig3rfccotrB14o3muzb/jw4U5Yo3wIIF5oV4Sl73znO+6llYhf/vKXTijlRUv5OR/9idLiP7cXXuwIh/TxRRdd5IRmhASEW9qXPkOhQEGmff/97387oeyDDz5wQjGgUKOYImigHCM4AC9QFTqxXiIIKxrky1ihfPQTQg2KrLqGgt/KiTJCuRiPJ554opSXl8vDDz/sXvIICN7fxoL2ufrqq52Q+Y1vfCOwf2kDdR9BOWLigHsGYQxlZ/PmzU64QeD86U9/KhUVFWmPhWT6AxD6EUgQolCgqC9tzHhHqH3uuedcvGEyUB7GBudGOKSfuKe5JsI8bZQstNOrr77q+gOh7cknn3TjcfXq1XsoXOmO01ikOh7od9qXiQfKzdh96qmn3H4mLf773/82t3cmLFiwwI2ZkSNHumcgkwW0DZNN++23nxs/J510klM4KCfPWSYRcIvs0aNHwvPT18A48XP77bc7AR+Bn+c5daUvGMf0x2WXXZZUHXiGM+ZQrL7yla/Ihx9+6IL0P/roIzd5xLV5Nnzxi1909y3f4aGA4kS7hg1unv/7v//rnveMf8bQ0qVLnTJIHz722GNOcdH7ir5HQUDg9z6rvQovEzQoAzxjubdRjubNmyd/+ctf3PneeuutKCvbG2+84RQino+8c1ByeRZyTt6PqcB1DjroIPecZ+xSZp4pPB/4HEQqzwDed9wLPMO514I8RuizP/7xj+6dzzkZ+zNnzmyuP+/ZILdx7lee11zPrMslTsQwSgiGdNCwfvbZZyOtWrVy2+LFi92+a665xh3bvn37yNSpU/f4zXHHHee+/+lPfxq1//XXX4+0bt060r1798iWLVua9//sZz9zx5911lmRXbt2Ne9fuHBhpFu3bu67Cy64IOpchx9+eGB54a677nLf8Vepq6uLDBkyxO3/+9//vsdvli1bFvV58ODBbosF56EMXkaOHBlp06ZNZN26dVH7a2trXT169+4dqa+vb95PnTjPokWLmvfx/6D6KjfddJP7/ne/+90e32mbzJ07N5KIBQsWRMrLyyM9e/aMLF26tHl/Y2Nj5LzzzgscDy+++GLz/j/+8Y97nPOGG25w35144olR9Vy1apVrS75jDCg/+tGP3L7HH3+8ed9VV13lxshRRx0VGTBgQPN+xgXjZtiwYYF1joVelzJt3749qkxdunRx286dOxO2F+OjrKwsss8+++zx3TvvvNM8fpVvf/vbbt/DDz+8x/Hr16+PGuexSDQWEvWH9jN96ueHP/yh+92//vWvqP16b3NuL3qdiy++ONLQ0NC8f+bMma6/xowZE1g2zhfUX1OmTIm6T7Zu3RoZPny4a+MVK1ZkNE7jkep4eOONN9zxAwcOjCoX4/uUU05x3/H8SvRsSOaeZ/vBD36wx29++9vfuu9uvvnmPb6j3bz1iEefPn0inTt3DhwP9AfPLtrBz5o1axLec96x+Le//S3qu4suusjt5xnofydcf/31gXVL9fke65m9cePGPcqv93O/fv0io0eP3uO7eP3Hs7WiosKN1erq6qjvnnvuOTd+zzjjjOZ9tPWoUaMCnwXUWdvMf7/F4thjjw1sL86t5/K3S1jPAIV6807z88wzz7j6f+1rXwv83QcffODOe8455yRVV6N4MRc7oyRhVomNWTdmiZld453BzBKzal6YRZs8eXLUPkzszKgyg+YPBGa2CWsSFhxmoRRmKJmBZqaYvwqz7rjDhQEzW7iyMOMXFCSaiU++wowbs4RYGfzX3rBhg5sVZrY6E3Cvw10Ba5WXuXPnulk/ZvWYgU4ErpG4OWEN8WazwuKBi1w8qwKzlsw2+2Fmld/jGumtJ+5CWOeAWUYFSxB407/y/3322cfNtDKWcOcAZlwZN/qbVPntb3/rXEu8ZcLSh9WTtksE44Nr4yrDbGmQdTDIguK9psIstnecZ0qs/oBhw4YFuipdeeWV7i8WkGTBZZK+9Y4N3HaYGWamHrfJZGFWGzcxBVch7g9capmBDmOchjEeGNPwwx/+0FlXFMY3FnT60TumM6FPnz5xrZlBY4l2C9rvh+fSqlWr3DViua5RpyCrZioxaViI6Ecvel9g7cNK5wVLkt7f2YBrBpWf+5n3G5YVLErJgpsvFkgsu34rCc8H3i8877GKq/WI8YQFy+9ZgOUPj4Bk4XmI5ZT3Ir/1wrmx2mX7GQDUO8hD4bjjjnMut7HOp/dPKu1tFCemIBklCe4FbLiUvPDCCy5+BDeOoAx2uEj5mTZtmvvL74JetupSoMfxIsFFgIdu0MsirHSruD1ALDeEMOBlj8CkAnMq7nXJgivNZz7zGeeywsvX6yIDxCQkg7Z/kLsNinC8FMBB/a79SNxCkPuEv98BVxGEO1WQEE6nTp3qBA09Xr9jLHrPk6qQhFuLH60jymsyaP95+1cVYgRs3J8UXAoR3nF9YVzgeokLVTYI6g9vrA1ujbho0Q6MT4QldcmqqalJ+jrEC+HylWk7AvELyZwnk3EaxnhgPMYad0xEIGjj6qbuxZmAK2WQ4InQjfsZLqu413Gvo6QnGz8HGqeEch4ESg3usCi8CM64Wa1ZsyblOgT1K88EVeT9Cq0qGbFiV8IAdzKemfQv7asxNb/73e9Svgc0bojJKJ1M9G64Je7atat5YkfHT5DyQlsEjetYeO+FoImBWO/KMJ8BwLj729/+5twGiUFCsdY2xaUy1vl0QiRWHKdROlgMklGSpPLS9c6oKiooxMrOpvuJZ/Aez8xmstdIB71eNlNqq5WBWT5m1MeMGeNemE8//bQTDiZMmBDKdYgHQODGioRVjlgQhHaEdNacSIZE7c7+WAvYhtHvgO86L3t80hHGUPgQLmhD2o7foCBdeuml7i8v4HQUJLInBaFWLq6ZDLQtCgLCARMICCmPP/64s2xhYfVazVBaiLH52c9+5mKwNOHEqFGjnJUAS2pYxLpHmOmmvUjgQFA2ShsCjU5cMBGSbDKPMNsx1rmCzpPJOE3l2omuH29cMyPOuE4nHiqZfkQRpA8RwHmWqPUdgf9//ud/krKyq5UpKDEHkCAHSwvxcVjXiHHkfkOwJ8lBkOITRFAbaLvG+y5R0pJ0eeihh5ylCKs7sU5MwmF10wQYKDqp3AOqaNIm8VBrapjvt3TOFfYzQMcK44OxTywf71QdXxoTGgQxdZCMxdMobkxBMlo8QWZ7fQmuXLkysH0IOPYep39x/wgi1nnURQn3G7/bmlcI9wtFqc6WpQruJChIKCy4AJF9izKmEsCeCAK5cW3UZA0EG/PiJpA9XuC/F7UE0O64RfiJ1R9h9bvCy5v2QgFCQUKQ0cx2fEfdeIGjbFBOlMB8wYudmWhcqigz7qfx3OuwkKFAUX5c8xBumbXGxRMhhRnYMIjlMkVQPIIRli9/4gP6Q7NVFTKZjNMw8I7rIAt30LjWLH1BBD2bvL+LBRMG9913nzsvWd+YVGAsXXHFFU7gv/jii+PWg+cfExLxMt5h6WSjjNyLKBe4GCIE44rGmM0VqT7fY4FrL/XGbZM29IJbaqpJgLSfUVaCrKmxjk/1/RbWucJ+BjDhhwKNssUY0eQ6it+93IuOvXw+w43cYC52hhGAxiS99tprgUICKUeBlL3AAxZ3FxSXIBekWKt5q6uIpo/14o1hUA488ED3F4E7GbAOpDIjrhA7o1YG4ikQoHnBJ7s4nrpOJLo2ViRmg7Ek4XKDcEVMWDr95IcZwKB2jQf9iABJP5JpKVG/B8Uh4UaHRQwlSb/DOoPfP24iQfFHybZXWHjd7LB6MZ6wDMbLcIhbD/W6/vrrnXABsdLBh1k3XB51TPoJMztkNgl7nKZ7/aDnEO2LaxgxIV6rFM+moHLRj5nG2vAsIUaPyRAVRnGHSwbSgiMUkw0vHtQFd9E///nPbrxzD77yyiuSS1J9vseCPsJt0K8c8WwOGlOqnMW65/Q9woRNMujzLuh+4xqxypDoXggqX6wxmuozIN5zh2yDtB3xRn7liHuB72Oh6b3jPSuN0sAUJMOI4WaGKwNuL5oqWyGlM0HXvPy8rmAkHuChy0vfu+4Rvv0qUMaKu+Al7gVBO2gWi9S1pCwlvWvQ934fePyzEYDVLSBVKwOKwm9+8xs324uwkeysGW2DspMokBWFixlFElvwoqPNCcZNFn6PsMUstFcIwcXyBz/4QVpCOeme+T3ry3h/j8+5rjPFMX4BgnqgMBBX4VWC1J0OdzbvZy/qR5+rwF+sW8TiUF5S3eLCEhRbxuxq0NjR2V8SHoQ1FmKhKXr9ghNCDPdaMZCNcZoKOl5Jy+6NyeG6uLfxvPJbb3g20Wckq/HCOWK5H8UD62NQjFMqY0ljVCgvFoWgCYwg92osBqlcIyxSfb7HuweYsPGuT0Q9cVdkeYcgeKbEUrxJjoCVnjgtjTPyQkyiV3liYgS3WhRM/6QIa6alEpeo71bei9711oBzByk86TwD4j1T9Xx+JQ2XQtK6x7KceuOASSRklDbmYmcYMUBwRJBEUEZIwH9d10Fidg5Tv3f2iXV7mAVlHR8EZlw6cKPQxRlRavygVOEHjvCMEsIsIS8sZvRRvjiXF9wsuD4zXwhdxO8wG4gVhnghXrzeh7uuy4QbFWXACkAQNYpWInC3wg0LAU4/JwvB2LjQ8ZIlcJpAcGb0CNT2xjAhsHBeVSBjZTGLBdYeLBqs5UK98E3X9WWYMWYfa6CkAgIj7c/Lmt+jGBL4TbsjaJHV0B+UTN0Q3FR48CpIxF5QToQIjgsKdOZ4zs8MKddDQeV33vWTwgY3JFx3UPoQ3v1ZuwDFVZOcYGGgX1EAaR8Un2SsfcmOhVgwVrHOkmCF4GlmoBF6cPtjPZRiyCaVjXGaCgi4jFv6E7ci4llwaaMfSZTCeOY5578PyORFZjHKS3A6CjOCLWM9llU8FsSv8bziWrQH44d7gmxpPJe8a7XFgwQPZN6jbH73Tp6ZjDeeiQjBKBGMO56BWKzCcgdNllSf77FAkSFxDWOf+qPckLQB5Yj7gzYMeqb861//ct/zPuI3vAPYSECD2yGKMy6fvB+4L5ko4X6izXBFVGsJExx33HGHU2y4vncdJN45/B7X22T5/e9/71x36XPerYx/rES4QwbVJ51nAAoM72neX4xxteZpJkcW+qV9sATxPkV5537E8s++WFZSyot1Mp04UqPIyHeeccMIk1TWE0m0ToKulcB6CIMGDXLrRvTo0SNy+umnuzVjgti0aVPkyiuvjPTv3z9SWVnp1o741a9+5dZwiLUWzEcffeTWM+nYsWOkQ4cObu2Kl156KeY6GbBkyZLIpZde6tZEolysrbP//vvvsZYJ64tQ/qqqKrfOi78M8dbKgL322ssdw/lZgynZNVFg3rx5bo0Vfsv6U7HqoutKsJ6Hd92hVLjnnnsikyZNcm3OWjOf//znIzU1NZFx48a5NWGSWdvGy44dO1xb8vu2bdu6vjn44IMj//jHP2L+Rtd5YY0W7xo7cMkll7jv6KMgOJ61Y4YOHerWy/H3S7z1rJIZx0Ewhljvg9/ST0GwJsiXvvQltz4Q9WLNMNbJ+sY3vtG8nlgyxBsLyfQHawd97nOfc/cV/TF27NjIjTfe6MZL0BiOtw5SKmv7JFoHKYh4920q4zQe6Y6Hf/7zn24cM54pA+3Imj6M9yAeeeQRt2YWx9J35557ruv3dNY+e+utt9yzaMKECW4tIfqRdXgYXx9++GEkFWhDnhf+++wPf/iDW7+H+6hdu3buOhzLWNm8eXPS6yAFjcVE9Ys1tlJ9vsfqW46bOHGiuwd5D1HPGTNmxOxv1oL67Gc/69at0/vcXy9+T314v7F+FO3FWOR59fzzz+9Rhvfeey9y/PHHu7qwHX300W6NrXSeQTwTPv3pT7txT50OPPBAt5ZcrHZJ9RkA9957r2szjvfLBtu2bYtcffXVbgwyvlmv7rLLLousXbs25v3N+lHsv+KKK5Kup1G8tOKffCtphmG0XMgYxEwrM3vqwhYGxCiQKYnZQE1raxiFho3T1ME9DQs6mfCSzXhpGJmClwhugXhrpOIKbhQnFoNkGEbewB1QF2RN1b1OIabCn16X8/Iyw/XQBCijELBxGh64R+G2SQyOzfEauYDEICTaYbFnU45aBhaDZBhGziE4lmBc4hjwKSdomODddMCP/8c//rGLL2BNFc1Wha8/1iNeaIaRb2ychgcxMWS9xIJE4oJsrgtnGEDCJhJCkJLeaBmYi51hGDmHmV/WriDwm6DfW265Je2F91iZHdc8slrpGhUkFCCQmBeaP42rYeQDG6eGYRjFgylIhmEYhmEYhmEYTVgMkmEYhmEYhmEYRhOmIBmGYRiGYRiGYTRhCpJhGIZhGIZhGEYTpiAZhmEYhmEYhmE0YWm+02Djxo0uRTEphSsrK9M5hWEYhmEYhmEYIVFXVyfLli2Tww8/XLp27ZrRuUxBSgOUozPOOCOjhjcMwzAMwzAMI1wefvhhOf300zM6hylIaYDlSDtgr732yqgDDMMwDMMwDMPIjPnz5zsDhsrpmWAKUhqoWx3K0bhx4zLuBMMwDMMwDMMwMieM8BdL0mAYhmEYhmEYhlHsCtK7774rX//6150Fp0OHDjJo0CD5zGc+Ix9//PEex86ePVtOOOEE6dixo3Tv3l2+8IUvyJo1a/JSbsMwDMMwDMMwCpeidbG78cYb5fXXX5dzzjlHJkyYICtXrpRbb71VpkyZIm+99Zbsvffe7rjq6mo57LDDpEuXLnLDDTfI1q1b5Ve/+pV8+OGH8s4770ibNm3yXRXDMAzDMAzDMAqEolWQvv3tb8s//vGPKAXn3HPPlfHjx8svfvEL+dvf/ub2oRRt27ZN3n//fWdlgv3331+OPfZYufvuu+WSSy7JWx0MwzAMwzAMwygsilZB+tSnPrXHvhEjRjiXO1zqlP/85z9yyimnNCtHcMwxx8jIkSPl/vvvNwXJMIwWS2Njo6xatcqtHcH/DcMwDKOQaNWqlVRUVEjnzp2lU6dO7nMuKNoYpCAikYh72ffs2dN9rqmpkdWrV8u+++67x7FYkaZNm5aHUhqGYeQfFKKlS5e6ha937tzpnp+GYRiGUSjwXmpoaJAtW7Y4mZ53Fp9zQdFakIL4+9//7hrw+uuvd59XrFjh/vbr12+PY9m3fv16N3MaLx0gCpY/oQN51g3DMIoZJpN27NjhEtf07t07Z7NyhmEYhpEKKEXI45s2bZINGzZIr169JNuUjII0Z84cufzyy+Wggw6SCy64wO3j5Q9BClDbtm2bj4mnIN12221y3XXXZa3chmEY+YDJodatW5tyZBiGYRQ05eXlzrBBojU2U5CShAx2J598sstU9+9//9u99KFdu3bNgoCf2traqGNicdlll7lMeUEr9RqGYRSzix3PSrMcGYZhGIVOq1at3DsrV+7gRW9Bwtx24oknOj/6V199Vfr379/8nbrWqaudF/bhWpJotV1cT9gMwzBKDVOODMMwjGKhVQ5dwYtaQcIKdOqpp7rFYZ977jkZO3Zs1PdVVVXODPfee+/t8VvWQJo0aVIOS2sYhmEYhmEYRqFTtFnsdu3a5dY9evPNN+WBBx5wsUdBfPrTn5bHH39cli1b1rzv+eefd0qV33XOMAzDMAzDMIyWTdFakL7zne/Io48+6ixIZKPThWGV888/3/29+uqrnQJ15JFHyhVXXOGCu2666Sa3oOyFF16Yp9IbhmEY2eTdd991z/zp06fL9u3b5fTTT5dHHnnE0pkbhmEYpasgffDBB+7vY4895jY/qiANHDhQXn75Zfn2t78tV111lbRp08YldPj1r3+dMP7IMAzDKD7q6+udhwDZSn/zm99I+/btncJkGIZhGCWtIL300ktJHztu3Dh55plnsloewzAMozBYsGCBLFmyRP785z/Ll7/8ZbfvvPPOkxtvvDHfRTMMwzCKgKKNQTIMwzCMIFhQELp27Rq1joaufxcv9bkuAWEYhmG0XExBMgzDMLIGa1bg8sZ6dPzN9hoWX/rSl+Twww93/8fNjrSwRxxxhFx77bV7pIjl89e//nX5+9//7jwNcLt++umn5e6773bfvfbaa/LNb37TZUNF2frqV78qO3fudMtKfPGLX5Ru3bq57Xvf+94e9frXv/4l++yzj3Tq1Ek6d+7s4l5vueWWrNbdMAzDaOEudoZhGEZhg9KARaahocH9H6VDLTnZWs8CJYYlHm644Qan3Oy3337Sp08fef311wOPf+GFF+T+++93ilLPnj1lyJAhzTGu3/jGN6Rv375y3XXXyVtvvSW33367U5TeeOMNGTRokLvGk08+6RL/7L333k5pgmeffVY++9nPytFHH93s1jd79mxXBhJHGIZhGIWNKUhGSYAAtnbtWje7SyIOBB0EMcMw8ncvlpWVSYcOHaSiosKtgI4LG9+zsS8bsOQD1iqUl0MPPVTOPvtstz+WgjR37lz58MMPo9bRUwUJxQoFCGXusssuk/nz5ztlCCXsD3/4gzvmkksucUrVnXfe2awgPfHEE85qROwr9TYMwzCKC3OxM4oehC0EFwQd3fjMfsMw8ncvst7cokWLnGIEKExYkvRzIYA7nn+RceXiiy+OsnQdcMABrvzsV1CA9t13X1m4cGHzPqxM27Ztc5YkwzAMo/gwBckoepitXrVqlZuRZsaXv3xmv2EY+bsXseayT+9FFCMUDhSlQmHo0KExv8ONzkuXLl2al4/w79+wYUPzZ6xNI0eOlBNPPFEGDBggF110kYttMgzDMIqDwnlLGUaa4MrD1rFjRyd88Vf3GYaRv3sRN7Ndu3a5fRqHhOtrIbm/tmvXLuZ3sdzjgvZ7kzT07t3buemxmPlpp50mL774olOWLrjggpBKbRiGYWQTU5CMoodZaratW7c6IYW/ui8ZENxWrlwpS5cudX/NNc8wwrsXUUBQmMgQR3KGbCZoKCRoh1NPPVVuu+02ty4TcUv33HOPc0E0DMMwCpvCmcYzjDQhIQNpd3HtYUMwwb2H/cnGTPA7TfDAufbaa6+CmuU2jGK9F8kCx9aS7qd169ZJjx49mj/jUjhhwgT3fxJIGIZhGIVNy3ljGSULghcKDYHRqWax88ZMsJ4JM9585lwIdYZh5OZeLCW+/OUvy/r16+Woo45yMUhLliyR3/3udzJp0iQZM2ZMvotnGIZhJKBlvbWMkgUBLB2FRmMmUI40fkmtSYWGpTI3SvleLCXOP/98t2YS7nVY1GiPc8891y1WW0gJKgzDMIxgWkWyvax5CTJz5ky3KOBHH33kVl83ihdijkhHjAUJ5QgLUn19vYwaNaqghLwgV0DcCM0V0EgXTUs9bNgwa0TDMAyj6N9bM0OUz20qy2jR4P6DooFShPLB32Tjl3KJpTI3DMMwDMPIDeZiZ7RoiiVmophcAQ3DMAzDMIqZwpICDSMPFEPMhDd9sroCppLK3DAMwzAMw0gOU5AMo8RTmRcTlojCMAzDMIx8YwqSYRQBxeIKmAm2JpVhGIZhGIVA6UhXhlHiFIMrYCbYmlSGYRiGYRQClsXOMIyCSkRBjJUmotB9hmEYhmEYucIUJMMwCi4RBcuzWSIKwzAMwzDygSlIhmEUBMWyJpVhGIZhGKWNxSAZhlEQtIREFIZhGIZhFD4meRiGUTCUeiIKwzAMwzAKH3OxMwzDMIwsc/fdd7vkI4sXL27ed8QRR7it2HjppZdcXfibLYYMGSJf+tKXsnZ+wzCMeJiCZBiGYRglyA033CAPP/xwvovR4mhsbJRf/vKXMnToUGnbtq1MmDBB/vnPfyb12xUrVshVV10lRx55pHTq1CmuIkr/HnjggdKrVy93nREjRsi3vvUtWbNmTdRxc+bMke9973syadIkd85+/frJySefLO+9914o9TWMUsQUJMMwDMPIA//973/dli1MQcoP//u//yvf//735dhjj5Xf/e53MmjQIPnc5z4n//rXvxL+du7cuXLjjTdKTU2NjB8/Pu6x77//vlN6uN7vf/97Of300+Wuu+6ST33qU7Jt27bm4/7yl7/In//8Z9l3333l17/+tXz7299210G5eu6550Kps2GUGhaDZBiGYRh5gEQkRmmBYoMScvnll8utt97q9n35y1+Www8/XL773e/KOeecI61bt475+3322UfWrVsn3bt3l3//+9/u+Fj85z//2WPfQQcdJGeffbY89thjct5557l9n/3sZ+Xaa691a8spF110kYwZM8btP+aYYzKstWGUHmZBMgzDMEoKYleIYfGDMIjLkhc+f/3rX3euaHvvvbdUVlbKuHHj5Omnn446bsmSJXLZZZfJqFGjpF27dtKjRw8nvHpjipSZM2fKUUcd5Y4bMGCA/PSnP3VuV378MUhBcUqxYn7mzZsnn/70p11SE9yruA4C8aZNm5rrhRXhr3/9q/s/mzemB0EeIZlU+lrnO++8c48yVldXyxlnnCEdOnSQ3r17y5VXXil1dXV7HLd9+3bnyrV27VpJRKKyx2LhwoWuzVEe2rdv7ywgTzzxRGBb3XfffXL11Ve7a1D20047TZYtW7bHOd9++2054YQTpEuXLu6cKDKvv/66pMsjjzzilihgrCiU59JLL3Vt+eabb8b9PS5w1C9ddNxv3LgxSunyKkfA+D300ENl9uzZaV/LMEoZsyAZhmEYLZrXXntNHnzwQSfUIqD+9re/dQL80qVLnSAJ7777rrzxxhtOkEegR4n5wx/+4BScWbNmOeEaVq5c6eJHGhoaXCwJwvntt9/ulKWwIA3+8ccf7xSVb3zjG04JQOF5/PHHnWCMsH/vvfc6y8X+++8vl1xyifvd8OHD3V/WGUO5UOWQGJannnpKLr74Ytm8ebOLY4EdO3bI0Ucf7drhm9/8pvTv39+d94UXXtijTO+8846r9zXXXOMU0UzKHgRlxnUMRYyy0C8ofyg+WFrOPPPMqON/9rOfufrh6rZ69Wq5+eabnaXkgw8+aO4L6nHiiSc6BYJyl5WVORc1lNtXX33VtV2qTJs2zfU51hkvei6+P+SQQyQsWFQbixPjDcWTMYeFKpnkH4xVW2fOMGIQMVLmo48+itB0/DUMwyhGFixY4LZS5IILLogMHjx4j/3XXHONe3Z74XObNm0i8+fPb943ffp0t/93v/td877t27fvcb4333zTHXfPPfc07/vWt77l9r399tvN+1avXh3p0qWL279o0aLm/YcffrjblLvuumuPY+DFF190+/kL06ZNc58feOCBuO3QoUMH1xZ+Lr744ki/fv0ia9eujdp/3nnnuXJqXW+++WZ3nfvvv7/5mG3btkX22muvqPJ4y0gbxyPZstN/3rJru7766qvN+7Zs2RIZOnRoZMiQIZFdu3ZFlaOqqiqyefPm5mOpA/tvueUW97mxsTEyYsSIyPHHH+/+r1B3znnsscdG0uHkk0+ODBs2bI/9tBvXv+qqq5I+F23kb2c/K1ascMfoNmDAgMh9992X8NyvvPJKpFWrVpEf/ehHSZfHMAr9vRWmfG4WJMMwDKOZlTfcIHWz5xRMi1SOGS19r746q9fAsqDWFSDrWOfOnZ1Ll+K1AOFChaVFFzaeOnWqfOELX3DfPfnkk84647U+YKH5/Oc/L7fddlso5VUryzPPPCMnnXRSs/UqGdAJiV35zGc+4/7vdYnDskMiAepz8MEHu7qQ8YyYFoVrYZEiK5oXLBa79c3slJ2y0KZe6wtuY5TlBz/4gbPi4SKpfPGLX3TWQIU6UBfOgwUKSxIWlx/+8IfOAuMFqxmWMtwisSqlAlY3XBb94Eqo34cJ7njPPvus1NbWOusUltCtW7fG/Q0WNZJGkGXP34+GYezGFCTDMAyjGZSj7e++26JahCxjfrp16yYbNmxo/oxg+/Of/9y5YOES5lUGvLEzxCodcMABe5yP2KWwQLAlE9n//d//yd///ncXS4Kr2fnnnx/TRU0hBTSubLj9scUSoLUuKIH+uK1M6pJu2WO1q7qy8b1XQSLltRfqQF00vgvlCC644IKY16RfGQex3NO8UHaUaLagGC0UGAjT1VITfWiShVNOOcUpdyi3xIvx2Q9xaezfsmWLcy31xyYZhrEbU5CMQPBnZmYRf3EewPgpl5fbcDGMUgeLTbGXxy/QK7t27QrcHyurmFcJIl4G5Yj4HDKFIRBzHWKSghIwpEMq5SZTGkkXSApAqnCsIihwb731louRioWWFYUklnKABS2bpFv2MNF2uOmmm1yq7CDiKQ9Yo7wwNqgT+1988UU3drz9yfpGQBxXNiFOizKgfPoVJN7nZ511lsyYMcNZ8LwKpWEY0ZjEawQqR/Pnz3dBsaogMePI7JspSYZR2mTbnS0XMOvvzeKlYGVIFxIBoFAg3HutAv7rDB48uNk64YV1Z5IpN/jPGavcrJPDhpsYCSSwHPzxj390WfNiKVy4++F6htKVKL0zdfnoo4/2EPaTqUsiEpU9qCxB1yVznn7vxd8H1IH3mip/6lKJK2U6aa5xa/NCFkBA2WLdIbLDjR07Nipbnn6fbRiX/oyAKIS4HT7//PNy//33u2x9hmHExtJ8G3uA5QjlqKKiwqWA5S+fk0nfahiGkS0Qcon/wYWJv7FiXhB+ERCZKffO4D/00ENpXxsrk/96LALqt+4QV4MlhKxuXrc2ZvQToUL7K6+80ryP8/td4Yh/YiLLC8oG8TJe9y6yqfmVLepBhj7ikFB+/FBWb12WL1/ulEOFLHJBrnnJpvlOtux+KAtt6k2TjbsYZSG1tVcZgXvuuce5kSnUgTFA1jogcx3t/atf/SowZsfbDkGgVHk3tSixWCvvTG+8GeMG5a+qqspZeBTKQ5sxllOFutPmfuhXXENZFNYLFlBSn1MurEiGYcTHLEjGHmA1YmM2k1lD3AzUmmQYhpEPEDKZGUe4VosGFm2C3/2WEtzeSO9M6mfctxAkSck9cuRIl4AgHXBXInAf1zqEcQT15557rjkNuELQO8exts4VV1zRnOYbC4dXYQsCKwQJHkg6sH79eheAT9IEv0JBemrSc7MmEHXie66pyo+CEkAZiffBtYv4H+J4fvGLXzg3MP7/la98xdWH69E2HM//ge9Y7BTLw/vvv++UAK4TlFgh2TTfyZbdD+mr//nPfzoFhz6lbUjzvWjRIqcU+JMp8D0JHS688EL3/iLNN14Q1Ak4HksP56PdOQ4Fhvgy2gbLEoutpgougrhh4rqH4rPffvu5NbZIG46S7HXnpJ+1Dt51u9SKxnpaQPsQLwRY3NRChmJ27rnnyujRo1193nvvPfnb3/7mzsXYU6g7ihGuofQdx3jhPmGcGobhIeM8eC2QUk/zTdrQl156KfL666+7dLf85TP7DcMoDYotzffOnTtd2mZSO5Mymb98Zn8Q//3vfyN77723S+E9atSoyN/+9reYab4vv/zyhGmmN2zYELnwwgsjPXv2jHTs2NGlh54zZ84ex8GMGTNc+u62bdu6dNM/+clPInfccUfCNN9AnxxzzDGRysrKSJ8+fSJXX3115Nlnn41K97xw4cLIRRddFBk+fLi7Rvfu3SNHHnlk5Lnnnos6F+U77LDDIu3atXO/95Zz1apVrt4DBw6MVFRURPr27Rs5+uijI7fffnvUOZYsWRI57bTTIu3bt3d1v+KKKyJPP/102mm+ky17ULvSNmeffXaka9eu7rf7779/5PHHH486Rsvxz3/+M/KDH/wg0rt3b1d/0m9Tl6C042eddVakR48ers257mc+85nI888/H0kXUo7fcMMN7lyMv3Hjxrnx54f6BaV196bt9m/KmjVrIpdccklk9OjRLp071yFtOenQ+S7oOrE2//UNo1DJZZrvVvzjVZiMxDCrQ3Aj7gnqd1zqMUi42lkMkmGUDprCetiwYVIM4H7F5o2D5FlFSuWgtMrFABncKDtWGyMcXnrpJWfJeuCBB6LSkxuGUfrvrZkhyufmYmfsOSjKy5vX98hlFjvLnGcYRixwIcKVTtem4S+fU12nppAgBsUfK2IYhmHkH1OQjOCBUV4uffv2zVnrWOY8wzASPZPYeFawaQxSMWbWJGsbC3ouWLDAxUoZhmEYhUXxvVmMks+cR3IIsgrxGStWLhU1wzAKExQiEjKgHKkVCeUo1tpBhcyf//xneeqpp1wwP8kBDMMwjMLCFCSjILDMeYZhJAJliEmUYodFRY3scMQRR8RM/24YhpEsxeu8bZQUxDmxYTni5cZf3WcYhmEYhmEYucIUJKMgIAkEmfJYNwLXOv7ymf2GYRiGYRiGkSvMxc4oCPKVOc/IDMs8aBiGYRhGqWHSp9FiM+cZmWGZB2O3C0lHTNE3DMMwjOLEFCTDMNLCMg/uiSmNhmEYhlH8WAySYRgZZR7s2LGjyy7GX93XUvEqjcTQ8ZfP7DcMwzAMozgwBckwjLSwzIN7YkqjYRiGYRQ/piAZhpEWlnlwT0xpLA3uvvtuZxVdvHhx1Po6bMXGSy+95OrC30S8++678qlPfUo6dOjgfvPBBx9IPvnSl77kLNOJ8PcN/Ub56Ufl2muvTWlR4ZNOOkm+8pWvpFFqI9n767333ot7XFCfDRkyxI2LeOP7vPPOk8985jN5eU4YpYMpSIZhZJR5cNSoUc0bn1ty5kFTGo10ueGGG+Thhx/OWwOytMI555wj69evl9/85jdy7733yuDBg6Ul8vrrr8t///tf+f73v5/yb5cvX+4E+3wrly0Z+u0///mPTJ8+Pd9FKQhqamqcwkiW4M6dO8vpp58uCxcuTPi77du3y+9//3s57rjjpF+/ftKpUyeZPHmy/OEPf5Bdu3ZFHauTEkHbv/71r7jPnbFjx7rjfvWrX0kh0XIlGcMwSirzYCFkj7N09aULAnO2FaSzzz5bzjjjDMkHCxYskCVLlsif//xn+fKXvywtuW9uuukmOfroo92ETzoK0nXXXecsHZMmTQq1XC2NH/7wh3LVVVel/DuE+H333Vd+/etfyz333CMtma1bt8qRRx4pmzZtkquvvtrFxTIBcvjhhzslvkePHjF/u3DhQvnGN77h7oVvf/vbTrl65pln5LLLLpO33npL/vrXv+7xm89+9rPO+urloIMOinmN3/3ud7J06VIpRExBMgyj6Cmk7HGFpDQa4cGYKmVWr17t/jLLHBbbtm1z7nrF1De0wxNPPCF//OMfQzunkf6zNN3nNxaTa665Rm677bak3DRLFeo/b948eeedd2S//fZz+0488UTZe++9nQLJxEws+vbtKx9++KGMGzeued9Xv/pVueiii+Suu+6SH/3oR3tMIkyZMkXOP//8pO+166+/3ln8fvzjH0uhYS52hpEFYX3lypVuVoS/fDayi2WPM7xgCWGWE7fPdu3auVlS3MeCYgVmzpwpRx11lDtuwIAB8tOf/lQaGxsTxrnEij8IiolAQPn0pz/tBI62bdu66xAnwawucDzKBDOy6pbijbPARQahhMyIlZWVTmC588479yhjdXW1s0ChlPTu3VuuvPJKqaurSzg4uBYzykA7cX1vXV944QU59NBD3XlRoHDRmT17dmC8yKxZs+Rzn/ucdOvWTQ455JC4rjVYWkaMGOHahD7i+GeffTZuWZn17tWrlysfs+Nhx4ehHPHMPuaYY6L243r4P//zPzJ+/HgncDObjqDpdeOiz1UIvfDCC5v70hsL5Ufb7eOPP3aCZZcuXVz9ED4jkYgsW7bMtTfXY/wg1Pqhj1EGEFYZHwMHDpTvfe97e/Q9Qi1jnbHBcbg24S7lB+vXKaecIq+99prsv//+rn+GDRuWtDUGl6p99tnHuWRRbtrslltuifubDRs2uGtxb8ydOzeqbdLh2GOPdfeUfzzxXp4zZ05S58C6wb3Wvn17N56xSv3jH/9ISinhd7Rx//795fLLL3cTdl4Yrygp77//vov74/kzdOjQQMU82f4N4t///rcbkzouYfTo0c4qdP/998f9LV4YXuVIOfPMM91f/zNAod2TyWaLdZBndLIKVa4xC5Jh5MiSAfl2ASv17HG8xDTluPaB0fIg2cAbb7zhlBAELpQYBEGEEgR4BB5gAgP3E+5bXtYoALfffrsTVsKCMXj88cc7YQZ3FYRcFJ7HH3/cPRsQiIn3wa0NAfGSSy5xvxs+fLj7yzg+8MAD3bj++te/7oTnp556Si6++GLZvHmzfOtb33LH7dixwwk9CIDf/OY3nWDGeVFuEsGscFVVlZtN5rcIUyhj8NxzzzlFAAEZgZXrIDgefPDBMnXqVCdMe0HBQunhXAj4seBcP//5z5vrTV0I2uecCLex+pW2RFB95JFHQu0nhXGDsuaPv8LdiBgx6ocgS7/86U9/coolY4r2HjNmjJsRZzacfkSpBATgRJx77rnu97/4xS+ckoai3r17d3cNlJobb7xR/v73vzsljf457LDD3O9Q5k877TSnzHBNzsGsP25UKF3euDbuAQRejufd89hjj7mJBM6BEO+F9xgun4yzCy64wCnkKNIoPkFCs4JCgpsVY5EyqyBNXNcVV1wR+Bvei/Q5SujLL7/cPPYzAeWP8cF1VaCHL37xi+4a8cYm4GrKvUAbUO7a2lqZMWOGvP32224CIN64RvFHwb700kudske7M3YpCy5uXqUQdzSsXbQZCgu/QT5gQiTV/vXDbymznssL9xyuqVu2bHGKbCqsXLnS/UWG8UPdv/vd77rnFWPlZz/7mYth8oNFiwkh6pWuEpx1IkbKfPTRR9xZ7q9heFmxYkXkpZdeirz++uuR6dOnu798rq6ujsyePdv9/7///a/7y+f6+nprwCy2O/uNYBYsWOC2UmT79u177HvzzTfdc/uee+5p3vetb33L7Xv77beb961evTrSpUsXt3/RokXN+w8//HC3KXfdddcex8CLL77o9vMXpk2b5j4/8MADccvcoUOHyAUXXLDH/osvvjjSr1+/yNq1a6P2n3feea6cWtebb77ZXef+++9vPmbbtm2RvfbaK6o8sdBy+8s5adKkSO/evSPr1q1r3sc9VlZWFvniF7/YvO+aa65xv//sZz8bSYaJEydGTj755LjH0B60C7z22muRzp07u9/U1tZGHefvG/qEstBH/vIl4pBDDonss88+e+znmrt27Yrax3UqKysj119/ffO+d999d49rx0PLdckllzTva2hoiAwYMCDSqlWryC9+8Yvm/Rs2bIi0a9cuapzce++9ri9effXVqPP+8Y9/dOflWRjvvjj++OMjw4YNi9o3ePBg99tXXnkl6r6grt/5znfi1ueKK65w/UQdYqH3Dm3FM3rcuHGuDIsXLw5sG3/ZvPX3329eRo4cGTnxxBOj9jFOkhkHp59+uitXPPzPANqoTZs2keOOOy5qrNx6663uuDvvvHOPcvz6179u3ldXV9d8v+3cuTPl/vWzZs0ad4x3fCq///3v3Xdz5syJpEJdXV1k7NixkaFDh0bJL0uWLHH1/sMf/hB59NFH3fNo0KBBruyPP/541DkaGxsj+++/f/OzQu/Xm266KeP3VpjyubnYGUYO1sHB19YWEM0elj3O8OK1LODKtW7dOmfFxT0MC4Xy5JNPOusMs6kKFprPf/7zoTUoFiIguJmsUKnALDfZuE499VT3f2badcOSgoue1oe6kGmKGW8FS5lapNJhxYoVzqUNywHWDGXChAluxp9r+vna176W1LnpC9wbcT9MxIsvvujqi1XiwQcfdG5G2YKxgiXaD9csK9stMpHBi+N4vuMi5B1T6eJNjNG6dWtnJaPPseB424zreTOQPfDAA86qgNuUd3xgddK2C7ovGDschwWM86m7p9cCoxYwvS/81w6CMga5tgWBSyjX5x595ZVXQs+aSD/6F+nGDTKR9UjrQfmw/CQL1lbe91h1dawA6eJxNcQy6AUrHtZbBcsRn5EXcL1LtX/9YO2FoPsFt0nvMcny9a9/3VlMb7311igPmEGDBrlnHPc/zyusbtOmTXPj5jvf+U7UOXA5xQqmFsZCxfx7DCNL6+Dw8uQvn1GWzAUse1j2uPC47rGZMmv5ZikUxvbvLNecGtulJwhe+rhvEXOBO5tXIPIKgsQqHXDAAXv8HkEwLHDHIgPU//3f/zkXKYROXGY03iQea9ascW54uP2xxUuuQF1QAv3uKpnUhXPGOgdCGwKRPxED9U0GXNGIrRk5cqSLxTjhhBPkC1/4glO+vODadPLJJzt3HVyQcuGWHCRA465EHA3xJYsWLYpKcxwvE1iyIGB6YWwgxPrdmNiPcqagYOLChiAab3wALl7Esrz55pt7KOvcF97x6C+PKhy4hcUDlz36CbdM3DZxr8KFjP71Q3/Tn5Q/G4lt6Md03bdIHIDCw+QJ9xX1wLUO19JU7xdkAFxU9XsFt0x/EhPuB8AtmMmbVPrXjyrEQbFK3FfeY5LN7vjnP/9ZfvKTn+yRqS4IJlWIxcNtFGUTd2dcaX/wgx84NzxiqQoZU5AMI0R4mSHQYC1i48GILz/KEi8gv+JU6pmxcolljwsHlKO3F62XYoZYH5QjZnJJMYvgh6BETFJQAoZ0iCV4+dcHAQLrscIQN4PfP7ENKHCkykVoiIWWFWWKOJAg/ApFvklW4CKGhtTi2iZ/+ctfXFwFQepeawqz3whjHPf000+75AHZBGUnSAkgporECcRzICAi/GElYIyFMaawGiWzz6/AcW2SIKCAB6FCKG2NBQ5LBMeyn/cPVkDa3V+HZK4dBAkgsDqiPBMrx8a9SOyPPy30WWed5RI/oHhyP4QN/Ug8XDowAUD8ELGCjDssuSjHxJcRZ5Mrku3fIBij3D9Ygv3oPpS0ZLj77rud0oiFiPTryaLlI76MZx1rHTFZTMydJrhBedL+Yh9lKgTZyBQkw8jC4qmY573JGAClyK84BQU5Gka+LTbFXh4yN6FQeDN+MWPqzySFS0+Qi5dm0YqHumH5z+mfJVYQctgQLkgEwEw0ygDB+LEULmaNCaBG6fJnVfNDXT766KM9Zs2TqUu8c8Y6B5nAeH5lksZbZ5jZeD6iNBHk7lWQqAuWN6xNJEhA4A4rY10QKBAIw0FjioQed9xxR9R++t/7HM91wDkJDcikh/IT79okZMCS8Oijj0ZZh+K5aKUL7zfcrNgQ8LEqkWzCnxaaiQw+o3QwiZHOmkexIPEKGQCx1qYLYxtBno33OQodSQewgKiLWqz7BYuRwm+xOvrvYdbM8ltgSbwAmvwk2f4NAgWeZw7JT/yQbIIyJpOg4ZFHHnH3JPVn4dhUUJdMtYCRRAZFKCjRB5MQbLjmFcIaYqYgGUaO1sEJUpwsi51RaKTqzlaIMPvtn+km85rfuoNl4uabb3YZlTQOCbc2BPJEaKYtYif0Zc75/a5wuJQQC+S91xFaEF68ri8ISX5li3qQHpzUwig/uKJ5oawqeFAXLDEI8igSgBtVLNe8ZCCmibox849QqGskURaulUl6XtzEvK5pWNZ5RiLU+uF5SewRcUgI3c8//3xU3FiYYHHEmoVg5xVyg8YU8SG4cHqFfhV2/X2ZLXBfwwqE65M/3gxXUxQUyqQWIb+7KdadMPH3K+NcrZxBrl4oTep2hZJEFrcwIE6GSRF/BkEEdO4LFOFU6sEYJC4LBZ2YqSAFCQWI43772986l0JVaFCqaWtcRf1KHIojLriAbMBn7mlcSlPp31gQk4jiiZJEXJsqcGS3JCOif9KDZ5VXgX7llVec5Z3JC56L3tiqWM8ihXuD7If0P88SwHruXwwbN0Fir7CyMxGSrJtutjEFyTBydbPZAqKGkRNwwyLFNQIXQg0xF8QT+GNFWEuE4xBmCCrWNN/MBJMeNx7MgBIjgGCH+wjWENZ/8a97hiBCYDNKC/EFfM81VflREIgoI640uJggJBAfhf8+s/z8n2Bv6sP1SAzA8fwf+I7AaVyZCPBGIOE6mtI8XYg7IJ4ExYGEAZrmm7bF2pMu1ANLEPWm7RDgUO5oq1iue7g7EZxOeUjV7FcYwwAhlmc1besVSBlTxE1h7ULoJsgcgdGrRKnijCKJdZDZecYUfZctoY84HmJ+cH1inGCZRFFH2GU/rm4IxsTQqGUHYRSLHUI3LnFBLljpgqWBMUk/4VKFRZXxgqKN21qsMYYCQapx2iyMdXFIEsHY96eMTzbNN+3FRCftibcHcUDcX4yPWFYXFASeB7jg8UzBeoUygmseqdn99eI+J1EBbmU8G+677z7nnsgzSNOBJ9u/scB6Rz9TbhQizsszhjr5kyfQPyTN0DXclixZ4uqAooeixYSAFxQfVX55lqobJ/WiTih7WMi8a2CxkCybF3W145nqV57ySsZ58FoglubbMIxip5TTfJMO+cILL4z07Nkz0rFjR5fKmHS2/hTBMGPGDJdyt23btpGqqqrIT37yk8gdd9yRMM030H7HHHOMS3/cp0+fyNVXXx159tlno9IOL1y4MHLRRRdFhg8f7q7RvXv3yJFHHhl57rnnos5F+Q477DCXxpnfe8u5atWqyOWXXx4ZOHBgpKKiItK3b9/I0UcfHbn99tujzkGq3dNOOy3Svn17V3dSLj/99NMZpfkGynrwwQe7spHC+dRTT43MmjUrMCUzqYWT4ac//alL9du1a1d33tGjR0d+9rOfNac39qf5Vkh3Tpph2mDevHmhp/kG2pD29af5JsU1KdcpL+1B6vigcfHII4+4MpaXlydM+R2r3YLqrnX1p5+mzW688Ua3n7HYrVs3l6r8uuuui2zatKn5ONIvT5gwwY3DIUOGuN+Qeto/1rlPglKwB9XVz7///W+X7plU1aS8JtXzV7/61aglF7xpvhXSYpP2mTZ7+OGHo9omnTTfBxxwQOT8888PrEMy4+BPf/qTux979Ojh2pT797vf/W5Ue8ZK9U9ab8Yz9yrPhUsvvdQ9k/zloL/ee++9yEEHHeT6hLrxWz/J9m8sli1bFjn77LPdvcvz8JRTTmm+d7xQF2//vtjUtrE2+kf5xz/+4dqrV69erg95/px55pmR999/P2H5CjXNdyv+ybeSVmyQmpSZK9wM4i2YZhiGUaiob7h/BtwIhuxzBDxjWTBKm1dffdVZt5ilTzfI38gfWGGwUmBlLYRYliAYX6TrRo40wntvhSmfZ20dJDqehwvmRW9KSsMwDMMoNnBDsqQqLUcZxsXql7/8Zb6LYqQBbqm4hBWqcmQUB6HFIOFniH8i2S7I0ONfnIsXCz7M+Bfii51J5hvDMAzDyAW8z0gQgH89aW6NlgHB+EZxQiygYeRdQcI6RP56grHIGELAFlkoMH+RBhUPPlL6keKQwFECSUntSJAgmTVsRs4wYkNAN5MNlvnOMPIDAc4Iy6x3Q4C+YRiGUfpkrCCRq50Ul2QhISNPrNV+vakAWWNAVwYnvaNhGMHK0fz58926SaogkTqW+83SgxtGbgg7DbJhGIZmijNKWEEiLSdrEyQLChTpCtlIT2gYRjBYjlCOSMuJNVYXmiWFbNA6S4ZhGIZhGEbmZJykIRXlKMzfGkapg9WIjQUUWYeAv7rPMAoN3KlZQJHFIPlrCVINwzCMYiUnC8UuX77crajLrPfAgQNzcUnDKHpwqWPDcoRyxF/dZxhhEJYSw3mIQcUtlP+j0OMGymrzupq8YeQDxiPjsrGxUcrKyty4tDFpGMVJpOn9kguyluZb06IeeeSRbjVlVpImXolVgHXVXMMwYkMCE1a7ZjYe1zr+8tkSmxhhgLDIiuxhKEkIoGyqGPFX9xmFR0ux9qnizkZd9f+lWl/DKGUikYh7Z5WEgkScETFHLOzEQ4ksdjt27JCLLroom5c1jJIAQZOEDGwoRV26dHGWJMMIAxY95WWzevXqjAVGZuc5B0oX8JfP7DcKi5akNJjibhilcy+vWLHCvbNyJQeVh7Uo13e+8x0XTO7lvffek8cff9xZjoBFu7785S/LD37wgzAuaxgtgi1btrhsj8Qebdq0ybnaWSY7I1OwRiIgr1+/3o2r1q1bx52ZQ4DWjeN0U0VIZ/b0HOznnKo0GYWBt6+UUu0r6kl9/XWlntTXMIzCJtL0flFvhPbt27ukVbkglKfh/fffL2PGjHGLxHrZZ5995MYbb5Rly5a5yn300Udyxx13yJQpU8K4rGG0qEx2CLT85bN/IWbDSBWExEGDBrmsiMS1xVOOeEGhqDPuWKqBv3xGAOUv6+GtXLnSxZoSc4rShbeAUXhgLaK/mGhhgXf+8pn9pQbug6zDyPII1JO/fGa/YRiFT6smt+1OnTpJVVWVe2flapmTUK6C6xxrGrEI7O9+9zu55ZZbZNy4cfLHP/5Rzj33XBk8eHDzTOO+++4rd955ZxiXNYySR7PWMWOimex0XaR8woQHAjGCMvd17969nQJn6zMVn5LUr1+/hMep8oOCrglDsDrR3/xlP4oW7noI2riEjh492sZDAUJfohCB9iUKA31WassHBK0lx3PKLPCGYeREQUJw++pXvyrnnXeeXHPNNU4Juvjii+UnP/mJvPrqq86ChO8gDyaUJcMwijeTHULH3LlzZc6cOU44hs6dOzsr8qhRo4pKKKYuKHkqPCEkhln+bJ8/34o6ViLvfgRs9jMeirGeLQHGIJYU+olNlYZSTP6icZwo78V+DxqGkVtCfUoQRH7zzTfLJZdcIldeeaV7MF177bVy+eWXW3pvwygRYQaBn0yU27dvd4IwgjGC8qJFi6RHjx5FMwsdNLtMW4c1u5zt8xeCot6uXTs3DgpJgTfi09KUBupVLM8kwzAKh6xEZI4dO1aeeeYZueuuu5zL3fjx4+XZZ5/NxqUMo0UIM1hmdMu3gI1QhRsV7lkIyKx1w/8J+M+3618hxXeVUvxYrJTzjEVLRV+8SgP+/PwtVeXIMAwjrwoSs4aXXnqpC6DC1eKEE06QWbNmyWmnnSYzZ86UL37xi/LpT3/afV6wYEEYlzSMFkOhCTPMOKMUEbiP5Qhlif+TNrqYLAfqNoblQ93G+EydiNNYunSp+5vuWj6xzl9MSmQiRZ1xUGgKvGEYhmEUhIJ02WWXyaOPPio33HCD/PWvf3UCxkknneQEAWZNv//977uYBZQnrEnf+973wrisYRh5siaQup90m6QfJw4JQXno0KEFF8egySSClB2v2xiJJviLYM9xPK90w00uHSUp6PzF7H4WS1EvNAXeMAzDMApCQXriiSfc2kYXXHCBsxL95S9/cQIJ1iOFTEkoTy+99JJL3BAGCBwkhcBi1b17dzdLe/fdd+9x3Je+9KWodTt0I8uSYRipgQCMpeCAAw5wKfsnT54sBx10UMElaNAYoFjKTpDbGIoeFrEw3OJiuaUVmhJpGIZhGEY05WElZyBAWyGAGwWE/X72339/efPNN8O4rBNarr/+ejdzOXHiRKd8xQL3HxQ3f7kNw0gdFKEBAwa4rVDxxgBhvWZChc8Ep6ulwx+sjvUbJYpkE5mmVW9pwfCGYRiGUSqE8qbGhQ43u+nTpztB5KmnnpKzzjpLhg0bJtkEqxTpwxF23nvvPdlvv/1iHotQcv7552e1PIZhFNcaUv4MV7jXhZlW3TJoGYZhGC2BSCQSd8HxFulixxpIL7/8slNQSNTwpz/9Se677z7JNliFUknfyarvxEwYhlH4xIsfylYMkLnFGYZhGEbyzF+9VW56Zo4c+ssXZfnGHVIqhObrccghh7itUNE1W/jLjPJnP/tZufHGG90ssWEYhUUYawils4aUucUZhmEYRnzWba2Tx6Yvl4em1cj06t0LxsPDH9TIZUfsJaVAxgoSCgfZrHL921Rd8cicR0A56Yiffvppue2225xLIHFL8QSu1atXy5o1a6L2IbgZhpG/+KFkSFfZMbc4wzAMw4imtn6XPD97tTw0rVpemrtGGhojUd9PHtRVBnfvIKVCxgrSwIED5YorrpCvfOUrThFJhpqaGueGh5KSi0UTf/7zn0d9Pu+882TkyJHyv//7v/Lvf//bfY4FZbzuuuuyXkbDMFKLH0oGU3Z2W+N4zlqiCMMwDCMVIpGIvLdkgzw4tVoen7FCttRGu7oP6NZOzppcJWdOGSBDe5aOchSKgvSHP/xBrr32WpdN7uCDD5ZjjjnGWWpYEwXhhsbdsGGDy3JHIoXnnntO3nrrLRkxYoRTPvLFlVdeKT/60Y9ceeIpSCSfOOecc/awIJ1xxhk5KKVhtEy88UNhJEsoBmUlG4pMGK6KhmEYRsti8dpt8uC0GmctWrY+Oq6oU9tyOXl8PzlzcpXsN6S7lJWVTmIGLxm/IT/zmc/I2Wef7RaKZQ2in/3sZ+5F7M9kgaLEy/m4445zVhvWSyorCyVHRFq0a9fOpfJdv3593ON69+7tNsPINjbTn1n8UKETT1mBbCgyYbgqGoZhGKXPxu075bEZK+ShqdUydenGqO/Ky1rJEaN6yZmTB8jRY3pL24rWUuqEMoWIooNFha2urk7ef/99mTNnjqxbt859jyLCoqz77LOPyzxXCGzZssUJD7169cp3UQzDZvpbQLKEeMoKZEOR8boqMklFJk/KwRpwxd6ehmEYRmbUNeySF+escZaiF+aslvpd0XFFEwZ0cS50p07sLz06Fob8nitCfzuiAH3qU59yWyFQW1vrVrDv1KlT1P6f/OQnTmA44YQT8lY2w1Bspj92/JBa1pYvX17UilKiuKowYq78qFsiE0JsJJzheVhdXS1t27Y1VzvDMIwWBrLvtGUb5aGpNfLYjOWycXt91Pf9u7SVMyZXyVlTqmSv3tGyc0ui+KQMH7feeqtzRUF4gscee8y9/OEb3/iGi3+aPHmyS+uNFQueeeYZefLJJ51ydPrpp+e1/IYRZlKCUqOUYmgSxVVlI+ZKXRUXLFjQ7KrYv3//5vFlrnaGYRgtg2Xrt7u03GyL1m6L+q5Dm9ZyEnFFU6rkwKE9SjauKBWKS8II4Fe/+pUsWbKk+fODDz7oNjj//POdAHDKKafIs88+K3/961+diwnC1Q033CD/8z//k9c4KKPlESvOqFSTEmRKKVnWEsVVeb9jTGDh2bFjh1skN12rmboqch6s6bgUsx4czz1TwA3DMEqbTTvq5ckPiSuqkXcWR8fcowMdOqKXsxQdN7avtGtT+nFFLUpBWrx4ccJj7r333pyUxTDStYaUYlKCMCgly1qiuCr9TpUiFBrGS6ZWM37DEgybN292/0c5KiUF3JKbGIZhfEL9rkZ5eS5xRTXy7OxVsrOhMap5xvbr7JSi0yb2l96d21rTlaqCZBilYg0ptaQEYVBqlrV46zLpdyhHjAHiOUlwE4bVrFQV8FJywTQMw8gkrmhG9SanFD02fbms2xY9idinc6WcMYn1iqpkdN/O1tBJYG8QwygQa4gtatpyBPtcW81SzQpYLFaZUnLBNAzDSJWajTvk4Wk1biHXBWui44raVbSWE/fu65SiTw3vKa0triglQn3jbd++XQ499FD5yle+Il/72tfCPLVhFD35soYUi7DbUtJ952ucJKuAF5NVppRcMA3DMJJhS229PPXRSqcUvbUwOq6IJUgPHt7TudAdP66vdKgsrGd2MRFqy7Vv314WLVq0xyKxhtGSUQWF2BKETWJLtm3blhNrSDEJu7FI17JWrIphrq1m/nYikU2xWGVKzQXTMAwjiIZdjfLq/LUu2cJ/Z62U2vrouKKRfTrKWVMGyOmT+ku/Lu2sEUMgdGmB1Nmk0f7qV78a9qmNkChWwbEY8Ssomp0MQbNdu3ZZb/sgF6QVK1a4cpHNrFT7v5gVw1xazYLaiSQOKPHFYJVpiS6YhmG0nLiiWSs2y4NTa+SRD5bL2q11Ud/37FjpFKIzJ1fJuP6dzTgRMqG/cX/0ox/JOeecI1/4wheckjR06FAnCPrp3r172Jc2SlxwLEaCFBTanXsizNn4WEqv3wUJK++yZcvcoqGUoVT7v9hjU3IVjxbUTqwdx4u5GKwyLdEF0zCM0mblplp55APiimpk7qotUd+1rShzKbmJKzp0r55S3tqWqskWob9Fxo0b5/7OmjVL/vGPf8Q8DjcOI/cUu+BYbOQiRiKe0ut3QeIYrAP0NzPtuej/fFgsLTYl/XZCeUaRrq+vL1irjFnBDcMoJbbvbJCnP1rpstC9Nn+tRCLR3x84rLtzoSPpQqe2FfkqZosidCnlxz/+sZn5ChgTHEsvRiKe0ut3Qaqrq3Ppo3v37p0T96l0LJZhCL8Wm5J+O+ECiuVfLZCFZpUxK7hhGKXArsaIvLFgd1zR0zNXyvad0YaD4b06OKXojMlVUtXV4opyTehvvGuvvTbsUxohYoJj6cVIxFN6/S5ILBa6Zs0alzAiF+5TqVoswxJ+0233lmaZiNVO9E2h1tus4IZhFDNzV25xGege/qBGVm2Ojivq3qGNW8CVuKIJA7qYwSGPFOYb0MgaFtScW1RBQRlBsCO2o1OnTjlVer3xLCgAfM5VUHuqFsuwhN90YlNammVClUFdkLZDhw45SRySKWYFNwyj2Fi9pVYe/WC5iysi8YKXNq3L5JixveXMyQPkiFG9pMLiigqCrL0FX3/9dZk6daps2rRJGhuj0xEiKJHMwcg9FtScHplaFhD0uRfUikOcR1iCdypKb677P1WLZZjCb6qJDlqSZSJIGaS9Bg4cmLWxEJZ1zqzghmEUAzt27nIpuYkrenXeWudS52W/Id2cUnTy+H7Spb3FFRUaob8J169fLyeffLK88847brYcIYe/oP83BallZMgqFTK1LGRb8E5V6clG/8cSflO1WOZT+G1JlolcK4NhWufMCm4YRqHS2BiRtxatc3FFLOa6ta4h6vshPdo7pQgXukE92uetnEYeFKTvfve7MmPGDJfB7oADDpBhw4a5dZEI+v3Nb34jb775pjz11FNhX9YwskY6cTReZYF4n2wL3vlUehMJv6kob/kUfluKZYL+WrlypRujJOtg0irbymCYCplZwQ3DKDTmr97SvF5RzcYdUd91aVchp07s5xSjKYO6WlxRS1WQnnzySbf+0bnnnivr1q1z+1h4ECHp97//vZx11lnyrW99S/75z3+GfWnDyLtlIUhZUPelUhW8S0X4bQmWCR2f1dXVzuVz+/bt0qtXLzcuszkmw7bOmRXcMIx8s25rnTw6fblzoZtRvSnqu4rWreSo0bvjio4c3Usqy1vnrZxGeoQudSBg6FpIvAQBgUk57rjj5Oqrrw77soaRtbiIVCwLQcoC6w6ROplrlKLgHU/4Tce1Kl/CbzFaJlKN69HxSR05js/Lly9343H48OFZG5MtxTpnGEZpU1u/S56fvVoemlYtL81dIw2+uKLJg7q61NynjO8n3TrY862YCf3N379/f+e+AbreyvTp0+X00093+2pqasy8aBQEyQrvqVgWgpSFbdu2OYGfDGHFIniHJfwWW+KDQrNMBClAwD5cN3nWooBrdkIUcR1rQWNMxyfjl75iQVjSvvPczma2vpZgnTMMozTBDfndxRucUvT4jBWypTY6rmhg93Zy5qQqOXPKABnas0PeymmES+hvw8MOO0yeffZZ+d///V/3GVe7X/7yl9K6dWuXze7mm2+W448/PuzLGkbKJCu8p2JZiKUsILAWkuCdK+EX60QyrlUtaf2hZOsapMCr2zK/37Bhg3OT69Kli8s+t3TpUpchkeNpb1X29XjNoOh199REGv369ctqexejdS4eLWm8FirWB0a2WbR2mzw0tVoe+qBGlq2Pjivq1LZcTpnQz1mL9h28+/1mlBahP9G//e1vOwWprq7OWZBYOHbmzJnNab1RoH73u9+FfVnDyGpcRLKWhZY4Ux5P+E3GtSpX6w8VgkCVSl2DFPhFixa5scpnFCN+y7N29erVUl9f72Y62c9v+K22uXfh4F27drnfYNnM5fgsNOtcurS09bIKEesDI1ts3L5THpuxwi3kOm3pxqjvystauXWKiCs6ekxvaVthcUWlTOhP8/Hjx7tN4UX+3HPPuRcIVqSwF8k0jEKKiyi1mfJMhd9kFMZcuOEVikCVSl2DFPgVK1a47/g/ig4uciRaYDKKv1gqObcq+1wPK5P3eihHJGbo3LlzixmfYVJsbqOliPWBESZ1DbvkxTlrnAvdC3NWS/2u6LiiCQO6yFmTq+TUif2lR8dKa/wWQs7eirw8DKOQyJa1p1RmysMgGYUxrAxn8SxEhSJQpVLXIAUeRYjf6T7qw2fikfjL915lH4tSUEwcytGgQYMK2tpWqLSk9bIKFesDI1N4Nk5durE5rmjj9vqo7/t3aStnTK6Ss6ZUyV69bWK/JZKVNx6+8DfccIO8+OKLLgD44Ycfdq51vHCvv/56ufDCC2Xy5MnZuLRhJE1LtfbkmkQKYxiWvEQWokIRqFKpa5ACz3pywLMURUcVPCxCPGtJ2MBfVfax2BN3lErbFoq1rVCxjHz5x/rASJel67a7tNwoRovXbY/6rkOb1nLS+H5y5pQqOXBoDykrs7iilkzob7tZs2bJoYce6hIysFAsL1peuPrCf+2119yL/Y477gj70kaBU4iz0qVi7SnEts2lJS+RhahQBKp4dQ3qwyAFHnr06LFHXw8ZMiQw4x3XI3YJ9zwsTChZ8dq2UKxthUpLjDMsNKwPjFTYtKNenvxwhTw0tUbeWbw+6jt0oENH9HKWouPG9pV2bSyuyNhN6BLU9773Pfcifeutt9xMLWm+vZx88sly3333hX1Zo8CxWelw29IrCHO/LV68uGhn/DOx5GlbLFu2zGV1Q0kIshAVikAVq64Qy2oTpJQE7QtS9nVySjMsJZNpqVCsbYWKWZ7zj/WBkYj6XY3y8lziimrk2dmrZGdDY9T3Y/t1dkrRaRP7S+/Oba1BjT0IXXp65ZVX5Mc//rFz+dCUtF7we2ctJKNlYbPS2VM02XCtwjpQaDP+yVq20rHkedtCU16jKKIkkbDAayEqJIEqqK6sZ5QNqw1tz8Y51XLGZyxQsc5bKNa2QqZULM/FjPWBERRXNKN6k1OKHpu+XNZti57U6dO5Us5w6xVVyei+na0BjbiELh3gWkdmpVjgH48gZ7QsbFY6e4om9xT33bBhwwpqxj8sq2EsJcvbFoMHD3bKkSpJtI3fQlTIAlWq90eyimc6912hWNsMwzCSoWbjDnl4Wo1Lzb1gzbao79q3aS0njOvr1is6aHgPaW1xRUa+FKQpU6bIE088IZdddlngS/1f//qXHHjggWFf1ihwbFY6eeIJv0ECL2vglJWVFdyMfxhWw3hKlr8tsBwtWbJEqqqq3MKpxRSHlcr9kYrimc59V0jWNsMwjCC21NbLUx+tdErRWwuj44rwJD5kr55y5uQqOX5cX+lQac8uI3VCHzU/+MEP5JRTTpFLL71UzjvvPLePFzlrIZHZbvbs2XLrrbeGfVmjwGnps9LJzvgnEn6DBF4WBm3btq07vpDaNpH1Ipk2iadk+duCVNccg3JUqJaiMO6PVBTPdO67Yk74YRhG6dKwq1Fenb/WJVv476yVUlsfHVc0qk8nF1d0+qQq6dvF4oqMzAj9rXfiiSfK3XffLVdccYXcfvvtbt/555/vfENZe+Oee+5xKb+NlkVLnpVOZcY/kfAbJPD269fPWU/YX0htG896kWybxFOy+vfv39wWZGjjnDxjWECV/+e7/tm6P1Jxm0v1vrNkKrnDFFHDSAyy46wVm+XBqTXyyAfLZe3Wuqjve3aslNMn9XeKEYkXkklEYxjJkBUJ4gtf+IKcddZZ8uyzz8q8efNcfMTw4cPl+OOPd+tyGC2TQo4BySapzPgnEn7jCbyF1rbxrBfJtkk8JUvbgv2ksSb+iOQMKF5btmwpmix+SrJ9mKrbXCpjw5Kp5AZTRA0jPis31cojH7BeUY3MWbkl6ru2FWUuJTdKEa505a3LrDmN0AldelChrUOHDnLGGWeEfXrDKDpSmfEPEn4RcFnskwWYVSEqNGUoiHjKXLJtkshFjHOxMQnTvXv35jYrlCx+xeaumm4yFbOGpIYpotnBxmFxs62uQZ6ZSVxRjby+YK1EItHfHzSsh8tAd+LefaVT24p8FdNoIYSuICGQnH322c6KxIKxhtHSSWXG3y/8IvzjMkamOtzIinGNoyAlJdk2ScZFrKVlSMymu2o6SR3MGpJ6HFdLG7O5wMZhcbKrMSJvLNgdV/T0zJWyfeeuqO+H9+rgMtCdMblKqrq2y1s5jZZH6BIWytF//vMfueOOO1ywNPFHn//852XMmDFhX8owSm7G3y/8YjnS1PisXVMq1pFU20TrGiR4tsQMidlyqUzHOmXWkNQF9ZY4ZrONjcPiYs7KzU4peviDGlm1OTquqHuHNm4BV1zoxld1sbgiozQUJBIz/P73v5fHH39c/v73v8uvf/1r+fnPfy6TJ092ViUy2/HCNYyWQqoz/l7hF7c6LEcoR6U005yOFSSW4EmCCp4pLTVDYr77xawhqQvqLT2rZzawcVj4rN5SK49+sNy50JF4wUub8jI5dkwfpxQdNrKXVFhckZFnsuKjw4vhzDPPdBsz4A888ID84x//kO985zvy3e9+V4455hhnWeL7du3MZGqUvktNujP+pTzTnGqb0L4oi9rGtbW17jOCZ7ouZ/mOWcj39cPol1Ieo9kS1FtyVs9sYeOwMNmxc5dLyY1S9Oq8NdLoiyvaf0h3F1d00vh+0qWdxRUZhUPWn8ak3b344otl4sSJcuONNzr3u6efftptZLS75JJL5Nprr3VJHQyjGMmm77vNNH8C6xzRxiyKq2m8Sc6ABSkdBTTfMQv5vn5YpDtGC1E5DFNQJ5Mi45O/pCpm3HopxMyTxYw9KwuHxsaIvLVonXOhe/LDFbLNF1c0pEd7F1fEQq4Du7fPWzkNIx5ZfRuRehc3O7aPP/7YuQl9/etfly9+8YvuBYI73m9/+1tZuHChU5wMo9AJEuqy6ftuM82fsG3bNqmrq3PtzMQL1un6+nq3Px0S9Vu2BfhSiZkI012y2JTDIKj7unXrZM6cOS71PDBe+T/9Wuz1K1TsWZl/5q/e0rxeUc3GHVHfYR06dWI/pxhNHtjV4oqMgif0JzUvhvvuu0/+9re/ydtvv+1efKeccor88pe/dIvIel8Ot956q0vkcP3114ddDMMInVhCHQkUspmRqthnmsNSNLAy09a0McpR69at3da2bVtZuXJlyueP5woVhgCfSSazXFpXwrhWOu6SpaAcxmoL6sFYpS70K9Yj6swkYbHXr5Ap9mdlMbJua508Nn25PDitRmZU754QUCpat5IjR/V2StGRo3tJZXnrvJXTMFIl9Dduv3793Av3oIMOkttuu03OPfdc97KIxbhx46R3795hF8MwQieWUIfQYzEY2bcUEK+I6xZWI/qA83EOsvzV1NSkfP54MQuZCvCZZDJD6cuVdSVflpxcBtTnw5WP1PwoSIxX6oeLXS6Sq5Sq26JRWNTW75LnZ6+Wh6ZVy0tz10iDL7Bo8qCuTik6ZXw/6dahZcYiGsVP6E/Oq6++2mWrGz58eFLHY11iM4xCJ5ZQh2UDIcQyUmXXUoCwxwQMvydBA8Igguj27dvdIrGpnj9ezMLy5cszEuAzyWSmwnQurCv5suTkKqCeMTJ37lxZvHixGzNYG4lZGzVqVFqKQ7IKSD4SBpSy26KRf3guvbt4g1OKHp+xQrbUNkR9P7B7Ozlz8u64oqE9LabcKH5Cf2qScMEwSpFYQg+WDVxFLSNVdi0FGmPAOYhvJKaDxA242yHgsz+V88eLWchUwM0kk1mmylkxpEZOJaA+E6sIrpfEAqFE4+bGXxSlLl26yIABA7KmgOQjYUApuy0a+WPR2m3y0NRqeeiDGlm2PjquqFPbcjllwu64on0H736GGEapYNNKRYi5UeSHeEKP+b7nZhFX2lmz12E14poIvLjZYcnDPS2V88fqt0wF3GTrHXT9XFof8pUa2ascouSSaAOXNMaPVwHK1CrC+VCkSZLARAbX4jP7U1WQUlFA8pEwwNYBSg57fyZmw7ad8viM3XFF05ZujPquvKyVHDGql1OKjhrdW9pWWFyRUZqYglRkmBtF/nzyLUuSFMQirl5BEEVJrS6rV692/w9jpj7Tvs5Ewcql9SGfqZFpS67DuCG5D2ta+RWgTK0iuAWBzmzrX92fTQUk15Mmtg5QYuz9GZu6hl3y4pw1zoXuhTmrpX5X9D0ycUAX5z536sT+0qNjZcbj1TAKHVOQigxzo8jvy9AsRbHHJQKuJlAgHXemi7gmKwiykeiF+CSsEEGWiFz3dSYKVi4V8Xwr/fo8w/JHv9Gn3LOskVdVVZWxVYRxgfUIyxFjEoWaz+kkBip0BcTWAUqMvT+jYaJg6tKNTil6bPoK2bSjPur7/l3aukVcUYz26t0p1PFqGIWOKUhFhrlRhPsyNHeLzND2W7JkidsIgkcIReAFLEi5EASHDh0apagVQoB6pgpWrqwP+VT6eZ7hIomgRiyZukyyNh6WrEyVEs4xZswYF7OGgoQSxlhhf6kpIPlWdosBe3/uZum67fLQtBqnGC1etz2qjTpWlsuJe/d1LnQHDO0uZWUWV2S0TOzJWWQU+ixmMb0Mzd0ieYIUSVALHS5uxHYghGLJYVxiTdqyZUtWrHh+QZDyLViwwALUiwz6jnHCmCBGiEQKZCZEWVIrYCZKCWOFjHWk4g9SGlKZICkGBcQs3PFpye9PrENPfrhCHpxa7bLReUEHOmxkL2cpOm5sX2nXxuKKDKNwnuxGScxiFtPL0NwtkiOWIokblFrocFlav369O5Z4EhImIOxy/IYNG7KmuCBM048E+XOdwYMH5zQbm5EZPLfIKEf8GP3GOOnVq5f7v65zlalSEktpSGeCxBSQ4qalvT/rdzXKy3PXyIPTquW52atlZ0Nj1Pdj+3WWs6ZUyWmT+kvvTm3zVk7DaBEKEkJRolSPuOGQQejII4+U7373u0mvmWQUxyxmsbwM8+luUUyufbEUSeI6vMkSyCqHxYjPWAOoF3VKt41jtZEKtrjScS6sVhp0z1/c+ihbS5kZLmboT1zesBgxPlC6+Yviq32XLaXEJkhaHi3h/ckzcEb1JudC9+j05bJ+W/Sztk/nSjljUpWLLRrdt3PeymkYhU7oT4Uf//jH8sgjj8jMmTPlxBNPdA8jmDdvnjz99NMyfvx4Oeqoo5yAc9ddd8k///lPeeWVV2TixIlhF6VkKeZZzFwqBolehvlytyg2175YiiT/97YfSpEqPkyCoIyyH9e7VNs4XhupYMt+JmRQ3PircSzEQlHWUp4ZLiV4lqnSTfxRrmb1LR6lZVLM78941GzcIQ9Pq3EudAvWbIv6rn2b1nLCuL5OKfrU8J7S2uKKDCMhoUtj/fv3dwIMi/MNGzYs6jsEniOOOELGjh0rN910k1OaDjroILn66qvliSeeCLsoRoGRD8Ug3sswX+4WxTZzHUuRpJ1QhCg76xDhKkX7UQeUJW1HrZ+3jakri3jGUpTjtZEKthp7RFYyFCPOiwWL7Gcs3JuLmeFisgQWKvma1W/J8ShGabCltl6e+milU4reWrg+6jsceQ7Zq6eLKzp+XF/pUGnPJcNIhdDvGBSfyy+/fA/lCHgJ8t3Pf/5zufDCC2XEiBHyta99TX7/+9+HXQyjACk0xSBIMOP/2RZ4i23mOpYiqX2WSLANauPFixfHVZTjtZEKsVgbOB7liKx5KCscj3KUi/FUbJbAQlb88jGrzzikbij3xECh4JNgxD9BYkqwUUg07GqUV+evlYem1sh/Z62U2vrouKJRfTq5uKLTJ1VJ3y4WV2QY6RL6G6+6ujrui5Tvli1b1vyZeAFiCIzSpxAVA69gFobAm4wwVWwz14lm+BMJttrG2jazZ892We84XyxFOV4bqcJGDBKxT2RBQ0HKdcB1oSn8yRAvrkv305a0r/e4ZO+DYlEmKCdKOko2YwgXTayhvI+85S1lJdgoHnAfnrl8s4sreuSD5bJ2a7TM1LNjpZw+qb9TjEi8kCgO3DCMxIT+hB83bpz84Q9/kC984Qt7rDWBSw3fcYzCeheFKkwY4VLoikGmAm+ywlQuXPvCFlQzneH3tg3lIi4JQVwXevWnX2dDaCUzHm5zGtOk9VCFDYGWDHZkzVO3vmwKrt52pWwI2NlW+MPqy1jjkzb0WvSYsGKjv1O5D4pJmdB7nXWR8HagjpSZ8nrrWIxKsFE6rNxUKw9/UOOsRXNXbYn6rrK8TI4bx3pFVXLoXj2lvHVZ3sppGKVI6G+tX/3qV83JGc4444zmJA28OB9++GE323vnnXe6fQgXd999tzveKH0KPcVqphauZIWpbMdc5EtQjSfIe9uGNM5kmcO1CcVGrT8aU6Rl5/lAP7Rv394JsYwVf/n5LdfJpmKk9aLMTPJQLvapIoECR/a1bCj8YfZlrPGpqdl1P14AKLCkbk/lPkg0/gvJupTsvV6IVm+jtNlW1yDPzCSuqEZeX7BWmhJ0NnPQsB4u2QKLuXZqW5GvYhpGyRP624kkDG+88YZcc8018uCDDzqhApgBPuaYY+Taa6+VKVOmNO/D1cZoGRR6itVMLVypCFPZjLnIx6x3IkHe2za4NNHv3PvEfvB/VZSDyq4udN7FPXOlAHqvxTpLKA4khVDLFQoT196+fXtWFP4w+zLW+PSma9f9gOJHXE6y90G88V9o1qVk7/VCt3obpcGuxoi8sWB3XNHTM1fK9p27or4f3quDnDVlgJwxuUqqurbLWzkNoyWRlTfT5MmT5dFHH3WCEAIQMBuJy4zRsinkFKuZWrgKRZjyC6pYYHCh0ti/MJRSvzWAdWviCfL+tmHjmcB6aHyvZUpGycylAui9FsoCShKKQ01NjfuMBQyLGAqcV7kIizAtGLHGJ66JKHi6n+c0SiBxD6ncB/7zkzyDcmKd4v9YDHFpKwRXNW8cG+8o6kw/Up5isnobxc2clZudUoQb3arN0XFF3Tu0kdMm9ndZ6CYM6GJxRYaRY7I6dcdLp1CFYcMI28JVKMKUV1BV5QjLByAIZzpzH2QN4F6PF48TlDGMMvjLkYySmUu3J++1sGShCNKW7ENZwgqOex372adrPoVlGQlT6Y41PjUxgXf/mDFjXB8xyZXsfeA9P4oHZUXJor9xRWTsjR49uiBc1agL9VaFl3oyfrlXvH2XC3fYQnE7NHLD6i218ugHy50L3awVm6O+a1NeJseO6eOUosNH9ZIKiysyjLyRlScxLx0WgCUBA//XVe4VXpB33HFHNi5tGBkJIalYuILOWwguhF5BVZUjLAKDBw927lSZztwHWXD0Pg8S5JPNGJaskplLS533WqDJI9RiRJ2oe48ePbJiGQlSLLG8UY5FixallKAinrCf6bjVewELEW2BQoRCyTkZeyhMtBN10IVh8+2qxjijvtRVx1GsmMFsTPQVmtuht1ymtIXLjp27XEpulKJX562RRl9c0X5DujkXupPG95Mu7SyuyDAKgdCfws8884ycffbZ7sXNixGhwY+loDRy9RLOlhAS77z5tpp6BV51q0M5Yn8YM/dBFhxm4bFWIRT7FZtkM4b5yx5rbOTSUue9FvVAKWRf9+7dXZkQ+CknbZCOZSTefRCkWHIMx06bNs39jmO4Ju3IGj7+cR10/qDxmYkSoPcCShDKOOXkfCiRvANoF5Q6FCTqUiiuavlOwFCIGfL8SVJ0IeZYSVKM2DQ2RuStReucCx2LuW6ta4j6fnCP9s5SdNbkATKoR3trSsMoMEJ/2n3nO99xD3cSNIwfPz7s0xslQC5nTrMlhBSicBNL4MW1CctRWNaWIAsOFqGhQ4c2xxF5hf2wBdFcJvvwXgvrDRne1Cqi9aZO6VizEt0HfsVSY59QQvgtyijXVkuWf/zFOz/Em6BIZQKD41COODdlYrzxV90PaSvGHwI2cT58LgR3snzHDOZbQQtCxxz9gkWYVPZ8ZswFucQaezJ/9RZnKWK9opqNu5NUKViHTp3YT86cPECmDOpqk8WGUcCE/qTjhXzTTTeZcmQUhHKRLSGkUISbRIJsNqwtsc5J3wUJT6kIoskqz+lYPJIV+mNZXfiL0O+tN0qhd0yn0r6J7gPvGENYRUHSNOMoTeyjPVE+KLMen+j8XneyoDZOdQJDY69QivieuuMSSPn4HeXjHEEWrlT6xn8M7aRucukoXPmOGcy3ghaEjiGsgCTWwHUTSyCfC2kCqNBYt7VOHpu+XB6cViMzqnfHeyoVrVvJUaN7O6XoyNG9pLK8dd7KaRhGHhWkESNGuBe5YRSCcpEtIaQQhJtkBNlsWFtSPWcqgmg8oT7IOhVmWyVzXFC9gbibVMuW6D7wjjGSQKB0cF7aBoGV41A+UERQmtQyk+j8ulBvrDbGGkQKduqZzASGJunAckTdiT/C3ZLzk6UQd8RECmmivvEfw37aBOGd79KxQud72YF8K2hB6JjjHa5WQHXNpV9t/adPqK3fJc/PXi0PTq2Wlz9eIw2+wKLJg7q6uKJTxveTbh0sLbxhFBuhvwl++tOfyuWXXy6f+9znXBC2YeRTuciWEFIIwk0qC9OGPeubyjlTEUSDhHoEdhISEIeTrktmsm2V6LhY9U6nfRPdB/74JwRWjeXh/7QHfzkeQTaZZBaUn3OSeht3N87hb2NVoFA+NCV7vAkMrsm5KBe/xeqAhQuXRNolUdsk0zf+Y7CkUWaNvUrXCp3PZQfyraAFoWNuwYIFTiFC+Wafxr/l07pVKHFF7y3Z4JSiJz5cIVtqo+OKBnZvJ2dOqpIzpwyQoT075K2chmFkTuhP4ueff969LEkTe+yxx8rAgQPdi9YLgs8tt9wS9qWNIiGXykW2hJBCEG5SscR53ZO4HxF8UknhnCnJCqJBQj1lR2DHEpGuS2aybZVL62ai+yAo/gkrEdYZlAMgxmfQoEEyfPjwPVwc/efnOxQqFBkUJBJMcG6UDvbTxv3793fPbyxTWKzIkMd4iSccc17WvgN+w7iivCguydzTybS5/xjKrPedV5FmKxRloxjXhdMxR3uiMDMmaF+sdfm2buWTRWu3yUNTq50LXfWG6LiiTm3L5ZQJ/Zy1aN/Bu8enYRjFT+hvj1tvvbX5/48//njgMaYgtWxyrVwkI4Skk1Uv38JNspY4f2Yq3GdUqMTyUAipheMpDSgFuG+lmykulbbis7qZacY473FhZl9M5j7QMeaNf0JhQVhFCSEGKlbsl//8tOucOXPcGEAhQglCUULZ4NwoXrQ1ChLXw80OJYr/JxKO+f1+++2XVtsk0zf+Y/Qa/EXZJ16Gca39k83EL6UO7aULOLfkdN8btu2Ux2fsjiuatnRj1HflZa3kiFG9nFJEfFHbCosrMoxSI/SnHbOHhlFM62wU6nokQfgtQd402pQVQRXBFxckbVevexIKhgbQ467FOXIZfJ2o74OUBmav6Z9MXDKTtVpyXa5H++n1q6qq3P5Uxkmi9N3pKOPpTCp4lXiUIY0P1VluXaNO45gYGyhKtDPjQwXlbE4YJNM3QcfQLzp+cQejTrQPVrVCyypZjOR7Aigf1DXskhfnrHEudC/OXS31u6LjiiYM6CJnTa6SUyf2lx4dK/NWTsMwsk9hSX9GyVOIykihp+yO13YIjrhXYRHQDGcc421Xr3sSaXuJJ0AgRhHACpGr7HvpZqjjdwj2mbhkJqtgUB6EbtzD1PWMz+yHZMZJovTa6abezlRgZfJKrUe6xg3jADc6QMFg/TqUJF30OBf3ZbKWNP8x3ix2mo4a5ahQUma3tImmYoV7YOrSjfLQtGp5bPoK2bSjPur7/l3ayplTqlwWur16d8xbOQ3DyC32NDVySiEqI4WSsjudtmMfGdQ0wxvB8Xz2tqvXPQnlCEEZoQDBP8wEGYkEtnT7PiyXzEQKBuVHyUTYxnqii5x6x0Iy4yRePSHoOwR7VQLDnDjw9gnKjxfGAOMBhQklic8ozCwqjCWSscRvCyVGLegY/Ux7ES+TjLtpKSgViSYbSqWe2WTZ+u3y0LQaZy1avG571HcdK8vlxL37Ohe6A4Z2l7IyiysyjJZGxk9MXrCa4lXTvSYKUuR7HuBGy6MQlZFCSNmdSdvhUodwiECEYK/r42i7Eniv7klYDnRxU+7ZoOxn6a5Rk8g6lEnfh+3uE7SmzuLFi10iBNqStiEWhzJ6x0Iy4yRRPYO+I9aHOJqwJg6oH79fuHChOy/txzjh/LjQKVgR1ZpI9jmS6vBXF3/NloU3bAE+GTe9QrRep0s8JZw6l0o9wwbr0JMfrnBK0buLN0R917qslRw6oqdTio4d00fatbG4IsNoyWT8tPzxj3/sXvT64NXPhlEsykghpOyOJTzqhAMCrAq6/rTNWD2IL4kl2PstMKlksUtWqFSBWo9BEeOzCmx8j2WGWBHqgXUmX30fVCctM+XVuC2SFDAOWK6A9vfWDWtMrHGSaIwHfUcfhzVxoPVjQ/FCiGZMoAxr0gvid2pqapoVZq5LXVCmURSTcSNMV8HJhqKSjJWxEK3XfpKNXeNeou+Cxksx1DOX1O9qlJfnrnHWomdnr5KdDdFx0uP6d5YzJ1fJaZP6S+9ObfNWTsMwSkxBuvbaa+N+NgqDQnG5KDRlpFBSdsfKOIdwgzKDC5YmLEDJUAEd4TaWYE9skjdldDrCUbLCFtYJ9qPQUQeuhwKGRcJrvaLsKHSUPxnrVTYIqpOmpx42bJgTNrGysE/rSJ/oAqWUm/1YWoLGSaIxHvQd10zGRSyV+tEXqhShlGJdpMyUF6Eaxc9fF8ZOIkUtUwUnWwJ8ojFeiNZrL6nErnEfseGWqUkpdLzkup6F8m7xwjNzRvUmpxQ9On25rN8WXfc+nSvljMlVctbkATKqb6e8ldMwjMIl9KcYM9heFw4j/xSSa0khKSP+chXC7KpXeETAxQKAkINwSxkRirAGYAWg7VBM6FvijryCvQrdCLyZtHGywhYKD2Wj3JQNgVwTR6DUqTCMQMfYoz66Tk6u+z6oTrQz7a0KCmWibMTh8J03rTSgUMQaL4nGeNB3oIpCphMHWj/GAuOJ+5+Nz7S7d/z42z8ZC2+mCk68MZWqsJ3K8YVovU43do37i3uLe0nd23W8aJrzXNSzkN4tULNxhzzcFFe0YE10zF37Nq3lhHG744oOGt7DudQZhmHEIvQnGEG+U6ZMkUMPPdRthxxyiBPejPxRaC4XhaKMFCJBGecQIrFuIOygiCDcsjgoICR5hSHalgVVUU4WLFiQsdCSrFBJkD/KBGVFeMONj40xhxKnwjCz3Qh0PBPyNQaC6sRzC2sK7eVVUGivIMsY1pd0x3is78KaOFC3SsYP4wCllBl19rNu0qhRo2KeNxkLb6YWilhjijZORdhOVTgvROt1urFrPAN4FqDwci95x0su6xnr3aLPolxMgm2prZenPlwpD06rlrcWro/6Dm//g4cTV1Qlx4/rKx0qW3YMlmEYyRP60+KnP/2pvPbaa3LnnXfK//3f/7mH+ejRo+Wwww5rVppwuzFyR6G7lrQUkpnt9gqPKBgI4/SZWjf8ykmQMKRudygsmSrEiYQtrRPuYShJCEpcV+vIPnUVTGc2OxvuO0F1wpqF0qNpo/VaLKwaZBnzZ4QrpIkDXVQWxYhxwxhgLKEEssVrv2QsvJlaYmKNKc0YGCvxgH8cpDrxU6jW63Rj1+hjxq2/rrmsZ9C7hdjDRYsWuWdXtqxKDbsa5dX5a+XBqTXy35krpc4XVzSqTyeXmvuMSVXSt0vbonMRNAwj/4T+FPj+97/vNmYsP/zwQ3n11VedwvTYY4/J7bff7o5h9psHqJEbCt21pCWQ7Gy3V3hEscAtinsJK0xQzE6QMOR1u8tUIY4nbPnjpTQ2gmtqWVloFEEdtz9c1RDQ1bUurDZLt05Ys9SFUWe8/cKm1zKGEkiZEPyop1qUsiFwBZ0Dkjmv1oN2o71RIKifxlllqqhlaqGINaZixT/pePaPA1XE/cK5N1lI2GtJhUGs8ZFO7FqsNs9VPYPeLdSPewVLdpgeCzwHZy7f7JQi4orWbq2L+r5nx0o5fVJ/Zy0a2293iv5icxE0DKNwyNoTgIfThAkTnPWIv3vvvbfce++98vHHH8vSpUuzdVkjgEJ3LSnFmT1/2YnDSWa22y88erPYxWoDvzDkd7vLVCGOJWz5Z/D98UWaOhvlCcFckwZgqclnML9CebEI0c6aIMEvGBFrxL1CHTgeYZ3+QAhHefIfH4bAFXQOshRqmyRzXspNm6lyFOakSBgWiqAxFWsiB2sd9fePA3Ut0+PpS/pI7710hd1sPncSjY9UY9fy/TwMerdgacWNlj4Jw2Nh5aZaefiDGnloao3MXbUl6rvK8jLnOoe16NC9ekp567Kidj83DKNwCP3pykvq9ddfd5Yjtvfee8+5pIwbN06OPvpoue6665ybnZE7UhVoCkExKeaZvaCyoxzESssb9uxvrhRiv3uNP74IRU1n87Fk8JfvaZtYSQLinT8VQSusRWv5Hcoe8Vzq1sQ+LYv/+DAELu85aDesXFjjGUOk4aYvE7mfBY0B9qFoM0GV6n0d1J5hC5Cxxi2WIsaRfxygoGqMGJtaL2kTzeyWattn+7mTaHykE7tWaO8WxhhtmMkEzba6Bnlm5kpnLXp9wVqJRKK/P3BYd5dsgcVcO7WtSLv85n5uGEYsQpc0NSHDvvvu6xSh733vey5RAy8DI38k+3KNNXuNoJbMujlhUcwze0Fl37Bhg3MRyYWbY65iEPwz/mqNYbzofm+CA/4yw8+GcJtI+EzXNTSRkMv3CNz0ExndNAFGkPKlbYnlCAVXM8BRl6DjwxC49Bzcc/yWstOmXJNrc85E7meU2W+JxEqm6cpTEfxzNVkRa9zGysqmC9vq8SSloIwoR+m2fbafO6UokPvfLYwX7vFUJ2h2NUbkjQW744qe/mil7KjfFfX98F4dnFKEG92AbuFkyjX3c8MwYhG6lIvgg6CkD0c2fN9NQSoO/AICfTl79mwnjOjLJBeWnGIWJILKjsBAPBHW1Fy4OeZittk744/CoWs2YfFg3KBQsKnbDc8BLEjMMGMV4HgEbwRaFi71WykQSmmjVAWteJm1uPbMmTNdGVEughbWDWpLrEi6UG+shBlhCVx6PGWkfSkzbUS7UDfGEeWI536mAr2OAax5/DYdwT+XkxVB4zaeRdR7PPszXUsq28+dliCQpzpBM2flZuc+hxvdqs3RcUXdO7SR0ybujisaX9Ul9EXoY1laeRalY2ktBgrBQ8QwioHQ7wpmymfMmNHsYvfjH//YvZwRQrAkaepvLExG4eEXEJhdRzBEKPO79mRTAM+FIBHWi8J/HjKGBWWcIsVyrlLf5loQ4h5H+eP/KENqNQPagzGkIPBzPO2GArVw4UJneSZeyWulYLwRr5SqJSxWZi3c5JYtW+YUNW9mQI7lWtQllvKVrNui/zhdWBZljDonU349B/GatBuWJOqC8sk5KD/HxHM/8wr0tLMqSMSHcZ5UBP9cTlbEuieTEbjDcC3N9nOnWONBw56gWb2lVh79YLmzFs1a8cmzAdqUl8mxY/rImZOr5PBRvaQixbiiVMvpHVs8q+ifMJZIKESK2XXdMHJN6HcEL9CJEye67etf/7rbx8Pmueeek5tvvlkefvhhdww3qlF4BAkIkInbSiEKEmG9KILOozEgOvOuZdcYg1IUhKg7gjvKkXfxVQQPlGusDyhMui4Px6F8q7I0d+5c1/6ZWinoD5QKFBIUBxQC/s9+tRpxDV3zCIGI/5Ntz+uCl66QDtQdxY+6qRWNMZLsGNNr6TMSJYh6YC1CuSEOSTMBJloUVMdndXW1s64kYzFLV2nIdMIh0T2ZaByE4Vqa7edOvlON59N6sGPnLvnvrN1xRa/OWyONvrii/YZ0cy50J43vJ13apR9XlCresZWJpbUYKGbXdcPINVl7MvIyf+ONN5wV6ZVXXpF33nnHCQo8jCZPnhzKNbi5b7rpJnn77bfd+RHA7rrrLvnSl760x7G4iV155ZUu5TgvhpNPPtmt04SwYMQWEBBimcFmtl1jaHLhEpJtQSKVF0U8oSLoPOwbPny4s4qUirUoESgaBMkjiCNEM14YN9Sd2BCUJ/ahLKGksE/TZKPQqDtLJlYKFbDVlY/nARsCrmbWopyatpvyML5R/lV5zURI9/+WjbryG8ZCKsII1yIDqCYhYEzxf1In8/tkBXodn/yG3/OZdNocwxhNRvBPRmkIY8IhDOEtU9fSXCgw+Uq2kA/rQWNjRN5atM650D310UrZWhc9MTqkR3unFGEtGtg9nLiiluranQylXj/DCJPQn4r/8z//4xSiDz74wD2QEYgOOOAAl6wB97qDDjrI7QsDXqjXX3+9W1cJi9VLL70UeBxCGwvVIrDdcMMN7sX7q1/9ymWGQrEqJf/vbLkc+K0huXAJyaYgkeyLgjGMdYN1u1AAEK5xlRs1alSzu1zQeRC8cykE5XNmmGszRmgfrBSAQjJy5EhnRaHtsBrRPsSy8VezjdGeTJygSKjLG8dg7eF8KE+x1hvyo2OUc6JccA5NrKDxdFwHODcbMZN8r+OZ3yNEUhZV9LxCeirKMs8dron1Jx1hxHsvqotekDUqnkCv45N7luvz7EWBxAqVrGCcjNKQSLlJZnwWgiuf1rcUZ9NzaT2Yv3qLsxQ98sFyqdm4+55TuravkFMn9HepuScP7Bp6XFEmlHqMWKnXz8gPDSUa1xZ6Df7617/KwQcfLOeee65TiKZMmZK1hsLNBDcaHu6kE99vv/0Cj0MpwqL1/vvvO2UK9t9/fzn22GPl7rvvlksuuSQr5StW/AICwlWpWUOSfVEgQGB9RDBFWFbLBJ9JLMC+fL5wNL4EJQTlRN3HculXzoORjTGDMoAyhLWRDWsFf9WljjHEXzaNcWM8aVwMSgvWJNoX+J7zYXWmXvHwC9i6WCrX1ngmzkvb8D3WGKwonFutR8RDoVhxLfpSXQY5b6IZ+KC05/QN50EITWds6L3IeTg3yp/fGhVvssI/znVBUp6dQWMj1osukdLgrTt9xnlQxFCQlyxZ4hJJ6FpescZnroS3lhqHkW0FdN3WOnls+nJ5cFqNzKjePVGiVLRuJUeN7i1nTh4gR47uJZXlrQtS2Cr1GLFSr5+RexpK+Hkaeul5KeYKhIVkZr7+85//yCmnnNKsHMExxxzjZrjvv/9+U5ASUIozqsm+KDQjm7qL8eLmdyhNCHCx4o1y8cLRBxMxft4MTFj9culX7he8ND01+1Ao2VAkEZCJQdL1fdjUSsN3w4YNc8onih4KE+eirdUqxQRIvAduPAGb32H145r0FedHmaOvvBYg+pry8Ruuzz7aUfs+3gy8//raFigMmY4NLEi0DeejrTg/kz7x0nyrMpSsQJRMevRYgqvWnfaj/tw39FtNTY1ra9oA6xXPYHUbDFpzKhfCWyHHYWRTOciGAlpbv0uen71aHppWLS/NXSMNvsCiKYO6yplTBsgp4/tJtw5tCl7YyneMWLYp9foZuWdtAT9PMyWrd8WsWbPc7CEMHjxYxo4dK7mGFzQv66CseViRnnzyyZyXySieF4W6fyDkqSuYCr48EHg4cJ58WNj0wUR5mCxgZl4zDqrSkgtiCV64ygFWIVVSUJBQiLDeUF79DkGYDeEfOIbjOR/1ZOJFrVSxSCRgcz6SMbAFQXtxDC53tCNl1fWIOAfWsHgz8EHXx9WPMabWk3TGhloJUTg4vya94LyUE1c+tVj5XQJTEYjivej4TTKKGMfwvOV+QVHnr/YnShLXoJzcS7qIMOfiGvxeLWS4PjJ+wriX/EoH93AhxmHEWoMu0/ETtgJKn767eINTih6fsUK21EbHFQ3o1q45rmhozw5FJ2yV4oRgS6qfkVt2lnBcW1akuEceeUS+/e1vu7S9XojdIDHCaaedJrmClzDgUuKHfQSLa2xJELzs/VYxXmJGy3hRIDwgIGMFYZxw0/MA0AU7eRAgvOBul2soC4ImgifWBLXUIEAjhObKzS+W4IVLGwIe+1A22BB6KR+ubbSfX2jn/9QBIZZ9tDnHq3teNmdH1f2L4xHQ1VVQ07MnmoHP1uwsQiP9zDikPehnXkRYwLTddV0pr0tgqgJRvBddIsFV6045KSPHaWIO+l3dKTkXih7HqeLCb7mHUKjYp8o0i8CGoRz5lQ7OyfjyJhQphDgMfxsz/ubMmeP6li1Ta0qm43PR2m3y0NRqeeiDGlm2PjquqFPbcjllQj+nGO07ePf4SYdSFrYMoxRpU8JxbaErSFhkPv3pTzuLEbE/Y8aMcftxSbr99tvlrLPOkscff1xOOOEEyQUalB2kAGlMA8fEUpBuu+02ue6667JcSqNQQfjDCoCyj4sTAjPWD4TVfD8IECgRNlHyUZDUOoOAhVAfa2Y4bDeeeIIX+7Fy6CSErgvEgzRIaOd3WHBoa10UVV3ykmnnTGZHvYoe9UBJ0vTsyc7AZ2N2VuOfUDgZc/Qz/U47MgGkih1jE6WE8ZnOmIz3oktGcNW6Uzb6m8+qtGuWQxQhTcjBeNE4LY0lZdIqTKtBkNKBJVAnOwClkvdUvuMw/G2MQklb0gZhrUGX6vjcsG2nPD5jd1zRtKUbo89V1kqOGNVLTp/YTyb0LJNWjSi3O10fp/s8KWVhqxAp1eB6I3f0LOG4ttDvhJ/85CcyYcIEl94bAUPBasS6SCwSi8KRKwXJ6+bjRwPB9ZggLrvsMjnnnHOi9jEjecYZZ4Re1mKnmB62yZZVY1dw+/FmEkMQzfeDAIGY8qubGkIgICyjUMQKws+Gj38swYv2GTFiRNT14rWZdxkA2ljTzOu6P9kk0Qx7vvz3VUBE2dBFeBGiVRmmDJrtD+WJY9JpK33RoaxgOef8KKvq/paM4Oo9B9+hGNGH6i6JVUjdJnVtNeqg7cln/uKazX2mLqyJEnSkonSgJGnqd7USxrpfcolfOaBsoPFsubKm1DXskhfnrJEHp1bLi3NXS/2u6LiiiQO6OPe5Uyf2ly5tW7vnyeIF4TxPSlnYKjTyHe9llAblJRzXFnoNZsyY4SxHXuVIYR9rFF199dWSK9S1Tl3tvLCP2dZY1iPAjYXNKJ2Hbapl9Qr/CHiFogQi7CE4ImhybyHQoiypUFoIPv7pPDypEwkZ8tHOiWbYk5mBD3uiIJbQSL+jGNHfWNroS/qdZBfpumBhpcJ6h3DOuVBSsJ6yn2smEly9/c1vOI/GdnEsbUfbUFZVBLSdVNn/6KOPnOWEcjAhwcbEWjpKUiylg7ajjJpQJNb9kkv8/azZH3OxBh3nn7p0o4sremz6Ctm0oz7q+6qu7eSMyf1dFrq9ends3k/fhPk8KWVhq9AohHgvozQoL9G4ttCfOrzEcPmJBd+lOxuYDsSGMAtKGnA/rIE0adIkKUYi+PU3WQwKgWJ62GZS1kJ6EKhrlS7ArKm12RdLiMqHj386bVZI7ZzviYIgoZH/E9+F8IwyoXFTmuwiXSgr10AoVUuR3hveNZlw6WRiiXvJL8Am6rsghY/nNIrevHnzXH2w6jO5hUJDoh3adO+99y4qpSPTfta+zWaGzKXrtstD02qcYrR43fao7zpWlstJ4/s6peiAod2lrKxVTp4nxXrvFxsW72UYOVaQjjrqKLnlllucCx2Lwnp5++235be//a0cd9xxkkuIiWJ9pmXLljkLADz//PPy8ccfy5VXXinFSPWVV0rtrFnSdvQYaTuGbbT7W96/f14W3iumh20xlTWeZQJBilgj4vs0FTYz4szcxxKizMe/OCcKvEKjVwlDOUbQx4LEWNCECdm4N9QKxLVRztSNLlUFMJbCp8oZliOUIxQmlBmug1KWjmUuH0pHJviVA/4fdobMTdvr5YkPVziliGx0XtCBDhvZy7nQHTe2r7RrE3u9okJ8nhSTm3e+KbS+M4xCI/Qnxy9/+UunGOESQRpt4jdg7ty5zmKDu9qNN94Y2vVuvfVW92Il8BYee+wxl50IvvGNbziBEZe+Bx54QI488ki54oor3IPgpptukvHjx8uFF14oxUjdrNnSsHyFbGV74YXm/WVdukjb0aOblabKMWOkctgwaZWjOIlieNgWU1njWSYQ7MgGh/BHzAgCrboxxRIKzMc/u32EMI+AhtUaty0sIfQNkzPa/skIbCg+TODwW5QtlF6sLPw2SAkj9kgXdM1EqMRlj3PEujfCUgCDrATqfofbFpYjlCPKw7WxVqVrmcuF0pEt4llTUlEG6nc1ystz18iD06rludmrZWdDtEvhmH6d5NgRXeTIYR2ld6emhB8raxKet5CeJ8Xk5l0IFFLfGUYh0iqiC1WECC/1n//85/LUU09FrYN00kknyVVXXRVqTA+Cg17Dz6JFi9z3MHPmTJd6/LXXXnMPgpNPPll+/etfp+WOwrlw98BXfty4cZJrIo2Nsu7Pf5Ha2bOldvYsqV+yNO7xrRAwRo5sVpic1WnUSCkLiBMLW4AvxJdTMZVVQWhkkgHBVAVXhGImIFK1TGRrljXReUtxdlfrpAk8dM0m6kd8I4oOwj4TNSgUyYwzfvPKK6+4Mcp5eURzPp5lEydOdIoX33EulGK+ZywzFnQx7GTb2n8vBKXc9pZ56dKlzmKJxUqPI3kEWeC8C3GnC3XnGY1bnZYdxZBEH8RCJTv+S3GspfoMY1zMqN7kki08NmOFrN8WbSHv07lSzphcJadP6CtlW3YLyTpe1XqIu26iMVsobR3mM7KlUCh9ZxhhEaZ8npU7AQXoN7/5jduyjX+tpVjQUM8884yUAq3KyqTnVy9p/rxr61apmztXamfNlto5KE2zpW7efJH63YG2EdbL+egjt31yklbSZvBgaTt2zCdK09gxUt6jR1plKqbg2mIqazbcArPh459o9rZYZ3fjCRDeOuEWhusWVg/aFhc0lAkUCKxJKDcoEslYWzgnkz4oIAh7/A7BFcUEi4quy+S18vCZ7/SatK2WW1Orc03/4qtBFiESJVBm6uKvMy5qHKNZ7lDWUJb4fxhQTrwPVDmkvIwRrpfs+C/WsZYK8Sx5DZWd5ZEPlst/plbLwjXbon7Xvk1rOWFcX7de0UHDe0jrsla7FYumc9G2KPgoV7zHGUuJxmyhxAwVq+t0PimUvjOMQqQ03hYtnNYdO0r7ffZxm4JSVLdwodTOnuOsTLjk1c6ZI41btzYdEJGdixe7TZ58qvl35b16SeXYJoWpyU2vYuBAp5SV0sM2VlkLdUYtkVtgvsudyPWqmJJ4JCtoe+uEhYjvmLHGckSWNCzYCJgoR/xNVmBDMdBjKAMg8OkCuiS6oX85hvOp1QfBFhc/FBw22pVyMYmE4sSxtL23DkFCJQkYUI6CLEJqseKvbvo5LFCS/AkZUnGLLaSxlq370t9vZZXt5YV5K+Xm6XNk2vJopYiuOWSvni6u6PhxfaVDZXnMczG2NIEFY0qz/GWiZOTq2VSMrtOGYRQuGT+lLrroopR/wwP9jjvuyPTSRrw2JsMZsUijR4ucuXvNJl569dXVTa55s6XOKU+zpWHVqubfNaxZIw0vr5FtL7/SvA9XvEpPXBN/2+y1l5SV2IunkGee4/mLF0K5E83epjK7G7ZAle75Egna3jppvBHWHv7Pb1CUqCv7khHYtJwoKICyxcb5EFr5nSo1ag1CYcIdTTO/MeuPksRn/q8WIV3rh3J565CqUInQjPLHubVclIH9hRIvUSiWhGzel26NqfIKeW3BBnlzZaO8tWy71Luwok+Uo1F9OslZU6rk9ElV0rdL7Myx3jGgVkHGC0p9pkpGLp9NFlNjGEaYZPyEeuGFF1KePcxHljVjd7u3GTjQbZ09mQQb1q9vUphQnOY4S9PORYtYaMd937htm+x4/323NVNRIZXDh+9WwnDTa1KgWnfqVLBNnUhQLqSZ51TcAsNeiyQdEgnayQriYQtUqZ7PO0Zwk8O1LZag7a8TiQQ4HuWE3+AKB8lkTPOWE4WDc2nmNoRV+pY03gitfKeucvyGWX+sRyhAmtEOiCVRJYp9ulirtw6pCpWaWl7PRd3jpZUPA+0T6k1yBdrB7ypYiJaEZJ4nqSrv9O/M5ZvlP++vlYen1sqG2mjFtGfHNnLGpCo5c0qVjO3XOal3rXcMMH7pT1XsNQYp3cD9XD5Ti9F12jCMwqU8VzFARuFS3r27dDz4YLcpjdu3S93HHztlycU2oUB9/LFE6up2H1BfL3Vz5rht08MPN/+uYsAApyhVNlmaXOrxpmDyfJKMoFwoM8+pugUWQrkTCdrJCuJhC1SpnM8/RthQLhDIcTnzC9reOqmCQp28sT6QTMY0bzlJSsA1NVGBWpToW03nzXn0NwixlI/yE4eka/3wF2WN33kD1711SFWozPUsfdB9S9lYrqFQyhiLRPdlKsr7yk218vAHNS7hwsermtykm6gsbyWHD+8q5x4wVA4f1UfKW6cWD+YfAyjhjB0sSZkqGbl+NhWTm7dhGIWNTa0YgZS1by/tJk1ymxJpaHAxS7td9D6JbdrVtAYP4MLHtuXZZ5v3te7WzaM0jXUWJxJEtGodf42NMElGUC6UmedU8ZYbAZp64VaFsIwQlosZ1ESCdrKCeNgCVSrn848RLDDMqCO0oij5Be1k65SMwOYvJ+ekDzk/5aFsGjhPGbzxQ+zjO8qJQoTCRFY5FDZc9LAwUg/OEaQspCJUZjpLn6rFRPtELWeMcZQK3PxQJGOdm+/pa7+Qn8tYvUTPk0TPpG11DfLMzJXy4NQaeX0B/R99/oOG9XCWohP37iud2lYUpGJRrM9UwzAMU5CMpGEtpcq99nJbl1NPdfsQzBoQwFRharI41dfUNP9u14YNsu2NN9zWfK527aTtyJGfKE2kIB85UsraxvaVz4RkBOVMZp7zmSRBy03sCevtIAwjTGLVUIE2V0pSPCErGSEsbIEqlfP5xwhCNsczBognCurXVAXLWOPEW05dOwkFCevR6NGjZcCAATHrhiuULlfAb4cNG+ZSG2s5WXTVmxWOpBGZjId0E5yk4z7JcboYrir8fF64cGGzohjr3P701EHH4EaJQkIMVTL3bSr3eaLnSdAzacXKlfL6gnXy+ssr5amPVsqO+mgXuuG9OrgMdKTnruraTgod6kob42nC8wnlPd5C1oZhGIVCxlITQZ3pxCBpdiajuHHuO/36ua3TUUc278eqVDtn7m6lqSkZRN2CBUR5u+8jO3bIjunT3dYMgejDhu5WmDyxTeXdumVczmQE5XRnx/OdJEHLTTmwelB+rAoIxIUSQ5UsYbtHpXK+oDGi6bHDaL9440TLiVvdvHnzmpVcXO28Sq5XQOfZq652KMOUlfXm/EoBwilCKr9BmcqG0pzMPZCO+yTnwQrGuVDuqDPKDMoS59PfJXPuIAvhnDlzXDuzJROflsp9nuh54h1vaxvayH/nbpTXqhtkY12023r3Dm3ktIn9XcKF8VVd8u6unA663GIWll0MjXxnAjUMo7DI+O7/8Y9/XJQPbCO7tO7SRTocsL/blEbSD8+bH6U01c6dK5Ht25sOaJSd8xe4bfNjjzX/rrxfv93xTM1K0xipqOqf0rhLVlBOx9WkEJI7UG7iThAidQHRQouhykegdSrnS2aMZCJEcU4EbKB/sBAhpKu7mC56jXLE9yg8fM/MO+XXpAxeAZ191C+WBSRXYzPoOpSb9tL1lDR9eSruk9QHV0EsahpLxRpN/N/7u2QsxP5jcL/DJZF2oJ+DypxozahM1giKVHaS19ZWyjNzNsjSLbsT4ihtysvk2DF9nFJ02MheUpFiXFGhQJuxYYHVSQc+E5dXSJM2+Z7kMgyj8Mj4zr/22mvDKYlR8pSRfWvvcW5TIihFS5Y0u+a5pBCzZ8uutWubj2lYsUK2sr3wwifn6tKlOY25LnZbOWyYcwPMdYajQkiSkI57WrZnTNM9f9jxEMmeL9EYyUSI4re4hfFblBmsIgjaxNaouxjnQmnCmsF1dT0jhHiuRyzRggULmt3/sKaosOmPx8n12PRfB0WdtZc0k56OQ+8Ct1iBNFtgrPHBZ5JScKzWm7+qEKYy9v3HUDbg/7HKnGjNqFTbcsfOXfLfWbvjil6dt0YafQaV/QZ3k7P2GSAnje8nXdplFldUCBTKs7EYJrkMwygsbGrEyCssQFs5dKjbOp94YtR6TM7C1Kw0zZL6JUubv2/ctEm2v/2225rP1aaNi2Ny8UzO4jRG2o4a6dZxKsRAZFUgmFkn1iRR+uIw3cmyPWNarDOyOka0b5YvX94svGciRPFbzTDHuVGM9K+6i9FOWDVItMH/UZRUWEcZYuFZrqfJCrBy+C0p+QqS919HY6iwHKh1RlNIU14sNeyjPTiWNvCPD+0DXXyX37MFjetkxr7/GM32pwujBpU5kzWjlMbGiLy1aJ1Tip7+aKVsrYt2Lx/So72LK2Ih14Hdd6doLxWyPf7CmuQpFkXOMIzckRVJhZfdb37zG3niiSecywjgG3/KKafIt771LfdSMoy4A7NXL2mLEDpypDTuPFE6tmkj3du1k4b58z9JCDF7jtTNmyeR+nr3mwgB3R995LZmWPtp8GBPMojdi92WhxgknE7cjCoQCIqadQ7Bl98RVJ+OIpGKlSzbM6bFPCMbS7mjf9IVojiGfsBdDEuQWkGwiKh1guvwPddCKVCribqUYUniGJQMBHrijjR5RDJjk7HGebkGdcw0w2GseCjveCYWTtuKSQBNgU4bUBbGg6ZQ944Pfx9QTo0HC5pESGbs+4+hzLRpvDJnsmbU/NVbnFL08LQaWb6pNuo7rEOnTuznFKPJA7uWrJt6NlOuhzkJY9n2DMPIuoLEjOuhhx7qZjvJvnRw09o6c+fOde5499xzj7z66qtOCDSMWMTMSjVxorTfZ5/m41CK6hYtalqrqSm2ac4caWxynyE3LqnJ2bY89fQnA79Xr6gMeihOrfr1k3Xr16flEhYknAGCYND5VChTQQ1FAiEJoTETRSKeBcRbl2zPmBbzjGws5Q5XtnRnw72KDRZD+hlLEQqSLrRKH+lzUdN1oxxNnjzZWTcoD8doNjfOgXIRT9jUscl1cOXjtyRqwFWP8oe5AK83HorroMBxLW9bodwwPvkN36sVzD8+gvqA7/T3seqa6J7xH8P/dZ2qWGXW/k1GCVu3tU4enb5cHppWIzOqP1n+ACpat5KjRveWMycPkCNH95LK8tYln2Agm67NYU7CFMraWYZhFA6hP0G///3vO6Hw8ccfl5NOOinqu6eeekrOOeccueqqq+Svf/1r2Jc2ipSgl3uyLz/c6tqOGuU2OfMMtw8hlDTjtbM+STuOu17DqlWfXHPNGrdte+XVTwrSrp3srKqSuqr+Ehk8WDZMmiTDjzhC2rRP7PbiF7y8AiRuQRr4TQpmXryqQFBf/Q4Bjfrqd+m2JfcfExQI2ZwPQds/s5rtGdNimpH1j79YyQQ0o1wsISqekOpNxc53jFH6hU3PEU+YVAULlzwUK9oTdzzGUyJhk+/5HcdTJ+2PsBfg9cZDqXUqVlslGh+5UrC9922iMvuPV2rrd8nzs1fLQ9Oq5aW5a6TBF1g0ZVBX5z53yoT+0q1D+OO/0N1Zs+XaHOYYyaYiZxhGcRL63f/00087Nzq/cgQnnniifPOb35Q///nPYV/WKFKy4c7E8W0GDHCbHHfcJ9dav353unEX07Q7GcTORYtc9jwHi4HOn+82xz33yoKmtZ+8acexNrXu1CkpAZIXLMLw+vXr3WeUFl7E1Ie6ojxxDMoRQiz1U4tCum2JdUAFPF7ynNcvDGd7xrRYZmSDxp8/mYDX+jFw4MBAISqRkOoVwMhWFyvmLJYw6W1Pzs9vaU9d/yhe/RiLrI+1YcMGd+10hUmvAsh4ZuzGuj8TCZyJxkc+FOxUhGTu6XcXb3BK0eMzVsiW2ui4ooHd2zlLEYrR0J67YyCzRTG7s2ZC2GMkW4qcYRjFSegKEi/+eC9tt0L4tm1hX9YoUrLhzhSLclLNHnyw25TGHTuk7uOPZfnrr8v696dK+1WrpNWSJdKqKa5JGhqcQsW26eGHm39XMWDA7ngmVZrGjpXyptgF7+wm7nMoPwjCKCp8pn64PHGfYFFgZh93Kb7PRJHQtqQMKJgoWlxbg/69wnC2Z0yLZUY2aPx5kwn4hfdYQlQyQmomAlg67elV2lCOUM5ZEwklCTeyVO4nvwKoGfY0TXmsdcXiucNlokBli0R9tGjtNnloarU89EGNLFu/I+q7Tm3LnZWI1Nz7Dt6tOOaCYnZnbQmTMIZhFCehSytjx46Vf/7zn/K1r31tj5cvQiDfcYxhxHu5J3JnCouydu2k3cSJ0qFPH6keN07qKyqkY7t2sn3+ApFFC6X31m3SetlSqZs12y1+2zyWq6vdtuXZZ5v3te7WzSlNxDZJ//7SjgxlHTu6cY/ATX2oH4IlcRrJWBTSaUsVWDVjGv/n3P770e9elEoMQzLHF8OMbND48yYTSCamTN0aaQ8C/Gn3bAipqbanV2kjSQ7KkSpJ1DeV+8mvAKJ4U2cEVFW2kklM4h8z6SpQuWTDtp3y+Izl8uC0Gpm2dGPUdyxP9KkhXeQz+w+RY8f1k7YV4cUVlaI7a5gU0hgxDKP0yEoM0rnnniv777+/XHbZZTJy5MjmJA1//OMfZcaMGXLfffeFfVmjSIn1co/nzpQuQQIaaKptdXlDQG7Tu5f0Gb+3DGpykXLKxsqVu1OPN20khCDWSdm1YYNse+MNt0EPEenWZndgfW3fflK213Apr62TSL/dKYPDViC0LbFSEdNEwDnKGRaqeMJrqjEMqRyfjeDxMM8Zb/zFiinz1hnlFoWjurraKR8oCyRWUBdKv5Cay2B6v/KnC9ESI8S9lcq1/edifHGfoBCqtTfe+dKJk8m2gh2vL+oadsmLc9bIg1Or5cW5q6V+V3Rc0YD2u2RCpx0ypZfI8Kr20q/tVilvFcn4uunQki0pxTAJYxhGcRL6m5kkDLw4ScSAFUndDBAweZneeeedcvbZZ4d9WaNIifdyD/PlFySgsUAlqLASL5Uw47iiXz+3dTrqqObzYlWqnTP3kwx6KE4LFojs2uW+L9tZL52Wr3CbTJ26+0dlZbJt2DCpcSnHd6cdx02vvFu30NqS8pIC2psYIpYQxvG0DYoVgr26AXrdw7xCnWb7wo0vXsxDNoLHOSeTLSgl6gqH4D+KJB2evkxW8ExWuIzlQkd5GEfUnWtp5kDOMXz48KjzhNkeyQjZfuWPSQDKjnKU6n0VpEjS9mTdS+Zc+YqTidVOQX2BG+KWyl7yyPQVLq5o044mN9smerVvLZO7N8hB/cqkwy4Sr+xybrGpZJ70J2/RtOsshstv07kvzJJiGIZRgAoSwhLuO7wolC996Uty/vnny3vvvRe1DtK+++5r5m8jL24SQQIaQjaKO4pEsqmE/bTu0kU6HLC/25RG4jPmzZe6ObsXut2BxWnOHJcEYvcBjbJz/ny3bX7ssU/aol+/3ckgmtz0SEFeUdU/6ViGdONUSP9MGmkE3qAFSP3CJII2lhLS+MeLeciGUIxb15w5c9z1UeT4i6CpCkCqykeybRbLFVQz3qEQsY94L5TH/v3773HtsNojWUUrTMtCrPWUcBetqalxLqPxxls+4mTitZO3L+oqOsljczfIqy8vklXbF0ado0Nlazl4UHuZ0q1eejRulC2bN0nHxk5St3On67dUM0/qdXlf8uyhPLpQbiZp1zOdTCrUNOGGYRj5IuMnIC+8e++9Vz73uc+5zxdddJF89atflQMOOEAOPPBAtxlGui/3bK6UjqAH/D9Moa2sslLa7T3ObUqERAxLlza55+22NLHtWrv2k7quWCFb2V588ZNzde68h9JUOWyotKqoCC1ORYU82pd2YB/Cn7qH+QV72o3ZdgQ7rhUr5iEbQjFlwZUNJQ5FFgWFz6Q1d1a+NJSPZNosniseSpru51y6nlGySpa/PRKN+WQVrWSVv2TjyfzrKXFdJsEQ9HU9p1hKaT7iZOK107rNO+S5RTvkvXU7ZfaaDVG/a13WSg4b0VPOnDJARnWokxnT3pPG+kZn+dWMk5wzncyTOgawvmryFsYCW74yzxV6mnDDMIx8kPHTj4cps4jK3XffLcccc4xTkAyjkFdK14U7cyG0tSorkzZDhrit84knflLHNWt8StMsqV+ytPn7Rhb2fOcdtzWfq00bqRwxoklhanLTGzVKyjp0SFmxVNdC4mYQ2LAMsA/rgFoa/II9rrIoSFhu4lkmsiEU01+uDZqsavoXC4au85OJ8hGLWNYYTZuNgobiiOCLu5S/Lbgu7YtCx3G0oca9edsjmTEfz5pFLBT1U5dm4oM4J2m52Uc7ed0tU73H6Hc2VQi4lo4JTaoSJOTnI07G305t23eQN2atlLs+nievL97SFFe02xUWBncukzMn9ZfPHzpaenWqdOP7ySefdG2qyrcu6Ey70Z5BmSfjjTHvPcFxukg0CibXy0fmuZaaJtwwDCOrChJuNn/5y1+coIBQBbguTdV4ixhMmTIl00sbJU62V0pnzHqvk4/g5nIC+tkOO6x5366t26Rurq7VtDu2qW7ePIk0pR6P7NwptTNnuq05r16rVlJWVSWthg+T1nuNkNp+fWUdLlBNgmy8mX3NsIerLGmbEfwQ8mMtKosgTjuhVGHJiaVoZEMoRhDnmpSBiRmUIj7rteIpY5ko3LGsMZ80f7TC5kWvi+sd1iZVMmgLLE3e8yQz5oMUT8pH7BMuiFjUgO9oG/qUDfg8ZswYF7OlMVN6Pb7j9x988IH7S301LkbrgPWI4zkW4Z768pd+8CqlQUpCrjOOcQ3qNX3ZRnl7VUReXrxNtuxEKdrcfEy3ylayf99WctjAStlnr2i3SOpLHfiM6ySTBxrHNW7cOKcM+zNPJhpjOk4//vjjZgsULr7cc/nKPNdS04QbhmHEI+O3089//nOXtQ6rEfCA/dGPfuS2IHgRcAwzmUbpEaYve5gv7ngCLrPsheR737pjB2m/zz5uU1CK6hYtcjFNGttEXFNjk+ArkYg0VleLVFfLrpdfkTKCytndtas0DBwoW6uqZPmBB0jfAw+UikGDnEUr3gKkXgU0SNFBsE9GsWBmHKGS/tO0zpm0L2VDwMdig4KkFhsSIjAxE08Zy1ThDnLF0/TenE+VFT4zpvRYPmvcDkolCoxaJCg/3+u4izfmubf4P9ckEQ7PUBQfFFw2zoMCpjFk9BlKGd8xecU++oK20/Lp9fgNZUTJQnBHgSP5BBNgKFPadpSXc1EWTTLA+VGSVClF6I+lJCSTxCCM50fNxh3yn482ywPv7pRlm6KTLbRv01pOGNdXTp/YT/bq3Ci7GuoDr0VbAeODugJtTt9MnDgxsFyJxhi/YWKGttUU6fzlvci4zkfmuZaaJtwwDCMeGUuCJ5xwgnvhvvvuu+5FQIKGSy65RA466KBMT20UGWH7sof94o4Va1IMbiS41eFGxyZyhtuHUEWa8ZVvvCGr335bKmpqpGJZtbRqys7nfrdxo1SwffihbHv6aVlAXFP79rsXt23KoDdg5EjpMnSoIEYGCYqZLlKqv0GQzhSuicAepNQmKmMi5SMdwZzjEZ5REHBjQznwu0pp8gidGFJlQhUW733C71H8cOvCasH3KCF877U80PcoK2Sk43dcD+WGc2PR8JaP43SfxmwtW7bMfVYXMeLJNN09x6IwIbyjdGpbs+k6TxqDpMoZv+MvSinfp6OIJnp+JOqjLbX18tSHK+XBadXy1sL1UecuayWy78BObr2ikyb0l/ZtEvct7UDb0U8ohSijjJlBgwbFHBvJTOpQJ+qCUo/ljf6g/Rg3XmU5V7TkNOH5xBJjGEZhE8pTGBeB448/3v3/rrvucqm+jz766DBObRQRYfuy24s7PghgbQYMEDnwQNnQtPDnrlatZNOyZbLyzbek87p10nbFcmm3cqV02LhJWjXF7zRu3y47pk51WzPl5VI5fLiUjxkjm8eOaVagWnfqlPEipWHHNcQqi3+/LuCqArUqA36FO57FI5GgqsoOCoa6mqHY8H8Faw9Kj7qxYdVhH4oHfYbgvWDBArcPQZlN45U4D+1HNlDKpFYz+l7j5yg/wjwKCkqNWuxAE2+wT4/nnGSe41juMTauzzXV6odCgOCuyp5OTKh7pYvpaUqxTj28WexQ1NJJRqEWsqAxw3kD16EaOkzeXLxRHpxaI/+duVLqGhqjrjGqTyc5a0qVnD6pSvp2SU1Bp/8ZP7QVbcE1dW22pUuX7qGkeePM+B3tQv3oM/bzvd9KSJ/Q74wBlFHqnOsECZYmPPdYYgzDKHxCfwK/6MnAZbQswvZlb0kvbr+wSJ0RlJKpt9/SJp07S+2okbJq0yapHznCfde+dWvpvGGD9NyyRap21kvZkiVS9/HHEmlyHZKGBqmbO9dtmx5+uPncFQMGeDLo7U4IUd4kIGdzLGQ6uxokgKgy4I8581s8EGb5LcoBCle8a6uiopnIvJ8V3BZRalBMOLceh7LEsQjHXF8tCygolAuXN36DO6O67mndUIpQxjgvwjgKDWMGpcer6LAoLOdnH+3Ab7ACodhwLOfEksFaWXxGWEfxoe4cq+5zmlAAKxntxH6WbuD+BO0r/nJcIstvUP/wO64bNGa8Cjf1nLl8k/zjpaXy7v1LZP32hqg+6dmxUs6Y1F/OnFIlY/vtdjdMB+p4yCGHuHKi9NDWgCLjV6TBG2dGO6FE6dpq7Nfnmfd+RbHkOz7jfhkv0UU28N9npKcvxedroWGJMQyj8LEnoVHQvuwtYaV0v7BInRGcEIL5LpFFI8jSxkw3wjez1wjPWBg2d+okayorZch++zk3oUhDg+xkwVVd4HbObNkxa7Y0btzYfO766mq3bXn22eZ9rbt12724rVOYxrr/k52vlWcttEzGQhizq0ECiCoDfvc8r8UDpUAtQrQdloN416afUERQOvgtQj7CtDfGkrZH4fEuSKq/1UV32Y/CRGwKLnV8RrHSrH2cV93zqBPHUD6UH9zxVABHwFWlRrPYUW82zk19UIYYW6qAUG5d02r27NnNChbjhnHEb/g9ygvHYCHTxYchWUU0UTwYSgXnDxoznHvV5jqZua21vLholSz1xRW1rSiT48b2ddaiA4d0lY0b1svOnZtk1aodGU2q0JZ77723+z+KKIsUB1m4QGO0cAHF7Zw+of1RRtXNUq1her/SDvQl/aaJL9KZVEpnQsGsGPnDEmMYRuFjCpIRGuYSlx5B6wwhjGE50HWG4s0qB1naEH68QqdmfEOAUyWlFW51e+3lti6nnuJ+M2/ePFnLoraLFknblSul4+rVUl5dLQ3VNc3X27Vhg2x74023Ka3atpXKUSOlctRoqR9QJQ2DBkmbdu2ktq7OWSVSiWvQ9qBeCIzqgobQPACXwgwEENrA34b+1Mtcn75AwUCR8Aq2fiHUmwXQmz5e+0DjejT+in2UCWGYc6OIqYCs6zrRXsBfVRhoA46nPTSoX9N2cy7Kx3GcC6uRlpXzUxaEfD4j4GPh8CsgGtvFefiNJtXgLwqQVyngGpSF3zBOgxRRxmO85CdB/UMdNVucKladu/eSV5fVyf3vLpH3ltZL5JO8jY59BnSScw8cKifu3Vc6ta3IqtCfSKj1fsdfFFLaU8eGdwJE71eUUBRcvvcmukhlUindOpsVI39YYgzDKHxMQTLCG0wtyCUuTPyCl86Y65orybinBcXfaAyJpn1GkA5ao0dRgbqiTx/pOHz4bktKfb0TnHu1b+8sTS6DnlqcFixwrnmAq17t9BluU7q0aiWd+vWTilGjpHLUKOm+7z6koWN16YTtQbk1GYBaS5iVTzYLXioCiH9Gn+vrjL4u4IniEhgDM2SIU/z8Ae7cA97j1U0NgZjy8DvKhIKhAjIKEvEu1BllQdfb4dooJKoUeZM9qCIM7KOvNY4l2bLqeKBdUa7YFNzEEikFQd9TFu95kukflEgsU9KqTF6fv1aemr1O3ly2WGobdlvRlL7tRQ4Z0EZOm9BXPjVpTFqL6KZDojHl/U7bnbGrsV+6yKw3fomNemeSICHdOpsVI3/YZKJhFD4muRrhDqgW4BIXNn7BK0i4SsdVEQEJoRhhGzcw+sW7SGgqAlPrvn2lwwH7u01pJPX4vHlSN2eOSzu+efp0qZ83T8qaFo4mKUTr5culcfly2fHii6I2qPJ+/aRtUxKI3bFNY6Wiqn9UYgFd3FSTD9AO6uqVzPhSAQRrnCZQIMZD3aFiKfYoRbjc0V5qvaE8WHOwCAQJof5JAVWOWDOIsmNJIWucZivj93pNFZApJ8oR56WuWFI0OxzjgOPZrxYI2gWlifIgcPNZlSesbZRD04hzTspDnVKdwEhGKUjHlTJIQNxW0VXumrZRHpu+QlZt+WTxcehSWSanTeovRw3rKMO6lrt6BZU9G5kK45XZq8z4v0NBVAukus3idkdfe608mU4qpavopNJ3LS3jWrbra5OJhlH4lO4TzjCKBL/gxcsTSwOuUAjZ/N+/oGiqLje6vpH3Je8XAmJleYsl7Ja1aSPtxo1zm3xaZOfSpbJk9mwhMqVs8WKRRYulfu5cl0Uv0hR34667YoVsZfMkdCnr3LlZaWozcqR021knq8mg1uTKpe5e8YQ+f31wxyPeBwUR1zqsUgTYB7keqWLPdVA2/EIwAjkKDGVAcdOEAigw/uQaXMO7oCrtyPcoMPQliot3hp/yUHZ1o0M5cjFjTYkVsJ4xFhCwOYe6/6E4US8UN80mynfqpsd5NHsaZaVM/jWuMlUK0p0JVwGxoaKDPDlztTw7fZPMW1sddUxFmcj+A9rJgX3LZGw3kXFjEpc9ltCfSaZCf5ljKTNBirImWtFYM8YRCrPfypPJpFKYSmpQ37W0WKVc1dcmEw2jsCm9p5thFBlewUtTBAMCM4K4plPOJEGB3+UmlSxvXoEp3syqE8ratpWtFRXS8aCDZOv48VJff4L0GzVKerI+0GyPe97s2bJzyZLm8zZu3izb33nHbYAT3v7l5VLbu5c0DBgorYYPk4YBA6RixMjAOgfVhw3FgDKq4JjI9SiWEMzv6A+EXE3njbCLtYlr+6/pXVAV5QZlJigexRunxDmxcvGdWos0PTdjQI/nOM6JAgQoU1grOD/nJiU4x3IM32mCB8bVhx9+2KxsJzOe/O2hrn7UW9smVQvIjp275L+zVsp/ptbIa/PWSGO0B51M6NdeJnap2x1XVLn7eskmLogl9Ke7NlNQe8QbO/7v9DNWPixHKEdhZPj0kqmSmqjvSilWKRnLUCnV1zCMIlKQeFnj3//DH/5QvvzlL5fkDJRhpIoKV7puD4ItwrJaHxCAkn05J+Nyk0qWN+86L/FmVuMJak4x6NVLOh52WHMZdm3dJnVzUZjmSO2c2VI3a7Zz2YvU785QVtbQIO2XrxBha1KcNv7q17J90CCpHDtG2o4eI235O2aMrA1YQwdlBmWCuBZtB02A4a9fIsFJ3dc0DkgzBGJNor381yQFtsZQ0SbqDued4QcW2OY3XisTx2AVQqnRlOD8VjPaaR+jILFxbk38wHlQzDg/9eS31INjKAtWJC2TP0V3LIFRxyZtRJIHYsF0PSayIfrXQQp6pjc2RuStRevcekVPfbhCtu38JMsfDOnRXs6cPMBloavYudldR3Zul0ib1DIgxhL6k12bqVCD8uONz0zctZKxYpRKrFKylqFSqa9hGJmRc+3ksMMOc+4f3/zmN+WXv/yle2EbhhHeyzkZYSyVLG/JzqymKqi17thB2u+zj9sUlKOad96Rmldfk/JlyySycKFULl8u5U1xTYJlBQvJkiWy5amnm3/Xqnt36dS3r3PPk2FDpePgwbKatXvKy5vbAcVAs7Bpam1NXoBbXDzBiXbhHLi2aQp2PZ792oYa7+RdUJXzofByLqw7fI9Swf95/qmFiGOJU0LRwV2OY7TM6iapyQywAo0YMcL9X2OzVCnlO29MkvYdCo13rR2UK9wGValTV06/wKjCOckk5syZ485L/bFQ8VvKyj6N85o8eXJz1r75q7c4pejhaTWyfFPTmltNdG1fIadO2L1e0eSBXZvL2tCwu/3TTVwQJPTnO2tYJkH5yQj22XTXynfbhUWylqFSqa9hGEWmIL300kvuLw+dV155JdeXN4yCJoyXczLCGMIswhZCryYkSHSdZJS3TAW1VhUV0jhwoGzeZ4q0PfhTuxdLRXBevVp6btkqHdeslq4bNjrFqaHJFREiJHRYv15k1iz3mRWZRlRWSuOggbKzaoBs6d9PdpBBjwVV+/RxygbKzMcff9y8Fg0KRCzBiXZB6EcxQJHgGFVCvH3Fd7rQqipLtD3KzPvvv++UClfepqQT6laHRUb3s/YQG9cn4QJKCf2J0qUul2wIzhq/4rf6AcfTfvQxv+d8uhAt7oIfffSRU3A0KQTHgDelubp8Uh9VplDgOAcTXdRB14LiWGK+NtU1Sk3rvvLI9BUyozo6LXdF61Zy1OjectaUAXLkqN7SprwsJwHs+c4alkmd8u3yle+2y/XkU6nU1zCMzMibfxsPp5NOOilflzcKAK/biMY2IDC2hCxJsQjj5ZxIGNMU4Ai0WCgQgBHsWSw03nVyNbOq50SIR3FBGdjVq5eUjR8vG+rqpPeoUc61q2HDBhfLhIvejlkzZcuMDyVSXe2y5wHZ9MrmzZfyefOFaJ3uKCBlZRIZMEC2k7CiRw/Z2LmT1AwZIpH27V39dW0hxiVtou0W1C9YnsBvvSE5BLE+mhwCpei1115rVkBQrPgOBQNFjT5COWMf1hiUIxV8SbFOObAg0E8qFHPOREH+lA9XPZQbroFywzUQELmuxjdRN76nrXVcqMXCKTybNrkyoBhRV00fj1LH5urRuasslZ7y2tKdMn/OBmmMfLLYMEwZ1NUpRSeM7SUN23cnn1i/dnXM+zwTRTuWO1o2lyBIJrYl3Trl2+WrVDKuJfv8KpX6GoaRGXbHG3nB6zaCsKXrvvDiQiAu5SxJ8cjk5ZxsalqO0XTZuIwhKCDIaxKBWORqZlWvg/UEAVyFeKwnXoGmnHTZn/qUdPjUp5rrv6a6Wmrnfuyy6LHA7c65c6Vu7lyJaOrxxkZptXSpdGQTkf5N16zt2kUaBg6SejLfdewoO3r2kOomq5GOw6B+Ab/1RvtAk0PoYqqMb+IvqRNjHnQtIxRVvsea5G1ProvCRf+gwKjbXjJCMm2IgoPyhVKGIsN1uD79DrQtx6H88B319aY0RzHie37DNTkXChJlKCtrLasaO8pr67rLolWVUtuIi1xl8/UHdmsnx43sKkcN7yTDe3dqzvCXzexgycTJaf/wNwzBN9tZzwrB5asUMq6l8vwqhfoahpEZWZE+n3nmGbnjjjucfz0vaG9wMehaHUbLxes2wnhQVx8EN43vKKWsQamsq5HOyzkVIU1npFXYpp11cc945GpmVa+DMEhCABXIKV88hYzf9cOq02TZUSJkmVu8WLbNnCmr3nxTts+cKRXLqqWiSUmBths3iWz8UOTDD0VXSmrs2FHqBg6QpRMmSo9995W2Y0ZLn6FDpVVrHPg+wd9X/hl/xjhlx41NrUUoI1hxUED4DsVE43eC2jMdIVlThDM2KANucOxDKVNXP82yRxtTHsrAX1zzKL+Wm2NU4avZvFNm1PaSmVvby6ZdFVHXbNs6Igf0K5fP7D9EhnWKODfD7avWydwN0Rn+suUqFs8djfJnQ5