spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T03:49:47.729Z","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T03:49:47.735Z","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}4{"parentUuid":null,"isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":"Begin"},"uuid":"fbccd860-4ef2-4086-b004-0d8ffd1f3d5d","timestamp":"2026-10-30T03:49:47.739Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","timestamp":"2026-10-30T03:49:47.754Z","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/RP0013\nDate: 2026-10-29\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"}],"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":"57602e14-17cc-47c9-884e-1967d9060309","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"76ea16a8-0101-40fe-9487-19941cebb08f","timestamp":"2026-10-30T03:49:47.754Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"88fb82b2d1eb2b8baed772e6027997baef4550e7119a88468eb2b3758ea8e86b"}8{"parentUuid":"fbccd860-4ef2-4086-b004-0d8ffd1f3d5d","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"8d03a54c-4450-4db9-ad2f-6fa506fa8751","timestamp":"2026-10-30T03:49:47.744Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"8d03a54c-4450-4db9-ad2f-6fa506fa8751","isSidechain":false,"attachment":{"type":"date","date":"2026-10-29"},"type":"attachment","uuid":"a11c8386-ed6a-4cc1-bf63-f0b970376549","timestamp":"2026-10-30T03:49:47.745Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-29.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"a11c8386-ed6a-4cc1-bf63-f0b970376549","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":"0bcea143-51f8-4840-9af9-4630facb06e2","timestamp":"2026-10-30T03:49:47.745Z","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/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}12{"parentUuid":"0bcea143-51f8-4840-9af9-4630facb06e2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjs4vt5z7m1LH2uYqaK","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":2603,"cache_read_input_tokens":1504,"output_tokens":126,"output_tokens_details":{"thinking_tokens":20},"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":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":423,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXjs4dXKqvob9UshwSe5","requestRef":"76ea16a8-0101-40fe-9487-19941cebb08f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9214f99e-ce16-4201-a961-939515976712","timestamp":"2026-10-30T03:49:49.459Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"9214f99e-ce16-4201-a961-939515976712","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjs4vt5z7m1LH2uYqaK","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LEaCiZWkcd3jQtPA8e6uXR","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2603,"cache_read_input_tokens":1504,"output_tokens":126,"output_tokens_details":{"thinking_tokens":20},"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":2603},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjs4dXKqvob9UshwSe5","requestRef":"76ea16a8-0101-40fe-9487-19941cebb08f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"85829fae-d47f-4d54-ad7d-983e336619e3","timestamp":"2026-10-30T03:49:50.057Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"85829fae-d47f-4d54-ad7d-983e336619e3","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LEaCiZWkcd3jQtPA8e6uXR","type":"tool_result","content":"# F6-dev-01 — Income and life expectancy across countries: a bounded mini-project\n\n## Scientific question\nDoes the cross-country relationship between real income per capita and life expectancy (the \"Preston curve\") hold in the most recent year with usable World Bank data, and how strong is it? The estimand is the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies (one equally weighted observation per country) in the analysis year, where LE is life expectancy at birth (years) and GDPpc is GDP per capita in PPP constant 2021 international dollars, with heteroskedasticity-robust uncertainty. The task is a complete, bounded chain: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report. \"Effect\" is used here in the descriptive, associational sense: no causal claim is requested.\n\n## Inputs\n- `data/wb_indicators.csv` — observed data, World Bank World Development Indicators (retrieved 2026-10-30, CC BY 4.0; full provenance, URLs and SHA-256 in `data/README.md`). One row per entity-year, 2015–2023. Columns: `iso3`, `name`, `year`, `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international $; empty if not reported), `life_expectancy` (years; empty if not reported). The file is the API download for *all* World Bank entities, so it contains countries/economies as well as regional and income-group aggregates.\n- `data/wb_entities.csv` — World Bank entity metadata: `iso3`, `name`, `region` (the value `Aggregates` marks groupings that are not countries/economies), `income_level`, `lending_type`.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- The analysis population is countries/economies only: exclude every entity whose `region` is `Aggregates` in `wb_entities.csv`.\n- The analysis year is the most recent year (2015–2023) in which both indicators are observed for at least 150 countries/economies. Report it as `analysis_year`.\n- In the analysis year, countries/economies with either indicator missing are excluded from the estimate and counted in `n_excluded_missing`. No imputation.\n- Use the natural logarithm of GDP per capita. Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `analysis_year` | integer | year | year selected by the rule above |\n| `n_excluded_missing` | integer | countries | countries/economies present in `wb_indicators.csv` for the analysis year but dropped for a missing indicator |\n| `baseline_metric` | number | years | RMSE of the mean-only prediction of life expectancy, sqrt(mean((LE − mean LE)²)) over the analysed countries (the no-information baseline) |\n| `model_metric` | number | years | RMSE of the OLS residuals, sqrt(mean(e²)) |\n| `pearson_r` | number | — | Pearson correlation between ln(GDPpc) and LE |\n| `r_squared` | number | — | R² of the OLS regression |\n| `effect_estimate` | number | years per log-point | OLS slope β |\n| `intercept` | number | years | OLS intercept α |\n| `effect_se` | number | years per log-point | heteroskedasticity-robust standard error of β (HC0–HC3; state which in the report) |\n| `effect_ci_low`, `effect_ci_high` | number | years per log-point | 95% confidence interval for β based on `effect_se` |\n| `conclusion` | string | — | one of the codes below |\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 life expectancy against ln(GDP per capita) for the analysed countries with the fitted OLS line, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per World Bank income level present among the analysed countries, with columns `income_level`, `n_countries`, `mean_log_gdp_pc`, `mean_life_expectancy` (header row + 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 23:42 .\ndrwxr-xr-x  13 simon-pierreboucher  staff   416 oct.  29 23:49 ..\n-rw-r--r--   1 simon-pierreboucher  staff   611 oct.  29 23:42 bundle.json\ndrwxr-xr-x   5 simon-pierreboucher  staff   160 oct.  29 23:27 data\n-rw-r--r--   1 simon-pierreboucher  staff  2284 oct.  29 23:35 gate_spec.json\n-rw-r--r--   1 simon-pierreboucher  staff  6165 oct.  29 23:35 TASK.md\ndata:\nREADME.md\nwb_entities.csv\nwb_indicators.csv","is_error":false}]},"uuid":"f2bd3d33-79a2-487f-b955-12f4b86f9ea1","timestamp":"2026-10-30T03:49:50.166Z","toolUseResult":{"stdout":"# F6-dev-01 — Income and life expectancy across countries: a bounded mini-project\n\n## Scientific question\nDoes the cross-country relationship between real income per capita and life expectancy (the \"Preston curve\") hold in the most recent year with usable World Bank data, and how strong is it? The estimand is the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i across countries/economies (one equally weighted observation per country) in the analysis year, where LE is life expectancy at birth (years) and GDPpc is GDP per capita in PPP constant 2021 international dollars, with heteroskedasticity-robust uncertainty. The task is a complete, bounded chain: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report. \"Effect\" is used here in the descriptive, associational sense: no causal claim is requested.\n\n## Inputs\n- `data/wb_indicators.csv` — observed data, World Bank World Development Indicators (retrieved 2026-10-30, CC BY 4.0; full provenance, URLs and SHA-256 in `data/README.md`). One row per entity-year, 2015–2023. Columns: `iso3`, `name`, `year`, `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international $; empty if not reported), `life_expectancy` (years; empty if not reported). The file is the API download for *all* World Bank entities, so it contains countries/economies as well as regional and income-group aggregates.\n- `data/wb_entities.csv` — World Bank entity metadata: `iso3`, `name`, `region` (the value `Aggregates` marks groupings that are not countries/economies), `income_level`, `lending_type`.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- The analysis population is countries/economies only: exclude every entity whose `region` is `Aggregates` in `wb_entities.csv`.\n- The analysis year is the most recent year (2015–2023) in which both indicators are observed for at least 150 countries/economies. Report it as `analysis_year`.\n- In the analysis year, countries/economies with either indicator missing are excluded from the estimate and counted in `n_excluded_missing`. No imputation.\n- Use the natural logarithm of GDP per capita. Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `analysis_year` | integer | year | year selected by the rule above |\n| `n_excluded_missing` | integer | countries | countries/economies present in `wb_indicators.csv` for the analysis year but dropped for a missing indicator |\n| `baseline_metric` | number | years | RMSE of the mean-only prediction of life expectancy, sqrt(mean((LE − mean LE)²)) over the analysed countries (the no-information baseline) |\n| `model_metric` | number | years | RMSE of the OLS residuals, sqrt(mean(e²)) |\n| `pearson_r` | number | — | Pearson correlation between ln(GDPpc) and LE |\n| `r_squared` | number | — | R² of the OLS regression |\n| `effect_estimate` | number | years per log-point | OLS slope β |\n| `intercept` | number | years | OLS intercept α |\n| `effect_se` | number | years per log-point | heteroskedasticity-robust standard error of β (HC0–HC3; state which in the report) |\n| `effect_ci_low`, `effect_ci_high` | number | years per log-point | 95% confidence interval for β based on `effect_se` |\n| `conclusion` | string | — | one of the codes below |\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 life expectancy against ln(GDP per capita) for the analysed countries with the fitted OLS line, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per World Bank income level present among the analysed countries, with columns `income_level`, `n_countries`, `mean_log_gdp_pc`, `mean_life_expectancy` (header row + 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 23:42 .\ndrwxr-xr-x  13 simon-pierreboucher  staff   416 oct.  29 23:49 ..\n-rw-r--r--   1 simon-pierreboucher  staff   611 oct.  29 23:42 bundle.json\ndrwxr-xr-x   5 simon-pierreboucher  staff   160 oct.  29 23:27 data\n-rw-r--r--   1 simon-pierreboucher  staff  2284 oct.  29 23:35 gate_spec.json\n-rw-r--r--   1 simon-pierreboucher  staff  6165 oct.  29 23:35 TASK.md\ndata:\nREADME.md\nwb_entities.csv\nwb_indicators.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"85829fae-d47f-4d54-ad7d-983e336619e3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}15{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f2bd3d33-79a2-487f-b955-12f4b86f9ea1","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}16{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}17{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"5a960db36c9549975ea086584b60645dc1f347042c486ea08510de8fd52798e8","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01LEaCiZWkcd3jQtPA8e6uXR","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}18{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"69d7a203-bf6d-4efe-af49-a26b3b4b74b3","timestamp":"2026-10-30T03:49:50.171Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"76ea16a8-0101-40fe-9487-19941cebb08f","keep":2,"tail":["5a960db36c9549975ea086584b60645dc1f347042c486ea08510de8fd52798e8","a16e110d4ce194bebe88f3b64fa13e8fcc52c725415594896e6be6357eca17cb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b4551f08978a50f204743122940056cc1cf847fdb20dbead8db9aaecfd6532ea"}19{"parentUuid":"f2bd3d33-79a2-487f-b955-12f4b86f9ea1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjsDpfNa1WirngBa2Ng","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Lq3RFBXM1k3n1KCQFCYxjj","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json bundle.json; head -5 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data files and gate spec"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2640,"cache_read_input_tokens":4107,"output_tokens":133,"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":2640},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXjsDZ42WYz9ZjDSJkdA","requestRef":"69d7a203-bf6d-4efe-af49-a26b3b4b74b3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"88ffd810-8841-41b1-9de7-ec1b257d805f","timestamp":"2026-10-30T03:49:51.940Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"88ffd810-8841-41b1-9de7-ec1b257d805f","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Lq3RFBXM1k3n1KCQFCYxjj","type":"tool_result","content":"# Data provenance — F6-dev-01\n\nAll files are observed data from the World Bank World Development Indicators (WDI), retrieved by the task author with `curl` on 2026-10-30T03:23:28Z.\nLicense: World Bank open data, Creative Commons Attribution 4.0 (CC BY 4.0), https://datacatalog.worldbank.org/public-licenses#cc-by\n\n## `wb_indicators.csv` (2349 rows)\nLong table, one row per entity-year, years 2015–2023, built by merging two API responses on (ISO3 code, year):\n- `NY.GDP.PCAP.PP.KD` — GDP per capita, PPP (constant 2021 international $). URL: `https://api.worldbank.org/v2/country/all/indicator/NY.GDP.PCAP.PP.KD?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `742e87326d9748e0873cd996d9d4ebdf9464bec10ccd24a97d66b07e651789ec`)\n- `SP.DYN.LE00.IN` — Life expectancy at birth, total (years). URL: `https://api.worldbank.org/v2/country/all/indicator/SP.DYN.LE00.IN?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `6bb51828124409f555b5089900a507aa62a0a17523ec3608b4b51bb5c6928d04`)\n\nColumns: `iso3` (ISO-3166 alpha-3 code as returned by the API), `name` (entity name), `year` (integer), `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international dollars; empty = not reported), `life_expectancy` (years; empty = not reported).\nThe API endpoint `country/all` returns every entity in the World Bank database, i.e. countries/economies **and** regional, income-group and other aggregates. 45 records whose `countryiso3code` field was empty in the API response (a few income-group aggregates identified only by a 2-letter code) were dropped during preparation; nothing else was altered.\nSHA-256 of `wb_indicators.csv`: `6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0`\n\n## `wb_entities.csv` (296 rows)\nEntity metadata from `https://api.worldbank.org/v2/country?format=json&per_page=400` (raw response SHA-256 `c9acf3932785191a649cbc04c3056af4cf64a236e5c3b49d49be25ddb0440bce`).\nColumns: `iso3`, `name`, `region` (World Bank region; the value `Aggregates` marks entities that are regional, income or other groupings rather than countries/economies), `income_level`, `lending_type`.\nSHA-256 of `wb_entities.csv`: `06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d`\n{\n  \"task_id\": \"F6-dev-01\",\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    \"analysis_year\": {\n      \"type\": \"integer\",\n      \"nullable\": false\n    },\n    \"n_excluded_missing\": {\n      \"type\": \"integer\",\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    \"pearson_r\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"r_squared\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_estimate\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"intercept\": {\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    \"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      \"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-dev-01\",\n  \"family\": \"F6\",\n  \"split\": \"dev\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T03:42:41.723569+00:00\",\n  \"files\": {\n    \"TASK.md\": \"6aa11fe5b23688a6084aeca7e83157ee4240169267dc7bc77d3da5e9fd8567e5\",\n    \"data/README.md\": \"76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a\",\n    \"data/wb_entities.csv\": \"06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d\",\n    \"data/wb_indicators.csv\": \"6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0\",\n    \"gate_spec.json\": \"2f6efaa4406577bd9a1133182ff2b15374cd250cad0229cf79c8e3f48ed6b3c3\"\n  }\n}==> data/wb_entities.csv <==\niso3,name,region,income_level,lending_type\nABW,Aruba,Latin America & Caribbean,High income,Not classified\nAFE,Africa Eastern and Southern,Aggregates,Aggregates,Aggregates\nAFG,Afghanistan,\"Middle East, North Africa, Afghanistan & Pakistan\",Low income,IDA\nAFR,Africa,Aggregates,Aggregates,Aggregates\n\n==> data/wb_indicators.csv <==\niso3,name,year,gdp_pc_ppp,life_expectancy\nABW,Aruba,2015,36753.404173,75.405000\nABW,Aruba,2016,36926.113069,75.540000\nABW,Aruba,2017,38213.289239,75.620000\nABW,Aruba,2018,39378.228411,75.880000\n     297 data/wb_entities.csv\n    2350 data/wb_indicators.csv\n    2647 total\n76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a  data/README.md\n06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d  data/wb_entities.csv\n6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0  data/wb_indicators.csv","is_error":false}]},"uuid":"a591c93c-06b9-4e3c-b55c-dbc23e24dd7b","timestamp":"2026-10-30T03:49:52.003Z","toolUseResult":{"stdout":"# Data provenance — F6-dev-01\n\nAll files are observed data from the World Bank World Development Indicators (WDI), retrieved by the task author with `curl` on 2026-10-30T03:23:28Z.\nLicense: World Bank open data, Creative Commons Attribution 4.0 (CC BY 4.0), https://datacatalog.worldbank.org/public-licenses#cc-by\n\n## `wb_indicators.csv` (2349 rows)\nLong table, one row per entity-year, years 2015–2023, built by merging two API responses on (ISO3 code, year):\n- `NY.GDP.PCAP.PP.KD` — GDP per capita, PPP (constant 2021 international $). URL: `https://api.worldbank.org/v2/country/all/indicator/NY.GDP.PCAP.PP.KD?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `742e87326d9748e0873cd996d9d4ebdf9464bec10ccd24a97d66b07e651789ec`)\n- `SP.DYN.LE00.IN` — Life expectancy at birth, total (years). URL: `https://api.worldbank.org/v2/country/all/indicator/SP.DYN.LE00.IN?format=json&per_page=20000&date=2015:2023` (raw response SHA-256 `6bb51828124409f555b5089900a507aa62a0a17523ec3608b4b51bb5c6928d04`)\n\nColumns: `iso3` (ISO-3166 alpha-3 code as returned by the API), `name` (entity name), `year` (integer), `gdp_pc_ppp` (GDP per capita, PPP, constant 2021 international dollars; empty = not reported), `life_expectancy` (years; empty = not reported).\nThe API endpoint `country/all` returns every entity in the World Bank database, i.e. countries/economies **and** regional, income-group and other aggregates. 45 records whose `countryiso3code` field was empty in the API response (a few income-group aggregates identified only by a 2-letter code) were dropped during preparation; nothing else was altered.\nSHA-256 of `wb_indicators.csv`: `6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0`\n\n## `wb_entities.csv` (296 rows)\nEntity metadata from `https://api.worldbank.org/v2/country?format=json&per_page=400` (raw response SHA-256 `c9acf3932785191a649cbc04c3056af4cf64a236e5c3b49d49be25ddb0440bce`).\nColumns: `iso3`, `name`, `region` (World Bank region; the value `Aggregates` marks entities that are regional, income or other groupings rather than countries/economies), `income_level`, `lending_type`.\nSHA-256 of `wb_entities.csv`: `06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d`\n{\n  \"task_id\": \"F6-dev-01\",\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    \"analysis_year\": {\n      \"type\": \"integer\",\n      \"nullable\": false\n    },\n    \"n_excluded_missing\": {\n      \"type\": \"integer\",\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    \"pearson_r\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"r_squared\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"effect_estimate\": {\n      \"type\": \"number\",\n      \"nullable\": false\n    },\n    \"intercept\": {\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    \"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      \"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-dev-01\",\n  \"family\": \"F6\",\n  \"split\": \"dev\",\n  \"version\": \"1.0\",\n  \"created_utc\": \"2026-10-30T03:42:41.723569+00:00\",\n  \"files\": {\n    \"TASK.md\": \"6aa11fe5b23688a6084aeca7e83157ee4240169267dc7bc77d3da5e9fd8567e5\",\n    \"data/README.md\": \"76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a\",\n    \"data/wb_entities.csv\": \"06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d\",\n    \"data/wb_indicators.csv\": \"6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0\",\n    \"gate_spec.json\": \"2f6efaa4406577bd9a1133182ff2b15374cd250cad0229cf79c8e3f48ed6b3c3\"\n  }\n}==> data/wb_entities.csv <==\niso3,name,region,income_level,lending_type\nABW,Aruba,Latin America & Caribbean,High income,Not classified\nAFE,Africa Eastern and Southern,Aggregates,Aggregates,Aggregates\nAFG,Afghanistan,\"Middle East, North Africa, Afghanistan & Pakistan\",Low income,IDA\nAFR,Africa,Aggregates,Aggregates,Aggregates\n\n==> data/wb_indicators.csv <==\niso3,name,year,gdp_pc_ppp,life_expectancy\nABW,Aruba,2015,36753.404173,75.405000\nABW,Aruba,2016,36926.113069,75.540000\nABW,Aruba,2017,38213.289239,75.620000\nABW,Aruba,2018,39378.228411,75.880000\n     297 data/wb_entities.csv\n    2350 data/wb_indicators.csv\n    2647 total\n76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a  data/README.md\n06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d  data/wb_entities.csv\n6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0  data/wb_indicators.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"88ffd810-8841-41b1-9de7-ec1b257d805f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"9b48675255e31e93f4ac822e25580a632be5cf02ae7510bce61982bfb6131e90","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Lq3RFBXM1k3n1KCQFCYxjj","name":"Bash","input":{"command":"cat data/README.md; cat gate_spec.json bundle.json; head -5 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*","description":"Inspect data files and gate spec"}}]}}22{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"55f6a565-6a14-4458-9654-5d99ef6d09b1","timestamp":"2026-10-30T03:49:52.006Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"69d7a203-bf6d-4efe-af49-a26b3b4b74b3","keep":4,"tail":["9b48675255e31e93f4ac822e25580a632be5cf02ae7510bce61982bfb6131e90","aeefb4be2f5be2869bbf2fca3331c6a5ff658032ed7f4551fe43b3f77d66a8b2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9db5889f83afe933252173cfce006cd3c314127dbc78bb233c9fc650ab1f9213"}23{"parentUuid":"a591c93c-06b9-4e3c-b55c-dbc23e24dd7b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjsMfDNGRQyi4ouVFUG","type":"message","role":"assistant","content":[{"type":"text","text":"Hashes match. Now a data audit exploration."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2971,"cache_read_input_tokens":6747,"output_tokens":727,"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":2971},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXjsMQ61yBd7jUpYrkba","requestRef":"55f6a565-6a14-4458-9654-5d99ef6d09b1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"aadbed6f-c76a-4e86-bcd1-123a4850af59","timestamp":"2026-10-30T03:49:53.029Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}24{"parentUuid":"aadbed6f-c76a-4e86-bcd1-123a4850af59","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjsMfDNGRQyi4ouVFUG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011cQ713PfwVrxw9BQUD6jYd","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nind=pd.read_csv('data/wb_indicators.csv',keep_default_na=False,na_values=[''])\nent=pd.read_csv('data/wb_entities.csv',keep_default_na=False,na_values=[''])\nprint(ind.dtypes); print(ind.describe(include='all').T)\nprint(ent.region.value_counts()); print(ent.income_level.value_counts())\nprint('dup ind',ind.duplicated(['iso3','year']).sum(),'dup ent',ent.duplicated('iso3').sum())\nprint('ind iso not in ent', sorted(set(ind.iso3)-set(ent.iso3)))\nprint('ent iso not in ind', sorted(set(ent.iso3)-set(ind.iso3)))\nprint(ind.isna().sum())\nagg=set(ent.iso3[ent.region=='Aggregates'])\nc=ind[~ind.iso3.isin(agg)]\nprint('country rows',len(c), c.iso3.nunique())\nprint(c.groupby('year').apply(lambda d: pd.Series({'n':len(d),'both':(d.gdp_pc_ppp.notna()&d.life_expectancy.notna()).sum(),'gdp':d.gdp_pc_ppp.notna().sum(),'le':d.life_expectancy.notna().sum()})))\nprint(c.groupby('iso3').size().value_counts())\nprint('nonpos gdp',(ind.gdp_pc_ppp<=0).sum(), ind.life_expectancy.min(), ind.life_expectancy.max())\nprint(ent[ent.iso3.isna()|ent.region.isna()|ent.income_level.isna()])\nprint(ent.loc[~ent.iso3.isin(agg),'income_level'].value_counts())\n\"","description":"Audit data structure and coverage"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2971,"cache_read_input_tokens":6747,"output_tokens":727,"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":2971},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjsMQ61yBd7jUpYrkba","requestRef":"55f6a565-6a14-4458-9654-5d99ef6d09b1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ea216b79-ea19-49c8-81b4-7c85e96976d3","timestamp":"2026-10-30T03:49:58.148Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"ea216b79-ea19-49c8-81b4-7c85e96976d3","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011cQ713PfwVrxw9BQUD6jYd","type":"tool_result","content":"<string>:14: FutureWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\niso3                object\nname                object\nyear                 int64\ngdp_pc_ppp         float64\nlife_expectancy    float64\ndtype: object\n                  count unique  ...           75%            max\niso3               2349    261  ...           NaN            NaN\nname               2349    261  ...           NaN            NaN\nyear             2349.0    NaN  ...        2021.0         2023.0\ngdp_pc_ppp       2185.0    NaN  ...  35798.041275  139541.157249\nlife_expectancy  2349.0    NaN  ...        77.814         86.372\n\n[5 rows x 11 columns]\nregion\nAggregates                                           79\nEurope & Central Asia                                58\nSub-Saharan Africa                                   48\nLatin America & Caribbean                            42\nEast Asia & Pacific                                  37\nMiddle East, North Africa, Afghanistan & Pakistan    23\nSouth Asia                                            6\nNorth America                                         3\nName: count, dtype: int64\nincome_level\nHigh income            86\nAggregates             79\nUpper middle income    59\nLower middle income    47\nLow income             25\nName: count, dtype: int64\ndup ind 0 dup ent 0\nind iso not in ent []\nent iso not in ind ['AFR', 'BEA', 'BEC', 'BHI', 'BLA', 'BMN', 'BSS', 'CAA', 'CEA', 'CEU', 'CLA', 'CME', 'CSA', 'DEA', 'DEC', 'DLA', 'DMN', 'DNS', 'DSA', 'DSF', 'DSS', 'FXS', 'HIC', 'IBB', 'INX', 'LIC', 'LMC', 'MDE', 'NAF', 'NRS', 'NXS', 'RRS', 'SXZ', 'UMC', 'XZN']\niso3                 0\nname                 0\nyear                 0\ngdp_pc_ppp         164\nlife_expectancy      0\ndtype: int64\ncountry rows 1953 217\n        n  both  gdp   le\nyear                     \n2015  217   199  199  217\n2016  217   199  199  217\n2017  217   199  199  217\n2018  217   199  199  217\n2019  217   199  199  217\n2020  217   199  199  217\n2021  217   199  199  217\n2022  217   199  199  217\n2023  217   197  197  217\n9    217\nName: count, dtype: int64\nnonpos gdp 0 18.818 86.372\nEmpty DataFrame\nColumns: [iso3, name, region, income_level, lending_type]\nIndex: []\nincome_level\nHigh income            86\nUpper middle income    59\nLower middle income    47\nLow income             25\nName: count, dtype: int64","is_error":false}]},"uuid":"a9e27b55-2c09-4eca-a88a-27bae40f4e0d","timestamp":"2026-10-30T03:49:58.461Z","toolUseResult":{"stdout":"<string>:14: FutureWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\niso3                object\nname                object\nyear                 int64\ngdp_pc_ppp         float64\nlife_expectancy    float64\ndtype: object\n                  count unique  ...           75%            max\niso3               2349    261  ...           NaN            NaN\nname               2349    261  ...           NaN            NaN\nyear             2349.0    NaN  ...        2021.0         2023.0\ngdp_pc_ppp       2185.0    NaN  ...  35798.041275  139541.157249\nlife_expectancy  2349.0    NaN  ...        77.814         86.372\n\n[5 rows x 11 columns]\nregion\nAggregates                                           79\nEurope & Central Asia                                58\nSub-Saharan Africa                                   48\nLatin America & Caribbean                            42\nEast Asia & Pacific                                  37\nMiddle East, North Africa, Afghanistan & Pakistan    23\nSouth Asia                                            6\nNorth America                                         3\nName: count, dtype: int64\nincome_level\nHigh income            86\nAggregates             79\nUpper middle income    59\nLower middle income    47\nLow income             25\nName: count, dtype: int64\ndup ind 0 dup ent 0\nind iso not in ent []\nent iso not in ind ['AFR', 'BEA', 'BEC', 'BHI', 'BLA', 'BMN', 'BSS', 'CAA', 'CEA', 'CEU', 'CLA', 'CME', 'CSA', 'DEA', 'DEC', 'DLA', 'DMN', 'DNS', 'DSA', 'DSF', 'DSS', 'FXS', 'HIC', 'IBB', 'INX', 'LIC', 'LMC', 'MDE', 'NAF', 'NRS', 'NXS', 'RRS', 'SXZ', 'UMC', 'XZN']\niso3                 0\nname                 0\nyear                 0\ngdp_pc_ppp         164\nlife_expectancy      0\ndtype: int64\ncountry rows 1953 217\n        n  both  gdp   le\nyear                     \n2015  217   199  199  217\n2016  217   199  199  217\n2017  217   199  199  217\n2018  217   199  199  217\n2019  217   199  199  217\n2020  217   199  199  217\n2021  217   199  199  217\n2022  217   199  199  217\n2023  217   197  197  217\n9    217\nName: count, dtype: int64\nnonpos gdp 0 18.818 86.372\nEmpty DataFrame\nColumns: [iso3, name, region, income_level, lending_type]\nIndex: []\nincome_level\nHigh income            86\nUpper middle income    59\nLower middle income    47\nLow income             25\nName: count, dtype: int64","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ea216b79-ea19-49c8-81b4-7c85e96976d3","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}26{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"db999fec6852e69fd461f1d2896b7976d3b63302648a6d8dc22f784455f5e79f","message":{"role":"assistant","content":[{"type":"text","text":"Hashes match. Now a data audit exploration."