{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:33:32.227Z","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","content":"Begin"}
{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:33:32.231Z","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":null,"isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":"Begin"},"uuid":"18469781-ce85-425e-b6c2-3f75598a1bbd","timestamp":"2026-10-30T05:33:32.234Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-shape","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","timestamp":"2026-10-30T05:33:32.244Z","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/RT0011\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md`.\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}}]}}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"811fdcd9-7438-41ff-8ec7-7bdb4bdc8970","timestamp":"2026-10-30T05:33:32.244Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"1eb2aed7cf7cfb6a89f04d5689af40427857ff6cb34a943ce11df4291b49e39e"}
{"parentUuid":"18469781-ce85-425e-b6c2-3f75598a1bbd","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"1dc58858-469a-4476-8e8f-fa5ac311a7eb","timestamp":"2026-10-30T05:33:32.238Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"1dc58858-469a-4476-8e8f-fa5ac311a7eb","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"edf23fe5-d17d-4473-a332-1616e1020c3d","timestamp":"2026-10-30T05:33:32.238Z","rendered":[{"content":"<system-reminder>\nToday's date is 2026-10-30.\n</system-reminder>"}],"renderedRole":"system","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"edf23fe5-d17d-4473-a332-1616e1020c3d","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":"8df5da3e-e240-4540-8f5d-ecb212b35f46","timestamp":"2026-10-30T05:33:32.238Z","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/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"tools-used","tools":["Bash"],"sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"8df5da3e-e240-4540-8f5d-ecb212b35f46","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsmuhnssaqio1pJmD9K","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01YYjqhYjaehRwEshBZifoMv","name":"Bash","input":{"command":"cat TASK.md; ls -R data | head -50","description":"Show task and data files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":730,"cache_read_input_tokens":1504,"output_tokens":89,"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":730},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsmuRB9BTcdVucZEFVg","requestRef":"811fdcd9-7438-41ff-8ec7-7bdb4bdc8970","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c65bb5da-2570-4316-b26e-1290514ba42f","timestamp":"2026-10-30T05:33:33.950Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"c65bb5da-2570-4316-b26e-1290514ba42f","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01YYjqhYjaehRwEshBZifoMv","type":"tool_result","content":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n  - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n  - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n  - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\nfirst_release.csv\nREADME.md\nRSAFS_current.csv\nUMCSENT.csv\nvintages\n\ndata/vintages:\nPAYEMS_vintage_2025-10-31.csv\nPAYEMS_vintage_2025-11-30.csv\nPAYEMS_vintage_2025-12-31.csv\nPAYEMS_vintage_2026-01-31.csv\nPAYEMS_vintage_2026-02-28.csv\nPAYEMS_vintage_2026-03-31.csv\nPAYEMS_vintage_2026-04-30.csv\nPAYEMS_vintage_2026-05-31.csv\nPAYEMS_vintage_2026-06-30.csv\nPAYEMS_vintage_2026-07-31.csv\nRSAFS_vintage_2025-10-31.csv\nRSAFS_vintage_2025-11-30.csv\nRSAFS_vintage_2025-12-31.csv\nRSAFS_vintage_2026-01-31.csv\nRSAFS_vintage_2026-02-28.csv\nRSAFS_vintage_2026-03-31.csv\nRSAFS_vintage_2026-04-30.csv\nRSAFS_vintage_2026-05-31.csv\nRSAFS_vintage_2026-06-30.csv\nRSAFS_vintage_2026-07-31.csv","is_error":false}]},"uuid":"f471c46b-e663-423c-a49f-97fe7ff9a983","timestamp":"2026-10-30T05:33:34.002Z","toolUseResult":{"stdout":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n  - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n  - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n  - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\nfirst_release.csv\nREADME.md\nRSAFS_current.csv\nUMCSENT.csv\nvintages\n\ndata/vintages:\nPAYEMS_vintage_2025-10-31.csv\nPAYEMS_vintage_2025-11-30.csv\nPAYEMS_vintage_2025-12-31.csv\nPAYEMS_vintage_2026-01-31.csv\nPAYEMS_vintage_2026-02-28.csv\nPAYEMS_vintage_2026-03-31.csv\nPAYEMS_vintage_2026-04-30.csv\nPAYEMS_vintage_2026-05-31.csv\nPAYEMS_vintage_2026-06-30.csv\nPAYEMS_vintage_2026-07-31.csv\nRSAFS_vintage_2025-10-31.csv\nRSAFS_vintage_2025-11-30.csv\nRSAFS_vintage_2025-12-31.csv\nRSAFS_vintage_2026-01-31.csv\nRSAFS_vintage_2026-02-28.csv\nRSAFS_vintage_2026-03-31.csv\nRSAFS_vintage_2026-04-30.csv\nRSAFS_vintage_2026-05-31.csv\nRSAFS_vintage_2026-06-30.csv\nRSAFS_vintage_2026-07-31.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c65bb5da-2570-4316-b26e-1290514ba42f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"86d81ab02256a41c6ec0bf9cfdc3a8dff1abbd339ee287e31225f1ba4575e573","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01YYjqhYjaehRwEshBZifoMv","name":"Bash","input":{"command":"cat TASK.md; ls -R data | head -50","description":"Show task and data files"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"005b111f-6db2-4770-ac03-bdda67706b9b","timestamp":"2026-10-30T05:33:34.006Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"811fdcd9-7438-41ff-8ec7-7bdb4bdc8970","keep":2,"tail":["86d81ab02256a41c6ec0bf9cfdc3a8dff1abbd339ee287e31225f1ba4575e573","a96f66075a0c7063e8873be3ab54a54662699d36f7b201b94a2f7815ddb10012"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f9076857645da96537836c3b0f0cd36bb4c21d39e0c15b7be6fe63d6d2c413a5"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f471c46b-e663-423c-a49f-97fe7ff9a983","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"f471c46b-e663-423c-a49f-97fe7ff9a983","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsn24nKDab29BBqWZ2n","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_016ZiPZz3jRr1hsPJhazWU7e","name":"Bash","input":{"command":"cd data; cat README.md; cat first_release.csv; for f in vintages/*; do echo $f $(wc -l <$f) $(head -1 $f) $(tail -2 $f|tr '\\n' ' '); done; tail -3 RSAFS_current.csv; tail -15 UMCSENT.csv; grep -c ',$' UMCSENT.csv; grep -n ',$\\|,\\.' vintages/* RSAFS_current.csv | head","description":"Inspect data files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4582,"cache_read_input_tokens":2234,"output_tokens":225,"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":4582},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXsn1nuaaDTPxNwuwGVV","requestRef":"005b111f-6db2-4770-ac03-bdda67706b9b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"86a7e234-13e2-483e-a257-880227d3e976","timestamp":"2026-10-30T05:33:36.260Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"86a7e234-13e2-483e-a257-880227d3e976","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_016ZiPZz3jRr1hsPJhazWU7e","type":"tool_result","content":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\ntarget_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\nvintages/PAYEMS_vintage_2025-10-31.csv 1041 observation_date,PAYEMS_20251031 2025-07-01,159518 2025-08-01,159540\nvintages/PAYEMS_vintage_2025-11-30.csv 1042 observation_date,PAYEMS_20251130 2025-08-01,159507 2025-09-01,159626\nvintages/PAYEMS_vintage_2025-12-31.csv 1044 observation_date,PAYEMS_20251231 2025-10-01,159488 2025-11-01,159552\nvintages/PAYEMS_vintage_2026-01-31.csv 1045 observation_date,PAYEMS_20260131 2025-11-01,159476 2025-12-01,159526\nvintages/PAYEMS_vintage_2026-02-28.csv 1046 observation_date,PAYEMS_20260228 2025-12-01,158497 2026-01-01,158627\nvintages/PAYEMS_vintage_2026-03-31.csv 1047 observation_date,PAYEMS_20260331 2026-01-01,158558 2026-02-01,158466\nvintages/PAYEMS_vintage_2026-04-30.csv 1048 observation_date,PAYEMS_20260430 2026-02-01,158459 2026-03-01,158637\nvintages/PAYEMS_vintage_2026-05-31.csv 1049 observation_date,PAYEMS_20260531 2026-03-01,158621 2026-04-01,158736\nvintages/PAYEMS_vintage_2026-06-30.csv 1050 observation_date,PAYEMS_20260630 2026-04-01,158829 2026-05-01,159001\nvintages/PAYEMS_vintage_2026-07-31.csv 