HJtgucuXyFQyFZhlraulKGUYyEfkfedNNNctVVVzlBZv/995fx48eHfQmjBPAKkbqujLo3ITSWUtagXKyrkYqQlsmMdK5mVtVywrUyFSRalZdL5V57ua3zySe7mJ6FCxZIh9o66bV1izTMm+fWbCIpRAVxTE2U0S6z50jd7Dmy/L77dp+rbVspQ0kaNlTajBwlPfbbV9qPGSNl7drFbF/NOIdioNYixjsZA3GDS5QBDvgOqw4KI8oL5xo6dKjb700Vrm57mt6b4zi/xlhp22osEv+nPNx7uAeioDE2veV3ayvtKpOn5m2T99Z1k8VbcFb8hDKJyNB2O2R8x+1y2F7dZeyoIe7cjPlEWQXDvs/juaNlS5HJtgtcMoK9CdzZcXPMRru2tHWlDKNYCf1uvOWWW+Soo46SJ5980r2IDCMIrxCp68podqxSyxqUiyDrVIS0YpqRDlsh43zEGmkmt1U7u0n5sGFOicBKsqG6WjqvXy+9t26T9qtWSetlS6VixUqRJutapLZWds2eLTJ7tjQ88aQ4Owyuf0OHSuXoUdIwcKA0kIYcN73GRqew0L4oe/QLrqRea5Fme0tWENNMb59kfGtwbmsoTdRH02/Tn1hjidXCiq/Z+1BcOD/XIdaJ+01jj0aOHOnKo8rYxwsWyfTV9TJ1fYXM3NBDdvnWK+pXuVP26xWRQwa2lT5de7vyDxs80Al6QWm1NWlFNl3F4in/2VJkwnaBCxoL2RK4M1EA0vltthS5bCgd2VJk8p10wzCMPClIvIzPPvtsU46MuHiFdNxuNM0xQir/L1SBPR1yEWSdipCWLVeTQpzFTiZgHwuKpqvmmLWdO8tcXBAPPcRZeYYNHCi7Fi+W1W+9JWvffU/aVFdLa5JBqIteY6PsXLDAbUoXEelEjNSIEdJm9CjpPHGiSwyxljFQVpbS+lLeuDHGkPYvn5lUQJlByVF3Ps1QyPec4/DDD3cZ66gn5+YYvufcKEyci/NqVr6pSzfK3W+vk5cWtpLtDdHjp3+XtnL6pP4yoXOt1K9b5u5VFDF1wdN070HjUTP8ce2wFXOvFU1d+VQ51WvwfTZieeJNOKR6TwSNBV0Ti8VmVQHGekgCD86VrsCdqWKV6m+zaTnJhtJRrBZHwzDCIXTpBbc6t8ifYcQbeD4htZSz2OUiyDpVq1DYlhm/8MP5EYa5BoJ3PmaXEwlkWn8ETywwJFugf3CHQ2EioQIucKtRTurrZd2QIbKpWzcnnGI1iqxcKZumTZP2q1ZLZNEiqVi2TNps29Z8/bING6TxnXeklk3udfvatGsn9VVVsmrwINkybpwMOvxw2dzkUhpPEIslVKEQsF/jnDTZglpM2IcVibp4M0bSDt7se43tu8s/Z2yUR6bPlsXrdscnKe3KRfbtUy7nHThMTtxnLykra9XUtu3c73VNKe94CxqPuPDRnuzPpstSrLGXLctpvAQeqSoEQUI5sbz8bndijN1rbM2ePdtdr6qqKm2BOxMFIJ3fZtNykg2lo1gsjoZhZIfQJdDbbrtNTjzxRNl3333lc5/7XNinN0qIlpIpKBcubfkOQPYKPwjpuH0hqLMPASMfs8uxBDKEEs6p19HseCqwqDCNZcS7DhFWEhR4rBPM3td16iSbx4+XTXvvXiSVY9rX1Umb5cudi16rxYulw+rVElm+3C1wC2U7dkjl/PlIziLPvyBLf/s7kYoK6dq3j7M2RYYMlU5DBsuqdu2iBLF4QhVWBVzksCJp/BC/RUlozvjXdK+pEupiojp2lekrd8lzszbLjBVLo9qurJXI5L5t5ahhHWT/qraycd0aGdWn0ilHiZQCsvaxD+sUZfVPevjv+UzdvFxM2cKFUdYszoVy5L1WNu+RoHpp9sJUFIIgoZy68Vvqpmts0d+4LKIgpStwZ6IApPPbbFpOsqF0ZEuRSeV9UIhWecNoKWR8p02YMCHwpv7CF74gl156qfO9Z8bSCw/H6dOnZ3ppwygKcpn9LZFLTVAwfxhl8Qo/KqxjEcStCgExV7PLXoGC5B8Ik16BDEsRiQ4Q2r19oS5YXoGF8qPoeRd3pe1YeBWlBGsIyiDf046UeVdlpWzAItOli0Q+ddDuZ9+OHdK4eLG0WrRIem3dJh1Wr5JWS5dJq4aG3YWur5c2y6pF2ORFt6t/q1ayo6pKqsfvLW1Hj5F2I0dIz4oKWbR+fXOSBixDoAoSddWshEFCF20ze+48eW7mcnmtuk5mrI1IfWN0+w3uXCaHDWor+/SMSO/ObaVjx/Zx14vx9k2QkksZsqUY629RIPg9fUEfcU2sWkGCd7x7JGxhNB2FIEgopwz8XrPB6l+NQ0tW4PbXj7GZrgKQjvKQTctJNiahcm1x9I81S+ZgGPklYwkNv319UCu4qrByvGEYhWEt05dtUDA/rk+ZxgF4hR9NHY3SgMKTq9llv0ChC5mSGEFjbXSRXJ5bqohprI53PSOEFywTxH9QF86Du5pmW2SfKoCck/26kKqu3cSm52s/ZIhs791bNrRq5RQbWrqxuloGohzV1MjGqdOkceFCKWtSxljslu+3sD31tNtXhgLTqZPU9u0r9YMGSu1ee0lt//7St39/Z12gXii+JIDQWCWgHDOqN8nfXv9Ynp65RrbUR7dblzYihw2qdGsW9Sjf3W5t2+62YKUiGOba7Up/yzjWftDFeL3Ws3TGThgWzHQUgiChXJNpoJzTNyj3uohxKlnu/PWLNTGQjAKQjvLg/Q3PISZRtN/YMnn+ZGMSKtcWRz+WzMEw8kvGd/pLL70UTkkMw8ga+rLVdXB0/SmElDDiALzCj65bhOCa6ewygqG6bCUSUPwCBS5+/Fbd4/i9Wny4hlcRQ/nBXckrTGIp4lgULHXZ0pl8FJGamprm9ZlArTe0L/v4rPFAnBO3NtoG6wb16DNlilQ1CeC9WOR2zRqpW7ZMypYslcqaGtn58cdSS7a8FSua61i+ZYt03LJFhNTkz78gnVCAyIQ3eLB0GzxYlrdtK/VDBsuaIUNk4coNMuONZfLqsjpZsOaT2ChoW95KDhrQTka22Sh7dW6UUSMHujKuXLk7NgnLPwkqqEO8dvdaJVAm/Ra7bCrG+luUQ/qEtqZ96afBgwenNNOfDWE0HSUiSCjn/7rIria0wXrpdx+MV86g+rGPPvYvdJyMApCO8qC/YbICqx/9xf2FGyvlyXSSJhuTUPmc2LJkDoaRX0J3Zr3nnnvksMMOcw/wIJYsWSIvv/yyfPGLXwz70oZR9GTL51xftiqsazC/ZjRLJw7AX1bueQQmZrpRTBDmggL4kxUmdR+xFgi+KB7+9NjxhG1cCHUtIIRABGlA+Yk3q6/CpCo7WJKYtadempJeLUka70O5aFM+cxzX4LoIgJSFtqI8tAMJE7DaefvWLXLbr58I2/77R9Wrbs0amfbQQ7Jh6lTpvHadSz9euXatszKBy6Y3d660njtXupdXymv9J8gLgxpkRs/hIrsTkTdboEZ2jcgRQ9rLkSO6y6667bJ+/W5FmXZGIaS/UO7oO+p5yCGHBLZ1kFWCjbpTT9oinmKsYwc3SKwijEX9ja7NRPIMVRCCEjvoubmmLnpMWVlnKVVhOxvCaLoWiCChnJi3dBSZRPWjj9NRANJ9TnGMKrOUg0kD7qWWkOY61TazZA6GUWIK0oUXXij33ntvTAXprbfecseYgmQYkjOfc33ZIviqAIp1xh/Mn2w5KSNlRXkBBB3ueU09jFtQKsJAkDDJdebNm+eUI4RoBGEEasrOmj3++CmvQMF3zLhj/VGLGfsoI/vizeqrMMl+BElNBIAwqdkWVdBjnyqcGhOEoqEufhyPtYljEAiZsaeeEKt9/IKU+9y/v2xs3162N6Xirt28WXrv2CHdN26S7XM/ltmby+T1TsPlrb7jZGfr6PXnhmxaLkcve1+OrJ4mHStbObe8xiGDpdXQYTJ04gR8omXW7NmuPSiDuk1jIaOP995776SsErQr44sxq+m2Y8XC6DjneNoJhVrTcqOgoahxfe0LroHCyVjVe8KrVPNbvsNylMr9om2N9YvreN0xw4iPCcsCkel5whS2M40bIwZQXSMpB/cO462U01yn02bFtF6dYZQioStIGkAaC15kloXFKGTylTkoG24+/vVh+IxQj2udBmmn8tLVFz2KC9ZgzoWgg6DLRkwB7lnpCHT+32BBUOVIBfdly5Y5xYf6+LPj6QKnfI8Ljx7DxnOHciP8JprV9wuTXJc2UqWStmM//0egxmKigqbGOHFtjud5SPugGLFp/WIJS0HfAW3L/1EQuX59fYNs6TNM/tu1hzxTO0G21EfHgXaN1MnhG+fJ0XNekRGrFn7yRa1I5aZNbqFbpaxrVxnRp490at9OWg0fLtKuvdT37iUrmtKIe8eRt838VglVLGgrXVMq6N4JUqyoPxY+9qnVkX5HAVfrEi6QtLn3nkgm9iaeIupV1Kgrf6lDqa3FFqawnWncGPcH16eNuT+8a5CVKum0Wb4zkxpGSyeUO23GjBnywQcfNH9+9dVX3cvHDw/oP/7xj2721zCKbaYPsqk4he3mE7Q+DJYeUvAjCKaTxU5f9JqIgHbAQkN5EXw0fiUM9NwIrirgAdfyZ8fje6wQXB9lCCsE9VfrhLqNoTghGMYT5IKESZQbFsHm2pyTa9CmmjVNBU1d0JXzI/AjCKFEMn40xile+mfwx1Ex467rHa3ZWi9zajvJvPo+sn4FStF6WmR3e7VuJRN7iIyoWC+T+rWTPr0OlG1b95b35s1z2fM6rV0j5UuXuaQQbVGSmmjcuFEqN26UwXyYtvs53lheLn169ZL2Mz6UtR/PkzWdOspqUo839Qvtw/j0WyV0/aF47RukWOGKiAsZEMCvVk6vpQ5lifHqdQlNlJUu3qy9X2jlfkABpQ6ML01yEevchZx+2V8+xhbtzDiizb2L+qZKpnFjtDfXp38pJwo/CnCpKKNhtlm+k/sYRksmlCf6Qw89JNddd537Pzf/n/70J7cFwYOaOCWjOCh0QSBXM30IF+qaFbb7W7Z8zoPqQtk5typ86b7osYoA50bAQYBNxoKcCow1YntQTKiLgjDlzY6nMT9YtXDLwsqAIM1ffofgjdCLkqRrM6l7YdCYjhUoj2VK21Mzp7ForFfQ9LrnadIGTQKRjLDEcdSXc/N/tq219TJ7Wwf5YEM3WbqzXbNCBK0kIiO6iBw5tIMcOaKbNOzYKhs3NjollXLRHitxQRs4UHa1ndS8hs7kkSNlZEUbqZs7R2pnzZYds2ZJ3fz50qqpH8saGqQjySFWrJA1zz7r9vUiW2n//lI/YIBsqaqSdgccIL379ZXVO3akZJVINM75q4kx6FueQSiklB2rIm2KpTDVpB3+WfugmDXcI7WPaCc2jqcf9HqQLVfYMAiaGOEeRbFXl1raRAXvXMbGqOWI+4/JGp1AIG4sV22Xj3eaxRMZRvERylPhkksukVNOOcUJR/vvv79cf/31brFYL/oCYia2EF4iRmJa4joMsYRXdfXJxirw2fI5z4ZFijZQawaCjq4RpCl7NRFCqufVNvbPbpOQAXDDQUgGrusVzNjP9wizlAvhS+N/OLe6p6Fs8YzCiuRdB8k/pmMJUMm4uyQjCMXL2IdCQz3Wb9goy3d1knfXtJJZm3tJfYQUC5/Qs02DjG23RSZ2rZNRA/tIhw4iW9bvdk2jnFofBHu1QGmKaBTM3kOHSoeqKulwwP7Nda5etEiq33xLypYskc4sJrt6tdTPnSuNntTjUlPjLFDUZvuDD7r9WJrKhg2TilEjpdvkKdLYsaNEqqqak1P42zLROOc7MpvRr5RZlV3+r1Y8fsNYjPc8SjT+/f3A+OMa6lKJkkbsGcowm44VJkvCdoUNE79iuHz5cjcGVDnhnlV3WMqby9gY72+5niYuYSvld5rFExlG8RHKE4HsSy4DE8scvviijBkzJi1BySgswo6JKQZrVCzhVYOIEykbmdQxDJ9z7/XVRSnMwGwUERWwAMHRpanu1cvNAqcq6HDeuXPnyuzZs115AcFt9OjRLuEDAt1+++3XHEcVlB2PMlA2lAHGKpsqA/wehUCTLahFAqtS0JhOJED5x32QKxNliic8xhKWUN7mrdkuL2/sJu+tbSWb66OVog6tG2Vk2y0yqnKjdJdt0ti4SyLbymXDhjauLiSg8LtMcl6exwjIuvYVVi9vP0XVuV9faTN4kJT36SOD9tpLWpeVyfKp02TZKy9Lm5rlUrm8RmThIinzuOhFyHzH9vbbsuKee92+sk6dpHLUKNnRr59s7tFddvTtK60GDZKN/fs3K3Cxxjnf0V/0HwojQjRtwz6UJn7H+ybR8yiRsurvB20f3l3c41wfZZVzM75RoFCYKKdmzuOYMDLehYlfMWTyQrMLapZJdYelLrmMjcl3XE2u1hYKeg9YPJFhFBehP5V4gfCCMQWp+AnTAlEs1qhYwit1R6hgVhmhiL8IbcTIhFnHTHzOg1xrUBo0ZiaMwGwESBQXhEWNDSK2RtdVYrY6FaGH8yK864y2LsKKOxtKjFqStE2CsuPxWdNvqyDM/1Vx45woVsA+2onzBI1prwCFYkU9P/74Y/cblLZEi2/SvpruPJ4AyHWpM2Vr3aGbvLyiQR54bK7MX4fi2br5uPJWEZnSp0IO6tdaeu1aI+vXrnXtgyMcyh/WDGCceZNANP++vDxhiuhEQmOfSRNlS8cObt+6pnP0btNG+tfVSf3H86R29iypmz1Hdi5Zgo+lO2fjli2y47333P87N22R8nLZ2b+/LNl7nHSbso90HjtGKkeOktYdO+xRZlwE6R82+pb2QoFG2OczsUL8pQ1jPY8Szdr7hXXOrxMAXI97HFAs+D3WK8YDY4t+43lAynZN756LJAPJTMD4FUPuf21H0IXddSHjXMfGlPLaQrvXElvpnmmMD+4pb+bFQrAwGoaRHKFLppdeeql78OCmwBoahx56qNv22WefKGHSKHzC9JsullXBY81wAi88JgD4CwhGOsMcFPSd6zoGXR/hyLtGTypZvuIJFszgcy1SWyMkpqsYajpsng263g6fYwm+QcKVN1YJhRCBFpcszXyG0sY+tUAg5LJxHv+Y1nryW+qji4/qtb3JOhCEiFlRq1Ey/a1K1dLlK+Wdmlp5e5XIzHXLpdEXujW2V6Uc3L+1TO7VSiaOGeHqg0KK4IX7GefhGUscB2WMpygkEkgTCY1xZ/2POKL5PI3ECc1lcdtZUjdnjmz+YLrsWrRQWjU0LaTb0CAVS5fKzqVLZdWTT+3+Ee5ygwZJ5Zgx0tZto93f8l69XJtyXbXu6PpTxB8xvtRCSNvEqneiWXtv29CmalFhQ4FgHKjFBcVJ07VrPBvl4h7Aesp3unZTMhMEqVqbk52A8SuGGi+nFrFmN8vevZszWYYV91joZDMWSPuH+1MVcvrCn3nRMIwWqiAhNLzyyivy2muvuWx23/ve99yLBgHlwAMPbFaYjvC8WI30yabbGg90zsmsKgIlL1ld4LLQZu5y0Y60B8IGLznKj7CmSQCCgr5zXceg66MQeNfo8dc5WcUmnmCRiWLI72lTTbGsGctirc0Uq5+8sUr8Xscq50ag1qQJWFwQErlWkFVB66QxZ7rGEeXheK07/9eUxVyf/UH97S1veUWFvLdkk9z/7hJ5b2WD1H6St8ExuEd7OWxQpUzsXCddyhukTZuy5vgM7Q9c6BDU6Sf2eV0J0xXykhEak5n1L+vQQdpPmew2aLVypcydNcstatth1Spp+Hiei2+qXL5cIlu37v4RVowlS9y25emnm8/VumdPpyh1HTlS2g+oksbBg2Vzr17NyjPjxK0HVVvr3jkIod5Mgt7xkaxQ6leouL/pXwReTdmuY0uVKV0AGDgu2QmCdKzNyd5n/B4rprqUcg9gkcNdMcjNsiWttZPNWCDtH54zumYX44ZJDG/mRcMwWqiCxKzU2Wef7TbATeGNN95wytK///1vufbaa5uDd43MyKbbGufGzQkBRGdueeDz4k3n3IWcxSfZdmTWmBefCtsITPGCvnNdx1Svn4piE0+wwEKTrmLI7xHWiEFSSw0CKOMs3gKj/n7yxir53e+8baKxI7GsalpP3OooD8fQHjzXUL5UKaLN2Ieywj6EIM7hbW8t79T5K+TVZViLIrK+NtpU1KFCZGLXBjlqeEc5asLg5ng3b9Y0FcQ1Dot2VqtGvPZKFn/fcj3aU2O+0p10ceft319WsV5Ut27SZsIE1/a4AkZWrW52zaudPVtq58yRBrLmNbGLdO2vvuo2paJdOxnRt69b5Lauf39Z36WLrKqsdM8p+hdFGLxjIFMXV/6vmRl1fSv6huM05bhOlKQyQZDOpEKyEzD67NbFb3UcTZo0yT3Lg2K+WspaO9mMgdL+0fXAGDf0Bf/3rpVmFA7FEBdt5I+sjgRm1FCM2LAq8ZkHxUEHHZTNy7YYsunS5Y05wX1EU0QjcKRz7kLO4pNsO6Ya9B1Ux7AeyOlkB/OTisUrnmCRiWKoMTKcNyiLnT/phKbM1kQMrJmj/RTL/c7fJliWYgnNWk+dwEFRUEWI32rcBm3G/1G0UBBRnriWtvfarXXy91fnykPTamTx5t2ps5XWrSKyd3eRyV13ysCKLbJj6xaJrKmUd95Z437vL19QbBlujepelsmaNv6+RQGgPrQ5f3VShD6KZw0JGtNxhdEBVdJmQJXIscd+cp4NG5xrHmnHUZhQoHYuXCTSlHpcsIYsWiSyaJGQ7JxVo4aWlcmufv1k1+DBsr5nD9lZVSXtx46Vbkm6PCbTNhp7Rhp5zZSoi5yiQCMQExOVygRBOtbmZO+zoOeZ19IdVMeW5PqVrfpqX6AwMy54JugSCIXyrssW/9/eeYDJTV1t+Gxfr722cfeuvcZ9XcHGxqbZlFBMMZhOKCEhQIBAAoGEFHoKoRNKgPwJhE6optfQAhgMLhjcu9e91931enf+57s7d6yRNTPSjDSj0Xzv88jr0Wikq6sr6Xz3nHtuNgqNbBkXTTKH663g/vvvj4gi9D7qsUgYm4TQuuHDh8eMGSfO8DKky+19Zzp7kRvn6nTQt/kc3Xogx9uPkzp2KmxiGRapil/sF2OF9ESqGngvp06dGgmbg0GKlzAMUnzWzxEY8G62O6NRjPMxZszDsSHUdJ1hwXoIlnYdO8u0tU1y+5NT5aO5a6XRNLCoX7siGdBiiwxoWSuyc7vUbquVHWFvDTqOYFihjGaj3srgheGF+krV0DMbNigDntsQhPi/MSW01QTAidq0E2O0cK+9pPCAA6SloQOtqa5O6ufOjczVtHnaNAktWiR5DQ3qe8zbVLh8uVqaZ+ZqJtSxo7TZe2/Z2rGD7Bg1ShrGjJFCZNILJyhwgm5DuNZ6bBr2Aw8SvJ+oG1wTJx0EyXQq2L3PvHwvZKMhnC6M10ePw0Z70dk9g1pP2So0Mj1mmPgf11vvFVdcoQyXU045Ra655hqVnIF4g5chXV7s2689lXbP1emgb68eyIn2Y3dfbnn1vBC/eOlCHCHUDcIIIWww1jGmSmen01nN9PxIbra7eMk69ITBKhytqEhqW1XIM/Pz5K2JM2RrXXTo8F5FjTK0dZ3s3zlP9ipsUPtCWRoa2ioPDdAJJXA+OI55vILR4IUw1EYqfpNKPVsZNqhLtAkY/RAAxpTQVgLJayMjv7RUWgwdqpa9EMK9a5esxZxZ06bJxilTpPW69VKC0LyFCyVfj2uCcFq7Vi1tkPTjzbdkPuoZYwiRBKJ6gJQOHCCl1dVS3LOn5NlMT60n3zULBKDP2+59lMy9Z/c+8+q9kK2GsJvEE4h+7gT0kmwVGpkeM0z8j+t37mWXXaYSNGC80SuvvCIjRoyIJGY46KCD1IuXuIOXYWt+DolzGyfnmorIc+uB7NZ+3Hyhuy1+8dKF5wbiCGVC+fQgeZyznuNJj42D18NtoyTWOaHOtoRK5b/fr5V3526SlVuahY6mvLRQDu/TVgaWbZVOeQhNDUlt7Q7ZurV5gDz2CZEF8YF2ZzwfHb5lNGa1cas9V9pAg8CCiEnWQLUybLTo1J4WY0poK2MRIY7YDwRrOuYEwnl2rayUjp07y/zevXenHi8qkg7Ikrpokez4fmZzMojly6Vg3brIbxs3bZIdX0xSiyYPk8Bivq3qainq31/qunaRxm7dpCSG+IzXJpx6KZO59+zcZ/GeZ6l4gLLVEHYLOwLRr52AXpKtQiPTY4ZJDgqk++67T/3FixZCSWezu/vuu9UDZvDgwUos6e1I8njZY5VLvWHpOle3HshuPtgz/UKPZbDhMwxuCACdeQuGOzxJ8JzgZazH40BIIUOXk17tZAzFjdt3yuvfrpCXpi6XqUs3RX1XmJ8nh/bvKCcP7yaHV3eSNSuXy5w5W6Rjx70jqcJRTpwHvDS4bnpSW5yXFkYYJxJrYlkYZxinhd8gpA/hfqkYqGbDBnWtE7LgeCgr0CmhzfWH8kCk6eQFKCfOy05bTDVUy5ypDWXvjWt+4IFR+92rpEQa589vTgQRTghRP38+CqD2E0JWvG+/VYsmBMHapbNs7NNXOowcKWWDB6k05AgBdNtL6cW9F8/7mcjAj3ddssEQ9jIEMNcFYtCERi51ApPk8MzaxUv12GOPVQvm7njvvfeUSPr2229lxowZFEgu4aWBm2njOZ2k41zdeiAH5cEer0cW/4e3GcY3BBI8LlgHY0SnWYagwHWD4YIwNQgGGPeJjBYnoUL1uxrlw9lr5aUpNfLhnDXS0BjtSdmnWxuZMKxSTtinQtq3KrE0GhAaiPOAFwYJJuDt0uOXML5HJ6NA+SEAzZkitcGLbVEXECt4vsJITcVANZYRAgOZz3R9QLRhgWBD1jmdEtpsLKKeUfcQfxBLKBvKGq8t4lznzJmj3gvGtNPxEkFY7cOYqQ11rOtpj+s+cqQUDxsmO9etk8KdO1WCh/LNm2UXxjaFRRPGNyEJBMgLhaRw5SqRlatknSGLHsYwwdOE8LwS9XegFFVWJjWuKRPPM7S7eAZ+ovvCz4Ywyo5yL1y4MOKNNU7Q6maWOj8LxEyQre+jXOoEJsnhSUuYOXNmJHMd/qJ3F6DX88wzz1QeJEKCjlVvphsP5Gx/sOt6iTfRKhYYOHpiS73NkCFDIhkVYZjDoNOeGazXwiGe0ZKoJxhCZsrSTfLy1Bp5bfpK2VzbnBBAU9GmVCYMr5QJw7pJn06tLI9h5fVBUgUkY8A56RTkEAgAwgjiDiLIKlOkNnjxW5w3zjFVA9Vo2Oh5n1AH3bt3V8IDZcEAcyvhYjQWYSjivLAPjNMxG6Tm+wB/kdYd+8c5wwOEzzi2OVGHG735Voa/moT2xBOl7SmnqG2WLF4sCz7/XDpu3Sr5ixeLLF4soQULpWDLlt37WbVKtmH56KPIuvzyciWa1NimAQPVRLclvXpJnscetGT2ncjAT1Sn6TCEk6kXfX2N9xpCPnWSFbc8PH4WiJkkm99HudQJTJzjegvGjYEZ7WFkIBPUuHHjVBY7iKJ42aYICRLxemPdeCBn64PdWC+xJlrVY3NgQAMY3zB4MBksRBO2AxBY2rOk0y5DLCF7FNY5NRQXr90mz303Twmjxet3RJW7ZUmBHDekqxJFo3q2k/z8PFsprq28PlgHkaPFEX6D/2PRaaSt0AYqxv3AEIS4QL3AMEnVsFm2bJlah2c0yoa2hTpBma0MHbOxGCvdeKxEEDhPLYJRH/iMc4JAsmMkO+nNtyOmSpAyvbJSthYVSasDDohkCuzboaO03rA+nHp8lpq3CZPaYoJb0LR1q+yYPFktmryiIinu20dNdKsTQmCcU0G43XqZ7MCc+VFPmKy9svEM/ER16rUhnGy96OurxyPq8Xp4bpgTnuSipyQdZOv7iJC0CqQf/ehHSgxBFPHBQXKVIMWru9nbbayXWBOtwoCGByPRHFxYh/2gPDCIUE4YtXpyVxhbEBMwvrWYgMgyGopSXCYfzN0ony7bJXM3zokqKzTQwHZ5cki3Yjl6SIUMru6X0Pi3SnFt5fXRCSdw3vgtzhViD6FusXqk9bgbdEBhW/weBjFCzZI1ro2GDa4FFju943aNxXiJIHTiB/1XTyBux0h20ptvR0zFOp9O4eO2MkQ9NG3fLnVzEJ43U2pnzpLtM2ZII+ZnCqceDzU0SP3MWWppnsq3maIeVUowNXTvJhthyPfqJXt16+bas8Eq8yPOCWDfia6ZnTr10hBO9pmpr68uM64x2hfuETcnaM1mTwkhxDmu39l33nmn27skJOuIZ5Rl01wibvd2G+sl1kSrEAsQNrruYOhBBGgvh3GCWj1ZKraBcQTRAFGlPS34C2MJhj+EBRg8dB9ZtLOVvDF1rUxds1F2Rc/jKj1a58voLvkydu+W0q1Da7XfjWtXy2xpUuJLXzM7Bh22g9hD+VEePfEqtkHZdPkgGnCuqA9tsFq1E2yPzzohglvGtdPecbvGotV9gG1xveAphNdMezrs1qnT8to1/O0av/ktW0rZ8GFSPHSIrNH3Rm2tlK5bJy3gdVu3TvIWL5GmBfOlacvWyO8alixVC9A+v1CbNmq+pm2dOsqOkSOl/pBDpLhHD8lDRj4HoK3Mnj07Mq5LjylC29JeyUTn6LaHMl1jfMwTtOp7Bs8Xtz08XgjEbHofEJJLeHYXfvzxx/LGG2/IEoQjwOjo0UOOO+44GTt2rFeHJMQ3xDLK8BLPprlE3PaEmevFONEqQoG0kay30eIIRh6A0NH1ZTSSUZfoLca+sOjsajAQUa/t23eQb2s2yQdfrpNv3/1UNtVGz1fUtlhkUPkOGdhim3Qo2in5jfnSqfWwSHa3pUuXRnl4dJY3uwad2VuC5Ac4X4ByQjhpD5dO2mDVTpwc0+vecTvGotV9gLLDe4jzhgdMi0bsC9fNzvk5Ka9dMeXU+NX3BgR6UWmpLM3Lkx1ID96rl7Q75hjp0L69lNfXy6658yRv8WIpWLpE6ufMkV0rVkb2kbd5s+RNny6tkRDkvfdlofxF8srKpBSpxwcMiIxtKunbR/LDWQXN6LaCBAU4TwhOlE17Vo1p4+OdoxceSidCINkxPuYJWnUiFyT+MId8+g3OLUWIf3H9yYGH31lnnaXmQIIxoHuf8ACDd2nChAnyzDPPKIOLkKASyyjTmce8Dr1zq1fS7cxNVvWCLGlGAwx1gfXwKiHcDj3iMHjQyQKvg7G+YhnJWoyu2FwnC3a1ky9Xh2RNnU7T3CyOyooL5JhBXWR4uwZpWD5TSoqLpHXrjpGxURBF2D9601EGjG0yJpOAyElk0GFfWPBbvQ0+47fxDPxYwtTOMf3UO251vSEMYYhrbxiuE9oWxJHOQKbPD59R9xs2bNijjuyW16vQKOwLAgLvObQRtBlkKURbxTnNmj1bCerCdnvJrtbl0vrgg5R3s21BgSz95BPZ+u234fmaVkjhqlUiTc2uzNCOHVI7dapaDCehkj8YRVNpdX8paNMm0lYgntHOUGfoSMAYPawzeiUToa8J2hkEEoTSggUL1LWwmijY7nMI9y3Kg/rCOquOoWTH+GRz6FuQQrEJCRquP0Fuuukmefnll+Xqq6+WX/3qV5H0sHiBQCDdfvvtcvPNN8stt9zi9qEJ8Q2xXtp2e8j90ivpduamRMaMTt8MQwoGGoxP1BMyq+lkDuaB42ZDYmtdg3y4pE4en1Mis9a3D68NT3yKrM9V5XLm6F5y9KAu0rKkUCZPnizTFu+Ujh3aK8MWxiEMQ5QBx9KpqOH1MF4zeKx0pqxYBl08gRnPwI/1OzvHdBM35iuKdb2tUktjPUSGTu2ORXcqQIAk2469EH84F3go9TgflBPr0G5Qbu29QRuGwNPngPL3HD9eNo0ZE6mTdq1aqXFMzfM1NY9fqsNYonDqcczbVD93rlpk4sRIGZBmvKlHDylp20baDhgo+a1aipSXy4aNG1WbgRdFeyWdij49VgzXAqF7Tr0xxmsLrxTOHSFwEMfmjo5UhU62Jglg6nBCckggPf300ypRw2233Ra1HsbFX//6V/VQfOKJJyiQ0gTjmzOH1Us7Hali3eyVTNSrm0z7imfMGHvD0duOXmeMicA4HngeYtXXrsYm+XTeOjWJ67vfr5J608Ciri1Cckj3Yhm/T4WM3qc6qow6bA4GIQw4GLeYk6iqqkotWA9vljmBAX4H4RbPoEv2esf6nZ1j+k1o27nexrYKgxxeDxjnKAPOFdcjUSrvdI/jwDHgLULnnxZIEEQQ2WhDAP/XQgnnA48o6hTns0dK8yFDpMWQIZGPocZGlTFPCSbDRLeNGzZEtmnAFBrLl0sbfHjzLYGPp2vLllLftavyNnUtK5O8mhoJ7b235NmoD9Qd6hKCDm1NCzyIG9RvMiGIuLaoJz3eDtcRn2OFTmaj0EmWdLwPCCHJ4fobBMbMqFGjYn6P75599lm3D0ssYHyz/0hHqlg3eyXj9ep60b7MZUfHCnqfYTSb6wuG2/crtshLU5bLq9NXyLptzWmzNR3LS+SEoV3k0B5l0qNNgRJdVoYzygshhvna8PzCMRBONGLEiEgaahi8EEkwhnXqZKMnJF5okfYqwDi2e73jtZN0GZHpCP9B/eD6ok7hOUJbRT1BqOoyQEzEa8eZes5h3/DQQAChLaKNouw6KyHOCV5Q3aZxrjgPbIPxQrie8cqXV1Cgwuqw7Dr6aFUXofp6KUIK6zVrpWHunOb047NmSUNNTeR3Bdu3S9n8+SKok9dea95XSYlKNa4nulVzN/XvL/ktMG3ubtC+UPd6bBXKh3WJ5hZLdC+jHiC40MmA60UhkPg+Z+cmIZnF9bcHDIuPPvpIfvazn8VM3pBMLDNxDuOb/Uc64uW9CIuzMoi9aF/mssOggkiCR0FnkGsoaiX/+N8SNV/R3NXbon5fWpSvQucmDKuUg/t0kMKCxNnAIIIwLQGMbBixMORwjbDeHPKn51pBmFCsa2YVNobfoE6wb7tetkyPq7ArtJM15PA7CFMdOoeEHGhLegwasNOOM/mcw/718SAo0EZwrfGOw2dkXtRp6iH0ECIJIQVRZdcjYznRbWWF9Bk7JlLP9Rs3ypovv5Sdc+aILFykJrrduWCBCs0DEFZ1336rlgj5+VK8997N8zVhglv8HThQeW51anzUO/5CvDp9fpjvZYhGPecVrhPnEIp9n4NsSuZDSBDxZB6kG264Qd3wV155pbqh8XKdN2+e3HPPPfL888+rcUrEexjf7E+89gCka0JDL9pXrEH9XbvvLe/PRgjdYvl8wXo9T6ciL09kdM/2cvLwSjlmcBcpL7WXAMZs2GNia7PxYQ75izUnUyKDHb+BOHJy3TMdbmRHaGvjHZ43eIJwnhCygwYNUiFkiSb4hMEMTwtEA8Qw2hHOWfeg62QdZs+dX55z2sDFMTFOB0IC1x0CCOUcPHiwEk3wTurERBD7Tjwytia63Wsv6X7MMSJYwjShXubPD49rmh0J1WvaEZ4EGd6thQvVsuWNN3afU+dO0rt7lWzv3Elqu3SVUK+e0mngQMfPD+O9jGuI64fnkJOOglzA6j5HxwGTNxCSWVx/Ov3ud79TWW8eeeQR+cc//qF6n4AecA0BhW2I9wQ5vtlpr3UuhSuky/vgRfsylr22rl6+XV0vL03dJu8+9ZHUNjRGbdu7Y0s5eXg3OWlYpVS2jQ4VSoTdsKxkjG/zb2LN4+R3jNkEYwkU3FNaHGHcCtoAPuP/SA7Qv3//mOeq5wSDNw6/03P2aGPRrudOtzmIEmyr58OCBycRbjwX9KTAOKZVtkLUg87Up8MFnXhkkhWA+ZgnbOBAtWhCTU3SsGxZRDDVzW5OCLFr7drddbJ6jcjqNdJSRC1qX+XlshxheTqDHjxOvXtLXpxstH7wgmYr7NwkJPO4/qTCS+mxxx6Tq666St58882oeZCOPfZYGTp0qNuHJBn2JKQbp2MOcnEsVjq8D161r/nrdsiLX6+XV6Yul7XbG6K+a1UkckBFkZwwpJOMGzUo6ekC7IZlJSMCjb+JN4+T3baXCXEfL7RQ93CjPBBCet4cCBwIAIQpYsHvIRBiJVRA4g3sQ4850nMkwbughRe+hzDT2dWsPHd6Mt5Zs2YpkQR0UoB443zcfC7EM2gxx5duXzgHp/eJXU+esY3oiYjNbQYT0GIiWiytjzl69+/hzYNogmCCcJo5SyWI0K7apq1bZcfkyWrRQBwV9+0TDtELi6b+1VKATHo+8YJmK0Hu3CQkW3D1LYuX/yGHHCIXXnihGoNEMZRZgtqD53TMAcdi+b99rdlaJ69OW6ESLsxcuSX6OHkiA9vukiP7tJaDereTuh3bpaFhszKKkzW+7PbQahEIYx1eFAgFhEjp+d0SCUctjiAArOZxSkSyRnyqoipWaCHW6/sNnxEah886AQGiBPAbdJRBDMRLqIDv8Tv8xT4gwLRwgLcN26C+8RvtodECzQi+gyCCsIIghUjD77QHx0koZLJjl+IZtKneJ3YySVqlSsc1iDXnkGUbOWC0tDrk4Mj3Tdu3S92cuVI3a6bUz4bHabZKMx4KX9MQUoDPbPZAbZaXIr8r6lEVnqepOSFESXW1FHXq5Kg+c52gdm4Skk24ainj5YQ4bLwoiT8IYg+e0/ADhiv4s33V7myUd2euUqLo03lrpckwrghUtyuUI/qUS8/CjbJl3Xrp03EvKSrIl8Ikx5gYDULzhKTmHlrjtjoNOIxuGOkw6CF8YokUo0Gsw+ogjqzmcUpEMka8G56RWPeMnkRXlwf1CA+SztYGcaRFAQRPooQKSFqgPT167BF+qycIxnYQl3pOHqy3AsfXRqQWasZ6tvKwQPRiHQQvfp/K2KVEBm0q90kigWWuU5wXPHwIhzQmkTC2GTttJL9lSykbPkwt+jdrV62S+gULJG/JEimuqZGdSkDNkqaw5w40LFmqlq1vvx1ZV9C+fXO4H0RTOCEEvFjwaLlJUEKpg9q5SUg24frddswxx8g777wjF198sdu7JiSp8AOGK2QebbjU1dfL92t2yn8XbpN3Zq6RbfXNWbY0e7cvkyN6t5LehRtlYFUndW03bGhUxjHCuGAwJBNuEm9CUnP6bfO2OgwMngkY/fgMIzSeSDEaxPCsw1OSSIhZGUHJiHs3PCOx7hkID2N5IF5QZnxGuB3OFUD4wNuTKKECfo+6wdgdY9nwe4gtbANxBG8IFqx3Ul49r4/VtcdxIfZQZnTu4Xg4Pwg+vU8rozTWNfPSoHUyqTCOjc+4/rHajNM2soeg6tFDOu+/vzpn5alasSKSDKJ25vey/bvvRQzjmhrXr5ftn36qFk1eWZmUIvX4gAGRsU0lfftIfklJUnUUtFDqIHZuEpJNuP7UuO666+S0006Tc889V4kkzBOBHlgzeCESEot4hqPT8AOGK2T+Wv7365ny6rer5PPlDbIheroiaVtWJCcMrZAJwytlWPe26prOmrVNeWl0djMYtDBctWfCabhJvAlJdfpw3cbMGaSWLl2qwutgUGNdvHAvK08FyhprnpNEBl0y4j5VjynKhQUeM4geCFNd5xCJECzG8kBcoMwA9YRj4vxg3MVKqJDofPDOwPEgjFHnun6s3iWJ7vFYHhakj0cZcX2xDc5Rp6JGm8Bn8/VIdM2SMWhT9XqY61TvB3UHwWdVx07bSCJBVVRZqZbyH/xA1e2iOXOkuL5eWq1dq7xM+YsXS9ma1dK0dJnKngdC6DiYOlUtEQoL1bxPkbTj1c0pyAvaqKlw48JQapINBMXLmQu4flWQ3hXMnDlTnn766ZjbweBJF5iX6bDDDrP87osvvpDRo0enrSwkMYmMEKe9tQxXyMzDHhO3vjZ9hfznq8Uya3U4tXCYgjyRg3u1lR8e2FsO699Jigt3h9pgHzBOkeDFKDRgiJtDsexiZRDq5ABVVVVxt4VQgLGJc8WYlljhXpbz1XTurISUyspXW6t+i9/NmDEjIkBglMfqxU9G3KfiMTWPEdJZ+DAOCccFEEz4HkID9YDxPzDEUWak9k41M54+b6zXdZlIFMe7x2N5WLBPeD8gurDemAwC54LvzNfDbSPcDa+HVRvBddDlt2ozTtuIE0EV2Rb10bWrFA0ZorZFRsMu7drJmsmTpX72HJFFiyR/yWKpnztPQrW1ukLUOCcsMvHVyD4hvpq9TLsTQkg4OYeuN9xfmUr3TkguejmDjutX5Prrr/ftGKQrrrhCRo4cGbVO93wS/2DHCHHaW8twhfQ87Nes2yCLGlrLq9NXykdz10qjaWBRdYdiObRnS+nfYpvsN7i7VFV1sbxW8OzMQS90OKwLIBwKxmsyODEIzdvq8S0oV7xwr3jtFsYpzmfu3LnKqMM5YX8QH+hUimXQacMfnhvtncF28YQqhJfRc2JlIMcStlbnABGE89UvcJQH5f7uu+8iyRuwP/w/3oveyaS7yXRqxLrH43lYAK6Fzp6np6NABx4Ek/l6uD2e0YnginXNrOoqVhY7jVPh7eT+QVuBd7ampiYy0Sy2w/qFNTWyOj9fdvbpLcUDB6hj9u7ZU5qWL1eZ81RCiHAK8sZwqCNoWL5cLdve/2D3gcrLZWdlpdRXVEjT3j0kr1cvKQyH4DLzG/Ej9HLmuEC68cYbxa8gw96pp56a6WKQBDCpQnY97AtgWDeUybvfb5IvVyySHdHDiqSidbGM7BSSMVUtpG+XNmGju3kwfyy09wKGI8QBvBXoIUYSGBhfbvSyxzIIzdsChGOhHPD2xAr3itduUVcLFy5U4ghGOBadDhvnhh7/eEYnvDYQZ9gXhKJRjFgJVZwDwptxPLOoiteLaWcOJ4CJT+EFgpiAAYzfg3ieFKeT7rrVqRHPw4K61O0M56LPA+IIxzdfD7fHM9p91tnxqpvrKl7dORWg5jrUoa5ovwip079FObEd7lGd2h5e2gEDBkQSZ1iKwV69VGhdm+OPU7/BtrvWrGme3BYZ9JR4mqXmcIqwdasUz56tFk15UZHsqqyQelzfHnvLXvsMlXYxxq35AYZb5Ra0bbKLnPPpwdCAYUN3pn9hUoXsYMGarfL8rB3y1do8WbM9OmS2vLRQjh/aVU3kum9luZo82kmYmHGQvu41154lGFh2w5qMBggEjtEjFMsgNBuPMKRh9On9xAr3itdudeY8/MW5aW8UygdDUhvjVvtN1Oto9T28Tfp4ZlEFgxbXQ09cCoGj92dnDif8RosjlBX715O8xvOkZMo4iOdhgYG/YsUK5e3Q48wAhDjqduDAgVHXw+3xjHafdV70PDsVoHqOK53JEQtEm1GsoZxYsF90KuB9i3YCwal/h2uP0FK0O6tU8ECJ1s6d1VJ+6KGR9Y1btyrBtPLzL2TjlClShg6MZcskLxyyn4cxa4uXqEU++1zk6adlATxYe+8dDs8Lj20aMEAKMzwO2otwKwouf0PbJscF0s033xz3ezz4YGB069ZNxowZkzBm3U1+/OMfqxcLDB54k26//XYZMWJE2o5P7MGkCv56ERqPVduYL1+s2CmvTFsp05Y197YbxxUN6Vggp4/sISeP7ielRQWR75yGSxkH6UMo4S96omEg6vLoDGpOJgLFPu0YIGbjEb/D+KN45U+UKADPHR3ChfMx9vzDoxJrv4mEhdX3MPZhnOoMc9qgxncw/rUnB+tRj/idntQ00RxO2kjGNYKnAPuBGLNK651J4yDePYLvAK4JDH9cE5Rfz2+lQzm1J8mr8Yx2n3XJiMtY5+/02WGV1RFtAO0W94RRrJnLqcMU0V5Q12iTENc6Zb4eB2aXgvJyKRs5Ulp27y41++4jO4uKpFVJidRizNKixdJx21bJX7pUhelhHicFUtAvXKiWLW+8EdlXYefOKu14ycBmwYSlqFu3tA0R8ON4NuIttG2yC09C7PQDRo8d0JjX48GISWXvv/9+9cD0CjwoTjnlFDn22GNVA0UCiTvuuEOJpM8//1yGDWue58EKGBp4oBvBQ4h4B5Mq+OdFiGPNnDNP3vtuhXy6rF5mrA9Jo2m+op5t8mVU5zw5qFup9K3qEi5HQUq91cZB+vBc6Pl1kOAAvc84b/T8w0iPdd5uGiB2yh+v3eJv9+7dVdl1Jw3KhWyeffv2VUYxyotzMhutRmGB88UzCcJEe6CshIc2QPHZah4jbA/jFM9iPN9QDj3OKtEcTtrwxX5QDhi9ANfIHHKVqckv490jwPgdyow2hrpFOwHYVtehl+mX7T7rnIrLWOeP8V4Qvk6eHeb7CN42tD14iMxiLV45USY9R5Ve9GenRLUlpOmvqJDOw4ZJVfg8Qk1N0lBT0xyaN7s5PA+iCWF7kTpavVq2Yfn448i6/FatdosmZNDDRLe9ekmeByI+k+PZSGagbZPjAgkPz+OOO06JjssvvzzyQpo3b57cd9998u2338pzzz2nbt577rlHHn74YdVr+Yc//EG84sADD1SLZvz48Wos0tChQ+W3v/2tvG2Y0M7Mgw8+KDfddJNnZSPWMKlCZl+EMFqmLN0oT/5vnrw7e51sbx7PHqFLebGcMqK7jB/aRdrkNYfJwKDEi97KyE/lRaKNbhjy+IvzxjMDPf/xzjsTIV