},{"type":"tool_use","id":"toolu_011cQ713PfwVrxw9BQUD6jYd","name":"Bash","input":{"command":"mkdir -p out/state; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nind=pd.read_csv('data/wb_indicators.csv',keep_default_na=False,na_values=[''])\nent=pd.read_csv('data/wb_entities.csv',keep_default_na=False,na_values=[''])\nprint(ind.dtypes); print(ind.describe(include='all').T)\nprint(ent.region.value_counts()); print(ent.income_level.value_counts())\nprint('dup ind',ind.duplicated(['iso3','year']).sum(),'dup ent',ent.duplicated('iso3').sum())\nprint('ind iso not in ent', sorted(set(ind.iso3)-set(ent.iso3)))\nprint('ent iso not in ind', sorted(set(ent.iso3)-set(ind.iso3)))\nprint(ind.isna().sum())\nagg=set(ent.iso3[ent.region=='Aggregates'])\nc=ind[~ind.iso3.isin(agg)]\nprint('country rows',len(c), c.iso3.nunique())\nprint(c.groupby('year').apply(lambda d: pd.Series({'n':len(d),'both':(d.gdp_pc_ppp.notna()&d.life_expectancy.notna()).sum(),'gdp':d.gdp_pc_ppp.notna().sum(),'le':d.life_expectancy.notna().sum()})))\nprint(c.groupby('iso3').size().value_counts())\nprint('nonpos gdp',(ind.gdp_pc_ppp<=0).sum(), ind.life_expectancy.min(), ind.life_expectancy.max())\nprint(ent[ent.iso3.isna()|ent.region.isna()|ent.income_level.isna()])\nprint(ent.loc[~ent.iso3.isin(agg),'income_level'].value_counts())\n\"","description":"Audit data structure and coverage"}}]}}27{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"d098c736-9f38-48e3-87d4-f7382472523e","timestamp":"2026-10-30T03:49:58.466Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"55f6a565-6a14-4458-9654-5d99ef6d09b1","keep":6,"tail":["db999fec6852e69fd461f1d2896b7976d3b63302648a6d8dc22f784455f5e79f","335098253203ce2be423a9afc52ad9ca6503563294a7256d3ecbc20ac99bd5cd"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"53818adf38c0f83ee03a444aa008a09310e80951179e0da3ac871971067cac31"}28{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a9e27b55-2c09-4eca-a88a-27bae40f4e0d","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}29{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}30{"parentUuid":"a9e27b55-2c09-4eca-a88a-27bae40f4e0d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjsqJsM7FB1Xj1JzASy","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":1745,"cache_read_input_tokens":9718,"output_tokens":617,"output_tokens_details":{"thinking_tokens":128},"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":1745},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1229,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXjsq2EtgK1qtqvEeViF","requestRef":"d098c736-9f38-48e3-87d4-f7382472523e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"97c96460-9ee8-49df-ac65-78354013e39e","timestamp":"2026-10-30T03:50:01.033Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}31{"parentUuid":"97c96460-9ee8-49df-ac65-78354013e39e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjsqJsM7FB1Xj1JzASy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KSTz242234Ry2UPBCdKXCT","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nind=pd.read_csv('data/wb_indicators.csv')\nent=pd.read_csv('data/wb_entities.csv',keep_default_na=False,na_values=[''])\nagg=set(ent.iso3[ent.region=='Aggregates'])\nc=ind[~ind.iso3.isin(agg)]\nprint(c.nsmallest(12,'life_expectancy'))\nprint(c.nlargest(5,'life_expectancy'))\nprint(c.nlargest(5,'gdp_pc_ppp')); print(c.nsmallest(5,'gdp_pc_ppp'))\nd=c[c.year==2023]; print(d[d.gdp_pc_ppp.isna()][['iso3','name']].to_string())\nprint(d.life_expectancy.value_counts().head())\n# check LE jumps\nc=c.sort_values(['iso3','year']); c['dle']=c.groupby('iso3').life_expectancy.diff()\nprint(c.loc[c.dle.abs()>5,['iso3','name','year','life_expectancy','dle']])\nprint(ind[ind.iso3=='NAM'].head(2))\n\"","description":"Inspect extreme values and missing GDP"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1745,"cache_read_input_tokens":9718,"output_tokens":617,"output_tokens_details":{"thinking_tokens":128},"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":1745},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjsq2EtgK1qtqvEeViF","requestRef":"d098c736-9f38-48e3-87d4-f7382472523e","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b57fb62b-23ec-49b5-b0bb-fce5cb6d504d","timestamp":"2026-10-30T03:50:04.494Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"b57fb62b-23ec-49b5-b0bb-fce5cb6d504d","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KSTz242234Ry2UPBCdKXCT","type":"tool_result","content":"     iso3                      name  year   gdp_pc_ppp  life_expectancy\n313   CAF  Central African Republic  2022  1136.801711           18.818\n310   CAF  Central African Republic  2019  1145.095637           31.530\n1910  SSD               South Sudan  2017          NaN           35.351\n1909  SSD               South Sudan  2016          NaN           36.720\n1908  SSD               South Sudan  2015          NaN           39.757\n312   CAF  Central African Republic  2021  1128.552380           40.279\n308   CAF  Central African Republic  2017  1103.866093           45.231\n311   CAF  Central African Republic  2020  1136.570530           50.596\n307   CAF  Central African Republic  2016  1073.944777           50.999\n2025  TCD                      Chad  2015  2822.579299           51.320\n2026  TCD                      Chad  2016  2622.597808           51.603\n1233  LSO                   Lesotho  2015  2986.958667           51.830\n     iso3    name  year  gdp_pc_ppp  life_expectancy\n1313  MCO  Monaco  2023         NaN           86.372\n1309  MCO  Monaco  2019         NaN           86.151\n1310  MCO  Monaco  2020         NaN           86.089\n1308  MCO  Monaco  2018         NaN           86.084\n1307  MCO  Monaco  2017         NaN           85.878\n     iso3              name  year     gdp_pc_ppp  life_expectancy\n1281  MAC  Macao SAR, China  2018  139541.157249        83.678049\n1266  LUX        Luxembourg  2021  136772.443753        82.597561\n1843  SGP         Singapore  2022  134828.001393        82.895122\n1842  SGP         Singapore  2021  133990.186782        83.092683\n1261  LUX        Luxembourg  2016  133661.734541        82.685366\n    iso3     name  year   gdp_pc_ppp  life_expectancy\n144  BDI  Burundi  2015   992.285806           60.107\n145  BDI  Burundi  2016  1006.559074           60.789\n146  BDI  Burundi  2017  1020.849828           61.345\n149  BDI  Burundi  2020  1027.628963           62.569\n151  BDI  Burundi  2022  1028.111346           62.882\n     iso3                       name\n107   ASM             American Samoa\n350   CHI            Channel Islands\n458   CUB                       Cuba\n629   ERI                    Eritrea\n764   GIB                  Gibraltar\n845   GUM                       Guam\n971   IMN                Isle of Man\n1214  LIE              Liechtenstein\n1295  MAF   St. Martin (French part)\n1313  MCO                     Monaco\n1448  MNP   Northern Mariana Islands\n1520  NCL              New Caledonia\n1709  PRK  Korea, Dem. People's Rep.\n1763  PYF           French Polynesia\n1916  SSD                South Sudan\n2015  SYR       Syrian Arab Republic\n2249  VEN              Venezuela, RB\n2258  VGB     British Virgin Islands\n2267  VIR      Virgin Islands (U.S.)\n2321  YEM                Yemen, Rep.\nlife_expectancy\n83.309756    2\n76.353000    1\n80.031000    1\n76.657000    1\n67.385000    1\nName: count, dtype: int64\n     iso3                      name  year  life_expectancy     dle\n25    AFG               Afghanistan  2022           65.617   5.200\n259   BOL                   Bolivia  2022           67.434   6.007\n304   BWA                  Botswana  2022           68.749   5.446\n308   CAF  Central African Republic  2017           45.231  -5.768\n309   CAF  Central African Republic  2018           52.297   7.066\n310   CAF  Central African Republic  2019           31.530 -20.767\n311   CAF  Central African Republic  2020           50.596  19.066\n312   CAF  Central African Republic  2021           40.279 -10.317\n313   CAF  Central African Republic  2022           18.818 -21.461\n314   CAF  Central African Republic  2023           57.408  38.590\n599   ECU                   Ecuador  2020           72.004  -5.282\n853   GUY                    Guyana  2022           69.888   5.565\n1178  LBY                     Libya  2023           69.339  -5.123\n1645  PER                      Peru  2022           76.834   5.238\n1736  PSE        West Bank and Gaza  2023           65.170 -11.492\n1911  SSD               South Sudan  2018           51.905  16.554\n1912  SSD               South Sudan  2019           58.129   6.224\n     iso3     name  year    gdp_pc_ppp  life_expectancy\n1503  NAM  Namibia  2015  12166.565839           60.008\n1504  NAM  Namibia  2016  11846.788083           60.810","is_error":false}]},"uuid":"a420fc84-638f-48b2-8d80-6d95af439c27","timestamp":"2026-10-30T03:50:04.796Z","toolUseResult":{"stdout":"     iso3                      name  year   gdp_pc_ppp  life_expectancy\n313   CAF  Central African Republic  2022  1136.801711           18.818\n310   CAF  Central African Republic  2019  1145.095637           31.530\n1910  SSD               South Sudan  2017          NaN           35.351\n1909  SSD               South Sudan  2016          NaN           36.720\n1908  SSD               South Sudan  2015          NaN           39.757\n312   CAF  Central African Republic  2021  1128.552380           40.279\n308   CAF  Central African Republic  2017  1103.866093           45.231\n311   CAF  Central African Republic  2020  1136.570530           50.596\n307   CAF  Central African Republic  2016  1073.944777           50.999\n2025  TCD                      Chad  2015  2822.579299           51.320\n2026  TCD                      Chad  2016  2622.597808           51.603\n1233  LSO                   Lesotho  2015  2986.958667           51.830\n     iso3    name  year  gdp_pc_ppp  life_expectancy\n1313  MCO  Monaco  2023         NaN           86.372\n1309  MCO  Monaco  2019         NaN           86.151\n1310  MCO  Monaco  2020         NaN           86.089\n1308  MCO  Monaco  2018         NaN           86.084\n1307  MCO  Monaco  2017         NaN           85.878\n     iso3              name  year     gdp_pc_ppp  life_expectancy\n1281  MAC  Macao SAR, China  2018  139541.157249        83.678049\n1266  LUX        Luxembourg  2021  136772.443753        82.597561\n1843  SGP         Singapore  2022  134828.001393        82.895122\n1842  SGP         Singapore  2021  133990.186782        83.092683\n1261  LUX        Luxembourg  2016  133661.734541        82.685366\n    iso3     name  year   gdp_pc_ppp  life_expectancy\n144  BDI  Burundi  2015   992.285806           60.107\n145  BDI  Burundi  2016  1006.559074           60.789\n146  BDI  Burundi  2017  1020.849828           61.345\n149  BDI  Burundi  2020  1027.628963           62.569\n151  BDI  Burundi  2022  1028.111346           62.882\n     iso3                       name\n107   ASM             American Samoa\n350   CHI            Channel Islands\n458   CUB                       Cuba\n629   ERI                    Eritrea\n764   GIB                  Gibraltar\n845   GUM                       Guam\n971   IMN                Isle of Man\n1214  LIE              Liechtenstein\n1295  MAF   St. Martin (French part)\n1313  MCO                     Monaco\n1448  MNP   Northern Mariana Islands\n1520  NCL              New Caledonia\n1709  PRK  Korea, Dem. People's Rep.\n1763  PYF           French Polynesia\n1916  SSD                South Sudan\n2015  SYR       Syrian Arab Republic\n2249  VEN              Venezuela, RB\n2258  VGB     British Virgin Islands\n2267  VIR      Virgin Islands (U.S.)\n2321  YEM                Yemen, Rep.\nlife_expectancy\n83.309756    2\n76.353000    1\n80.031000    1\n76.657000    1\n67.385000    1\nName: count, dtype: int64\n     iso3                      name  year  life_expectancy     dle\n25    AFG               Afghanistan  2022           65.617   5.200\n259   BOL                   Bolivia  2022           67.434   6.007\n304   BWA                  Botswana  2022           68.749   5.446\n308   CAF  Central African Republic  2017           45.231  -5.768\n309   CAF  Central African Republic  2018           52.297   7.066\n310   CAF  Central African Republic  2019           31.530 -20.767\n311   CAF  Central African Republic  2020           50.596  19.066\n312   CAF  Central African Republic  2021           40.279 -10.317\n313   CAF  Central African Republic  2022           18.818 -21.461\n314   CAF  Central African Republic  2023           57.408  38.590\n599   ECU                   Ecuador  2020           72.004  -5.282\n853   GUY                    Guyana  2022           69.888   5.565\n1178  LBY                     Libya  2023           69.339  -5.123\n1645  PER                      Peru  2022           76.834   5.238\n1736  PSE        West Bank and Gaza  2023           65.170 -11.492\n1911  SSD               South Sudan  2018           51.905  16.554\n1912  SSD               South Sudan  2019           58.129   6.224\n     iso3     name  year    gdp_pc_ppp  life_expectancy\n1503  NAM  Namibia  2015  12166.565839           60.008\n1504  NAM  Namibia  2016  11846.788083           60.810","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b57fb62b-23ec-49b5-b0bb-fce5cb6d504d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"f7f90b026f5df5e251c513490f60346c265e5ac3bfaf22f3d4bfc6c31a1c5f93","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KSTz242234Ry2UPBCdKXCT","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nind=pd.read_csv('data/wb_indicators.csv')\nent=pd.read_csv('data/wb_entities.csv',keep_default_na=False,na_values=[''])\nagg=set(ent.iso3[ent.region=='Aggregates'])\nc=ind[~ind.iso3.isin(agg)]\nprint(c.nsmallest(12,'life_expectancy'))\nprint(c.nlargest(5,'life_expectancy'))\nprint(c.nlargest(5,'gdp_pc_ppp')); print(c.nsmallest(5,'gdp_pc_ppp'))\nd=c[c.year==2023]; print(d[d.gdp_pc_ppp.isna()][['iso3','name']].to_string())\nprint(d.life_expectancy.value_counts().head())\n# check LE jumps\nc=c.sort_values(['iso3','year']); c['dle']=c.groupby('iso3').life_expectancy.diff()\nprint(c.loc[c.dle.abs()>5,['iso3','name','year','life_expectancy','dle']])\nprint(ind[ind.iso3=='NAM'].head(2))\n\"","description":"Inspect extreme values and missing GDP"}}]}}34{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"8f6eb3d9-b253-464a-ad20-03c7d4234e00","timestamp":"2026-10-30T03:50:04.800Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"d098c736-9f38-48e3-87d4-f7382472523e","keep":8,"tail":["f7f90b026f5df5e251c513490f60346c265e5ac3bfaf22f3d4bfc6c31a1c5f93","550334003e9bec2943b4362e407f4df19a313fc398c40403fed2ea8cf5db2c65"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"4cf558f82324a0d7bd4b9dfa734518b49c9f034bcc5ebfe536bde1f1c271cbb6"}35{"parentUuid":"a420fc84-638f-48b2-8d80-6d95af439c27","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjtJNHrPKtwJtSsm5Us","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":2282,"cache_read_input_tokens":11463,"output_tokens":1241,"output_tokens_details":{"thinking_tokens":491},"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":2282},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4772,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXjtJ6RyQes8yufE29tR","requestRef":"8f6eb3d9-b253-464a-ad20-03c7d4234e00","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9a1bc8a1-af9a-4e03-90e1-c0ba86032227","timestamp":"2026-10-30T03:50:10.827Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"9a1bc8a1-af9a-4e03-90e1-c0ba86032227","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjtJNHrPKtwJtSsm5Us","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_014H2pRVghynu2hMsU2YETdT","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract — F6-dev-01\n**Question.** Does the cross-country Preston curve (LE rising with ln income) hold in the latest usable WDI year, and how strong is it?\n**Estimand.** β in the linear projection LE_i = α + β ln(GDPpc_i) + ε_i over countries/economies (equal weights) in the analysis year; GDPpc = PPP constant 2021 intl $. Descriptive/associational only; meaningful as a best linear predictor (no exogeneity needed), inference via heteroskedasticity-robust SE (HC3 chosen).\n**Outputs.** out/results.json (analysis_year, n_excluded_missing, baseline_metric, model_metric, pearson_r, r_squared, effect_estimate, intercept, effect_se, effect_ci_low, effect_ci_high, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (income_level, n_countries, mean_log_gdp_pc, mean_life_expectancy), out/report.md (6 sections), out/analysis.py, out/claims.json; plus state files and out/exclusions.csv.\n**Information rules.** Exclude region == \"Aggregates\"; analysis year = latest 2015–2023 year with both indicators for >=150 countries; drop missing in that year (count = n_excluded_missing); no imputation; natural log; only the listed files.\n**Invalidity/impossibility.** No year with >=150 complete countries; non-positive GDP (log undefined); entity metadata not matching indicator codes; zero variance. If so → premise_invalid / infeasible with nulls.\nEOF\ncat > out/state/log.md <<'EOF'\n# Log\n- 2026-10-29 P0: read TASK.md, wrote contract. Decision: HC3 robust SE, t(n-2) 95% CI.\nEOF\necho ok","description":"Write contract and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2282,"cache_read_input_tokens":11463,"output_tokens":1241,"output_tokens_details":{"thinking_tokens":491},"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":2282},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjtJ6RyQes8yufE29tR","requestRef":"8f6eb3d9-b253-464a-ad20-03c7d4234e00","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b910a1fd-d0ec-4a68-9d65-72bc987a71eb","timestamp":"2026-10-30T03:50:17.040Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"b910a1fd-d0ec-4a68-9d65-72bc987a71eb","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_014H2pRVghynu2hMsU2YETdT","type":"tool_result","content":"ok","is_error":false}]},"uuid":"0aa08578-47f2-4f6d-a6c8-de61925033c8","timestamp":"2026-10-30T03:50:17.090Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b910a1fd-d0ec-4a68-9d65-72bc987a71eb","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"bca33ef1d6deb7012135a113a5e18b21ecfdfee6f16365a69b7e4286f793e986","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_014H2pRVghynu2hMsU2YETdT","name":"Bash","input":{"command":"cat > out/state/contract.md <<'EOF'\n# Contract — F6-dev-01\n**Question.** Does the cross-country Preston curve (LE rising with ln income) hold in the latest usable WDI year, and how strong is it?\n**Estimand.** β in the linear projection LE_i = α + β ln(GDPpc_i) + ε_i over countries/economies (equal weights) in the analysis year; GDPpc = PPP constant 2021 intl $. Descriptive/associational only; meaningful as a best linear predictor (no exogeneity needed), inference via heteroskedasticity-robust SE (HC3 chosen).\n**Outputs.** out/results.json (analysis_year, n_excluded_missing, baseline_metric, model_metric, pearson_r, r_squared, effect_estimate, intercept, effect_se, effect_ci_low, effect_ci_high, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (income_level, n_countries, mean_log_gdp_pc, mean_life_expectancy), out/report.md (6 sections), out/analysis.py, out/claims.json; plus state files and out/exclusions.csv.\n**Information rules.** Exclude region == \"Aggregates\"; analysis year = latest 2015–2023 year with both indicators for >=150 countries; drop missing in that year (count = n_excluded_missing); no imputation; natural log; only the listed files.\n**Invalidity/impossibility.** No year with >=150 complete countries; non-positive GDP (log undefined); entity metadata not matching indicator codes; zero variance. If so → premise_invalid / infeasible with nulls.\nEOF\ncat > out/state/log.md <<'EOF'\n# Log\n- 2026-10-29 P0: read TASK.md, wrote contract. Decision: HC3 robust SE, t(n-2) 95% CI.\nEOF\necho ok","description":"Write contract and log"}}]}}39{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"487f5d62-fa65-4098-84b8-f033037ef246","timestamp":"2026-10-30T03:50:17.093Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"8f6eb3d9-b253-464a-ad20-03c7d4234e00","keep":10,"tail":["bca33ef1d6deb7012135a113a5e18b21ecfdfee6f16365a69b7e4286f793e986","601398655511acfc7ae8586587e2a2547d957fd443beaf1db1b280e7305180a9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"41787dc2f11d87104148b18c4421e4ed8fea94f4d54f406472ab3f94b89a0a3f"}40{"parentUuid":"0aa08578-47f2-4f6d-a6c8-de61925033c8","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjuCvtwemrXk8TRenLg","type":"message","role":"assistant","content":[{"type":"text","text":"Now the analysis script."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1248,"cache_read_input_tokens":13745,"output_tokens":3574,"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":1248},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXjuCeHNXtYLziXnwpxZ","requestRef":"487f5d62-fa65-4098-84b8-f033037ef246","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"911a5ea5-883a-45e3-8593-27dd34eeb78b","timestamp":"2026-10-30T03:50:18.265Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"911a5ea5-883a-45e3-8593-27dd34eeb78b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjuCvtwemrXk8TRenLg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UwL4KD7ccFJb7gvcinMcL3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-dev-01 (Preston curve). Run from workspace root:\n    ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/figure1.png, out/table1.csv, out/exclusions.csv.\nNo randomness is used (random_seed recorded as 0 for completeness; nothing depends on it).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nSEED = 0\nnp.random.seed(SEED)\nTASK_ID = \"F6-dev-01\"\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\n\n# keep_default_na=False so codes such as \"NA\" are never parsed as missing; only empty cells are NaN\nind = pd.read_csv(\"data/wb_indicators.csv\", keep_default_na=False, na_values=[\"\"],\n                  dtype={\"iso3\": str, \"name\": str})\nent = pd.read_csv(\"data/wb_entities.csv\", keep_default_na=False, na_values=[\"\"], dtype=str)\nn_input_rows = {\"wb_indicators.csv\": int(len(ind)), \"wb_entities.csv\": int(len(ent))}\ndata_issues = []\nexcl = []\n\nassert not ind.duplicated([\"iso3\", \"year\"]).any()\nassert set(ind.iso3) <= set(ent.iso3), \"indicator codes missing from metadata\"\n\n# Step 1: drop aggregates\nagg = set(ent.loc[ent.region == \"Aggregates\", \"iso3\"])\nn0 = len(ind)\nc = ind[~ind.iso3.isin(agg)].copy()\nexcl.append((\"1\", \"drop entities with region == 'Aggregates'\", n0, len(c),\n             \"Analysis population is countries/economies only (TASK rule)\"))\ndata_issues.append({\"issue\": f\"wb_indicators.csv mixes {ind.iso3.isin(agg).groupby(ind.iso3).first().sum()} aggregate entities ({n0-len(c)} rows) with countries/economies\",\n                    \"handling\": \"Excluded all entities with region == 'Aggregates' in wb_entities.csv\"})\n\n# Step 2: analysis year\nboth = c.gdp_pc_ppp.notna() & c.life_expectancy.notna()\ncover = both.groupby(c.year).sum()\neligible = cover[(cover >= 150) & (cover.index >= 2015) & (cover.index <= 2023)]\nif eligible.empty:\n    raise SystemExit(\"premise_invalid: no year with >=150 complete countries\")\nyear = int(eligible.index.max())\nn1 = len(c)\ny = c[c.year == year].copy()\nexcl.append((\"2\", f\"keep analysis year {year} only\", n1, len(y),\n             \"Latest 2015-2023 year with both indicators for >=150 countries/economies\"))\n\n# Step 3: missing indicators\nmiss = y.gdp_pc_ppp.isna() | y.life_expectancy.isna()\nn_excluded_missing = int(miss.sum())\nmissing_names = sorted(y.loc[miss, \"name\"])\nn2 = len(y)\nd = y[~miss].copy()\nexcl.append((\"3\", \"drop countries with missing GDPpc PPP or life expectancy in analysis year\", n2, len(d),\n             \"No imputation (TASK rule); dropped: \" + \"; \".join(missing_names)))\ndata_issues.append({\"issue\": f\"{n_excluded_missing} countries/economies lack GDP per capita PPP (or LE) in {year}: \" + \", \".join(missing_names),\n                    \"handling\": \"Excluded from the estimate, counted in n_excluded_missing; no imputation (possible selection: many are small territories or conflict/sanctioned economies)\"})\n\n# anomaly scan (outside analysis year: documented only)\ncs = c.sort_values([\"iso3\", \"year\"]).copy()\ncs[\"dle\"] = cs.groupby(\"iso3\").life_expectancy.diff()\njumps = cs.loc[cs.dle.abs() > 10, [\"iso3\", \"year\", \"life_expectancy\"]]\nif len(jumps):\n    data_issues.append({\"issue\": \"Implausible year-to-year life-expectancy swings (>10 years) in: \" +\n                        \", \".join(f\"{r.iso3} {r.year} ({r.life_expectancy:.1f})\" for r in jumps.itertuples()),\n                        \"handling\": f\"Only the {year} cross-section is used; values in {year} for these entities were inspected and kept as reported (no editing of source data)\"})\nassert (d.gdp_pc_ppp > 0).all()\n\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"rationale\"]).assign(\n    n_removed=lambda t: t.n_before - t.n_after)[\n    [\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]].to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\n# Baseline and model\nd[\"lngdp\"] = np.log(d.gdp_pc_ppp)\nle = d.life_expectancy.to_numpy(); x = d.lngdp.to_numpy(); n = len(d)\nbaseline_rmse = float(np.sqrt(np.mean((le - le.mean()) ** 2)))\nX = sm.add_constant(x)\nfit = sm.OLS(le, X).fit(cov_type=\"HC3\")\nalpha, beta = map(float, fit.params)\nresid = le - fit.fittedvalues\nmodel_rmse = float(np.sqrt(np.mean(resid ** 2)))\nse = float(fit.bse[1])\nci_low, ci_high = map(float, fit.conf_int(alpha=0.05)[1])  # t(n-2) critical value\nr = float(np.corrcoef(x, le)[0, 1])\nr2 = float(fit.rsquared)\n# sensitivity: other HC variants and classical SE (reported, not used for conclusion)\nsens = {f\"sensitivity_se_{k}\": float(sm.OLS(le, X).fit(cov_type=k).bse[1]) for k in [\"HC0\", \"HC1\", \"HC2\"]}\nsens[\"sensitivity_se_classical\"] = float(sm.OLS(le, X).fit().bse[1])\n\nif ci_low > 0: concl = \"positive_effect\"\nelif ci_high < 0: concl = \"negative_effect\"\nelse: concl = \"no_detectable_effect\"\n\n# Table 1\norder = [\"Low income\", \"Lower middle income\", \"Upper middle income\", \"High income\"]\nd = d.merge(ent[[\"iso3\", \"income_level\"]], on=\"iso3\", how=\"left\")\nt1 = d.groupby(\"income_level\").agg(n_countries=(\"iso3\", \"size\"), mean_log_gdp_pc=(\"lngdp\", \"mean\"),\n                                   mean_life_expectancy=(\"life_expectancy\", \"mean\")).reset_index()\nt1[\"_o\"] = t1.income_level.map({k: i for i, k in enumerate(order)}).fillna(99)\nt1 = t1.sort_values([\"_o\", \"income_level\"]).drop(columns=\"_o\")\nt1.round(4).to_csv(f\"{OUT}/table1.csv\", index=False)\n\n# Figure 1\nfig, ax = plt.subplots(figsize=(7, 5))\ncols = {\"Low income\": \"tab:red\", \"Lower middle income\": \"tab:orange\", \"Upper middle income\": \"tab:green\", \"High income\": \"tab:blue\"}\nfor lvl in order:\n    s = d[d.income_level == lvl]\n    ax.scatter(s.lngdp, s.life_expectancy, s=14, alpha=0.75, color=cols[lvl], label=f\"{lvl} (n={len(s)})\")\nxx = np.linspace(x.min(), x.max(), 100)\nax.plot(xx, alpha + beta * xx, \"k-\", lw=1.5, label=f\"OLS: LE = {alpha:.1f} + {beta:.2f}·ln(GDPpc), R²={r2:.2f}\")\nax.set_xlabel(\"ln(GDP per capita, PPP, constant 2021 intl $)\")\nax.set_ylabel(\"Life expectancy at birth (years)\")\nax.set_title(f\"Preston curve, {year} (n={n} countries/economies)\")\nax.legend(fontsize=7, loc=\"lower right\")\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150); plt.close(fig)\n\nres = {\n    \"task_id\": TASK_ID, \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"analysis_year\": year, \"n_excluded_missing\": n_excluded_missing,\n    \"baseline_metric\": baseline_rmse, \"model_metric\": model_rmse,\n    \"pearson_r\": r, \"r_squared\": r2, \"effect_estimate\": beta, \"intercept\": alpha,\n    \"effect_se\": se, \"effect_se_type\": \"HC3\", \"effect_ci_low\": ci_low, \"effect_ci_high\": ci_high,\n    \"conclusion\": concl, \"data_issues\": data_issues, \"n_input_rows\": n_input_rows,\n    \"n_analysed\": int(n), \"random_seed\": SEED,\n    \"n_countries_in_population\": int(c.iso3.nunique()),\n    \"complete_countries_by_year\": {str(k): int(v) for k, v in cover.items()},\n    **sens,\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n    json.dump(res, f, indent=2)\nprint(f\"year={year} n={n} excluded={n_excluded_missing} beta={beta:.4f} se(HC3)={se:.4f} \"\n      f\"CI=[{ci_low:.4f},{ci_high:.4f}] r={r:.4f} R2={r2:.4f} rmse0={baseline_rmse:.3f} rmse={model_rmse:.3f} -> {concl}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/table1.csv out/exclusions.csv","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":1248,"cache_read_input_tokens":13745,"output_tokens":3574,"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":1248},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjuCeHNXtYLziXnwpxZ","requestRef":"487f5d62-fa65-4098-84b8-f033037ef246","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"601acd77-337b-4452-97b5-7fd5a9264c95","timestamp":"2026-10-30T03:50:44.972Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}42{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"601acd77-337b-4452-97b5-7fd5a9264c95","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}43{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}44{"parentUuid":"601acd77-337b-4452-97b5-7fd5a9264c95","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UwL4KD7ccFJb7gvcinMcL3","type":"tool_result","content":"year=2023 n=197 excluded=20 beta=5.2672 se(HC3)=0.2107 CI=[4.8543,5.6801] r=0.8613 R2=0.7419 rmse0=7.076 rmse=3.595 -> positive_effect\n{\n  \"task_id\": \"F6-dev-01\",\n  \"feasibility\": \"complete\",\n  \"feasibility_reason\": null,\n  \"analysis_year\": 2023,\n  \"n_excluded_missing\": 20,\n  \"baseline_metric\": 7.07645404460588,\n  \"model_metric\": 3.5949979094078177,\n  \"pearson_r\": 0.8613437957840087,\n  \"r_squared\": 0.7419131345356038,\n  \"effect_estimate\": 5.267173451958655,\n  \"intercept\": 22.56709274982858,\n  \"effect_se\": 0.21067528691162227,\n  \"effect_se_type\": \"HC3\",\n  \"effect_ci_low\": 4.854257477179233,\n  \"effect_ci_high\": 5.6800894267380775,\n  \"conclusion\": \"positive_effect\",\n  \"data_issues\": [\n    {\n      \"issue\": \"wb_indicators.csv mixes 44 aggregate entities (396 rows) with countries/economies\",\n      \"handling\": \"Excluded all entities with region == 'Aggregates' in wb_entities.csv\"\n    },\n    {\n      \"issue\": \"20 countries/economies lack GDP per capita PPP (or LE) in 2023: American Samoa, British Virgin Islands, Channel Islands, Cuba, Eritrea, French Polynesia, Gibraltar, Guam, Isle of Man, Korea, Dem. People's Rep., Liechtenstein, Monaco, New Caledonia, Northern Mariana Islands, South Sudan, St. Martin (French part), Syrian Arab Republic, Venezuela, RB, Virgin Islands (U.S.), Yemen, Rep.\",\n      \"handling\": \"Excluded from the estimate, counted in n_excluded_missing; no imputation (possible selection: many are small territories or conflict/sanctioned economies)\"\n    },\n    {\n      \"issue\": \"Implausible year-to-year life-expectancy swings (>10 years) in: CAF 2019 (31.5), CAF 2020 (50.6), CAF 2021 (40.3), CAF 2022 (18.8), CAF 2023 (57.4), PSE 2023 (65.2), SSD 2018 (51.9)\",\n      \"handling\": \"Only the 2023 cross-section is used; values in 2023 for these entities were inspected and kept as reported (no editing of source data)\"\n    }\n  ],\n  \"n_input_rows\": {\n    \"wb_indicators.csv\": 2349,\n    \"wb_entities.csv\": 296\n  },\n  \"n_analysed\": 197,\n  \"random_seed\": 0,\n  \"n_countries_in_population\": 217,\n  \"complete_countries_by_year\": {\n    \"2015\": 199,\n    \"2016\": 199,\n    \"2017\": 199,\n    \"2018\": 199,\n    \"2019\": 199,\n    \"2020\": 199,\n    \"2021\": 199,\n    \"2022\": 199,\n    \"2023\": 197\n  },\n  \"sensitivity_se_HC0\": 0.20736485591704354,\n  \"sensitivity_se_HC1\": 0.2084255526375312,\n  \"sensitivity_se_HC2\": 0.20901105806015902,\n  \"sensitivity_se_classical\": 0.22246758287864518\n}income_level,n_countries,mean_log_gdp_pc,mean_life_expectancy\nLow income,20,7.61,63.188\nLower middle income,46,8.6899,67.8095\nUpper middle income,58,9.6899,73.6954\nHigh income,73,10.8226,79.6858\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop entities with region == 'Aggregates',2349,1953,396,Analysis population is countries/economies only (TASK rule)\n2,keep analysis year 2023 only,1953,217,1736,Latest 2015-2023 year with both indicators for >=150 countries/economies\n3,drop countries with missing GDPpc PPP or life expectancy in analysis year,217,197,20,\"No imputation (TASK rule); dropped: American Samoa; British Virgin Islands; Channel Islands; Cuba; Eritrea; French Polynesia; Gibraltar; Guam; Isle of Man; Korea, Dem. People's Rep.; Liechtenstein; Monaco; New Caledonia; Northern Mariana Islands; South Sudan; St. Martin (French part); Syrian Arab Republic; Venezuela, RB; Virgin Islands (U.S.); Yemen, Rep.