1051 observation_date,PAYEMS_20260731 2026-05-01,158927 2026-06-01,158984\nvintages/RSAFS_vintage_2025-10-31.csv 405 observation_date,RSAFS_20251031 2025-07-01,727414 2025-08-01,732010\nvintages/RSAFS_vintage_2025-11-30.csv 406 observation_date,RSAFS_20251130 2025-08-01,732059 2025-09-01,733258\nvintages/RSAFS_vintage_2025-12-31.csv 407 observation_date,RSAFS_20251231 2025-09-01,732444 2025-10-01,732633\nvintages/RSAFS_vintage_2026-01-31.csv 408 observation_date,RSAFS_20260131 2025-10-01,731412 2025-11-01,735904\nvintages/RSAFS_vintage_2026-02-28.csv 409 observation_date,RSAFS_20260228 2025-11-01,735085 2025-12-01,734967\nvintages/RSAFS_vintage_2026-03-31.csv 410 observation_date,RSAFS_20260331 2025-12-01,734685 2026-01-01,733537\nvintages/RSAFS_vintage_2026-04-30.csv 412 observation_date,RSAFS_20260430 2026-02-01,739772 2026-03-01,752063\nvintages/RSAFS_vintage_2026-05-31.csv 413 observation_date,RSAFS_20260531 2026-03-01,753370 2026-04-01,757085\nvintages/RSAFS_vintage_2026-06-30.csv 414 observation_date,RSAFS_20260630 2026-04-01,757036 2026-05-01,763705\nvintages/RSAFS_vintage_2026-07-31.csv 415 observation_date,RSAFS_20260731 2026-05-01,766876 2026-06-01,768553\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n2025-07-01,61.7\n2025-08-01,58.2\n2025-09-01,55.1\n2025-10-01,53.6\n2025-11-01,51.0\n2025-12-01,52.9\n2026-01-01,56.4\n2026-02-01,56.6\n2026-03-01,53.3\n2026-04-01,49.8\n2026-05-01,44.8\n2026-06-01,49.5\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n210","is_error":false}]},"uuid":"6dc1fbf9-efa9-4985-a2ef-ed18b1318418","timestamp":"2026-10-30T05:33:36.394Z","toolUseResult":{"stdout":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\ntarget_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\nvintages/PAYEMS_vintage_2025-10-31.csv 1041 observation_date,PAYEMS_20251031 2025-07-01,159518 2025-08-01,159540\nvintages/PAYEMS_vintage_2025-11-30.csv 1042 observation_date,PAYEMS_20251130 2025-08-01,159507 2025-09-01,159626\nvintages/PAYEMS_vintage_2025-12-31.csv 1044 observation_date,PAYEMS_20251231 2025-10-01,159488 2025-11-01,159552\nvintages/PAYEMS_vintage_2026-01-31.csv 1045 observation_date,PAYEMS_20260131 2025-11-01,159476 2025-12-01,159526\nvintages/PAYEMS_vintage_2026-02-28.csv 1046 observation_date,PAYEMS_20260228 2025-12-01,158497 2026-01-01,158627\nvintages/PAYEMS_vintage_2026-03-31.csv 1047 observation_date,PAYEMS_20260331 2026-01-01,158558 2026-02-01,158466\nvintages/PAYEMS_vintage_2026-04-30.csv 1048 observation_date,PAYEMS_20260430 2026-02-01,158459 2026-03-01,158637\nvintages/PAYEMS_vintage_2026-05-31.csv 1049 observation_date,PAYEMS_20260531 2026-03-01,158621 2026-04-01,158736\nvintages/PAYEMS_vintage_2026-06-30.csv 1050 observation_date,PAYEMS_20260630 2026-04-01,158829 2026-05-01,159001\nvintages/PAYEMS_vintage_2026-07-31.csv 1051 observation_date,PAYEMS_20260731 2026-05-01,158927 2026-06-01,158984\nvintages/RSAFS_vintage_2025-10-31.csv 405 observation_date,RSAFS_20251031 2025-07-01,727414 2025-08-01,732010\nvintages/RSAFS_vintage_2025-11-30.csv 406 observation_date,RSAFS_20251130 2025-08-01,732059 2025-09-01,733258\nvintages/RSAFS_vintage_2025-12-31.csv 407 observation_date,RSAFS_20251231 2025-09-01,732444 2025-10-01,732633\nvintages/RSAFS_vintage_2026-01-31.csv 408 observation_date,RSAFS_20260131 2025-10-01,731412 2025-11-01,735904\nvintages/RSAFS_vintage_2026-02-28.csv 409 observation_date,RSAFS_20260228 2025-11-01,735085 2025-12-01,734967\nvintages/RSAFS_vintage_2026-03-31.csv 410 observation_date,RSAFS_20260331 2025-12-01,734685 2026-01-01,733537\nvintages/RSAFS_vintage_2026-04-30.csv 412 observation_date,RSAFS_20260430 2026-02-01,739772 2026-03-01,752063\nvintages/RSAFS_vintage_2026-05-31.csv 413 observation_date,RSAFS_20260531 2026-03-01,753370 2026-04-01,757085\nvintages/RSAFS_vintage_2026-06-30.csv 414 observation_date,RSAFS_20260630 2026-04-01,757036 2026-05-01,763705\nvintages/RSAFS_vintage_2026-07-31.csv 415 observation_date,RSAFS_20260731 2026-05-01,766876 