2x2i3W77fffur/EB4wFuGZ6d27t+qFjyd4tTGIsUpISa29NqgPfA+j15xKHKGI8IJYzWOE+sM+tcDS3jmrSU2t5nDSWQYBRBLKon9nDrny0vtixOwVwedY9wjQGfi0RxIL6gZ1hr/au5GMd8uph8bOs86puIz1jEDZMC7NybPDfB/hvsN9iN+a5yWLV048F9COIKyQBAOdBGhfViI0EYnaEiagLa6qUkvrY46O/G4X5mJDEojZEEzN8zbtXLwYDzz1fdO2bbLj66/VoskrKpLivn2avUxaNPWvloJWqY1tytR4NpJZaNvksEC69NJLpbq6Wv71r39FrR8+fLg8+uijcuaZZ8q1114rL7zwgjz22GOqN/Txxx/3VCBZgYfriSeeKC+99FLkYR3rfDCvkxEYASeddFKaSkpyJaTN7jG8fBEuXLNFnv58vrw1c70s3xK9vxaFeXJQVZns27Zexo3oLS3LymTnzi140yujx2nPtN0XifaSwHsEYxxhufrc45233+K9YXCPGjVKiSLjNU4keLUxCGGE9RjDBAFkTENtNcZGXw+joarnMcJvUR4cG8IWHiEzsYxdbUjr42F/EGu4NqhneJQwxgnCSqfw1m0gVePA6h4BZoGpx7dY3SN43mtPGP6vhT3KpsdboT6sJrr12rvrJFNdvGeQfkZA+OKc9Fg3nWTEybPDfB9pDyKEjVkExSun9lqi7eH32F+yIjTZtlTYoYO0OuRgtWgQileH1OKGZBBIMx4K10mooUHqZ85SS3PraKaoR1V4nqbdY5sKO3a0HaKXqfFshJAMCaT//ve/ctttt8X8fuzYsUogaRD2dvXVV0smQMgLHuJ6PhQrYPhhIblLOkLanBxDv/RgiMJI0QOhkw1T3byjQd6YsVJe/GaZfLM0elxRfp7IoPb5MrZHCxnbu6001O2Q+vqQrDGMR9DlgUEab06fVOtFp5xG7z8MW2N4mVcGiNvC2MqosyN4UQ5kjkOInh7LgWcWEinoBBbm/VoZqgC/RR3iGNobBa8C6tnY3hIZ5fp48Gphf/CEoR3qeZLQHiCe3LpXYt0jur6MAhP1hLq0MhZxPXHe2B51iDLi/8j6BwEZb6JbL727yWSqi4UOl4RIxj0DTw3OC2GETo1oq/sInaA4J9yH5nYRq5x+HX+R37KllA0bphZNCPMxLVy4WzTh76xZ0hQW0KBhyVK1bH3nnci6gvbtI4IJf0uqB0gxUpBbPJszNZ6NEJIhgYSX7Zdffik/+9nPLL+fNGlS1MMYLwWreT3SAdLuogcrU8cn2UGqRo8dA9vJMbAPGLSzZ8+OSqWL/9s16hoam+TjOWvlhW+WyX9nr5GdpoFFPfcqkoMqCmVER5HObVo0p2NevzbSC2wWQ/AgQKwh2YDRyNfhcckaAMZ6QWIXGADwOm/cuFF5UuBN0mFTbhsg6RrrlajnF+WYOnWqCl/WIUkQSTDsIUpiCeNYhirKj31CyGDsETqAsF+r9mb04tkZIwWDGW1Bh/lhG7fCP2PdIzoTmlFg4twgHiEOzMYi2iTaLuoNdYgy4v/oMINISoVUvLtuhs7qMEicH0QrhBHOWafnRnmcGNE4Dx1+qNuclTgKyviLPNRTv35qaTN+/O7U4ytXKqG0WzTNlF0rVkZ+17h+vWz/3//UEqG0VPJ79ZKifn2lzb7DpGzQICnp11fyw9cj3ePZCCH2cP3OOeuss+SBBx5QD9FLLrkk8sJB5iSM53nyySflsssui2z/4YcfqlSqXoIXNl7WRqZPny6vvvqqjBs3ztMEEST7SdbocWJgOzkGfouXIAwevFz1ZIwwsHDfxXrh4gX/bc1meXnqcnl1+grZsD16322KQ7Jv251y8vDu0qt98wB+lAH7g4GlzwEGJs4LxzJmTUMZjEY+yqnFUbICw1gvEIDauINRjzLpFNyxzjkVAyRdg54T9fyiHDpRDMoCox8iCe0Lf51m3UKdQFDrTIGJ2luidmwsP8qK8mGMGI6hU4i7Ef4Z6x5BOzULTLQTiHV8hzLhL7xDQJ+3PpdY81qlO8zJzdBZ3e7xe4Szod1gf2hH5vvZSSZIbIfOGdx32oObSqdBNqWlVqnHKyrUUn7EEZH1jZs2NYslHZ6H8U0LF4mEU48LJkaeOVPqZ86UNa9MbF5XUKCSP6jxTIYwvQKLUFcncHwLIe7h+pMI4XV4mN51111y9913R8SHTm+LbHI6BA89Uhi4bEyg4AVnnHGGeiHgODCskMXukUceUT2Mt956q6fHJpl7Sbq132SNHicGttNjoPcWAkkbuFrMWBlTyzfVyitTl8tLU2pkwdpw6tswJQUi+3ctliP7tZGOTRtkzer10mLnRgmFukTKgHvHWF6IHnNZYYSZe6atPE1OBYaxXnA9sT8cC9cSBriXg5Dthr6l2sYS9fxinZ67Cf/H9dBZ11AmrHPqpXPS3oztGHUOMTx37lx17gi1MpYf1waeLi3a3RwHEavMWiybBSYEvE5VrsdKwbOEsUU6Q2K8ea3SHebk9hgSnZVPi6NY97OTZxhCKdHWUH/YRyohhGg3evyvG2IrUxS0bSstR49Wi6aprk5WTJokyz/9nxSvWC7FNcslb8kSydPPjsZGqZ83Ty0y8dXI7yC+jBn0kFGvsGvXtKUeJ4TsxvWnEF42yFKHcUbIDrdkyZJIqtijjz5aJWswbnv99deL1yChwlNPPaVEG16S8CadfPLJcsMNN0Sy7JHM4FUYk5v7TdbocdIj7PQYiYyprXUN8tZ3q5QomrRwwx7jig7q00HGVJVK18bVUlXRLLJ27eosm9EbWlcXtwxWZYXBBMMT6+N5mqzOP57IMB4Lhi72o5MBeDEI2VgWHX4VL/TNjTaWSGRhHYQHrgvGS6JetVjB+mS8dE7am3HAP7ZFvejQTi2OdM+1Du2y2m+qYjJWmfViFpjxOiichCKZy60nmbX6bSphTm6PIXFjf+ZnmBbpqNNUQwhTEVt+J7+0VJp69ZItDQ2qzpvQidXYKOtnfCc9kH5/7ZrmbHqzZknjht3P56M8Dn0AAGmVSURBVIYVK9Sy7f0PIuvgVdKT2+qxTcU9e6owQEKId3h2hyHNd7z5hdLJFVdcoRbiP7wKY3J7DpxkjB4nPcLmtNY6YxvOw+6cMh06dpLvN4TkTx9OlXe/XyX1u6LT51Z3KZeTh1fKiftWSufWpco4mTNnU6R8OC5e5uhAgDFsPk+joYhwJfxGezb0dok8TebztzMw3ZzuG0JBj3NxcxAy9ouxPno8lZ5AFAP6cT2sQt+M6aKxHT47aWN2RJaeEwplwjG0Vw6eE3jBk/HSOWnT+prBc6RTg6N9aCFkPFas/YJUxaTdpBF2OijshiLF8npgf/BGwUuG+wXvOp36PNkwJyfXxI7YdGNMivkZpveDNo97I5UQwlTEVjawx/N/xw7Jr+ouZf37S6dw+1DjmtasVWOZjFn0GsJzkIHGzZtlx6RJatHklZRICcZIGRNC9O8v+S6EiRJCmmEXBMkobsbde7nfZIwepz24ejwHDDLE+cPYjmVIauMHHoTvV2yRt+Zvkfc/rZF12xZG7bNjeYmcuE+FnDy8mwysaB2zfDiWNnxRZyin8XhWhjy2iWfg2jl/O0JW1wu2xTqIFSRoQKiQm+GYEEcIHYPRAuEBMYD6iCUYIdiM6aL1VAHwpNnF7vlrQxfjaoznb9dL57RNGw1wiACcN1J3w3OEukBZINAgJs3HstovhG06xnO5HbJm5fXAopM8oP6RMASMHDky5baY6DmD64K6xJheXAuUC8Islth0+tyy8paZ59hCYhSdYl7f09guUZinm2IrG7Dz/FPjmjp3Ukv5oYdG1jdu3dosmMJeJoxxqscE9Q3NE9KF0FEyY4ZaDDtTnqVI2vFwmF5hu3bpPXFCAgIFEskobsfde71fJyTTg2vX87Vqc528Mq15XNHc1dui9lFalC9HD+qiRNFBvdtLYUF+3PKhfrTBhbEtMLjRO240uJLxyNk5f7vjfMziDPtA1jG3xiroRAgw1FBGHAeGG+qhb9++UlVVtcdvIFTM6aLxG6x3W8ibs8np73FsYztHGfAdBHayY6Ks6hvnB6NYZy9DedFWkvUeJNNh4TSk0TjBrk4iArEbK+uhnXLjmDhvtBM9ua5uOxAIKIdXCQf0+UOoRrzGHTpEzYflVGwa25NOeGIUSDDoIfjNc2wZQwyNc27Fuy5WgsFKbAUlLXUqHryC8nIpGzlSLZomtMX583eLJpUQYraax0kRCsnOhQvVsuWNN3aXo1OnZg+T8jQNVOKpqHt3jmsiJAEUSCSjeDV3g1/mhHDagxvPkNxev0ve/m6VykL32QJk5tr9O4zhPaBXe5kwrFLGDekqrUrshy1hQfgWUj5rMWk2uJI1cBOlibYjZNORTU4nQoBXRs8NBLERbyJLeHGs0kVjvV2szh/7wf4wv5CxrqwEAr7TRjqEAH4P412HwyUzJspc3xDO06ZNU+IP4Xw4BkQgvFkwcNOVgMBpO8A5w7iHh0fPGYbyw5i3WydWXg8Y9DqsEvUL9OS4wM2xlFbnr8fh6TTeei4sp95xc3tCu8eCuoxVv1ahfXavi5VgMIotPWGvVSr5bMXNrHL5SHwzcKBaNKGmJmmoqYmE5tUhg97MWbIrnPUS7FqzRrZh+fjj3ftq1UolgDCObSrp3VvyAuK9I8QNsvvpQ7Ier+ZuyNY5IcwG2ZatW2XO5nx58b/L5eMFM6W2IZw6NkyfTq2UKMJS0Ta5+HM74icVAzdez78dIetVGKYRnQgBYgBGIgxeHAseh1gCwI100ebz12Nc4JEwh1haGaJYh+8QYgcPBgx3tHl4N5IVkub6Rl2gDNgnpm2Ad0qLSLsCwIuEAXbagTa+cZxY4j+ZckN0LTOME8E1gaBF/eB7r0S8Hv+nhTDuLfwfotypd9zcnpB9EO0foZNW9RvrPkY7sHtdrASD7kBJx5xjQQMT0BZXVaml9TFHR9bvWreu2dMEwRSet2knEmaFe9Watm2THV9/rZYIRUVS0qdPs2Cqrg6nIK+WAs4TSXIUPnlIxvFq7gY7k1z6DW2QfT1/hXwybbN8tTokm+rxUquLbNO+ZbGcsE+FnDK8mwyubJ1yqIQd8ZOKgasNMfS8w5jC/mEMwdCDByKWkNXXDQY5voOhro1Dt8MldSIEACMRIkcPvo83xirVdNFmIQ+PAMQR6gmix2hoxxIIEFSoR3yH30LIpCIkze0B9a7nEcI1xPnpcThuJVhIplzGdhAraUGq4tqq3NjHZ599pjxR2CfqG8eHaNTzUhmPYzd7n51shljgacExca31nFjJeMet6gboDIX6uuupOmJ5itBO0+0dJPEpRIfAIQerRYNQvLo5c3eLplmzpR5jLvW90NCg1mNpbgHNFFVVRQkmhOkVdurIED0SeFy3EjE57Lnnnuv53EaE2CGbeibXbK2TV6etkBe/WSOzVtVGfVdcmC9HDuwsJw+rlDH9OkpRjHFFyWBH/KRi4GJ7hDbB2NJZ0PB54cKFkWQQZiPIeN2wLQbD6/AuCBEcG8LAKgwtmVTSyZyfW15K4/njfCA+rJIuJBKybo27M7cHGMioc22M4xo69ZSZz9PNdor6j3WPu1En5nKjjenQMp1qHW0bIXaoG4DjoK6AneeP3WyG+vzRNhASi+Mj1NGcVMUO5rrBdYYIxjEQogmwfwgmnH8ssQnvFY6dbu+gV2TT5LVOyG/ZUsqGD1OLJgRRtGhRRDDphBBNYZEMGpYuVcvWd9+NrCto3z4imtT4puoBUrx3D+XRIiQouH7XP/3002oSVsR+n3POOWrBIGdCMoHfeyZrdzbKuzMxX9Fy+XTeWmkyjCsC+/dsp0QRxhW1aVHkSRnsGvrJGrg6UxUMLxjVeqA/jEmdmS7RdYMRht9rwwtGGwxKozGJZ46dweLx6iGZFPButqN4Bn0iIZuMly+WMWhsDzD+58yZE8ngpgfXp3sOuVjt1NxW9HggiGqEixm3SXUsohYyCGeEx0hnksM4IIgLhN5pcQHhBMGLtp8oDbvTbIZuGO9W7aWiokI2bNigPIVaNKFs2ktk1TZxTyNhilfewXSSTR1qbpCHLIhIF96vn7Q58US1ToVurlihhJIa26Sy6c2UXStWRn7XuH69bP/sM7VE9lVW1rwvg6eppF9fyS8pyci5EZIqrt/xeDm8+uqr8uSTT8qtt94qf/zjH2XEiBFy3nnnyRlnnBGYDDUkO/BTz6SmqSkkkxatV6LorRkrZfvO6HFFPTu0VKLopGGV0r1dWVaHOQLc8zAW8WxQaW2LilT4Gv4f6zqYrxt6smHwotccZYXRZjYmYdwgHC+WkZkNPcPxRE4iA9mpAZ3IGDS2BxjISNSgU4zvu+++kXl/0olVOzW2FRh3EEja8wgRjjro3bv3HnN2OQX1NXv2bOX5xH5QDrQ3hO5CiBnFBcQSxAW+x3Hh5Yn3/HGazdANrNoL7jFk6UObQzlQn7ocOL94bdML76CVveDlfez3DrV0oJ7RlZVqKT/iiMj6RkwiHkk9PlPqEaK3cKFIY/P7K7Rjh9ROm6aWCAir7tUznAyiOYMePE8FDjJJEpIpXLcO0FN22mmnqQW9af/5z3/kqaeeUhO1XnXVVXLkkUcqsTR+/PiMvGBJbuF1z6STl/X8NVuVKHpl6nJZsXn3mCLQtqxIThiK+YoqZd/ubQMV3436wOB1GKs4LxiPeu6gWNch3nWLZUzCuItlZNrtGfZaRCXavx0RlGgCWLuGnF1jEGXGAH5cL+39w+d09qrHqzdjW9EJLvAZIlyLaQi8VAxc3X4gjlBHEOxY4DmBCOrWrZvqBDCLC5QFdZbo+ZMpD4qTyZ29THxjd99ee3j82KHmFyBqWo4erRZNU12d1M+bF0k5rjxOc+ZIqDYcIt7YKPXz5qtly6uvRX5XWNG1WTAZwvQKu3YN1HuPZD+evt3wkLn44ovVglCDa665Rp5//nl56623lJF06qmnKuE0dOhQL4tBchg3031bTaKYKKRr3bZ6eW36CiWMZiw3Dn0VKSrIkyOqO8uE4ZVyWP9OapxRUIERpg1w9Ownug7xrhuuQaxQHxioVsadHTHgtfFld//GiXGxHf564e2KJzT1pJ8w7uH5wwS6OD5ERyrz7nhRb8a2grpCSBu8HRAwKL8bBq5uP+gAhBBCmSD49SS6uh7M7RLboiMQx4/3/PHLtASJyuGlp9nOvr328Pgl1C9byC8tlRZDhqhFE2pslJ1Lloa9TLvHNjVu2BDZBuF627B88EFkXUGbNs2eJoNowsS3eT7z8pPcwfOWh1So8CBh+f7771VPHkLt8MBBGN5jjz0m9913n0ruQLIXv4YvudXraWWkYYGxbx5f0KJVa5mxQeTlKcvlo7lrpdE0sGh4VVs1ievxQ7tK27LcePE6vQ7xto9lxGEMUqzB4giDStQz7LXx5cRjk45xEFbGIPavxZEOUUO59aSwGHODzH0QSenqVbdTb+hwg7CD1wbl1ONn3DJwtZhEKB2OgesBzxE8VvCOoiyoO3O7RF2hXRonVo01vi/e/ZGu56vfp0fw2sOTbqHq1/dmKuTpsLpePUWOO273uKY1a6V+dni+pvC8TQ2GVPmNmKh80iS1RPZVUiIlGNdkzKLXv7/kl6Un9JzkNp7ciXjA6NA6pEPFDX/cccfJLbfcov7iRQf+8pe/yFlnnSU333wzBVIW4/eBrW70eloZaQif0eMLIIGW7CiSN2dulqkfTJdtO5szWGm6t2shE4Z1U/MVYYxRLpLoOlgZC7EmAI1lxMVab6dn2Gvjy+7+0zUOwsoYhLdDi34IDITSQXigLFhQViRqgNGYrl71ePVmfvbgWsOTCC9SsgauVTvUbUWPg0MdQBwhUQPEo558Nlb7szPdQKz7I93PVy+9RH738KRTIPr9ven6uKbOndTSauzYyPrGrVulfs4cQzKIWVI/f75KOQ5C9fVSN2OGWgw7k+K9927OnocxTQjVGzhACtu1y8SpkQDj+l04YcIEFUKHG37UqFHKO3TmmWeql5sZvIQRZvfKK6+4XQySRnJhYKuVkYbQo3X1+fLR12vl8+UNsmZ7dLKF8tJCOX4o5iuqlP16NP/OTxgNQXgE0MuX6kD2eMeIt1+nxkIsIy7Wejs9w14bX3b377ZQi3UNYg3Sx3WApx8JB/Q8ODqlN5I0AISOOe1VT7a3PF69WT17IFoQCogQO6dtOVY7hBcI7QXCaN68ecqzhmOiXpAUAuv18y5ZkROrfnLh+eonD0+6BCKvq0hBebmUjRihFg3mZYJIap7odndCCMzj1LxBSHYuWqQWefPN3detU6do0TSgWoq6dWPqceIfgTR16lQ11giJGOyk90bShg8//NDtYpA0kgsDW41GWlNRC/lg7kb5eGmJLNwMT9HuhAsFeSKH9u8op+zXXQ6v7iSlRQXiR8zzDMHI09cOXgQ3ejKdiB43jIV4BridnmGvjS+7+3dTqCW6BvEG6UM0Az0Pkhb4qEOElTlpG6kIhHj1ZhU6CREHcVRVVeW4vuK1Q5QVZYQYgjBCvcFTpdN9x3veJWrf8eonkQctaCFa2RwC6IRceG8mQx482QPhFRoYWRdqapKGmppIaF7zZLezZVc4pT7A/7dh+fjjyLr8Vq2kpLp/VEKIkt691TEISYTrTxWEGjgBPX1jDS5Xkn3kwsDW8rbtZF5dS3lzyjqZvmajNJrmK6ru1EKOG9hBTj+gj3Ru4//4aKPBhpczwgXhLcAYCyeD8OMZaE5ET6rGgh0D3E4GOC+NL7v7d1OoORWexmNDOMNTBIGE8urJSaurqx33sKciEFINnXRCvHaI40F4Yc4j/B9lRhQEOhcgmOIdM1H7jlc/sc4R92mqIVrZKLD8HALohFx4b7oFJqAtrqpSS+tjjo6s37V+fVTacYinnbBBQ80v6KZt26T262/UEqGoSEr69FHeJuPYpoJWrTJxasTHuP4kxEMbyRcwtsiK5557Tn74wx+q+G0SDPySgcltIBimLN2oMtC9/u1K2VzbHBetqWhTqjLQYWxRn07Z9XA1GmwIpYIRjPPFfQmj2I44SWTUOhE9qRoLThIgJEqz7aXxZWf/bgo1p8LTfGy0C4RdIiEBfq/HhTktSyoCQR8v2dBJJyRqh/iL+wPHhPdIp65HR1+8Yybab7z6iTX/kJ6jyInX1dj+cW3h+TLeD0EdA+NHgvreTCeF7dtLq4MPUoumaccOlWo8knZ89mypnztXjWdSwOuLsU6zZokxr2xRVVV0MogBA6WwU/N8fSQ3cf0piIc2lljAAGODCxZBCnsAS9Zvl5enLlfLkvU7or5rVVIoxw7pokTRqJ7tJD8/Ox+eRoNNG8G4b9HBYVecJDJqnYieVI0FO2FIOn01PCNYl26D0ElvvVtCTdc3DHlcYxUi2tQUCZ+ze2xzuJpTz0MqAiER2BbXVHtA0W6SvZ6J2iH+IjMdgLhA6CHE0bBhw+IeM9F+49UP9osxUKhztGF4q/AZYyCd1Jm5QwML9odrjbLk8timTBC096ZfQIa7smHD1KIJ7dqlJrU1iiZ4m5o275ZIDUuXqmXru+9G1hW0b7+HaCruUaUy9ZHg48mdGEsA4SX9zjvvsIckgGR72MPmHQ3y+owVKjX310s2Rn1XkJ8nh/TtoFJzHzmgs7Qozv6HozmUSo8xQUYu/N+OOElk1OrwIITvwZhDzzuMS6v9pmos2AlDwsTVMGoRJgUDE8ahlwahOQkG6jvdvfWoQ3h/Zs2apZ6/QHtAkhUSyWTfSlYgQLzrtOPmNqHLgTFBuK7YFm0ZCSaSrVM7E/Um004T/S5e/eA8EbqO64jf4h7F75Da3InX1dyhgbkJ9ZxiEJd6/Fauj4FJJ9n+3swWMJdSKdKF9+snbcaP3516fOXK5jFN4fA8hOphjiZN4/r1sv2zz9QS2VdZmdpPczKI5vmakIo8v6QkI+dGvMOVN/NNN92kUnUDGErnnHOOWqxAo8TksIRkmp27muTjuWvl5ak18v7MNbKzMTo196CK1iot9/h9K6RTeakECbPBlkwWu3i93tqog8GKfeqB/nquIreNhVgGpjEMyRgapSfx9GpQtFlEYCA/FpyfW5nI7Hhx8BnnCa8Dxs7AqMa1wO8gJJI5djIJNZIRCFgXLwQM6yGO9DWFcIAIBiNHjoyZLdFOnSUaq2acXNgNr2C8+oFAtKpv3HNo43a9rsYODdyTaI/oJEAd4j7F/nWnBvGGbBzzFVRU6vGKCrWUH3FEZH3jpk1hD9PusU3wPkl4WEhoxw6pnTZNLRH03E9qXNOA5oluMa6pbdtMnBpxCVfuzP33318uvfRSZYw8+OCDKjNdv3799miMLVu2lP32209OPvlkNw5LiGPQRqfXbJaXp9TIq9NXyMYd0eOKurQulROHVcjJw7pJ/y7lkRfa0o3Be6Gl2nsZr9dbG9EYxI55omDUwSjA9l70mMYyMI1ZzmAUQijAkMZ19XJQtDbeYbjD8IShjwUhYG6l7rbrxdGiF9cGx9aiMdljJxsO51QgIBwb52glxHBtUb/Lly9X2+HdotsdPJb4az6WkzqzY8i6PY9NrPrR9Q2hCy8g2hTaEv468WYZOzRQdniLcD+g4wL3BK4ljs8xMN6QS/MeZTMQNS1Hj1aLpqmuTurnIfX4zOa5miCe5syRUG1t8waYE23efLVsefW1yO8KK7pGZdCDt6mwa1cOM8kSXLkrx40bpxaAh+7PfvYzNQcSIX6hZuMOeWXqcnlp6nJZuDY8n0KYsuICOWZwFzlleDcZ3au9CqkDfKHFx2jUoica9z4EkR7vk+4UtlYGptnLhfKhtxwGJspmd5yT055fHb6Hc4cBD2NWHxeGbqrizIkXx+1sWW7tL9HEwAgBs2pDeq4miF9kkIMnBF4xAIMfgtCqnTlJ5GFMgY/PCMuE0DeGJcbaH7x08Mgmait225QehwSPrPb6oD7gWerevbvtDgdjhwaOi+NjbBnqFW0UbTOZBBzEHpz3KHvJLy2VFkMGq0UTamyUnUuWNnuZ9NimWbOkccOGyDYI19uG5YMPIusK2rQJe5p2i6binj1VGCDxF65fkUcffdTtXRKSFFvrGuStGavkxSk18uWi3Q8tAA10UB+MK6qUowd1kbLiPW8FvtASo+epgUGJMRLo1TcOLs90ClujUQjPAsQJjFwYgjCm7XgEkxHKEIswZmE8w7jG9jBqtXBKNWOVEy+O29my3NifnTqNJcRQt2hrEDYQMDU1Neoz6gLXF4tVO7NbZ/q+RzngbUOWR3yGgED54mVpRPtfuHBhRKTFaitO2hTqFV4eCEaUB6GSaFc4dytPmZ0ODbRJCEzUFQQd6hbnoScEJu7DeY+CRZ4Oq+vVU+S443aPa1qzVupnG8c1zVLJHzSNmzfLjkmT1BLZV0mJGscUlRCif3+VcIJksUB6/PHH1d9zzz1XvST050RgIllC3GZXY5N8Om+d8hS9+/0qqd8VPa6ouku5EkUn7lspnVvHH1fEF5o9rISkDmNDD3+iBA1+zxSVjFBGyBe8VfBsICwKx8X28EIg61mq4ZpOvDhuZ8tKV53GEmKoVwgRo0GPNqbHW8VqZ3brTN/3+trhGPAI4XOiLI069TfKFq+tOGlT2jOK73F++Izjae+T02unw+hwXkwxnT7c9uQSn45r6txJLa0M83s2btvW7GXSogkT3c6br1KOA6Qgr5sxQy2GnUnx3ntL6YDqqLFNSG1OskQgnX/++apRnHnmmepGx+dEYHsKJOIW6LX5fsUWNV8RxhWt2xae7yBMx/ISOXGfCpWFbmBFa9v75QvNHmYhCcMLvd3o9QZ2EjT4eaxVMkIZdQBjXgsI/beystKVMVhOvThuZ8tKR53GEmI685o2NLVo6tatW8T4t2pndutM3/cQ9xA8aLtalMArqMtotT8IGHQOYNt4bcVpm0J7wrYQVG4Y10wxnX4471Hugkloy0aMUIsmhOQ9CxZEZdDD2Kam7eEhAKGQ7Fy0SC3y5luR3xV26rQ7g15YNBV166Ym0yXukrK1sggXL/xSMX4mxGtWba6TV6Ytl5em1Mjc1duivistylehcxBFB/VuL4UF+Z680JLJShS0TEZmIYnefBiS7dq1Uwar1wkavCYZoazny9FGr93U6Xbbip8M3GTas906tRJiVvelMfQtFnbrTO9/wYIFqh2jAwbrIPSNZbTaH+oCv0t0Xk7blBfGNVNMpxc/3bMk8+QVF0fShItMUOtCTU3SUFMTlUEPGfV2rV4d+d2uNWvUsv3jTyLr8jG+trp/VEKIkt691TFI8qR8Z/bo0SPuZ0LcZHv9Lnn7u1VqEtfPFqxDJ0sETL81umd7FUI3bkhXNamrly+0ZMamZDLxg1fCzGy8wahEj75bGdvSjbmecP2dpFOOl0Yd4z6cCGljsgB4M+Ch6NmzZ2QwfaYFZ7LtWc/PhMQDCJfTHkY7Bn8qhqadOtP7h9cG7Rchc/AKoU2bw/fM+9PZERO1lWQ8gDSusx8/3LPEv8ALVFxVpZbWRx8VWb9r/XollOrhaQpPdKs8S2EDqGnbNqn9+hu1RCgqkpI+fZoFkxJizaF68GYRe7hukf3617+Ws846S80sTogbNDaF5PMF61QIHcRRbUPzfASaPp1aKVF00r6VUtG2RdpeaMmMTclU4gcvhZnZeINBiYQIOtTI3DvuZw+aVT3BcIXxnszkoLimyda9bitaXOE38M6hflGnfkgPnGp7xnkZ/6bb0IzXFpFQAyJJj0eyEyaK77AN9qt/b/WbZAQPjWtCchOMO2p10EFq0TTt2KFSjUfSjkNAzZ2rxjMpGhqUoMKy+eWXI78r6t49SjCp1OPhzkwSjetv1/vuu0/uvPNONRgZ45JOP/10GTJkiNuHITnA7FXN44omTlsuq7dEjytq17JYxu9ToVJzD65sHffm9sogT2ZsSqYSPyAlMEJ/cEw9WWgqwixeimZ8h/q16h33e+p0oyiBxwAGP8qLOsP4oXSKCN1WUA6dLADXD0s6RLUdkm3PqBMsCMPUIjqVyWuTIZ6HDiQzj5eeIBneMWyPTgIthpxOSEsIIbFAhruyYcPUognt2qU8S81jmnZn0WvavDmyTcOyZWrZ+u67kXUF7drtDs0Li6biHj1Upr5cxnWLBD2cL7/8sjz33HNy2223yZ///Geprq6OiKX+/fu7fUgSINZsrZNXp62QF6csl1krt0R9V1yYL0cO6CwThlXK2P4dpcjGuCIvDfJkxqZkIvED6gBjA7XBh2MizS8M2mSEWaI6jdc7DqGWCQ+aXVBeGMvwaECU4FzxGambjXPgpENEGNsKygFRi3qDWEOZkr12bnYWJNuejXWClNi6XGiX6fIoxvPQoRyo42SEn5/bt1f42StMSK6AuZRK+vZVS5vx43enHl+5Mko0wavUsGJF5HeYu2n755+rJbKvFi2ktF8/KRm4OxkE9os5oXIF159geHkjQx0WvHBefPFF+c9//iO33HKL3HjjjcqbBLF07bXXun1okqXU7myUd2euUt6iT+etlSZTtM3+e7eLjCtq06LI0b69NFiSGTidiUxGqAPM4YJjIUwID0yEwKH3PhlhZqdOY/WO+z11OuoDngRcI3hsIEowiSaMZpy3zqLmRUKCWG0FYhTGOsqBFOGot2REtZPOArsGb7LtWZdfhwvqY2GMFuo9HR7FeB463C/46/SaIaxu48aNyhMF4Yff4l7T7TuIQsLvXmFCJNdTj1dUqKX8iCMi6xs3bZK62eEQPczbNHOW1C9cKNLYPIQhVFsrtdOnqyWCnvvJkEEPnqeCtm0liHj69ILBdMEFF6gFIQdPPPGE3HDDDfL73/+eAinHaWoKyaRF65UoemvGStm+M3pcUc8OLZWnCEv3dslPlualQZ7sOIJ0D7bGcSBmcBztFYEI0L316ahTbRjq0COkUNYTVPppLhDUB4xbeBLUi6WoKCJKUFZ44mDwwvjVc+7YSUiQjIjQbQX1BA8Wrh3KAaGUjKi221ngxOBNtj0bxR/qGmWqwAu8vDxtHpd4HjqExmFCVtwndq8Z9gEPKcSVFtgQX3ri2qAKiVz1mhF3CWLngZ+BqGk5epRaNE319VI/d15zBr3Z4Xmb5syR0I4dzRs0Nqr5m7BsefW1yO8KK7o2C6YBA6TV2DHSYuhQCQKetz68YN566y0Vcvfaa6+ph2f37t29PizxKfNWb1WTuE6culxWbK6L+q5tWZGcMLRCJgyvlGHd27oyaNCtkLZ46ZadGgHpHnugPUcIJYLRhzqAgY+xFcm8gJzWqXmsB3rZ8Re/Szb9tVegPjAGRYsRGMv4i+cYxnDBAIYHDvUI4xYkMgRTzbqGsU+oo1SNB7vC1qnBm+w9gDpBO0DWQ2Q81GGf6fIoxvPQoV0iIyvaQbxkC+Z6w35wHmgvEFn4rNt3NguJeMar373CxP8EtfMg28gvKZEWQwarRRNqbJSdS5c2Z9AzjGtqXL8+ss2uFStlG5b//lfyioookBI19nfffVeJookTJ6qXDHpaf/zjH8sZZ5whBx54YNzfk2CBiVsxrgipuWcs3z1YEBQV5MkR1Z2VKDqsfyc1zsgLIwiphNFTjV5iGEEwSlJ9eMNgwl+/93gZPRgoa8uWLZXRhiXV/Vn1rpuNKRieRsMQx8fv8Zt4E3tmCj13kxZ0WmDCM6DnxMG5wQjGOjuGYDwRYafn1A1RbVfYpsvg1eeEOoR41166dHkU43nocA3g5bSTbEFfv2XLlqlzQQcgRBXW47NOyZ6tQiKR8Wq3XdFDQGKRzZ0HQScPYXU9e6ql9bHHRtY3YL5Do2iaPUsalixVYXdBwXWrBOF0r7zyiorDxksGKb8x5mjMmDFMI5hD1DU0ynszVytR9PHctSpVt5HhVW1lwvBucsLQrtK2zB1vTry0u2iPMHjgOYHRi0xTdnunrB7eEFzYpzZ6/Nzj5XZYX7z9WRlTEKXGAe/oYYcBqSeS9QPmNmVO643y4pzgSdDzPMGghnBKxZg31xfqEPtEveBYyVynWPeH3VA/LxOJuDHHlJvE8tDpCV+dhCPieaBFNNoP2gzC67Zv3y5Lly5V7QXHS2eClnQYr3Yn1KaHgMQiWzsPcpmiTp3U0mrs2Mi6xm3bAjU5reuWHMTRhAkTlKfo8MMPVz2DJDfAuKLJizeocUVvzlgpW+t3RX3fvV0LmTCsmxpXhDFGyZDMi1Z7efDC1oaJk94pq4c3vFEQXNhnNvR4uR3WF2t/VsYUDEcYjX41DGPNfWRsUwitg7ELAxgCCdcebQHeyFSMeWN9QThCuMOQxjrUn1PRnej+sCOUvUokEiutdlVVlSoXPDeZ8sSa2zMEjdNwRIgiXD+0kSVLlqhzwzlhzBo6VHAMfEb7gWhyWq+Z8sAkMl6N7QqiEOeGDgSd1ATfu+0hoDcqWGQiuytxn4KATULr+tMVDz2/9aATb1m4dpvyFEEYLd9UG/VdeWmhHD+0QmWhG9Gj+QWbCsm8aFPtnbJ6eMMrorNUsccrfl1DTDgd8J4OA0nvA+KnpqYm4s2walPYP8KEAQxgeHcgjjAhdirPO2N9Yb+oI4hJGNdo406NyFjeTpwrBFgmE4nES6vdu3dv17yvbrSNZMMRtUiCVwptBOIIYgHzO2EfEEdoN3avhR88MHbqQnsoUUaEJaLNGcvopoeA3qjgkYnsroQkwvUnK8VRbrBx+0557dsVShRNW9Y8WF1TmJ8nh/bvpETR4dWdpLTIPS9iMi/aVHunrB7eMHJ0ogH2eMWva4SMIfGBHoeRqsHthoFk3IdOg47fosxWbcor0WDOpIaxLjCsIXCSMSLN9weEKcbGQKRiv3bryotEIumY+NYt49l4zxsFJjxAeiJkq/aO64e6xzgkHB+/hTjSzyp4V7AfeM2yZYyGXeM1Xhnd9BBwvErwyER2V0ISkXLrg+GD3vTZs2erByM+J/IS4HvEd5Pson5Xo3w4e42axPWjOWukoTF6XNE+3drIycO7yfFDu0r7ViWelCGZF22qvVNWD2/8Hz3Fxn1ifzCeEJ6Tqw/4WHWtB6q7gRsGknEfyKAGwxbrICiMA8+9Fg3G+tJz70BAJGtEmu8PHc4WzzuWLryY+NYr41nf86hDpHbHtUEbgfiC2NSCK96zBWVxK3lBJsdo2DVe45URKdzd8hBwvEowSXd2V0ISkbLFMnbsWPUwxMvO+JkEA4TCTFm6UXmKXv92pWyubYj6vrJtCzlpWIUaW9Snk/fxp8mIHTd6p6we3sZ9ImwI5YLw93vSBi9Jta7TZSwa94E2Do8gJilFSBSOma7wDvP4DYT7QSygHMkYkeasjTDq9fpMh4LGSquN+kd5EJqVaseCm8azTuOPUFokFLEavxivvbuZvCDTYzTsGK/xyuimhyDTdWGG46EICSYpW26PPfZY3M8kO1m6focaV/Ty1BpZvD48SViYViWFcuyQLkoUjerZTvLz0yeIk33RetE7ZdwnDFsY9kxTmnxdJzIW3Zxs1mxkYYHxip5ujDVKp/fPWF8IzUpl/Iw5ayNEAgQIwuywHoIpU8akVVptlA1iEH/1eKRUOhbQUYe6w5gyPYdVKudrR3DFau92nlV2PV7ZMEYjURndegb7qS44HoqQ4OK6BfD444+rlN54GVuB7D4ff/yxnHfeeW4fmqTI5h0N8saMlUoUTV68Meq7gvw8OaRvBxVCd+SAztKiOHPZCf3oimfYR+rEMxb1AHC3Jpu1MrJ0ogBdFrdi4Z2mpU+1bRuzNkJw6cxq+It6zaQxiXqA5wiTFEMU4bNOkIGxOamEAOp5h9A2ILR05sHq6uqkzzdVb0Wi62n3uZENYzTsljFVj4uf6oLjoQgJLq4/UTAZ7BNPPBFTIE2aNEltQ4HkD3bualLzFEEUvT9zjexsbIr6flBFa5WWe/y+FdKpvDRj5fQ7fgv7yEbiGYtmQyTVyWZjGVkgUciTEwMvEz3MVpnV0DGFzGoQTInqyouQoVip1CFg4EGCOEo1JA5lxoL2gHFluAcRHodrnKyR7rW3wslzw6l4zkToV6IyunU/+KWTjB1jhAQX15+W6BWMB7L4+KnXKxfBNfq2ZrO8NKVGXvt2pWzYHm2MdGldKicOq5CTh3WT/l3KM1bObMJPYR/ZSjxj0WyIuDHZrJWRBa9DvJAnpwZeJnqYzfWIetKZ1RId0+n52TXCY9UDMry51bGg2wjuO7QR1DGOAY9VsufotbciHXNO+WlMZNA8LuwYyzwcA0a8wpUn5bfffivTpk2LfP70009VozWDB/RDDz0k/fr1c+OwxCE1G3fIxGkr5MUpNbJw7fao78qKC+SYwV3klOHdZHSv9iqkjkhWhn1kK25kBPO6RxjlQAIEzFcEIw/z2uCz2cDTL22M/cF4oB49eqQtSUIqRrcTA9aJER6rXuEJxLZuCAS7xqpTI91Lb4Xbzw3z3F7w0CEEFePRkEAG9dKtWzfJFEHzuLBjLLP4tSOABANXWtDLL78sN910k/o/HnoPP/ywWqzAiwDjlEh62FrXIG/NWKVE0ZeLNkR9Bw10UB+MK6qUowd1kbJiPlBSwS9hH9kMBtbD44HnCIwPnSksXYZIIiMbZcPxUT54JpC9EBhDio0vbYgjjItBUgJ4S5AkAWFf+nde9JimYnQ7MWCdCI1Y9Yq5kODZSkUg6PrAtcHvMTYNkQqx2ki8c/RjWJpdzHN74X7BWCwkrkBbhZhHynI3U+7nuseFHWOZJWgeSeIvXHlKXnTRRXL88cer0K39999fbr75Zhk3blzUNngRobcQA6Gp7L1lV2OTfDpvnbw0dbm8+/0qqd8VPa6ouku5EkUn7lspnVtzXBHxZ08ger69METiGcGJhBgMbxiaeCEjzA8GKLxJWG/10oZwgjhCj75O3Y1efT1+ymn57faYJmt0a2MVHgcIOfzFc11P45CsmIpXr6kIBHN9YF9oN9gfxJdVG9Fpp3FNcI10PeIcY9UtSLdwcop5bi+UHW0OYaiY3wvXEWJdj9PyGqv7LIgeF3aMZY6geSSJv3DlCY+0uFjAhx9+KAMHDlTzW5D0gZff9yu2qPmKXp2+QtZtq4/6vmN5iZy4T4XKQjewojUvDcm6nkA3DJFEAiNe8gYY1BBCWjBAHGF7/B+dP7Fe2vAcIYU1PiONOLbH+WK90/PxuscU54o06pj4G8Y0gBDE/82eBydiyquedqv6wP4hjmLVB8oAjwpCI3VZkMAC66zq1jj/kZMwnnR7o8xze8Ebi+uGdZh8WM+FlQ7jMd59xlBk4hZB80gSf+H603rIkCEq9jmWQJoxY4aKgcZDnKTOys218srUFSoL3dzV26K+Ky3KV6FzyEJ3cJ8OUliwp+FCSK70BMJog+EPjw68DOhlR8hbIiFmDpkDMEDR843vdKhYrJe2DveCOMJx8Ntkz83resK5o4wwqFEH2H8sQedETOl9u+25SKY+YKgjxBFl0QlA8BnX1mpfOHeckxNRmomxEeZ2h2sBkQSPJdq6DrVLh/GYSMgz/Im4QRA9ksQ/uP6kvvLKK2XOnDkqnbcVF198sQwYMED++c9/un3onKF+V6O8Nr15vqLPF6wXY+LAvDyR0T3by4ThlTJucBcpLy3KZFEJ8UVPoDZYIY7wIoXxqEUOwpDiGdTmkDk9rxA8JlbzCplf2vCuwEiFgYpjpnJu6egxhRGtPQ7YP0II9fxCyYopr0imPvRYI0Q96Il0cZ3w12pfWO9UhGVibIS53eG69OzZU4k/hIWm03gMWugTM6X5E44BI1klkP773//KJZdcEvP7E044QWWyI8kDQXTza9/LlrrdmQL7dGqlPEUnDauUyra7e7MJyQaMxh1Cn2CQQMTAWMf/7aaYBlZhTdpghdEIsYLf4ngA3qREBrV5XiGIpFjzCplf2jBQcSxdhlQM1XT0mOoxOjhHiCN42XDeCDHE+RrPVYspnVo7Fe9YMiRTH7FEFbws8ASa9wUvDMIp7YowtC3UFa439ok6SYdAsDIW8X89cXA6x04FKfSJmdL8DceAEa9w/UmJ3th4Lycdj0+Sp7SoQI7fp0Le/m6VjFfjiiplSGUbZaAQko1o4w7GFDJtwWMBwxxeH3hqzKFJVkYLwr3MAkmHNWmRow1WGLw4BgxipOB2YlCjXInmFTK/tGFo49mXqqGajh5T7A+iEXWEukIdQQQhO5x5gH+mDeFk6iOWqNKL1fgztEG9vU4EAY8ahJDxeLpdIsxct2GEm6Nu0lEvVsZiJsLZghT6xExphOQmrgskhC1MnTo15vfffPMNEzi4wK+P7i83jR8kRRxXRAKCTpKAkDRk3jIOjjeHJlkZLRBW6CTAZ3NYkzZOYdRqbweM3F69eiUcF+KGsedmL6fXPaZ6/zhXeNtQx7gWVqGIfjCEndZHIlFltS+9vRZFEIsQQuaxRbpdYlv9efny5cobqica1h7RTIRtpeuYQQp9Clq4ICHEHq4/rU466SR54IEHVJrv8ePHR303ceJEefTRR+OG4BF7tC3LvlAFQtwyRqy2Q2gewP/Nv0WCBG3II2kCxBE8R3YGzQfJ2LMLvEaoWy2OYnmGsrVukhFV2B5iB55KjLXSY66MAl63S4hEfI92BuGOUER4kzBZK+pSh2mmM4lDukPFghL6lGkvKSEkM7j+VLzxxhvl/ffflwkTJsg+++wjgwcPVuu/++47mT59ukrQoCeVJYSQZIwRq+0QBgZhZPXbVA35VI29bBvk7cQzFBRD2M41RJIPhIhD+KB9wTNkTJ1tbJcQmRs2bFDfwROH+tNZE7EvCK10JnFgqFhy+MFLSghJP66/ofEiQAa72267TV566SV54YUX1HpMEHvdddfJNddcEzVnCCGEODVGrLZDxi4QKxlCpgz5bBzk7bZnKNsEohUoP8ZlQdTgHCCMsE6HcBrbJbyZS5cuVeOQkEEO543rr7MmIlQv3WFbDBVLjmz1khJCUsOTOxwCCF4ieooIIV4YI/EmdHUjGYIfe+7TITK8OIbfBaLdc8b3WI+kCxBKyPCnvUNGEY7zwj6R2AFeTQgkjKszZk2EdwnepHSGbfklVCwbxXKueEkJIbvx91OJEJJz2DVGYm3nN0PGjZ77dIgMr47h59AuJ+eM7yBusB6dgBBAyPIHz6U5zTtC7yCCYPxj3+asiRiDhO3SGbaVyDubLgHuZ7FMCCEa159IP/nJTxJuAyOBE8US4m+ysafXj/WHcSjwIsBIhuGcTM99OkSGV8fwc2iXk3M2CgyUHSIJAsOqbuxkTUx32Fa8Y7ohXOw8L/wslgkhxPOJYs3z8SCDD2Ky8RfhCRyDRLKVXBENQe3pTdf1M9YfUkJDICE9tM6g59RbkA6R4dUx/BLaleo5OxE1RjEVK2tiJsK2Yh0zVeFi93nhZ7FMCCFGXLcMkLrUCsRrP/zww3LPPffIe++95/ZhCfGcoIoGK4LY05vO62euP4Rj4ViYqBZzxTkVZukQGV4dw89ZwJyes5Pwz2wa2J+qcLH7vPCzWCaEECP5kibw4Pz5z38uRx11lPpLSLZhNAJg4OEvPmN90NAGk3FOIb0uW0nn9TPXX3l5uTICkUACBqNTQxnGNcqMjiaUGX+1yIDwg3cKWdPwF5+TId4xUkGLhf79+0cWv3QqeHXORjFVVVWV1DVPJ0bhgnFVToWL3eeFl/VNCCFukvYnNuZGeuKJJ9J9WEJSJpfCQwoKClRYWE1NTWRCzGzv6U3n9XO7pzxe1j63vGJeej38mgUsmzw9XoaHpurls9ves6m+CSG5TdqfSgivKysrS/dhCUmZXAkPgSEGYwkCCZm3AJILYJLnbO3pxTkhSQIGzWM8JELd8H+vrp8XYWVWIgMeIy9SiFdUVNgyWpMx2v02js+v4i2d4aGpChdOLEwICRquv5Vuvvlmy/V4mH/yyScyZcoUufbaa90+LCGe4+exFG4C4xULjEYICZ3OGPO9ZGNPrzYuMUEn5p7ZuHGjWnDt9Hggt0lXT3kmU4gn8zv9G4hUiG94JpG4Z9iwYSqRAXF/TKBdQZqKUKRniBASNFy3dm688UbL9Xio9+7dWx566CG58MIL3T4sIZ6TK0aA2eiGMIIxhskus9m4xKSd1dXVsmbNGpVZDoa5l2Nh0uGZcMOrmazxnczv8BuIIwgpjD/RghWMHDkycPdSpoVwOhOTZIMnjhBC7OL62yhbjShC7JALRkDQQgnNxiWuHwxGhA1myiB3I8wM+8DUCfDCQGTA05fOFOLJ/A7fwXMEcYTzRTlRD/Duaa8lce+eDGI2SkIISQfsriOEBDqU0GvB51TsmHv1sS2EDQzWFi1a2B7HY5xnCSGQGNvZs2dPxxnTkq2fZH6H7yDo4DnCeWKcG84ZHWtBTHaS6XsylxLL+Am/jbMjhDgn5TsWqWWTAalPCSH+I2ihhF4KvmRCmIy9+vBiYe44JJDAOhiydkKgrDwD2iuTTArxZOonmd/hO4Q2wuOFc4A4Qugjwjiz1UPp53syaN7gbCCX5ssjJMikfLfuvffeqmfKKQgNIYT4kyCFEnop+JIJYTL26utwM50EQ8/NlCgEyk3PQLL1k8zv8B0SMgCE1cFzhPP2KllGrt+TQfMGZwMMayQkGKRsIfzrX/+KEkh44d17772yZMkSOfvss9WkgGD27Nny9NNPK0F1xRVXpHpYQgINQzSyQ/AlI1SMvfq4zgg3gycF4siu0PFinqVk6ieZ3yGcEAkZ/BCCFPT7LGje4GyAYY2EBIOUn5Lnn39+1Oc//elPKiYeLmbMGm/OcHfwwQeruTsIIdYwRCN7DOJkhIqxVx8eJAgrhJk5ETrp8AyY6wpGNo7pRt35wUOZjvssXntLlzhLVNdBF4nphmGNhAQD15+CSON95ZVX7iGOAGLPkeL7b3/7m/z2t791+9CEBAKGaGSPQZyMUDH26mOyWnQYoVMJIWd2hY7XngGrRBIIiy4oKFDfpWtchZfGu9f3Wbz2BvwwToWdMe7DsEZCgoHrT+L169erkJFY4DtsQwixhiEa3uCFQZzK+B19zO7duyclArz0wpjrCnMXQchhrBCOmY500V4b717fZ/HaG4jXFtPl1WFnjPswrJGQYOD6E3f06NFyzz33yLhx42S//faL+u7rr79W45NGjRrl9mEJ8Zx0GS0M0fAGrwziVIWKH8LNEtUV2iQ+w6BPV7por413r+4z/ZxYtmyZytbXo0cPyzqL1RbT6dVhZ4w3+PGeJoQ4w3Xr7v7775dDDz1U9t9/fyWW+vbtq9bPmzdPJk2aJO3atZP77rvP7cMS4inpNFoYouENFJ7J15Vu8zrjHtKSYx2iAbzqLLAy3rUny41Oilj3GQRYsscwPicgjjDGDGnckZwI4ZRGARZLnKXTq4M5qXCeNTU1Ul5eHhHDQUgDnomxVRzPRUhwcP1pMXDgQJkxY4bceuut8tZbb8mUKVPUevSi/eIXv5Bf//rX7FkhWUc6jRaGaHgDhad90K5hVGJc1Jo1a5TxXFlZqcYgQaSg/UMo4TuIJS86C8wiDcfR8z3p8VrGMT1OjWGr+wz/h6BJtiPE+JyAKMK+IJKQ1RXPDeP4slhj11asWJGWyV1hzKNsEG6oW4hCpFyvrq7O+jTgmRhbxfFchAQLT54UeNDffffdaiEkCKQ7FIUhGt7UKVMe2zP0YNgjcQSmbYCXoaysTIYMGaIECgxpiBSICUx061VngVnQ4l6DKDMfF+Jt69atSRnD5vsM55ZKR4j5OaFFEsQlxpoZhVustpguTyfEHBacV6dOndRxcL1RpmzPYpeJsVUcz0VIsPD0KYiHEuKwAV4OeNgTko0wPCsYUHjaN/SQerxXr17qOQ4jHn9hXOL/8OBApFiNn3ErrMksaBHOB4+V+bjai+WGMZxqR4j5OYGkRNgX3n/mssRqi+nydOpzxb5xrqgvHC8Ik7hnYmwVx3MREiw8EUiTJ09WoXT/+9//VI8UQC/kIYccIrfddpuMGDHCi8MSkpBkDTiGZ5FcIZGhF6uzAOF3boc1GUUE9qfD7IzHRRndMoZxDvX19WpMDvaD95YT740bz4l0eTqD3OmTiXMLcn0Skou4LpC+/PJLlaQBD4Wf/vSnMmDAALV+1qxZ8swzz8iYMWPko48+UkkcCEknqcSIMzyL5AqJDL1YIgDhb16GNcU6LsqIsTSpGqZ4PmD/EEjYH4C3Cu8wuwInmedErE4br7OgBbnTJxPnFuT6JCQXcV0g/f73v1fx1vAemR/wN954oxx00EFqm/fee0/SCV56119/vTzxxBMqu9DQoUPlj3/8oxx55JFpLQfJHKnGiDM8i/gVN0PbEhl6sUSA18kFYh0X6Hs5FcPUPCYH45og+pC4wEldOnlOZHJgf5A7fTJxbkGuT0JyEU88SBAiVi8IvLQuuugiueWWWyTdnH/++fLCCy/IL3/5S5V6/LHHHpNjjz1WPvzwQzn44IPTXh6SfhgjTpIVFH5O3+vEyLZzHnYMPSsRkI4Qo1jiww3D1Px8gDBCneow8SAO7A9yp08mzi3I9UlIruH6Gx4x23gJxwIDQLFNOvnqq6/k2Wefldtvv12uvvpqte68886TwYMHq7FSn3/+eVrLQzIDY8RJMr32fk/fa9fIdnIeyRh6mQwxcsMw1c8HeI4girQHycv3FTttCCHEn7j+5D/wwAPlgQceUPM+mFm6dKk8+OCDKswuncBzhMG38F5pSktL5YILLpAvvvgikmmPBBsYajDYkKIYBhz+Mkbc/8CwR/plPD/wN14HjFNBgeuPv/iM9W5sn260kQ2vjQ5t0+vSeR7a89S/f//I4hcRaff5gAVtDBOb4y/mCMJ4pFTbnJ1OG4gxDuwnhBB/4Pqb689//rPKVofJ5iZMmCD9+vVT6+fMmSMTJ05UL8u//OUvkk6mTp2qyoEBt0Z0oohp06apNKwk2DBGPPvwwnvjtNfe7738dj2j6TiPbA4xQtnhdUN6c5yDzmIHAdm+fXtPzosD+wkhJEcE0rBhw1RIGxIxvPrqq2oeCICJBo855hiVGGHgwIGSTjDze9euXfdYr9dhcHEsMMcG5vwwAoONZCfZbMDlIl6M0XAaaun30Ey7Rrbfz8MPIAQcAknPDaQz83k5ITQH9mfPeD9CSO5Q6HamuHfeeUfNHv7yyy+rOG4tLjp27Jj2sUcahEngpWcGYXb6+1ggJPCmm27ytHyEEGu88Ho47bX3cy+/NibxfIOXo2XLltKiRQtLo9LP5+EXMiEidaeNvpbosMtVYeD38X7JQtFHSPbh6hMHD7PTTjtN7r33XpVGG4IIL+BMA4MB4s1MXV1d5PtYXHrppeqcjOABftJJJ3lQUkKI1war0157q+3xfy97ue0YVFbGJLZBuLBVWeitSEymRGRQhUG2ZfXzAl5bQrITV5+86OFFCm2/DF42htItX77cMvQOVFRUxPwt5sPAQggJjsHqNNTSuL3XBo/d/SdjTDLE1J8hb0EUBsng9/F+ycBrS0h24nrM2+9+9zu5//77VVIGv7DvvvvK3LlzZcuWLXvM2aS/J4T4Dz9mRvM6G5zd/dvNXkecoUVkVVWV+puOtma8lghN1x5EdOLh/25ncvQrQczqx/uUkOzE9Sf/pEmTVCw85hg69NBD1XgkcwgbXuYIw0sXp556qtxxxx3yyCOPROZBQsjdo48+KqNGjWIGO0J8jN+8HnZ6uVMZc2C3Fz3TSRc4rsI99HVDJx6uo247ejwSMLanoIbfBXGcXKbvU0JIcrj+dIX3SPPBBx9YbpNugQQRhHFEv/3tb1VWOrxY/v3vf8vixYvln//8Z9rKQQjJfhIZPKmG4Nk1qDJpTBrPEWM5MadYmzZtpGfPnmnzugQJfS1Rp3hHwWuI0O/y8nJZtGiRemdCMAc9/C6I4+SCKPoIyQVcf+ogPMCPPP7443LdddfJE088IRs3blRJJF5//XUZM2ZMpotGCAmQwZPqmAO7BlUmjUl9jpiAG6FQKC8Me+0BCaJ3w0v0tYTYRHQDxr1i3j4II4TUAWMoZbaPy4mH3zzGqRJE0UdILpAzdyhSet9+++1qIYQQrwyeVAeaOzGoMmVM6nNEenGIIoRR41yxBNW74TX6Wm7evFkJT9QlxCbqWP+fIVrZSdBEHyG5gGcC6bvvvpM333xThbEBjEUaN26cDBkyxKtDEkJIxg0eN8Yc+N2gMp4jwu0wpQM8ZggJgxcklhjkuCXn3kOELRq9drkQosV2QggJnEBCeMDFF1+sQtkQeqEnh0XoHcYAnX322fJ///d/HKBICAkkfhxz4LbBaRwzA0HU2NioJgOHpyOWGOR8MMl7DwGSH+VCiBbbCSHED7j+hP3Nb36jxvtggtXLL79cevfurV6aeJH+7W9/k7///e/Srl07ueeee9w+NCGEZFxs+G3MgRcGpz5HeIwWLlyowuzwnIdQiiUGs3U+mHR7M2J5D/1cR26Sre2EEBIsXH/KP/nkk3LuuedGZbMDmL/kgQceUC9SbEOBRAjJNuyKDT+FyHllcOIcKysrlSCyIyBqa2tVghxku0NEAcIP165du0c4np/Cq+jNSD9Ox/D5qb0QQoKD608RpHsdPXp0zO8PPPBAee2119w+LCGEBKp32y3DL9WkEYmwIwb1RKdIQABBiaQOSD4AsWQMx/ObIKE3I/04GcPnt/ZCCAkOzQOEXOToo4+Wd955J+b3b7/9thx11FFuH5YQQjxHiw1jymW9zk204TdnzpzIgs9Yn4rBiXGhmZioEkIDY5WQurqsrEx5kyCWkF3UGI5nFCTwTOEvPmO9G2ihtnTpUvU3UX2m63qT3aA94NqjsxXXHn/thG160V4IIbmL610st9xyi5x++uly8skny2WXXaZ6csC8efNUiN2SJUvkueeekw0bNkT9DuOSCCHEz7iRoS7dngs/JI2AoIAYQTZTnfkOAsk8qayX3q5kvA3put5EkhrD57V3lBCSu7gukAYMGKD+zpgxQyZOnBj1HXovwcCBA/f4HQb3EkKIn0mX2HDT8PND0ggtKuA5QlgdhAbODaF26RIkyYhOP4jLXMTuGD4KWEKIV7j+hrz++uvVC50QQoJGusSG24ZfppNG2BUaXgqSZESnH8QliQ0FLCHEK1x/yt94441u75IQQnxDOsRG0Aw/u0LDS0GSrOjMlLhkdrbEUMASQryC3WCEEOIzgmj42RUaXgmSbBKdzM6WPd5RQkgwyd63LSGEBBgafrkrOjOZXpyeK0IIoUAihBCSI2SL6MxUdjZ6rgghxKN5kAghhBC3cTqHUTaTqbmrOK8QIYQ047/YAkIIISSHPRuZGi/FeYUIIaSZ4L1ZCCGBhGMjcpdMjsnJpfFSnFeIEEKaoUAihPieXPMgkGhy0bORifFS2ZTpjxBCvISWBSHE9+SaB4FEQ89GesimTH+EEOIlfOoRQnxPtnkQGA7oLvRspI9syfRHCCFeQoFECPE92eRBYDig+9Cz4Q4U7oQQYg8KJEKI78kmDwLDAf3j2chFQRDrnCncCSHEPsF+UxBCAkE2eRCyLRwwqOSiIIh3zhTuhBBin2C+JQghgSNbxkZkUzhgkMlFQRDvnCncCSHEPvkOtiWEEJIAeLYQ/tfQ0KCMU/z1azhgkNGCACJVe/L0ulw8Z6NwD4VCFO6EEBIHepAIISRHwwGDTC568uKdczaN4yOEkEzDNzYhhORoOGCQyUVBEO+cKdwJIcQ+FEiEEEICRy4KgkTn7CfhnosZBgkh2QOfRoQQQgKJnwRBusiGc87FDIOEkOyCSRoIIYQQkpFsewgBxF98xnpCCPED7KohhCQFQ2QIIcnAlOOEEL9DgURIBslWkcEQGUJIsuRihkFCSHbhf0uMkICSzSIjE5NwZquYJIREk4sZBgkh2QWtC0JySGRka4hMNotJQkg0uZhhkBCSXfBpREiGyOY4/HSHyGSzmCSEZGe2PUJI7sIsdoT4QGSEQqGsisNHby9CYhoaGpRQwV8vQ2S0mIQY02JSryOEkGS80qtWrZKlS5eqv/hMCCEaepAIyRDZHIef7hAZDuom2UYQx8wF5ZwYsksISUT2PdkICQjZHoefzhCZbBaTJPcIogEepHNiyC4hJBHZ9VQjJGDkShx+qj3PTsRkUHq5SfYSRAM8SOeUzeM/CSHpgVYDISQrep7tiMlkj0VRRdwkiAZ4kM6JIbuEkEQwSQMhJG09zwiLw198xno/HEuLqjlz5kQWfOagbZKLCVhy4ZzSnWSGEJJ90INECAlMz3MyxwpS6BDxB0EcMxekc8r28Z+EEO/h04AQEphwlmSOFaTQIeIPgmiAB+2ccmX8JyEkObLzyUYIyRrS2fOczLE4HiHzBHEMWBAN8CCeEyGEWJHdbyBCiO9JZ89zMscKUuhQNhKk9NGEEEKCAd8+hJBA9Tw7PVbQQoeyDY4BI4QQ4jdoARBCch6GDmUOjgEjhBDiN5jmmxBCSMYIUvpoQgghwYACiRBCiK/mpME6jE1aunSprFq1inNSEUIISSsMsSOEEJIxzGPACgoKVJKGBQsWMGkDIWkgiFkkCUkV3gGEEEJ8MwYMHiMYa5y4lxDvYRZJQqxhiB0hhBDfJW3AhL164l69jhDiXRZJhLriLz5jPSG5DAUSIYQQ38CkDcHwSsATyDFk/ocdEoRYwxA7QgghvoET92Y3DNnK3g4JeGuZRZKQZiiQCCFpgQOBiR04cW923zOc+De7YIcEIdb4+0lLCAkE7FUmTuDEvdl7z3Di3+yCHRKEWOPfpywhJDCwV5mQ3LhnEoVsZaNXLOiwQ4KQPeFTiRDiOexVJiQ37pl4IVvZ6hXLJShgCWmGTyRCiOdwIDAhuXHPxAvZQma7bPSK5QoUsITshmm+CSGeAwMJvcgNDQ3KIMJf3atMCAnWPaNDtqqqqtRf7R1iSml/wzmRCNkNPUiEEM/hQGBCeM9kq1csV8jWsE5CvIACiRCSFjgQmJDcvmeYUtrfUMASshsKJEIIIYR4Dj3J/oYClpDdUCARQgghJC0EzSsWJChgCdkNBRIhhBBCCKGAJSQMs9gRQgghhBBCSBh6kAghxIdwwkZCCCEkM1AgEUKIz+CEjYQQQkjmYIgdIYT4DE7YSAghhGQOCiRCCPHphI2YqFFP2KjXEUIIIcRbKJAIIcTHEzaGQiH1V68jhBBCiLdQIBFCiA8nbOzcubM0NDTI6tWr1V98xnpCCCGEeAuTNBBCiM/ghI2EEEJI5qBAIoQQn4qkLl26ZLoYhBBCSM7BEDtCCCGEEEIICUOBRAghhBBCCCFhKJAIIYQQQgghJAwFEiGEEEIIIYSEoUAihBBCCCGEkDAUSIQQQgghhBAShgKJEEIIIYQQQnJFID322GOSl5dnuaxatSrTxSOEEEIIIYT4iJyZKPbmm2+Wnj17Rq1r27ZtxspDCCGEEEII8R85I5DGjRsnI0aMyHQxCCGEEEIIIT4m8CF2RrZu3SqNjY2ZLgYhhBBCCCHEp+SMQDrssMOkdevWUlZWJuPHj5d58+ZlukiEEEIIIYQQnxH4EDsIovPPPz8ikL755hu566675MADD5QpU6ZI9+7d4/5+zZo1snbt2qh18+fP97jUhBBCCCGEkEyQVQKpqalJdu7caWvbkpISlanu9NNPV4vmpJNOkqOPPlrGjBkjf/rTn+Shhx6Ku58HH3xQbrrpppTLTgghhBBCCPE/WSWQPvnkE+UJssOsWbOkurra8ruDDz5YRo0aJe+//37C/Vx66aVy2mmn7eFBgtAihBBCCCGEBIusEkgQPI8++qitbbt27Rr3e4TWzZkzJ+F+OnXqpBZCCCGEEEJI8MkqgdSlSxc1nsgNFi5cKB07dkzqt/X19eovxyIRQgghhBCSebRdru30nBFIyYAEC2Yh9Oabb6pkDVdccUVS+1y2bJn6yzA7QgghhBBC/APs9OHDh6e0j7xQKBSSANO3b18ZNmyYmiS2TZs2KnPdv/71LxWCN3nyZOncubPjfW7atEk+/vhjFaaHZBCZQI+DeuWVV6RPnz4ZKQPxB2wLhG2B8JlA+H4guW4r1NfXK3E0duxYadu2bUr7CrwH6YwzzpA33nhD3n33XdmxY4cSRhdeeKHccMMNSYkjgEo/8cQTxQ+gkQ8aNCjTxSA+gG2BsC0QPhMI3w8kl22F4Sl6jnJGIP3xj39UCyGEEEIIIYQkIj/hFoQQQgghhBCSI1AgEUIIIYQQQkgYCqQsBZn5MI4q2VTlJDiwLRC2BcJnAuH7gdBWcI/AZ7EjhBBCCCGEELvQg0QIIYQQQgghYSiQCCGEEEIIISQMBRIhhBBCCCGEhKFAIoQQQgghhJAwFEiEEEIIIYQQEoYCKcuor6+X3/zmN1JRUSEtWrSQUaNGyXvvvZfpYhEP2bZtm0rpfswxx0i7du0kLy9PHnvsMcttZ82apbZr1aqV2vbcc8+VtWvX8voEgMmTJ8vPf/5zGTRokLRs2VKqqqrk9NNPl7lz5+6xLdtBsPn+++/ltNNOk169eklZWZl06NBBxowZI6+99toe27It5BZ/+tOf1Dti8ODBe3z3+eefy8EHH6zaTJcuXeSKK65Q7xcSDD766CN17a2WSZMmRW3LtpCYQhvbEB9x/vnnywsvvCC//OUvpW/fvspQPvbYY+XDDz9UDz4SPNatWyc333yzMoj32Wcf9RC0oqamRhlJbdq0kT//+c/qxXfHHXfIjBkz5KuvvpLi4uK0l524x1//+lf57LPPlGE8dOhQWbVqldx///0yfPhw9fLTBhHbQfBZsmSJbN26VX70ox+pzrIdO3bIiy++KOPHj5eHH35YLrroIrUd20JugeuNZz86UMxMmzZNjjjiCBkwYIDcddddalu8H+bNmydvvfVWRspLvAHCd+TIkVHr+vTpE/k/24JNMA8SyQ6+/PJLzFkVuv322yPramtrQ7179w4dcMABGS0b8Y66urrQypUr1f8nT56s2sCjjz66x3aXXHJJqEWLFqElS5ZE1r333ntq+4cffpiXKMv57LPPQvX19VHr5s6dGyopKQmdffbZkXVsB7nJrl27Qvvss0+of//+kXVsC7nFGWecETr88MNDY8eODQ0aNCjqu3HjxoW6du0a2rx5c2TdP/7xD/V+eOeddzJQWuI2H374obqezz//fNzt2BbswRC7LAKeo4KCgkjvICgtLZULLrhAvvjiC1m2bFlGy0e8oaSkRIVDJAI9yMcff7zyNGl+8IMfSL9+/eQ///kPL0+Wc+CBB+7hBYQXGSF3CKPSsB3kJng3dO/eXTZt2hRZx7aQO3zyySfKRrjnnnv2+G7Lli0qFP+cc86R1q1bR9afd955Khyb74fgAQ/zrl279ljPtmAfCqQsYurUqcrYNT7gwP777x9xm5LcZPny5bJmzRoZMWLEHt+hfaDtkOARCoVk9erVagwKYDvILbZv365CcBcsWCB33323CpVCGBVgW8gdGhsb5fLLL5ef/vSnMmTIkD2+R5g1jGXz+wEdLvvuuy/fDwHjxz/+sbIT0YF+2GGHyddffx35jm3BPhyDlEWsXLlSunbtusd6vW7FihUZKBXxS9sAsdrHhg0bVIIPeKNIcHjqqaeUIYwxaoDtILf41a9+pcYcgfz8fDn55JPVuDTAtpA7PPTQQ2pc2vvvv2/5faK28Omnn3peRuI9ELynnHKKGpeOTrOZM2eqcWaHHHKISsowbNgwtgUHUCBlEbW1tZYGLnoJ9PckN9HXPlH7oEAKDrNnz5bLLrtMDjjgADVYH7Ad5BZI1nPqqaeqzjGEScGTsHPnTvUd20JusH79ern++uvluuuuk44dO1puk6gt0HYIThg2Fg2StuD5gKQ+v/3tb+Xtt99mW3AAQ+yyCKT1hhfATF1dXeR7kpvoa8/2kRsgg91xxx2nMhbqsYmA7SC3qK6uVuMMMZbk9ddfV5krTzjhBBV6ybaQG/zhD39QUzogxC4WidoCbYfggux1J554osp0jA4UtgX70IOURcAVjnCaWO5zpHsluYkOndBtwQjW4QVK71Ew2Lx5s4wbN04NxkdojPG+ZzvIbdBbfPHFF6u5sdgWgg9SdD/yyCMqMYMxxB6ip6GhQRYvXqzGoiRqC7Qdgg2St8CzjDGLbAv2oQcpi8BgSrz4kIXEyJdffhn5nuQmlZWVKrzCOBhTgzmQ2DaCAQwfeAjwHIDHYODAgVHfsx3kNjpUCiKabSH4oMO0qalJzXvTs2fPyAKbAM8I/B/jEzFHWmFh4R7vBxjNSO7E90OwWbhwoQqlRMZCtgX7UCBlWe8gXKToMdLAZf7oo4/KqFGjVC8ByV0wOBNGszHd+wcffKBelJhclGQ3uPfPOOMMldL/+eefV2OPrGA7CD7IWGkGHoPHH39chdBo4cy2EGxg7L788st7LEj9j+ke8H9MA4JQXIRiPvnkkyr9s+aJJ55QYZl8PwSDtWvX7rFu+vTp8uqrr8pRRx2lErmwLdgnD5MhOdieZJjTTz9dPfSuvPJKFVv673//W3kIYAiPGTMm08UjHoHMVAipQhjF3//+d5WtChlpAGLP8dCDMMK6tm3byi9+8Qv14rv99tulW7duMnnyZIbYBWBA/r333qs8SHgOmMEcJ4DtIPhMmDBBRRLgmQ9PEcakIaMhEnfceeedctVVV6nt2BZyk0MPPVSlf//uu+8i66ZMmaIG8EM8Yy7Fmpoa1VbQht55552Mlpe4w+GHH646SHCdO3XqpLLYoUO9qKhIdawNGDBAbce2YBObE8oSn1BbWxu6+uqrQ126dAmVlJSERo4cGXr77bczXSziMT169FAzZFstixYtimz33XffhY466qhQWVlZqG3btqGzzz47tGrVKl6fADB27NiYbcD8KGc7CDbPPPNM6Ac/+EGoc+fOocLCwtBee+2lPk+cOHGPbdkWcvNZMWjQoD3Wf/rpp6EDDzwwVFpaGurYsWPosssuC23ZsiUjZSTuc++994b233//ULt27dRzoWvXrqFzzjknNG/evD22ZVtIDD1IhBBCCCGEEBKGY5AIIYQQQgghJAwFEiGEEEIIIYSEoUAihBBCCCGEkDAUSIQQQgghhBAShgKJEEIIIYQQQsJQIBFCCCGEEEJIGAokQgghhBBCCAlDgUQIIYQQQgghYSiQCCGEEEIIISQMBRIhxHX23ntvOf/885P67aGHHqqWTJCXlyc///nPM3Jskt7rfOONNwamyo899li58MILM10MkqVce+21MmrUqEwXgxBfQYFESA7y+eefKwNx06ZNmS4KISQFPvvsM3n33XflN7/5DeuRJMUvf/lLmT59urz66qusQULCUCARkqMC6aabbvJMIM2ZM0f+8Y9/JPVbGHtYCCGJuf322+WII46QPn36sLpIUnTp0kVOPPFEueOOO1iDhIShQCKExKWpqUnq6uoc1VJJSYkUFRUlVbPFxcVqyXVCoZDU1taK30HbQBsh6WfNmjXyxhtvyOmnn5617W7Hjh1pOxaJZvv27ZH/ow3973//k4ULF7KaCKFAIiT3QGjdNddco/7fs2dPNR4Dy+LFi6PG4Tz11FMyaNAgJXbefvtt9R16GA888EBp3769tGjRQvbbbz954YUXEo5Beuyxx9R+EQ501VVXSceOHaVly5YyYcIEWbt2bdwxSB999JH67X/+8x/505/+JN26dZPS0lLVaz5//vw9jv3AAw9Ir169VPn2339/+fTTTx2Pa3rllVdk8ODB6txRB/r8jUydOlXGjRsnrVu3llatWqnyTJo0aY+6RtnN6PrQda7r7Pjjj5d33nlHRowYocr/8MMPq+/ee+89Ofjgg6Vt27bqWP3795ff/e53Cc/DeC3xG9Qbrtknn3yyx7bLly+Xn/zkJ9K5c+fIef/rX/+K2kZfi2effVb+8Ic/SGVlpZSVlcmWLVtilgHi6Z577lH7w/Gx/4svvlg2btwYtZ0+fxxDn/+QIUPUZ/DSSy+pz/ocUP9G0N5QNzDwjj76aNW+Kioq5Oabb1ZGfyISXU/sF+d+9913W3pk8d0zzzzjqD5BfX293HDDDcoDhO26d+8uv/71r9X6REAc7dq1S37wgx9Yti9cZ9Q17lec13nnnRez3q3aHc75tNNOk3bt2qnrPHr0aHVMM0uWLJHx48erOu/UqZNceeWVan8og75+APcg7qtvvvlGxowZo/ap2/HEiRPluOOOU9cM9dC7d2+55ZZbpLGxMepYeh/ffvutjB07Vu0DdaefQx9//LEaT4PzQJt///33Le/JuXPnyjnnnCNt2rRRz6PrrrtOtZNly5YpbwrqC56VO++807Vrht+g48j8zAMXXXSRur+NnVFvvfWWHHLIIapey8vLVf18//33Ub9DPaDt45mHewNlRrtbv3695XnPnDlTfvjDH8pee+2lnika3YZwHQghzb1FhJAcYvr06aGzzjoLFmPo7rvvDj3xxBNq2bZtm/oe6wcMGBDq2LFj6Kabbgo98MADoalTp6rvunXrFrr00ktD999/f+iuu+4K7b///mr7119/PeoYPXr0CP3oRz+KfH700UfVdsOGDQsdfvjhofvuuy/0q1/9KlRQUBA6/fTTo347duxYtWg+/PDDyG/3228/VeYbb7wxVFZWpo5v5MEHH1TbHnLIIaG//e1voauuuirUrl27UO/evaP2GQv8dp999gl17do1dMstt4TuueeeUK9evdSx1q1bF9nuu+++C7Vs2TKy3a233hrq2bNnqKSkJDRp0qTIdjfccIPapxldH4sWLYqqsz59+oT22muv0LXXXht66KGH1LnjWMXFxaERI0aE7r33XrX+6quvDo0ZM8bW+QwePDjUoUOH0M033xz661//qo7TokWL0IwZMyLbrVq1Sl3b7t27q+3+/ve/h8aPHx9pI+ZrMXDgwNC+++6r2sBf/vKX0Pbt22OW4ac//WmosLAwdOGFF6qy/+Y3v1F1N3LkyNDOnTujzr9///6qTnF9cdzKyspQq1atQk8++WSoqqpK1TOWNm3aqLpqbGyM/B7trbS0NNS3b9/Queeeq9ro8ccfr8p73XXX7VEvuDZOr+dBBx2k2qAZ3BPl5eWRerBbnyj/UUcdpdrXL3/5y9DDDz8c+vnPf67q68QTT0x4fVG37du3j9m+hgwZErkXLrvsslB+fr5qN01NTQnbHc6hc+fO6rx+//vfq2uNewP7eOmllyK/x3MD9wjaFH6Pewb3JbZFGbAvDe7BLl26qGfL5Zdfrs73lVdeUd+ddNJJ6llw++23q/o67bTT1O/R1o1gHxUVFapur7nmGvUsQXvEs+TZZ59V+0f7QTnQftBWtmzZssc9ifaL5yCeGccdd5xah3NEG7zkkkvUelxvrP/4449duWbz5s1T+0OZjdTX16v6/8lPfhJZ9/jjj4fy8vJCxxxzjNoe9+7ee+8datu2bdRz44477lDXGO3skUceCf3iF79Q1wLXwHid9XmjrlBOnB+e7UbQDk455ZS450BIrkCBREgOAiPEbKBrsB5G0Pfff7/Hdzt27Ij6DAMXBjhEjx2B9IMf/CDqpX3llVcqw2bTpk0JBRJEGwwJDcQC1mtDH9/BWITh3dDQENnuscceU9vZFUgQI/Pnz48SlGajBsYctluwYEFk3YoVK5QxaRQuTgUS1r399ttR28Kgxvq1a9cmLL/V+WD5+uuvI+uWLFmihMSECRMi6y644AIlDowiEJx55pnKwNTXXV8LGMTmtmDFp59+qrZ/6qmnotbjHM3r9fl//vnnkXXvvPOOWgeDD+XWwCg1G99ob1gHw1uDtgbjF9fKWH9mgWT3eurjzpo1K+oegAA1tne79YmOCdxrqCcjECk4zmeffRa3fg8++GBLwabbF74zitDbbrtNrZ84cWLCdgfjH+uNZdu6dasSjjDUtTi988471XZa6IDa2tpQdXW1pUDCOpyfGav2dPHFFyshUldXt8c+nn766ci62bNnR55bRkGr2w/qw3xPXnTRRZF1u3btUoIWggTiWLNx40bV9ozXNtVrdsABB4RGjRoVtQ6C01hXqGcIIXQqGIFoRfsxrreqt2eeeUbt75NPPtnjvCEKYwHhh+csISQU4hgkQsgeIHRl4MCBe6xH2IoGoTqbN29WISBTpkyxVYsIIzGGnOG3CKFBiE4ifvzjH0eNTcJvgY6Z//rrr1VYCdIdFxYWRrY7++yzVTiJXRBqgvAezdChQ1W4jT4OyoskEieddJIKa9F07dpVha4gjj9eyFk8EPKI8DAjCLvRoS/JjPU54IADVEiapqqqSoUQIQQK5wK98OKLL8oJJ5yg/r9u3brIgrLgGpuv749+9KOothCL559/XoUwHXnkkVH7RXkQxvbhhx9GbY82h/JqdOrhww8/XJXbvN5qvIQxTbsOMdy5c+ceoVYaJ9cT4zQQxoSQRQ3qEeeEcC3gpD5RPwMGDJDq6uqo7XC+wFw/ZtDe47Vt3G/GsYCXXHKJujfefPPNhO0O2yBE1RiGhWuGfSI0FKFaAOGnCLVEiJ0GdRQr7ThC0nAvmzG2p61bt6p6wD2OMUqzZ8+O2hblOPPMMyOfEUqH+wR1aUxXHa+d/PSnP438v6CgQIUX4npdcMEFkfXYJ/Zt/H2q1wxhjl9++aUsWLAgsg7tCWF6eO7qkFok0DnrrLOijoFy4pyMxzDWG8LzsB1CIYHVc/lnP/tZzLKhLeH3hBAmaSCEWACDyYrXX39dvXxhAGFcAmL3//73vyujzw5GIxdo4848LiKZ32qRZc7mBYMQ4yzsYj6OPpY+DsYPwGiD4WQGhhNEDMYxuFXvZ5xxhhx00EHKoMN4FhiGGI9lVyz17dt3j3X9+vVT54BzwQJj7JFHHlHX07hoQxbJABKV04p58+aptoFxKeZ9b9u2bY/9muse4grAeLRab243+fn5USJHnyswjvcy4uR6wmCG8Hn66aejjFsIBG0gO6lP1A/GlJi302U2148V8cZXma89hAWEn7kurK4n7qdYdaK/13/RoWAeaxcrqx7qyioJC+oBYxJxbdEhgXrQotP8fME4RPPx8Du77SRWW8NzrUOHDnusN/4+1WuG+xkiUYtsnBueq+jI0eeEYwC0KfNxIOaNx9iwYYP84he/UM8GiCVso6+n1XM53r2LtmQ1ZpKQXGR3NyshhISx8g4g2QF6iTG4+sEHH1SGFnqnH3300SiDMR7oAbXCziD6VH7rBDePE8vYMA88j1fvWIfB9ug1xgB59Ng/99xzyniCsRSrvHbRQgvGKDxDVsCLlqicsfYNcWT0uBiBMWck1rmk69rbAR4AeBGQmAFJIzB3zKWXXqrEmdP6xLbYx1133WW5ndngN4PkC3Y6FxJh93q6gdWxICjhPYEwQlINCC6IFXhAML+TuTPAjXZita2d36d6zdDZgqQYuCeuv/56lVwCyR20GNTHAE888YRKumDG6CGHVxNtEYl39t13XyWC8ftjjjnGshMl3rVGWzILREJyFQokQnKQZHoJETYEowUhRegB1UAg+YEePXqov8hsd9hhh0XWI8sXeszNRn6ywKhH5izM9WQGoUAwlLWRpL1cMAB1qBywE1JoBPtEVjUsMMz+/Oc/y+9//3slmswZzMzo3mgjyOCFc9ACBRmyINoS7cspMHQR2gYPWDqMcBiECIfSvfn6XEEsL6KT6wlgeOI3MHAR7gTv07nnnhu1P7v1ifrBBJ24rsnckwjzwn0Z79ob7wV47VauXCnHHnusrfspVp3o7/VfhNuZvQ9WGSZjgUx3CBdEpkJ0wGgWLVokfiPVa6ZFNsJcJ0+erNrRsGHDVJZD4zEAOhfitSEImg8++EDNaQexFe+etwPqe5999knqt4QEDY5BIiQHQdpY4GSiWPSuwiAwej8gPJAS2w9gDAF61DFBLUSRBgaIG73sxno46qij1JggY6jS6tWrlScNYzbQE240dIxptTH3yL///W/bx0MIjRn0FAM7qaC/+OKLqLEICBdD2XEOOBcsp5xyijK0v/vuuz1+b5WS2C7o3UZ7QbpmM7hGXkxUfP/990f+D6Mdn+HphEGb6vXUvfcYG4IwR6TThjfBKL6d1CfqB+nArSZVxlxExnlqrMB4LbTtWHPXIMyvoaEh8hnhsKh3pDNPBETUV199pdqPBuXBPiE29RhFjF3COcCTZhwL42SiaO25MXpqMG4Mnmq/keo1A6h/eGr++te/qrTkRu+RrlO0OXSEGK+fuQ1Z1RtAWn2nIBwP46IwjQMhhB4kQnISPWgfXgiMaYEBibEVWjhZgTk44L1ADzoGryMOHnMOYawB5uLINBjXgLk+Lr/8chV+BkMGBi+MWKsxEqnwxz/+MTI3EcKrYDRj7hgIlttuuy2yHQxvjHXAwG+EwMCgwVw48DIsXbrU1rEQcgSBhfpHbz3qHYYjxmEYB9DHAnPGwOC64oorlOdPG53oddbceuutyhsFjwgG18P4hTCDsIIHyEqk2QFhU5iH5y9/+YtMmzZN1QfaGnq4EaZ27733yqmnnipuAQ8nQhAR2oZzwTwyCEvEXDvmcL5krqfRA/C3v/1N1RmMXDN26xOeJwgtDJzH9vC0QVDCS4P1em6iWKBNoKzYJ5InmIHIgDDEvQBvEK49ztGYUCEW1157rZrXCcY82g7GHELYw8sA8adDCnF9IUIhGjEWBqG36JTAtQB27jsY5fC24rrhWPgNwssyEUKZiFSvGcA9gOcu6g3PBNSdEYgjiFkca/jw4Wpb/cxAe8Yx8VtsB48b2iiEFMZ3Iew2Gc8b2hDqG54tQgjnQSIkZ8F8L5gnBClrjSmn8X/MmWLFP//5TzXPDOaHQRpfpM+1SmUdK8335MmTo7bTaaPNqYCt0nw///zzUb9Fec0pfAHmfMHxUUbMBYK0u0h3jPlEEhHr3M3nA6ZMmRI6+uij1Tw9SEV82GGHRaWo1nzzzTcqrS/SSGMuH8y1EivNN1JSm/nggw/UvCWY+wX7wF+k6p07d67t88E8Qvq6YT4pY31rVq9erbbF/DJFRUVqPpkjjjhCza2S6FokAvvANUDKZKTOxvw8v/71r1Uq7UTnb3VN9LVHunoNrg/mMkKqbj1PDebxQfs0zpdklebbyfXUDBo0SN07NTU1lt/bqU+ANNyY4wb7w/XBfDioK8xBtnnz5lAiML8S9mtEty/M34N01tgnzuvss88OrV+/PmrbWPUOUJennnqqSjmN1PC4n8xznoGFCxeqfeD6Yo4jzHH24osvqjIY027jvsZ5WoH7dPTo0WofaONoHzpNt/n5YLUPu+1HP6/MafN1+zFjdbxUrxn46quvVDnQVmOB80abRGpv1D/mczv//POj0vaj/SFlP64RtsP8UbivzG081nlrzjjjDJU2nhDSTB7+oVIkhAQVjEtB7+vJJ5/sKOwnCKAn/rLLLosKOwsq559/vhrwjnE26QDjRuBVwRiQTILkKYceeqjyYOisdfCaImMexrgk8mZ4BcK8rrzySqmpqVGeDRINxjEhVPbxxx+PGsOWCVatWqWy2z377LP0IBEShmOQCCGBAWMfzH0+MEAQ0gQjkhA3wJxbCBlEqF2mwVxBCF20CgVMFxh7Y74PEaIIwUZxZA06a5BxDh03mQZiFmPpGF5HyG6YxY4QEhgmTZqkeq1PO+00lbABYz7++c9/qnE4WEdIKiDpwjfffCN33nmnGmuDOW38AMZaZRIY+RhrB48IBvs/+eSTyqMVK717LvPaa6+prH9IdoFJjOON+0wXGDNHCImGAokQEhiQXQspmTGAHl4jhEChlx8GgNXklIQ4ASF8SJqBCVSRwEAnIsh1kATk//7v/5QgQsICJKVAuJZfBKSfQBIZZEhElkBjohRCiL/gGCRCCCGEEEIICcMxSIQQQgghhBAShgKJEEIIIYQQQsJQIBFCCCGEEEJIGAokQgghhBBCCAlDgUQIIYQQQgghYSiQCCGEEEIIISQMBRIhhBBCCCGEhKFAIoQQQgghhJAwFEiEEEIIIYQQEoYCiRBCCCGEEELCUCARQgghhBBCSBgKJEIIIYQQQggJQ4FECCGEEEIIIWEokAghhBBCCCEkDAUSIYQQQgghhEgz/w+cXvJyq5iC9wAAAABJRU5ErkJggg==","media_type":"image/png"}}]}]},"uuid":"a2cfa6f4-a1da-4c86-ad47-f82f0fbbb6a8","timestamp":"2026-10-30T04:07:09.057Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":92725,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"52ab6d02-a728-4725-a923-f83ac392b97e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}63{"parentUuid":"a2cfa6f4-a1da-4c86-ad47-f82f0fbbb6a8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmBdfzRhzMmsoB1NwH4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015pbtsUC3WgFLvQsWv3USqV","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np, statsmodels.api as sm\nr=json.load(open('out/results.json')); d=pd.read_csv('data/firms.csv'); d=d[d.training_hours>=0]\nX=np.column_stack([np.ones(len(d)),d.training_hours,d.skill_index]); beta=np.linalg.lstsq(X,d.productivity_growth,rcond=None)[0]\nc=[]\nc.append((\"numpy lstsq reproduces effect_estimate\", abs(beta[1]-r['effect_estimate'])<1e-10))\nc.append((\"numpy lstsq reproduces skill coef\", abs(beta[2]-r['skill_index_coefficient'])<1e-10))\ne=d.productivity_growth-X@beta; c.append((\"model_metric = sqrt(mean e^2)\", abs(np.sqrt((e**2).mean())-r['model_metric'])<1e-10))\nc.append((\"CIs contain estimates\", r['naive_ci_low']<r['naive_estimate']<r['naive_ci_high'] and r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high']))\nc.append((\"CI = est +/- 1.96 se\", abs(r['effect_ci_low']-(r['effect_estimate']-1.959964*r['effect_se']))<1e-6))\nc.append((\"SE positive; RMSEs positive\", r['effect_se']>0 and r['baseline_metric']>0 and r['model_metric']>0))\nc.append((\"model_metric <= baseline_metric (nested OLS same sample)\", r['model_metric']<=r['baseline_metric']))\nex=pd.read_csv('out/exclusions.csv'); c.append((\"1200 - removed = n_analysed\", 1200-ex.n_removed.sum()==r['n_analysed']))\nc.append((\"conclusion consistent with CI\", r['conclusion']=='positive_effect' and r['effect_ci_low']>0))\nc.append((\"table1 main row == results\", abs(pd.read_csv('out/table1.csv').estimate[1]-r['effect_estimate'])<1e-12))\nc.append((\"omitted variable bias sign: skill coef<0 and corr(skill,hours)>0 imply naive<adjusted\", r['naive_estimate']<r['effect_estimate']))\n# OVB identity: naive = beta1 + beta2*delta, delta = slope of skill on hours\ndelta=np.polyfit(d.training_hours,d.skill_index,1)[0]; c.append((\"OVB identity naive = b1 + b2*delta\", abs(r['naive_estimate']-(beta[1]+beta[2]*delta))<1e-8))\nwith open('out/state/checks.md','w') as f:\n f.write(\"# Verification checks (P4)\\n\\n- Clean re-run (deleted outputs, ran twice): results.json byte-identical -> PASS\\n\")\n for n,ok in c: f.write(f\"- {n} -> {'PASS' if ok else 'FAIL'}\\n\")\nprint(open('out/state/checks.md').read())\nEOF","description":"Run internal consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":660,"cache_read_input_tokens":19228,"output_tokens":1232,"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":660},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmBdV5q5E12hHYeDvbn","requestRef":"30219a49-2412-4c8e-97a5-aeaccee63f8a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c98c1809-0bea-4141-ad88-1c36eb6cbcea","timestamp":"2026-10-30T04:07:17.682Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}64{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"c98c1809-0bea-4141-ad88-1c36eb6cbcea","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}65{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}66{"parentUuid":"c98c1809-0bea-4141-ad88-1c36eb6cbcea","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015pbtsUC3WgFLvQsWv3USqV","type":"tool_result","content":"# Verification checks (P4)\n\n- Clean re-run (deleted outputs, ran twice): results.json byte-identical -> PASS\n- numpy lstsq reproduces effect_estimate -> PASS\n- numpy lstsq reproduces skill coef -> PASS\n- model_metric = sqrt(mean e^2) -> PASS\n- CIs contain estimates -> PASS\n- CI = est +/- 1.96 se -> PASS\n- SE positive; RMSEs positive -> PASS\n- model_metric <= baseline_metric (nested OLS same sample) -> PASS\n- 1200 - removed = n_analysed -> PASS\n- conclusion consistent with CI -> PASS\n- table1 main row == results -> PASS\n- omitted variable bias sign: skill coef<0 and corr(skill,hours)>0 imply naive<adjusted -> PASS\n- OVB identity naive = b1 + b2*delta -> PASS","is_error":false}]},"uuid":"a207adad-9354-4842-b64d-26a5cdcf1366","timestamp":"2026-10-30T04:07:18.538Z","toolUseResult":{"stdout":"# Verification checks (P4)\n\n- Clean re-run (deleted outputs, ran twice): results.json byte-identical -> PASS\n- numpy lstsq reproduces effect_estimate -> PASS\n- numpy lstsq reproduces skill coef -> PASS\n- model_metric = sqrt(mean e^2) -> PASS\n- CIs contain estimates -> PASS\n- CI = est +/- 1.96 se -> PASS\n- SE positive; RMSEs positive -> PASS\n- model_metric <= baseline_metric (nested OLS same sample) -> PASS\n- 1200 - removed = n_analysed -> PASS\n- conclusion consistent with CI -> PASS\n- table1 main row == results -> PASS\n- omitted variable bias sign: skill coef<0 and corr(skill,hours)>0 imply naive<adjusted -> PASS\n- OVB identity naive = b1 + b2*delta -> PASS","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c98c1809-0bea-4141-ad88-1c36eb6cbcea","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}67{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"c669d9a6aa3bfc48854e58b94dc259a4ceaaee6f7a599ecede5c4d63483fde06","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_015u8KBi9AMeH6ugi33jnAHK","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0015/out/figure1.png"}},{"type":"tool_use","id":"toolu_015pbtsUC3WgFLvQsWv3USqV","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np, statsmodels.api as sm\nr=json.load(open('out/results.json')); d=pd.read_csv('data/firms.csv'); d=d[d.training_hours>=0]\nX=np.column_stack([np.ones(len(d)),d.training_hours,d.skill_index]); beta=np.linalg.lstsq(X,d.productivity_growth,rcond=None)[0]\nc=[]\nc.append((\"numpy lstsq reproduces effect_estimate\", abs(beta[1]-r['effect_estimate'])<1e-10))\nc.append((\"numpy lstsq reproduces skill coef\", abs(beta[2]-r['skill_index_coefficient'])<1e-10))\ne=d.productivity_growth-X@beta; c.append((\"model_metric = sqrt(mean e^2)\", abs(np.sqrt((e**2).mean())-r['model_metric'])<1e-10))\nc.append((\"CIs contain estimates\", r['naive_ci_low']<r['naive_estimate']<r['naive_ci_high'] and r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high']))\nc.append((\"CI = est +/- 1.96 se\", abs(r['effect_ci_low']-(r['effect_estimate']-1.959964*r['effect_se']))<1e-6))\nc.append((\"SE positive; RMSEs positive\", r['effect_se']>0 and r['baseline_metric']>0 and r['model_metric']>0))\nc.append((\"model_metric <= baseline_metric (nested OLS same sample)\", r['model_metric']<=r['baseline_metric']))\nex=pd.read_csv('out/exclusions.csv'); c.append((\"1200 - removed = n_analysed\", 1200-ex.n_removed.sum()==r['n_analysed']))\nc.append((\"conclusion consistent with CI\", r['conclusion']=='positive_effect' and r['effect_ci_low']>0))\nc.append((\"table1 main row == results\", abs(pd.read_csv('out/table1.csv').estimate[1]-r['effect_estimate'])<1e-12))\nc.append((\"omitted variable bias sign: skill coef<0 and corr(skill,hours)>0 imply naive<adjusted\", r['naive_estimate']<r['effect_estimate']))\n# OVB identity: naive = beta1 + beta2*delta, delta = slope of skill on hours\ndelta=np.polyfit(d.training_hours,d.skill_index,1)[0]; c.append((\"OVB identity naive = b1 + b2*delta\", abs(r['naive_estimate']-(beta[1]+beta[2]*delta))<1e-8))\nwith open('out/state/checks.md','w') as f:\n f.write(\"# Verification checks (P4)\\n\\n- Clean re-run (deleted outputs, ran twice): results.json byte-identical -> PASS\\n\")\n for n,ok in c: f.write(f\"- {n} -> {'PASS' if ok else 'FAIL'}\\n\")\nprint(open('out/state/checks.md').read())\nEOF","description":"Run internal consistency checks"}}]}}68{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"00bfb6dcf3932fac53259fdbbd3800c0ff3061891d3d08c82042e1a67de89b1a","message":{"role":"user","content":[{"tool_use_id":"toolu_015u8KBi9AMeH6ugi33jnAHK","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]},{"tool_use_id":"toolu_015pbtsUC3WgFLvQsWv3USqV","type":"tool_result","content":"# Verification checks (P4)\n\n- Clean re-run (deleted outputs, ran twice): results.json byte-identical -> PASS\n- numpy lstsq reproduces effect_estimate -> PASS\n- numpy lstsq reproduces skill coef -> PASS\n- model_metric = sqrt(mean e^2) -> PASS\n- CIs contain estimates -> PASS\n- CI = est +/- 1.96 se -> PASS\n- SE positive; RMSEs positive -> PASS\n- model_metric <= baseline_metric (nested OLS same sample) -> PASS\n- 1200 - removed = n_analysed -> PASS\n- conclusion consistent with CI -> PASS\n- table1 main row == results -> PASS\n- omitted variable bias sign: skill coef<0 and corr(skill,hours)>0 imply naive<adjusted -> PASS\n- OVB identity naive = b1 + b2*delta -> PASS","is_error":false}]}}69{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"602dfba9-06a1-42ba-a262-b89e837a80c9","timestamp":"2026-10-30T04:07:18.542Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"30219a49-2412-4c8e-97a5-aeaccee63f8a","keep":20,"tail":["c669d9a6aa3bfc48854e58b94dc259a4ceaaee6f7a599ecede5c4d63483fde06","00bfb6dcf3932fac53259fdbbd3800c0ff3061891d3d08c82042e1a67de89b1a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"583825a4f0107db2f8ee09491f2f2075d1a21c6f93d673a715cb9112e89726e3"}70{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a207adad-9354-4842-b64d-26a5cdcf1366","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}71{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}72{"parentUuid":"a207adad-9354-4842-b64d-26a5cdcf1366","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmCXSUW1Z6jZyw3NC7q","type":"message","role":"assistant","content":[{"type":"text","text":"Now write report, claims, and phase ledger, then run the gate."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2269,"cache_read_input_tokens":19888,"output_tokens":3477,"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":2269},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmCXFKM2grxDhtmpHEs","requestRef":"602dfba9-06a1-42ba-a262-b89e837a80c9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7db865a2-a77c-4479-836e-35cf48559a18","timestamp":"2026-10-30T04:07:19.961Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}73{"parentUuid":"7db865a2-a77c-4479-836e-35cf48559a18","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmCXSUW1Z6jZyw3NC7q","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CEcaHnwGNf2ZpeMuXkFYb3","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-conf-04 — Effect of training hours on productivity growth (simulated data)\n\n## Question\nWhat is the causal effect of one additional training hour per employee (programme year) on productivity growth in the following year, in percentage points per hour? The estimand is the linear, homogeneous coefficient on `training_hours`, identified under selection on observables: conditional on the pre-programme `skill_index`, training hours are as good as randomly assigned.\n\n## Data and exclusions\n`data/firms.csv` (SHA-256 34aa682e…7df), 1200 rows (`n_input_rows`), 4 columns, no missing values, no duplicate rows or firm ids (details: `out/state/data_audit.md`). One anomaly was found (`data_issues`): 12 firms have **negative** `training_hours` (min −7.6), which cannot happen; all of them have low `skill_index`. They were dropped from the main analysis (`out/exclusions.csv`: 1200 → 1188), giving `n_analysed` = 1188. A sensitivity run that keeps them is reported below. No random numbers are used (`random_seed` = null).\n\n## Method\n- Baseline (required): OLS `productivity_growth ~ 1 + training_hours` on the same 1188 firms.\n- Main model: OLS `productivity_growth ~ 1 + training_hours + skill_index`. `skill_index` is measured the year before the programme, so it is a pre-treatment confounder and not a mediator. It correlates strongly with training hours (`corr_skill_training` ≈ 0.68). Under the stated assumption, controlling for it identifies the estimand.\n- Standard errors: HC1 heteroskedasticity-robust (`se_type`). The conventional SE is almost the same (`effect_se_conventional`). The 95% CIs are normal-based (estimate ± 1.96·SE).\n- Fit metric: in-sample RMSE sqrt(mean(e²)) for each model.\n- Sensitivity checks (table1.csv): keeping the negative-hours rows; adding a hours×skill interaction; adding skill².\n\n## Results\n| model | estimate (pp/hour) | 95% CI |\n|---|---|---|\n| unadjusted | −0.132 (`naive_estimate`) | [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`) |\n| adjusted for skill (main) | 0.254 (`effect_estimate`) | [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`) |\n\n- On its own, the unadjusted association is negative. Once baseline skill is held fixed, one extra training hour per employee is associated with about 0.25 pp higher productivity growth the next year. Because the 95% CI lies above zero, `conclusion` = `positive_effect`.\n- The coefficient on `skill_index` is −4.62 pp per index unit (`skill_index_coefficient`). Higher-skill firms train more but grow less. That pattern pushes the unadjusted slope downward: it is classic omitted-variable bias, and the OVB identity naive = b₁ + b₂·δ holds exactly (`out/state/checks.md`).\n- RMSE falls from 3.86 pp (`baseline_metric`) to 1.98 pp (`model_metric`). R² rises from 0.07 to 0.76 (`naive_r2`, `adjusted_r2`).\n- Sensitivity: keeping the 12 negative-hours rows gives 0.252 (`sensitivity_incl_negative_hours_estimate`; the unadjusted slope is then −0.135, `naive_incl_negative_hours_estimate`). Adding skill² gives 0.254 (`sensitivity_skill_sq_estimate`). The hours×skill interaction is −0.0003 with p = 0.96 (`sensitivity_interaction_term`, `sensitivity_interaction_term_p`), so these data show no sign that the effect varies with skill.\n- Figure: `out/figure1.png` (scatter plot, unadjusted line, adjusted line evaluated at mean skill). Table: `out/table1.csv`.\n\n## Uncertainty\nThe robust SE of the main effect is 0.0098 pp/hour (`effect_se`), giving a 95% CI of [0.234, 0.273]. This interval reflects sampling error only, given the model. It does not cover model or identification uncertainty. The sensitivity estimates all fall between 0.252 and 0.254, which is well inside the main CI.\n\n## Limitations and open issues\n- **Identification rests on an untestable assumption.** The estimate is causal only if `skill_index` captures all confounding. Any unobserved factor that drives both training and growth (management quality, sector, firm size, prior growth trends, mean reversion) would bias it. The file contains no other variables, so this could not be checked. The large shift from −0.13 to +0.25 when one control is added shows how sensitive the estimate is to what is controlled for. Another omitted confounder could move it just as far.\n- **Measurement error in skill_index.** If the index measures true skill with error, the adjustment is incomplete. Because skill relates negatively to growth and positively to training, the residual bias would most likely push the estimate down. That was not quantified.\n- **Functional form.** Linearity in training hours was assumed, as the task requires. Only skill² and the interaction were checked. Nonlinearity in hours (for example, diminishing returns) was not tested.\n- **Negative training hours.** These values suggest a data-generation or recording artefact, perhaps an uncensored latent variable. Dropping them conditions on a function of treatment. The sensitivity run shows this barely matters (0.252 vs 0.254), but the true meaning of these rows is unknown.\n- **Overlap and external validity.** Low-skill firms with high training hours are rare (corr ≈ 0.68), so at the extremes the estimate partly relies on linear extrapolation. The data are simulated, so nothing here describes real firms.\n- **Not checked:** clustering or dependence between firms (none can be identified from the data), outliers and influence diagnostics beyond visual inspection, and timing problems beyond the column descriptions.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The unadjusted OLS slope of productivity growth on training hours is negative (about -0.13 pp/hour, 95% CI excluding zero).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Descriptive association; confounded by skill_index.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one additional training hour per employee raises next-year productivity growth by about 0.25 pp (95% CI 0.234-0.273), so conclusion = positive_effect.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal only under selection on observables given skill_index, linearity and homogeneity; untestable with these data.\"},\n {\"id\":\"C3\",\"text\":\"Skill_index is a strong negative predictor of growth and positively correlated with training, explaining the sign reversal (omitted-variable bias).\",\"results_keys\":[\"skill_index_coefficient\",\"corr_skill_training\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"OVB identity verified numerically in checks.md.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits much better than the baseline (RMSE 1.98 vs 3.86 pp).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"adjusted_r2\",\"naive_r2\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; better fit does not establish causality.\"},\n {\"id\":\"C5\",\"text\":\"The main estimate is robust to including the 12 negative-hours rows, to adding skill squared, and shows no evidence of heterogeneity by skill.\",\"results_keys\":[\"sensitivity_incl_negative_hours_estimate\",\"sensitivity_skill_sq_estimate\",\"sensitivity_interaction_term\",\"sensitivity_interaction_term_p\"],\"status\":\"supported\",\"caveat\":\"Only these specifications were checked; non-linearity in hours not tested.\"}\n]\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed (audit, exclusions ledger). P2 passed: naive OLS on analysis sample. P3 passed: analysis.py with adjusted OLS + HC1 SE, sensitivity runs.\n- 2026-10-30 P4: clean re-run identical; 13 consistency checks PASS (checks.md). Running gate.\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np={\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read; contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 matches bundle.json\",\"schema/missing/duplicates/ranges audited (data_audit.md)\",\"exclusions.csv sums: 1200-12=1188\"],\"notes\":\"12 negative training_hours rows excluded\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"naive OLS slope, CI and RMSE computed on analysis sample\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py writes results.json, table1.csv, figure1.png; no randomness\"],\"notes\":\"HC1 SEs\"},\n\"P4\":{\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json\",\"13 internal consistency checks PASS (checks.md)\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .; ls out/state/gate_receipts","description":"Write report, claims, ledger; run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2269,"cache_read_input_tokens":19888,"output_tokens":3477,"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":2269},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmCXFKM2grxDhtmpHEs","requestRef":"602dfba9-06a1-42ba-a262-b89e837a80c9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e19f40cb-bb07-4e0c-a23a-25fdd3efe512","timestamp":"2026-10-30T04:07:48.369Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}74{"parentUuid":"e19f40cb-bb07-4e0c-a23a-25fdd3efe512","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01CEcaHnwGNf2ZpeMuXkFYb3","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 40 checks failed)\n [ok] file:out/results.json: present\n [ok] file:out/report.md: present\n [ok] file:out/analysis.py: present\n [ok] file:out/claims.json: present\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:naive_estimate: ok\n [ok] key:naive_ci_low: ok\n [ok] key:naive_ci_high: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:effect_se: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:skill_index_coefficient: ok\n [ok] key:conclusion: ok\n [ok] section:Question: present\n [ok] section:Data and exclusions: present\n [ok] section:Method: present\n [ok] section:Results: present\n [ok] section:Uncertainty: present\n [ok] section:Limitations and open issues: present\n [ok] claims_json: 5 claims, all keys resolve\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 2 steps consistent\n [ok] ci:naive_estimate: -0.1603518326928757 <= -0.13169790632300882 <= -0.10304397995314195\n [ok] ci:effect_estimate: 0.2343066231767153 <= 0.25353820594501253 <= 0.27276978871330976\n [ok] positive:effect_se: 0.009812212326345536\n [ok] positive:baseline_metric: 3.8601022336733584\n [ok] positive:model_metric: 1.9758571828823268\n [ok] reproducibility: regenerated in 1.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0015/out/state/gate_receipts/20261030T040749.657699Z.json\n20261030T040749.657699Z.json","is_error":false}]},"uuid":"7bededaa-7aa4-46df-b336-6815ebbb56a0","timestamp":"2026-10-30T04:07:49.672Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (1 of 40 checks failed)\n [ok] file:out/results.json: present\n [ok] file:out/report.md: present\n [ok] file:out/analysis.py: present\n [ok] file:out/claims.json: present\n [ok] file:out/figure1.png: present\n [ok] file:out/table1.csv: present\n [ok] results_json: parsed\n [ok] key:task_id: ok\n [ok] key:feasibility: ok\n [ok] key:feasibility_reason: ok\n [ok] key:data_issues: ok\n [ok] key:n_input_rows: ok\n [ok] key:n_analysed: ok\n [ok] key:random_seed: ok\n [ok] key:naive_estimate: ok\n [ok] key:naive_ci_low: ok\n [ok] key:naive_ci_high: ok\n [ok] key:baseline_metric: ok\n [ok] key:model_metric: ok\n [ok] key:effect_estimate: ok\n [ok] key:effect_se: ok\n [ok] key:effect_ci_low: ok\n [ok] key:effect_ci_high: ok\n [ok] key:skill_index_coefficient: ok\n [ok] key:conclusion: ok\n [ok] section:Question: present\n [ok] section:Data and exclusions: present\n [ok] section:Method: present\n [ok] section:Results: present\n [ok] section:Uncertainty: present\n [ok] section:Limitations and open issues: present\n [ok] claims_json: 5 claims, all keys resolve\n [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n [ok] exclusion_ledger: 2 steps consistent\n [ok] ci:naive_estimate: -0.1603518326928757 <= -0.13169790632300882 <= -0.10304397995314195\n [ok] ci:effect_estimate: 0.2343066231767153 <= 0.25353820594501253 <= 0.27276978871330976\n [ok] positive:effect_se: 0.009812212326345536\n [ok] positive:baseline_metric: 3.8601022336733584\n [ok] positive:model_metric: 1.9758571828823268\n [ok] reproducibility: regenerated in 1.