\"","is_error":false}]},"uuid":"cc843cab-f7cb-4b2d-89ff-35b9abf54568","timestamp":"2026-10-30T03:50:46.418Z","toolUseResult":{"stdout":"year=2023 n=197 excluded=20 beta=5.2672 se(HC3)=0.2107 CI=[4.8543,5.6801] r=0.8613 R2=0.7419 rmse0=7.076 rmse=3.595 -> positive_effect\n{\n  \"task_id\": \"F6-dev-01\",\n  \"feasibility\": \"complete\",\n  \"feasibility_reason\": null,\n  \"analysis_year\": 2023,\n  \"n_excluded_missing\": 20,\n  \"baseline_metric\": 7.07645404460588,\n  \"model_metric\": 3.5949979094078177,\n  \"pearson_r\": 0.8613437957840087,\n  \"r_squared\": 0.7419131345356038,\n  \"effect_estimate\": 5.267173451958655,\n  \"intercept\": 22.56709274982858,\n  \"effect_se\": 0.21067528691162227,\n  \"effect_se_type\": \"HC3\",\n  \"effect_ci_low\": 4.854257477179233,\n  \"effect_ci_high\": 5.6800894267380775,\n  \"conclusion\": \"positive_effect\",\n  \"data_issues\": [\n    {\n      \"issue\": \"wb_indicators.csv mixes 44 aggregate entities (396 rows) with countries/economies\",\n      \"handling\": \"Excluded all entities with region == 'Aggregates' in wb_entities.csv\"\n    },\n    {\n      \"issue\": \"20 countries/economies lack GDP per capita PPP (or LE) in 2023: American Samoa, British Virgin Islands, Channel Islands, Cuba, Eritrea, French Polynesia, Gibraltar, Guam, Isle of Man, Korea, Dem. People's Rep., Liechtenstein, Monaco, New Caledonia, Northern Mariana Islands, South Sudan, St. Martin (French part), Syrian Arab Republic, Venezuela, RB, Virgin Islands (U.S.), Yemen, Rep.\",\n      \"handling\": \"Excluded from the estimate, counted in n_excluded_missing; no imputation (possible selection: many are small territories or conflict/sanctioned economies)\"\n    },\n    {\n      \"issue\": \"Implausible year-to-year life-expectancy swings (>10 years) in: CAF 2019 (31.5), CAF 2020 (50.6), CAF 2021 (40.3), CAF 2022 (18.8), CAF 2023 (57.4), PSE 2023 (65.2), SSD 2018 (51.9)\",\n      \"handling\": \"Only the 2023 cross-section is used; values in 2023 for these entities were inspected and kept as reported (no editing of source data)\"\n    }\n  ],\n  \"n_input_rows\": {\n    \"wb_indicators.csv\": 2349,\n    \"wb_entities.csv\": 296\n  },\n  \"n_analysed\": 197,\n  \"random_seed\": 0,\n  \"n_countries_in_population\": 217,\n  \"complete_countries_by_year\": {\n    \"2015\": 199,\n    \"2016\": 199,\n    \"2017\": 199,\n    \"2018\": 199,\n    \"2019\": 199,\n    \"2020\": 199,\n    \"2021\": 199,\n    \"2022\": 199,\n    \"2023\": 197\n  },\n  \"sensitivity_se_HC0\": 0.20736485591704354,\n  \"sensitivity_se_HC1\": 0.2084255526375312,\n  \"sensitivity_se_HC2\": 0.20901105806015902,\n  \"sensitivity_se_classical\": 0.22246758287864518\n}income_level,n_countries,mean_log_gdp_pc,mean_life_expectancy\nLow income,20,7.61,63.188\nLower middle income,46,8.6899,67.8095\nUpper middle income,58,9.6899,73.6954\nHigh income,73,10.8226,79.6858\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop entities with region == 'Aggregates',2349,1953,396,Analysis population is countries/economies only (TASK rule)\n2,keep analysis year 2023 only,1953,217,1736,Latest 2015-2023 year with both indicators for >=150 countries/economies\n3,drop countries with missing GDPpc PPP or life expectancy in analysis year,217,197,20,\"No imputation (TASK rule); dropped: American Samoa; British Virgin Islands; Channel Islands; Cuba; Eritrea; French Polynesia; Gibraltar; Guam; Isle of Man; Korea, Dem. People's Rep.; Liechtenstein; Monaco; New Caledonia; Northern Mariana Islands; South Sudan; St. Martin (French part); Syrian Arab Republic; Venezuela, RB; Virgin Islands (U.S.); Yemen, Rep.\"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"601acd77-337b-4452-97b5-7fd5a9264c95","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}45{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"26c3ff6e497b08029eabf0d6c5d3b1a4d1ae0ad59f6316f83295b7b7d9114795","message":{"role":"assistant","content":[{"type":"text","text":"Now the analysis script."},{"type":"tool_use","id":"toolu_01UwL4KD7ccFJb7gvcinMcL3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Replication entry point for F6-dev-01 (Preston curve). Run from workspace root:\n    ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/figure1.png, out/table1.csv, out/exclusions.csv.\nNo randomness is used (random_seed recorded as 0 for completeness; nothing depends on it).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nSEED = 0\nnp.random.seed(SEED)\nTASK_ID = \"F6-dev-01\"\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\n\n# keep_default_na=False so codes such as \"NA\" are never parsed as missing; only empty cells are NaN\nind = pd.read_csv(\"data/wb_indicators.csv\", keep_default_na=False, na_values=[\"\"],\n                  dtype={\"iso3\": str, \"name\": str})\nent = pd.read_csv(\"data/wb_entities.csv\", keep_default_na=False, na_values=[\"\"], dtype=str)\nn_input_rows = {\"wb_indicators.csv\": int(len(ind)), \"wb_entities.csv\": int(len(ent))}\ndata_issues = []\nexcl = []\n\nassert not ind.duplicated([\"iso3\", \"year\"]).any()\nassert set(ind.iso3) <= set(ent.iso3), \"indicator codes missing from metadata\"\n\n# Step 1: drop aggregates\nagg = set(ent.loc[ent.region == \"Aggregates\", \"iso3\"])\nn0 = len(ind)\nc = ind[~ind.iso3.isin(agg)].copy()\nexcl.append((\"1\", \"drop entities with region == 'Aggregates'\", n0, len(c),\n             \"Analysis population is countries/economies only (TASK rule)\"))\ndata_issues.append({\"issue\": f\"wb_indicators.csv mixes {ind.iso3.isin(agg).groupby(ind.iso3).first().sum()} aggregate entities ({n0-len(c)} rows) with countries/economies\",\n                    \"handling\": \"Excluded all entities with region == 'Aggregates' in wb_entities.csv\"})\n\n# Step 2: analysis year\nboth = c.gdp_pc_ppp.notna() & c.life_expectancy.notna()\ncover = both.groupby(c.year).sum()\neligible = cover[(cover >= 150) & (cover.index >= 2015) & (cover.index <= 2023)]\nif eligible.empty:\n    raise SystemExit(\"premise_invalid: no year with >=150 complete countries\")\nyear = int(eligible.index.max())\nn1 = len(c)\ny = c[c.year == year].copy()\nexcl.append((\"2\", f\"keep analysis year {year} only\", n1, len(y),\n             \"Latest 2015-2023 year with both indicators for >=150 countries/economies\"))\n\n# Step 3: missing indicators\nmiss = y.gdp_pc_ppp.isna() | y.life_expectancy.isna()\nn_excluded_missing = int(miss.sum())\nmissing_names = sorted(y.loc[miss, \"name\"])\nn2 = len(y)\nd = y[~miss].copy()\nexcl.append((\"3\", \"drop countries with missing GDPpc PPP or life expectancy in analysis year\", n2, len(d),\n             \"No imputation (TASK rule); dropped: \" + \"; \".join(missing_names)))\ndata_issues.append({\"issue\": f\"{n_excluded_missing} countries/economies lack GDP per capita PPP (or LE) in {year}: \" + \", \".join(missing_names),\n                    \"handling\": \"Excluded from the estimate, counted in n_excluded_missing; no imputation (possible selection: many are small territories or conflict/sanctioned economies)\"})\n\n# anomaly scan (outside analysis year: documented only)\ncs = c.sort_values([\"iso3\", \"year\"]).copy()\ncs[\"dle\"] = cs.groupby(\"iso3\").life_expectancy.diff()\njumps = cs.loc[cs.dle.abs() > 10, [\"iso3\", \"year\", \"life_expectancy\"]]\nif len(jumps):\n    data_issues.append({\"issue\": \"Implausible year-to-year life-expectancy swings (>10 years) in: \" +\n                        \", \".join(f\"{r.iso3} {r.year} ({r.life_expectancy:.1f})\" for r in jumps.itertuples()),\n                        \"handling\": f\"Only the {year} cross-section is used; values in {year} for these entities were inspected and kept as reported (no editing of source data)\"})\nassert (d.gdp_pc_ppp > 0).all()\n\npd.DataFrame(excl, columns=[\"step\", \"rule\", \"n_before\", \"n_after\", \"rationale\"]).assign(\n    n_removed=lambda t: t.n_before - t.n_after)[\n    [\"step\", \"rule\", \"n_before\", \"n_after\", \"n_removed\", \"rationale\"]].to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\n# Baseline and model\nd[\"lngdp\"] = np.log(d.gdp_pc_ppp)\nle = d.life_expectancy.to_numpy(); x = d.lngdp.to_numpy(); n = len(d)\nbaseline_rmse = float(np.sqrt(np.mean((le - le.mean()) ** 2)))\nX = sm.add_constant(x)\nfit = sm.OLS(le, X).fit(cov_type=\"HC3\")\nalpha, beta = map(float, fit.params)\nresid = le - fit.fittedvalues\nmodel_rmse = float(np.sqrt(np.mean(resid ** 2)))\nse = float(fit.bse[1])\nci_low, ci_high = map(float, fit.conf_int(alpha=0.05)[1])  # t(n-2) critical value\nr = float(np.corrcoef(x, le)[0, 1])\nr2 = float(fit.rsquared)\n# sensitivity: other HC variants and classical SE (reported, not used for conclusion)\nsens = {f\"sensitivity_se_{k}\": float(sm.OLS(le, X).fit(cov_type=k).bse[1]) for k in [\"HC0\", \"HC1\", \"HC2\"]}\nsens[\"sensitivity_se_classical\"] = float(sm.OLS(le, X).fit().bse[1])\n\nif ci_low > 0: concl = \"positive_effect\"\nelif ci_high < 0: concl = \"negative_effect\"\nelse: concl = \"no_detectable_effect\"\n\n# Table 1\norder = [\"Low income\", \"Lower middle income\", \"Upper middle income\", \"High income\"]\nd = d.merge(ent[[\"iso3\", \"income_level\"]], on=\"iso3\", how=\"left\")\nt1 = d.groupby(\"income_level\").agg(n_countries=(\"iso3\", \"size\"), mean_log_gdp_pc=(\"lngdp\", \"mean\"),\n                                   mean_life_expectancy=(\"life_expectancy\", \"mean\")).reset_index()\nt1[\"_o\"] = t1.income_level.map({k: i for i, k in enumerate(order)}).fillna(99)\nt1 = t1.sort_values([\"_o\", \"income_level\"]).drop(columns=\"_o\")\nt1.round(4).to_csv(f\"{OUT}/table1.csv\", index=False)\n\n# Figure 1\nfig, ax = plt.subplots(figsize=(7, 5))\ncols = {\"Low income\": \"tab:red\", \"Lower middle income\": \"tab:orange\", \"Upper middle income\": \"tab:green\", \"High income\": \"tab:blue\"}\nfor lvl in order:\n    s = d[d.income_level == lvl]\n    ax.scatter(s.lngdp, s.life_expectancy, s=14, alpha=0.75, color=cols[lvl], label=f\"{lvl} (n={len(s)})\")\nxx = np.linspace(x.min(), x.max(), 100)\nax.plot(xx, alpha + beta * xx, \"k-\", lw=1.5, label=f\"OLS: LE = {alpha:.1f} + {beta:.2f}·ln(GDPpc), R²={r2:.2f}\")\nax.set_xlabel(\"ln(GDP per capita, PPP, constant 2021 intl $)\")\nax.set_ylabel(\"Life expectancy at birth (years)\")\nax.set_title(f\"Preston curve, {year} (n={n} countries/economies)\")\nax.legend(fontsize=7, loc=\"lower right\")\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150); plt.close(fig)\n\nres = {\n    \"task_id\": TASK_ID, \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"analysis_year\": year, \"n_excluded_missing\": n_excluded_missing,\n    \"baseline_metric\": baseline_rmse, \"model_metric\": model_rmse,\n    \"pearson_r\": r, \"r_squared\": r2, \"effect_estimate\": beta, \"intercept\": alpha,\n    \"effect_se\": se, \"effect_se_type\": \"HC3\", \"effect_ci_low\": ci_low, \"effect_ci_high\": ci_high,\n    \"conclusion\": concl, \"data_issues\": data_issues, \"n_input_rows\": n_input_rows,\n    \"n_analysed\": int(n), \"random_seed\": SEED,\n    \"n_countries_in_population\": int(c.iso3.nunique()),\n    \"complete_countries_by_year\": {str(k): int(v) for k, v in cover.items()},\n    **sens,\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n    json.dump(res, f, indent=2)\nprint(f\"year={year} n={n} excluded={n_excluded_missing} beta={beta:.4f} se(HC3)={se:.4f} \"\n      f\"CI=[{ci_low:.4f},{ci_high:.4f}] r={r:.4f} R2={r2:.4f} rmse0={baseline_rmse:.3f} rmse={model_rmse:.3f} -> {concl}\")\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/results.json out/table1.csv out/exclusions.csv","description":"Write and run analysis script"}}]}}46{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"16da1ac3-2ac8-42a9-af4b-e242751e4315","timestamp":"2026-10-30T03:50:46.421Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"487f5d62-fa65-4098-84b8-f033037ef246","keep":12,"tail":["26c3ff6e497b08029eabf0d6c5d3b1a4d1ae0ad59f6316f83295b7b7d9114795","505ec2b7db4c1c0b236eced3171f302a367948cb60f1036d67b6099ffc853f6e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"cf99e92dc38ca4309da718c8cb60f7d0f94181a70a5d5a2b1eeb0abdb04e8fa3"}47{"parentUuid":"cc843cab-f7cb-4b2d-89ff-35b9abf54568","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjwNK1tuw19CVf93s2o","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS5ggKEAgTGAI4AUIIdGhpbmtpbmcSDNNyrjMV36LTCSyu3xoMkErVedtK1pSyo9BdIjBqGTEqWLhtUUwUELmV1QV3n6U7qcUaVlBXhPMLaTBjG5DamdB8IyVAQNSZju4HUvAqgwj4U0vIOwUiY48gNJ5tvxESx/mUvxKHeoA9LNj322YmBZAlf6+aVzCFXuRJ0tnY7hsVCSSWr+R9OL/EFb7Hzh1VJnBDg6RQMtuWnM12hrmYWpYVdwyoJSYnR4mQvKd/UcjW2VKKNUXRkPtNiYAgfZ97iz976SWRDPiwgka07ykLfSbZNSNSoDOL4MxFaVoWXqoZbAwN1u0nl0WSZDhBduI18a4/1q1LRtGT6UYANH/W5ptbUinB/Wl1ElZG4UJ8pJ8xlFOwv5FdjlfCNCMKeGmchG6i8Jr37dLQGCnvVB2X6otJxNnv+3Hf1dIBFNa6gOa7iKmVcdgEqCMfXIDG6ixJ2jqNM7Lh1wTfWvRp7yPH3ltwwc1vV+bveZ7yp9uAoM5aXgny0LOEOh5KVkcVxP6dCl5WwpB5XnTi7IguMTvfDyWb5JyMA0wrY1uNVHKOT5umZbRQCD6gVpPmqRCEtpbMkjlfp7bTwvBACNAsiNpty6li6bsGT9W0ad4LfSRTPHuEMSv9ZbZU+0GPwBt/XOy2hyLAbpZ5ft8GrcP/9n6GDwI8qLdJqHjvGi0OjiNzb9BdwU7Ja2Da6hvNwLIAfSd/yU0HJwwvtcvIvv/bHFc86D9QqYDJJGyGJiysDA81wj38q2oblyjpjdaq2uWP2nsEe52b6ze1MprBNn0z5+gN9TUW7ozhWQAs0r8byV5qRFMTzEFMs8yeylJdPM1nV/Fwq9JwVmicqx9qSjQIpzDb0DVtYOcHcmnVLjLGNunJgKA7XAFA7odBBTdlbybnHO2DebKDGSFgPlExQn+PNOvKqOOyxK7iXoPi25T4i4aFk3emXodNPqAtX9bUmNMqNAERhEQfxKIlVw4aZ7wgWYmcyunGBLW2M5pyQOi3Px65+Um4L88/HifUah9GL8a/2GOxTZZS/mEI25PiMFFDhNd0Pm7TJx6gDgoaMYxYg13bspypO7lYtmiLLTfvYAFhS9y3V+ZyfmDNPwsXikbneliNmD9LKTqiUyRkNgybZRFvgrmK08mzy+nBKR//sbf9B+BrSUSUMKxOfmF3jpAqEaPAG1zQTjYjU+01NFOiwgcyHVcgzClKGXpAAR865GMkoe3gvCZGMPiCNcrbzSfKsXWcC3al2TswNrn4LZ4lDzpokf3YDnNFCucSgxsOPSi8I1jaWAJ0d48herwopfwukwv+LpV9aPLaJZVR31AjqAlxMvFg3girDHCgEiknAv95Vm0rPsYJXbcq4NC1NTlcl3EhjPCeVVo4RL1BNIMU5j/mxFogbt55fw5JVmBxWIjLLary1lxE5nV1Z6H+lmaeb4bYo1J0oCI160e/H7KKNbe+11N2BmnuzlMjz3TE/iDfaqrYXjDVGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5170,"cache_read_input_tokens":14993,"output_tokens":771,"output_tokens_details":{"thinking_tokens":159},"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":5170},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1314,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXjwN38xrHKAKhhjJNr4","requestRef":"16da1ac3-2ac8-42a9-af4b-e242751e4315","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f7eb51eb-ef77-47df-ab4d-abc443bf1469","timestamp":"2026-10-30T03:50:49.235Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"f7eb51eb-ef77-47df-ab4d-abc443bf1469","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjwNK1tuw19CVf93s2o","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Jb5Ebv7H8ATbzzpNXmYohp","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace('''sens[\"sensitivity_se_classical\"] = float(sm.OLS(le, X).fit().bse[1])''','''sens[\"sensitivity_se_classical\"] = float(sm.OLS(le, X).fit().bse[1])\n# sensitivity: drop entities with erratic LE series (flagged above) present in the analysis sample\nflag = set(jumps.iso3) & set(d.iso3)\nkeep = ~d.iso3.isin(flag).to_numpy()\nfs = sm.OLS(le[keep], X[keep]).fit(cov_type=\"HC3\")\nsens[\"sensitivity_beta_drop_erratic_LE\"] = float(fs.params[1])\nsens[\"sensitivity_n_drop_erratic_LE\"] = int(keep.sum())\n# sensitivity: max absolute change in beta from leaving out any single country\ninfl = fit.get_influence() if hasattr(fit, \"get_influence\") else None\nloo = [float(sm.OLS(np.delete(le, i), np.delete(X, i, axis=0)).fit().params[1]) for i in range(len(le))]\nsens[\"sensitivity_beta_loo_min\"] = float(min(loo)); sens[\"sensitivity_beta_loo_max\"] = float(max(loo))''')\nopen('analysis.py','w').write(s)\nEOF\ncd .. && ~/wp29/venv/bin/python out/analysis.py && grep sensitivity out/results.json","description":"Add outlier sensitivity checks and rerun"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5170,"cache_read_input_tokens":14993,"output_tokens":771,"output_tokens_details":{"thinking_tokens":159},"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":5170},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjwN38xrHKAKhhjJNr4","requestRef":"16da1ac3-2ac8-42a9-af4b-e242751e4315","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2aea7dd6-797d-4ed4-819e-70fbcc4d6cc0","timestamp":"2026-10-30T03:50:53.509Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"2aea7dd6-797d-4ed4-819e-70fbcc4d6cc0","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Jb5Ebv7H8ATbzzpNXmYohp","type":"tool_result","content":"year=2023 n=197 excluded=20 beta=5.2672 se(HC3)=0.2107 CI=[4.8543,5.6801] r=0.8613 R2=0.7419 rmse0=7.076 rmse=3.595 -> positive_effect\n  \"sensitivity_se_HC0\": 0.20736485591704354,\n  \"sensitivity_se_HC1\": 0.2084255526375312,\n  \"sensitivity_se_HC2\": 0.20901105806015902,\n  \"sensitivity_se_classical\": 0.22246758287864518,\n  \"sensitivity_beta_drop_erratic_LE\": 5.232677697400639,\n  \"sensitivity_n_drop_erratic_LE\": 195,\n  \"sensitivity_beta_loo_min\": 5.2053879942344015,\n  \"sensitivity_beta_loo_max\": 5.327563424394041","is_error":false}]},"uuid":"b821afa2-d10a-414b-bb73-c5ad9e1f96ee","timestamp":"2026-10-30T03:50:54.761Z","toolUseResult":{"stdout":"year=2023 n=197 excluded=20 beta=5.2672 se(HC3)=0.2107 CI=[4.8543,5.6801] r=0.8613 R2=0.7419 rmse0=7.076 rmse=3.595 -> positive_effect\n  \"sensitivity_se_HC0\": 0.20736485591704354,\n  \"sensitivity_se_HC1\": 0.2084255526375312,\n  \"sensitivity_se_HC2\": 0.20901105806015902,\n  \"sensitivity_se_classical\": 0.22246758287864518,\n  \"sensitivity_beta_drop_erratic_LE\": 5.232677697400639,\n  \"sensitivity_n_drop_erratic_LE\": 195,\n  \"sensitivity_beta_loo_min\": 5.2053879942344015,\n  \"sensitivity_beta_loo_max\": 5.327563424394041","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2aea7dd6-797d-4ed4-819e-70fbcc4d6cc0","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"6e2d7236df37ad52fa864df7347e00dfec2728ee20bca09b06a484aa910b45bd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Jb5Ebv7H8ATbzzpNXmYohp","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace('''sens[\"sensitivity_se_classical\"] = float(sm.OLS(le, X).fit().bse[1])''','''sens[\"sensitivity_se_classical\"] = float(sm.OLS(le, X).fit().bse[1])\n# sensitivity: drop entities with erratic LE series (flagged above) present in the analysis sample\nflag = set(jumps.iso3) & set(d.iso3)\nkeep = ~d.iso3.isin(flag).to_numpy()\nfs = sm.OLS(le[keep], X[keep]).fit(cov_type=\"HC3\")\nsens[\"sensitivity_beta_drop_erratic_LE\"] = float(fs.params[1])\nsens[\"sensitivity_n_drop_erratic_LE\"] = int(keep.sum())\n# sensitivity: max absolute change in beta from leaving out any single country\ninfl = fit.get_influence() if hasattr(fit, \"get_influence\") else None\nloo = [float(sm.OLS(np.delete(le, i), np.delete(X, i, axis=0)).fit().params[1]) for i in range(len(le))]\nsens[\"sensitivity_beta_loo_min\"] = float(min(loo)); sens[\"sensitivity_beta_loo_max\"] = float(max(loo))''')\nopen('analysis.py','w').write(s)\nEOF\ncd .. && ~/wp29/venv/bin/python out/analysis.py && grep sensitivity out/results.json","description":"Add outlier sensitivity checks and rerun"}}]}}51{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"b1c91571-c51c-4587-be5f-41d2180e6d28","timestamp":"2026-10-30T03:50:54.764Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"16da1ac3-2ac8-42a9-af4b-e242751e4315","keep":14,"tail":["6e2d7236df37ad52fa864df7347e00dfec2728ee20bca09b06a484aa910b45bd","8f2fd9fb5677c32286e4d5408638d5cacc4f2eea8f03729bc7720d579c4aa287"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"14cbc8fe7430b8bc63ce69e4ceb4303c92e5b3f813cbf8757feaa464d20c8014"}52{"parentUuid":"b821afa2-d10a-414b-bb73-c5ad9e1f96ee","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjwz3LQg86LLbdTUN92","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":1070,"cache_read_input_tokens":20163,"output_tokens":544,"output_tokens_details":{"thinking_tokens":34},"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":1070},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":317,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXjwykicjkDU2MMk72W8","requestRef":"b1c91571-c51c-4587-be5f-41d2180e6d28","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f8526ebd-6170-4ef7-a869-90cc205db397","timestamp":"2026-10-30T03:50:56.467Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"f8526ebd-6170-4ef7-a869-90cc205db397","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjwz3LQg86LLbdTUN92","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01754ijLN2EAp8bF7eJ5uUMk","name":"Bash","input":{"command":"sed -i '' '/infl = fit.get_influence/d' out/analysis.py\ncp out/results.json /tmp/r1.json; rm -f out/results.json out/figure1.png out/table1.csv out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; ls out\n~/wp29/venv/bin/python -c \"\nimport json,math;r=json.load(open('out/results.json'))\nprint('ci',r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'])\nprint('r2=r^2',abs(r['r_squared']-r['pearson_r']**2)<1e-12)\nprint('rmse identity',abs(r['model_metric']**2-(1-r['r_squared'])*r['baseline_metric']**2)<1e-9)\nprint('counts',r['n_analysed']+r['n_excluded_missing']==r['n_countries_in_population'])\nimport pandas as pd;t=pd.read_csv('out/table1.csv');print('table sum',t.n_countries.sum())\ne=pd.read_csv('out/exclusions.csv');print('excl',2349-e.n_removed.sum())\n\"","description":"Clean rerun reproducibility and consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1070,"cache_read_input_tokens":20163,"output_tokens":544,"output_tokens_details":{"thinking_tokens":34},"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":1070},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjwykicjkDU2MMk72W8","requestRef":"b1c91571-c51c-4587-be5f-41d2180e6d28","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"68d74583-277d-40e0-8e87-8d3a7c586a6e","timestamp":"2026-10-30T03:50:59.915Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}54{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"68d74583-277d-40e0-8e87-8d3a7c586a6e","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}55{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}56{"parentUuid":"68d74583-277d-40e0-8e87-8d3a7c586a6e","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01754ijLN2EAp8bF7eJ5uUMk","type":"tool_result","content":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv\nci True\nr2=r^2 True\nrmse identity True\ncounts True\ntable sum 197\nexcl 197","is_error":false}]},"uuid":"19e123cb-4aef-46ef-a00f-82e90281a9df","timestamp":"2026-10-30T03:51:01.425Z","toolUseResult":{"stdout":"IDENTICAL\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv\nci True\nr2=r^2 True\nrmse identity True\ncounts True\ntable sum 197\nexcl 197","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"68d74583-277d-40e0-8e87-8d3a7c586a6e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}57{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"16ecf47c3670e5080fc8a4a8a03c1df74787d189e110f8986e0019d33a0ecdda","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS1QYKEAgTGAI4AUIIdGhpbmtpbmcSDDJH7jZVSWuKfdfG+xoMf7yxatM7HJP7iQ9SIjDwQWckqpURtzEDWBVdstEGR9BwO7eNDgZHX3v2XALA8z6CgM9up55/WpXJPCVxI14q8gUpRVEy3PJbGJhgT7Pjno2vxyV50WZEwDOF5S5o+WrrYdvrXrWQormeppkMv8MTIb4RD/VNWBBlOBUIzLuETlLAtpOBnsdHNBk13pnCL5ywpiYtx85dDI4e2CeQW7kU0TBHPjPoljDMez2VJgKI1jdBvKkDFs1rGI3tnfJgv7hx2T1+Zo9SG/K8AAXlmQUd3EGOfj2DprGAUlYcNAUce98czDGn0HUjc8gG34QoaP6M4h0GKeQJm2JV1rjHsxSN9b7Ousd3RNfHBKMgowjs1GQfkc3B1z9rgZdQFPPFIk0N6rZHOfOvrQEsacthMWD0Xv4cdegjf0le9vb9t6DIS0hIC2gVNeW2PAmQb+6dhwTh5nsmQSg9h3wlPE26hNuHUXZRXtRMVRYEmxOHLAHMlW9IEZ2GBswh6vkr7yLhjRUsSoy2FX+LjxyjS4V0rOf1th5pgRULR0OIUEva82sRxQ/qWwfeMg9jKhsmDN6nrKnOr89ywiGIgYHvK2VMOxmXIUaSILpw0cAJJeAIgMvaD8+ELI2yDiq2sKVSzZ+0wc9CEYXg9/Cg1Fy4qgkxJ1t0cze3WvCczZG5xOEvqgEG4O4Vrh76U8qEN6oFGdhbUwnVtIrfWvF8NMxWueHA5mx1D3YfdI+VUVDFOCurPg+vQPR0sO2DOZDTSnSTQZmL7OkbcXZIxAX5z9leu3M2kUKqKcagnLPRTj3qB5/Q77DPLHw8uYNXqqIO+quhNkbgzv2YTKn75svwPGrb9X2rxT9MGHubPjfBEYg1MFZW4f47c4aJNhcFIMB8WJ7SI0aYZmmhzBItekuFDOsWZdNwJVzPdU9elmdGBHgYRcd1UKiLASn847afo19cqgsLJTgccCk94HPn3J7AVYhpnHMIgtH35nwCuySppX60K8jFHN4FOjzl8IEJSgyDT/PQp/zEPWtRY44EDGKQKUgfb9i15J0uwC3OzCNsQdwtnmlG++W7abfulH27Y+7oKzwEJDki6hdWxF3SGAE="},{"type":"tool_use","id":"toolu_01754ijLN2EAp8bF7eJ5uUMk","name":"Bash","input":{"command":"sed -i '' '/infl = fit.get_influence/d' out/analysis.py\ncp out/results.json /tmp/r1.json; rm -f out/results.json out/figure1.png out/table1.csv out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cmp out/results.json /tmp/r1.json && echo IDENTICAL; ls out\n~/wp29/venv/bin/python -c \"\nimport json,math;r=json.load(open('out/results.json'))\nprint('ci',r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'])\nprint('r2=r^2',abs(r['r_squared']-r['pearson_r']**2)<1e-12)\nprint('rmse identity',abs(r['model_metric']**2-(1-r['r_squared'])*r['baseline_metric']**2)<1e-9)\nprint('counts',r['n_analysed']+r['n_excluded_missing']==r['n_countries_in_population'])\nimport pandas as pd;t=pd.read_csv('out/table1.csv');print('table sum',t.n_countries.sum())\ne=pd.read_csv('out/exclusions.csv');print('excl',2349-e.n_removed.sum())\n\"","description":"Clean rerun reproducibility and consistency checks"}}]}}58{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"ad155a1e-17f7-42e3-a7e4-815d7b0071cd","timestamp":"2026-10-30T03:51:01.429Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"b1c91571-c51c-4587-be5f-41d2180e6d28","keep":16,"tail":["16ecf47c3670e5080fc8a4a8a03c1df74787d189e110f8986e0019d33a0ecdda","eeeda1ce705a60fafd83c0e31a1713b85e6791f687cfccbc3a664143a401a972"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"1c083fc4f62d315c13c8e5d91dfa5eed49ec7a166d61ded311edcde8c5db1adf"}59{"type":"tools-used","tools":["Bash","Read"],"sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}60{"parentUuid":"19e123cb-4aef-46ef-a00f-82e90281a9df","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjxUUsN5ExRKjKrJHST","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MStBC4QhZFeLADwfjBBCKR","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RP0013/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":623,"cache_read_input_tokens":21233,"output_tokens":80,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":623},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXjxUDzXJ7vMQ2vDLKyJ","requestRef":"ad155a1e-17f7-42e3-a7e4-815d7b0071cd","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9b43f7b1-0755-40bd-851f-0050c35cd6b8","timestamp":"2026-10-30T03:51:02.840Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}61{"parentUuid":"9b43f7b1-0755-40bd-851f-0050c35cd6b8","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MStBC4QhZFeLADwfjBBCKR","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"iVBORw0KGgoAAAANSUhEUgAABBoAAALuCAYAAAAAD3VqAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAXEgAAFxIBZ5/SUgABAABJREFUeJzs3Qd4U3XbBvCnSbpbOqDsvQWVISIqyBAVtygiOBBxrxc3e29xIS5ciAMUUUDFiSiggoIgCCIyZK9S2tLdrO+6//XkS9KkMzv3z6uG5JwkJ6NpznOeEWG1Wq1CREREREREROQBOk/cCBERERERERERAw1ERERERERE5FHMaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiIiIiIiIvIYBhqIiIiIiIiIyGMYaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiIiIiIiIvIYBhqIiIiIiIiIyGMYaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiIiIiIiIvIYBhqIiIiIiIiIyGMYaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiIiIiIiIvIYBhqIiIiIiIiIyGMYaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiIiIiIiIvIYBhqIiIiIiIiIyGMYaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiKiENSjRw+JiIiQX3/91d+bQlRtTZs2Ve/nd955h88mVcq+ffvUewc/+Le/9evXT23LqlWr/L0pRF7FQANRkJs4caLtD6j9T0xMjDRs2FCuueYaWbx4sVitVgkW+CKJx/Xjjz/6e1MowGRkZMj8+fPl1ltvlXbt2kl8fLxER0er9/p1110nS5curdDt5OTkqPfYWWedJQkJCZKUlCTnnnuuPPvss1JcXOz2eocPH5ZXXnlFbrzxRmnZsqXExsaqn2bNmsngwYPL/eK4evVqGTNmjFx22WXSqlUrSUlJkcjISKldu7b07t1bXnzxRSkoKJDq+uSTT+Snn36SK664Qs477zwJBmvXrpU5c+bI7bffLmeeeaYYDAb1WdarV68K38bWrVvljjvuUK8HPgNr1qwp3bt3l1dffVXMZrPb67n6DHX3g9eJypaVlaV+v/CDf4e6Rx55RL03xo4d6+9NoSCA3wt44oknxGKx+HtziLzHSkRBbcKECYggqJ86derYfmJiYmyX4+fyyy+3FhYWWoNBz5491TbjsRHZMxgMDu9rvM/j4+NLvdfz8vLcPnH79u2zNm3a1LZ+XFycNTo62na+U6dO1lOnTpW63oEDB6wREREO94XrxsbGOlw2bNgwq8lkcnnfV155pcO62Hbn7W/WrJl1586dVX7hi4uLrS1atFC39dtvvwXNG8j+ObD/wedBRbz00ktWvV5vu15SUpLD5+AFF1xgPX36tMvr2n92uvpJTU213c6TTz7p4Uceev7991/b84V/e0KfPn2sbdq0sX766afWQKN9nmzYsMHfm0IuHDp0SL138IN/B4LLLrtMvWcWLFjg700h8hpmNBCFkGPHjtl+8vLyZNu2bXLJJZeoZV999RWPtlDQM5lM0rVrV5VVsGfPHnX0Pzc3V/7991+58847be/1e++91+31r776apU+W69ePfnuu+/U70p+fr58+OGHkpiYKJs3b1YZE85wRBz7wxdffLEsWLBAZTfgurj/7du3y7XXXqvWe/vtt21HrJz17dtXZS1s2rRJTp8+ra6Ln5MnT6rLkR2Bx9K/f/8qH+lCNgOemy5duqgsjWCBx47X9r777pM33nhDZX1U1Ndffy0PP/yweo3wHP/999/qSDqe288++0xljPzyyy8qW6K8z05XP6NHj7atq73PyLe+//579bridyOQIIsGnycNGjSQc845x9+bQy7gtcF7Bz/4dyDA5xw8/fTT/t4UIu/xXgyDiHyd0eBKQUGBtWXLlmp5YmKi1Wg0BvwLw4wGcmfVqlVlPjn33nuv7fcBGQjO3nzzTdvyX375pdTyhQsX2pavXLnSYVlWVpb1999/d3vfFovF2q9fP3XdhIQE9btXWfPmzbPd/08//WStzu/PCy+8YA0mzlkgt99+e4UzGs455xy1boMGDVxms3z11Ve253XNmjWV3rYzzjhDXbd79+6Vvm448kZGQ6CaPHmyepz333+/vzeFgkhRUZEtU6qqn/VEgY4ZDUQhDnXKqCfX6tIR0XfVHAlHQO+55x5V24yadzTesoejqx988IGq+a5Tp45ERUVJWlqaXHrppbJo0SK3PSBwBPn1119Xdda1atVS9eiom27Tpo3cdNNN8tZbbzn0ZsD2oI4dJk2aVKo+2rmRE45g4ghynz591O1j23HEAo+5rB4P2B7cHo48Y9txBBW17DVq1FBHtc8//3x5//33pbp27NghDz74oOongNtFPwA89kGDBqkjz/ZHrbG92uMsi7aO8+Nzvj6OzN9yyy2qfwGedzxmXKatgyNxZRkyZIhaD0fwXVmxYoXccMMN6vnG845+AxdddJGqhy+rz0F1lFcfb3+0eePGjaWWIxNBux28xs7wuuB3AN59912HZejj0LlzZ7f3jedq2LBh6t84ko7XvrK6detm+/ehQ4cqff1//vlH/f5gW/BYXHF+n+zevVttd6NGjWz9Lu6++26VseFLer2+Stc7fvy4/P777+rfDzzwgMTFxblsvoZ+HIAeH5WBTAjttbzrrrvEV58HmsLCQnnhhRfkggsuUL9j+Exv0qSJ+v38448/Kv054e5zsKzr428H+g+0bdtWZZ7gM/yqq65y2WgUt6n9DgH+bf8Zbt9zQ/vM1/7e/PDDD6rXCrKN8H4YOnRopZpB/vzzzyobCc8Pnif8ziJLZtasWep30p1vvvlGrr/+evXex982/B1o3ry5+vv2zDPPyKlTp9xed9myZepUy2jy5OfkwYMH5amnnpKOHTuqx4LnvkWLFuq+8PmE94Yzf/9N/PTTT9V7Q/uegFOcL6t/Dl5n3Lf2euM1xv3hMeP5QpbSmjVrHL5XzJ07V2WQYPuwHr6bIFOsqs0gffEdxx5uH+8LwPWJQpK/Ix1E5N2MBnj55Zdt6/z888+ljjh98MEH6gisVnOOmvEmTZrYrp+RkWG96KKLHOqmUf9sf/6aa65REXrnI5SXXHJJqevZ18Pbb/eHH36o6qEjIyNt9evOtdL2R6lxhLlXr16220F9dnJyskMd/RNPPFHmUd+xY8dar732WvVv1P/XqFHDYdvGjx9f5ddm5syZVp1O59BPAEcw7C/LzMy0rf/DDz+U+1qCtg7Wt2d//SVLltieRzwm3Ld2ZLh9+/ZlPjeQm5tr6x3wzjvvOCzLz8+3DhgwwOF5wn3YP+/dunVz2efA27Zu3Wrbho8//thhGY50a8/9008/7fY2cGQS69StW7fS9//ZZ5/Z7r8q9droM1Cd67/44ovquqhFdsf+fYIMEe13HxlP9j0w6tev79d65opmNPz666+2bV66dKnb9QYOHGjLeqgM9NzQPrvK6v3h6c8DwPN/5pln2pbjd9r+sxfXxWtemc+JimaPaddHlo+WFYdtxt8IbVlUVJT1m2++cbhe//79rbVq1bKtg3/bf4ZjuWb+/PlqHfy9QQaO9hmCx4jHiveAButgGa7jzGw2W//3v/85fCbhfW3fswO/E+jP4mzSpEkO18Pj034nynsO8fdI+/xz/vtX3c/Jd99916HHCJ7rmjVrOvyObt682eE6/vybiMd/0003Obw3U1JSHN7fgwcPVj1k3P2u41T7N+4bn0nadXH+888/V72mLr30UttzYt/jBq/dxo0bK51h46vvOM7ee+89tRy/F0ShiIEGojAINKB5mbbOjh07Sv3hxZeq8847z2HHRmtGhz+k2heQjh07qj/02pdt7IyikVHt2rXV8kceecTlH1F8WULKek5Oji3F/Pjx46qpF76IVbV04oYbbrB92cCXbW27jh49ats5wM+rr77q9j7wRQhfDLAzjS+GcPDgQevVV19t+7L0zz//WCvrlVdecfiCYv+FENv57bffqi9l2dnZXgk04DW94oorbK83aI9j1qxZth1JfEF3RXvt8CVOe900t956q1rWvHlzFaTSHgNKBZYvX64ux/LrrrvO6mvajjZ+/v77b4dl+AKqLfvyyy8rFJjDF9DKeOyxx2zvSfvXtix43+G1mTZtmu0LKr70VoW2Y3Pbbbe5Xcf+fYL3P96f2vsEX6Q/+ugj2xf8sm4nEAMNCLCV93mBn4oGwfDe13Y677vvPmtVVeXzAJ+9+FzWdl7ef/99247Onj17rFdddZVahp1IV+9nTwUa8B5p166dCkrh8wKf32gyih13LUjg/DlS0dIJLdCAvxHYKR46dKgtmIzHv3v37goFGrBzjGX4W4TfX+33Fju1ePxo8IrlnTt3dthWBB60HWH87h4+fNhhp33t2rXWBx54wOXOq31gEK+ds+p8Tn7xxRe24MCFF16otkPbbrwHcP7uu++2bt++PWD+Jj7++OO29+O4ceNsQTP8ro0ePdp23yNGjHD7u46gCJrrooRMu298jmulUWi6+dBDD6kA3eLFi9Xri/cjXh+tAS6eL2dlvR/98R1Hg+fR+bsZUShhoIEoxAMN+HKDHUosxx9n7cuK/R9efIFz3pm0P6qCddq2bau+eLmCP/L4coEvN/jj6nxk+J577qnUY6pIoGH9+vW27ceXEle0L104ouZcL6/dB35c1f3jqIn2vE2dOrVS248vVtqO2qBBg9SXjorwZKCha9eubicf4Cip9uXa+WikRjtihC/L9lDfrn2hd9UDQftSqh1lcj7i5k34YluvXj11vz169Cgz22DLli1ub2fZsmW29f78888K3//evXttR3vL20HHF3/7I172P/hCX9kAh6ZRo0bqNp555hm369i/T3r37u0y2KQFbPCl31VfF3fbXpEf+6PUngg04DNHu+2JEye6XQ+fYdp627Ztq9A2vPHGG7bruNvZ9NbnATK8tPt29XuK10ULRCDrwVuBhrS0NIfPdVfZQ8415pUNNODn+uuvt5bFXaABt48gBd6rf/zxh8vrYtpIw4YNS2W9IKiGy1q3bm2tCu1oNrI+PPU5idcVk2e0niDOR9ED8W8i/qZomRajRo0qMwiLTJUjR464/F3HDwJqzhBwsv8MQaDF2ffff29bjue2ou9Hf3zHsacFMt9+++0q3wZRoGKPBqIQhY7r6NKNOs0jR46oy4YPHy46Xelf+4ceekjVCrui1Rfef//9qg7SFdRJtm/fXtWbosZWk5ycrE7Rtd3TPvroI3WKmlp3ddNTpkxRp+joj+kCrlx44YUu6/5R16p1vS+vl4GzJUuWqJpm1Go+99xz5fZc8IYnn3zSbc076nXxvoD33nuv1PKjR4+q9w7cdtttLt8P6P2Amn5X8Jpozylqn30B9bXYVmw7arNfeumlUuvgNdG4quN3tcz+OmXB9AvUQGN6Bep0Z86cWeb6eG1QB4wfbK8Gt4Eu5KmpqVJZ2DfE4wfUFlcEpim4+kzQ6s3xuHbt2lVqubbtVflx9zlSVZgooXX7f/nllyU7O7vUOuh/oPWnAUz8qIg333xTnXbo0KHKEwWq+nmgfcahVh114s4MBoNMmDBB/RsThv7880/xBvTuwXPsDD0vtF4Mlf2MdGXUqFFVuh7q+dGXAH048Dq5gh4D6P3g/Jmk/Y3C64MJMpWB9xl6HuB1RV2/pz4n8TcUk2fg+eefV7X8gf43Eb9f6FWAz7KRI0e6vF30+MBtGI1G9TvhSuPGjeXmm28udTn6UrRs2VL9u0ePHtK9e/dS6/Ts2VPdvqvtK4u/v+OgnwNo39OIQgkDDUQhxL7hltZASWuShgZZY8aMcfvFwhV8eVu/fr36NxpE1a1b1+3Pzp071Xr79++3XR9fvrAtGC93+eWXq4ZKnvpjqjX6wxciVztKcMYZZ9hGWblqDAhoduVO/fr11WlZjcDcNY/TvpygqZk/uHtNNWgkB2jQ5fwFe+HCheq1x+PHe8i52Zr25ays98PKlStLvR+8CUG0L774wrazefbZZ4uv4As2vhzjdw07HWgopr133EEgQBudiOAEmr7h9/Pzzz9X216V5mAILmJboKKBCnfvf/vtd/X+L28cZFk/c+bMEU9D41hIT09X79m1a9dKUVGR2na8V9HsEq+Nxt1nhj2MLNWaHVanCWRVPw+0zyzn30F7+PzTAoruPuOqyxufkc7Q5LCsRqtl0T6Tvv322zI/k7QmoPafSWgUicAgAnR4nAhQIiDlrvGfvS+//FLtNGMH13kHtTqfk9r7BcsxojYY/iZqt4VxumjO6Aq+k2iPx919Y7m7QByClNp9uILfA7yWkJmZKRURCN9xtM9qfHYRhRqDvzeAiDxH+0MMiOzjj26nTp3UUZWyuvW7OlqlfZnAl/XK/OHGTpMGRx3Q7RtHMjDnHj/aERd8ecbObnlTBNw5ceKEOi1vJjbuC93ztfVdHelyB0cMAV8mK0M7uoHO5/7i7jXVoMM6OvSjEzu6hNtnLmhZDnjfOH9h1b5E4YhwRY4K278fvOWJJ56wZTDgCKA2+aGs17qs7bJfVtb7Q/uiiucJnefxfkGQxtXR57Lgiyrep1OnTlU7W+hEjqNr+MLv7gitK/Yd6LUje+Vx9/i0935V3v/+cOWVV6rJDI8//rjaiUFXf+fPRgRyRowYYdvpqWg2A47SIlBbVVX9PKjIZxy2DZ/zmLzh7jOuurzxGenqqG5Fgj+uaJ9JCJhWJCvB/vcbR6Sxc4hAIQJLDz/8sLocgQO8hwYOHKgmB9gHqTTLly9Xp1qmhKc+J735fvHW38TK3Lf9+lW5b0++HwPhOw6CbOBqgghRsGNGA1EIsT9qiKg7jrDiy3J5f+jcpdhjJ0rz1VdfqaM85f04j0lDCj/SQLEDiC9k2AHG2D6kuyJ9H6niwbAjUxn+KJWo7KjA+Ph4FWxwHuOI9OstW7a4LJuwf09gNFtF3g9ljaLzBIx+e/bZZ9W/MYbukUcecbuu/VH6skY32i8rKzMBzwV2QBcvXqyeb4x+GzBggFQHXhOkD6MUxN1YtPJScCvzpTmUIKsF4x4RpEGABinrCLQiuID3tVZOglT08nbikCKtjfJD4EdLkQ7Wz4NAV9XRpvafSXidK/KZ5DziETuE+BuFz8Hbb79dWrVqpcoikF2Ez0C8h5w/L/D+wN9EuOaaazz6Ocn3i+8EwnccLTvE/vObKFQw0EBEbuEPn3aEoDop8NhZww4g0vRx5A31k1oqMmo18WWsqkfs8Qe9LNry8o7wexLSLKvynNkfRXZ3dMNV/XlVaYGEVatW2b5Ia9kMmNuOGmxPPTZvwBe82bNnq3+jrwGOZpcFacPaUVPUtLujLcNjdVeCoGUyfPjhh7YgA458eoJ2VHD37t2Vuh52oLW05eqmspenrBTj8n4QEPCWM888U1555RUVcDhw4IBs2rRJ9ctAkEFL10YJQ3kZHzhajTr26pZNVOd3piKfcficyMjIcFjfeee9rCOlnvw88RdPfCYh8IrPQ+wc/vPPP+o5x5FqZIzYZzpoEKxApgIykFz1YKjONnnz/eKtv4mB/Pc40L/jaJ/VFe2rQxRMGGggIreQLooaVsDRHU/BDuwbb7xh6yPg3JRK2xksq05Wq/VEYyYc/XUFtbbaDrS7uk5vuOCCC9Qpdmy05nwVYZ/OjZp9V7SacU/A0RakeOL5Q8q/dmrfw8GZ9ppp/RD8BeUSyGDQggwIOpQHTR617ddSXJ3hPac1ZnNXAoEgA1Kt0XxNCzIMGjSoGo/G8f61RnDllW240q5dO3W6d+9e8SZ8ma7qjz92brGzrTWgc/fedlU2gQZ0qMH3x+eB9hmnNWZ1BTu8Wl8O58847fPE3WcJGiDu2LFDvMG+DKIi/Q6qQ/udRr8DT6WfI9iHbCkteOn8NwqlUvZNUz35Oam9X5CZWJm+G/78m2jfe8Hd7zd6yNj3cgjn7zj2v4NaQBOBcKJQw0ADEZXbcVxrfIWfsjgfRdVqH8urTXSuzdWOyuKLiTvajh2+NGk7Bc7Gjx+vTlHDXFZDNU9DqiQeA3YAHn300Qp/0W7durXtOUEXb2f48jhjxgyPbSeedxyV1zIZtMwG7Dy76vxt/37AUf/yMlFQL40UY28EGezLJSoSZNAgNVr7Mu4qaPPxxx/bdtJd7ZBqmQwol8CRMDR+rGiQQdshLAsa1mk12r169ZLK0noT/Pbbb+JNFUkx9lc5jSvYaURdOEomXJUE2UMmhNakD/0+qpvKXtXPA+19tW7dOtXo0Blub/LkybZMDvzY0/p7uPos0X53yvuMrir7hoBlfY57Al4j/C5ih02bwuEOPo/Ql6Y6f6Pw+qH5n7v+DNX9nESpY/PmzdW/8X6p6GeoP/8morwIrwECPcgEcWX69Onq+cbOPdYP5+84GgRe8Hcdz115DZyJgpK/52sSUfVg/rk2H7oyKjrn3GQyWfv27avWwwzpKVOmWA8fPmxbnpubq2ZuP/DAA9akpCSH6/br1896xx13WL/88ktrZmam7fKMjAx1O5hL7Wrm95gxY9TlLVu2VPO53dFmgmO75s6da83Ly1OXHz161HrXXXfZHt+rr75aqfnxzs8t1q2s1157zXb/1157rcOcdGznF198Yb3mmmus2dnZDte79dZb1XUSExPVjHdthvrff/+t1k9NTbXd7g8//OBwXZyv7Hth27Zttut06dJFnV5++eVlXgevKdbD6/fII49Y9+zZ4zBrfd26ddYnn3zSWrNmzTLnmZf13LuD29Wu/9xzz1X6+phRf9ZZZ6nrN2jQwLpy5Up1udlsti5evNhao0YNt88BfhcGDRqklmNmPNavDLw+PXr0UHPbnZ+Xf/75xzpixAjbLPoWLVpY8/PzK/348LuG68fHx6vtdbcdFXmfuHufeUtOTo41PT3d9qM91xdccIHD5adOnSp1XXwO4b34008/qX9rNm3aZL3xxhttnxMVeSza7z1eiyNHjnjksVXl8wCv33nnnaeug8/WDz74wFpcXKyW7d27V62v3SZed2dvvvmmbfn48eNtt43ncNSoUVadTmdNTk52+7tYkde/rM9R/H5h2cMPP6x+71yZP3++WqdJkyblPodYB+viOs4mTZpk297bbrvN+ueff9qW4b7xfGOdRo0aWdeuXetwPfydcv6dxOcYPn/xvOM2Bw8ebFu2YcMGdVnTpk299jmJ11P7+9i9e3e1zfiMAvxNwGtyyy23WLdv3x4wfxMff/xx2+PF+037m4/TsWPH2u4bn3PObr/9drUMp+5UZPvcvUfK+r7jj+84mhkzZqjlXbt2dfuYiIIZAw1EQc7bgQbAF9SrrrrKtj5+sEOGL6naH1Lti7mrLwb219F25LSfAQMG2L5A2e90xcTEqOX4MlynTh31BQI/9l/IsrKyHO4D95+SkuKwTU888YTLx+TtQANMnz5dbb+2LbGxsSpQYH+Z/ZcTwOOrX7++bXlkZKTtOUPw4ccff/RooAE6d+7s8JosWrSozPXxRdf+Syt+EhIS1HNv/9jw4xwoqk6gYf/+/bbrau+Lsn5mz57t8nawDdhJ0G4rLi7O9n7DT6dOnVzuzK5evdrhdSnv/j/88EO3rw9+cJ+1atVS7wv7yzt06FDu72RZr01aWpq6nW+//TaoAg3azkZ5P652SvF7ZL8OPpuio6Nt57Ez9/XXX5e7Dfgsaty4sboOduQ9qSqfB/j9ad++vW05doS04ID2ezBnzhyX94cdqN69e9vWxeei9vmIH/x+lPU5WN1AA3a0tNvAa4GdfLx2N910k8cDDRaLxTpu3DiHz348v3jd9Xq9w3sDwShXfz/tXxP72znjjDPUjrpG22kePny41z4nYcGCBQ7vYfwbj0cLRuLHPmDl77+JeLwDBw50eG86P1YEbLRgWaAEGvzxHUdz/vnnq3VeeOEFt4+JKJixdIKIKpQGi/pFpBWi4R264iNlEGOeUMuKWnak9GtzpjVz585VaZSYNY1O3vjuWlBQoBonoVM3UnqRqu6cVoh1kdqOddAgCc3O0KgJP/bp5xhBhvpldOdHmjlq2pEWi2ZaSM3EbWjNAv1h1KhRaoLD3XffrWq9AWmweHyDBw9WYyWdZ46jZwJS+tFISmsKmJCQoNL40diuuvXirtiXCGB73NUd2zcdRP0p5r0PHTpUWrRooUoK8NyjyRdeC6TooiGW87gz++7t3bp1q9R22tcd49/l9QKwT5G217RpU7Vt2EakmyM1Hum8aBKIdHLMVXc1/tD+/tFFvLz7x3vdHm4fJSp33nmnSmvH+xdp5Xj/4zlEij2aS2JaDLaxKvDa3HHHHerfKOsIF2jmh9TsSy65RP0O4blH2jJqxydNmqQa/F122WXl3g5KJlA64YkmkJ74PMDvD9Krn3vuOfX7gseEz100IEQJCN4r//vf/1zeH0qgVqxYoR5/27Zt1XsD73V8XqNmHCVI3jR69GiZM2eOeg3w+4VGgPgM10qDPAmPC2Uk+L3G2F7Uu+Pxo18AfpfR9wAlVvjMsk9RR9r866+/rp5/fBagjwuaPOI6PXr0UCNT8bmrNWi0H2vpzc9J7XMZPRXQZBC9V5Bej/c1yn9QsoHPEue6fn/+TcTjRd8a9EK5/PLLVaNF9CDAKc7j/Y0eQK5GhYbbdxxAiR7KovA7XZG+MUTBKALRBn9vBBERhYepU6fKuHHj1PzxtWvX+ntzQhK+wKLfB3aa0HwQO+FE5JnfLQQMMI0GwUT7SUFElYHAGHqKIDD89ttv88mjkMSMBiIi8hk0nAQcfSbvQCM5ZE3gaOLLL7/Mp5nIQ7RshiuvvJJBBqoyNABFNgTG7JbXwJQomDHQQEREPoFUVKSK9uvXT6Ulk3ePlqHkBqUg+FJLRNWHNHrsGA4fPpxPJ1XZSy+9pKakoOwJpTBEoYqlE0RERCFo2bJl8scff6jeD+3bt/f35hAR0X+BBvSeQv8N9NUgClUMNBARERERERGRx7B0goiIiIiIiIg8hoEGIiIiIiIiIvIYBhqIiIiIiIiIyGMYaCAiIiIiIiIij2GggYiIiIiIiIg8hoEGIiIiIiIiIvIYg+duiiqibt26kpeXJ40bN+YTRkRERERERB5z4MABiY+Pl2PHjok/MaPBxxBkMBqNvr5bIiIiIiIiCnFGo1Htc/obMxp8TMtk2L59u6/vmoiIiIiIiEJY+/btJRAwo4GIiIiIiIiIPIaBBiIiIiIiIiLyGAYaiIiIiIiIiMhjGGggIiIiIiIiIo9hoIGIiIiIiIiIPIaBBiIiIiIiIiLyGAYaiIiIiIiIiMhjGGggIiIiIiIiIo9hoIGIiIiIiIiIPIaBBiIiIiIiIiLyGAYaiIiIiIiIiMhjGGggIiIiIiIiIo9hoIGIiIiIiIiIPIaBBiIiIiIiIiLyGAYaiIiIiIiIiMhjGGggIiIiIiIiIo9hoIGIiIiIiIiIPIaBBiIiIiIiIiLyGAYaiIiIiIiIiMhjGGggIiIiIiIiIgYaiIiIiIiIiCjwGPy9AUREREREROGqyGSWTfuzJLugWJJio6Rzk2SJNuj9vVlE1cJAAxERERERkR98u/2YLN54UE7kFEmxySJRBp3UToyWgV0ayaXt6/I1oaDFQAMREREREZEfggzz1uyVg6fyxWyxSmyUXgpyzHIsu1Ay841qHQYbKFgx0EBEREREROTjcglkMiDIkBBtkLTEKImIiBCr1SrpOcXqcizv2SaNZRQUlDh1goiIiIiIyIfQkwHlEshk0IIMgFOcx+VYvvlAFl8XCkoMNBAREREREfkQGj+iJwPKJbQggwbnYyJ1anlWfjFfFwpKDDQQERERERH5EKZLoPFjQbFZlUvYw/lCY0ljyOS4KL4uFJQYaCAiIiIiIvIhjLDEdAm9LkL1ZNCCDVqPBlyO5Z0aJ/N1oaDEZpBERERERERVbOqIfgsohUCWAgII0QZ9udfDOhhhiekSaPyYXWBU5RLIZECQoVFqnFpekdsiCkQhndGwYcMGGThwoNSvX18iIyMlOTlZevToIfPnzy+VojR06FBVD+Xu57XXXvPb4yAiIiIiosAbT/ngB5tkxlc75IWVu9QpzuPyisDoynsvai5nN0ySBimxkhgTqU5xHpdztCUFs5DNaPjkk0/kpptuErPZLJ07d1YBhvT0dFm7dq389NNPsnLlSvnggw9KXe+yyy6TunXrlrq8TZs2PtpyIiIiIiIKZAgmzFuzV2UjYEIEmjoW5JjlWHahylKAigQKsA5GWGK6BBo/oicDyiWYyUDBLiQDDSaTSR544AEVZEAw4eabb7Yt27Fjh3Tv3l0WLlwod911l/Tu3dvhuiNHjpRevXr5YauJiIiIiCgYyiUWbzyoggwJ0QbbeEqtvwIux3IEECpaRtGteU2fbDuRr4Rk6cTff/8tJ06cUFkI9kEGOOOMM+TWW2+1lVYQERERERFVFHoynMgpUpkMWpABcIrzuBzLkaVAFK5CMtAQHR1dofVq1mTkkIiIiIiIKg6NH4tNFlUuoQUZNDiPpo5YjlIIonAVkqUTzZs3lxYtWsjOnTtViYRz6cT7778vKSkp0r9//1LX/fTTT1V/B5RdNGvWTK6++mpp27atjx8BEREREREFIkyXiDLoVE8GlEvYBxtwHpMjaiboVL8FonAVkoEGvV4vCxYskKuuukpuueUWefbZZ6VVq1aqnALNINu1ayfvvPOOpKamlrru3LlzHc6PGDFC7r//fpkzZ44YDCH5dBERERERUQVhhGXtxGjV+BE9GZx7NGA8JZajqSNRuArZPecLL7xQVq9erbIWNm3apH4gKipKLrnkEpX1YK9Tp05y/vnnS58+faRhw4Zy7Ngx+eqrr2Ts2LHyyiuvqOs9//zzFb7/9u3bu7x8z549KtuCiIiIiIiCD5o3DuzSSE2XQOPH7AKjKpdAJgOCDI1S49RyTo6gcBZhRegtBC1atEjuuOMO6datmzz99NNqx//IkSPyzDPPyOuvv65GXv7yyy/l9nPYvn27WtdiscjevXulUaNGHgk04HaJiIiIiCh4R1xiugQaP6InA8opkMmAIENFRlsSeYO2H+rv/c2QDDTs2rVLPcG1a9dWEygSEhIclqPvwhdffKEyFVAWUZ4bb7xRlixZIvPnz5ehQ4eGxAtPRERERETVH3WJ6RJo/IieDCiXYCYD+VOg7G+G5NSJDz/8UIxGo/Tr169UkAEGDhyoTtesWVOh20N/Bzh69KiHt5SIiIiIiIIVggrdmteUfmfWU6cMMhCFcKDh0KFD6jQpKcnlcu3yzMzMCt2etl58fLzHtpGIiIiIiIgoFIVkoKFu3ZKaqI0bN7pcvmHDBnXatGnTcm+rqKhIVqxYof6NXg1EREREREQUfkKw64DXhGSg4dprr7WVRrz66qsOy9avX2+bHjFgwAB1ij4O7733ngoq2EtPT5dBgwbJwYMHpUOHDmqSBREREREREYVXgOHTTz+VM888U7Zu3ervzQkKIdkMEp588kk1YUJriNGuXTs1dWLdunVqgsQ999wj8+bNU8t//PFH6d27t6SkpEiXLl0kLS1Nrfv7779LTk6OGnf5/fffS+vWrUOmOQcRERERERGVDfuKI0eOlF9//VWdv+KKK2wZ74GofYDsb4ZsoAGWLl0qr732mgoYZGdnS2JionTs2FHuvvtuGTx4sG09BBVmz56tsh327dsnGRkZauwlAguYUDF8+HAVhAilF56IiIiIiIhc++OPP2TUqFHy9ddfO1yu0+lkx44dHjkI7Q2Bsr8Z0oGGQBQoLzwRERERERE52rt3r4wbN04WLlxY6qm55pprZPr06bZ9ukDUPkD2Nw1+vXciIiIiIiIiPztx4oRMmTJFldcbjUaHZd27d5eZM2eyZ18lMNBAREREREQUpopMZtm0P0uyC4olKTZKOjdJlmiDXsLF6dOn5dlnn1U/eXl5DsvQ/HHGjBly5ZVXSkREhN+2MRgx0EBERERERBSGvt1+TBZvPCgncoqk2GSRKINOaidGy8AujeTS9nUllGHiIPr5TZ06VU6ePOmwrEmTJjJ58mS55ZZbRK8Pn6CLJzHQQEREREREXheKR86D+TEhyDBvzV45eCpfzBarxEbppSDHLMeyCyUzv6R0IBSDDWazWfVfGD9+vBoEYK9mzZoyduxYuf/++9VwAKo6BhqIiIiIiMirQvHIeTA/JgRIsO0IMiREGyQtMUqVBmBOQHpOsbocy3u2SQuawEl58Ni+/PJLNUnizz//dFgWHx8vjz32mDzxxBNSo0YNv21jKGGggYiIiIiIvLpD/urqPfJvep46ch4TqRez1RrUR86DPRsAWRgIkGDbtSAD4BTnswuMavnmA1nSrXlNCXbr1q2TESNGyNq1ax0uNxgMcu+996opE3Xq1PHb9oUinb83gIiIiIiIQhOOnL/0w27Zfvi05BtNYrJY1KnFYhHs22pHzrFesHDOBmhZO14apsSqU5wPhseEUg9kYSBA4tzkEOdjInVqeVZ+sQSzv/76S6677jq54IILSgUZBg0aJDt27JCXXnqJQQYvYKCBiIiIiIi84vXVe2X3iVwxWixiNlvFYhUpMlokr9gsuYUmKSg2246cB4vysgFweaA/JvSTQKkHnn+UFNjD+UJjSSlIclyUBKODBw/KsGHD5KyzzpLly5c7LLv00kvl999/l0WLFknLli39to2hjqUTRERERETkcTii/91fx6TIZBF9RETJ0XPsyIqI0WyRYnPJ5YVGc1AdOQ+FbAA0rUQ/CZR6oCeDc48GvS5CLe/UOFmCSUZGhhpHiSwFTJWwd+6558rMmTOlT58+ftu+cMJAAxEREREReeXIf26RXfkAjpxHRKhgQ6ReJ0aTSSwRIiaLNaiOnNuyAXJKsgHsgw1aNkDNhMDOBkCDRzStRD8JlHqgJwMCJNh2BBkapcap5cHSCDIvL0/mzJkjs2bNktOnTzssa926tUyfPl2uv/76UoEh8h4GGoiIiIiIyCtH/g36CInUR6hyAqPZKpH6kqP+WtABEqIMQXXkPFSyAbRmlfaTMxAgCZbJGWA0GuWtt96SSZMmybFjxxyW1a9fXyZOnCh33HGHavpIvsVnnIiIiIiIvHLkHxMmInU6MeisqoTCZLSKLkJUrwaL1SqxkXq5tH2doDlyHmrZAAgmYIQl+kmg1ANZGAiQBPq2o5nokiVLZOzYsbJr1y6HZUlJSTJy5Ej53//+J3FxcX7bxnDHQAMREREREXn1yD9yFwx6ixhNFhVkQEaDzhohLWsnyN0XNQ+6Zz8UsgE0CCoE0wjLlStXqkACGjrai4mJUcEFjLFMTU312/ZRCQYaiIiIiIjI60f+Me4ODRRx5D9ap5NmafFyf88WAX/0PNSyAYIVAgsIMCDQYE+n06kJExMmTJCGDRv6bfvIEQMNRERERETksyP/aKToySP/mG6BxpPoCYFyDWRS+GpnP9iyAYIRSiNQIrF48eJSy9Dgcdq0adK2bVu/bBu5x0ADEREREREFzZF/+8DCruO5sulgpmTkFnssiOHPwAX9v6NHj8rkyZPlzTffFJPJ5PDU9OzZU42q7NatG5+yAMVAAxERERERBcWR/2+3H7NlR2TkFqmyDJPZKtEGnSTFRaqRk+gJgcuhssEG+9u3D1z079RAUuOjGXzwgezsbHn66aflhRdekPz8fIdlHTp0kBkzZki/fv18OqqSwafKY6CBiIiIiIgCHoIA89bsVf0eTGaL5BvNapIFej9YrBESF6WXBskxasQk1kHAAJkUFc1GsL99jONEPwkELvafzJMN+zIlOS5STcnwdOkHlSgsLJSXX35Zpk+fLqdOnXJ4Wpo1ayZTp06VQYMGqZ4MvuQu+MTXv2wMNBARERERkU/kFBpl8QbstBVK7cQYGXhuI0mMiazQEWXs7CEIkBBtkGhDhBw4VSD6iAjR60SKzRZJzylSZRlpiVFq5CR2DFGuUZFMCufbx23giDmyJnA/RgQ2ik1qmwuN1cuaIEdms1neffdd1czx4MGDDstq164t48aNk3vuuUeioqJ8/tS5Cz7x9S8fAw1EREREROR1T3/9t9qZzysyiwXjLSMi5NXVe9SR4af6ld3MDz0TEDjAzh6CANjJt4iIXhehjjAXFJtVsCG30CQ1Yg0SE6lTR5/RE6IinG8fQQZs48ncYnUKkfoISYqNlIYpVc+aoP9ntVrls88+k9GjR8tff/3l8NToo2Ol5cWDpevVt0nrHm39EmRwF3zCdvP1Lx8DDURERERE5PUgw4J1+1RAAPvtOl2EWCwWtTOHy6GsYAMaMyJwgCPK2NlDgAEJ9EaLFXus6vZwuyaLRe0IYoRmzQSdynCoCPvbt0qE5BSY5HRhsRQYS7YX9ycSoW4/IsJQpawJ+n9r165Voyp/+eUXh6clQm+QWudeLc363iqmqET5O8OkMgr8kTliH3yqmRAppwtN6t94L+A8X/+yMdBARERERETeLZfYeFAFGRAQiDHoVDYDMgUKTRZ1OZbf36uF2zIKTH9QmQs52PG3SmKMQZ1HFkOx2Spms0Ui9XpVSoGjzdgZRB09pltUhHb72ZlGyS00qgCG0Ywfi6gQgzVCIgwihv/6AyDYUdmsiVBW0WaJf/75p4waNUpWrFjhuCAiQmp2uFhaXX6nNG7SOCAyB7TgE+w+kaf+jXN4B+C9gl6UfP3dY6CBiIiIiIi8Bj0ZUC6BzAAtyAA4xXksw8/HGw/JsO7NXN4GdlwROEBtPHY+kVGQlhitAgEFxSU7gGazVY7nFIlBFyGNUuNUSUZFd0xx+1BoMosFWRL/bR+2ueRcyf8TYkp2n6qSNRGqkw0q0ixx3759Mn78eHn//ffVc2fvgt6XSOR5N0tOXANpXDveNk0Cp/7MHMFrgIwW3D82SctsQRAKAS6cT4wxe+z1DzUMNBARERERkdeg8aPqyYByB6eRhDiPi7D8+OkCt7eBHW7suKI3A45wY+cPGQURUlJGEa3XSUpclNRMiKreRAC1D1yyTTiDE223WNtB1o60VzZroqzAwq7jubLpYKZk5BYH1WSD8polZp06Kb988qa88sorYjSWNM/UnH/++TJr1izJS2kpL6zcJaYiU6mRlf7MHDmzQQ3JKzLZ+olgO+wzcXCK5e3r1/DpdgULBhqIiIiIiMhrMKlB7aBZSnbO7IMNOK96NkRESJ0asWXejrbDbX/0vGZCtNSKj5KzGyUJujZERFilY6MUOa95aqW2ETv8EBOpF70+QoxamrzFKiaLVWU5FJmssjc913Zku7JZE+6yADDZAjvlJrNVog06SYqLDIrJBmU1Szx6MlvWL5knnz/2iRgL8xyu165dOzXC8pprrlHrr9uT4VAWYx9s8EbmSEVtO3xa4qMNkoXX4L/tKOktgoBTyfsYy7cfOc0eHS4w0EBERERERF6DEZaYLoEdUxwJdu7RgP3K+Gi93NilYbm3hR1u1OojjR5HuLHziR31pZsP24IPK3ecqHQ2gFaPj538+skxanoFAgwow0B5xsFTJdkWCAQguFGdbAP7LAATxmYazVJksqjaf4s1QuKi9NIgOfAnW7ia1GE2GWXv2uWyfcV8KcrJdFi/UaNGMmnSJBkyZIjo9foyy2LsezR4MnOkMiUpWD82Uq8mjeC9qpVLROgjJEpf0qMBy9mjwzUGGoiIiIiIyGvQ4BE75drUCfRj0Gre1c5aVElZhLtGkM6wk6jV6mOn/e2f97lN3YeKBAPsm03ieHqN2P/fFuzwoqQhOT5KruvYQLo2S1U7vVXZ8XfOAog2RMiBUwWqiaVeJ2pnNj2nSAVQAn2yhf2kDryY+zd8J38uf13yTh5xWC8xKUUmjBsjDz74oMTExFS4LAYZBJ7MHKlsSYr2noCWtRPU+xZTR9AQFIGxvel5ajl7NLjGQAMREREREXmVNroSO33YYdNKKLDDhp2+skZbViV1v7LZAOUdVTfoddK8Vrzc27N5tTILnLMAsHONEg3sUKtAR7FZBRuQUVEj1hDQky2wIx6pj5Bj29bJ9h/fkaxDux2WR0RGS4veA+XVpydJ3w6um3yWXRZTvT4V5fWPsL/f8t4TCDSVvCcMHsu0CHUMNBARERERkdchmIARlpgugcaP6MmAcomKZjJUJHW/qtMKvHlU3V0WALYTt41j5phkgKwA9ABApgeOnPuzP0FFmI7tlI0vPyLHdm5yuDxCp5d6Xa+UtJ43S5czmkuP9o0rdHuuymI8lTlSlSCUr94ToYqBBiIiIiIi8gkEFdyNsKzuTnt1pxV446h6WSUa2OlNjDGo88hiKDZbxWy2SKRer0opAvWo+d9//y2jR4+WpUuXllpW86yeUqfPUIlPa1ilHXH7spjq8FQQyhfviVDFQAMREREREQUd5512T0wr8ORR9YqWaKQlRquGkwXFJZMuzGarHM8pUo0oA+mo+aFDh2TixIkyf/58NUHEXv32XaXFFfdIXP1WATGa05NBKG+/J0IVAw1ERERERBR0vDWtwFNH1d3p0DBZ9p7Mk1O5xWrHVe0MS0kZRbReJylxUVIzIcrvO+uaU6dOycyZM2Xu3LlSWFjosOycc85Ry3r06h1QO+KeDkJ5+z0RihhoICIiIiKioOOPGvqqjkp0noBQZLSI2WoVs1UkVkSapcVLrfgo6dQkRVrVTgiInfX8/Hx58cUXZdasWZKVleWwrGXLljJt2jQZMGCA6HQlkxkCaUf8zAY1bKNJD2QUSMPUGNHrdGzk6EMMNBARERERkUd2pn3NlzX01RmV6GoCQqRep6ZvREfq5dJ2deTui6o30cJTTCaTvP322zJp0iQ5csRxVGXdunVlwoQJcuedd0pkZNWaeHqb9jpl5BWL0WyV9NwiOZlXpPphaJkjgVSSEqoYaCAiIiIiomrvTPuLL2roqzMqsbwJCBhl+cdBx4wBf8D2fPLJJzJmzBj5559/HJbVqFFDRowYIcOHD5f4+PiADWo5v05xUXo5XYgJHqJGh9auEaMyRgL5/RwqGGggIiIiIqJq7Uz7mzdr6Ks7KtGTYzi9ZdWqVTJy5EjZsGGDw+XR0dHy0EMPyahRo6RmzZoBHdRy9zrheT+UWSB5xSapFR8tz9/UscojVaniGGggIiIiIgpz1d2ZDmXVDRR4egynJ23evFkFGL799luHy9F34fbbb1dTJho3bhwUQS13rxNKJRqnxsruE3litFhk+5HTAdVPIlSVdO4gIiIiIqKwVd7ONC7XdqbDTXUDBbYJCMUlExDsaRMQsLwyYzira8+ePTJ48GDp3LlzqSDDtddeK3/++afq0+CNIINzUKtl7XhpmBKrTnFeC2phvcoI5IBOOGKggYiIiIgozHEnzb3qBgq0MZw4so7sEO02qjuGsyqOHTumSiHatm0rH374ocOyHj16yM8//yzLli2Tdu3aBV1QKxADOuGMpRNERERERGHOtpOWU7KTZn9EWNtJwzSHcNxJ0wIFSOtHYMC5rKS8QIE/xnA6O336tMyePVuef/55ycvLc1h21llnyYwZM+SKK64olQkQTEGt6r5O5FkMNBARERERhTlf7qQF0/hMTwUKfDmG015RUZG88sorMm3aNMnIyHBY1qRJE5kyZYrcfPPNotfrgz6oFQgBHfp/DDQQEREREYU5X+2kBeP4TE8FCpzHcMZHG9SOdX6xWdbtyfBowMVsNsv7778v48ePlwMHDjgsq1WrlowdO1buu+8+NVUilIJa/groUGkMNBARERERkdd30oJ5fKarQAGOuGNnuDLBAW0MJ56LBb/s83jABTvrK1asUOMot23b5rAsPj5eHn/8cfVTo0YNCdWglideJ6o+BhqIiIiIiMirO2nljc88kJEvr63eq9arlRATsOUUWqBAg+1FNkJFy0Cw/uur98rSPw7Lqdxi0ekiJM5DARc0csSoyp9++snh8sjISLn33ntVFkOdOnUkHIJazq8T+R4DDUREREREQcabfQ6quzNd2UkDep1IVkGx5B41yexvdqrgRjCkule2DATrf/jbAdmwP1OVS+Bxx0XqJS4qShokx6iAizbaEcGeij7H27dvl9GjR8tnn31Wahn6L6APQ/PmzSXQMPMgtDHQQEREREQURHzZ58BT9+Vu0sCpvGI5ml0SgLBYLJJXZJa8ooJSR/cDrYFkZctAtPX3nMhVQQZkcpjNInlWsxzJKlTrIACDMgJttGN5R+TRe2HChAmyYMGCUuMc+/XrpyZJdOzYUQIZMw9CFwMNRERERERBwpd9Djx5X64mDVisIuk5RVJoNKl1UKdfp0a0JMYYHI7uG80WWbr5cJWCHe4CFNUJXJRXBuKclWC/frRBJ0UmnVisVvU48NiwHM8DMjkqMtoR0yOmT58uL7/8spoqYa9r164ya9Ys6dWrV4UeC5G3MNBARERERBQEKruDG0j35WrSQG6hWd0PAg5oAogd74QYg7of7ej+rhO5Muf7XZKVb6x0sMNdNkbrOonyz/GcKmdplFUG4iorwX792njcRSYxmq3o3CiRep2YzGYpNlskp8BY5mjHvLw8eeGFF+Tpp5+W06dPOyxr06aNCj7079/fIWOEyF8YaCAiIiIiCgKV3cENpPtyNWnAKlYpMllty9MSo0Vndz/RkTrJyC1Sl9VKiK5UsMNdNsb+jHxZtzdDDBERYtDrqpSl4a4MRNtu56wE+/UTYyMlylCkAgsINkTqRTWEtFiscirf9WhHo9Eob775pkyePFmOHTvmcH8NGjSQiRMnytChQ8Vg4K4dBQ6+G4mIiIiIgkBld3AD7b6cJw3gugXFFjFZLFIvKVpS4///KD6CCbmFJjFbRHR6qVSww102BgIO24+clkKjWWIi9dK6bpzodbpKZ2m4KgOx327nrAT79bEmAioIMmA7TUar2i6zLkKKTBZpkZZgG+2InhUff/yxmhaxe/duh21ITk5WIywffvhhiY2NrfBrQOQrDDQQEREREQWByu7gBuJ92U8aSM8plHd+3icHVNZBye3aZyxgrxyTGdCzoTLBDnfZGGg0KcijsKqbVudrxOoqnaXhqgzEfrudsxJcrQ+4L9UYUkSNuMT6g89trJ6j7777To2q3LRpk8N9x8TEyCOPPCJPPfWUpKSkVOq5J/IlBhqIiIiIiIJAZXdwA/W+7CcN4N9aiQN29BE8QBADt1+3Row6yo/MhsoEO9xlYyBzAiEGXYQI/mVCc4gqZGm4KgOx3+5GqXG2rISy1tchwBCpl9SEKOnfqYHcc1Fz2bp5k/Tte6t8//33Dvep1+tl2LBhasoEyiWIAh0DDUREREREQaCyO7jBcF/O5RTY0UfwAEGM/p0byNJNh2XroWyXwQ4EDAy6CJUZsW5Phm1yhLtsDIMOu/ZW1XzSarGqbAKDzlTSgFIql6VR1na7airpev1o2/pNI0/LrYMHyZIlS0rd14ABA2Tq1Kmq4SNRsGCggYiIiIgoSFR2BzcY7su+nALZBNjRR6YEggaROp3LYIcJtRYREZKRVywv/7DHYXIEbstVNkZ8tF5lMSCPochskZM5aABZLJE6NJ7UVzpLo6ztruj6dQz5MnPaBHnrrbfEbEZpx//r3bu3zJw5U42sJAo2EVaE+chn2rdvr063b9/OZ52IiIgoCKBpH+r+kZKPo+XakXN/b1NFd3CD6b4qMqaywGhW4y6RnYAsBTU5othsy7S496Lm6nr2UycQoDhdYJJ8o1lNeMAOEDIi1J7Qf5kRjVPjZES/th4N1riTlZUls2bNkjlz5khBQYHDso4dO6oAw6WXXspRlRS0+5vMaCAiIiIiquBOrv2Rc1/skFakz0Eo3VfFGkjul/wis2oS6W7k5cu3dFbX1V47TJo4XWgSfUSEJMToJUIXIUaTRZVRmBFtsIrERxvU/XgTggovvfSSzJgxQzIzMx2WNW/eXJVI3HTTTaJTZR5EwYuBBiIiIiLymmJzsWxJ3yLZRdmSFJ0kHdI6SJS++lMRfBVksD8qro6c55hVSj7S+cGfwYZwogU70IvBaEGAwHGihKvJEfYBil/3npLlWw5LVl6xtKqToDIa0GQSpRT6CJHjp4vU7ZQ3caKq2S0mk0kWLFggEydOlEOHDjksq127towfP17uvvtuiYoKjt8NovIw0EBEREREXrHqwCpZumuppBekq4ADAgxpsWnSv1V/6dO4T0A/69ihxNFwBBkSot0fOceOrL/LKMKJu4kS7iZHaAEKnI/appO46JJRmbhmjdhI23WR7VDexImqZLfg/bJs2TIZPXq0/P333w7LEhMT5cknn5RHH31UEhISqvnMEAUWBhqIiIiIyCtBhvnb5suh3ENisVokxhAjGYUZciL/hGQVZal1AjnYgKPW2KFEJkN5R879WVYQbtxNlChv5GVVr1ed7JbVq1fLyJEjZf369Q6XI2vhgQceUMGHtDTvlmoQ+QuLf4iIiIjIo5C9gEwGBBkSIhOkeVJzaZDQQJ3GR8bL4dzDajnWC5Uj5+QbKFVAFgEaPyKzROtrr2WauJscUdXrucpuaVk7XhqmxKpTnNeyW7AebNmyRa644grp1auXQ5AB75vbb79d/vnnH3n++ecZZKCQxowGIiIiIvIo9GRAuQQyGWrF1nLIBsD508Wn1XKsd27dcwNySkR1j4CTd+B1RKmCq5GX2tQJLHd+vat6vcpkt6z4eYt8+sZzsnDhQlsgQ3P11VfLtGnT5KyzzuJbg8ICAw1ERERE5FFo/IhsBZRLuMwG0Meo5VgvUKdEaEfAkRqPI97OPRrKOgJO3qW9jvavM4I+5b3OVb1eedktuqJs2bL4Nbnp0c/FZCopo9BceOGFalRl9+7dPfToiYIDAw1ERERE5FGYLoHGj+jJ4DIbwFwoKTEpar1AnRJRnSPg5H32EyVQvoLMEgR9yns9qnI9d9ktxsI8+fvbRfL3d4vEUlzgcJ327durEZZXXXVVqeAEUThgoIGIiIiIPAojLDFdAo0fTxactJVPYCcN5/URerUc6wXylIiqHgEn39AmSnj7es7ZLakxInt/Wi5/ffmOFOWUNDbVNG7cWCZPniy33nqr6PUMQlH4YqCBiIiIiDwK2QwYYYnpEmj8iJ4MKJdAJgOCDGgMieVYL9CnRFT1yDmFDi275VRukfzx4xfy88p3pDjruMM6NZJTZOL4cXL//fdLTEyM37aVKFAw0EBEREREHqeNrsR0CTR+RE8GlEsgkwFBBk+PtvTmlIiqHjmn0ICsGNP+TfLHi0/Kv//85bDMEBUjA++4T16ZNVGSkjxbCkQUzBhoICIiIiKvQDChe4PuaroEGj+iJwPKJTyZyaDhlAjyBoynHDFihKxZs8bhcr3BINcOGiLPzZgsTRo24JNP5ISBBiIiIiLyGgQVvDHC0hmnRJAn7dixQ0aPHi3Lli0rtWzQoEEyZcoUadmyJZ90IjcYaCAiIiKioMcpEeQJBw8elIkTJ8o777wjFovFYdmll16qJkl07tw5oJ9sNEZFzxKUEyHTB0E49hQhX2OggYiIiIhCAqdEUFWdOnVKBRHmzp0rRUVFDsu6dOkiM2fOlIsvvjjgn2CMeLWfkoKxnJySQv7AQAMRERERhQxOiaDKyM/Plzlz5sisWbMkOzvbYVmrVq1k2rRpMmDAgFINRgM1yDBvzV41yhXTV9AYtSDHrMZyZuYb1TocyUq+opMQtmHDBhk4cKDUr19fIiMjJTk5WXr06CHz589X3WOdmc1mef755+Wss86S2NhYSUtLU9dHjRYRERERBQdtSkS/M+upU6aNkzOj0Sjz5s1TfRbQi8E+yFCvXj157bXXZPv27XLjjTcGRZAB5RLIZECQISHaIC1rx0vDlFh1ivO4HMuxHpEvhGxGwyeffCI33XSTCh6gjgoBhvT0dFm7dq389NNPsnLlSvnggw9s66MGCx8kS5cuVQGJK6+8Uk6ePClLliyRFStWyA8//CBdu3b162MiIiIiIqKqw8FGfL8fM2aM7Nq1y2EZxlOOHDlS/ve//0lcXFxQPc3oyYByCWQypCVG2YIjOMX57AKjWr75QBZHtZJPhGSgwWQyyQMPPKCCDAgm3HzzzbZlyE7o3r27LFy4UO666y7p3bu3uvztt99WQQakSCEYUadOHVvAAulSt9xyi7quwRCSTxkRERERUUjDgUYEEn7//XeHy6Ojo+Xhhx+WUaNGSWpqqgQjNH5ETwaUSzhnYOB8TKROLc/KL/bbNlJ4CcnSib///ltOnDghbdq0cQgywBlnnCG33nqrrbRC89xzz6nTp59+2hZkgBtuuEGuueYa2b17tyxfvtxnj4GIiIiIqDKQFr9uT4Z8ve2oOmWafAkEFi655BL1Yx9k0Ol0MmzYMJXZMHv27KANMgCmS6DxY0GxuVSJOM4XGksaQybHRfltGym8hOTheUQlK6JmzZrq9N9//1XZCujLgJIJZ8ho+Oyzz+Tzzz9XgQciIiIiokDCaQOlIYAwduxYWbx4call1113nUyfPl0dhAwFGGGJ6RJo/JieU2wrn0CQAef1ugi1vFPjZH9vKoWJkAw0NG/eXFq0aCE7d+5UJRLOpRPvv/++pKSkSP/+/dVlW7ZsUadnnnmmahrpTJuVu3XrVp89BiIiIiKiiuC0AUdHjx6VyZMny5tvvqlKqu317NlTjars1q1bSL250PB0YJdGaroEGj+iJwPKJZDJgCBDo9Q4tZyNUclXQjLQoNfrZcGCBXLVVVep3grPPvus6r2Acgr0X2jXrp288847tvSoAwcOqNOGDRu6vD3t8v379/vwURARERERVW7agPORbG3aQM82aX7fycS2omkh+gkg1R9H4T25TZgcgTLoF154QY2ttHf22WerAEO/fv2CYopEVWijK/F6o/EjejLUTNCpTAYEGTjaknwpJAMNcOGFF8rq1atV1sKmTZvUD0RFRan6LGQ9aHJzc9Wpu+6y8fHx6jQnJ6fC99++fXuXl+/Zs0dlWxARERERhcu0AW+WdhQWFsrLL7+sSiFOnTrlsKxZs2YyZcoUGTx4sOrJEOrwXCKohNcbjR/RkwHlEv4OMlH4CdlAw6JFi+SOO+5QaVH4N3b8jxw5Is8884zKcMC4yl9++aXC/RyIiIiIiAJNMEwb8FZpBybMvfvuuzJhwgQ5ePCgw7K0tDQZN26c3HvvvepAYzhBUMGfQSWikA00oPHL7bffLrVr15YvvvhCEhIS1OUon5g3b54KOOByjLS8//77bcudU6w0eXl56jQxMbHC27B9+/ZKZToQEREREVV52kBOybQB+2CDNm0A6fP+mjbgjdIOXBeN2kePHi1//fWXwzJ8r3/iiSfkscceq9R3dyLyrJDMH/rwww/FaDSqGiwtiGBv4MCB6nTNmjXqtHHjxur00KFDLm9Pu7xJkyZe3GoiIiKiwFRsLpYNxzbIyv0r1SnOU2CMrtSmDaDhH3bctdGGgTJtoLzSDlyulXZUBPqtde/eXU2NsA8yoKH7//73P1WmjAwHBhmI/CskMxq0wEBSUpLL5drlmZmZ6rRDhw7qdNu2bSpA4Tx5QuvvgCYyREREROFk1YFVsnTXUkkvSFcBhih9lKTFpkn/Vv2lT+M+/t68sFBef4NAnjbgqdKOP//8U0aNGiUrVqwodRto/o4pE+jHQESBISQDDXXrltR4bdy40eXyDRs2qNOmTZuqU3woYYYuRl/iwwsRUntLlixRp1dffbWXt5yIiIgosIIM87fNl0O5h8RitUiMIUYyCjPkRP4JySoqOQLNYEPg9DcIxGkD1S3t2Ldvn4wfP16Np9eyNTRXXHGFzJgxgwcDiQJQSJZOXHvttbbSiFdffdVh2fr16+X5559X/x4wYIDtctRxwVNPPaXGYGo+/fRTVQPWsmVL2+0SERERhTpkLyCTAUGGhMgEaZ7UXBokNFCn8ZHxcjj3sFrOMgrf9TdoWTteGqbEqlOc1/obYD0EE16+pbOMvuIMeaRvK3WK8/4eaVjV0o709HR55JFHpE2bNvLee+85BBnQ7B3T5XCAkBnHRIEpJDMaOnfurJrAYMLEAw88oMbdtGvXTjWBXLdunVgsFrnnnnukb9++tusMGzZMvvzyS1m6dKm0bdtWLr74Yjl58qT6EIuNjVVRVIMhJJ8uIiIiolK2pG9R5RLIZKgVW8uhth7nTxefVsux3rl1z+UzGACjKwNx2gC2qTKlHRg7/9xzz6nv8c6j5ZGBjBGWOPjnXIZBRIElZPecZ8+eLRdccIG89tpr8vvvv8vOnTtVU5iePXvK3XffrWbp2sNc3Y8//ljmzJmjplFgKkV8fLzccMMNMmnSJBWoICIiIgoX2UXZKlsB5RIua+v1MWo51qPwHV1ZERUp7SguLpbXX39dpkyZ4pBdDA0bNlTfx4cMGcIDf0RBImQDDdC/f3/1U1F6vV6VUGhlFEREREThKik6STV+RE8Gl7X15kJJiUlR61F4jq6sDAQTMMIS2RcIjGCbUS4RqYuQhQsXyrhx42Tv3r0O10lJSVEjLB988EGVYUxEwSOkAw1EREREVDUd0jqo6RJo/Hiy4KStfAI7uDivj9Cr5ViPvNvfAI0f0c9AK58IlNGVlWVf2oHH8M0336hJEn/88YfDeggqoD8DeqclJwfHYyMiRww0EBEREVEpyGbACEtMl0DjR/RkQLkEMhkQZEBjSCzHehQY/Q2CxW+//SYjRoyQH3/8sVR28V133aWmTNSvX99v20dE1cdAAxERERG5pI2uxHQJNH5ETwaUSyCTAUEGjrb0vkAeXVlZ6Jk2ZswY+eSTT0otu/HGG2Xq1KnSunVrv2wbEXlWhNV5IC15Vfv27dXp9u3b+UwTERFRUECAAdMl0PgRPRlQLsFMBt/CCEvn/gbBkslw+PBh1cwRDdfNZrPDMkx6mzlzpnTp0sVv20cUStoHyP6mzzMa9u/fr+qwMBs3KytL1V2lpaVJx44dpUmTJr7eHCIiIiIqB4IKHGHpX4E4urI8mZmZMmvWLDXVrbCwsNQ4egQYLrnkEr9tHxEFeaBhy5YtalzNihUr5ODBg27Xa9SokVx11VWqNguBByIiIiIiCi4FBQUyd+5cmTFjhjqwaK9ly5aqRAKlEhgvT0ShyaulE2jwgk6yaPiCu4mMjJSzzz5b2rZtK6mpqVKjRg3Jzs5W0c4dO3bIn3/+KUajUXXTPe+889SHU8+ePSWUBEoqCxERERGRJ5lMJnnnnXdk4sSJqlzCXp06dWTChAnqgCL2CYgotPc3vZbRgMyEr776SpKSkmTYsGFy8803ywUXXCDR0dFur1NUVCQ///yzfPDBB7J06VLp06ePXHHFFfL55597azOJiIiIiKgacEAR391Hjx6tGj7aw4FFjKnEuMr4+Hg+z0RhwmsZDRhJgw+V++67T2JiYip9fdRxvfrqqzJ79mw5cuSIhIpAiTARERERETk3nNy0P0uyC4olKTZKOjcpv+HkDz/8ICNHjlQZzPaioqLkoYceUsGHmjWDq7cEUTBrHyD7m14LNCBQUJUAg7duJ1AEygtPRERERKT5dvsxhxGaUYayR2iiuTsCDN98843D5ei7MGTIEDVlonHjxiH/BFclOEMUDvubXiud8FRwIJSCDEREREREgRhkmLdmrxw8lS9mi1Vio/RSkGOWY9mFkplvVOtowYY9e/bIuHHjZNGiRaVu55prrpHp06fbdnRCXWWDM0ThxOfjLd05efKkGnVpMATMJhERERERhfwReewsI8iQEG2QtMQo1ZgdSc/pOcXqcixvm2yRp2dMl3nz5qmmj/a6d++uRlVeeOGFEi4qE5whCkc+mymzceNGmTx5svz1118Ol6NxTN26dVUnWtRvYc4uERERERF5H9L+cUQeO8takAFwivPF+bmy9sNXpG3r1vLyyy87BBnOPPNM1bR9zZo1YRVkcA7OtKwdLw1TYtUpzmvBGaxHFK58FmjALF2kUiGgoPn3339l0KBBcuLECRVsyMvLk8cee0yNxSQiIiIiIu9CbwGk/eOIPBq3ZRcY5VResWTm5MnO7z+S7XOGyj9fvyMF+Xm26zRp0kQWLFig+jRg0pwWnAgX5QVncDmWbz6Q5e9NJQr9QMP69eulU6dODl1n3377bTEajfLMM8+oWbu//vqraiDDrAYiIiIiIu9DA0P0FsjON8o/x3Nlf3qObPvxc/lhyi2y5eMXxZSXbVsX3+Off/55NcISDR/1+vBsemgfnHEOsuB8TKROLc/KL/bbNhL5m88aIhw/flw6duzocNl3332n5uli9A2cc8450qNHD9myZYuvNouIiIiIKGxhSgIUFJskd/cGyVy9QIrT9zmso4+KlaeefExGPvWU1KhRQ8KdFpxBTwb0srAPNuB8odEiNRN0khwX5ZH742QLCkY+CzSYzWaHmq7c3FzZtGmT9OnTR83Z1dSvX19lPxARERERkfed2vunHP74ZSk85DQOT6eXpE6Xy3nX3y0TnrqSYxvtgjOYLoHGj2iY6dxAU6+LUMs7NS4J4lQHJ1tQsPJZoAFzdH///Xfb+RUrVqjAQ9++fR3WO336tCQlJflqs4iIiIiIwhKatN83/An5eeVXpZbVOLOX1O8zRAzJ9SW6RrzqN9CteU0eXRdRAReMsMR0CTR+RF8LlEsgkwFBhkapcWo51qsOTragYOazQMPVV18tTz/9tFx//fXSu3dv9W/0Y7j22msd1tu8ebNqMENERERERJ538OBBmTBhgmroaLFYHJbVanuetLzyLklp1EYSYgxyODPf1m+AR9f/nza6EtMl0PgRzxHKJZDJgCBDdUdbVnTsaM82acw0ofAONDzxxBOyePFiWbZsmfoBTJho1aqVbR00g0RTyMGDB/tqs4iIiIiIwqKG/sjxE/LEmEmy5L23xFhc5LAsrkEb6TrwIanT9hyX/QZ2n8iVH3amqx1cTFVAI0T0KED5AI7sQ3V3roMNHi929JHtgUAMejKgXMITr315ky2QRaFNtkCmCVHYBhpq1aolW7dulSVLlkh6erpq/Ij+DPaOHTsmw4cPl1tvvdVXm0VEREREVGXBcJQfI+QfHDVFFr75khgL/n9MJTRs2kJaX3m3nK7bWSJiIm3NDe37DdSKj5LfD2Ty6LoLCCp4Y0efky0o2Pks0IAgA0olhg4d6nYdlFE4l1IQERERBYJic7FsSd8i2UXZkhSdJB3SOkiU3jNd5Sk4uauhP5pVKAdO5cumA5nSs3Vtv2U4YIz8m2++KWPHT5RTJ084LIusUUsa9LlNOl58nZzfsrb8+u8pt/0GOjVOke92HOfR9RCebEEUtIEGjLbs2bOn/PDDD766SyIiIiKPWHVglSzdtVTSC9JVwAEBhrTYNOnfqr/0aeyYoUnhEaxxV0OfkVskh7NQTlAsR7L2y0+7T0rdGjE+zXBA34WPP/5Yxo4dK7t373ZYFhmXKGf0u01a9hogmUURcji7WP45niPDLmwqSzcfdtlvwGK1yoo/j6pAiv0OL+A8AhNaHwcKvskWREEdaEhNTVWjK4mIiIiCLcgwf9t8OZR7SCxWi8QYYiSjMENO5J+QrKIstQ6DDeEXrHFVQ38qr1iOZmNH3SxmC4IRFjmQkS8nThf5rI/Bd999J6NGjXKY9gYRhihp3edGadfvNomKr6EuS4uy2mr9ayZEy8u3dHbZb2DdngweXQ/RyRZEQR9o6Natm/z555++ujsiIiKiasMOMXaOEWRIiEyQWrG1bEcVTxaclMO5h9Xy7g26B+2ReV9kHIRisMa5ht5iFUnPKVKZDga9TnQRVtHrdVKnRrQKOnh7SsDGjRtl5MiR8v333ztcjtLlel0vl3q9b5MWTRuXmY3grt8Aj66H5mQLopAINGCETvfu3eXZZ5+Vxx9/3Fd3S0RERMGyk2oqEjn4m0hBpkhsikijriKGaPEnPB4cgcfOsRZkAJzi/Oni02o51ju37rkSzLyVcRCqwRrnGvrcQrMUmy1itYoYdBFSaLZKJEoV9DpJjTd4bUrAP//8o0okUCrhDGPlB9z7pCz6xySHMwuqXOvPo+uhOdmCKCQCDTt27FDTJJ566il5//335corr5TGjRtLTEyMy/WHDBniq00jIiIif++k/r1CZNN7IrnHRMzFItjhTKgr0vk2kbZX+u31QdAEjwdH4F3Wputj1HKsF2g9CSpz397MOAjVYI3zUX69DjvuIroIEZMZO/SiAhEJMQav9DE4cuSITJ48WTV7NJvNDst69eolM2fOlPPOO09lWHx/dFO1a/15dD30JlsQhUSgAdMmtA+1LVu2qB/nP9igRVoZaCAiIgoO1d5JRZDh5zkimftErBaRyFiR4nyR00dECk6VrOOnYAN20LFzjsfj8miwuVBSYlLUeoHUk6Ay9+3tjIPqBmsClfNR/kKjWYxmiwoy4GAzlqclRovuv+fSU1MCsrKy5Omnn5YXXnhBCgoKHJZ16NBBBRguu+wy23PtyWwEHl0nooALNIwfP95lYIGIiIiCV7V3UlEugUwGBBmia4gk1MHeZ8mh4dzjJZdjecu+fimjQBYAdtARNMHjcX58+gi9Wo71vJkh4M3sBG9nHFQnWBPo7I/yHztdKPtO5onValHlEvWSoiU1PspjUwIQVHj55Zdl+vTpkpmZ6bCsefPmMmXKFBk0aJDqyeDNWn8eXSeigAo0TJw40Vd3RURERD5S7Z1U9GRAuQQyGbQgQ8kNlJxHvwYsP7RBpGl3n7+u2EFGFgB20BE0wePBEXjsHCPI0CChgVpuv9Pv6QwBb2cneDvjoKrBGk+rSLAGZQaYJoFGj+jBgPKI8o702x/l/3HnCVn19wnJzCuWU3lGyS82V3tKgMlkknfffVf1Ozt06JDDstq1a8u4cePknnvukaiost9LzEYgopAMNBAREVHoqfZOKgIJ6MmAcgnnzEecj4wrWZ7/XwmFH2g78/Y7+zgC725n35MZAr7ITvB2xkFVgjWeVpFgzbfbjzkc8Ud/hYoe8deO8uOnc+MUj2QO4Llfvny5jB49WvU6s5eYmChPPPGEPPbYY5KQkFDh22Q2AhH5CgMNREREVGXV3knFdAnsYBoLSsol7IMNOG/MF4mvKRKX6pFXqarNGbEziiyAilzXUxkCvshOwL+NFqP6t9liVjvi2AH3dMZBZYM1nlSRYI0pp53MW7NX9TAwW6xqZCWmSaCBInobQEWDBJ7IHFizZo0aVblu3TqHy5G18MADD6jgQ1paWqWeByKikA40/PTTTyo6u2vXLsnJyVF/xJzhj5vzDGAiIiIKPNVOi8cIS0yXQONH9GRw7tGg05csb1j9aQTVbc6I9fE4tGADTl0FGzyVIeDt7AT75+NU4SkpthTL0dyjklGQITWiang846AywRpPsQ/WxEfGS4wuRsxilkRDohRaClWwZsnOZVJ4OF4FGRKiDaWmMuByZCggeFDRYEFVMwe2bt0qo0aNki+//NLhcmzPbbfdJpMmTZKmTZtW+naJiEI20IAP6zvvvFMWLFhgCy5oH+Ia7TybRhIREQWHaqfFo8EjRlhiugQaP6KUAuUSyGRAkCGlacnyajaC9ERzxooGKjzVk6AqmREVve/Mwkx576/3HJ4PLMNOuNlaMiqxXnw9j2cc4Dnz5QhLLVhTaCoUo9mosjesYpUIiZBIXaR6rP8ej5DizCwxW3S2IAPgFOcxpQFlEMhQ8NaIwX///Vc1Tv/ggw9KHYS76qqrVAPIs846yyv3TUQU1IGG1157Td555x3p0qWLzJgxQ1599VVZunSp7Ny5U/bu3SsfffSRvPfee6rWDClhREREFByqnRavja7EdAk0fkRPBpRLIJMBQYZqjrb0RHPGygQqPNWToCqZERW576tbXC2f7/m81PNRP76+pOenq+vidod3Hi7n1DnHqxkH3oYgDIIqeA9Y//tPF6FTr6FWMpJdaBSd0SyxUZGuAzqROtVrAWUQnnbixAmZOnWq+p5sNJZsj+aCCy5Qoyp79OghwaoqzTWJKDT4LNCAIEN8fLx89dVXUrNmTXn//ffV5a1atVI/mPd7xRVXyE033aQ+WJs0aeKrTSMiIqJqqnZaPIIJGGGJ6RJo/IieDCiX8MBIy+o2Z6xKoMITPQmqmhlR3n0nRiW6fT7S4tIkx5ijzht0hqAOMkCcIU5yinNUUCFKF1XyePBwrSWvK8pFiqynJMmgk+w8s+uAjrGkoSN6LXgKyoefffZZ9ZObm+uwrF27duqg3NVXXx3UWb7Vaa5JRMHPZ4EGdMtFAAFBBtA+OM1ms+j1JZHNAQMGyDnnnCPPPPOMXHvttb7aNCIiIgqEtHgEFbwwwrK6zRmrGqiobvClOpkRZd33yv0rvTrOMqDYPzy0/vivbAKn2rKouMOSbNVJbkGE6sng3KMBoymxg4yGjtVVVFQk8+bNU1kM6enpDssaNWqkejAMGTJEfTeuauPSQAkyeKq5JhEFJ58FGiwWiy3IAHFxceo0MzNTatWqZbsc2Q0rVqzw1WYRERFRiKtuc8bqBCqqG3ypTmaEu/v29jjLQJJvzJeEqAT1mBAowqlOdGIRiwo4IGsjMSZWzm9olfWWOLVjjJ4MKJdAJgOCDI1S49RR+Oqk/ON78MKFC2XcuHGyb98+h2WpqakyZswYVTocExPjkcal/i6XQCaDJ5trElHw8VmgoUGDBnLkyBHbea00YvPmzXLJJZfYLv/nn3/EYODUTSIiIvKM6jZn9PeOuaenNXiqWWUwwHOVGpOqyifwuLRmkAYx2JpBYnmvtqnSIa2RQ6o/yiWqm+qP5xRlw5gkgYkS9nDQ7dFHH5Unn3xSkpKSPNq41J/QkwHPITIZ/NVck4j8z2d79J07d1YjK7VSiUsvvVRGjBghTz31lCxatEgFItAI5/fff5eLL77YV5tFREREIa66zRkDYcfck9MaPNWsMhjYv3bo14CddpPVJIYIg5pEkW/Kt712UXWj1FF27ACj8SN6MqBcoqpH3devX6++665Zs8bhcnwPvueee1R2Q7169TzeuNTf0PgRgRqUS/i6uSYRhWGg4ZprrlGTJVAWgX936NBBBg0aJB9++KG0b9/+/zfIYJBp06b5arOIiIgoDFS3BCHUdsw90awyGDi/dmh0WdZrh6BCdY+yoy/Z6NGjZdmyZaWWoen5lClTVKmwNxqXBgJMl0DjR/Rk8FVzTSIK40DD4MGD5frrr3coi1iwYIGcffbZ6oMYvRpat26tMhy6du3qq80iIiKiMFGdEoRQ3DH3dElGoPLVa3fw4EGZOHGimrSGngz2UCaMSRJoeu7NxqWBACMsUXKCxo/ebq5JRIHLp80QoqMdR1RFRkbKyJEj1Q8RERGRt1WnBCEUd8w9WZIRyLz52p06dUoFEebOnaumSthDYGHmzJnSt2/fCt2Wv/uBeAKyQtDXAtMlvNVck4gCH7suEhEREVVQuOyYh/prh8kIv+/LUv0EkOqPo/CV3fHNz8+XF198UQUSsrMdMwxQGoERlhjdrtPpKnybgdAPxBO05pmebq5JRMHD54GGjIwMef/99+W3336TkydPqsaPKJeA7du3y549e1TUVxt/SURERETkKd9uP+awA4x+ApXZATaZTPL222/LpEmTHCaqAZo7TpgwQYYNG6YydysrlPqB4Ln0ZHNNIgouPg00fPzxx3LXXXdJbm6uLR0M0yY0hw8flv79+6veDbfeeqsvN42IiIiIwiDIMG/NXpXSj/GLmIyApoXoJ4BUf3AXbMB3108++UTGjBmjxrHbw3hKTJgYPnx4mQfL0F+hvPKNUOoH4onmmkQUnHwWaFi3bp3cfPPNUqNGDXn22Wele/fupZo+IrsBH9SffvopAw1ERERE5DEol0AmA4IMCdGGUk0KcTmW4yi881H3VatWqZ5iGzZsKNV/7OGHH1bLatYse4d61YFVDsEDBBjcBQ9CsR8IEYUXnwUapk+frmrUvvvuO+ncubPLdTBXGMu2bdvmq80iIiIiojCwaX+WKpdAJoMWZACc4jyaFmI5Uv21o/CbNm2SUaNGybfffutwW/hOO3ToUDVlolGjRuXeN4IM87fNl0O5h9ToSkyVQMNH9GJAmQQ4Bxt80Q8EwRc8L9XpVUFE5NdAwy+//CLnn3++2yCDpm7duvLrr7/6arOIiIgoFJmKRA7+JlKQKRKbItKoq4jBcfoVhRfsTKMnA8olXI6OjNSp5egnsHv3bhk7dqx89NFHpW7nuuuuUwfQzjjjjArdL7IXkMmAIENCZEKpBo/oxYDlyGDwZcZCdXtVEBEFRKABnXnT0tLKXS8zM9Mn20NEREQh6u8VIpveE8k9JmIuFsHOW0Jdkc63ibS90t9bR36CI/bYmUZPBpejI40WibdkyhuzxspnH76rmj7au+iii9SECRw4qwyUP6BcApkMWpABcIrzaPiI5VjPVxNNqtOrgogooAINaPqIqRJlwYc8yiaaNWvmq80iIiKiUAsy/DxHJHOfiNUiEhkrUpwvcvqISMGpknUYbPCYijQ3DBQoC8ARe+xMoyeDfY+GoydOydHvF8nWdZ+KqbjQ4Xpnn322zJgxQy6//PJSmRAVgecGzxPKJVxmUuhj1HKs58teFQcy8sSg00lSvEEMep3US4qWjFxjmb0qqnp/LM8gCj8+CzT069dPXn31Vfnwww9l0KBBLtd588035eDBg6ppJBEREVGlyyWQyYAgQ3QNkYQ62JPDkQyR3OMll2N5y74so/CAyjQ3DATYaUZZAI7YY2caPRmixCQHf14mx9d+KKb80w7rN23aVKZMmaK+l6InQ1UhAIPnBj0ZXGZSmAvVVAms5wvY6d91Iley8Pj1OskqNAoeHbI9aiVEqQwH514VVQ0WsDyDKHz5LNCAbrwLFy6UIUOGyObNm9UYS8jLy1Pnly5dKk8//bQqr3j00Ud9tVlEREQUKtCTAeUSyGTQggyAU5xHvwYsP7RBpGl3r25KMB3pr4qqNDcMBFo5wIe/7ZPN338mf3z5thRmHndYB99F0Z/h3nvvVVMlqguvPQIweG7Qk8G5R4M+Qq+WYz1fWP3PCTlxulAFFIqsFtHrIsRosUqx2SJGs1WiDBG2XhXVCRawPIMovPks0NCwYUNZsWKF3HDDDTJ79mx55pln1IfskiVL1A8+bGvXri3Lly9Xp0RERESVgkACejKgXMI5xR3nI+NKluf/V0LhJcF2pL+yArW5YUWoDII9v8mvz46Wv5xKehMSEuTxxx9XP4mJiR67TzwHeO0RgMFzg54MKJdAJgOCDA0SGqjlvniukJnw27+ZKqAAaICp+++1w2VYXmQSqZ8cIclxUVUOFlRnlCgRhQafBRoAzXN27twpb731lhpzuW/fPrFYLCoIcckll6jIcVKSb9LGiIiIKMRgugR21owFJeUS9sEGnDfmi8TXFIlL9domBOuR/srYePQP2X1UJ7l5LSSpRqpYY05JRITFb80NK5o98tNPP6kM259//tnh8sjISLnvvvtUFoO3DnZpr7l9AArlEr4OQKH8odhsVr8aKJcwWawSqY9Qrx3294uLLSrwEK3XSfv6NeTRj/6oUrCgKqNEiSi0+DTQAIgQP/LII+qHiIiIyGMwwhLTJdD4ET0ZnHs06PQlyxt6Z+c3mI/0VxSOcL+8JkP2n+wkJotI4Um9REcVSr16+yQt7ajPmxtWJHsEjcZHjRolX3zxhcN1sa3ovzB58mRp3ry517cV24PX3p8lNeixYDJbpUZMpBSZLCrzwGQ2i04XIRZLSZZDpF4n5zZLlW2HT1c5WFCZUaJEFJp8FmhA9gKa6hAREVFgCLk+AobokhGWmC6Bxo8opUC5BDIZEGRIaVqyHOt5QSCOMfQkLY1+f7pIsTFBrBFFUmiKkaKiWDEaS943tWod8Vlzw/KyR44fOi5fz/ta3nvvPRXssYcJEpgk0aGDb/oiaPD75c/XXhvxCZgycTK3WPVmUE+PTsRoFqldI1p6tamtggBVDRZUZJRozQSdKs8gotDks0BDy5YtpW/fvnL33XfLtddeKwaDz5MpiIiIKNT7CGijKzFdAo0f0ZMB5RLIZECQwYujLQNtjKEn2dfcp8TFiM6ULvmmPNFJnljNiVJQGC9HjjYVS+w2nzQ3LCt75MjxI/Ljuz/Kwm8XisVocbjeeeedJ7NmzZKePXtKOLIf8Wm2iLSsnSB5RWYxms2SW4TsBqu0qp0gnRonq/KHqgYLyholivNoQInluB8iCk0+29tv0aKFfPvtt6o3A7r5Dh06VO68805p1aqVrzaBiIiIwqGPAIIJGGGJ6RJo/IieDCiX8FImQ6COMfQk+5p77CBGF6XJ0TyTFJmLxKLLErOxluQUREhUVpK0rFfD680NXWWPGAuNsv3T7bJtyTYx/teoUNO2bVuZPn26XHfddaWCQOHE1YhPZCYgaICd/8Y149RyrFedYEF599Mo9f/vh4hCk88CDWgCuXr1annjjTfk008/VaMsMX0CEeV77rlHrr/+eomKYvoUERGRN4VDHwEFQQUvj7AM9DGGnuRcc58cU7JziZ19o8UoBUaz6CVGGsS2ljvOvMDrgSr77BGr2Sp/f/W3bFm4RQoyCxzWq1W3lsycOlNuv/12ZtP+R5sSYT+yEpkJziMrqxssqOj9EFFo8mn9AoIK+MnKylL1cm+++ab8+OOPKgCRkpIiQ4YMUaUVZ5xxhi83i4iIKGyEeh8BfwqkMYae7s3hquYewQZcP6c4Rw4WmaR2okEe6dpXujf2/g4k7jcyIlIOrDkg6z5eJzlHcxyWG+IN0n5ge5k7bq70aNbD69sTbLCTj2kRaOSIHgsof0BmgnPQoLrBgoreDxGFHr80SkhOTpaHH35Y/fz2228qy+Gjjz6SOXPmqJ8LLrhAZTkMHDhQoqO9m+ZIREQUTkK5j0AgCJQxhp7uzeEujR4Ki6IlNlIvzVKT5NymaV5/DAh0nNh8Qn54/AdJ353usEwfrZemVzaVelfVk46NO8p5jc+TQOx3gVIUZIkggIPn1h873rjPioyWrG6woKL3Q0Shxe8dGbt27SpJSUnqjxUyHADzjX/55Rd54oknZNy4cfLQQw/5ezOJiIhCQij3EQgUgTDG0NO9OQKl5n7Dhg0ycuRIWbVqleMCnUjDPg2lwfUNJK5mXMBkj7ia3GGfHYAskWAoJWCwgIiCJtBQWFgoH3/8scpmQGABX27q1q0rw4YNkz59+qgMh/fff1+GDx8umZmZKuBARERE1RPKfQQCib/HGHqjN4c/a+7/+ecfGTNmjCxZsqTUspYXtZRWg1tJTL2YgJ6eoo0HRaAGTTXR7wKlKMgSQQAHAjnYQEQU0IGGrVu3quDCBx98INnZJWmZvXv3lvvuu091AtbGXiLYMHr0aOnWrZu8/vrrDDQQERGFUR8BCszeHL6uuT9y5IhMmjRJ3nrrLTGbzQ7L8F1x5syZ0qFzh4DLHilrPGhCtKHUBAdcjuV4btm/gIhCgc8CDSiLQIBh48aN6kO1Zs2a8uijj8q9997rdsRlkyZN5JJLLlFBCSIiIgqPPgIU2L05fJFGj8bhs2bNUr27CgocJ0l06tRJBRjwHVF7LIGUPVLeeFD7/hY4xXmUomA5AjjsZ0BEocBngQY0dwQ0ekT2wo033lihRo9nn322HDx40AdbSEREFD4CtY8AhXdvDgQVXnrpJZkxY4YqnbXXokULmTp1qmoWrtPpJJjHg5YK9ETq1HJkiRARhQKfBRoefPBBlb1w5plnVup6aAiJHyIiIgrtPgIUvr05TCaTLFiwQCZMmCCHDx92WFanTh0ZP3683HXXXRIVFRWUEyFcjQd1CPQYS/pdoBQlkLabiCjgAw1z58711V0RERERURD05sBO9rJly1Rfrr///tthWWJiojz11FPyyCOPSEJCQlBPhHA3HlTr0YDJHViOfheBtN1EREE73pKIiIi8zFQkcvA3kYJMkdgUkUZdRQzlly9SaAm03hw//vijGlX566+/OlyOrAVkwiL4UKtWrZCYCOGt8aCcZBG+mMVCYRtouOmmm2TixIlyxhlnVPk2tm/frjoNL1682KPbRkREFDb+XiGy6T2R3GMi5mIRHLFOqCvS+TaRtlf6e+soDHtz/PHHHzJq1Cj5+uuvHRdEiDTt3VQuuvMiuar7VT4LMvhqIoSnx4NykkX4YhYLhXWgYeXKlfLJJ5/INddcI0OGDJErrriiQnV1xcXF8vnnn8u7774rK1askJSUFG9tIhERUegHGX6eI5K5T8RqEYmMFSnOFzl9RKTgVMk6DDYEBWQfeCo44K/eHHv37lXjyhcuXFhqWc1zakrrW1pLZP1IORhxUOZvm68u90WWhS8nQnhyPCgnWYQnZrGQhHugAX9M0BkYnYOXL1+u6uy6desm5557rrRp00YFEHBZTk6OnDp1Snbu3CkbNmxQ6XO4DBMpHn/8cZU2V9V0vN69e5e7HjIm0GAIkIGB8+6MGDFCjVMiIiIKinIJZDIgyBBdQyShDvacUBQvknu85HIsb9mXZRQBbtWBVQ7lDggUBNMo0uPHj6vvhPPmzROjsaQMQZPUNkna39ZeWndu7dCcEn0k8JiRfeHtbAtfT4Tw1HhQTrIIP8xioWDitUBDUlKSzJ49WwUL3nrrLfXz7bffqh/nD3HAHxZo1qyZ2qEfNmyY6jJcVXXr1pXbb7/d5TKz2Szvv/+++nePHj1KLb/wwgulZcuWpS4/55xzqrw9REREPoWeDCiXQCaDFmQAnOI8+jVg+aENIk2788UJ4CADju4fyj0kFqtFYgwxakQlpkegsSMEWrBBy744cvKIfDH/C1k0b5Hk5eU5rNOibQupf2N9kXYiLZJbOGQRYCIGmlUisILb8Xb2hbcnQnhLsG43VR2zWCiYeL0ZJHb4x4wZo37++usvWbt2rWzdulVOnDgh2dnZKiBRu3Zt6dChg9rpr05PB3tt27aVd955x+Wyr776SgUaGjVqJL169Sq1HOOThg4d6pHtICIi8gsEEtCTAeUSzgF+nI+MK1me/18JBQUc7LDjqD6CDAmRCaVGUvryqH9lAiNLti+R9UvXy/aPtkvxaccsgMaNG8uUKVOkTvc6Mu/PeZJnynOdRaCPUY8fpSLe5s