2026-06-01,768553\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021\n2025-07-01,61.7\n2025-08-01,58.2\n2025-09-01,55.1\n2025-10-01,53.6\n2025-11-01,51.0\n2025-12-01,52.9\n2026-01-01,56.4\n2026-02-01,56.6\n2026-03-01,53.3\n2026-04-01,49.8\n2026-05-01,44.8\n2026-06-01,49.5\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n210","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"86a7e234-13e2-483e-a257-880227d3e976","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011/data","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"3e90782645e214235d2ceb35a14d988a17d32de5641df0ef21b603432f003b54","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_016ZiPZz3jRr1hsPJhazWU7e","name":"Bash","input":{"command":"cd data; cat README.md; cat first_release.csv; for f in vintages/*; do echo $f $(wc -l <$f) $(head -1 $f) $(tail -2 $f|tr '\\n' ' '); done; tail -3 RSAFS_current.csv; tail -15 UMCSENT.csv; grep -c ',$' UMCSENT.csv; grep -n ',$\\|,\\.' vintages/* RSAFS_current.csv | head","description":"Inspect data files"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"660a9b8c-ac51-4e4f-9990-556ef25970ec","timestamp":"2026-10-30T05:33:36.397Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"005b111f-6db2-4770-ac03-bdda67706b9b","keep":4,"tail":["3e90782645e214235d2ceb35a14d988a17d32de5641df0ef21b603432f003b54","37f471f812ec6b96814f66b4ffdfeb2267e81607b3d494eeec3929b11be49c05"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b8038faafa486932f81ce3328ea7d776eb42a72ce8a0366996f6ba00759b5150"}
{"parentUuid":"6dc1fbf9-efa9-4985-a2ef-ed18b1318418","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnCGwL6Ymey788hUuX","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":7250,"cache_read_input_tokens":6816,"output_tokens":1211,"output_tokens_details":{"thinking_tokens":849},"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":7250},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":8055,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsnC1KoeoyGzjZaiWCp","requestRef":"660a9b8c-ac51-4e4f-9990-556ef25970ec","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3fb8c44c-bbf5-482b-8f64-7a5b32b29095","timestamp":"2026-10-30T05:33:45.742Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011/data","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"3fb8c44c-bbf5-482b-8f64-7a5b32b29095","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnCGwL6Ymey788hUuX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WGNEYDwvV9Bm6hck66mpbY","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('vintages/*'))+['RSAFS_current.csv','UMCSENT.csv']:\n    d=pd.read_csv(f,parse_dates=['observation_date']);c=d.columns[1]\n    gaps=(d.observation_date.diff().dt.days>31).sum()\n    na=d[c].isna().sum(); dup=d.observation_date.duplicated().sum()\n    print(f,len(d),d.observation_date.min().date(),d.observation_date.max().date(),'na',na,'gaps',gaps,'dup',dup, d[c].dtype)\nd=pd.read_csv('UMCSENT.csv');print(d[d.UMCSENT.isna()].observation_date.max())\n\"","description":"Audit data for missing values and gaps"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7250,"cache_read_input_tokens":6816,"output_tokens":1211,"output_tokens_details":{"thinking_tokens":849},"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":7250},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsnC1KoeoyGzjZaiWCp","requestRef":"660a9b8c-ac51-4e4f-9990-556ef25970ec","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f493998d-9878-42ae-8e4a-376486636f4e","timestamp":"2026-10-30T05:33:48.283Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011/data","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f493998d-9878-42ae-8e4a-376486636f4e","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"f493998d-9878-42ae-8e4a-376486636f4e","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WGNEYDwvV9Bm6hck66mpbY","type":"tool_result","content":"(eval):cd:1: no such file or directory: data\nvintages/PAYEMS_vintage_2025-10-31.csv 1040 1939-01-01 2025-08-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2025-11-30.csv 1041 1939-01-01 2025-09-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2025-12-31.csv 1043 1939-01-01 2025-11-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-01-31.csv 