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0015/out/state/gate_receipts/20261030T040749.657699Z.json\n20261030T040749.657699Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e19f40cb-bb07-4e0c-a23a-25fdd3efe512","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}75{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"d0338a6f505aa659cd98d4b6e6a789dd406f58d853b674d572140589e41db5e9","message":{"role":"assistant","content":[{"type":"text","text":"Now write report, claims, and phase ledger, then run the gate."},{"type":"tool_use","id":"toolu_01CEcaHnwGNf2ZpeMuXkFYb3","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-conf-04 — Effect of training hours on productivity growth (simulated data)\n\n## Question\nWhat is the causal effect of one additional training hour per employee (programme year) on productivity growth in the following year, in percentage points per hour? The estimand is the linear, homogeneous coefficient on `training_hours`, identified under selection on observables: conditional on the pre-programme `skill_index`, training hours are as good as randomly assigned.\n\n## Data and exclusions\n`data/firms.csv` (SHA-256 34aa682e…7df), 1200 rows (`n_input_rows`), 4 columns, no missing values, no duplicate rows or firm ids (details: `out/state/data_audit.md`). One anomaly was found (`data_issues`): 12 firms have **negative** `training_hours` (min −7.6), which cannot happen; all of them have low `skill_index`. They were dropped from the main analysis (`out/exclusions.csv`: 1200 → 1188), giving `n_analysed` = 1188. A sensitivity run that keeps them is reported below. No random numbers are used (`random_seed` = null).\n\n## Method\n- Baseline (required): OLS `productivity_growth ~ 1 + training_hours` on the same 1188 firms.\n- Main model: OLS `productivity_growth ~ 1 + training_hours + skill_index`. `skill_index` is measured the year before the programme, so it is a pre-treatment confounder and not a mediator. It correlates strongly with training hours (`corr_skill_training` ≈ 0.68). Under the stated assumption, controlling for it identifies the estimand.\n- Standard errors: HC1 heteroskedasticity-robust (`se_type`). The conventional SE is almost the same (`effect_se_conventional`). The 95% CIs are normal-based (estimate ± 1.96·SE).\n- Fit metric: in-sample RMSE sqrt(mean(e²)) for each model.\n- Sensitivity checks (table1.csv): keeping the negative-hours rows; adding a hours×skill interaction; adding skill².\n\n## Results\n| model | estimate (pp/hour) | 95% CI |\n|---|---|---|\n| unadjusted | −0.132 (`naive_estimate`) | [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`) |\n| adjusted for skill (main) | 0.254 (`effect_estimate`) | [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`) |\n\n- On its own, the unadjusted association is negative. Once baseline skill is held fixed, one extra training hour per employee is associated with about 0.25 pp higher productivity growth the next year. Because the 95% CI lies above zero, `conclusion` = `positive_effect`.\n- The coefficient on `skill_index` is −4.62 pp per index unit (`skill_index_coefficient`). Higher-skill firms train more but grow less. That pattern pushes the unadjusted slope downward: it is classic omitted-variable bias, and the OVB identity naive = b₁ + b₂·δ holds exactly (`out/state/checks.md`).\n- RMSE falls from 3.86 pp (`baseline_metric`) to 1.98 pp (`model_metric`). R² rises from 0.07 to 0.76 (`naive_r2`, `adjusted_r2`).\n- Sensitivity: keeping the 12 negative-hours rows gives 0.252 (`sensitivity_incl_negative_hours_estimate`; the unadjusted slope is then −0.135, `naive_incl_negative_hours_estimate`). Adding skill² gives 0.254 (`sensitivity_skill_sq_estimate`). The hours×skill interaction is −0.0003 with p = 0.96 (`sensitivity_interaction_term`, `sensitivity_interaction_term_p`), so these data show no sign that the effect varies with skill.\n- Figure: `out/figure1.png` (scatter plot, unadjusted line, adjusted line evaluated at mean skill). Table: `out/table1.csv`.\n\n## Uncertainty\nThe robust SE of the main effect is 0.0098 pp/hour (`effect_se`), giving a 95% CI of [0.234, 0.273]. This interval reflects sampling error only, given the model. It does not cover model or identification uncertainty. The sensitivity estimates all fall between 0.252 and 0.254, which is well inside the main CI.\n\n## Limitations and open issues\n- **Identification rests on an untestable assumption.** The estimate is causal only if `skill_index` captures all confounding. Any unobserved factor that drives both training and growth (management quality, sector, firm size, prior growth trends, mean reversion) would bias it. The file contains no other variables, so this could not be checked. The large shift from −0.13 to +0.25 when one control is added shows how sensitive the estimate is to what is controlled for. Another omitted confounder could move it just as far.\n- **Measurement error in skill_index.** If the index measures true skill with error, the adjustment is incomplete. Because skill relates negatively to growth and positively to training, the residual bias would most likely push the estimate down. That was not quantified.\n- **Functional form.** Linearity in training hours was assumed, as the task requires. Only skill² and the interaction were checked. Nonlinearity in hours (for example, diminishing returns) was not tested.\n- **Negative training hours.** These values suggest a data-generation or recording artefact, perhaps an uncensored latent variable. Dropping them conditions on a function of treatment. The sensitivity run shows this barely matters (0.252 vs 0.254), but the true meaning of these rows is unknown.\n- **Overlap and external validity.** Low-skill firms with high training hours are rare (corr ≈ 0.68), so at the extremes the estimate partly relies on linear extrapolation. The data are simulated, so nothing here describes real firms.\n- **Not checked:** clustering or dependence between firms (none can be identified from the data), outliers and influence diagnostics beyond visual inspection, and timing problems beyond the column descriptions.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"The unadjusted OLS slope of productivity growth on training hours is negative (about -0.13 pp/hour, 95% CI excluding zero).\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Descriptive association; confounded by skill_index.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one additional training hour per employee raises next-year productivity growth by about 0.25 pp (95% CI 0.234-0.273), so conclusion = positive_effect.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal only under selection on observables given skill_index, linearity and homogeneity; untestable with these data.\"},\n {\"id\":\"C3\",\"text\":\"Skill_index is a strong negative predictor of growth and positively correlated with training, explaining the sign reversal (omitted-variable bias).\",\"results_keys\":[\"skill_index_coefficient\",\"corr_skill_training\",\"naive_estimate\",\"effect_estimate\"],\"status\":\"supported\",\"caveat\":\"OVB identity verified numerically in checks.md.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits much better than the baseline (RMSE 1.98 vs 3.86 pp).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"adjusted_r2\",\"naive_r2\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; better fit does not establish causality.\"},\n {\"id\":\"C5\",\"text\":\"The main estimate is robust to including the 12 negative-hours rows, to adding skill squared, and shows no evidence of heterogeneity by skill.\",\"results_keys\":[\"sensitivity_incl_negative_hours_estimate\",\"sensitivity_skill_sq_estimate\",\"sensitivity_interaction_term\",\"sensitivity_interaction_term_p\"],\"status\":\"supported\",\"caveat\":\"Only these specifications were checked; non-linearity in hours not tested.\"}\n]\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed (audit, exclusions ledger). P2 passed: naive OLS on analysis sample. P3 passed: analysis.py with adjusted OLS + HC1 SE, sensitivity runs.\n- 2026-10-30 P4: clean re-run identical; 13 consistency checks PASS (checks.md). Running gate.\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np={\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read; contract.md written\"],\"notes\":\"\"},\n\"P1\":{\"status\":\"passed\",\"checks\":[\"sha256 matches bundle.json\",\"schema/missing/duplicates/ranges audited (data_audit.md)\",\"exclusions.csv sums: 1200-12=1188\"],\"notes\":\"12 negative training_hours rows excluded\"},\n\"P2\":{\"status\":\"passed\",\"checks\":[\"naive OLS slope, CI and RMSE computed on analysis sample\"],\"notes\":\"\"},\n\"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py writes results.json, table1.csv, figure1.png; no randomness\"],\"notes\":\"HC1 SEs\"},\n\"P4\":{\"status\":\"running\",\"checks\":[\"clean re-run byte-identical results.json\",\"13 internal consistency checks PASS (checks.md)\"],\"notes\":\"\"},\n\"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py .; ls out/state/gate_receipts","description":"Write report, claims, ledger; run gate"}}]}}76{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"b7bd9e63-6351-4e19-a154-dd52e76e25ff","timestamp":"2026-10-30T04:07:49.676Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"602dfba9-06a1-42ba-a262-b89e837a80c9","keep":22,"tail":["d0338a6f505aa659cd98d4b6e6a789dd406f58d853b674d572140589e41db5e9","b36cdd0bdbdb9d294d53031814a89e1bcdf2d29cdc5b453f786afc294140cf0f"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"afa868c9fc6723f2ff409a12250945e703c5decafb40c96e3ff78e1aabaa586b"}77{"parentUuid":"7bededaa-7aa4-46df-b336-6815ebbb56a0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEpede71SHmXCgHrKG","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":4358,"cache_read_input_tokens":22157,"output_tokens":711,"output_tokens_details":{"thinking_tokens":42},"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":4358},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":569,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmEpN1tymTeUNXvTR1T","requestRef":"b7bd9e63-6351-4e19-a154-dd52e76e25ff","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"676eaa63-9702-405f-b72f-6d830c70dfb8","timestamp":"2026-10-30T04:07:51.584Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"676eaa63-9702-405f-b72f-6d830c70dfb8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEpede71SHmXCgHrKG","type":"message","role":"assistant","content":[{"type":"text","text":"The gate's only failure is the expected one: P4 and P5 were still open. I'm marking them passed, recording the receipts, and re-running the gate."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4358,"cache_read_input_tokens":22157,"output_tokens":711,"output_tokens_details":{"thinking_tokens":42},"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":4358},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmEpN1tymTeUNXvTR1T","requestRef":"b7bd9e63-6351-4e19-a154-dd52e76e25ff","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a6e0129f-3759-4cf4-9b8f-c8b4b7616f3b","timestamp":"2026-10-30T04:07:51.584Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}79{"parentUuid":"a6e0129f-3759-4cf4-9b8f-c8b4b7616f3b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmEpede71SHmXCgHrKG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QnYqRJKFaZDGiwq5T75oPX","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np[\"P4\"][\"status\"]=\"passed\"; p[\"P4\"][\"checks\"].append(\"gate run end of P4: receipt gate_receipts/20261030T040749.657699Z.json — 39/40 ok; only failure = phase ledger non-terminal (P4/P5 open at the time), all contract/reproducibility checks ok\")\np[\"P5\"]={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, each number cites a results key\",\"claims.json 5 claims, keys resolve\",\"final gate run end of P5 (receipt recorded in log.md)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"GATE|FAIL|receipt\"; R=$(ls out/state/gate_receipts | tail -1); echo \"- 2026-10-30 P4 passed; P5 passed. Final gate receipt: $R\" >> out/state/log.md\n~/wp29/venv/bin/python - <<EOF\nimport json\np=json.load(open('out/state/phases.json')); p[\"P5\"][\"checks\"][2]=\"final gate run end of P5: receipt gate_receipts/$R\"\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"GATE|FAIL\"","description":"Finalize ledger and rerun gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4358,"cache_read_input_tokens":22157,"output_tokens":711,"output_tokens_details":{"thinking_tokens":42},"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":4358},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXmEpN1tymTeUNXvTR1T","requestRef":"b7bd9e63-6351-4e19-a154-dd52e76e25ff","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"041912db-f153-48e0-a8ef-2077ee203764","timestamp":"2026-10-30T04:07:55.987Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}80{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"041912db-f153-48e0-a8ef-2077ee203764","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}81{"type":"atis-latch","atis":"","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}82{"parentUuid":"041912db-f153-48e0-a8ef-2077ee203764","isSidechain":false,"promptId":"588d9e92-fba5-48c3-ae2f-f152b4e3ac7f","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QnYqRJKFaZDGiwq5T75oPX","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0015/out/state/gate_receipts/20261030T040757.228693Z.json\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","is_error":false}]},"uuid":"40dfcca4-5d96-4212-b334-5d9b6aa57864","timestamp":"2026-10-30T04:07:58.471Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RC0015/out/state/gate_receipts/20261030T040757.228693Z.json\nPGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"041912db-f153-48e0-a8ef-2077ee203764","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}83{"type":"api-request-blob","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","hash":"7def0cbad7bd8a4100f468abee73b2457a74d54c8e64bfe0928f998b580da4f2","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"The gate's only failure is the expected one: P4 and P5 were still open. I'm marking them passed, recording the receipts, and re-running the gate."},{"type":"tool_use","id":"toolu_01QnYqRJKFaZDGiwq5T75oPX","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np[\"P4\"][\"status\"]=\"passed\"; p[\"P4\"][\"checks\"].append(\"gate run end of P4: receipt gate_receipts/20261030T040749.657699Z.json — 39/40 ok; only failure = phase ledger non-terminal (P4/P5 open at the time), all contract/reproducibility checks ok\")\np[\"P5\"]={\"status\":\"passed\",\"checks\":[\"report.md with 6 sections, each number cites a results key\",\"claims.json 5 claims, keys resolve\",\"final gate run end of P5 (receipt recorded in log.md)\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"GATE|FAIL|receipt\"; R=$(ls out/state/gate_receipts | tail -1); echo \"- 2026-10-30 P4 passed; P5 passed. Final gate receipt: $R\" >> out/state/log.md\n~/wp29/venv/bin/python - <<EOF\nimport json\np=json.load(open('out/state/phases.json')); p[\"P5\"][\"checks\"][2]=\"final gate run end of P5: receipt gate_receipts/$R\"\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -E \"GATE|FAIL\"","description":"Finalize ledger and rerun gate"}}]}}84{"type":"api-request","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","id":"4e19b99d-108a-4424-ba8e-a2a1ddde5bde","timestamp":"2026-10-30T04:07:58.475Z","version":"2.1.314","querySource":"sdk","shapeHash":"bec39a5d6081c8f2e8a4dc8b978f50d3d27e26519599b1018c7d154b2d01a008","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":"b7bd9e63-6351-4e19-a154-dd52e76e25ff","keep":24,"tail":["7def0cbad7bd8a4100f468abee73b2457a74d54c8e64bfe0928f998b580da4f2","336238ddb181b0cc0283a9a5a2c0b154d4dcb534870d8bc3eee94422f9dbc8d5"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c68837f6178e9d8ac725fe611417c17e1e04074b41460cc89a793651584a6e42"}85{"parentUuid":"40dfcca4-5d96-4212-b334-5d9b6aa57864","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmFUGZL3KfgjgSrzVn5","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":842,"cache_read_input_tokens":26515,"output_tokens":830,"output_tokens_details":{"thinking_tokens":30},"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":842},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6539,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmFTyhFr5F2pL7CUU52","requestRef":"4e19b99d-108a-4424-ba8e-a2a1ddde5bde","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"5e6ef9d1-5480-4120-a8e4-2469584d877f","timestamp":"2026-10-30T04:08:06.507Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"5e6ef9d1-5480-4120-a8e4-2469584d877f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmFUGZL3KfgjgSrzVn5","type":"message","role":"assistant","content":[{"type":"text","text":"Once firms are compared at the same baseline skill level, one extra training hour per employee is linked to about **0.25 percentage points** higher productivity growth the next year, with a 95% CI of 0.234 to 0.273. The conclusion code is therefore `positive_effect`. The final gate run passed all 40 checks, and re-running `out/analysis.py` from scratch reproduces the same results.\n\n**Main results** (from `out/results.json`):\n\n| Model | Estimate (pp per hour) | 95% CI | Residual RMSE |\n|---|---|---|---|\n| Unadjusted (required baseline) | −0.132 | −0.160 to −0.103 | 3.86 pp |\n| Adjusted for `skill_index` (main) | 0.254 | 0.234 to 0.273 | 1.98 pp |\n\n- **Why the sign flips:** firms with higher baseline skill train more (correlation about 0.68) but grow less (−4.62 pp per index unit). Leaving skill out drags the unadjusted slope below zero, a classic omitted-variable bias.\n- **Standard errors:** I used heteroskedasticity-robust (HC1) errors; the main SE is 0.0098, and the conventional SE is almost identical.\n- **Data problem:** 12 firms have negative training hours, which is impossible. I dropped them, leaving 1,188 firms. Keeping them changes the estimate only slightly (0.252 instead of 0.254), and the exclusion is logged in `out/exclusions.csv`.\n- **Other checks:** adding skill squared gives 0.254, and there is no sign that the effect varies with skill (interaction p = 0.96).\n\n**Limitations:**\n- The estimate is causal only if baseline skill accounts for all confounding. That can't be tested, because the file has no other variables. Adding this one control moved the estimate from −0.13 to +0.25, so another missing factor could move it just as far.\n- I did not check measurement error in the skill index, nonlinear effects of training hours, or influential outliers.\n- The data are simulated, so nothing here describes real firms.\n\nEverything is in `out/`: `analysis.py` (the replication script), `results.json`, `report.md`, `claims.json` (5 claims), `figure1.png`, `table1.csv` (the two models above plus three robustness variants) and `exclusions.csv`. Working notes and verification checks are in `out/state/`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":842,"cache_read_input_tokens":26515,"output_tokens":830,"output_tokens_details":{"thinking_tokens":30},"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":842},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmFTyhFr5F2pL7CUU52","requestRef":"4e19b99d-108a-4424-ba8e-a2a1ddde5bde","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fe5e3331-55e3-4152-bf1a-c0c836279376","timestamp":"2026-10-30T04:08:06.981Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0015","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","version":"2.1.314","gitBranch":"HEAD"}87{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"fe5e3331-55e3-4152-bf1a-c0c836279376","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d"}88{"type":"cost-state","sessionId":"e0307a28-de07-4f7b-8a06-334ae241306d","totalCostUSD":0.46625120000000003,"totalAPIDuration":128523,"totalAPIDurationWithoutRetries":128517,"totalToolDuration":9406,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":138120,"startTime":1793333148871,"modelUsage":{"claude-opus-5-5":{"inputTokens":28,"outputTokens":15109,"thinkingTokens":483,"cacheReadInputTokens":173471,"cacheCreationInputTokens":25853,"cacheCreationEphemeral5mInputTokens":25853,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.46625120000000003}},"hasUnknownModelCost":false}89