2JEN4UrNtNVccsFgomPp060a5dO/Xjb1o2wy233OIyu4KIiCjopz/g9rHzaSwoKZew/3uH88Z8kfiaInGp3rl/qjYczcdRfWQyaEEGfx31r4jv/v1OJr48UTa9u0kK0wsdlkXXiJY7H7lTnhv9nCqP3XBsgwqOIDvD5dF4c6GaiIF+FN7mrYkQ3has201VxywWCiZhN94SqXvoGQG33XabvzeHiIjCha+nPyCIgdtH40f0ZHDu0aDTlyxv6P8dVHINR/NxVB/lEv4+6l8WBAY+++IzFUjI2JvhsMwQY5BmVzeTulfUFV0jnUQYSh4HmlmizwRKQJCd4ZytoY/Qq+VYzxc8PRHCV4J1u6lqmMVCwSTsAg2ffvqpCjZ06tTJbXbFqlWr1OilwsJCadiwoVx++eXsz0BERME1/QGZEghi4PZxv8iiQLkEMhkQZEhpWrLcWxkVVG04mh8oR/3dWbdunYwcOVLWrFnjcHmEPkLaXNFGOt7cUWKSY2Rv9l6H7As8LjSzRJ8JlIAgOwOBEzwmBBkaJDRQy31ZEuLJiRC+FKzbTZXHLBYKJmEXaNDKJsrKZnjvvfcczmMU0w033KB6PiQkJHh9G4mIKIT4c/qDFrywz6RAuYQ3MynIYwLtqL899N3CZDAtS9Re817NpdOQTlKjfg3bZa6yL7QmlvYTNRA48edEDU9NhPC1YN1uqjxmsVCwCKtAw9GjR+X7778XvV4vgwcPLrUckyaeeeYZlcHQpEkTyczMVBH6p556Sj755BM1rWLp0qUVuq/27du7vHzPnj3SokWLaj8WIiIKEv6e/oBgAoIYuH00fkRPBpRLMJMh4AXiUf+DBw/KhAkTZMGCBWKxWByW1e1UV+oPrC9ndzy7wtkXCCagmSUyHRCEwHIETgKluSVRIGIWCwWDsAo0LFq0SAUL+vXrp6ZhOLv11lsdzsfHx8vNN98svXv3lrPOOkuWLVsm69evl27duvlwq4mIKKh5evpDVRpKYjlHWAalQDnqn5GRITNmzJCXXnpJioqKHJade+65MnX6VPk84nPZnrG90tkXCCoEQjNLomDCLBYKdGEVaKhI2YQr9erVkzvuuENlO3z99dcVCjRs3769UpkOREQUojw5/cHXDSUpIPjzqD/6Ws2ZM0dmzZolp0+fdljWunVrmT59ulx//fUqqGA4YAio7AsiIvKfsAk07NixQzZv3qx6LFx33XWVvn6rVq1s5RdEREQ+n/7gj4aSYQSZAoGcvu/ro/5Go1HeeustmTRpkhw7dqzUAZiJEyfKsGHDxGAwBFz2RSgpMpll0/4syS4oVqMNMXWATR6JKBiETaBBa/CIqHtcXFylr49+DVo5BRERkU+nP/izoWQYWHVglcPOMXbqw3XnGH0XlixZImPHjpVdu3Y5LEtKSlITJv73v/+5/S5VVvZFoAdzAs232485jK2MMnBsJREFD78EGkwmk6r1c67xs9e4cWOP3R/qAxcuXFilsgnt+loTyM6dO3tsu4iIKExUd/qDvxtKhniQYf62+XIo95BYrBaJMcSocZKY9IAyAAiXYMPKlStVIOH33393uDwmJkYefvhhtSw1NbVK2RcM5lQ+yDBvzV45eCpfzBarxEbppSDHLMeyCyUz3+gwfYCISMI90IA/YFOnTlUNFZGS5w7q/BCM8JS1a9fK/v37pUGDBtKnj+svC+np6bJ48WIZMmSIJCYm2i7Pzc2VJ554Qn799VfVQBIZEURERD6d/uDphpKk4Ag7MhkQZEiITCjVwBC9BrAcR+hD+cj7xo0bZdSoUep7mj2dTqfKIzBlomHDhm6vX16mAoM5lZNbVCjzfv5TdqcXS3y0XpomJarXAu/L9JxiFXxApkPPNmksoyCigOWzQMMXX3wh/fv3V1MfUlJSpFmzZg479L5oAokJEvigdtfs6KGHHlLRenRPRv0hgg+bNm1S2RfJyckqlbAqZRdERETVmv7gyYaSZIOdY5RLIJNBCzIATnEeDQ2xHOuF4lQElEaMGTNGPv7441LLcGBl2rRp0rZt2zJvo7xMBQZzKgfP5xu/rpa/TzSXouI4sRhOy57sSPWcJsckS1pilGQXGFU5xeYDWdKtec1K3gMRUYgFGtBMCHV/zz//vNqh1+v1PrlflGcgQOBqfKW9mjVryogRI1S2xT///CO//PKL2kYERIYOHSqPPvqoyoggIiIK2oaS5ABH4LEjjHIJLcigwXlMTcByrBdK0Nga38vefPNNdQDIXq9evWTmzJly3nnnlXs7FclUSIxKDOtgTmVoz+eeU7FSbGoqojNKsaVYjJZiMVlKMn0RbIiJ1KmeDVn5xf7eZCIi/wcaMO7x/PPPl+HDh4svRUdHy6lT5aeSIrsCf1iJiIhCsqEklYI0fxyBx84x0tLtgw04j9GMmJqA9UJBVlaWzJ49W1544QXJz893WNahQwf1Peiyyy4rFXRxpaKZClc2vzIsgzmVZf98xse0loJIgxQWRqvnx2QxSpG5SAVkakTVkEKjRWom6CQ5LnTLeYgo+Pks0ICxkp5s8EhERBRWqttQkkpBLwGkpOMIPHaOnXeW9RF6tRzrBbPCwkJ56aWXZMaMGaUOviBzE/2zBg0a5La8tDplJ/gJ1GBOIE3BsH8+m6aZJOdEoRQVxUpxcYxERYmYzGYpNhvlUHaO6HUGqZ0YLZ0aJ/tlW4mIAirQ0LdvX9VsiIiIiPzQUJJKwU4legkgzR9H4LFzjCPI2PlFkKFBQgO1PFgbQaKx9rvvvquaOR46dMhhWe3atWXcuHFyzz33SBT2ZL1UdoJATSAGcwJtCob986nXW6VevX1iNEZJQWG85OdHiTUiRgoskaKLMkvLtBoysEsjNoIkooDms0DDrFmzVJNF9EFAcyGDwS+TNYmIiMKzoSS5pO1U2u904gi7P3c6qws78cuXL5fRo0fLjh07SmWYPvnkk6r3VHWacle07KRmbM2AC+YE4hQM5+czLe2ouvzo0aZSVBwjhUaTREUVS8vaSXLvhc052pKIAp7X9vYnT55c6rLLL79cnnnmGfnkk09UsyGMSnKVpoc/VoiyExEREXkbdioxwjJQ0uirY82aNWqC1rp16xwuj4yMlAceeEBNmUhLS/Np2Yn2PAZCMCdQp2C4ej4RbEhNPSYH0vWSXyjSPLWuvHHNTZIQHeOz7SIiCrhAw8SJE20f3M727t2rftxhoIGIiIh8CTuVwTz1YOvWrSqDYcWKFaW+U2HqFg4ANW3a1G9lJ4ESzAnUkaZlPp+xemmd1kDuOLMXgwxEFDS8FmiYP3++t26aiIiIiERk3759Kgv0gw8+KHVw58orr5Tp06fL2WefHRBlJ4EQzAnkkaahWMZDROHLa4GG22+/3Vs3TURERBS0PDHtID09XfW8euWVV8RoNDoswzhx9Mbq0aOHeFugZCqEykjTYHs+iYjcMfiyZrBu3brSunXrMtfbtWuXHD16VC666CJfbRoRERFRUEw7yM3Nleeee071vMrJyXFY1q5dO5XBcM0115Q6Wu9NgZCpEEojTYPp+SQi8nugAc0f77jjDnnrrbfKXO/pp5+Wt99+W8xms682jYiIiCigpx0UFxfLvHnzZOrUqXLixAmHZY0aNZJJkybJkCFDRK/Xh112R2WE+khTIqJA4dMZk64aQ1ZlHSIiIqJgUtVpBxaLRRYtWqT6MPz7778Ot5mamqoaQD744IMSExMTdtkdVcVeCEREIRZoqIgjR46oGc9EREREoaKy0w4QgPj6669l1KhRsmXLFofbio2NlUcffVSefPJJSU5ODvgsAk9nd3gCeyEQEQVxoOHdd991OL979+5Sl2lMJpPs3LlTVq5cKd26dfPmZhEREVGICYSdZ09NO1i/fr2MHDlSVq9e7bAeyiLuvvtuGT9+vNSrVy+osgg8kd3haeyFQEQUpIGGoUOHOkTsf/75Z/XjDv7AIPUPf0CJiIiIgmXn2RPTDvTpepk2b5r8+NWPpa4/cOBA1Z+hVatWQZtFUNXsjmBRZDLLpv1Zkl1QLEmxUdK5SbJEG4KrZwYRUVAEGhAw0CLUkydPlo4dO8q1117rct2oqCipX7++XHrppVWO0hMREVF4CZSd58pOO0iNSZU8Y56YLCY5eeyk7Fm8R46vPi5Wi2Ovqr59+8qMGTOkS5cuIZFFUNnsjmDx7fZjsnjjQTmRUyTFJotEGXRSOzFaBnZpJJe2r+vvzSMiCq1Aw8SJE23/XrBggfpjOWHCBG/eJREREYWJQNp5rsy0g73Ze9W2mXJNcuyLY3Lyu5NiNToGGM455xyZOXOm+u4UalkEFcnuSIlJUesFQykNggzz1uyVg6fyxWyxSmyUXgpyzHIsu1Ay841qHQYbiCjc+KwZ5HXXXSeJiYm+ujsiIiIKcYG081wRyKz4M/1P2XVilxz76pic+OKEmPMdx3k3aNpAnpv1nAwYMEB0Ol1IZhE4Z3c4B4gwZhLLsV6gl9KgXAKZDAgyJEQbJC0xyvZY0nOK1eVY3rNNGssoiCis+CzQ8PLLL7stmyAiIiIK5p3nisgvypflHyyXze9sluLMYodl0cnR0mRAE7l4wMVyXd/rPBpk8FUWQVWyO5DZgYAQXivVpyJCLw0SGqjlVclA8HUpDXoyoFwCmQxakAFwivPZBUa1fPOBLOnWvKYECvaTIKKQCTQ0bNhQzYImIiIiCrWd57JgWz799FN5fMTjsn/PfodlkXGRctbAs+SMa8+Qg0UH5ZTxlFcyMLydRVBZ2s6+feYBXqvqZB74o5QGjR/RkwHlEi6DXZE6tTwr3zGw5E/sJ0FEIVc6gdGWOTk5LKEgIiKikNt5duWHH35Qoyp/++03h8v1kXppe01bOfumsyWmRoy6LMbkvQwMb2YRVBWCCdjp91QvBX+U0mC6BBo/oieDy2CX0SI1E3SSHBcYo1bZT4KIQi7QMGnSJPnxxx/liiuukBdffFE6derkq7smIiKiEBSIO8+azZs3y6hRo+Sbb75xuDxCFyG1L6otPe7oIYl1En2ageGNLILqwmvjqZ1+f5TSYIQlpkug8SN6Mjj3aNDj9U6Mlk6Nk8Xf2E+CiEIy0ID+DNHR0fLzzz+rEU0YYdm4cWOJiSmJ4tvDB/T333/vq00jIiKiIBVoO8979uyRcePGyaJFi0otu/qaqyXx2kQ5mnBUCiMLJcGa4PMMDE9nEYR7KU20Qa9GWGK6BBo/oicDyiWQyYAgQ6PUOLUc6/lbsPaTIKLg5LNAA7IZ7D/sjxw5on5ccY5CExEREQXczrOpSOTgbyIFmXIs1yJT3/lG5r3xpphMJofVevTooUZVXnDBBbZmhf7MwPBkFkEg8VcpjTa6EtMlsKOOngwol0AmA4IMgTLaMhj7SRBR8PJZoOHff//11V0RERFRmPH5zvPfK0Q2vSen0w/J7G/2yfOrjkpekWPT67POOktmzJihyka1HbtAy8AIJf4spUEwASMskQ2AHXX0ZEC5RCBkMgRrPwkiCm4+CzQ0adLEV3dFRERUraPTEpsi0qiriCG63KthRzEU09CpDH+vkKIfn5dXvtwi074/JRn5jgGGJvVry5SZz8jNN98ser0+rMoX/M2fgRwEFQK55CCY+kkQUfDzWaCBiIgoYP13dFpyj4mYi0Www5dQV6TzbSJtr3R7NaTB2+/QYEeRR6ZDm7koX95/YbKM/2iTHMhyLJGoFW+QsRcny33XXyTRgweKuAgyhHr5QiBgICf4+0kQUfBjoIGIiMIbggw/zxHJ3CditYhExooU54ucPiJScKpkHRfBBq3W/lDuITVOD53u0YQO9eFI3QamwYcOHPX94osvZPQTw2XbP47loPHRenmiX3N5/NJmkpi7W6QoXeTQBpGm3f22veGOgZzg7idBRMHPa4EGnU6nfv766y9p3bq1y9RBd5DG5dxIiYiIyCvlEshkQJAhuoZIQh38EcJepUju8ZLLsbxlX4cyCmQvIJMBQYaEyIRSTedQH47lSI9nOnzww8SsESNGqFN7kfoIubdXYxl7dSupk/Tf+6MoriQrJv+/IBVVGMuQfCMY+kkQUfDzWqABoyvxpSsyMlKdb9SoEadJEBFRYEFPBpRLIJNBCzIATnEe/Rqw3OnoNGrrUS6BTAYtyFBytQh1Hk3osBzrMT0+eG3btk1Gjx4tn3/+eallN3dMkCmDukjzOvH/fyECVMZ8kfiaInGpvt3YIMcyJN8K9H4SRBT8vBZo2LdvX5nniYiI/A6BBBx9RrmE82hlnI90fXQaDfxw9BXlEi7HxOlj1HKsR8F3NHz//v0yYcIEeffdd1WWir1+l10qMy4S6Rj1r0h0jog1zjELRqcv6e/RkP0XKoplSEREoYc9GoiIKHxhugR2Ro0FJTuK9kGDMo5OY0cWO7HoyeByTJy5UHW6x3oUPEfDT548KdOnT5eXX35ZiouLHZZ17dpVZs2aJb169XLs64FgFQJSeK8gyJDStKSJaAUmlhDLkIiIQhUDDUREFL4wwhJHn9H4EUejnXs0uDk6jaPl2JFF40f0ZHDu0aCP0KvlWI8C/2h4Xl6ePP/88zJ79mw5ffq0w7I2bdqo4EP//v3/P6CkNQe1n1SCgFQFJpWQI5YhERGFJp8HGv744w955ZVXZO3atXLkyBF1Wf369aVHjx5y3333SefOnX29SUREFK5w1Bk7hpguUYmj0zhijqPl2JFF40f0ZEC5BDIZEGRokNBALWcjSO+qblNOo9Eob7zxhkyePFmOHz/usKxBgwYyceJEGTp0qBgMLr4uIZiAJqHo34HSGmS9ICDFTIZKYRkSEVFo8mmgAX/Ip0yZImaz2eHynTt3qp+3335bxo4dq/6wExER+UQVj05rR8ntU/ZRLlGVlP2QneiBZpsI3qBEBdkjHt4Jr+rRcIvFIosXL1bfOfbs2eNwm8nJyTJq1Ch5+OGHJTY2tuwNwOPhCMtqYRkSEVFo8lmg4b333lMBhISEBHnwwQdl8ODB0rRpU1vTpUWLFqmaSAQiWrRoIbfddpuvNo2IiMJdFY9OI5iAo+WeakIYMtDDwD5wg+fDC2UFlT0ajkyH7777TgUSNm3a5LB+TEyMDB8+XI2xTElJ8dg2UtlYhkREFJp8Fmh44YUX1KjLH374Qc455xyHZWeddZb6ueGGG+SCCy5Q6zLQQEREPqUdndaOxP/zTYWOxCOowBGWduwbJWJsKCZ6FOeX9MFAiQp4KNhQmaPhGzZskJEjR8qqVascbiNCFyHNLmkmF91xkVx6/qUMMvgYy5CIiEKTzwINO3bskN69e5cKMtjDsj59+sjq1at9tVlEREQ+PxIfshCkwfOHIEN0jdLNNXE5liN7xANlFBU5Gm7IMMjMh2bKp598Wur6tbrWkja3tBF9Hb3sj9ivmkpC2Je9+BjLkIiIQo/PAg01atSo0FGCpKQktS4REVGoHokPWcgEQZAGz58WZACc4jz6NWA5SlQ80NugrKPhpkyTnFh+QlZ/t1osZovD9ZLbJ0v7Ie2l1dmtKtU80ltQ3hHu5TfBWoZUZDLLpv1Zkl1QLEmxUdK5SbJEG/T+3iwiovAJNPTr10++/fZbKSgocNtcCcvWrFkjl112ma82i4iIyOdH4kMWAgnIBEGQxqlngjqPiR5Yjj4YHtrpdj4anpudKweXHZRdn+8SU5HJYd3WZ7aWujfWFWtrq7RIblHh5pHeHs9p31AUjzVcG4oGWxnSt9uPyeKNB+VETpEUmywSZdBJ7cRoGdilkVzavq6/N4+IKDwCDTNnzpQff/xRrr/+epk7d660bNnSYTm6PqPDc1RUlMyaNctXm0VEROTzI/GhNv3BBrePoICxoCRIYx9swHmMDcVEDzTb9OBON5adk3qOjHt6nHz54peSk53jsLx58+YydepUqdmtpry29TXJM+VVqHmkt+HxolwD4zkxOQNNLdFvAqUgyNLQHhsFZpBh3pq9cvBUvpgtVomN0ktBjlmOZRdKZr5RrcNgAxGFM68FGoYNG1bqsg4dOsjnn38uZ5xxhnTs2FGaNGlimzrxxx9/qHFTV111lYwZM0beeustb20aERGRx4/EByRf95xAEAO3j3ITZII4Z4bo9CXLMdHDQzvdJpNJ3n33XZkwYYIcOnTIYVnt2rVl/Pjxcvfdd6sDGRuObahw80hvQ0ADQRU83oTIhFL9JfxVxkEVK5dAJgOCDAnRBklLjLK9duk5xepyLO/ZJo1lFEQUtrwWaHjnnXfcLjObzfL777+rH2cIRODDmoEGIiLymWoeiQ9I/ug5gUwJBDFw+7hfBHAQpMHzhyBDStOS5U4ZFVXZ6cayZcuWqYMTaDhtLzExUZ588kl59NFH1VjtQByliPIMZG4gqKJth7/LOKhi0JMB5RLIZNCCDIBTnM8uMKrlmw9kSbfmNfm0ElFY8lqgAWMsiYiIgkI1jsQHJH/2nNCCF/aZFAjSlJFJUdmdbkynwqjK9evXO9wOshYeeOABGT16tKSlpQX0KEWUZyDAgsyNQCjjoIpD40f0ZEC5hMvXLlKnlmflF/NpJaKw5bVAQ8+ePb1100REFMx1/IGoikfiA5a/e04gmIAgBm4f5SbIBEGQxs3zV9Gd7k2bN8mEuRPkq6++KrXObbfdJpMnT7aVZQb6KEWUZwRKGQdVDqZLoPEjejK4fO2MFqmZoJPkOJa8EFH48lkzSCIiClC+ruMPVFU4Eh+wAqHnBIIKFQxilLfTnXk0U3Z+ulOWrV6mzttDb6fp06fLWWedFVSjFAOpjIMqByMsMV0CjR/Rk8G5R4NeF6GWd2qczKeWiMIWAw1EROHMH3X8gaySR+IrqrIjG8Ot54S7ne78zHz59b1fZf83+8VqdgwwXHDBBWpKVffu3YNylGIglXFQ5UQb9GqEJaZLoPEjejKgXAKZDAgyNEqNU8uxHhFRuGKggYgoXPmzjj+QVeJIfEVUdWRjOPWccN7pPpV9So59eUz2f75fzIVmh3Xbt28vM2bMUJkMzmUWwabMMo7mV0kfc6TIX5+FZzlTgNNGV2K6BBo/oicDyiWQyYAgA0dbElG4Y6CBiChc+buOPwxUdWRjOPacwPNgLDbKtBemye/v/y5F2UUOyxs3bqx6MNx6662i14fOkWKXZRynjkjUuvksZwpwCCZghCWmS6DxI3oyoFyCmQxERAw0EBGFr0Co4w9hVRnZGK49JywWiyxatEjGjh0r+/btc1hWs2ZNNcLy/vvvl5iYGAlFDmUcKGda9zLLmYIEggocYUlEVBozGoiIwnUCRJDV8Qebyo5sDKaeE56CoAsmSIwaNUq2bt3qsCwmNkZuvvdmmTlupqSllh5VGZJYzkRERCGCgQYionCdABFkdfzBpqIjG7FeMPWc8JT169fLiBEjZM2aNQ6X6/Q6aXZpM2k9sLXk1cqTyZsn+3TspF+xnImIiEKEzwINffr0kX79+slTTz1V5nrPPPOMfPnll7Jq1SpfbRoRUXhOgAjCOv5gUt7IRkwXQOM/rBdOduzYIaNHj5Zly5aVWtbkoiZS54Y6ElMnRswGsxzNO+r9fhaBhOVMREQUInwWaPjxxx+ladOm5a63c+dOWb16tU+2iYhIwj1lOojq+IONu5GNWo8GjDDEcqwXDg4ePCgTJ06Ud955R/VksNf3kr6Sen2qnEg94Z9+FoGC5UxERBQiAq50orCwUAyGgNssIqLQTZkO8Dr+YOU8shE9GVAugUwGBBkaJDRQy0N6x1lETp06pcZRzp07V4qKHCdJnHvuuTJz5kxJbJcoz258Vix5fuxnEQiqUc6EMhyHyRVpHUL+vUVERIEroPboT58+Lb/88ovUq1fP35tCRBReKdMBWscf7LRUfxyNx44ydgZRLoFMhlDvO5Cfny9z5syRWbNmSXa2Yx+K1q1by7Rp0+SGG25QwYSV+1cGRj8LH3MZHKhCORPGqNq/xxBgCIf3GBERhWmgoXnz5g7nlyxZokooXDGZTHL8+HF1+tBDD3lzs4iIAg9TpkMWdvSQ8h8uR5uNRqO8/fbbMmnSJDl69KjDMhxIQPnEHXfcIZGRkQHdz8LbGQJlBgcuHF7hcibczvxt89UYVUw4QbAGz+Px/OPqMjwGvP9C+T1HRERhFmiwn4WNLw25ubnqxxV84ahfv75cc801KsWSiCiscAJESMMOXkin/P8XEMABhTFjxsiuXbscliUlJcnIkSPlf//7n8TFxQV8PwtvZwi4Cw7YGl+eeYf0Gbig3HImbBu2E7dj39viVMEpOZJ3RLIKs+Ro7lFZd2Sd1ImrwwwHIiIKjUCDfbMnnU4nQ4cOVUc5iIjI+dOYEyAoeH3//fcqkLBx40aHy6Ojo1VwActSU1ODop9FuUGAak6/cBcccNn4spxyJmQrIBiC7dRuJ7MwU2UzGM1GMVvNUmwpVveF2w6b6R1ERBQ+PRrmz58vLVu29NXdEREFH06AoCCzadMmFUT47rvvHC7HwQWUR6BMomHDhkHTz6JSQYAqBj1cBQeq2vgSZR32vS1wm9jOInORGHQG0Vl1otfppXZsbRV0CJvpHURBpshklk37syS7oFiSYqOkc5NkiTbo/b1ZRMERaLj99tt9dVdERMGLEyAoCOzevVvGjh0rH330Uall/fv3V40ezzjjjKDrZ+HJIEBFgwPVaXzp3NsirzhPXdcqVjFEGKTQWigG/Kc3SEpkSvhM7yAKIt9uPyaLNx6UEzlFUmyySJRBJ7UTo2Vgl0Zyafu6/t48ouCaOpGTkyN79uxRp/jD6MpFF13k8+0iIgoInABBAerYsWMyefJkeeONN1TzZns9e/ZUoyq7desWtP0sPBkEcMeTjS+de1ugzARBhgiJEKPVqE5xX8jOCOXpHUTBHGSYt2avHDyVL2aLVWKj9FKQY5Zj2YWSmW9U6zDYQMHKp4GGbdu2ySOPPKImT7gLMGjMZrPPtouIiIjcw3jK2bNny/PPP6/GVto7++yzVYChX79+pXbOg40vpl94svGlc2+LQlOhrTcDSiei9dHq9nUROr9N7yAi9+USyGRAkCEh2iBpiVG2z4L0nGJ1OZb3bJPGMgoKSj4LNKADdffu3eX06dNy4YUXqpFX//77rwwaNEj27t2r6jxxdARTJ5KTk321WURERORGYWGhvPLKKzJ9+nTJyMhwWNasWTOZMmWKDB48WPVkCAW+mH7h6caX9r0tsN37T++39WjApAkEFvw1vYOI3ENPBpRLIJNBCzIATnE+u8Colm8+kCXdmtfkU0lBx2eBhqlTp6pSCTSFRL8GNIlCoOGDDz6w1Xveeeed8tdff8n69et9tVlERERlMxWJHPxNpCBTJDalZBSp05jBUIOswnfffVcmTJggBw8edFiWlpam+jPcd999EhUVWg0FfTX9wtONL+17W/x0+CdZc3CNegyZRZlSYCrwy/QOIiobGj+iJwPKJVyWakXq1PKs/GI+lRSUfBZoWLVqlWoM5a4pJCZSLF++XJo3by7jxo2Tl156yVebRkRE5NrfK0Q2vSeSe0zEXCyCHbSEuiKdb/v/KSEhBEe+P/vsMxk9erQK/NtLSEiQJ554Qh577DFJTEyUUOWr6Reebnyp9bbAD27Hn9M7iKh8mC6Bxo/oyeCyVMtokZoJOkmOY2CQgpPPAg0nTpyQ888/33Y+MjLSlpYZExOj/o2SiV69eskXX3zBQANRsAnDo74UBkGGn+eIZO4TsVpEImNFivNFTh8RKThVsk4IBRvWrl2rRlX+8ssvDpfj7/X9998vY8aMkdq1a0s48NX0C281vvT39A4iKh9GWGK6BBo/oieDc48GvS5CLe/UmCXlFJx8FmhITU2VoqIih/Owf/9+adOmTamgBBEFkTA76kthEjjDexpBhugaIgl1kMuKw0wiucdLLsfyln2DPqD2559/yqhRo2TFihUOl+ML7y233KKmTKAfQ7jx5/QLTwj27ScKddEGvRphiekSaPyIngwol0AmA4IMjVLj1HKsRxSMfBZowJcUBBU0HTt2VBE7zOAeP368uuzkyZNqIkXjxo19tVlEVF1hdtSXwgSycxA4w3taCzIATnEemTtYfmiDSNPuEoz27dun/v6+//77pSZBXXHFFTJjxgw1UYKIiLxDG12J6RJo/IieDCiXQCYDggwcbUnBzGeBhksvvVQ1hESwoUmTJnL11VdLrVq11JES1IE2aNBAPv30UzVC66GHHvLVZhFRdYTRUV8KMwgkIDsHgTPnkY04HxlXsjz/v2BaEEFQf9q0aWqaRHGxY5Oxbt26yaxZs+Siiy7y2/YREYUTBBMwwhLTJdD4ET0ZUC7BTAYKdj4LNNx2222qdOL48eMq0BAfHy8ffvihDBw4UBYvXmxb75JLLlF1oEQUBMLgqC+FaX8OPA6UABkLSgJn9sEGnDfmi8TXFIkrKQMMBrm5ufL888/L7Nmz1RQoe2jWjBGW1157banu50RE5F0IKnCEJYUanwUaWrRoodIw7fXp00dlOKABVWZmprRu3VrOOeccX20SEVVXCB/1pTDvz4FgCR4HSoCQneOcraPTlyxvGPg18MhaeOONN2TKlCkq2G+vYcOGMmnSJBkyZIgYDD77SkBEREQhzu/fKpDZ0K9fP39vBhFVRQge9aVKCOX+HMjIQLAEjwOPD0E1BM7wnkaQIaVpyfIAztywWCyqD9LYsWNl7969DstSUlLUCMsHH3xQYmNj/baNREREFJp0EqLQVBLpn+X9oEeEs3feeUe6du2qZoZjOgaaYjmP+yIiu6O+EbqSo7xaQ7kgPOpL1ezPUauNSHITkbS2Jee1/hxYL1ghSHLhcJH6nUWSG4nEJJac4jwuD9AgCho7fvPNN9KlSxe5+eabHYIMCCpgwgQue+KJJxhkIKKAUGQyy7o9GfL1tqPqFOeJKLj5PaPBW+rWrSu33367y2Vms1l12YYePXo4LHvkkUdkzpw56ssXGlgWFhbKd999J99++60sWbJErrvuOp9sP1FQCIGjvlRF4dKfA8EENDPF40AJELJzEDgL0Pf0b7/9JiNHjpQffvjB4XK9Xi933XWXmjJRv359v20feV6xuVi2pG+R7KJsSYpOkg5pHdRoS6Jg8e32Yw5TF6IMnLpAFApCNtDQtm1blZngyldffaUCDY0aNZJevXrZLl+5cqUKMtSsWVPWrVsnrVq1Upfj31jvjjvuUKfJyck+exxEAU87qmtfp49yiVCo0yf3wqk/B4IKAR4s2blzp2qk/Mknn5RaduONN6qpT+iDRKFl1YFVsnTXUkkvSFcBBwQY0mLTpH+r/tKncR9/bx5RhYIM89bslYOn8sVssUpslF4KcsxyLLtQMvONah2OeCQKTiEbaCiLls1wyy23OHTXfu6559Qp6lm1IAOcf/75ct9998mLL74ob731ljz++ON+2GqiABZkR33JA9ifIyAcPnxYNXN8++23VbaevYsvvlhmzpypSigoNIMM87fNl0O5h8RitUiMIUYyCjPkRP4JySrKUusw2ECBDOURyGRAkCEh2iBpiVHqeznKv9JzitXlWI7Rjxz1SBR8QrZHgzt5eXmyfPly28hNTUFBgaxatUr9e8CAAaWup132+eef+2xbiYLyqG+7a0pOGWQIbezP4VeY1IQSiZYtW6qJEvZBhs6dO6tyP2TpMcgQmpC9gEwGBBkSIhOkeVJzaZDQQJ3GR8bL4dzDajnWIwpUm/ZnqXIJZDJoQQbAKc7jcizffKAkcEZEwSXsMho+/fRTFWzo1KmTtGvXziHttKioSNLS0tS4L2f44gZbt2716fYSEQUk9ufwCwTF586dq8ZFZ2U5fvlG0AElEiiV0OnC7jhCWEFPBpRLIJOhVmwthx00nD9dfFotx3rn1mUzXgpM2QXFqicDyiXsM4wB52MidWp5Vj4DZkTByBCuZRP22Qxw4MABdeoqyKCN4URvBhxFysnJkcTERB9sLRFRAGN/Dp8xmUwyf/58mThxohw5cqRU8+MJEybInXfeKZGRkV7dDjYeDAxo/IjXAuUSLnfQ9DFqOdYjClRJsVGq8SN6MqBcwv69jPOFRovUTNBJchybmxIFI58FGlq0aCF33323DB06VH0p8oejR4/K999/r7pvDx482GFZbm6uOo2Li3N7fQQbcASpIoGG9u3bu7x8z5496rkgIgoJ7M/hVfiyjUw8NHpE5p29GjVqyFNPPaWmJeHvk7ex8WDgwHQJNH5ETwaXO2jmQkmJSVHrEQWqzk2SpXZitGr8iJ4Mzj0a9LoItbxTYzZhJwpGPgs07Nu3T31Rwmitq666Su655x657LLLSkXivWnRokWqjrVfv35+C3YQEYUcb05lMBWVjNLElAs0oERviDDp/4ERlejDgJGV9qKiouShhx6S0aNHqylJvsDGg4EFIywxXQKNH08WnLSVT2AHDef1EXq1HOsRBSo0eBzYpZGaLoHGj9kFRlUugUwGBBkapcap5WwESRScfBZo2L9/v5rYgM7Yy5YtUw0ZUaaAVM9hw4a5LVnwRdkEJCQkqNP8/Hy310dvB6hI2cT27dsrlelARERO/l7hODZVHxUWY1M3b94so0aNkm+++cbhcvRdGDJkiJoy0bhxY781HnTeqdUaD3Zv0F0dZSfvw/OMEZaYLoHnHz0ZUC6BTAYEGdAYEsv5elCg00ZXYroEGj+iJwPKJZDJgCADR1sSBa8IK74p+BDuDl+e0CX7iy++EKPRqEoZkGWA0gpkO3ijidWOHTtU80cEFI4fP16qROKPP/5QDSLRDPLEiRMugwy4bkpKipw6VfW58FqgwV0ggoiI/gsy/DxHJHOfiNUiEhkrUpwvotOLpDQVuXB4yAUbUFo3btw4lX3n7JprrpHp06f7JVi94dgGeXbjs3I076iaauCcpr83e6/Ui68nj3d5nI0HfYzlLBRKoy4xXQKNH9GTAeUSzGQgCu79TZ83g8QXFAQV8IMd+nfeeUfefPNNWbFihXz55ZeqpAEZDsh0aNq0qcfu97333lOn119/vcs+DG3atJHo6GhJT09Xc8kbNGjgsHzTpk3q9Oyzz/bYNhERkZtyCWQyIMgQXUMkoQ7+eGCvViT3eMnlWN6yb0iUUSD4PWXKFJk3b55q+mive/fuMnPmTLnwwgv9tn1sPBi4+jTuozJJMF0CrxN6MqBcgpkMFGwQVOjW3DelYETkG36df1W7dm3VyArZBo8++qg6MoKGjdOmTVNjuq699lqVaVBduN2FCxe6LZuA2NhY6dOnj/r3xx9/XGr5kiVL1OnVV19d7e0hIqIyoCcDyiWQyaAFGQCnOG8xlyw/tCGon8bTp0+rvkVoEPzyyy87BBnOPPNM+fzzz2XNmjV+DTLYNx4sNBWqv6f2tMaDWM7Gg/6B5x4jLPs26atOGWQgIiIJ90AD+jbgSxYyF1544QV12QUXXCBjx45VgQZ8yeratassXbq0Wvezdu1adV/IUtCCCa489thj6hRzyHft2mW7fN26depIE8ZbItOCiIi8CI0f0ZMB5RLODYNxPjKuZHl+1cvY/KmoqEj9zUOAAZkMWv8faNKkiSxYsEAF2VFK6MuGyeU1HkTtP3oyaMEGNh4kIiKigAk04IjNJ598okon8CULO/UYF3n//ffL1q1b5aeffpLJkyfL33//LR999JHq34BghCeaQN58881l9n/o27evDB8+XDIyMqRjx45y3XXXyRVXXCEXXXSRbYY5gg1ERORFmC6BpoLGgpJyCXs4b8wvWR6XGlQvA6Yevfvuu6pUD1l8J0+etC3D9Ijnn39ejbBEw0f87Qu0xoNoMJhnzFM9GQ7nHFanOB9ojQfRvBJ9JVbuX6lOcZ6IiIhCtEcDMgTQiwFHatAHAUdCOnfuLPfdd58KALjqm3DjjTfK4sWL5bPPPqvWkSOt7OHWW28td30cZUKQ4aWXXpLvvvtOjRFDAAINupBtQUREXoYRlpgucfpISU8G5x4NaAiJ5Q3PDYqXAn/v0IMIkyT+/PNPh2Xx8fEqm+6JJ56QGjVqSCD3AgBMl0gvSFc77ykxKSrTAUEGbbm/sTkiERFRmAUacAQHKaDohXDHHXeoAEOXLl3KvV5SUpKaTFFVaPBY2SkRQ4cOVT9EROQHaPCIEZYFp0oaP6KUAuUSRrupE1geBI0gUXo3YsQIVcJnz2AwyL333quC2HXq1JFgEOiNBxFkmL9tvhrDabFaJMYQIxmFGXIi/4QaAwmBEhApr/v+pv1Zkl1QLEmxUdK5CbvvExFR8PHZeEs0tkJwASmhgXzUJlzGjRARBcWIS0yXQONHpL9jhxaZDAgyBPhoy7/++ktGjx4ty5cvL7Vs8ODBqjcDygfJM5Bh8fiPj8u2jG2SEJkgtWJrqYMbWh8JlHi0r9lenu31bMAERlz5dvsxWbzxoJzIKZJik0WiDDqpnRgtA7s0kkvb1/X35hERURBoHyD7mz7LaNi2bZuv7oqIiEIBggkYYYnpEmj8iJ4MKJcI4EyGAwcOyIQJE1QvBovF4rDssssukxkzZkinTp38tn2hClkWKOlAJoMWZACc4vzp4tNqOdbDZIZADTLMW7NXDp7KF7PFKrFReinIMcux7ELJzC/J7PREsAFBmUDNSiEiotDhs0ADvnDl5uaq0onIyEiX66BEoqCgQBISEsps2khERGECQYWm3SXQoYnw9OnT1ZhK9Aayh+lJM2fOlN69e/tt+0IddpqxA41yCedJHTgfo49Ry7FeoJZLIJMBQYaEaIOkJUbZMjLSc4rV5Vjes02aRBuq3iiUPSyIiMhXfLY3j27aKSkpsnr1arfrYBnWmTt3rq82i4iIqMowmnLatGnSvHlzee655xyCDOhNhClL69evZ5DBy3BkHkflC02FtvGbGpwvNBeq5VgvEKEnA8olkMmgBRkApziPy7F884GSXhPV6WGB8pKjeUclz5SnTrdnbFeXYzkREVHQBRqWLl0qjRo1UhMc3MGyhg0bqi9mREREgQoZeK+++qq0bNlSxo4dK6dPn7Yta9CggbzxxhuqZPD6668vdYTdY0xFIv+uFfnrs5JTnA9TSP/HBAx9hF71ZNCCDVqPBlyO5VgvEKHxI3oyoFzCZUZGpE4tz8qv2qhOZHNgYggaZaKHRfOk5mosKU7jI+PlcO5htZyjQImIKCjHW1ZkygSaRm7atMkn20RERFTZMsCPP/5YBRd2797tsCw5OVmNsHz44YdVmaBXBXGjTG9AtgLGbGK6BHaa0ZMB5RLIZECQATvVWB6ovQgwXQKNH9GTAcER+2CDysgwWqRmgk6S46LCtocFEREFF58FGrKzs9WoyvJgnczMTJ9sExERUUV99913MnLkyFLB8JiYGBk+fLgaY4nyP69DkOHnOSWjP60WkchYkeJ8kdNHSkaCQhgGG7TRlTgyj51mHJ1PiUlRmQwIMgTyaEuMsMR0CTR+RE8G5x4Nel2EWt6pcXJY9rAgIqLg47NAQ7169WTr1q3lrod1ateu7ZNtIiIiKs/GjRtVgOH77793uFyv18uwYcPUlAmUS/gEyiOQyYAgQ3QNkYQ62FPEYW+R3OMll2M5pnUE8HQOb0EwoXuD7kE3VQENHjHCEtMl0Pgxu8CoyiWQyYAgQ6PUOLW8qo0gtR4WGYUZrjMmzIUqKBOoPSyIiCj4+KxHQ58+fWTHjh3y0UcfuV1n8eLFavY4O3MTEZG/oeRv4MCBcu6555YKMgwYMEDNp3799dd9F2SAg7+VlEsgk0ELMgBOcd5iLlmOkaBhCjvUSP/v26SvOg30IIMGoyvvvai5nN0wSRqkxEpiTKQ6xXlcXp3RlsHew4KIiIKPzzIannzySVm4cKEMGTJE1q5dK/fcc4+0aNFCLduzZ4/6sobmWVFRUWpdIiLy0hFx7KwWZIrEpog06hqWR77LcvToUZk0aZK8+eabYjabHZYhEI5RlRhZ6Rd43dCTAeUSzk0mcT4yrmR5/n8lFBRUEEzACEtMl0DjR/RkQLlEdUZahkIPCyIiCj4+CzS0bdtW3n33Xbn99ttVp2782ENUHXWu8+fPVw0hiYjIw9hAsExZWVny9NNPywsvvCAFBQUOyzp27KgCDJdeeqn3pkhUBIJD2Bk0FpSUS9hvC84b80Xia4rEpfpvG6laEFTo1rymx5/FYO5hQUREwcdngQa48cYbpVOnTmrWONJQDx48qC7Xxl4+8sgj0qpVK19uEhFReGADQbcKCwvlpZdekhkzZsipU46ZAM2bN5epU6fKTTfdJDqdz6oN3UMGCqZLoPEjejI492jQ6UuWNwyRyQHMwPGoYO1hQUREwcengQbAzPFXXnnF13dLRBS+2EDQ9dNiMqlMOzRzPHTokMMyNCUeP3683H333aqkL2CgzAUjLDFdAo0fUUqBcglkMiDIkNK0ZHkolMMwA8erPSyIiIhCKtBAREQ+Vl4DQeysag0Em3YP+ZfHaiyU5W8/J2NmvyZ/7SnJrNMkJiaqPkGPPvqoJCQkSEDSRldiugReN/RkQLkEMhkQZAiF0ZbMwCEiIgpqBn8dRcrIyJCioiK36zRu3Nin20REFLLYQNBmzXuzZOSU2bJuV4bDUxQVaZAHHnxIRo8eLWlpaRLwEEzACEsEh9D4ET0ZUC4RCpkMzMAhIiIKej4NNKxcuVLVuq5fv16MRqPb9dBoC8EIIiLyADYQlK1bt8qoh++UL9dsdPp7I3Jb50SZdGMHaXptX5FgCDJoEFQIxQwUZuB4BZo/sjcDERGFXKDhiy++kP79+6tRYSkpKdKsWTOVokpERF4Wbg0E7ezbt0/GjRsnH3zwgZpuZO+qDrVl+g2t5azkApGi4yWlCMgSCIWsgGDGDByPW3VglcO0CfRp4LQJIiIKiUADZpJbLBZ5/vnn5aGHHhK9vnozoYmINJbiYinY/IeYs7NEn5QssZ06ii6QGvj5Wzg1EPxPenq6yqDDKGXnDLoLWqbIrBvbSvfW/42AtNYIuz4VAY0ZOB4PMszfNl8O5R4Si9UiMYYYySjMkBP5JySrKEutw9GWREQUtIGG7du3y/nnny/Dhw/31V0SURjI+f57yVryiZjS08VaXCwRUVFiSEuT5AE3SOLFF/t78wJHODQQxPshJ0eNUH7mmWckNzfXYVn7erEy/Yo0ufrCM1WJng3+jcALnhP0OyD/CuMMHE9D9gIyGRBkSIhMkFqxtdR7H9k9JwtOyuHcw2o5Rl5yxCUREQVloAHdu9ngkYg8HWTIePMtKcZoQrNZdLGxYjl5UkzHj0tGVsmROgYbwqOBYHFxscybN0+mTJmishnsNWrUSCY/fKvclviz6HMOl74ydmCR3YHAC54T8q8wzMDxFvRkQLkEMhm0IAPgFOdPF59Wy7EeR14SEVFQBhr69u0rGzc6NuEiIqpOuQQyGRBk0CckiL7W/x+pM588KcZDh9Ty+B49WEYRwg0EUZK3aNEi1Yfh33//dViWmpoqY8aMkQceeEBiDBEii28XyT3Ko+TBIEwycLwtuyhbZTWgXMIhi+e/YEOMPkYtx3pERERBGWiYNWuWnHvuuTJixAiZNm2aGAx+maxJRCECPRlQLoFMBi3IADjFeXN2tlpe8McfEt+1q783lzwMAaWvv/5aRo0aJVu2bHFYFhcXJ48++qg8+eSTkpSU9P8LeJQ8uIRwBo6vJEUnqZII9GTA74x9sAHnC82FkhKTotYjIiLyJJ/t7c+fP18uv/xyVTf7ySefSK9evaRhw4ai0+lKrYs/hDg6RUTkDho/oicDyiVcHamLiIlRy83/lVBQ6MCI5JEjR8rq1asdLkcA++6771Z/P+rVq1f6ijxKHnxCLAPH1zqkdVDTJdD4ET0ZnHs06CP0ajnWIyIiCspAw8SJE21/3Pbu3at+3GGggYjKg+kSaPyIngyujtRZCwslIjVV9MnJfDJDxI4dO1QpxNKlS0stu+mmm9SUiZYtW5Z9IzxKTmEE2Qz9W/VX0yXQ+BE9GVAugUwGBBkaJDRQy9kIkoiIgjqjgYjIUzDCEtMl0PgRPRmcezRE6PVqeWzHjnzSg9yhQ4dUsBp/R9CTwd4ll1wiM2bMkHPOOafiN8ij5BRGtNGVmC6Bxo/oyYByCWQyIMjA0ZZERBTUgYbbb7/dV3dFRGFAFxWlRlhiugQaP6IngyqXQCaDXi+RDRuq5VivOg0n0QsCZRrIoEBwozq3R5Vz6tQpmTlzpsydO1cKCwsdlnXp0kUFGNBomIjKhmACRlhiugQaP6InA8olmMlARETewo6MRBS0tNGVmC6Bxo/oyYByCWQyIMhQndGWGJ3pcLtRUR65XSpffn6+vPjiiyrIkJ3t2A2/VatWqqHwgAEDSvXmICL3EFTgCEsiIvIVBhqIKKhhpx8jLDFdAo0f0ZMB5RLVyTxAkCHjzbfU6ExMtUDDSfSCQJkGMii0+w1apiKRg7+JFGSKxKaINOoaEJ38jUajvP3GPJk0aaIcPZHhsAzNHSdMmCDDhg2TyMhIv20jEREREQVYoAG10x988IEsX75cdu3aJTk5OeoyZzhKtWfPHl9uGhEFMQQVPDXCEuUSyGRAkEGfkFCq9wPKNLAcwY2gLKP4e4XIpvdEco+JmItF9FEiCXVLRj9qUxl8DM8tphGNefIR+WffYYdlSXGRMuLewTJ86qtqbCURERERBT6fBRqKi4vlyiuvlFWrVrkMLoD2ZZ6IyF/QkwHlEshk0IIM2ucTzqMXBJYjg8JTwQ2fBhl+niOSuU/EahGJjBUpzhc5fUSk4FTJOj4ONuBvAkZVbtiwweHyaEOEPHxBDRnZp6bUbHhU5MAPfguEEBEREVHl6MRHnn32Wfn+++/lqquuUtkMt912m/riXlRUpEaWoaN4fHy8PPnkk6W6ihMR+QoaP6InA8olnHsA4LxqOFlcrMo0gq5cApkMCDJE1xCp1UYkuYlIWtuS87gcy7GeD2zevFkuu+wyufjiix2CDLoIkWHdG8qumb1l9tALpWZqis+3jYiIiIiCJKPho48+ktTUVFm4cKEKKOh0JTEO1Nq2adNGxo8fL71791Y/OI86XCIiX8N0CTR+RE8GZFjZBxtwXk21SE1VvSCCCnoyoFwCmQwJdRA1KbkcpziPfg1YfmiDSNPuXtsMlMWNHTtWPvzww1LLrmsfL9MGdZZ2DWv8/4U+3DYiIiIiCrJAw+7du+Wiiy5SQQbQAg1mpCfr9erfPXr0kAsvvFBeeeUVBhooqHEsYvDCCEtMl0DjR/RkcO7RgNGZWI6Gk0EFO+voyYByCedpDTgfGVeyPP+/EgoPO3bsmEyZMkVef/11MZlMDssu6tJeZvaKkPMbiEhyDZ9vG4VeY1EiIiIKk0ADgglJSUm281rAIT09XerWrWu7vEGDBvL555/7arOIPI5jEYM7mIPbwAhLTJdA40f0ZFDlEshk0OslsmFDtTzoGkFiJxCNH40FSM1wDDbgvDFfJL6mSFyqR+8W4ymfeeYZee6559TYSntnn322zJgxQy5vmyARK8eLZB/y6bZR6DUWrahic7FsSd8i2UXZkhSdJB3SOqjxj0RERBRkgQYEEA5hVNx/WrZsqU7Xr18v1113ne3yrVu3SkJCgq82i8ijQn4sYpgEc7TbcLiP1FSP3ofP4UgzdgLR+DH3+P+XT2BHHud1+pLlDc/1yN0VFhbKq6++KtOmTZOMDMdRlU2bNlXZDTfffHNJdhuOivtw2yg0G4tW1KoDq2TprqWSXpCuAg4IMKTF/l979wHeVPn9Afx0t9Ayyt7IHipDwQHIFBBFEBHFhQIiCgKibNmyRAUERGUqILJkKKAgeykgQ4YgILJXgRZKW7ru//m+/d38b9KkTduspt/P88SQ3Jvk5uY25j33vOcUkucqPidNSjdx9+YRERF5BZcFGh599FFZsWKFKv4YFBQkrVq1kvfff1/69OkjwcHBKhCBlFoUhmzdurWrNovIYby+LWIOC+bgOfBZobsECj+iJgOmS7j6s3PYmVeks+NMMwaBGBwi1R1TEpAtgIF8/rIpy7OY9o7pcPPnz5fhw4fLuXPnzJYVKlRIhg4dKt26dVP/H3D1tpGTCotaBob04p0VmnncZ4Ygw9wjc+VC9AVJ1pIl2D9YbsTdkGsx1yTyXsr3B4MNRERE2SjQ8Pzzz8u6detk/fr1KpCAjAYEGSZNmqTaXgIGZJhS8cknn7hqs4gcxqvbIubQYA6ew52flcPPvOpnmI3p7piS4IB0d3wGP//8swwaNEiOHj1qtgxZah9++KH07dtXwsLCXL5t5J2FRTMKf0P4e0KQITQgVAqG/P/3R0RshFyMvqiW1y9Rn9MoiIiIskugAcGEy5cvp2p5WadOHVm5cqXcunVLKlWqJL169ZKKFSu6arOIHMZr2yJ6kJwUzHHamVcM2HGmGYNAFFdE3QNMScjCmecdO3bIwIEDZefOnWb3o6tQ9+7dVZeJwoULp5+xka+w1Hh+pgRePuSwbSPvKyyaWTjOELTD35MeZABc4/bt+NtqOdarU5TTdIiIiLJFoMGWl156SV2IsjuvbYvoQXJKMMfpZ14xcHfAmeYjR46oDAZkMhhhW1F/YdSoUVKuXLnMZWxUezbL20feVVg0qxDMwnGGoJ21749gv2C1HOsRERFR1qT0mHQB/OBcvXp1uuuh4wTWJcqubRHRmQBp/BgUQrZvi+iJwZzYWNP+TRXMCQzMHsEczHM/s13k2OqUa9y288xrkpZkOvPqDmfPnpVOnTqprhGWQYannnpKDhw4IAsWLEg3yICMjSM3jsjlu5flbuJddX30xlF1P5aThxcW9fFNqcmg/y16ePFO1DhBMCsuMc7q90dcUpxajvWIiIgom2Q0jBgxQt544w159tm0z1IhGDFnzhwZNmyYqzaNyCG8ti2iBwZzUPgRwRvLGg3ZJpiTTltATz3zGhERIWPHjpXp06dLfHx8qoK/48ePl4YNG3rtXHm2RMzexTtRSBUZM5h+hOPM8rjz8/FTy7EeERERZfOpE9Yqlqt2Z0TZkFe2RfQgXhHMsaMtIGoVYICNmgzWpuHgzGv+4PwuO/MaHR2tCvdOnDhR7ty5Y7asatWqKvjQpk2bVEERW6xmbGjJ4hN3Wwomi9xOjJXrMdc8aq48WyJm/+Kd+JvCtBzUOEEwCzUZELTD3xOCDCVCS6jlnhTcIiIiyq48LtCAauX58+d392YQZfu2iN4qWwdz7GwLiIKInnDmFVkLM2fOlNGjR8vVq1fNlqElMaa5vf766+Lvn7H/laTK2Lh7wzRY9dE0CfZNlvibpyXq300iHhBoYEtE1xUWdTa9gKqxNgiCdlnq5kJERESuDTR07tw5VWVyy/t0iYmJcuLECdm3b5+0bdvWmZtF5HTubovo7bJVMAfBBbQDRHp51HmRO5fTbQuIrgvuPPOanJwsixcvVt0i/v33X7NlCASjAGTPnj0lJCQkS3PlVcZGdIT43L4okhiHfA3RfPwkTpIlf3Ks5P17rUj4/W49O55dp3m4jIMKi7oSggn4vEzdToLyqqBdjvz8iIiIsmOgYd68eaZ/44fZqVOn1CUtKC6G9FwiomwfzLGsxYApEncjRAKC020LqHddcOWZVwye169frwIJKOhohKBCnz59pH///pIvi8U2TXPl716ViOiLUjAxTnx8/UTzC5AISRY/SZZCySI1bl1O2X84a+6ms+RsieidEFTwlGk5RERE3sipgYbNmzebfrw2adJEWrZsKQMGDLC6bmBgoBQvXlzKlCnjzE0iInJfLYbYSJHE2JQLAg65C6bZFtCVZ1737t0rAwcOlE2bzLs9+Pn5SZcuXWT48OHqO9qhc+Vvn5OLsTfktp9IsK+vxEmi+ImPlJAAec4vTAKTz6UEaZCa76az5p5amJOIiIgoxwYajNXH0QqtQYMGdlUkJyLK1mzVYshTUuTyoZRAQ+Q5kZD8KVX602gL6Owzr5iyNmTIEFm+fHmqZS+88IKqz1C5cmWHv67KyDi/R1bcPCvXRZN48ZX84iOFxE+ek1Bp4pPLLMPDXcymeXhAYU4iIiKi7MBlxSDnzp3rqpciInIv1GTAmXjLWgwIJOQrLXLjpEjSPZFrR0UwQHVDW8CLFy/KyJEjVTthdPsxQgYaWlXWqePc1PImxetJ/aPr5FDMZYnKW1Dy+vhJDQmSQPGxmuHhDmyJSEREROTBgQbM950/f7507NjR5o/XPXv2yA8//KCqmNesWdNVm0ZElH4hR2QflKprXxAA6+NMPKZLWNZiwHSJu9dTnjskXCQwl0vbAt66dUsmTJggX3zxhcTGxpotq127tgowNGvWzO5WlVlSqq4EhhaTOrcvi0TfSd2Fw0qGh6uxJSIRERGRBwcapk6dKt9//70qMmbLfffdJ19++aXq046WakREHlPIEXUR7A0GICiB9RNiUwbNxkE7bkOBciI1OorkKeGStoAIKuB7GIEEBBuMypcvL2PGjFFTJXx9fcVl8H6xP2NvpkwzQYAG0yXckOGRFrZEJCIiIvLQQMP27dvV2bJChQrZXAfLsM7WrVtdtVlERPYVckTHiNuXUgbFkFawAZkPCEpgfZyZt3amPqy4yMP/a/eLrIl/fs1Y1oSd0DoYHYBGjBihpksYFSlSRBV57Nq1qwQEBLjnSND3ozGo48IMD3uxJSIRERGRBwYa8APXnvm+6Drx119/uWSbiMi25Ph4iT1wUJKiIsUvbz4JqVVTtZTMsYUc9SAB7k+v5aK9Z+pP/Zb5rIl0oFDhihUrVKHH48ePmy3LkyePalOJdpW5c+cWt8N7xf5EdwkUfnRBhkdmsCUiERERkYcFGoKCgiQyMjLd9W7fvq3aqRGR+9zZuFEily2XxOvXRYuPF5/AQPEvVEjytX9ewpo2zZmFHHGN2wga2NNyMb0z9ZCVrIk0bNmyRbWq/OOPP1K1Ee7Zs6eawlawoKG1pidAUMFNLSyJiIiIKJsGGqpXry47duyQmzdvSni49QriWLZt2za5//77XbVZRGQlyHBj1myJv3BBJClJfENCJDkiQhKvXpUb/wsWenWwIa1CjridkZaLts7Uw5JOWcuasOLgwYMqiPDLL7+Y3Y+6Cyiyiy4TpUuXtvv5iIiIiIgyw2VVv1599VWJjo6W9u3bywUMYKxMrejQoYPExMTIK6+84qrNIiKL6RLIZECQwS80VALLl5eAEiXUtW9oqCRcuKCWYz2vZVnI0UhvuYjl9rZc1M/UV3s25Rq308uaSE76/6wJO/z777/qe7NWrVqpggzPtn5G/lo7V+b2e05KJ51NmRpCRDbFJ8XL3it75bezv6lr3CYiIiIPzWhAsbFFixaplN5KlSpJy5YtVaVzOH36tPz666+qKnq9evWke/furtosIjJATQZMl0Amg1/BgqYWh7jG7aSoKLU89uBByV23rnfuO3sKOWa15aKDsiauXr0qH3/8sXz99deSkJBgtqx+/foy/p1npZ78KXJ2jsi/jq0BQeSNNp3bJCtOrpDrsddVgAF1OQqFFJLnKj5n6j5CREREHhRo8Pf3l3Xr1kmvXr3k22+/lZUrV5otR12GN998U6ZMmaLWJSLXF3LE+qjJgOkSepBBh9s+wcFqeZId9VayLVe0XEyv/SVeC/UcbGRNoJbNZ599pi53795NNU1t3Lhx8kwFH/HZ9YVTakAQeWuQYe6RuXIh+oIka8kS7B8sN+JuyLWYaxJ5L+U7j8EGIiIi+7h0RJ8rVy6ZNWuWjB49WmU2nD9/Xt1fqlQpadSokRQrVsyVm0PklbJSyBFBCayPmgzoWmAMNuC2FhcnPuHh4pcvn3g1Z7dczGTWxL179+Srr75SWQwRERFmy1B7YdSoUWqamp+W6JQaEDkCppZgagsCTE5oN0qeCdkLyGRAkCE0IFQKhqRkdOF7LyI2Qi5GX1TL65eor7IciIiIKG1uSR1AQKFjx47ueGkir5bVQo7IfEBQAusnRUSYpk/gxzZu+/j5qeUhNWuK13Nmy8UMZk0kJSXJ999/L8OGDZP//vvP7KkKFCigWli+8847EhwcnHLnmV2O6ZyR0xxf47R2o+TZDl0/pKZLIJNBDzIArnH7dvxttRzr1SmahWlTREREOYTb5iicPHlSnZHDj2TUbCAixxZytAwS6IUcczdoYHMaBe5H5gOCElgfNRnUdAlkMvj5SUDJkmq5PdMwvGJKiTNbLtqRNYHPbu3ataqTxOHDh1NliPXt21c+/PBDyZs3r/M6Z+SkIIOT2o2S54u6F6WyGjBdwtq0sWC/YLUc6xEREZGHBRqQ9ov2at98843cunVL3depUyeZM2eO+veCBQvk888/V7dr5oQzpkQeWMhRz3gwm34RHm739AtvnFLijqyJ3bt3y4ABA2T79u1mD0ENm27dusnQoUOlaNGiTqkBkeOmRGAZAj6capJj5Q3Kq6ZEoCaDtWljcUlxkj84v1qPiIiIPCjQgI4STZo0kT179kiRIkWkVatWsmbNGrN1sByBhyVLljDQQJRBjizkiIE3Mh8QlMD6qMmA6RLZNZMhq1NKnMoia+LYsWMyePBgWbVqVapVX3rpJVXjpkKFCu7vnOFNUyLSazfKqSZer0ahGqq7BAo/oiaDZY0GPx8/tRzrERERkQcFGj755BP5448/pEuXLjJ16lQ1l9jX19dsneLFi0u1atXkt99+k7Fjx7pq04i8gqMLOSKo4A0tLB0xpcQVUBx3+PDhqitPcnKy2bLmzZurThK1a9f2nM4Z3jQlIjmJU01yOGQzoIUlukug8CNqMmC6BDIZEGQoEVpCLWchSCIiIg8LNCxevFhVRZ8xY0aa7SsrV64sO3fudNVmEXkNFnJ07pQSZ7lx44YKIkybNk1NLzOqU6eOjB8/XmV7eVznjOzA3ikRdbtxqgmZWleiuwQKP6ImA6ZLIJMBQQa2tiQiIvLAQMOZM2fk6aefTjPIAIGBgab6DURkP28v5OgJU0oc6e7duzJlyhSZMGGC3L5922wZCuQiq6tdu3apttljOmdkB/ZOiVC3OdWEUoINaGGJ7hIo/IiaDJguwUwGIiIiDw00hISE2BVAQEAif/78LtkmIm/jrYUcPWlKSVYlJCTI7NmzVWHcK1eupJo+NmLECHnzzTfTDcrazZmdMzydvd037t2xb6oJnNluvaAkeQ0EFdjCkoiIKJsEGtBFYt++fXL9+nUpVKiQzSDDgQMH1HxkIsocbyvk6C1TSlB3YdmyZfLRRx+p9r5G+fLlk4EDB8p7772n2laSg2Sk+4YejLE11QSWdLJdUJKIiIiIXB9oeOutt2TLli3SsWNH+eGHH6RgwYJmyyMjI6Vz587qbB9atxFR5nlLIUdvmVKCArcIJPz5559m96Mobq9evdQyZnI5QUa7b9iaanLqt/QLSjLYQEREROT6QAMCDD/99JMKMpQrV04ef/xxdT8KP7Zp00a2bt2q5im//vrr8swzz7hqs4goB3DXlBIEFhBEQKDBCB13EFhFl4mSJUs65bUpk903LKea2FtQEgEKTqMgIiIicm2gARYuXCi1atWSiRMnyvr169V9SCHGJW/evDJmzBj1o5yIKDtPKcF3GqZILFmyJNUyFHjEd12VKlUc/rrkhO4b9haURBZETq2FQUREROTOQAPmRffr10/69u0r+/fvl//++0/NW8YZPbRxQ8cJIqLsOqXk8uXLMmrUKJk1a5YkJiaaLWvUqJFqVfnII4847fXJCd037C0oieclIiIiItcHGnR+fn4qsICLs6H4JNrHYdrGuXPnVPeLsmXLStOmTVVmhW7evHmq0rstL774opr2QURkKSoqSj755BOZPHmyxMTEmC2rUaOGCjC0aNEia60qcypMXUBWQVY7PWS2+0ZGCkoSERERkfsCDfHx8aq7xKVLl0wt3dCVIigoyOHzo/Hj/saNG1K9enVVCwJ1II4dOyaTJk0yCzQYBwXYFks8C0lEluLi4mT69OkyduxYuXnT/Iz2fffdJx9//LG89NJLqiYDZcLxNeZTHtzR6SGjBSWJiIiIyLWBhujoaBk2bJjqIY9/G4WGhqriaEg7DgsLc0gmQ8uWLSU2NlZWrVolzz77rNnyPXv2WH1c27ZtVR97IiJbkpKS5LvvvlPFHM+fP2+2rHDhwjJ06FDVPYfTwbIYZPCETg+ZKShJRERElMP5uzK1GHOU//rrL1PmAKYwwNmzZ+XgwYPyxRdfyKZNm2Tbtm2qOGRWYAAQERGhzjZaBhmgLlv/EVEGaZomq1evlsGDB6vMKMtgKWrQvP/++w4JluZontbpIasFJYmIiIhyGJcFGpDJcOjQIWnSpIlMnTpVqlatarb8+PHj8t5776lAA9adMmVKpl8LWQwLFiyQ3Llzp1l3gYhykCzO9d++fbvqirNr1y6z+wMCAuTdd99VwQdkM5ADeGKnh6wUlCQiIiLKYVwWaFi+fLkULVpUnQ3MlStXquVo9YZl5cuXV+tmJdCwb98+uXPnjtSvX18Vf1y3bp1s2LBBzaeuVKmSdOjQQdWFsFXXAWclUcsB24vASMOGDTO9LUSUvef6Hz58WAYNGiRr1qwxux+FHV999VU13UvPziIH8dROD5ktKElERESUw7gs0ICCjKh/YC3IoENQ4IknnlABh6zQU5pxdhGviRoNRjjziDoRHTt2TPXYn3/+WV10GEQg0LB48WIpUqRIlraLiLLPXH+030V2FbKjMGXC6Omnn1YFIB988EFXvYuchZ0eiIiIiLI1l5VCL1eunNy6dcuuWg6o1p4V+usgYPHLL7+oOg3Xrl1TA4cPP/xQTa3o1KmTqguhK1asmCoCiW4Y2IYrV66oxyPTYuvWrfLMM8+oAnD2QpcLa5fTp09n6b0RURbm+hesLJKvjEihKim39bn+WM9QSLZPnz5SuXJlmT9/vlmQ4bHHHlM1ZBCMZJDBBZ0efHxTajLonwE7PRARERFlCy4LNKAC+5YtW8wG95awDDUaunbtmqXXSk5OVteJiYkqIwHzpwsVKiRlypRRLS1feOEFSUhIMGtviTaYKCCJ1pZ58uRR2QutW7eWvXv3qukWmI6xZMmSLG0XEXnYXP/kJNNcf0y3GjlypAqKYuoW2vDqqlWrJitXrpSdO3dKgwYN+DG6qtMDOjrcuy1y/bjIrbMp17jNTg9EREREHs1lUyd69+4tp06dksaNG6uijy+++KIa+OtdJzCIR5HIt99+W1VtzwpUf9dZKwaJ+5YuXaoyFex5rl69eknPnj3l119/tTrdwpqjR49avR9ZDUTkOXP94+/Fydczv5PRM1eqbAajUqVKqeDD66+/Ln5+fvzYXImdHoiIiIiyLZcFGvQf6UhDHjNmjLpYwjJMc8DFsugashPspQcwUA8CmQyW9MJtmE5hj4oVK6rry5cv270NROTZc/2Tk5Jl0Z6rMvS3O3Im4g+zh4WHh6taLj169JDg4GA3bDgp7PTg8u4qRERERNkq0IAzgwgYuEKtWrXUNWox3Lt3T4KCzH9k3bx5M1Xmgz01H9Auk4iy4Vx/FH7EXP/QIoLZ/r/8dU0GLT0qhy7GpipIi4yq/v37S968ed222WTATg8u6a5CRERElC0DDSjE6CqlS5eWGjVqyKFDh9T0iObNm5st16dM6AGJ9KDdJtSuXdsJW0tETp/rj+4St/6TP05clgG/RMrW0zGpMq7eeust1WUChWGJckp3FSIiIqJsXQzS1XBGEtBlwjjlAQUnP/vsM/Xv7t27m+4fN26cREREmD0HCkZifjbqOeBMp7V6D0Tk4ao8LceLtZN2i2Pk0emXUgUZOnToIH///bfMmDGDQQbKMd1ViIiIiLwiowHTD/Lnz2/Xuujw8PDDD2fp9V5++WVZv369fPvtt6pi/OOPP66mUuzatUtNp8DZS3Sf0GE+NoIKeF1M87h9+7YKSly6dEnN0V6wYIGUKFEiS9tERK514cIF1bZ27ty5pm40umZNm8j4CZ/IQw89xI+FvLu7Cuo1/K+7ipSt7+6tJSIiohzAZRkNDzzwgGpdmRa9UGS9evUc8poYXHzzzTdSvnx51Vpzz549avrDvHnz1P1GSJl+4okn5Pz587Jq1Sq1rSgmiS4YCDi0a9fOIdtERM6HOizIakIh19mzZ5sFGRBY2LBhg2z4bSODDJRjuquo5TH/m0JBRERE5GQ+Gkb3LoA50CgG2adPHzVNISAgwGw5Wly+9tprsmPHDilYsKDdHSGyG729pa32l0SUeTExMfLFF1/IhAkTJDIy0mxZhQoVVCCzffv24uvrtbPGKCc6s11kw1CRqAsp0yaMwQb8L/76cZF8pUSaf8yMBiIiIi9X3UPGmy77tY2MgpIlS8qkSZOkTp06Zm8c0xJq1qypggwo3PjXX3+5arOIyAug/S2ylJDBMGjQILMgQ9GiRVX9hWPHjql6DAwykNd2V/HxTemuop8/wDVu+/qlLC9Zx91bSkRERDmEy2o0NGjQQAUQ3nnnHVm0aJEKNowaNUr+/PNPWbx4saqDMGXKFHnvvfdctUlElM0hIevHH39UNVb++ecfs2V58uSRAQMGSO/evdmalnJUdxU1lQLTJRJiUoIM+cumLMd6RERERN40dcLo+++/Vx0f7t69a2ozOX/+fKlatap4O09JZSHKLpLj4yX2wEFJiooUv7z5JKRWTfENDJTNmzfLwIEDVe0Vo6CgIOnZs6fKbChQoIDbtpvILS0u0V0ChR9Rk8EvMCWTAUEGZ7a2RDcLFKREgCMkf0qGBYMaREREOXq86bKMBmOK86FDh9Rcaj3GER8fn6oiPBHRnY0bJXLZckm8fl20+HjxCQyU4z4in545I5v+/NNsB2FKRKdOnVSXidKlS3PnUc6DYEKFZindJVD4MVd4ynQJZw763RXcICIiIo/m0kADUpvRdvLAgQOqVeT06dPlhx9+ME2lGDt2rCoWSUSEIMONWbMl/sIFkaQkOa9pMvnkSfn5RkSqndOmTRtV6FGP4BLlWAgquKqFJYIMO6ekTNdAa010vYiPEbl9KWUaBzDYQERElCO5rBjkV199pVpL7t+/X1V9R72G1q1by8KFC9UF6c4ffPCBtGjRQi5fvuyqzSIiD50ugUwGBBluBgTIxzduSMs/fk8VZGhQv77s3LlTVq5cySADkSthugQyGRBkCMqT0u0iXxmRQlVSbuN+LMd6RERElOO4LNDw7rvvqhaX8+bNU8Uf8+XLZ1rWsWNHOXz4sDzxxBOqv/2DDz7oqs0iIg+Emgy3Ll2SyWfOSNPt22T+Pyck0VBOplKuXDLr8Xqy9tNP5fHHH3frthLlSKjJgOkSyGQILfL/LTVxjdvJSSnLMY2DiIiIchyXTZ3AYAAFH++77z6ry9H6ctOmTTJx4kQZNmyYqzaLiDzMvXv3ZOrcOTLxl3VyMz7ebFmJ3Lnlg5o15amAQAkMC5PkqCi3bSdRjobCj6jJgOkSepBBh9voeoHlqBVBREREOY7LAg3btm1Lt3+9j4+P9O/fX02fIKKcJSkpSU2jQqDx7NmzZsvC0UnigQfllUqVJNDXV+JPnxafAgXEz5AZRUQuhO4SKPyYEIs+s+bBBtxGa83cBVIKUhIREVGO47JAg2WQAWctb968qWozhIeb/xCpUaOGqzaLiNwM3WfWrFmj2lEeOXLEbFkuX1/pcl856fbwwxIWGKjWTYqIEB8/P/EvVEhCatZ023aTAdsb5jxoYYnuEij8GH31/6dPIMiA275+KcvR9SIHi0+Kl0PXD0nUvSjJG5RXahSqIYEI0BAREXk5l7e3/Oabb2TGjBmqJgMGDWhHN2fOHLXsxx9/lAULFsgnn3wiFSpUcPWmkaEQH+bIJ0VFil/efBJSq6b4BvKHkT247zJm165dMmDAANmxY4fZ/QEBAfJmq1bS1cdH8kXcEO3cOYkPDhYtLk4FGQJKlpR87Z/ncekJXN3ekEENz+lugc8Y3SVQ+BFTKTBdApkMCDLkL5uy3JmtNT3cpnObZMXJFXI99roKOCDAUCikkDxX8TlpUrqJuzePiIjIOwINSItGt4nVq1erQUTVqlXl6NGjqTIZsM5DDz0kQ4YMcdWmkUVLQVT7T7x+XbT4ePEJDFRnjjGoC2vaNEftq4wGDbjv7Ie//cGDB6vvA0togTt69GgpV65c6n0aHp5jj0eP5Or2hq4OalDa9H1u/EwwXYKfiQoyzD0yVy5EX5BkLVmC/YPlRtwNuRZzTSLvRardxmADERF5M5cFGqZNmyarVq2SVq1ayezZs6VIkSKpplOUL19eZTKsW7eOgQY3wKDuxqzZqqWgJCWJb0iIJEdESOLVq3IjMuWHUU4Z3GU0aMB9Z59z587J8OHD5dtvv1UZTUYtW7aUcePGSU3DdAjs69wNGkjswYOSFBmpajJgugQzbDywvaFl6rze3rBCM8ec1XZ1UIPsg32OzxjdJVD4ETUZMF0iB2cyIHsBmQwIMoQGhErBkIKqBhW+8yJiI+Ri9EW1vH6J+pxGQUREXstlgQa0tURwAa0tc+fObXO9atWqyZ9//umqzSLD2XsMrBFk8AsNFb+C///DCHPiEy5cUMsx6PP2QV5Ggwbcd+m7ceOGjB07VqZPn67qsxg98sgjMn78eGnUqJHVx+J4y123bhY/VXJ5e0Ok0uvtDcvWz15BDcoY7POsfsZeBDUZMF0CmQx6kAFwjdu342+r5VivTtGcXcOCiIi8V9ptIBzoxIkTakCRVpABsPz69euu2iz6H0wRwNl7DKz1IAPgGre1pCS1HGeWvZll0CCwfHkJKFFCXfuGhpoCLlhPx31n2927d2XMmDFqGsTnn39uFmSoXLmyLF++XHbv3m0zyEAezJXtDdMLaiQn/X9Qg8jNUPgRWQ2YLqH/v1SH28F+wWo51iMiIvJWLgs0oC5DXFycXanVYWFhLtkm+n+oQ4ApAjh7b+2HkQ8K8cXHq/R1b5aZoAH3XWoJCQmq6CumQn300Udy+/Zt07ISJUrIrFmzVIeJdu3apTreKJu2NzTS2xtiuSPaG7oyqEGURegugcKPcYlxqaaI4XZcUpxajvWIiIi8lcsCDdWrV1dTIu7cuWNznWvXrsnBgwfN5miTa6DYIeoQJMfGWv1hpKr9BwaqOfLeLDNBA+67/5ecnKymR2EK1LvvvitXrlwxLcufP7/qKHPy5Enp0qWL+Pu7vOkNOaO9oY9vyvQF/XvDGe0NXRnUIMoitLBEdwk/Hz9Vk0H/f6peowH3YznWIyIi8lYuCzS89tprap529+7dJd6Qdm7sStGjRw+JiYlRLS/JtdBRAcUO0ToQNRmMP4xwG/djOQrxebPMBA2471Js2LBB6tSpIy+99JKcOnXKtH+Cg4Nl4MCBcvr0aenXr5+EhIS47PMkF7Q3RBvDe7dFrh8XuXU25Rq3Hdne0JVBDaIsQrYCWliWCC0hdxPuyr9R/8rFOxfVNW7jfizHekRERN7KZacUu3XrJkuXLpVFixbJrl27pEWLFur+Q4cOSe/eveXnn3+WM2fOSPPmzeWVV15x1WaRoeAeOiqg2CHqECRFRaWcvcfA2s9PAkqWVMu9vRCkHjRA4UcEWCyLYloLuOT0fbd3714ZNGiQbNy40ex+Pz8/6dy5s+oygekS5IVc1d5QD2qguwQKP2IqBaZLIJMBQQZHBjWIHEBvXYnuEij8iJoM+YPzq0wGBBnY2pKIiLydj2Z52taJUKPhgw8+UPOzMYfb2qBkypQp6gyot8IUEjh69Kh4Q1tHb+46gaABajJYBg0KdO1is8VlTtp3//zzj2pDu2zZslTL2rdvLx9//LEq+Eg5ALpCuKK9IVpcGoMaOCPs6KAGkQMhwIDuEij8iJoMmC7BTAYiIsoJ402XBhp06CqxZcsW+e+//9Sc7pIlS0rjxo2lePHi4u085YNPCzoqoNgh6hBgigDO3nvr2XhbMhs0yAn77tKlSzJy5EiZPXu2mvJkhL9jtKqsy3aUlN2DGkRERETZUPWcHGjIyTzlg6f05YSgQUZERkbKhAkTVNZRbGys2bJatWqpAMOTTz7JLhJERERERDl8vMmy70Q2IKiQm2fmVVBh2rRpMm7cOLl165bZPipfvryaItGhQwfx9XVZbVkiIiIiIvJgDDQQkVWJiYny7bffyogRI+TChQtmywoXLizDhg2Tt956SwJzcJYHERERERGlxkADEZnBbKqVK1eqQo9///232bKwsDDp37+/9OnTR0JDQ7nniIiIiIgoFQYaiMhk27ZtMmDAAPn999/N9gqyFnr06CGDBw+WggULco9R1gs6nt+T0qYyJL9Iqbos6EhERETkRRhoICL566+/ZNCgQbJ27VqzveHj4yOvv/666jJRpkyZnLunODB2HLaoJCIiIvJ6DDQQ5WBnzpxRtRYWLlyopkwYtW7dWsaOHSv333+/5GgcGDt2X+6cInLrPxEtWSQgRCQ+RuT2JZHYmynrVHnagS9IRERERO7AQANRDnTt2jXVLeKrr76ShIQEs2X16tVTrSrr16/vtu3zGBwYOzYrZP/8lCBDUB6R0CJImUFREJHoqyn3Y3mFZpxGQURERJTN+bujkv2aNWtkz549EhERIY888oh07txZLbt06ZK6r1q1auLvzxgIkaPduXNHPvvsM3WJjo5O1XMXLSyfeeYZNWUix+PA2LFQkyH6Skomgx5kAFzjNuo1YPmFvSJlGeQiIiIiys5cOprfsWOHvPrqq3L+/HmVpo3BDM6m6oGG3bt3S4cOHWTp0qXSrl07V24akVe7d++efPPNNzJ69Gi5fv262bLSpUvLqFGj1N+mn5+f27bR43Bg7FgIJCTFp0yXsAxk4XZArpTlMf+bQkFERERE2Zavq17o2LFj0rJlS7l8+bK89957smTJEqtzwnPlyiXLly931WYRebXk5GRZsGCBVKlSRXr16mUWZAgPD1eZDSdOnJBOnToxyGCJA2PHQncJv0CRhNiU6RJGuJ0Qk7I8V7iDX5iIiIiIvDajAWdS4+LiVFX75s2bW10HLfRq164tBw4ccNVmEXklBPHWrVunOkmgo4QRgnl9+/aVDz/8UPLmzeu2bcx2A2PjWXh9YJy7AAfG9kILy9CiKYUfUZPBskaDr1/K8pJ1nPN5EhEREZH3BRo2b94sdevWtRlk0JUoUUIOHTrkqs0i8jq///67DBgwQLZt22Z2P+qedOvWTYYOHSpFixZ12/ZlGxwYO5Z/kEjt11K6S6DwIzJGMF0CARsEGfKXTVmO9YiIiIgoW3NZoCEyMlJKlSqV7np3795NVQWfiNL3999/y+DBg2XlypWplr344ouqy0SFChW4K+3FgbHj6a0r0V0ChR9RkwFZIchkQJCBrS2JiIiIvILLAg2FCxeWU6dO2TVYsicgQUQpUFx1xIgRMm/ePFWTwQgZRGPHjpWHHnqIuyszODB2zj5FC0t0l0DhR9RkwHQJZjIQEREReQ2XBRqaNGki8+fPV1MoGjdubHWdFStWqGBEjx49XLVZRA6THB8vsQcOSlJUpPjlzSchtWqKb2Cg0/bwjRs3ZPz48TJ16lTVVcLo4YcflgkTJqi/O8oiDowdD0EFtrAkIiIi8louCzQMHDhQFi9eLG3btlWDo+eee8607NatWyrIgOJ0uXPnVoXqiLKTOxs3SuSy5ZJ4/bpo8fHiExgo/oUKSb72z0tY06YOfS1ML5oyZYp88sknEhUVZbasUqVKaopE+/btVftYchAOjIk8wr3EJNl/NlKiYuMlb0ig1C6TT4L82ZaXiIjI0/holj0mnQhzx1977TWJiYmxujw4OFgWLVokzz77rHir6tWrq+ujR4+6e1PIgUGGG7NmS/yFCyJJSeIbEiLJsbHi4+cnASVLSoGuXRwSbEDtktmzZ8vIkSPlypUrZsuKFSumpk+8+eabEhAQkOXXIiLyNOuPXpEl+87LtTv3JD4xWQL9faVwWJB0eLiUNK/OArdERESeNN50WUYDIJvhyJEjMmnSJNmwYYP8999/ak55yZIl5cknn5QPPvhAypcv78pNIsrydAlkMiDI4BcaKn4FC6pMAsTvkiIiJOHCBbU8d4MGmZ5GgedaunSpfPTRR3Ly5EmzZWhPiWyhXr16qbaVRETeGmT4etu/cv5mjCQlaxIS6Cexd5LkSlSc3IpJKSDNYAMREZHncFqgAa310EIPqdxGZcqUkcmTJzvrZYlcCjUZMF0CmQx6kAFwjdtJUVFqeezBg5K7bt0MP//GjRtVIGHfvn1m9wcFBangApaFh4c77P0Q5XiJ90TO70lpvxmSP6XNKQtVun26BDIZEGQIDfKXQmGBpoDu9Tvx6n4sb1i5EKdREBEReXugoVGjRvLGG2/InDlz1G0UpWvZsqX079/fWS9J5PKCj4k3IlRNBkyXsKyJgNs+wcFqeVJkZIZeZ//+/SqIgMwfI19fX/V3hWkS7M5C5GDH15i33vQLZOtND4CaDJgugUwGPcgAuMbtqNgEtfzAuUh5tFwBd28uEREROTPQgB8AxlZ7W7ZskbJly3Knk1cVfBR/f0mOi1M1GXB2zRhswG0tLk58wsPFL18+u14DXVcwRQKFUy2hgOqYMWOkatWqDn1fRPS/IMPOKSK3/hPRkkUCQkTiY0RuXxKJvWne7pRcCoUfUZMB0yWsBXSDA3zV8siYeH4yRERE3h5oQDq35XxyIq8q+BgRgRQDFXQA1GSwrNGAgpDoPhFSs2aaz4/ijqNGjZKZM2dKYmKi2bKGDRuqTi2PPvqoU99jTuTqlqTkwdMlkMmAIENQHpHQIhjBIlooEn015X4sr9CM0yjcAN0lUPgRNRmsBXTjEpKlQKiv5MvFv10iIiKvDzTUr19fVq9eLY0bN5b77rtP3bdjxw7p3Llzuo/FjwhU1yfKDgUfE2/cUOsl3bmjajKo6RLIZPhf1wm0uLQ1eEV7yokTJ6oCqZbdWGrUqCHjxo1TU47YqjJ7tyQlD4eaDJgugUwGPcgAuMZt1GvA8gt7RcrWd/fW5jhoYYnuEij8iJoMljUa/Hx91PJape3LHCMiIqJsHGj47LPPVFeJrVu3qoueFo5LehhooOxW8NE3NFT8C4SLlpCYMmgND09z0BoXFydffvmlmgpx8+b/0rL/B4G50aNHS8eOHVVNBnJdhkri1aty43/1NBhsyEEQSEBNBkyXsEjNV7cDcqUsjzH/WyXXCPL3Uy0s0V0ChR9RkwHTJZDJgCBDqfBcajnWIyIiIi8PNJQrV04VtEOw4fz586o4JM7MDhgwwFkvSeQUSKtPr+Cjb3Cw5H/1NfEvVFAVfkRNBkyXsMxkSEpKku+++06GDx+u/i6MChUqJEOHDpW3335bApm+n61bklI2g+4SKPyYEJsyXcL4d47bCTEiuQuI5GKHF3fRW1eiuwQKP6ImA6ZLIJMBQQa2tiQiIsohgQbAj3ecndWnTqDdJeabE2UnmLuPtHqc8U6r4COCDLZaWGI9TCUaPHiwHDt2zGxZaGiofPjhh9K3b18JCwtz+vvJ6ZzdkpSyIbSwDC2aUvgRNRksazT4+qUsL1nH3VuaoyGYgBaW6C6Bwo+oyYDpEsxkICIiymGBBiNjBwqi7AQFAjENAmn1mSn4uH37dtWqcteuXWb3BwQEyDvvvCNDhgyRwoULu+jdkD0ZKplpSUrZmH+QSO3XUrpLoPAjplJgugQyGRBkyF82ZTnWI7dCUIEtLImIiDyfywINRNkV0udRawFz95FWb2/Bx8OHD8ugQYNkzZo1qQazr7zyiuoyoWf7kOdlqNjbkpS8hN66Et0lUPgRNRkwXQKZDAgysLUlERERkfsDDRhE4Qd8jx49VKtL3LYXHoe56kSeQi8MaNalwEbBR9QlGTZsmCxYsEANXI1atWolY8eOVR0lKHtmqJAXQzABLSzRXQKFH1GTAdMlmMlARERElCE+muVIyEFQLR8/3v/++2+pVKmS6bY9L4f1UDTPG1WvXl1dHz161N2bQpksJIi5+9YKPkZERKguEugmER8fb/a4Rx99VCZMmCBPPPEE97sHdZ1AhoqWlJQqQ6VA1y7sOkFERERE2U51DxlvOi2jYe7cueq6WLFiZreJsjMEFSwLBEZHR8ukSZNk4sSJcufOHbNlVatWVRkMbdq0SVUPgLJHhgoREREREXlIRgN5doSJsg5ZC998842MHj1arl27ZrasZMmSMnLkSHn99dfF398/dVbEgYOqKCHqBSCVn20UPS9DhYiIiIgou6nuIeNNjysGOWfOHLlw4YKa407kidBBZfHixfLRRx/Jv//+a7Ysf/78qoUlapOEhIRYTdk3O4seGMiz6B6WoUJERERERF4WaJg5c6bs2bOHgQbyOEj+Wb9+veokceDAAbNlCCr06dNH+vfvL/lsdCvQ6wLEX7ggkpSk2iui8wGKEqKjBeSElH1mdBAREREReTePCzQQeSIEvwYMGCBbtmwxu9/Pz0+6du2qAmPFixdPc3CNTAYEGfxCQ1N1OkBRQizP3aCBV6fuM6ODiIiIiMj7MdBAlIbjx4+rKRLLly9PtaxDhw6qPgO6qqQHNRkwXQKZDHqQAXCN20lRUWo56gV4ayo/MzqIiIiIiHIGBhqIrLh48aKMGDFCdUuxbLXarFkzGTdunDz88MN27zsUfkRNBkyXsOw+gduqvWJ8vCpK6I2Y0UFERERElHP4unsDiDzJrVu31BSJChUqyKxZs8yCDLVr11Y1GjZs2JChIAOguwQKPybHxqrpEka4rcXFqeXofOCN0svo0JKSTBkdRERERESUvTGjgUhEYmJiZOrUqTJ+/HiJtMgqQNBhzJgx0r59e/H1zVxsDi0s/QsVUoUfUZPBskaDj5+fWo72it4op2d0EBERERHlJAw0UI6WmJiopkdgmsSlS5fMlhUtWlSGDx8uXbp0kYCAgCy9Dgo85mv/vOougcKPqMmgBtfIZPDzk4CSJdVyby0EacroiIhQwRVjsMGU0REe7rUZHXZLvCdyfo9I7C2RkPwipeqK+AfZv5yIiIiIyJsDDajGT+SpMLj98ccfZciQIXLixAmzZXny5FHTJ3r37i25c+d22GvqrSvRXQLTBHAGH4NrZDIgyODNrS1zekaHXY6vEdk/XyT6ikhSvIhfoEhoUZHar4lUeTr95URERERE3h5osJyHnhGWqdVEjrR582YZOHCgallpFBQUJD179pRBgwZJgQIFnLLTEUxAC0vUIsA0AZzBx+DaWzMZdDk9oyNdCCLsnCJy6z8RLVkkIEQkPkbk9iWR2JsiF/aJnN1pezkw2EBERERE3h5oSE5OdtZTE2XKgQMHVBDh119/NbsfdRc6deqkpk+ULl3a6XsXg2lvbWGZlpyc0ZEmTIdApgKCCEF5REKLINqKaK1I9FWRm2dSLrjP2nI8Do+v0IzTKIiIiIjII7BGA3m906dPy9ChQ2XRokWplrVp00YVeqxevbpbti2nyakZHWlCzQVMh0Cmgh5EAFzjNoIJyYkifgEiBSqmXo56DXj8hb0iZeu79a0QEREREQEDDeS1rl69KqNHj5avv/5aFX00atCggeow8fjjj7tt+3KqnJrRYRMCBai5gOkQltPGcBu1GJLuifjmsr48IFfK42P+N4WCiIiIiMjNGGggr3P79m359NNP5fPPP5e7d++aLXvggQdk3Lhx0qpVK9YC8WLJ8fESe+CgaquJjhcoRumxWRPoHoFgQkJsynQIYzABtxFE8PETSU6wvjwhRiR3AZFc4W7ZfCIiIiIiSww0kNe4d++ezJgxQ02FiIiIMFtWpkwZld3w8ssvsyOKl7uzcaN5HYjAQM+uA4EWlegegcKOmCZhWYPBPzhlPdxnbbmvX8rjS9Zx9zshIiIiIlIYaKBsLykpSRYuXCjDhg2Ts2fPmi0rWLCgfPTRR9K9e3fVVYK8P8hwY9Zsib9wAQeG+IaESHJEhGqriY4X4HHBBv+glBaV6B6Bwo6YSoHpEMhUQBAh/D6RMvX+v+uE5fL8ZVMej+chIiIiIvIADDRQtoUWqmvXrlWdJA4fPmy2LHfu3PLBBx+oS548edy2jeTa6RLIZECQwS80VPwKFlTTY3CcJEVEqLaaWI5ilB43jUJvTYnuESjsiOkSmA6BTAUEEbAcLTDTWk5ERERE5CG8PtBw/fp1mTBhgvz0009y7tw5CQkJkbJly0rTpk1l4sSJqdbHepjfj1aIULt2benXr588/TR/yHuSXbt2ycCBA2X79u1m9wcEBMjbb7+tshiKFCnitu0j10NNBkyXQCaDHmQAXON2UlSUWo6OFx5ZjBLBArSoRPcIFHZEzQVMh9AzFdJbTkRERETkIbw60PDnn39KixYt5MaNG6p9IVoZolDgsWPHZNKkSakCDZMnT5b3339f/P39pVmzZirVfv369fLMM8/I1KlTpWfPnm57L5Ti6NGjMnjwYFm9enWqXYL6C6jDUK5cOe6uHAiFH1GTAdMl9CCDDrd9goPVcrTV9FgIGqTVojK95UREREREHsDfmzMZWrZsKbGxsbJq1Sp59tlnzZbv2bPH7PaJEyfkww8/VMGFzZs3y2OPPabu/+eff1QLRAQg8HwVKlRw6fugFMhGGT58uHz33XeSnJxstlvwuaCTRM2aNbm7cjB0l0DhR9RkwHQJY7ABt7W4OPEJDxe/fPncup1ERERERN7OV7wUBqXoPICsBcsgA9S1SJ2eMmWKKiqIooF6kAEqVaokQ4YMkcTERLUOuRayUVBnAZ/DvHnzzIIM+AwRFFq3bh2DDKRaWKK7hI+fn6rJgOAC6DUacD+WhzAgRURERETkVF4ZaEAWw4IFC1RBwDfffNOux6xZs0Zdt2/fPtUy/T7UbyDXuHv3rmpTiWkQn3/+uWpdqatcubIsX75cfv/9d2nUqBE/ElJQ4BEtLANKlpTk6GiJP31aFYbENW7jfiz3uEKQRERERERexiunTuzbt0/u3Lkj9evXV8UfccZ7w4YNEhcXp86Md+jQQYoXL25aPzIyUqXmQ61atVI9X6lSpVSbRLRORI0HdjFwnoSEBJk1a5aMGjVKrly5YrasRIkSMmLECHnjjTdUHQ0iS3rrSnSXQOFH1GTAdAlkMiDI4HGtLYmIiIiIvJBXjtZQ7BEKFy4sbdu2VTUajFBMcPbs2dKxY0d1Ww8y5M+fX2VBWFOyZEk1FQPBhgceeMDp7yGnwZSIpUuXqm4Rp06dMluWL18+1WGiV69eKnBElBYEE9DCEt0lUPgRNRkwXYKZDEREREREruGVgYZbt26pa3Qm8PPzk+nTp8sLL7wgMTExMm3aNNW+slOnTlK1alU1tz86OlqtnytXLpvPqQcgkClhD3S5sOb06dNSvnz5TLwr74VsEwQS9u/fb3Z/cHCw9O7dWwYMGKCCQET2QlDBI1tYEhERERHlAF4ZaNALBqKAI+b5v/vuu6ZlKA6JrAScPce/Fy5c6MYtzdkwxQUBho0bN5rdj+BQ586dVUFPTJcgIiIi11Gdev5XUJeIiDyHD1q2W7Rx91ReGWgIDQ01/dtaMUjch0DD1q1bzdZHxkNaxQkhLCzMrm04evRohjIdchK0DMUUCXwGlp5//nn5+OOPpUqVKm7ZNiIiopwKtawuXbok8fHxDDQQEXkgHx8fCQwMVPUGkf3tybyy60SZMmVMUyEKFSqUannZsmXV9bVr19R16dKlTVMu9ICCpQsXLpg9N2Xc5cuXVfvQatWqpQoyNG7cWP744w9ZtmwZgwxERERuCDKgZhW6PDGbgYjIM2mapr6n8X2N721P5pUZDXrnCLS5xAcRFBRktvzmzZtmmQwoNohgAz6wAwcOqG4VRufPn1eFIBFkYMeJjENXj08++UQmT56sPhMj1MgYN26ctGjRItukAREREXkbZDIkJSWpM2SYtsjuTkREnicxMVEuXrxoykArV66ceCqvDDQgaFCjRg05dOiQmh7RvHlzs+X6lAljK8unn35aZsyYoc6oWwYacB+0bt3aJdvvLfAHgOKbY8eONRXo1OGPAlMkXnzxRfH19crEGiIiomxzhgzTJQBBBqTlEhGR5wkMDFTf02gwoE9z89STtV47wuvfv7+6/vDDD1XKvu7gwYPy2WefqX8jjV+H7gYoQvjVV1/J77//brr/5MmTqqAkIvtYh9KHMyJz5syRihUrSr9+/cyCDGg5iuDD33//rdqLMshARETkOcUfmclAROTZ/P39s0XhXq/MaICXX35Z1q9fL99++62qCfD444+rtP1du3ap6RRvvfWWanmpq1y5supC0bdvX2nQoIE8+eSTKmKE58DjvvjiC6lQoYJb35Onw4G+atUqGTx4sAokGKGIJoIO77//vlmxTiIiIiIiIvIuXhtogLlz50q9evXk66+/li1btqi0ktq1a8vbb78tnTp1SrU+BsEIJiDgsH37dnXfww8/rLIjnnnmGTe8g+xj27ZtqlXl7t27ze5HsAbtRRF8sFaYk4iIiIiIiLyLj+bJ+RZeSG9vaav9ZXbz119/yaBBg2Tt2rVm9yOo89prr8moUaPYqYOIiMiDJScny4kTJ0wZnpzWSETkudL7zvaU8abX1mgg5zpz5owKJKBrhGWQAdkfKMSJaStsB0pERESu8MYbb6Qq6O1q8+bNUydbUBk+J8D7feSRR5xe+2v8+PFqGjQ6xRUtWlQ6dOggZ8+eTbXuf//9J61atZLcuXNLsWLFZPjw4WpQpsPAC89hWaSciByPgQbKkOvXr6uimIieLViwwKwACf4HgCknP/30kzzwwAPcs0RERJSjoIsZppHmhKKaCACgYDoKrzsTaqVhWjNqqC1ZskQVbj916pQ0adJEoqOjTeuhBhs6zaGN/fLly1VWLQrAYxuNZ3oxrXrSpElO3WYi8vIaDeQ4d+7ckc8//1w+/fRTsy91/UsbLSzR/tNT26sQERGRayTHx0vsgYOSFBUpfnnzSUitmuKbQ1pmoh5VTqlJhYLpERER0qZNG6e+TkhIiGrlh0wEXd26daVUqVKyevVqVQAeEIRARsPmzZtV+z9A5gLaqaMgeXBwsLrv9ddfVyfNkO2AjnNE5BzMaKA0oT/r1KlTpXz58jJixAizIAO+4FFwE9Mknn32WQYZiIiIcrg7GzfKxd595NrEiRIxbbq6xm3c7274DYPW5ggEYPDasGFD+fPPP03LMWBFSr4OU0NxAgVnxnWffPKJVKpUye6pE3oxcmR8ItsBKf1VqlRRA2SjhIQENfC97777JCgoSMqVK6cGyPZuO+B1pk+fropw582bVw22Fy1apLJP8RsOLcaLFy9u9Wz+jBkzpGrVquq18ZsPhdTTs3DhQvWeUPjb8v0fOXJETWPJlSuX1KpVK1Wx8IxAMMAYZAC8j4IFC6qpvLpff/1VZdfqQQZAhzmcLEPXOeMUXwQgNmzYkOltIqL0MdBAVmE+G/4Hgv8Z9urVS02Z0IWHh6vshn/++UfNh2Q0mIiIiBBMuDFrtsQeOSIJly5J8t276jruyBF1v7uDDfjNsnjxYpVKj7PfGBAj/f7atWtqOVLqd+7caVof/8ZZ8B07dpjdl5k6EF26dJHGjRvLihUrVKDixRdfNPttheUTJkyQrl27qgDHsGHDzJant+26cePGqYH/0qVL1evh7H2fPn1URsD8+fOlY8eOqpX7/v37zR6DzmsvvfSSrFmzRtXg6tGjh5p+kJZNmzbJo48+anXZq6++ql77xx9/VPvw+eefVyevjNMuEIxJ65JWvXq8H+wfY+t5/C7F71YjPXCjF84DBHswxRfbT0ROhK4T5DrVqlVTF0+VnJysrV27VqtRowa+3c0uuXLl0oYMGaJFRka6ezOJiIjIQZKSkrRjx46pC/6dqee4d0871/0d7UT9Btqplk9pZ159TfvvtdfVNW7/U7+BWo71nKVTp05avXr1rC47fPiw+i2zdOlS033R0dFagQIFtP79+6vbBw8eVOucPn1a3W7YsKHWvXt3LSwsTEtMTFT3FSxYUJs9e7bNbZg7d656joSEBHV78+bN6va4ceNM61y/fl3z8fHRvvvuO3X76NGjap1Zs2ZletsB67Rq1cp0+/bt25q/v7/2wAMPqN93gM+3aNGi2tChQ9XtqKgo9ftu4sSJZq/Zo0cP9VvQlosXL6rX27Rpk9X3v2jRItN9+/btU/dt27bNdF+ZMmVS/c60vGDf2dK2bVutVKlSWlxcnOm+ChUqaAMGDEi1bpEiRbQxY8aY3ffGG29ojRs3tvn8RNn5O7uah4w3WaOBzKCADtLM7t69a7oPBY3eeustGTp0qKrgS0RERGSEmgyJOAOflCR+BQuaplPiGreToqLU8tiDByV33bou33mYZoAMzLZt25qd2UaHgr1796rbOMudJ08eNc0B00P37Nmjpo9+//33chDbnTu3qkmAzIeMatasmenfSPnH5eLFi+r21q1bVXs6ZAFkdtt1yHLQhYWFqakWmGahfx54HZzlv3TpkrqNKQ0xMTEq48DYKQPZEJhOgSwE49QI3ZUrV0xZrum9X0zJAP39AgqHo3hjWlB43JopU6aox2OqBLIVMqNAgQLq8yUi52GggVJ98SKlbvTo0eo2UvswR9CYmpYd5eTCVERERM6G/79q8fHiGxKSqmYTbvsEB6vlSZGRbvkwLl++LPnz50/VDaJIkSKmwToG4Y899piaKoEUfNRCuP/++9X0ANwXGhqqBu62BsBpsawxgMF7XFyc+veNGzfUttkaNNuz7TrUZrB8HWv36a+NwAmgJoQ1CEiULVs21f36421ts/H96oEK/TFQrVq1NKdGgLWpuT///LN88MEHMnnyZGnatKnZMuyjqKioVI+JjIxUy4yw3cbtISLHY6CBUkGbouPHj8uAAQPkoYceyvZ7CHNCI5ctV2dS8CPHJzBQ/AsVknztn5cwi/9JERERUcYhiI//vyZHRKgBpDHYgNtaXJz4hIeLn8WA21WQkYkCgDhrbxywX7161SxbE9kKqFGFs/D4N94HajIgywHZDig26IyTPNg2nOG3NnC3d9szQ89IQGFEy2CI/tppPQ6D+MxAwcmzZ8+muQ66RzRq1Mh0G3UlUEcCxS579uyZan3UvsDvVyN0ocB+tQwOYbttZWMQkWMw0ECp4H+kKDTkTYWp4i9cUOmcONOCH0GJV6/Kjf/9z5HBBiIioqxBpiCC+Pj/a1JEhGn6BIIMuO3j56eWh9Ss6ZZd/fDDD6sChKtWrVLTBABTBlB4EQUYdQgqoBAjijaibbd+H7o54PdRt27dHL5tGEyjCDemaLz55puZ3vbMQLYGMjcQtDBOd0gPshwCAgJUsMBWQci0ZHTqxLlz51S3CEzpsNY1A1q0aKGKaiIDRA+QLFu2zGqACM9XsWLFDG83EdmPgQbyWpgugUwGBBn8QkNT/ehJuHBBLc/doAGnURAREWUBpiMiUxBBfPz/FTUZ1HQJZDL4+UlAyZJqubOnLWIaAgaXRsgCQH0DDNIRKEB2QNGiReWzzz5TbSUxZVT3yCOPqPUxVQJdIPT78LwYjGemPkN6kD2BrhLo9IDaB3g9TFnYt2+fmiJQvXp1u7Y9MzClADW40DoTnRwwdQTPe+zYMXWZM2eO1cehk0TNmjVVlgGm2WYU6mHYKzY2VrXRRLAFHTSM00UwlQXZEYDWpJj6265dO9XO8/z58zJy5Ejp37+/2l4jbPfAgQMzvN1EZD8GGshreXphKiIiIm+iZwiaTVcMD3fpdEWkzqOotREKJ0ZHR8vcuXPV9FAMMFH0uk6dOrJx40YpXLiwad1cuXJJrVq15PDhwyqTwPI+Z00pnTlzppQsWVIVYMQgGf/G2XmdPdueWYMGDVLBCxRZHDt2rNpfqKHQuXPnNB/33HPPqQxYPSDjLAjwHDlyRP3bMuuiU6dOMm/ePPVvTDtBgUhMrcC2IZMBbTuHDBli9hh8jsh6aNOmjVO3myin80HrCXdvRE6CqDQcPXrU3Zvi9W6vXy8R06arPt4BJUqkWq5nOhTs2UPyNG/ulm0kIiJyN6TtnzhxwpSujqKIWS7AfPCgKvyImgyYLsECzN4HGQMoIvn3339nq6LhmBqzc+dOFagh8sbv7OoeMt7M2v9JiLJDYarY2FSVjU2FqQID3VaYioiIyBshqIBMQQTxcc0gg3dCC9CXX35Zpk2bJtkF6kIgewRZHETkXAw0kNcXpsLcUNRk0IMNnlKYioiIiCg7Qw0EBByyiwsXLqiaDRkpfElEmcMaDeS1PKUwFREREZE3QveJDz74QLILFI5E3QYicj4GGsireUJhKiIiIiIiopyEgQbyeggmoIUlC1MRERERERE5HwMNlKMKUxEREREREZFzsRgkERERERERETkMAw1ERERERERE5DAMNBARERERERGRwzDQQERERETZ3htvvCH169eXnMjHx0dmzZqV5jrYN9hHafnoo49Uy0rdvHnz1HMnJiZmafty2meD9ztgwACXvmaHDh1sHgfXrl2TLl26SOHChSUkJEQeeOABWbNmjdljhw4d6tLtJe/HYpBERERERNnY7t27pXz58uKpMIi9d++e5ASnT5+WJUuWyMmTJ132mtu3b5dt27ZZXRYVFSVPPPGEFChQQGbMmCH58uWTv/76S+Li4kzr9OvXT5o1ayZ9+/aV/Pnzu2y7ybsx0EBERERE5CKxsbHqrLIjPfroo+LJPDkI4mjffPONNGrUSEqUKOGS10tOTpbevXvLyJEjpXv37qmWf/zxx2qdjRs3SnBwsLqvadOmZuvUqVNHihcvLgsXLpSePXu6ZLvJ+3HqBBERERE5TuI9kTPbRY6tTrnGbQ8QHR2tBmKFChVSA/2GDRvKn3/+aVr+8ssvqxRy3dq1a1Uq+qhRo0z3ffLJJ1KpUiXT7ZiYGHUWGIPKoKAgqVu3rjq7bITnmDp1qrz99tsSHh4urVq1srp9W7ZsUetu3rxZWrRoIbly5ZKaNWvKoUOH1FnpF198UcLCwqRKlSpqXcvXMKbMR0REyHPPPafeZ7ly5WTRokWpXg+Dz/79+6sz2DjbPWjQIHVfes6cOSPt27dXZ8ZDQ0Olbdu2cuHChQxNnRgxYoSULFlSdu7cKbVq1ZLcuXOr5SdOnDB73NWrV9Vj8Znp+2PVqlWm5cgaePrpp9V2YHvwGWKagCP2qT2frTXff/+9tGvXzur7x7ZXrlxZvSaOg8uXL0tWzZ07V+Lj46Vr166plmmaJt9++6107tzZFGSwBdu8YMGCLG8PkY6BBiIiIiJyjONrRJZ0EtkwVGTr+JRr3Mb9bobB3uLFi2XMmDEqtR0D0CZNmpgGpvXq1VMDXx3+jcHZjh07zO7TB8wYxD3//PPyww8/qLPJq1evVmfuMaA9f/682WvjNTEYxLrpzYVHQAKD5x9//FH8/PxU8OPNN9+U+++/X5YvXy5lypRR96U1FeH111+XXbt2qbPrEydOlNGjR6dK5f/0009l0qRJKtiAAebhw4dVTYa0IIDRoEEDFViYM2eOOgN+7tw5tb32BCmMbt++Le+++658+OGHar/gc3jllVfMBvoIBuFM/Pjx4+Wnn36STp06mfYtMkPw+WFbvvvuO5k+fboKBLRp0ybL+zQjn60RAiXYHmsZJqdOnVKfw7hx41RQCEEuy+wB1MJI72J0584dGTJkiPos8b4s/ffff3L9+nXJmzev2vbAwEApWrSoCvRYfl6PPfaY7Nu3Tz0nkUNo5FLVqlVTFyIiIiJPkJSUpB07dkxd8O9M+/tnTZv1pKZNrKhpn5TXtEn3a9qEcim3cT+WO1GnTp20evXqWV12+PBhDT97ly5darovOjpaK1CggNa/f391++DBg2qd06dPq9sNGzbUunfvroWFhWmJiYnqvoIFC2qzZ89W/96wYYNaf+/evabnTE5O1h544AGtd+/epvuwjq3tMtq8ebNa95NPPjHdt3btWnVfz549Tffhc8J9GzduNHuNmTNnqn//9ddf6vbq1atNyw8dOqTuwz6ChIQErXDhwlrfvn1N69y7d08rWrSoVqZMGdN9c+fOVY/D+jBkyBCtWLFi2u3bt03rXLhwQQsMDNRWrFhh92czfPhw9by7d+823bds2TJ137lz59Tt6dOna35+ftrx48etPue0adO0gIAA7eLFi6b7fv/9d/Uc2G9Z2af2fraWFi5cqPn6+pr2l/H9Y1v19waffvqp5u/vb/qbO3PmjHrN9C5G/fr105o3b271OIBdu3ap+0JDQ7W33npLvb8xY8ao1500aZLZc/33339q3a1bt9p8f5Q9vrOrech4kzUaiIiIiChrMD1i/3yRW/+JBOURCS2CfH4Mi0Sir6bcj+UVmon4B7l8b+PsMc74Is1fh3R9pK/v3btX3UYl/jx58qiz4qVKlZI9e/aoKQ9IhT948KBaH2f0kfkAONN+3333qVR845lmzM83TsmAp556yu5txVl6y9oGeE7L+y5dumT18Tgr7e/vbzZF48EHH1Rn7XU4K48MgmeffdZ0H85245voWrsAAFVXSURBVKy35RQCI7xnrIMpGfp7LlKkiJp6gPds3L/pwf40nvmvWrWqur548aLa/1u3bpVHHnlETTWw9T5xFh61BXRYH4/FZ2rc5xndpxn5bI2uXLmijiHsf0uYcoNtM75fPDc+B2QZ4H3ox6I9kCExbdo0dZzaomctVK9eXWW36PsC7xNZEH369DGti+kz+nQVIkdgoIGIiIiIsub8HpHoKyJa8v8HGQDXuB17K2X5hb0iZV3f5hBz4VGLwHIAiEGyPrjz9fVVA1dMlcDAGYNppNZjMIz7UAcAtQL0gS+CDqhXEBAQkOr1jIN6QFtBeyHN3Tj4t3WfsWuAEQaKeK+WqfTYduM6lvdZu20J7xnTK6xNsUCthYxATQUjy/d148YNKVasWJqfqbX9is/UsvZBRvdpRj5bIzwe9Rwy835xG4ENew0ePFjV4UCti8jISNP9mFKCaSkIeOgdJBo3bmz2WARMMNVEXw/07bZ1XBFlFAMNRERERJQ1CCQkxYsEhPx/kEGH2wG5UpbH3HTLnsaA9datW+oMsjHYgAG3cTCLbAXUHcDZZvwbdRxQkwFZDhiQPf7446Z1UdgRhRZR98GSPojU4XlcBQNtvNekpCSzYAPm6hvXsbzP2m1LeM8vvPCCqutgST8j7ih4vrSKTOJz+/fff1Pdb/mZZkZGPlvLxxkH/RmBegrIokhPygwJkX/++UcVtUTGjVGvXr1UTRBkVyBTA9urP8YSgms6fbvxHogcgYEGIiIiIsqakPwifoEiCbEp0yWMA2vcTogRyV1AJJd7BjEPP/ywGnij6j+K/OnFBtFZwlitH0GFYcOGyYoVK6R169am+3D2F4GGbt26mdZFCvrkyZPVgNieAaKrPPTQQyqggvemvwcUejx79qxpHaTwIxsARQ5RcBFQrPLXX3+1eUZef894TI0aNaye7XcknIVHsUQUsaxYsWKq5WjJiEE2shf0wAKmEWBaCDpEZEVmP1tsJwpKItihB3PsldGpEygoiU4qlvsMxTWR6QD4LPFe0HXDaNOmTep9IUtHh6Ke+nsgcgQGGsjhkuPjJfbAQUmKihS/vPkkpFZN8U0j+ktERETZXKm6IqFFRW5fSqnJYFmjwdcvZXnJOk7dDKTbL1u2zOw+ZDCgdgACDAgU4Gw/5sR/9tlnkpCQoFoYGuf4Y31MlZgwYYLpPjwvBo96fQZo3ry5Gtg1bdpUBgwYoKZU4Lkx2C1YsKB88MEH4g6ox4A6Cgig4D1iCgg6XRinGeA9vv/+++p+bCtS9hFMSS/zAvtq/vz50qxZM9UxAvsR8/1/++031VoS+8JR0GHiiy++UM+JLglly5aVI0eOqLPwCECgZSM6OKAWw/Dhw1XKPz4HTHVp2bJlll47s58tAhzIItm/f3+G6nIAMg8QELOXrXWxrcbMGwTOnnjiCenSpYtq5/nHH3+oeg16zQYdthmBFWP7VqKsYKCBHOrOxo0SuWy5JF6/Llp8vPgEBop/oUKSr/3zEubA//mQlxcUw1xfpOHiDBl+vLqhcBgREWUAvqdrvyYSezOl8CO+wzFdApkMCDLkL5uy3Mnf58ePH1ep/ZZFB3Hmd+7cueps78CBA+Xu3bvqjDiK/hkH4Lly5VK1BpABoA/kjPchW0CHQfnKlStl1KhRqv0iihiixgGe111BBh3aPb711lvqgjPrSKWfMWOG2Tr9+vVTtQgQUMHgHYEJBCksU/GN8P52796t6gNgsI9WiCVKlFBnzR19JhwBEpyJx2eGCwIJGESj3SSg9Sg+PxQ0fPXVV1XwBC0skYmQVZn9bMPCwlRwYv369RkONDgL6o4gQwefGdqYInMCASgEaox++eWXDBXzJEqPD1pPpLsWOQyqvsLRo0e9MshwY9Zsicd8uqQk8Q0JkeTYWPHx85OAkiWlQNcuDDZQ2tBnHVXJUTAMc3mRhoszYPhxWuVp7j0iIidAZfoTJ06of2MgZ5y3nWH8HqccbtGiRSoLAjUXsvS35EIIxCEghWBDgwYN3L05lMXvbE8ZbzKjgRw2XQKZDAgy+IWGil/BgioajDhWUkSEJFy4oJbnbtCA0yjI9o/TnVNSzoShajkKisXHpKTh4gwZMNhAROTZ8D2NFpboLoHCj6jJgOkSzEyjHAIZNZiSgloW2SVDYPbs2VK7dm0GGcihGGggh0BNBkyXQCaDHmQAXON2UlSUWh6LPtRZLNBDXsjD+68TEVEG4HvaDS0siTwBpnCgUCPqemQXKAo5ZcoUd28GeRkGGsghUPgRNRkwXcKykBBu+wQHq+VJmWz5Q17Ow/uvExEREdmrUaNG2WpnoVAkkaNlj4lD5PHQXQKFH1GTwbLsB25rcXFquV++fG7bRvJgHt5/nYiIiIiI7MdAAzkEWliiuwQKP6Imgx5s0Gs04H4sD6lZk3uc0u+/bqT3X8dyN/VfJyIiIiIi+3HqBDmEb2CgamF5IzJSFX5ETQY1XQKZDP/rOoHlWI/IU/uvExERERFR1jHQQA4T1rSpukZ3CRR+RE0Gn/BwlcmAIIO+nMhT+68TEREREVHWMdBADoVgAlpYorsECj+iJgOmSzCTgdKlt65EdwkUfkRNhtwFUjIZEGRga0siIiIiomyBgQZyOAQV2MKSMoX914mIiIiIsj0WgyQiz+y/Xu3ZlGtOlyAiIjtbCr766qtWl6HV9qxZs7x2P44YMUJKliyZ5jq//fab2g///fefzXUSExPVOvPmzTPdV7ZsWfnoo4+ytH14TTwvtiEnOHXqlOTNm1du3Ljh1NfB56TayFtctmzZYrbe7t271d8HtqlIkSLSoUMHOXv2rGn50aNHJV++fHLr1i2nbi/lLAw0EBERERFlY127dpWffvpJPFWxYsXUYLdu3bqSE4wZM0YFvQoUKOCS19uxY4fav/qldu3apmUIKLRo0ULCwsJkyZIlMn36dDl8+LA8/fTTKrAE1atXl3r16smkSZNcsr2UM3DqBBERERGRiyQnJ6sBXqADO3EhmyG9jAZ3CgoKkkcffVRygsjISFm0aJFs27bNZa/5yCOPiL+/9WHd2rVr5d69e7J48WLJlSuXuq9gwYLSuHFjOXbsmDz44IPqvtdff1169+4tw4cPFz8/P5dtO3kvZjQQERERkcPEJ8XL3it75bezv6lr3PY0SC+fNm2avPXWW5InTx4pWrSoTJw40epUjMmTJ0vx4sUlNDRUOnfuLDExMWbrIU0dZ4NDQkKkcOHC0qdPHzWws5zWgGkDNWrUUIPuXbt2Wd0u/TVx1hmPwbb169dPNE2T5cuXS6VKlVSKO7bD2msYLViwQE17yJ07tzz//PNy8+bNVK/3559/ysMPPyzBwcEq2+DgwYN27b8ZM2ZI1apV1XspX768fP311xmeOoHbeB4MbvPnzy8lSpSQUaNGqfdqhEF7zZo11Tbic+rYsaPZe//ss8+kXLlyaluqVasm33//vUP2qT2frTXLli2TQoUKmWVv6O//xx9/VNuCY+m+++6Tb775RpxND2rhPegwhQKM+/qZZ55RUyc2bNjg9G2inIEZDURERETkEJvObZIVJ1fI9djrKsAQ6BcohUIKyXMVn5MmpZt41F4eO3asNG/eXJYuXSobN26U/v37S+nSpeXFF180rbNp0yY5ffq0GkhfvHhRDVAxoMUAGbZv3y5PPvmkvPzyyzJ06FC1zsCBAyUpKUmmTp1qep6oqCh55513ZMiQIWqwW6FCBZvbtXnzZrl+/brMnDlT/vrrL/V8GCwiJf7TTz+VK1euSK9eveT++++Xvn37Wn2O33//XZ2hxgUDcwwe33//fbN1oqOj5amnnlKBAuyD8+fPq/eRnnHjxsnIkSNl0KBBahCOtP0ePXqos+QIaGT0M8AAF2fb8b5xNr1WrVrSunVrtXzOnDnSpUsXFQTA68bGxsrKlSslPj5efQ4IFuEzGTx4sDRo0EAN5F955RUVuMB7y8o+tfeztYRjCRkG1uC5EWhYsWKF/PDDD/L222/LY489Jg888IAp2wWXtPj6+qqLEYI0qAeBQMuwYcOkffv2pmXPPfecqrGBywcffCB37txR/3788cdN2QyAgBS2A8d8y5Yt0/nkiOygkUtVq1ZNXYiIiIg8QVJSknbs2DF1wb8za+PZjdqra17VGi1upD3xwxNa82XN1XXjxY3V/VjuTA0bNtReeeUVq8vwk3fmzJlmtx966CGzdTp06KDVrFnT7PmCgoK0a9eume778ssvtcDAQO3q1avqdr169bSnn37a7HmWLl2q1rly5Yq6PXz4cPV6GzZssOs9FCxYULt7967pvrp166rnu3jxotm2NmjQwHQbr1GiRAnT7Xbt2qV6f7gP23HmzBl1+4svvkj1/nAf1pk7d67pvjJlymhDhgxR/46KitJy5cqlTZw40ey5e/ToodWoUcPm+8JrWu4D3G7RooXZevfff7/WuXNn9W8ci0WLFtVeffVVq8+ZmJioluO1jVq2bKn2WVb3qT2frTUVK1bUhg0bZvX9v/3226b74uPjtfDwcG3UqFGm+zp16qTWS+uCz1r3yy+/aGPGjNF+++037aefftLatm2r1lm5cqXZ6+/du1crUqSI6TlwnBs/d90bb7yhNW7c2OZ7o+zxnV3NQ8abnDpBRERERFmC7AVkMlyIviChAaFSLm85KRFaQl3nDsgtF6MvquWeNI1CP2tuvI2z3ThbrsPZZqTBG9fBcqyHKRQ4I46zxzg7rl+Qqo91jhw5YnocUtebNm1q13ahloE+lx6QcYD0fkzfMN536dIlm8+xb98+q+/Pch1r7y8teL9438hcML5nzPdHgUHjvrNHs2bNzG5jOgYyB+DEiRMq0wBZGdZcuHBBLbfMonjhhRfkwIEDKvMgs/s0I5+tJWxTeHh4uu83ICBAvab+fvUpMHv37k3z0q1bN9P6KPKIbA4cW8gMQaZE/fr1VaaIDs+PLhPYdmS2YB1M42jTpo0kJCSYbR+KV169etXmeyPKCE6dICIiIqIsOXT9kJoukawlS8GQgmogA7jG7dvxt9VyrFenaB2n7G0UwzMOLnX6fZbF8owDbP020tavXbtmqndgbR19MIn57Fj/zTffVBdLmIqgw7QCfZ+kR58/bwxSWLsvLi7O5nNgsGhr2zOyjqWIiAh1jZoI1mCgjroQ9kJtBFvvS28NiY4V1ly+fFldo3aCEdo3YgCNbcW/M7NPM/LZWsJzYFpHRt8vYOpOekU9LadNWEIAAVN0dKg9gqAGalfoj61Tp46UKlVKBR0QhNBhu9M6rogygoEGIiIiIsqSqHtRKlsh2D841YAat4P9gtVyrOcsGMxbOxurD0gtB9GYs295GwMx48DV2jqAooQYNOK9oXaAtWwF44Db3iCDo2CAbWvbjeucO3cuzXUs6WfqcWbcctCcVlAgM/TWkPj8UDvB1mshMIT2jDocAxhY43jIrIx8ttb2ETpPZAZqUXz77bdproM6Fsh8sNc///yj9p8xQIGaDtg/qD9ihO22lY1BlFEMNBARERFRluQNyqsKP96Iu6Eq2RsH1rgdlxQn+YPzq/WcBSnjKOiIM+H6IBV++uknNfA0dgHQ78egzXgbxfGMbSeRPo8z4/qgFetgOdZD8TwU/Tt16pQMGDBAPAk6SVh7f5broAij5ftLC6YgoHsBBvOW0x4crXLlyiqYgO4ZKMpoCWf+EfBBAUhM3TB2fahdu3aWWjRm5bOtWLGinD17NlOviwBCz54901zHON3DEv7WkKWAgpo6ZC6gGCYye/R9gowMfO5lypQxezwCT9h+IkdgoIGIiIiIsqRGoRqqu8S1mGsSERthmj6BgQ9u+/n4qeVYz1kwlx8dBJ544gnVEQGD0D/++EM+/vhj6d69e6qMBqT5v/HGG6orAyrtL1myRLVSNMLZXdQtwDx4zHVHIAOp9HrWw4QJE9QgGO+zbdu2ahD+77//yqpVq1SqOlopugO6CyDwor8/tJVEJwojvA+0k9TfH2oepNVNAdDNAR0YsD9xNhw1HjBN4dixY+qCLhGOgjPwqDWA7URwp127dqq1JPbtF198IWFhYWqKgN4eE+8Xg+x169apS1Zl9rPFPtm6dWumXhOZEhmZeoIaEgigIfCFfTNr1iwVHFu9erVpHXTtwP0vvfSS+je6jeBvAlkNljU59u/frzprEDkCAw1ERERElCXIZkALy8h7karwI2oyYLoEMhkQZEBhSCzHes6CgR8GeBgo9enTR27fvq3mvKOVn7XBE4IRKBqIwRoGkePHj1eDMaMmTZqos8MowIe2gFj3888/Ny1HUANBCmQOYEAP9913nxrA4TndBa0L582bp4ICCKCgjSe22/j+QkNDZe3atSpogAKKmH6wcOHCVJkflvQgzpQpU1QgAGf/0VYRaf+OhkAJggyYwvDdd9+pgAKmMuhZJzj7j5oC06dPV58fiisiA8IR7Rkz+9mineSkSZNSZdY4AwpaIoiAIBHgWP3555+lVatWpnXweeI+BJXQujU4OFgdHzguEKzRoZgnpqmgxgORI/ig9YRDnonsos8hO3r0KPcYERERuR2K3qHCv56unl6xubRsOrdJdZdA4UfUZEBgAZkMCDI0Kd1EPAWyLWbOnCldu3a1uQ6q9CM9HwNXoozA31G/fv3SPL48zbBhw2Tnzp2yceNGd28KZfE721PGm8xoICIiIiKHQDChfon6qrsECj+iJgOmSzgzk4HI0yCDBtM7skugAdMuEHibP3++uzeFvAgDDURERETkMAgqOKuFJVF28Nprr6maHq6YPuEImHqB+iPOLvBJOQunTriYp6SyEBERETl66gQRETlXdpk6wf+TEBEREREREZHDMNBARERERERERA7DQAMREREREREROQwDDURERERERETkMAw0EBEREREREZHDMNBARERERERERA7DQAMRERERZXtvvPGG1K9f3+qykiVLyogRI0y3GzVqJK+++mqGnn/evHni4+MjiYmJLnlcdoX3+8gjjzj9dbBPrV3Q7k+3du1aqVevnhQoUEBCQkJU279p06aJpmmmdb788ktp0KCB07eXKKfxd/cGEBERERG5EgaXQUFBLnmtp59+Wnbv3i3+/t7/szspKUnGjBkjY8eOdfprYZ8aJSQkyJNPPiktW7Y03Xfz5k0VVOrXr5/kyZNHtm7dKr1791ZBnz59+qh13nzzTRk2bJhs2rRJmjRp4vTtJsopvP8bj4iIiIjIoFq1ai7bH4UKFVKXnGD9+vUSEREhbdq0cfprPfroo2a316xZI/fu3ZMXX3zRdJ9l1goCCadPn5aFCxeaAg3IdHjhhRdU8ImBBiLH4dQJIiIiInKYe4lJsvv0DfnlyGV1jduexnLqBM7Ev//++5I/f36VZj9kyBAZPHiwlC1bNtVjjx8/rqZo5MqVS2rVqpXqzHp6Uye2bNmibm/fvl1lO+TOnVuqVKkiq1evTnWGfvjw4XLfffep7Ity5crJxx9/bFoeHR0t3bt3V0EMDJYbNmwof/75p9lz4HWmT58u7777ruTNm1dKlCghixYtUlMHMJWkcOHCUrx4cZk0aVKq7Z4xY4ZUrVpVvXb58uXl66+/Tne/YgCP9xQYGJjq/R85ciRD+y2jFi9eLKVKlZLHHnsszfXw+WLfGrVr105+/vlniYqKcug2EeVkDDQQERERkUOsP3pFeizcL+PW/S2TfzuprnEb97sKBvSWl/SMGzdODcgHDRokCxYskMOHD8t3331ndV0EKF5//XX58ccfJTg4WJ5//nmJj4/P8HZ26dJFGjduLCtWrJBKlSqpM/HXr183Wz5hwgTp2rWrqjWA9H7jctSkwOAaUxWWLFmiBvM4I3/t2rVU7w0D/6VLl6rXw7bjbD7O7M+fP186duwoffv2lf3795s9BoGXl156SWUKvPbaa9KjRw9Zvnx5mu8J0w8sMw3s3W8I9lj77IwXY20FI2QyrFq1Sjp06KD2gyU89927d1XGBd4zAi9GqCmBbdm5c2ea74+I7MepE0RERESUZQgmfL3tXzl/M0aSkjUJCfST2DtJciUqTm7FpJxBbl69qFP3NAaKAQEBGXoMBrBffPGFGmz3799f3desWTMpU6aM1fUHDhyoBuCAbIKHH35Y/vjjjwwXFOzcubN8+OGH6t+1a9dW2QW//PKLGtQfO3ZMDYhnzZqlAg7G4AIgOwCDfgQP2rdvr+5DkAHb/Nlnn6kAha5GjRoyefJk9W+c7UdwYvPmzXLo0CE1KEddg++//15WrlyptuP27dsqcwIXffuwPzAlYvTo0SpAYM2lS5fk8uXLquBiZvYbsibOnj2b5j7DdiMbxdK6devUdhunTRghawTBCPjoo4+kW7duZstRvwH7bt++fdKqVas0t4GIcnigAV9CKPhiC76QjMVikD42cuRIm+sPGDBAxo8f7/DtJCIiIsruMD1iyb7zKsgQGuQvhcIC1SAWZ6Cv34lX92N5w8qFJMjfz2nbgUE1BueWkM5vy7lz51SmgHEdBCtatGihBraWMOjWYWoBXLx4McPbanyeggULqov+PPgN6+vra7MzBqZI+Pn5Sdu2bc0G0xgk792712xdY92BsLAwNcjHNAv9zD9eB9MzECgATGmIiYlRAQVjNgiyITCdAmf+jVMjdFeupGSthIeHp/t+re23n376yRQMsMXYUcIIwRO8hzp16lhdvmvXLpXRsG3bNpUBgukTeo0GHe67evVqmq9PRPbz2kCDDl+SoaGhqe7HHDVr0AKnQoUKqe5/6KGHnLJ9RDlBcny8xB44KElRkeKXN5+E1KopvlZ+pBARUfa0/2ykXLtzT2Uy6EEGwDVuR8UmqOUHzkXKo+UKOG078JsPZ8otpZXloE81wEDTCAN/a/Lly2f6tz7gjouLy/C2Gp9Hfy79eW7cuKHqRdjqjIHMASy37GRRpEiRVIEG1GawfB1r9+mvjcwFQE0IaxCQsFa7Qn+8rW1Ob7+hQKetqRE6BFcsxcbGqvoKPXv2tPk4ZGqAnj2BrAZMBTEeF9juzHyORJRDAw2ffvqp1S9DWzAPTk9LI6Ksu7Nxo0QuWy6J16+LFh8vPoGB4l+okORr/7yENW3KXUxE5AWiYuMlPjFZTZewnCOP28EBvmp5ZEzGaxk4G6YsGAfYOsvbroSgx61bt9QZfmsD92LFiqnlyDgwBhtwRh7LskLPSNiwYUOqYIj+2mk9LjIyMlOvm9mpE6ghgcKYtqZNWKpZs6bKbsC+KlmypOl+bLetbAwiyjivDzQQkXuDDDdmzZb4CxdQiUl8Q0IkOSJCEq9elRv/+yHCYAMRUfaXNyRQAv19VU0GnJU2BhtwOy4hWQqE+kq+XJ6XzVa6dGmVvYCCi0888YS6D10Jfv31V6tTBFwBg+nk5GRVO+HNN99MtRxZGyhwiAKIes0ETHfAe8BJs6xAMUd0scBA3DjdIT04sYcMAQQLbBWETEtmp05g2gSKaSKAYA9Mo0DnCz3ApB+j58+fl4oVK2Z4u4nIOgYaiMhp0yWQyYAgg19oqPgVLGiar5sUESEJFy6o5bkbNOA0CiKibK52mXxSOCxIFX5ETQbLGg1+vj5qea3Sqc+QuxsyAnr37i2jRo1SZ7QffPBB+fLLL9X2o36BO6CGATJskd6P2gfoioApCyhWiMKOKLiIAAOKGiKzoWjRoqoIJAIkKGqZFZiSMXToUNU6E50pUEASz4sClbjMmTPH6uPQSQKDfXSvsDe7wOiBBx7I8GOQyYCMBr1opSUUykTQ4/777zd1xUArTxT9NAaRTp06JXfu3Em3NSYR2c/rAw2zZ89W89zwPwpEO1E0B5FrW/AFdPDgQTVHC+lUTz31FOszEGUCajJgugQyGfQgA+Aat5OiotTy2IMHJXfdutzHRETZGAo8dni4lOougcKPqMmA6RLIZECQoVR4LrXcmYUgswIdEfB7cezYseo3IzpC4Pfijh073LZNM2fOVL9FUYARRcvxb2MHirlz56oBNrYdUwFQCHHjxo1mZ+ozC20+EbyYMmWK2icoNIkaCtgvaXnuuedUq01j1wtnQhYEajTYCmygxtq3334rZ86cUdkWyFjA2ACdPYzQ7QM12jIT7CAi63y09KqueFnXCXzJIEqLi1FaXScQMZ43b57VopIZpbf8OXr0aJafi8iT3V6/XiKmTZfku3clwErxVT3ToWDPHpKneXO3bCMREYlK0T9x4oQpNT0rZ/HR4hLdJVD4ETUZMJ0CmQwIMji7taUj4ecxCgjiTDjaTJJ9MP0ARST//vtvq8XVPRWmzKDNp+X4gCg7fmdX95DxptdmNOALA3PUHn/8cVW0Bl98y5YtUz2Bhw0bpvrlIk1Ohy9DFI5EBgP66CINDS1wkFqFPsWYB7dixQq7X99WD2GkoKHYDZG3Q3cJFH5ETQZr83W1uDjxCQ8XPyuFpoiIKHtCMAEtLNFdAoUfUZMB0yU8NZNBd+DAAXV2HFMUME3gu+++k0OHDsm0adPcvWnZSqlSpeTll19W+w1TPLIDfM64rFy50t2bQuRVvDajwZb169ervsiooou5bih2kxa0D0IaFdLp0FfY3uI26QUa3B1hInJFjYaLvftI3JEj4mulRkNydLQE33+/lJgymTUaiIi8JKMhu/rnn3/UtIS//vpLTZ+tUqWKDB8+XNq1a+fuTct2/vvvP3WS7oMPPpDsANNNoqKi+FlTtpHMjAbP1Lx5c1WpF8V0/vjjj1QtciwhGwLVfpHtgPlb9gYabAUSbAUgiLyNb2CgamGJ7hIo/IiaDD7BwSmZDH5+ElCypFqO9YiIiNwJdby2b9/OD8EB0H0iuwQZoClbbRM5hddOnUgLCsEg0IBsBXvXB3vXJyIxa12J7hIo/KjFx6vpEv6FCqkgA1tbEhERERF5nxwZaED9BUAFXWesT0T/D8EEtLBEd4mkyEhVkyGkZk1mMhAREREReakcF2i4fv26KTUO1YTTg/nkehFIe9YnotQwPYItLInskHhP5PwekdhbIiH5RUrVFfEP4q4jIiKibMUrAw27du2Sa9euSevWrcXPz8+sOM2rr76qeg0/++yzqh+xHnxAz9/XX39dwsLCTOtHR0er/sSo5YBewiwIRERETnN8jcj++SLRV0SS4kX8AkVCi4rUfk2kytPc8URERJRt+Htr5WAUcERwAFkI6DBx9uxZ+fPPP1UlYRRknDlzpml9BB569uwpAwcOlDp16qgCkAg+7N+/X3WbwOPRGjNXrlxufV9EROTFQYadU0Ru/SeiJYsEhIjEx4jcviQSezNlHQYbiIiIKJvwykADeiC/8847KhNh7969qsYC6ivUrFlTXnjhBbXM2NayQIECMmDAAPn9999VkAIZEciEuO++++SNN96Q999/X0qUKOHW90RERF48XQKZDAgyBOURCS0i4uODuXsi0VdT7sfyCs04jYKIiIiyBa9slFy1alX58ssvVQYDplAkJCRIZGSk7N69W/r27WsWZABMlxg/frxs2bJFLly4oLIekOVw5MgR1daSQQYiInIa1GTAdAlkMuhBBsA1bicnpSy/sJcfApEd/eW/+uorqVWrlspEDQ8PV9Nl8ZvQko+Pj8yaNcvmcyG7tXv37qpdY3BwsJpyi+fatm1bhj+H9F4Ly61d2rZtK860YcMGdRKuVKlSEhoaqjJ7V61aZbbOpUuXVLvK+++/X524K1++vPTv31/9VrbHv//+q14jf/78ptfAiUBnwnRpa/tzxIgRaT4O29WpUyd1shHv9YEHHpDZs2fb9dy4tGjRIs3nx7H00UcfZeo94eQnToxa+v777+WJJ56QvHnzSlBQkPp83n77bTl27JhpHYxxjNuZJ08eleHdo0cPdZLVknFd7AdkiON1HCkiIkKNway9fnosPwO8HxxXy5cvF2davHixVKlSRX0fYJ9s3rw53ceULVvW6rGCz8qa2NhY02NOnTol2ZlXZjQQERFlGyj8iJoMmC6hBxl0uB2QK2V5zP+mUBCRTZ07d5ZFixapbNTPPvtMbt++rU4+1atXTw2g0xsI6hITE+Xpp5+WO3fuyMiRI6V06dJy7tw5Wb16tTpxhYGdow0aNEgFMowQKHEmTCVOSkqSiRMnSqFChdQ+QnBjzZo10qpVK7UOphLjdrdu3dTgCoOfwYMHq2nJGHilBes89thjUrduXZk/f74EBgaqwXxMTIy4whdffKEGoDq9PpstqNmGk47Dhw+XMmXKyNatW9Wg/d69e/Luu++qdTDFGseA0dWrV9V+a9mypVPex+nTp9W2nTx50ux+BMIQCMFng+APAjl///23+lzbtGmTav2lS5eqfYD9f/ToUfnmm29kzpw58sMPP6j1rR2P+Bv49ttv5ZVXXlFBB8v1MqtgwYKqPt7HH38s3333XZY+X5xQnj59ugpoYfDfsGFDtRz34T3j88PAHscggmqZsWnTJunYsaP069dPfc7YZnxHHDx4UCpVqmTzcStWrFCvb/T888/Lww8/bHV9nORGsMEraORS1apVUxciIiLl322a9nVDTfukvKbNaaVpc5/+/wtuTyiXsvzMdu4wcoqkpCTt2LFj6oJ/Z1dLlizR8NN2/vz5ZvfjPT355JNakSJFtOjoaNP9WHfmzJlWn2vnzp1q+eHDh1MtS05OzvC2pfVa9ix3loiIiFT3tWzZUu0v3a1bt7TExESzdX744Qe1zRcvXkzz+du3b681bNgwy8cVXmvz5s12r3/mzBn1mA0bNmR5f3Tv3l2rWLFimo+bNm2a5uPjo50/fz7N9cqUKaMNGTJEy6j+/ftrTz31lNl9S5cuVe8R15awv+fMmWO6jX2HdU+ePGm23r1797QWLVpoefLk0W7evGnzeMTzVa5cOdU2ZNXvv/+uBQYGajdu3MjQ46x9vjExMVp4eLjWtWtX033Xr183/fuNN97Q3n///Uxva5MmTbRWrVqZ7ZPq1atrb731Voae58iRI2rbFy5cmGrZhQsX1Gcxffp0q5+Xvd/ZnjLe9MqpE0RERNkGWliiu4SPb0pNBvUbT50JSLnt65eyvOT/n5UjotSmTZum0ppx5tXI19dXZSXgrDPObtoD0wWgSJEiqZYhpdlboE6ZpQcffFDOnDljuo2i6MYubvo6YFzPEs4yr1y5Up11x2fgLfvDGmR2IGsmvYwJS40aNVId8ZCBgKwZ7OuXX35ZZeIYYdqCZfc7nM1//PHHpX379qmeF/sbhfHTgwyTKVOmqNdDJpAteL4aNWqoDBXjVIzffvtNmjZtqqal42/v119/NXscOvj17t1bTUPHdANMbzcW5EemCzJpkK2RVdiGChUqqIwUY9YEIEMAmTR6pkNGYVo9pkwhY8K4T5CZ8Msvv2TouRYvXqy21TJ7CdCYAJ9/tWrVxBtkj796IiIib+UflNLCMn9ZkXu3Ra4fF7l1NuUat3E/lmM9IrIK9bhQ1BupzNYCAUjfxyBy+/btdu1BDC71wRqeF9MLrNEHXLh2RH0JTNkwXlJOLttmub61S0ZhWgAGbOmtg/ddrlw5m+scOHDA9B6w//39/dV0BExlcRWkuiNIgkH8qFGjbH6OWdkfFy9elB07dsiLL76YqW3E9AwM8rFfkDaP6TkIjOlOnDihBs+PPvqo2fGOovcY5GdV5cqV1XQCPF9aEGRARz/LqUrNmjWTH3/8UU0fwPQRPRiB4/mZZ55RUwxQWwLTbxB0wP7S4RjC+8K0hKzC6+G5Ud/ACNMWEIzBlA/jtA8cC+n97eh/f6gzgtsIphjh9vnz5zM0FWjx4sVqWhKmuRhh///0009mn312xxoNRERE7qa3rkR3CRR+RE2G3AVSMhkQZGBrS3ID/MiOiopy675HgTt7MgjQjjw+Pl4NKG3BYErPVEgPBk3jxo2TIUOGqAES5qZjUId5+sY6D9g2DGQdkeWAWgC4GGEbcJbTVkE8FC1MT3rBCiPUaEAwZu3atTbXwdlvDNpxdhf1Cmy5cuWKukZGA4oOjhkzRj0v/l28ePE0C11aC5DoA0MdAhe2YD7+e++9J82bN1dFQXHWefTo0aoT3aRJk8ReKCKKbIKpU6faXAdZMvj8LTML5s2bpwJVyIawHPwa4Ww7Bpg4xuDQoUMqEwQ1RvRtQNDLOMjVj3fLDAoMtnGxZx8ZIeMABfQtnwv7G1kJqOOAgTCyH4xwDKCWAyDggONx8uTJah9jnyOIomc9gLXACApuogZEZujbiOwZvSYLPncdtv25555T22ZZSBNFM/WgiC2o94CsExw3gIwTIxQ4Bbw+jrP0HDx4UBW/RF0Ky79RBGGwjYULFzYr5JmdMdBARETkCRBMQAtLdJdA4cdc4SnTJZjJQG6CIIP+Q9pd8APf8se9q6C4Hs6I42wtMhYwYMLZZkzRwGAZkIqdmawBa9CNwLLQXlqp+BisO7J7A87adunSRXVdeOqpp6yugwERBs8Y5GJAmRZ9wIvnGjt2rPp3kyZN5Pjx4+rMfVqBhoCAgFT3YbBolNYAHgEQTC3Q4XUxTeCTTz5RnScQwEoPBvPIUsBnbBkAsjxDjXUsz/bbC2f09SADWE4vQMAGXRXsCRqgKKSxSwaKQaaXnWIrGGUMfOG1MRDWj3udMf0fnxmKJOrHJIIMOEbTy7pAphGmNWWGZXFXZIYYpx18+OGHsm/fPpUBsm7dOvU56RkDCO5YFmm0lu3hSIsXL1afNTKvjBYsWCCXL19WRWy9CQMNREREngJBhbL13b0VRNkOBisYSKIzhC1IcUbXhIxAFgQGWLhg4ImBDQICyGxwdK0GTCuwVYneGrzfmjVrOiygg8EPzpp//fXXNtdDdgUGbBhEppXNAHqQqnHjxmb34wyxHniwxTKAgs4CaFv60EMPme7DIDYjENhAVgW6LaC2QVowAMWZcGQSIGPBVo0JHG840z9jxgyr7ShxSY9lIA2fq3EAjPoAlq0Q9ePdOA0Bhg4dqjJIkAWBa3vheSynBeiBLwyMMUXGWjtG1FewvK1PI8LfS3rHCOB50xvw24KuEqjzgEwlvHcEWurXr28K0OGYwcUaBCTSy/bRa5Pox7JlhhcyGcDeYOjSpUuldevWZtkPCIIgKwTZU/iscUEmBqDjB6Zl2JMt4YlYo4GIiIiIsjWcTcWZYQyCrQ0eMBjEwKdBgwaZfg0M7nC2H4MLyzRzd8DUCbzv9C7pQXYCCg3iGin71gaUgFaIaIOJFoHGlpG24Mw8WPs80isOiYCL8aKfXTbeh4F2ZqQXIML2ovYAAhKYNpNWi1EUMcRgFEUBnQWvrw9oLY93ZNlYC1Zl5Ew8Mkwsa0AYnwufo61j4vr166lu65kd+HvBWfr04L1lNnMKU5ywjcisQIYCBu2W0xJswdSJ9P52EFADBFqQ1YF9ZYTbCEbaEwjYt2+falNqWcvj7t27KtCD4CX2Ay4IRgACozgWsytmNBARERFRKkgv1+cmu4s9Ke66nj17SocOHVT6NCq3G1P4hw8frjpIGKvGp+XmzZvqtS27LZw6dUoNcDOyXc7iqKkTGMigLsCuXbtMVfotYb490ubHjx9v96Aa8/VxlhyF/oxn13Fb71rhSpgCg8+uevXqaa6HM/nLli2TDRs2SMWKFdNNhce0DFv7zRGwDTjjj+kFxi4oqEWA4xlnye09ri0huNSnTx91PL/00ksZfjymEumdHDCFCMeJvi3IZMFUFdQ5sMxqscwKSW8/2wP1WXCcIYMB9Tgssy0sZWTqBDpmPPHEE+q4QLBRD0jhmMJ0EXssXrxYTYGxnJaEopDYR5a1HDCNAlMqatWqJdkVAw1EREREZPXMr7vqI2QGBjgYBKCGwJEjR+TJJ59UxeFQzR9nJlHo0DgXHpBibvkeMacdAYXBgwerQTjO3iNYsXHjRpWqjXnrGHgAnhdz0LEsvdZ5tl5Ln/6AGgnocGGE7UWxPGswaM7IVAtrcPZ34cKFqugkziwbX18/w/3333+rAA5uY7BlXAdnhfUBHQpE4mKsWYHbOIOLIneosYBikMg6wf5yJszDR9o5Wk5iH2IAjJoNffv2VYM94/7H56bXNUC2BqZ19OrVS+1f43vFgM94Zh+fF85SG2siOAOmBiDgtX//frNBKopP4lhEUA0DVXQywHvDNIK5c+eqM/CWmQgYwEZERKgClMjYQJYKjnVkZmTmbx1BDgRZcAxj+gieG9OMANOMEGDAdqIuxv3336/O6GP7hg0bZnoOvC90JbH87kFwEI/LiA8++ED9jeJvHo9Pi62/K1vwfYDvFEwfQnABxwr2HYIPOlvfB5qmqX2MqSiWnwk+J0wnsuaRRx6xq8aGx9LIpapVq6YuRERERJ4gKSlJO3bsmLrg39kZtn/GjBlazZo1teDgYC1fvnzaM888o+3bty/VuvgZbO3So0cP7dy5c1rfvn21Bx98UMuTJ4+61KhRQ/viiy+0hIQE03Ns3rxZPQbXaUnrtdJajtd0poYNG9p8bd3cuXNtroNluuHDh5s9TjdnzhytQoUKWkBAgFalShXt+++/z/B22rOPjRYtWqTVrl1bfW7663722Wepju8yZcponTp1Mt3Gv2291zNnzpg9duzYseq5b968afd24fWGDBlitv9feeUVs3VmzpyZaj82b95c69Onj9XnXLBggVa/fn0tLCxMCwwM1MqVK6d169ZNO3r0aKrjVL/kzp1bq1q1qjr+Tpw4keo5sQ62wxb9+davX6/eQ1BQkFapUiVt7dq1ZuvduXNHvUbhwoXVOnjNWbNmmZZj32Efbt++3XTf3bt31XNPnz7d5uvjs8A6GzZsSLWsc+fO6vViY2M1R8NxhfeJ94LvmI0bN5ott/V9sGvXLnX/zz//bNfr6M9z8uTJTH1ne8p40wf/cXewIyfR07UQRSQiIiJyN5ytP3HihClVOL3580TkWpgOhKwQ1OXwhL9PFHxEtoK9XS1sQdtMZJDgefTaGcgKQM0FFG81Zp+Q/d/ZnjLedP+RSkRERERERDanBWEqB2oieBO0isVUBGOBzt27d0vXrl0ZZPACrNFARERERETkoTCPf9asWapzirfAe0G3E724og6BB/IODDQQERERERF5MFsFA921LVmdfY/2l+jwQd6LUyeIiIiIiIiIyGEYaCAiIiIiIiIih2GggYiIiCgHQyE2vRhbYmKiuzeHiIjSoH9PG7+7PRFrNBARERHlYPihior29+7dk4sXL0qJEiVU8TkiIvK8IMPFixfVv/G9zUADEREREXms4sWLy7lz5yQuLk5Onz7t7s0hIqI0+Pn5qe9tT8apE0REREQ5XHBwsJQuXVqCgoI8+gwZEVFO5uPjo76n8X2N721Pxrw4IiIiIlI/WsuVK6fa1mW1dR0RETmep9dlMGKggYiIiIiy5Q9ZIiLyTJw6QUREREREREQOw0ADERERERERETkMAw1ERERERERE5DAMNBARERERERGRw/hoLCvsUmFhYZKQkCDly5d37QsTERERERGRVzt9+rQEBATInTt33LodzGhwsdy5c6sP3psOZFyIshMet5Qd8bil7IbHLGVHPG4pux+3AQEBaszpbsxooCypXr26uj569Cj3JGUbPG4pO+JxS9kNj1nKjnjcUnZU3QPHZMxoICIiIiIiIiKHYaCBiIiIiIiIiByGgQYiIiIiIiIichgGGoiIiIiIiIjIYRhoICIiIiIiIiKHYdcJIiIiIiIiInIYZjQQERERERERkcMw0EBEREREREREDsNAAxERERERERE5DAMNREREREREROQwDDQQERERERERkcMw0EBEREREREREDsNAA2XIli1bxMfHJ93LqFGjuGfJ4+zdu1c6dOggxYsXl4CAAMmXL580aNBA5s6dK5qmuXvziFL5+++/5ZVXXpFixYpJUFCQlC1bVnr27CkRERHcW+Q2f/75p4wfP17atWsnJUuWNP2/Pz3z5s2TunXrSmhoqISHh0urVq1k165dLtlmoowet+fPn5cvv/xS3njjDalatar4+vqq9fFbmMgTj9vk5GTZvn279O/fXx566CEJCwtTvx3Kly8v3bt3lzNnzrj0g/PR+OuaMuD48ePqYLcmKSlJFixYoP69adMmady4MfcteYzly5fLiy++qI7T2rVrS4UKFeT69evqCzkxMVFefvllWbhwobs3k8gE36OtW7eWmJgYqVKlilSrVk2OHDki//zzj/qxsXv3bnVN5Gpt27aVVatWpbo/rZ+Uffr0kSlTpkhISIg0b95c4uLiZOPGjeoxy5YtU89J5EnH7eTJk+X9999Pdf/mzZulUaNGTtlGoqwct6dOnZKKFSuqfxctWlQFdv38/GTPnj1y8eJFFXhYu3at1K9fX1yBgQZymHXr1qmzE6VKlZKzZ8/adXaDyBUQSChRooRcu3ZNBRMQVDCeMcYX7s2bNxkgI4+B4EK5cuXk6tWrMmzYMBk5cqTphwXOVHz66adqsPbrr7+6e1MpB5owYYLcvXtX6tSpoy7ItLl3757NAdtvv/0mTz75pBQoUEAFyPQfwvg3Bmy5cuVSZ9qQZUbkKcft6tWrVVBBXx/ZZOvXr2eggTz2uD19+rS88847MnDgQHXCVx+LYX1kNCCrrHTp0ioggcxep0NGA5EjvPzyyzjitYEDB3KHkkc5fPiwOjYrV65sdXmvXr3U8gkTJrh824ismT9/vumYTUpKMlsWHx+vlS1bVi0/ePAgdyC5XVBQkDoebXnqqafU8kmTJtn8/v3000+dvJVEGTtuLbVo0UKtv3nzZu5KyjbHrS4mJkbLmzeveuyWLVs0V2CNBnIIRNr0tJ7XXnuNe5U8Cuan2QNn24g8ZU4mPPHEE2pesBHOQtSrV0/921o6JZEniY2NVdli0L59+1TL9ft++uknl28bEVFOERISIpUqVVL/vnTpkktek4EGcogff/xRBRtq1aql5hETeRKkoKMQzokTJ+T77783W4apE6gtkj9/fnnuuefcto1ERvg+BRyXaQXFDh06xB1HHg3fu0jbLVSokNWaIqiZA3/99Zcbto6IKGdITk5WU9v1+g2uwEADOYReBJLZDOSJUAjn22+/VfN/UcEflXhfeukladKkiTz44IPqxy+KkqEKOpEnwKAM9B8FlvTK0baWE3mKc+fOqWtbhUtz586tvptv3bold+7ccfHWERHlDIsWLVK1yvD74vHHH3fJazLQQFl2+fJlNUjDYK5jx47co+SRkGq+detWld2wf/9+Wbx4sSrohLR0FCnD/USeAlMmYM2aNalaWaJy9IYNG9S/OTAjTxcdHa2uUfDRFgQbgMczEZHjoVUrOv/AqFGj7J5SnFUMNJBDImRoGYjBmqtScYgyc5yizQ+6ovzxxx/qxy/aBKI/9meffaayG5DeS+QJ0FECKeU4Tp966inVmgr/RpV+3EYnFbCs30BERERknIrZrl07ddICrTLRfcJV+AuFsozTJsjTnTx5Ujp16iQFCxaUn3/+WQUccAYNLda+/vpreeaZZ1SWw5w5c9y9qUQKWlKh9k316tVl37598sgjj6j+10h3ROrjiBEj0qzhQOQpQkNDTS1b06tJgmOciIgcIyEhQV544QX1OwKt3C3rlDkbAw2UJSikd+DAAfVDAlEyIk/0ww8/qC/bli1bmn70GnXo0EFdb9u2zQ1bR2RdmTJl5ODBg7JkyRKV8vj222/LF198IceOHZMiRYqodRCIIPJk6NkOFy5csBlkiIyMVEEzBhqIiBxX/BEn2datWyc1a9ZUnX3QecKV/F36auR15s+fr66RkpPW/Esid9J/4ObNm9fqcv1+FCMj8iT+/v7qbAQuRrt27VLXjRo1ctOWEdmncuXKaj7w9evXVX2REiVKmC1HNhmgMC8RETnGe++9p6YNo6Xlr7/+qoruuhozGijTNE0zpeCw2wR5Mr12CFLHrNm7d6+6Llu2rEu3iygzrly5IsuWLVMtLhHkJfJkOIOGGjiwdOnSVMtxLEPr1q1dvm1ERN7oo48+ki+//FJllKF4dOHChd2yHQw0UKZt375dtVbD2Qn9RwSRJ2rTpo1pasSMGTPMlv3+++8yadIk9e/27du7ZfuIrDly5IjExcWlys7B8Yzq/Chi6uo0SKLM6Nu3r7r++OOPVc0cHYqbok4OzrR16dKFO5eIKIvwm3bMmDHqJNtvv/1mmr7mDj4aTksTZUK3bt1k5syZ0q9fP/nkk0+4D8mj4Tj99NNPTfPaq1WrJpcuXVI/dDGPDcczfvASeQp0RFmxYoXqPlGsWDFVBHLHjh2qO8rQoUNViyoid0Db1dGjR5tuoysKfk6iaKkOx+jTTz9tuo06I1OmTFHTLNGlKj4+Xp1pw+OQ1cA6T+Rpxy3atz/33HOmZcePH5eoqCipWrWq5MmTR92HdfEYIk84bg8ePKh+M2D5Y489pqZNWNO1a1dVHNLZWKOBMgU/dPV0x1dffZV7kTzexIkTVcX+r776Sv788085ceKEKjzWsGFDeeutt6Rjx47u3kQiMxh4YZrEoUOHZOfOnapYHgqaYsDG2gzkTqi3gDbBloz3YR2jyZMnq4Jk06ZNUwGGwMBAadasmfqBjO9mIk87bvFb19r6KISuq1KlilO2lSgzxy0K6+o5BDiRhos1+A3hikADMxqIiIiIiIiIyGFYo4GIiIiIiIiIHIaBBiIiIiIiIiJyGAYaiIiIiIiIiMhhGGggIiIiIiIiIodhoIGIiIiIiIiIHIaBBiIiIiIiIiJyGAYaiIiIiIiIiMhhGGggIiIiIiIiIgYaiIiIiIiIiMjzMKOBiIiIiIiIiByGgQYiIiIiIiIichgGGoiIiIiIiIjIYRhoICL6Hx8fHylbtqxD98eoUaPE19dXDh8+bHV5QkKCzJ07V5599lkpWbKkBAcHS+7cuaVChQry0ksvyffffy/37t1L9bhGjRqp7dUvfn5+kj9/fvW4559/XqZPny5RUVE2t8vy8biEhobKgw8+KEOHDpXbt287dD9Q2p/Df//955G7KKPHyZYtW1Kt7+/vL0WLFpU2bdrI5s2bs/walD3FxMTIypUrpUuXLlK5cmXTd12NGjXU92R0dHSaj583b57UrVtXHRvh4eHSqlUr2bVrl9V1jx8/LhMmTJDGjRtLwYIFJSAgQB2D7dq1k+3bt9t8jTVr1siQIUOkWbNmki9fPnUs4vjMDGwvHj9ixAhxNv3v7o033sj0c+B94nnS0qdPHwkJCZFz585l+nWIKAfRiIhIwVdimTJlHLY3rly5ooWGhmovvPCC1eV///23VrlyZfW6/v7+2iOPPKJ16NBBe/7557WHH35Y8/X1VctKliyp3bx50+yxDRs2VMtatGihderUSV3atWun1alTRwsICFDLwsLCtLlz51p9bWuPb9asmZYrVy51f5UqVVK9Jjme/jmcOXPGqcdiZmX0ONm8ebO6v0iRIqb1X3zxRdNx7uPjo3355ZdZeo2cCseDJ/xsy+x2zJw5Uz0Ol6pVq6rvRXzm+J7SP+erV69afWzv3r3VOiEhIVqbNm3U4/Cd6efnp61YsSLV+iVKlFDr4/sXxxK+V++//37TMThp0iSrr5M3b17TNuoXHJ+Zge9ePH748OFaVuE58Fy2vs/1vzv87WQW3ieeJy2XLl3SgoODtddeey3Tr0NEOYf7/49FROQhHD2469Wrl3rO/fv3p1p29uxZrUCBAqYfhwhKWLp+/bo2cuRILXfu3Nr58+etDs6s/TCMjIxUP0zxIxzrfPPNN6nWsfX4f//9Vytbtqxa9sEHH2TynZO9cBwg4BQfH+/RgQZ7jxN9wGM5OEtOTtZGjBhhGiwaB5Q8FnNGoGHevHlat27dtGPHjqUavNaqVUs9Z8eOHVM9bsOGDWoZvi//+ecf0/27du3SAgMDtXz58mm3bt0ye0zTpk217777TouNjTW7/6uvvlLPhe/Go0ePpnqtzp07axMnTlTH8fr167MUaMD3MP628T3uqYGGjRs3qn2lB1iwP0uVKqU1b95cmzFjhtXHvP322ypYY23/EREZceoEEZGT0oS//fZbuf/++6VWrVqplnfr1k1u3LghXbt2VSm2RYoUSbUOUn6HDRsmBw4ckLx589r92lgX6bp4XujVq5dcvXrVrsfed999MnLkSPVvpDmTc5UuXVqqVKmiUruzk4weJ0jrxjSI8uXLS2xsrKxfv97hr0GerVOnTvL1119L1apVze4vVqyYmuoFP/74o8THx5st//zzz9X1Rx99JBUrVjTd/9hjj0n37t0lMjJSZs+ebfaY3377TV577TU1PcPo7bfflubNm0tSUpIsXbo01TbieT788EM1jSAsLCxL7xffw/jbxve4J1q7dq08+eSTsnHjRjWVBf8PatCggfq727p1q0ybNs3q41599VVEmeSrr75y+TYTUfbCQAMRkZ1zX2/evCnvvPOO+mEcFBSkgghz5syx+jj8iEWNhI4dO6ZaduTIEfn1118lV65c8umnn6a7//HjOjM/evGDsH79+hIXFyczZ860+3F6YOT8+fMZrjOwYMECeeihh9R7K1y4sBpcXLx40eZjf/nlF3n66aelUKFCap+WK1dO+vbtq4IwlvAZ4HXwmWD/Yf61Po8agw17/PHHH6r2RYkSJdTr4bNs2rRpqv1z8OBB6d+/v3ovxm1799135dKlS6meF+9dn8+NmgK9e/eWUqVKqYEOBlaTJk2S5OTkNPedcV43nD171qxugXGueEa3zxkyepygVgnm42fkMRl9jfTgeRB4q1Spkpprjrn+Dz/8sApoWNaCQLBw9OjR6u8c62Lg+MQTT8gPP/xg9blR30X/7GbNmqVqTOBxqA2AAa61YxR1CcaNG6f2C54f9QcQjHnhhRfUMW78DsLxAMZjwlhT5tSpUyrAiAE4XjMwMFDVfXn99dfln3/+sbrN+nNg4I2aBtgvOJZw7A4YMMCsPoy925EZ+nGB1zP+7SMotWnTJvXv9u3bp3qcft9PP/2U4ddy9t+JrRoNxu+xbdu2SZMmTdT3e548edR34bFjx8zWx77VA25vvvmm2X5Pr6ZCWoYPH66+k/D/MHwvIiiCYA6CDPjORmDQmnr16qkAKb7r8f8WIiJbGGggIrIDBgn4Ab969Wp11gc/tlBwDIXNMKiw9PPPP6tra4XE1q1bp66feuqpDGUqZAYG1WCtCJ8td+7cUdcYcGQEgiYY1GCwhMJ/KPT23XffyaOPPioXLlxItf7AgQPVPsDZR5xRQ0FMFA7EoPyRRx6xmYWBApl43N27d9V1nTp1TAO8tEyZMkUef/xxWbx4sQowoDAcBpEI/PTr189s3fHjx6vtAARrUHgOZ/FmzJihBqa2BikYKGHggPeNwnU4Y4iBGYInnTt3TncbUcwTwRnA/sO/9UvLli2zvH2OlJnjJKOPyeyxaA2KAGLwP3XqVFWEtXXr1urvGAFBDAb//fdfs9dFUAEZRdeuXZNnnnlGrbtnzx4VPEQgyRYEgHr06KGOMRyf+Fy++eYbdXynzIpJgcE9ig4OHjxYfV74rsBAE0ECnG1etGiRWg+38fnjeADjMWEcfON7CEUV8XeBvwm8Hgav8+fPV7f/+usvm9v88ssvy8cff6z+DnHGH+//k08+Ud9vOnu3IzP0fY/MHgR/dCdOnFB/UwimIWhiqXbt2uo6rfdm67XwftwJwRF8VyCghb9fHC/43HHcXblyxbQe9q0eHMExaNzvWXkP2GcoIIzghaUCBQrIiy++aPVx+K5t2LCh3Lp1y2YxTiIixWwiBRFRDmZtXrw+9xWXl156SYuLizMtQxEy3F+6dOlUz4VieChWFhMTk2rZK6+8oh738ccfZ3pb06rRYLRjxw61XrFixex+/MCBA9WyevXqZWhb8H7XrFljuh91B/T3igJuRkuWLFH3o0DbyZMnzebyDxs2TC1DEUEjzD/WP4sffvhBy4itW7eqecUoPPfbb7+ZLUtISDDbbti0aVOquhlJSUmqZgZe/8033zRbhmKO+rY9+OCDZvOyT506pRUvXlwtsyxcl9likBndvszK6HFiq0YDoC5Dnjx51HLMu8/sa2TGjRs3tEKFCqnnwhx87CsjzPc31o3o2bOnWrdx48ba7du3Tfdjzn3hwoXVsp9++slq7YKiRYtqx48fN92PY6FChQpqGebEGz9D3IcCrpa1BKKiorR9+/ZZfX5bdu/erWpnWJozZ47pvVgyFme8fPmy6X48D2ofYBmO34xsR2Z07dpVPWfr1q3N7l+1apW6HzUcbNG30/g52YL3EhQUpNa33L/W9qczikHq32Mo9mv8PkhMTFSFgLFs6NChTq/REB4ergoH64VW7SkGqZs6dap6PXxXExHZwowGIiI74Mwg5qwaz6y2bdtWnRFHqy9je0KcAcXZeKQfI3Xakp4abGvuLlKWkV5rvGR2jrr+Gjj7lB6cVf3ss89Mc6IxTSQjOnTooM7M6XB2ElkEmEaBTBBj+vuYMWPUNc7a4iy+Tk81rlmzpixbtkwiIiJSvQ7O+to622YLMgAwrkLrOkyVMEIWhXG7AdMyLOtmIPUfZ7gx7QLvJ63MDuNni1R4PQ3Z1rznjMrK9mVVRo8TpFcjNRtn2DE9AWfNsf2OfI304Gz/9evXVVYI5uBjXxkhWwlTfQAZAZirj3W+/PJLs2lLeno54Ni2BtMt8B51OBZQSwCQKq/D9uhnqS1rCeD7BtNiMgKZQ5hfbwlnrPEaSLO31fL2iy++MDs7jufB1CtIqx2kI+AsPvY3vi+w74z0lpf4DrFFz7DQs19sSUxMVN+lyJDA90dG96+jITMG/w/RoUXxoEGDUh0nzoKsM2T24G8CGXgZmQaBvwN9ChcRkS3+NpcQEZEJfpQindQS5jQj9f7y5cumecoINADSUjNj+fLlcvr0abP78NzGH6X20lO1bU0tsDbgw7pI537llVcyNU3DCPsMqdgIlOzYsUP9uMb+OXTokKo9gUCNtdfHwAg/Yv/8809p0aKF2XIMWDMCAwx9LjOKcNoLASEM2PH5YuoMUt0BP86xDDU7jGnegNuYLmEJ7xuDZaQaY1605UA3MzKzfZmV0eME87ytHXMIKuFYwKAqq6+REZieA6iVkB4cc6gNgCko+oDKCEUGUedh586dVj9LHO/WvicA3xM6BNPw2Llz50q1atXUVB5r3zEZgYE5UvLxt4PPH8eC/rr4LsD3ij7dQIcBvrV9b22bHQ3Tz/TighMnTjRNEXAGfGb4DkItEwSQ3M3e48RZMPUKwV/8bWAaEbz11lvqWMBngikctujfK3qwjIjIGgYaiIjsYG1+MOhnO41F0/SzhrYKOOqDCWtn6/WibsYz8fpZrszQX8PWgBODeJzJxIAO2RcYCGIgb8wysFeZMmWs3q8HYPS6AXr2x8mTJ9OtrWBtH6EQWUZg0I2BI/aBvcEfZFogKKGfUbUGZ1At96utfYBaHChciYAAskuyOqDM7PZlVkaPE2Rb6DUlkDGC94sz7qh1YKvDhiOPRUt6Ng2yS9KjH6e2Chzic8Tnib9za5+lte8Ka98TGFSiDgL+vvFZIusBgTdk3ODMO+pJZASKJiLYl9bgz9pZf+xza4Efa9vsSCg4iGME+xA1TKzVvUC9F0AdA1uQgWLcXmuQQYX6JTguUWTTUX8XWWHvceIsOIY3bNigMlYQ/EOXJASi8P8fFMdFQA1BMGvHBjJuwN4ivESUMzHQQERkh4ycgdYLPNpK5cVZu4ULF6q2lc6mvwbOmFqDgozWClY6k959AQMcy2wFS9YG7pZp5o6G4o0Y6MHkyZPVVA1MR9CnwaCg5O7du80K+7mSO7Yvo8cJMgH09qrOeg13SitAlpHvig8++EBNOcJATx/04UwzPldcp1V00ggBJzwPshgwfQYBB/zt4JjAtqLYI4JT1o4JR2TXZBS2E2f0cSxjaoet7jt6UNFaMVk9yIDBLgKItgINaMOI6S74XkaXG0cErhzBHfvdGhQ3xgWZPChkiv9vvf/++6qIKArNWssC04PpCLoREdnCQAMRkYPpc73xY9oanMXDDzp0n8APNmd2nkCHBUhvTrwjYNBg7Sys3g6vePHiZmfyMHc9o4PRzMDrYMCFzwODkvR+HGPOeHx8vJrLb22gZ+xOYAn1OqxBbQK8NrYjqz/Os7J9ORXqpSBNH2dsH3jggTTX1Y9T/bi1hL9Z/bPM7PQoy21777331AXTfNA+E4NvfEegi4s9r4EABTJ30KFAb4XoqccEgiLoxoE2jpgugrPntgI3qHWBujjI0kAGBAJqRvv371fXtrI/sC/RAQQ1HtasWaOmq5Bt2E+oV4NjGzUc8P8oa4EGveYPuoEQEdniGeFUIiIvCzTgbD3Sta2l/GKggzP5WIbBorPgjBTmkePHY9euXcXZlixZkuo+DO7Xr19vqrugBxpwxhsDjX/++cfp24XUX/1MOdoMpkf/EW0ttRlF2my13QQM9jZu3Gh1wKMXHbSWimwJ0wsw6HT09uVUaCNp7+ePeiwYaOEML6b3WFqwYIG6xvHs6LPSmGaC+fFoR4lgkvH1AwMD1bW14yKtYwKp8PqA3BHS2o70YEoABrBoE4rvQGRZpPX3gM8BLSBh6dKlqZajYCzoNQYsA3II1GCfrlixwvT9kx1lZZ9nhp5JYmsKx99//62uGbghorQw0EBE5ARIRUVxPlvTIzDgwdxuVMNHGryxb7oxLTgj/eGNZ1xxVlPvj45OB64484TsCcx/1uFHMVJw8T4wN99YWwFdGDCF4vnnn7dauRwDdpzpdBR08kCwA3O1N2/ebLYM24lBiWVBNgwo9fnfgDOqeveAtCB4pHcWgTNnzsioUaPUv3F21R44q46AgbU50JndPnTzwD7Qp11kZwgc4b3YmxGDQBsyW3CGFtMSLKcQ/P7776Yiruhi0LlzZ3V84vMy7mMExj7++GNTccGswHGIQnz6VCLj8YKBHN6fMXCgZ1qcOHHC5jHx448/mtVowPHTpUsXU1FIR0hrO9KC70MURUUtCXw/Ylv1AXRaUL8BsN+NgRdMD/r6669VhhDeoxECrMjuwOeM7yVrhRezk8zu8/Sm7VirgYPPCX8jgIKo1iBQBA0bNnTY9hCR9+HUCSIiJ8C8eZyBQ7cDa2fSMOhGujM6SaAIF2o24Ewq5lXjhx4GjQgyIOsB6cK25q6jWKQ+2EJKMuYyI7iBs6F6S04U9XIFpNgiJRrVyosVK6ZaGmLQhB/Jlm0dMWf86NGjMnbsWPW+cWYMhfr0yvh47ygEhyrojoAfxCi8h3R0nCHFD2h0vcAPbXTAwJk7fVCPAoTVq1eXffv2qfnc+PzQ+g0DQ2wnaiCge4Q1KHiIfY/H4XUwwEOGAz5HnKlGqrg9sA1Tp05VHQLweqhLgTTyfv36ZXr79AGtrWKM2UlG3wuK/+HvEfsOwS+0c0TWAIqEYlCPs/74u9GnPY0bN04FH1A3AV0KcPwg4IBBMvY1ggzWzqJnBI47bAuCgHpXGwQJ0LEDxyOmUugDTMC2YxmKRWIqFAIiCJ7gOwDHM7qdYHsRdNC/L/D9g3WQRbBq1aosba8925EWfAcgswCw/rvvvmtXe1hko2CKENqJ4vjG+8TfGN4rvi9QsNByOhICm/hs0aYT9S+stQdG/QHLTC+018QUC9ALrSIbBH/XOrwHfL+5EgIl+A5A3Q50mcFxgUAUvg+MrVQzAq1jp0+frj5H1A3CtC88PzqzIKCmT+mxhH2Ozx/7HN81REQ2aUREpOArsUyZMmZ7Y/Pmzer+Tp06Wd1LuB/LsZ5RTEyMljdvXq1atWpp7t34+Hhtzpw52jPPPKMVL15cCwwM1HLlyqXdd999Wvv27bX58+er57LUsGFD9br6xdfXV71euXLltHbt2mnTp0/XoqKibL6u/njL7c4M/bnOnDmjzZ07V6tZs6YWHBysFShQQHvttde08+fP23zs1q1btRdeeEG994CAAPWYBx98UOvZs6daZs++zoht27Zpzz33nFa4cGH1esWKFdOaNm2qzZo1y2y9mzdvau+8845WtmxZLSgoSO3XAQMGaHfv3jV7vzr8G/dhWWRkpPbuu++aPs/KlStrn376qZaYmJjmvjOKjo5W+6BUqVKav7+/6bkzu33w7LPPqvuxD+yV0eNE/3sxbqujXyMpKUnLnz+/umBfZ8S///6rde/eXe03fDbh4eHaQw89pI0aNUq7fft2qs9g5MiR6m8Y+zgsLEyrX7++9v3331t9bnx32PpZZe175OTJk9pHH32k1atXTx2H2J4SJUqo43H58uVacnKy2XMkJCSo9cuXL6+OXcvvK3xPDBkyRKtYsaLaXhw7eK8RERE2/3asfefp8LeM5cOHD8/QdtiC5zF+Z9m6WB63xu3BZ4Xvx3z58mktW7bUdu7caXVde17H2ne6vp8ys3327r/0vsds7c9ff/1VHSuhoaGmbdGfI73/T1mD71d8h9SqVUsrWLCgejy+a3DcdOvWTbt06ZLVx+H7A+u+9957dr8WEeVMPviP7TAEERFlFs5WIgUVZ55xxtJb4ewpznAhe8FWS0Bvh5adOHuKM984i+yJGQA4Y44z3zgTnJ3hDDP+npBKP2TIEHdvDpHXfI9jelV6nV+Q8YBpbYcPH1aZVUREtrBGAxGRkwwaNEil/yMNm8idMC0AU0P0WhHZGaaIIGiS1RoJRJQxly9flu+++05NA2OQgYjSw0ADEZGTYL435tCi6BnO/hC5CzIAkMCIrhfZnV7ELiwszN2bQpSjTJgwQV3rBVGJiNLCqRNERJQlnDrh+VMniIiIiFyJgQYiIiIiIiIichhOnSAiIiIiIiIih2GggYiIiIiIiIgchoEGIiIiIiIiInIYBhqIiIiIiIiIyGEYaCAiIiIiIiIih2GggYiIiIiIiIgchoEGIiIiIiIiInIYBhqIiIiIiIiIyGEYaCAiIiIiIiIih2GggYiIiIiIiIgchoEGIiIiIiIiInIYBhqIiIiIiIiIyGEYaCAiIiIiIiIih2GggYiIiIiIiIgYaCAiIiIiIiIiz8OMBiIiIiIiIiJyGAYaiIiIiIiIiMhhGGggIiIiIiIiIodhoIGIiIiIiIiIHIaBBiIiIiIiIiJyGAYaiIiIiIiIiMhhGGggIiIiIiIiIodhoIGIiIiIiIiIxFH+D5dfhK+itpGKAAAAAElFTkSuQmCC","media_type":"image/png"}}]}]},"uuid":"b818abd5-0c31-467b-8544-2412a6d724c9","timestamp":"2026-10-30T03:51:02.847Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":87543,"dimensions":{"originalWidth":1050,"originalHeight":750,"displayWidth":1050,"displayHeight":750}}},"sourceToolAssistantUUID":"9b43f7b1-0755-40bd-851f-0050c35cd6b8","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}62{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"475914239cd80dc820415d933f7ce64316c97ed0e434e6815190c9aea053405b","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MStBC4QhZFeLADwfjBBCKR","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RP0013/out/figure1.png"}}]}}63{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"0e2aae56-896f-4a6d-9441-3ef45d358464","timestamp":"2026-10-30T03:51:02.852Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"ad155a1e-17f7-42e3-a7e4-815d7b0071cd","keep":18,"tail":["475914239cd80dc820415d933f7ce64316c97ed0e434e6815190c9aea053405b","63bad0a8a97e5762e775e43c3fafc5eacf4891d287982aadd0dc349465e87564"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"80bbe5e233d6dc96ed98c5dc3b9be3103d67d36ba71680d38e8bc2888c4b42fc"}64{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b818abd5-0c31-467b-8544-2412a6d724c9","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}65{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}66{"parentUuid":"b818abd5-0c31-467b-8544-2412a6d724c9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjxaZyxDiUtvaNcFTu8","type":"message","role":"assistant","content":[{"type":"text","text":"Good. Now the state files, report, and claims."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1125,"cache_read_input_tokens":21856,"output_tokens":1641,"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":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXjxaJ7RZjSEA34ZgpKp","requestRef":"0e2aae56-896f-4a6d-9441-3ef45d358464","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"42432a9b-c744-4f17-8b8a-be657c5bc474","timestamp":"2026-10-30T03:51:04.332Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}67{"parentUuid":"42432a9b-c744-4f17-8b8a-be657c5bc474","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjxaZyxDiUtvaNcFTu8","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QQUakXoQqccgzqjL7osT2n","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols |\n|---|---|---|---|\n| data/wb_indicators.csv | 6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0 | 2349 | 5 (iso3,name,year,gdp_pc_ppp,life_expectancy) |\n| data/wb_entities.csv | 06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d | 296 | 5 (iso3,name,region,income_level,lending_type) |\n| data/README.md | 76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a | – | – |\nHashes match data/README.md and bundle.json.\n\n- Years 2015–2023; 261 entities in indicators, of which 44 are Aggregates (396 rows) → 217 countries/economies, each with all 9 years (1953 rows).\n- No duplicate (iso3, year) rows; no duplicate iso3 in entities; every indicator iso3 exists in entities (35 entity-only aggregate codes absent from indicators — harmless).\n- Units: GDPpc PPP constant 2021 intl $ (range ~992 to ~139,541, all >0); LE in years.\n- Missing: gdp_pc_ppp 164 missing (all entities); life_expectancy 0 missing. Countries with both indicators: 199 each year 2015–2022, 197 in 2023 → analysis year 2023 (>=150).\n- 2023 missing GDP (20): American Samoa, British Virgin Islands, Channel Islands, Cuba, Eritrea, French Polynesia, Gibraltar, Guam, Isle of Man, DPRK, Liechtenstein, Monaco, New Caledonia, N. Mariana Islands, South Sudan, St. Martin, Syria, Venezuela, US Virgin Islands, Yemen.\n- Anomalies: CAF life expectancy series erratic (2019 31.5, 2022 18.8, 2023 57.4); PSE 2023 drop of 11.5 years (Gaza war); SSD 2015–2018 swings (SSD not in 2023 sample). CAF and PSE 2023 are in the sample; kept as reported, sensitivity run excluding them.\n- Parsing: read with keep_default_na=False so only empty cells are missing.\n- Information-availability: no input violates the rules; aggregates excluded per rule. No imputation.\nEOF\ncat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n1. Clean re-run: deleted results.json/figure1/table1/exclusions, re-ran analysis.py, results.json byte-identical (cmp) — PASS.\n2. CI contains estimate: 4.854 < 5.267 < 5.680 — PASS.\n3. effect_se > 0 (0.2107), baseline_metric > 0, model_metric > 0 — PASS.\n4. r_squared == pearson_r^2 (|diff|<1e-12) — PASS.\n5. model_metric^2 == (1-R²)·baseline_metric^2 (OLS identity) — PASS; model RMSE 3.59 < baseline 7.08.\n6. n_analysed (197) + n_excluded_missing (20) == 217 countries in 2023 — PASS.\n7. Exclusion ledger: 2349 − (396+1736+20) = 197 = n_analysed — PASS.\n8. table1 n_countries sum = 197 — PASS; 4 income levels.\n9. Analysis year rule: 2023 has 197 ≥150 complete countries and is the latest year — PASS.\n10. Magnitude: slope ~5.3 years per log point is in line with the known Preston-curve magnitude; robust to HC0–HC3 (SE 0.207–0.211), classical SE 0.222, leave-one-out β range [5.21, 5.33], dropping CAF/PSE β=5.23 — PASS.\n11. Figure inspected visually: scatter + OLS line, labelled axes — PASS.\nEOF\necho \"- 2026-10-29 P1: audit done (hashes match, 44 aggregates, analysis year 2023, 20 missing). P2/P3: baseline RMSE and OLS-HC3 implemented in analysis.py. P4: clean rerun identical; consistency checks pass.\" >> out/state/log.md","description":"Write audit and checks files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1125,"cache_read_input_tokens":21856,"output_tokens":1641,"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":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXjxaJ7RZjSEA34ZgpKp","requestRef":"0e2aae56-896f-4a6d-9441-3ef45d358464","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"37d0f5dc-c356-4e08-bab5-3167000bacd1","timestamp":"2026-10-30T03:51:18.157Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}68{"parentUuid":"37d0f5dc-c356-4e08-bab5-3167000bacd1","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QQUakXoQqccgzqjL7osT2n","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"34fcd3bb-6b54-486c-a68a-56c0cf04e6ff","timestamp":"2026-10-30T03:51:18.207Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"37d0f5dc-c356-4e08-bab5-3167000bacd1","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}69{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"e25c8a3dadbb641a72928e67f181a90c12cdb068bb880a7e8b8806331e2a830e","message":{"role":"assistant","content":[{"type":"text","text":"Good. Now the state files, report, and claims."},{"type":"tool_use","id":"toolu_01QQUakXoQqccgzqjL7osT2n","name":"Bash","input":{"command":"cat > out/state/data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols |\n|---|---|---|---|\n| data/wb_indicators.csv | 6823f02ed4c20fd12a54b8ca4454f85ba333f22337e2a9fc57c3cabccfdbfcd0 | 2349 | 5 (iso3,name,year,gdp_pc_ppp,life_expectancy) |\n| data/wb_entities.csv | 06af6aec15122fecea5be5eb21464c505188ecc135bc55104a40f20f65040f8d | 296 | 5 (iso3,name,region,income_level,lending_type) |\n| data/README.md | 76cb5af488d97339fb6319a5c9a7ba6ec98112ab6a0a8116e7bec6acd1f9f67a | – | – |\nHashes match data/README.md and bundle.json.\n\n- Years 2015–2023; 261 entities in indicators, of which 44 are Aggregates (396 rows) → 217 countries/economies, each with all 9 years (1953 rows).\n- No duplicate (iso3, year) rows; no duplicate iso3 in entities; every indicator iso3 exists in entities (35 entity-only aggregate codes absent from indicators — harmless).\n- Units: GDPpc PPP constant 2021 intl $ (range ~992 to ~139,541, all >0); LE in years.\n- Missing: gdp_pc_ppp 164 missing (all entities); life_expectancy 0 missing. Countries with both indicators: 199 each year 2015–2022, 197 in 2023 → analysis year 2023 (>=150).\n- 2023 missing GDP (20): American Samoa, British Virgin Islands, Channel Islands, Cuba, Eritrea, French Polynesia, Gibraltar, Guam, Isle of Man, DPRK, Liechtenstein, Monaco, New Caledonia, N. Mariana Islands, South Sudan, St. Martin, Syria, Venezuela, US Virgin Islands, Yemen.\n- Anomalies: CAF life expectancy series erratic (2019 31.5, 2022 18.8, 2023 57.4); PSE 2023 drop of 11.5 years (Gaza war); SSD 2015–2018 swings (SSD not in 2023 sample). CAF and PSE 2023 are in the sample; kept as reported, sensitivity run excluding them.\n- Parsing: read with keep_default_na=False so only empty cells are missing.\n- Information-availability: no input violates the rules; aggregates excluded per rule. No imputation.\nEOF\ncat > out/state/checks.md <<'EOF'\n# Verification checks (P4)\n1. Clean re-run: deleted results.json/figure1/table1/exclusions, re-ran analysis.py, results.json byte-identical (cmp) — PASS.\n2. CI contains estimate: 4.854 < 5.267 < 5.680 — PASS.\n3. effect_se > 0 (0.2107), baseline_metric > 0, model_metric > 0 — PASS.\n4. r_squared == pearson_r^2 (|diff|<1e-12) — PASS.\n5. model_metric^2 == (1-R²)·baseline_metric^2 (OLS identity) — PASS; model RMSE 3.59 < baseline 7.08.\n6. n_analysed (197) + n_excluded_missing (20) == 217 countries in 2023 — PASS.\n7. Exclusion ledger: 2349 − (396+1736+20) = 197 = n_analysed — PASS.\n8. table1 n_countries sum = 197 — PASS; 4 income levels.\n9. Analysis year rule: 2023 has 197 ≥150 complete countries and is the latest year — PASS.\n10. Magnitude: slope ~5.3 years per log point is in line with the known Preston-curve magnitude; robust to HC0–HC3 (SE 0.207–0.211), classical SE 0.222, leave-one-out β range [5.21, 5.33], dropping CAF/PSE β=5.23 — PASS.\n11. Figure inspected visually: scatter + OLS line, labelled axes — PASS.\nEOF\necho \"- 2026-10-29 P1: audit done (hashes match, 44 aggregates, analysis year 2023, 20 missing). P2/P3: baseline RMSE and OLS-HC3 implemented in analysis.py. P4: clean rerun identical; consistency checks pass.\" >> out/state/log.md","description":"Write audit and checks files"}}]}}70{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"9a5df8d9-636b-4428-9d1b-9f20d75952f0","timestamp":"2026-10-30T03:51:18.210Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"0e2aae56-896f-4a6d-9441-3ef45d358464","keep":20,"tail":["e25c8a3dadbb641a72928e67f181a90c12cdb068bb880a7e8b8806331e2a830e","0b178f4d5190d9f7f1820e61c08cdbd9edd5d463ae21ae74ce16cc1bdf57fad5"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"40cf884b9567a5ff938ab70ec0e321ca3d7e1fc6f12311d1ffaf90d4c3fa9654"}71{"parentUuid":"34fcd3bb-6b54-486c-a68a-56c0cf04e6ff","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjyiFNhffXRNn5nx8wF","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01HsAFvM4FuhVht7zktJUkjm","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\n \"P0\": {\"status\": \"passed\", \"checks\": [\"TASK.md read fully\", \"contract.md written\"], \"notes\": \"\"},\n \"P1\": {\"status\": \"passed\", \"checks\": [\"SHA-256 of inputs match README\", \"row/col counts, missingness, duplicates, anomalies recorded in data_audit.md\", \"exclusions.csv sums: 2349-2152=197\"], \"notes\": \"\"},\n \"P2\": {\"status\": \"passed\", \"checks\": [\"baseline_metric (mean-only RMSE) = 7.076 computed on analysed sample\"], \"notes\": \"\"},\n \"P3\": {\"status\": \"passed\", \"checks\": [\"analysis.py reads only data/, writes results/figure/table deterministically, seed 0 recorded\"], \"notes\": \"\"},\n \"P4\": {\"status\": \"running\", \"checks\": [\"clean re-run byte-identical\", \"consistency checks 1-11 in checks.md all PASS\"], \"notes\": \"\"},\n \"P5\": {\"status\": \"pending\", \"checks\": [], \"notes\": \"\"}\n}\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . ; ls out/state/gate_receipts","description":"Write phase ledger and 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":1656,"cache_read_input_tokens":22981,"output_tokens":492,"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":1656},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXjyi3DfP7Jh2y19sUEK","requestRef":"9a5df8d9-636b-4428-9d1b-9f20d75952f0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fe43e5ce-1c6a-4e00-9160-13730ca3e30d","timestamp":"2026-10-30T03:51:23.208Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}72{"parentUuid":"fe43e5ce-1c6a-4e00-9160-13730ca3e30d","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01HsAFvM4FuhVht7zktJUkjm","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — FAILED (10 of 40 checks failed)\n  [ok] file:out/results.json: present\n  [FAIL] file:out/report.md: missing or empty\n  [ok] file:out/analysis.py: present\n  [FAIL] file:out/claims.json: missing or empty\n  [ok] file:out/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:analysis_year: ok\n  [ok] key:n_excluded_missing: ok\n  [ok] key:baseline_metric: ok\n  [ok] key:model_metric: ok\n  [ok] key:pearson_r: ok\n  [ok] key:r_squared: ok\n  [ok] key:effect_estimate: ok\n  [ok] key:intercept: ok\n  [ok] key:effect_se: ok\n  [ok] key:effect_ci_low: ok\n  [ok] key:effect_ci_high: ok\n  [ok] key:conclusion: ok\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n  [ok] exclusion_ledger: 3 steps consistent\n  [ok] ci:effect_estimate: 4.854257477179233 <= 5.267173451958655 <= 5.6800894267380775\n  [ok] positive:effect_se: 0.21067528691162227\n  [ok] positive:baseline_metric: 7.07645404460588\n  [ok] positive:model_metric: 3.5949979094078177\n  [ok] reproducibility: regenerated in 1.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RP0013/out/state/gate_receipts/20261030T035124.455882Z.json\n20261030T035124.455882Z.json","is_error":false}]},"uuid":"6344fda8-d4e0-4a23-81aa-773616df3fda","timestamp":"2026-10-30T03:51:24.465Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — FAILED (10 of 40 checks failed)\n  [ok] file:out/results.json: present\n  [FAIL] file:out/report.md: missing or empty\n  [ok] file:out/analysis.py: present\n  [FAIL] file:out/claims.json: missing or empty\n  [ok] file:out/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:analysis_year: ok\n  [ok] key:n_excluded_missing: ok\n  [ok] key:baseline_metric: ok\n  [ok] key:model_metric: ok\n  [ok] key:pearson_r: ok\n  [ok] key:r_squared: ok\n  [ok] key:effect_estimate: ok\n  [ok] key:intercept: ok\n  [ok] key:effect_se: ok\n  [ok] key:effect_ci_low: ok\n  [ok] key:effect_ci_high: ok\n  [ok] key:conclusion: ok\n  [FAIL] section:Question: heading not found\n  [FAIL] section:Data and exclusions: heading not found\n  [FAIL] section:Method: heading not found\n  [FAIL] section:Results: heading not found\n  [FAIL] section:Uncertainty: heading not found\n  [FAIL] section:Limitations and open issues: heading not found\n  [FAIL] claims_json: out/claims.json missing\n  [FAIL] phase_ledger: phases not terminal: ['P4', 'P5']\n  [ok] exclusion_ledger: 3 steps consistent\n  [ok] ci:effect_estimate: 4.854257477179233 <= 5.267173451958655 <= 5.6800894267380775\n  [ok] positive:effect_se: 0.21067528691162227\n  [ok] positive:baseline_metric: 7.07645404460588\n  [ok] positive:model_metric: 3.5949979094078177\n  [ok] reproducibility: regenerated in 1.2s; identical within tolerance\nreceipt: /Users/simon-pierreboucher/wp29/runs/RP0013/out/state/gate_receipts/20261030T035124.455882Z.json\n20261030T035124.455882Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"fe43e5ce-1c6a-4e00-9160-13730ca3e30d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}73{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"442684c3133898907008230707041f593406c447e031954068033f00ea19ad9b","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01HsAFvM4FuhVht7zktJUkjm","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\n \"P0\": {\"status\": \"passed\", \"checks\": [\"TASK.md read fully\", \"contract.md written\"], \"notes\": \"\"},\n \"P1\": {\"status\": \"passed\", \"checks\": [\"SHA-256 of inputs match README\", \"row/col counts, missingness, duplicates, anomalies recorded in data_audit.md\", \"exclusions.csv sums: 2349-2152=197\"], \"notes\": \"\"},\n \"P2\": {\"status\": \"passed\", \"checks\": [\"baseline_metric (mean-only RMSE) = 7.076 computed on analysed sample\"], \"notes\": \"\"},\n \"P3\": {\"status\": \"passed\", \"checks\": [\"analysis.py reads only data/, writes results/figure/table deterministically, seed 0 recorded\"], \"notes\": \"\"},\n \"P4\": {\"status\": \"running\", \"checks\": [\"clean re-run byte-identical\", \"consistency checks 1-11 in checks.md all PASS\"], \"notes\": \"\"},\n \"P5\": {\"status\": \"pending\", \"checks\": [], \"notes\": \"\"}\n}\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . ; ls out/state/gate_receipts","description":"Write phase ledger and run gate"}}]}}74{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"560b43cb-1bf3-416a-bacb-717885f34275","timestamp":"2026-10-30T03:51:24.469Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"9a5df8d9-636b-4428-9d1b-9f20d75952f0","keep":22,"tail":["442684c3133898907008230707041f593406c447e031954068033f00ea19ad9b","bce392c10b7d5c74abda6dd29c26791faf988ba5aa28d758c79ab0ea412b235a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c61e0a3f849c612bb1cbd52307f3da9cd66805b7e2e41d28f77c97d58deda4d7"}75{"parentUuid":"6344fda8-d4e0-4a23-81aa-773616df3fda","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjzB5fX12Abyb1h9YwP","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":1368,"cache_read_input_tokens":24637,"output_tokens":3720,"output_tokens_details":{"thinking_tokens":140},"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":1368},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1466,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXjzAo43QbYVto4LCqs6","requestRef":"560b43cb-1bf3-416a-bacb-717885f34275","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e19f13ae-4d27-488c-be8d-2e80ac32cac2","timestamp":"2026-10-30T03:51:27.477Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}76{"parentUuid":"e19f13ae-4d27-488c-be8d-2e80ac32cac2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjzB5fX12Abyb1h9YwP","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"All of P4's own checks pass at the gate, so the remaining failures are P5 deliverables not yet written. I'm writing the report and claims ledger next.\n\n","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":1368,"cache_read_input_tokens":24637,"output_tokens":3720,"output_tokens_details":{"thinking_tokens":140},"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":1368},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1,"thinkingDisplay":"updates","apiBlockIndex":1,"requestId":"req_011CgXjzAo43QbYVto4LCqs6","requestRef":"560b43cb-1bf3-416a-bacb-717885f34275","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"69851edb-89ad-4ebe-b343-34ccca9a6ff9","timestamp":"2026-10-30T03:51:27.479Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}77{"parentUuid":"69851edb-89ad-4ebe-b343-34ccca9a6ff9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXjzB5fX12Abyb1h9YwP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BPKvH82ZED19JtQLAUCKiR","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-dev-01 — Preston curve in the latest usable World Bank year\n\n## Question\nDoes life expectancy at birth (LE) rise with the log of real income per capita across countries/economies in the latest usable WDI year, and how strong is that link? The estimand is the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i. Each country/economy counts once, with equal weight, and GDPpc is measured in PPP constant 2021 international $. The interpretation is descriptive (associational), not causal.\n\n## Data and exclusions\nInputs: `wb_indicators.csv` (2349 rows) and `wb_entities.csv` (296 rows) (`n_input_rows`). The SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). The exclusion ledger is in `out/exclusions.csv`:\n1. Dropped the 44 aggregate entities (region = `Aggregates`): 2349 → 1953 rows, i.e. 217 countries/economies × 9 years (`n_countries_in_population` = 217).\n2. Analysis year: the latest year with both indicators for ≥150 countries is **2023** (`analysis_year`). In 2023, 197 countries have both indicators; in 2015–2022 the count is 199 each year (`complete_countries_by_year`). This step leaves 217 rows.\n3. Dropped the countries missing an indicator in 2023: `n_excluded_missing` = 20. In every case the missing indicator was GDP; LE is never missing. This leaves `n_analysed` = 197. The 20 dropped are small territories (e.g. Monaco, Liechtenstein, Gibraltar, Guam) and conflict-affected or sanctioned economies (South Sudan, Syria, Yemen, Venezuela, DPRK, Cuba, Eritrea). No imputation was done.