1044 1939-01-01 2025-12-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-02-28.csv 1045 1939-01-01 2026-01-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-03-31.csv 1046 1939-01-01 2026-02-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-04-30.csv 1047 1939-01-01 2026-03-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-05-31.csv 1048 1939-01-01 2026-04-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-06-30.csv 1049 1939-01-01 2026-05-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-07-31.csv 1050 1939-01-01 2026-06-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2025-10-31.csv 404 1992-01-01 2025-08-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2025-11-30.csv 405 1992-01-01 2025-09-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2025-12-31.csv 406 1992-01-01 2025-10-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-01-31.csv 407 1992-01-01 2025-11-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-02-28.csv 408 1992-01-01 2025-12-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-03-31.csv 409 1992-01-01 2026-01-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-04-30.csv 411 1992-01-01 2026-03-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-05-31.csv 412 1992-01-01 2026-04-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-06-30.csv 413 1992-01-01 2026-05-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-07-31.csv 414 1992-01-01 2026-06-01 na 0 gaps 0 dup 0 int64\nRSAFS_current.csv 417 1992-01-01 2026-09-01 na 0 gaps 0 dup 0 int64\nUMCSENT.csv 887 1952-11-01 2026-09-01 na 210 gaps 0 dup 0 float64\n1977-12-01","is_error":false}]},"uuid":"e65ec13a-3024-45a0-866d-7cf156e33ae5","timestamp":"2026-10-30T05:33:48.518Z","toolUseResult":{"stdout":"(eval):cd:1: no such file or directory: data\nvintages/PAYEMS_vintage_2025-10-31.csv 1040 1939-01-01 2025-08-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2025-11-30.csv 1041 1939-01-01 2025-09-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2025-12-31.csv 1043 1939-01-01 2025-11-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-01-31.csv 1044 1939-01-01 2025-12-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-02-28.csv 1045 1939-01-01 2026-01-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-03-31.csv 1046 1939-01-01 2026-02-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-04-30.csv 1047 1939-01-01 2026-03-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-05-31.csv 1048 1939-01-01 2026-04-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-06-30.csv 1049 1939-01-01 2026-05-01 na 0 gaps 0 dup 0 int64\nvintages/PAYEMS_vintage_2026-07-31.csv 1050 1939-01-01 2026-06-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2025-10-31.csv 404 1992-01-01 2025-08-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2025-11-30.csv 405 1992-01-01 2025-09-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2025-12-31.csv 406 1992-01-01 2025-10-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-01-31.csv 407 1992-01-01 2025-11-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-02-28.csv 408 1992-01-01 2025-12-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-03-31.csv 409 1992-01-01 2026-01-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-04-30.csv 411 1992-01-01 2026-03-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-05-31.csv 412 1992-01-01 2026-04-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-06-30.csv 413 1992-01-01 2026-05-01 na 0 gaps 0 dup 0 int64\nvintages/RSAFS_vintage_2026-07-31.csv 414 1992-01-01 2026-06-01 na 0 gaps 0 dup 0 int64\nRSAFS_current.csv 417 1992-01-01 2026-09-01 na 0 gaps 0 dup 0 int64\nUMCSENT.csv 887 1952-11-01 2026-09-01 na 210 gaps 0 dup 0 float64\n1977-12-01","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f493998d-9878-42ae-8e4a-376486636f4e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011/data","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"23386d0141fac9d78bd703d50b9f89012a3501d6b256844bd5f3e8bcf8e17905","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WGNEYDwvV9Bm6hck66mpbY","name":"Bash","input":{"command":"cd data; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('vintages/*'))+['RSAFS_current.csv','UMCSENT.csv']:\n    d=pd.read_csv(f,parse_dates=['observation_date']);c=d.columns[1]\n    gaps=(d.observation_date.diff().dt.days>31).sum()\n    na=d[c].isna().sum(); dup=d.observation_date.duplicated().sum()\n    print(f,len(d),d.observation_date.min().date(),d.observation_date.max().date(),'na',na,'gaps',gaps,'dup',dup, d[c].dtype)\nd=pd.read_csv('UMCSENT.csv');print(d[d.UMCSENT.isna()].observation_date.max())\n\"","description":"Audit data for missing values and gaps"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"0b66ac60-f7b0-44a9-aeb1-211a26b0c641","timestamp":"2026-10-30T05:33:48.521Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"660a9b8c-ac51-4e4f-9990-556ef25970ec","keep":6,"tail":["23386d0141fac9d78bd703d50b9f89012a3501d6b256844bd5f3e8bcf8e17905","572d037561d0cebf14f9a5c5fb4e02c6bb165b6635d2e85b4609607ac8345e2c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d7360d7d3ba7d541f442ea5bf9524fec097d1961703c37f451e10fc3e2d74542"}
{"parentUuid":"e65ec13a-3024-45a0-866d-7cf156e33ae5","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXso6C6tf5PQrXxH15hX","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":2509,"cache_read_input_tokens":14066,"output_tokens":597,"output_tokens_details":{"thinking_tokens":245},"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":2509},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2350,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXso5tFYxdqcB1cEwdUd","requestRef":"0b66ac60-f7b0-44a9-aeb1-211a26b0c641","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7adf5c77-1a60-4d02-8d03-5248d59f768b","timestamp":"2026-10-30T05:33:51.891Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011/data","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"7adf5c77-1a60-4d02-8d03-5248d59f768b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXso6C6tf5PQrXxH15hX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01GB2xqLUHGVQ2zCEEopEgp5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nc=pd.read_csv('data/RSAFS_current.csv',index_col=0,parse_dates=True).RSAFS\nfr=pd.read_csv('data/first_release.csv',parse_dates=['target_month'],index_col=0)\ng=100*np.log(c/c.shift(12))\nx=fr.join(c.rename('cur')).join(g.rename('gcur'))\nx['rev_lvl%']=100*(x.cur/x.level_first_release-1)\nprint(x[['level_first_release','cur','rev_lvl%','yoy_first_release','gcur']].round(3))\nprint(c['2025-01':].to_string())\n\"","description":"Compare first release with current vintage"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2509,"cache_read_input_tokens":14066,"output_tokens":597,"output_tokens_details":{"thinking_tokens":245},"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":2509},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXso5tFYxdqcB1cEwdUd","requestRef":"0b66ac60-f7b0-44a9-aeb1-211a26b0c641","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4e20ab17-7989-4818-942e-e6a1bc34dd65","timestamp":"2026-10-30T05:33:54.478Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011/data","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"4e20ab17-7989-4818-942e-e6a1bc34dd65","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01GB2xqLUHGVQ2zCEEopEgp5","type":"tool_result","content":"              level_first_release     cur  rev_lvl%  yoy_first_release   gcur\ntarget_month                                                                 \n2024-06-01                 704324  666040    -5.436              2.253  0.235\n2024-07-01                 709668  673662    -5.074              2.630  1.536\n2024-08-01                 710773  670668    -5.642              2.109  0.454\n2024-09-01                 714358  676005    -5.369              1.722  0.729\n2024-10-01                 718867  681808    -5.155              2.809  2.074\n2024-11-01                 724609  685709    -5.368              3.726  2.853\n2024-12-01                 729191  691794    -5.129              3.847  3.655\n2025-01-01                 723853  687058    -5.083              4.111  3.927\n2025-02-01                 