\n\nData issues and how they were handled are listed in `data_issues`. The Central African Republic's LE series is erratic (18.8 in 2022, 57.4 in 2023). The West Bank & Gaza value falls by 11.5 years in 2023. Both entities are in the 2023 sample and were kept as reported. A sensitivity run without them is reported below.\n\n## Method\n- Baseline: the mean-only prediction of LE, scored by RMSE over the 197 analysed countries (`baseline_metric`).\n- Main model: OLS of LE on ln(GDPpc) with equal weights, scored by the in-sample residual RMSE (`model_metric`). I also report the Pearson r and R².\n- Uncertainty: heteroskedasticity-robust **HC3** standard error (`effect_se`, `effect_se_type`), with a 95% CI from the t distribution with n−2 degrees of freedom. I chose HC3 because it is the most conservative of the HC variants in finite samples.\n- Conclusion code: `positive_effect` if the 95% CI lies above zero.\n- Everything is produced by `out/analysis.py` (statsmodels/numpy; no randomness; `random_seed` = 0 recorded). The script also writes `figure1.png` (scatter plus OLS line) and `table1.csv` (means by income level).\n\n## Results\n- The fitted line is LE = 22.57 + 5.267·ln(GDPpc) (`intercept`, `effect_estimate`). A 1-log-point (≈2.7×) higher GDP per capita goes with about 5.3 more years of life expectancy. A doubling of income goes with about 0.69 × 5.27 ≈ 3.65 years.\n- Pearson r = 0.861 (`pearson_r`) and R² = 0.742 (`r_squared`).\n- Residual RMSE is 3.59 years (`model_metric`), against 7.08 years for the mean-only baseline (`baseline_metric`). That is roughly half the prediction error.\n- `conclusion` = `positive_effect`: the Preston-curve gradient holds strongly in 2023.\n- Table 1 (`out/table1.csv`): mean LE rises steadily across income groups. It is 63.2 years in low-income countries (n=20), 67.8 in lower-middle (n=46), 73.7 in upper-middle (n=58) and 79.7 in high-income (n=73).\n- Figure 1 (`out/figure1.png`) shows the scatter and the fitted line.\n\n## Uncertainty\n- HC3 SE = 0.211 (`effect_se`); 95% CI [4.85, 5.68] (`effect_ci_low`, `effect_ci_high`), well away from zero.\n- The SE barely depends on the variant: HC0 0.207, HC1 0.208, HC2 0.209 and classical 0.222 (`sensitivity_se_HC0`, `sensitivity_se_HC1`, `sensitivity_se_HC2`, `sensitivity_se_classical`).\n- Leaving out any single country moves β only within [5.21, 5.33] (`sensitivity_beta_loo_min`, `sensitivity_beta_loo_max`).\n- Dropping the two entities with erratic LE series (CAF, PSE) gives β = 5.23 with n = 195 (`sensitivity_beta_drop_erratic_LE`, `sensitivity_n_drop_erratic_LE`).\n- The CI covers sampling-type uncertainty only. It does not cover measurement error in either indicator or model misspecification.\n\n## Limitations and open issues\n- **What would invalidate the result.**\n  - Systematic errors in the 2023 PPP GDP or LE estimates. Many 2023 LE values are model-based projections from the UN WPP, not vital registration. The CAF series shows how unstable they can be.\n  - Non-random missingness could also distort the slope. The 20 excluded economies include very rich microstates with high LE (e.g. Monaco, Liechtenstein) and poor conflict economies with low LE (e.g. South Sudan, Yemen). Their combined effect on β is unknown. I did not bound it, because no imputation was allowed.\n- **Functional form.** The figure suggests the relationship flattens or spreads out at high incomes. Some high-income economies have notably low LE: the highest-income ones are likely resource-rich economies with residual-heavy points, which I did not investigate. A single linear-in-log slope is a summary projection, not a structural curve. I did not test nonlinearity (splines, quadratic terms).\n- **Not checked.**\n  - Population weighting. The estimand is equally weighted, so microstates count as much as China or India.\n  - Stability across 2015–2022. Only the analysis year was estimated.\n  - Regional heterogeneity.\n  - The quality of GDP PPP for small or dollarised economies.\n- **Main threats.**\n  - Confounding by health systems, education, disease burden (HIV, malaria), conflict and inequality.\n  - Reverse causality: health raises income.\n  - Ecological fallacy: a cross-country slope says nothing about individual-level effects.\n  - The association must not be read as a causal effect of income.\n- **2023 specifics.** Post-COVID recovery and conflict shocks (e.g. Gaza) affect individual LE values. The leave-one-out and drop-erratic checks suggest these do not drive β.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\": \"C1\", \"text\": \"The analysis year is 2023; 197 countries/economies are analysed and 20 are excluded for missing GDP per capita.\", \"results_keys\": [\"analysis_year\", \"n_analysed\", \"n_excluded_missing\"], \"status\": \"supported\", \"caveat\": \"Excluded economies are non-randomly selected (microstates, conflict/sanctioned economies).\"},\n {\"id\": \"C2\", \"text\": \"In 2023, life expectancy rises by about 5.27 years per log-point of GDP per capita PPP (95% HC3 CI 4.85 to 5.68); the conclusion code is positive_effect.\", \"results_keys\": [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"intercept\"], \"status\": \"supported\", \"caveat\": \"Descriptive association only; not causal.\"},\n {\"id\": \"C3\", \"text\": \"ln(GDP per capita) explains about 74% of cross-country variance in life expectancy (r = 0.86) and halves the prediction RMSE from 7.08 to 3.59 years relative to the mean-only baseline.\", \"results_keys\": [\"r_squared\", \"pearson_r\", \"baseline_metric\", \"model_metric\"], \"status\": \"supported\", \"caveat\": \"In-sample fit; no out-of-sample validation.\"},\n {\"id\": \"C4\", \"text\": \"The slope estimate is robust to the choice of HC variant, to leaving out any single country, and to dropping entities with erratic life-expectancy series.\", \"results_keys\": [\"sensitivity_se_HC0\", \"sensitivity_se_HC1\", \"sensitivity_se_HC2\", \"sensitivity_se_classical\", \"sensitivity_beta_loo_min\", \"sensitivity_beta_loo_max\", \"sensitivity_beta_drop_erratic_LE\", \"sensitivity_n_drop_erratic_LE\"], \"status\": \"supported\", \"caveat\": \"Does not address functional-form misspecification, missing-data bias, or measurement error.\"}\n]\nEOF\n~/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 1 receipt out/state/gate_receipts/20261030T035124.455882Z.json: all P4-relevant checks ok (reproducibility, ci, positive, exclusion ledger); failures only for P5 deliverables not yet written')\np['P5']={'status':'passed','checks':['report.md with 6 sections written','claims.json written, all keys exist in results.json','final gate run (see receipt appended)'],'notes':''}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-29 P4 passed (gate run 1). P5: report and claims written; running final gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"","description":"Write report, claims, update ledger, run gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1368,"cache_read_input_tokens":24637,"output_tokens":3720,"output_tokens_details":{"thinking_tokens":140},"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":1368},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXjzAo43QbYVto4LCqs6","requestRef":"560b43cb-1bf3-416a-bacb-717885f34275","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e5a07d3d-07de-43e1-b265-0da38336b046","timestamp":"2026-10-30T03:51:56.912Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}78{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"e5a07d3d-07de-43e1-b265-0da38336b046","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}79{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}80{"parentUuid":"e5a07d3d-07de-43e1-b265-0da38336b046","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BPKvH82ZED19JtQLAUCKiR","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RP0013/out/state/gate_receipts/20261030T035158.231150Z.json","is_error":false}]},"uuid":"6816754f-ab18-41b2-8314-23d0b1b9d93d","timestamp":"2026-10-30T03:51:58.240Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RP0013/out/state/gate_receipts/20261030T035158.231150Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e5a07d3d-07de-43e1-b265-0da38336b046","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}81{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"3ae0cc20398ef97aea62611899fde013b448a2e865f319c61fa1c111fdbeed0c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"thinking","thinking":"All of P4's own checks pass at the gate, so the remaining failures are P5 deliverables not yet written. I'm writing the report and claims ledger next.\n\n","signature":"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"},{"type":"tool_use","id":"toolu_01BPKvH82ZED19JtQLAUCKiR","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# F6-dev-01 — Preston curve in the latest usable World Bank year\n\n## Question\nDoes life expectancy at birth (LE) rise with the log of real income per capita across countries/economies in the latest usable WDI year, and how strong is that link? The estimand is the slope β of the linear projection LE_i = α + β·ln(GDPpc_i) + ε_i. Each country/economy counts once, with equal weight, and GDPpc is measured in PPP constant 2021 international $. The interpretation is descriptive (associational), not causal.\n\n## Data and exclusions\nInputs: `wb_indicators.csv` (2349 rows) and `wb_entities.csv` (296 rows) (`n_input_rows`). The SHA-256 hashes match `data/README.md` (see `out/state/data_audit.md`). The exclusion ledger is in `out/exclusions.csv`:\n1. Dropped the 44 aggregate entities (region = `Aggregates`): 2349 → 1953 rows, i.e. 217 countries/economies × 9 years (`n_countries_in_population` = 217).\n2. Analysis year: the latest year with both indicators for ≥150 countries is **2023** (`analysis_year`). In 2023, 197 countries have both indicators; in 2015–2022 the count is 199 each year (`complete_countries_by_year`). This step leaves 217 rows.\n3. Dropped the countries missing an indicator in 2023: `n_excluded_missing` = 20. In every case the missing indicator was GDP; LE is never missing. This leaves `n_analysed` = 197. The 20 dropped are small territories (e.g. Monaco, Liechtenstein, Gibraltar, Guam) and conflict-affected or sanctioned economies (South Sudan, Syria, Yemen, Venezuela, DPRK, Cuba, Eritrea). No imputation was done.\n\nData issues and how they were handled are listed in `data_issues`. The Central African Republic's LE series is erratic (18.8 in 2022, 57.4 in 2023). The West Bank & Gaza value falls by 11.5 years in 2023. Both entities are in the 2023 sample and were kept as reported. A sensitivity run without them is reported below.\n\n## Method\n- Baseline: the mean-only prediction of LE, scored by RMSE over the 197 analysed countries (`baseline_metric`).\n- Main model: OLS of LE on ln(GDPpc) with equal weights, scored by the in-sample residual RMSE (`model_metric`). I also report the Pearson r and R².\n- Uncertainty: heteroskedasticity-robust **HC3** standard error (`effect_se`, `effect_se_type`), with a 95% CI from the t distribution with n−2 degrees of freedom. I chose HC3 because it is the most conservative of the HC variants in finite samples.\n- Conclusion code: `positive_effect` if the 95% CI lies above zero.\n- Everything is produced by `out/analysis.py` (statsmodels/numpy; no randomness; `random_seed` = 0 recorded). The script also writes `figure1.png` (scatter plus OLS line) and `table1.csv` (means by income level).\n\n## Results\n- The fitted line is LE = 22.57 + 5.267·ln(GDPpc) (`intercept`, `effect_estimate`). A 1-log-point (≈2.7×) higher GDP per capita goes with about 5.3 more years of life expectancy. A doubling of income goes with about 0.69 × 5.27 ≈ 3.65 years.\n- Pearson r = 0.861 (`pearson_r`) and R² = 0.742 (`r_squared`).\n- Residual RMSE is 3.59 years (`model_metric`), against 7.08 years for the mean-only baseline (`baseline_metric`). That is roughly half the prediction error.\n- `conclusion` = `positive_effect`: the Preston-curve gradient holds strongly in 2023.\n- Table 1 (`out/table1.csv`): mean LE rises steadily across income groups. It is 63.2 years in low-income countries (n=20), 67.8 in lower-middle (n=46), 73.7 in upper-middle (n=58) and 79.7 in high-income (n=73).\n- Figure 1 (`out/figure1.png`) shows the scatter and the fitted line.\n\n## Uncertainty\n- HC3 SE = 0.211 (`effect_se`); 95% CI [4.85, 5.68] (`effect_ci_low`, `effect_ci_high`), well away from zero.\n- The SE barely depends on the variant: HC0 0.207, HC1 0.208, HC2 0.209 and classical 0.222 (`sensitivity_se_HC0`, `sensitivity_se_HC1`, `sensitivity_se_HC2`, `sensitivity_se_classical`).\n- Leaving out any single country moves β only within [5.21, 5.33] (`sensitivity_beta_loo_min`, `sensitivity_beta_loo_max`).\n- Dropping the two entities with erratic LE series (CAF, PSE) gives β = 5.23 with n = 195 (`sensitivity_beta_drop_erratic_LE`, `sensitivity_n_drop_erratic_LE`).\n- The CI covers sampling-type uncertainty only. It does not cover measurement error in either indicator or model misspecification.\n\n## Limitations and open issues\n- **What would invalidate the result.**\n  - Systematic errors in the 2023 PPP GDP or LE estimates. Many 2023 LE values are model-based projections from the UN WPP, not vital registration. The CAF series shows how unstable they can be.\n  - Non-random missingness could also distort the slope. The 20 excluded economies include very rich microstates with high LE (e.g. Monaco, Liechtenstein) and poor conflict economies with low LE (e.g. South Sudan, Yemen). Their combined effect on β is unknown. I did not bound it, because no imputation was allowed.\n- **Functional form.** The figure suggests the relationship flattens or spreads out at high incomes. Some high-income economies have notably low LE: the highest-income ones are likely resource-rich economies with residual-heavy points, which I did not investigate. A single linear-in-log slope is a summary projection, not a structural curve. I did not test nonlinearity (splines, quadratic terms).\n- **Not checked.**\n  - Population weighting. The estimand is equally weighted, so microstates count as much as China or India.\n  - Stability across 2015–2022. Only the analysis year was estimated.\n  - Regional heterogeneity.\n  - The quality of GDP PPP for small or dollarised economies.\n- **Main threats.**\n  - Confounding by health systems, education, disease burden (HIV, malaria), conflict and inequality.\n  - Reverse causality: health raises income.\n  - Ecological fallacy: a cross-country slope says nothing about individual-level effects.\n  - The association must not be read as a causal effect of income.\n- **2023 specifics.** Post-COVID recovery and conflict shocks (e.g. Gaza) affect individual LE values. The leave-one-out and drop-erratic checks suggest these do not drive β.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\": \"C1\", \"text\": \"The analysis year is 2023; 197 countries/economies are analysed and 20 are excluded for missing GDP per capita.\", \"results_keys\": [\"analysis_year\", \"n_analysed\", \"n_excluded_missing\"], \"status\": \"supported\", \"caveat\": \"Excluded economies are non-randomly selected (microstates, conflict/sanctioned economies).\"},\n {\"id\": \"C2\", \"text\": \"In 2023, life expectancy rises by about 5.27 years per log-point of GDP per capita PPP (95% HC3 CI 4.85 to 5.68); the conclusion code is positive_effect.\", \"results_keys\": [\"effect_estimate\", \"effect_se\", \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"intercept\"], \"status\": \"supported\", \"caveat\": \"Descriptive association only; not causal.\"},\n {\"id\": \"C3\", \"text\": \"ln(GDP per capita) explains about 74% of cross-country variance in life expectancy (r = 0.86) and halves the prediction RMSE from 7.08 to 3.59 years relative to the mean-only baseline.\", \"results_keys\": [\"r_squared\", \"pearson_r\", \"baseline_metric\", \"model_metric\"], \"status\": \"supported\", \"caveat\": \"In-sample fit; no out-of-sample validation.\"},\n {\"id\": \"C4\", \"text\": \"The slope estimate is robust to the choice of HC variant, to leaving out any single country, and to dropping entities with erratic life-expectancy series.\", \"results_keys\": [\"sensitivity_se_HC0\", \"sensitivity_se_HC1\", \"sensitivity_se_HC2\", \"sensitivity_se_classical\", \"sensitivity_beta_loo_min\", \"sensitivity_beta_loo_max\", \"sensitivity_beta_drop_erratic_LE\", \"sensitivity_n_drop_erratic_LE\"], \"status\": \"supported\", \"caveat\": \"Does not address functional-form misspecification, missing-data bias, or measurement error.\"}\n]\nEOF\n~/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 1 receipt out/state/gate_receipts/20261030T035124.455882Z.json: all P4-relevant checks ok (reproducibility, ci, positive, exclusion ledger); failures only for P5 deliverables not yet written')\np['P5']={'status':'passed','checks':['report.md with 6 sections written','claims.json written, all keys exist in results.json','final gate run (see receipt appended)'],'notes':''}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-29 P4 passed (gate run 1). P5: report and claims written; running final gate.\" >> out/state/log.md\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"","description":"Write report, claims, update ledger, run gate"}}]}}82{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"12ac0f61-903a-4dee-9179-e016d22d6e29","timestamp":"2026-10-30T03:51:58.243Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"560b43cb-1bf3-416a-bacb-717885f34275","keep":24,"tail":["3ae0cc20398ef97aea62611899fde013b448a2e865f319c61fa1c111fdbeed0c","1e25343d0b113a4184e9f3df348d57dbbd0158f7767f7488a4a7c69676a76514"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a93117324daa56138b57f43ff9ba817d4bca6d258d54a4623be46d1bf62657d3"}83{"parentUuid":"6816754f-ab18-41b2-8314-23d0b1b9d93d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXk2fQ4VTqYK7UatWrFn","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS+AcKEAgTGAI4AUIIdGhpbmtpbmcSDL86vf/hO6Zg62aPyRoMWrEcOSqVQjHeIpjSIjBozaZMvp6edVNjY6EglDg9GGnMObPs9lN4kwKpoQqegJEURuUeRf/peBo3mfxKY7AqlQfBdBCxEBGxeAngMyBN0chYBBEDZPNAp7XLMJPQjUCbhLfFgHCsFRBTGjs8LO7vKzYsn1iGFPPOzwf6gZzDd2xksWKXlwa/U2f4+UPGvcJOu83My8m4gyf53Arb88wtCK+8JKqLLFnhTPPbckT1f3IKDIBCXWHYJnbZa4dbY2EqS0/0IBwD925X7SJvoLS63Tk27yulwRplCGhFID5J/VkrWVuB1pCnlbagSwmQ/WJn2ZhbTn9RYRGrhQDkSto7/mWoKbBSIAnIIVnJCSstJ+IYt6bCF246vKZ8dVQV6BnPJPkaBXqEoTX0oEEj26K1o25c+qH8rUmhat4SxGr7bjuu7rhKHQmeaO09SzLMlLHNMffnTlnFRzIgUxo833ixbzQ6sigpHj5qfmnSyowDYE7TIm5vAnbhwrHirBJonTllIBdAtwIrgJzB5V5N7xiOjNOVgfjNUlgkwynXC2NDipsPiGNiaA0dIM9BoIZKXXHa23+48OdOw3kj5DZgZ/fleG8rJY9hprvPjuajP221Khas7XhyFYW+I10vypFjESHob81YIjuzz9KQMXWighoPcTGBafNJzSuHvypGV9Bsu94LUJ1/wlzB874HYMWGJ2cUxWP92/9dVzyjBSz6NKJzneLIWXXvoEa+tkAGQXEgw17hpmossG+tJvfBMgF6Dzz9qepowYJw7IshwW0fC9CNJPfRR2CLcSXdV4RdNEp7Soe6Ivii2EnW1/hu8ULEddO/cLnPEHlbOFy+3AiuLVGoqlVgLp5xjaQb1JxNHQNzKKRIAaPhiKFrNwGGIfuRLeyVNlHxoN0kXm21+sLXTReLmj7FTvLIcclu1S1fAAQ+tKM1QmkVdBI93rDhq5cOWJSXA+Xa1zlxYBKjAXkJZMV9TFRXxRe+4ayIs28D5Ura0fafz26rn7jqx27Gp0UM/ingPd4h7ASa2/Qr8hOcfFTtWTwT433L8vYcs8lJAS5pNS9sIDyZmI1zys32XpJYLca+E06rfGm2UthBm50eEkQYOfX8k4NzQZYTu0tW0h7eOlzuJhPimzwBhOz5FyqkLUwdU1evinRYdR6lQhvvQ89XulkA/rx+G2WheZUzynfnJGuB+NW1eOIiToXld+yP2tfY5oZ5jOwAsaTt2WzrGeDiJEyrhWGmpuKsNf9PIQHZcClYIn/EBIZOF/0SkO6/a/SiWEoNxeGpiZvw1HIY8pLIvy64fM/TKhgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3815,"cache_read_input_tokens":26005,"output_tokens":584,"output_tokens_details":{"thinking_tokens":83},"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":3815},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1149,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXk2f7gnNoSNqxDzpHNi","requestRef":"12ac0f61-903a-4dee-9179-e016d22d6e29","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4a044fe9-2713-4f4c-bd12-14ee328ac34b","timestamp":"2026-10-30T03:52:01.650Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}84{"parentUuid":"4a044fe9-2713-4f4c-bd12-14ee328ac34b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXk2fQ4VTqYK7UatWrFn","type":"message","role":"assistant","content":[{"type":"text","text":"The gate passes. One sentence in the report guesses which countries the low-LE high-income points are, and I didn't check that, so I'm cutting the guess before the final gate run."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3815,"cache_read_input_tokens":26005,"output_tokens":584,"output_tokens_details":{"thinking_tokens":83},"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":3815},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXk2f7gnNoSNqxDzpHNi","requestRef":"12ac0f61-903a-4dee-9179-e016d22d6e29","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"021da44a-dd30-4f84-82cd-e64eef7e958b","timestamp":"2026-10-30T03:52:01.650Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}85{"parentUuid":"021da44a-dd30-4f84-82cd-e64eef7e958b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXk2fQ4VTqYK7UatWrFn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SaqGoCAXqtFrv16TNNdTSn","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('report.md').read()\ns=s.replace(\"Some high-income economies have notably low LE: the highest-income ones are likely resource-rich economies with residual-heavy points, which I did not investigate.\",\"Several high-income economies have LE well below the fitted line. I did not identify or investigate these points.\")\nopen('report.md','w').write(s)\nimport json\np=json.load(open('state/phases.json'))\np['P5']['checks'][2]='final gate run receipt state/gate_receipts/20261030T035158.231150Z.json: PASSED 0/40 failed; re-run after report wording edit (see log)'\njson.dump(p,open('state/phases.json','w'),indent=1)\nEOF\ncd .. && ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"; echo \"- 2026-10-29 P5 passed; final gate PASSED after removing an unverified sentence from the report. Task complete.\" >> out/state/log.md","description":"Fix wording, update ledger, 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":3815,"cache_read_input_tokens":26005,"output_tokens":584,"output_tokens_details":{"thinking_tokens":83},"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":3815},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXk2f7gnNoSNqxDzpHNi","requestRef":"12ac0f61-903a-4dee-9179-e016d22d6e29","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d7673b4a-71a5-4f39-a3af-f0f9e0ae9074","timestamp":"2026-10-30T03:52:04.847Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"d7673b4a-71a5-4f39-a3af-f0f9e0ae9074","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01SaqGoCAXqtFrv16TNNdTSn","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RP0013/out/state/gate_receipts/20261030T035206.144438Z.json","is_error":false}]},"uuid":"f2b639d7-9e4b-41f3-910d-5a20ec5c73f2","timestamp":"2026-10-30T03:52:06.151Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)\nreceipt: /Users/simon-pierreboucher/wp29/runs/RP0013/out/state/gate_receipts/20261030T035206.144438Z.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d7673b4a-71a5-4f39-a3af-f0f9e0ae9074","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}87{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"42e9e2377485d13a367b91c2aa98ab97d3b2f062446da9696d252b9892c2445f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"The gate passes. One sentence in the report guesses which countries the low-LE high-income points are, and I didn't check that, so I'm cutting the guess before the final gate run."},{"type":"tool_use","id":"toolu_01SaqGoCAXqtFrv16TNNdTSn","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('report.md').read()\ns=s.replace(\"Some high-income economies have notably low LE: the highest-income ones are likely resource-rich economies with residual-heavy points, which I did not investigate.\",\"Several high-income economies have LE well below the fitted line. I did not identify or investigate these points.\")\nopen('report.md','w').write(s)\nimport json\np=json.load(open('state/phases.json'))\np['P5']['checks'][2]='final gate run receipt state/gate_receipts/20261030T035158.231150Z.json: PASSED 0/40 failed; re-run after report wording edit (see log)'\njson.dump(p,open('state/phases.json','w'),indent=1)\nEOF\ncd .. && ~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | grep -v \"\\[ok\\]\"; echo \"- 2026-10-29 P5 passed; final gate PASSED after removing an unverified sentence from the report. Task complete.\" >> out/state/log.md","description":"Fix wording, update ledger, rerun gate"}}]}}88{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"62bcaf09-bae6-4a92-b10c-cae677a9ecca","timestamp":"2026-10-30T03:52:06.154Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"12ac0f61-903a-4dee-9179-e016d22d6e29","keep":26,"tail":["42e9e2377485d13a367b91c2aa98ab97d3b2f062446da9696d252b9892c2445f","f3e93a1dc0411b51ed1da77b5efc8a7bd50a2155cf1081b4d47f92128b7f4685"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7e1b66a9b10d599a94a5e14699186879a88be5f349e9ed4c0f5907080976e0a8"}89{"parentUuid":"f2b639d7-9e4b-41f3-910d-5a20ec5c73f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXk3FHWg6rqsvhSni7TP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01NtMZUUdozJ8ueSATfBhqnY","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'].append('latest gate receipt out/state/gate_receipts/20261030T035206.144438Z.json: PASSED 0/40 failed')\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record final receipt and confirm gate"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":679,"cache_read_input_tokens":29820,"output_tokens":246,"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":679},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXk3F199fAAThL8YQNem","requestRef":"62bcaf09-bae6-4a92-b10c-cae677a9ecca","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"19dab8c7-b690-47ea-8dc1-f727765be4dc","timestamp":"2026-10-30T03:52:08.868Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}90{"parentUuid":"19dab8c7-b690-47ea-8dc1-f727765be4dc","isSidechain":false,"promptId":"fe2a4627-36b0-431b-8956-d03e16b9c1c0","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01NtMZUUdozJ8ueSATfBhqnY","type":"tool_result","content":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","is_error":false}]},"uuid":"005ad452-afdf-471a-ace7-8effa6df9c81","timestamp":"2026-10-30T03:52:10.143Z","toolUseResult":{"stdout":"PGAR GATE pgar_gate/1.0 — PASSED (0 of 40 checks failed)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"19dab8c7-b690-47ea-8dc1-f727765be4dc","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}91{"type":"api-request-blob","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","hash":"f2b23b03ea8ff4b91de0a58b6e323aa6599051819b573229a3e574897425ba6a","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01NtMZUUdozJ8ueSATfBhqnY","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']['checks'].append('latest gate receipt out/state/gate_receipts/20261030T035206.144438Z.json: PASSED 0/40 failed')\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\n~/wp29/venv/bin/python ~/wp29/gates/pgar_gate.py . | head -1","description":"Record final receipt and confirm gate"}}]}}92{"type":"api-request","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","id":"b4565895-7006-4747-8ff7-369fa8aa55e3","timestamp":"2026-10-30T03:52:10.147Z","version":"2.1.314","querySource":"sdk","shapeHash":"f5e83e4c32630f760ebde06a9b8a4760cbe8853b7713b87d34a804680b6ed05b","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":"62bcaf09-bae6-4a92-b10c-cae677a9ecca","keep":28,"tail":["f2b23b03ea8ff4b91de0a58b6e323aa6599051819b573229a3e574897425ba6a","44b707039bce3d45d2d2ca2f1e259f14a048a8b5fa1843a720a2120d244102c0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b2dfb11c754cd67dd06219f02b67c592c1b42097ead5a3456a8d9b943b5d593f"}93{"parentUuid":"005ad452-afdf-471a-ace7-8effa6df9c81","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXk3YLvMZ8yD33meddqs","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":286,"cache_read_input_tokens":30499,"output_tokens":889,"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":286},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":5788,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXk3Y25NADPwovhtSbpw","requestRef":"b4565895-7006-4747-8ff7-369fa8aa55e3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d5a1a2e5-86e5-4fbb-8c23-9f4643c09a11","timestamp":"2026-10-30T03:52:17.451Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}94{"parentUuid":"d5a1a2e5-86e5-4fbb-8c23-9f4643c09a11","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXk3YLvMZ8yD33meddqs","type":"message","role":"assistant","content":[{"type":"text","text":"The task is complete: the Preston curve holds strongly in the latest usable year, and the final gate run passed with 0 of 40 checks failed. Re-running `out/analysis.py` from scratch reproduces `results.json` exactly.\n\n**Main result (2023, 197 countries/economies):**\n- **Analysis year:** 2023 is the latest year with both indicators for at least 150 countries (197 in 2023; 199 in each year from 2015 to 2022).\n- **Exclusions:** 20 countries/economies were dropped for missing GDP per capita, with no imputation. Life expectancy is never missing in the file.\n- **Slope:** life expectancy rises by about 5.27 years per log-point of GDP per capita (intercept 22.57). That is about 3.65 more years for each doubling of income. The robust standard error (HC3) is 0.211 and the 95% interval is 4.85 to 5.68, so the conclusion code is `positive_effect`.\n- **Fit:** the correlation is 0.861 and income explains 74% of the variation across countries (R² = 0.742). Prediction error falls from 7.08 years with the mean-only baseline to 3.59 years.\n- **Robustness:** the slope barely changes under other standard-error variants (0.207–0.222), when any single country is left out (5.21 to 5.33), or when the two entities with erratic life-expectancy series (Central African Republic, West Bank & Gaza) are dropped (5.23).\n\n**Limitations (set out in the report):**\n- **Who is missing:** the 20 dropped economies are not random. They include rich microstates such as Monaco and Liechtenstein and poor conflict-affected economies such as South Sudan and Yemen. I did not estimate how their absence affects the slope.\n- **Data quality:** many 2023 life-expectancy figures are modelled estimates rather than counts. The Central African Republic series swings implausibly (18.8 years in 2022, 57.4 in 2023); its 2023 value is in the sample and was kept as reported.\n- **Not tested:** whether the relationship flattens at high incomes, population weighting (every country counts equally), and whether the slope is stable across 2015–2022.\n- **Not causal:** this is an association only. Other factors (health systems, disease, conflict) and reverse causation (health raising income) could drive it.\n\nFiles are in `out/`:\n- results.json\n- report.md\n- analysis.py\n- claims.json\n- figure1.png\n- table1.csv\n- exclusions.csv\n- state/ (contract, data audit, checks, log, phase ledger, gate receipts)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":286,"cache_read_input_tokens":30499,"output_tokens":889,"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":286},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXk3Y25NADPwovhtSbpw","requestRef":"b4565895-7006-4747-8ff7-369fa8aa55e3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"99b95800-1f1b-479b-8440-fbdd2d0220f1","timestamp":"2026-10-30T03:52:18.631Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RP0013","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","version":"2.1.314","gitBranch":"HEAD"}95{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"99b95800-1f1b-479b-8440-fbdd2d0220f1","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}96{"type":"atis-latch","atis":"","sessionId":"57602e14-17cc-47c9-884e-1967d9060309"}97{"type":"cost-state","sessionId":"57602e14-17cc-47c9-884e-1967d9060309","totalCostUSD":0.5061272,"totalAPIDuration":140709,"totalAPIDurationWithoutRetries":140703,"totalToolDuration":10142,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":151046,"startTime":1793332187592,"modelUsage":{"claude-opus-5-5":{"inputTokens":32,"outputTokens":15385,"thinkingTokens":1085,"cacheReadInputTokens":259471,"cacheCreationInputTokens":29281,"cacheCreationEphemeral5mInputTokens":29281,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.5061272}},"hasUnknownModelCost":false}98