722708  683772    -5.388              3.059  2.841\n2025-03-01                 722025  694750    -3.778              4.791  4.478\n2025-04-01                 724131  695464    -3.959              5.027  4.501\n2025-05-01                 715417  685488    -4.183              3.236  2.635\n2025-06-01                 720106  691883    -3.919              3.848  3.807\n2025-07-01                 726283  698280    -3.856              3.842  3.589\n2025-08-01                 732010  700407    -4.317              4.878  4.339\n2025-09-01                 733258  700948    -4.406              4.174  3.623\n2025-10-01                 732633  700790    -4.346              3.410  2.746\n2025-11-01                 735904  705453    -4.138              3.278  2.839\n2025-12-01                 734967  706264    -3.905              2.399  2.070\n2026-01-01                 733537  701860    -4.318              3.107  2.132\n2026-02-01                 739772  707959    -4.300              3.886  3.476\n2026-03-01                 752063  719700    -4.303              3.893  3.528\n2026-04-01                 757085  723921    -4.380              4.758  4.010\n2026-05-01                 763705  731415    -4.228              6.650  6.485\n2026-06-01                 768553  732898    -4.639              6.503  5.759\n2026-07-01                 763602  729915    -4.412              4.888  4.431\n2026-08-01                 737763  739322     0.211              5.223  5.407\n2026-09-01                 745021  745021     0.000              6.098  6.098\nobservation_date\n2025-01-01    687058\n2025-02-01    683772\n2025-03-01    694750\n2025-04-01    695464\n2025-05-01    685488\n2025-06-01    691883\n2025-07-01    698280\n2025-08-01    700407\n2025-09-01    700948\n2025-10-01    700790\n2025-11-01    705453\n2025-12-01    706264\n2026-01-01    701860\n2026-02-01    707959\n2026-03-01    719700\n2026-04-01    723921\n2026-05-01    731415\n2026-06-01    732898\n2026-07-01    729915\n2026-08-01    739322\n2026-09-01    745021","is_error":false}]},"uuid":"7115a704-bb16-4744-99ff-d3e07bdcb781","timestamp":"2026-10-30T05:33:54.691Z","toolUseResult":{"stdout":"              level_first_release     cur  rev_lvl%  yoy_first_release   gcur\ntarget_month                                                                 \n2024-06-01                 704324  666040    -5.436              2.253  0.235\n2024-07-01                 709668  673662    -5.074              2.630  1.536\n2024-08-01                 710773  670668    -5.642              2.109  0.454\n2024-09-01                 714358  676005    -5.369              1.722  0.729\n2024-10-01                 718867  681808    -5.155              2.809  2.074\n2024-11-01                 724609  685709    -5.368              3.726  2.853\n2024-12-01                 729191  691794    -5.129              3.847  3.655\n2025-01-01                 723853  687058    -5.083              4.111  3.927\n2025-02-01                 722708  683772    -5.388              3.059  2.841\n2025-03-01                 722025  694750    -3.778              4.791  4.478\n2025-04-01                 724131  695464    -3.959              5.027  4.501\n2025-05-01                 715417  685488    -4.183              3.236  2.635\n2025-06-01                 720106  691883    -3.919              3.848  3.807\n2025-07-01                 726283  698280    -3.856              3.842  3.589\n2025-08-01                 732010  700407    -4.317              4.878  4.339\n2025-09-01                 733258  700948    -4.406              4.174  3.623\n2025-10-01                 732633  700790    -4.346              3.410  2.746\n2025-11-01                 735904  705453    -4.138              3.278  2.839\n2025-12-01                 734967  706264    -3.905              2.399  2.070\n2026-01-01                 733537  701860    -4.318              3.107  2.132\n2026-02-01                 739772  707959    -4.300              3.886  3.476\n2026-03-01                 752063  719700    -4.303              3.893  3.528\n2026-04-01                 757085  723921    -4.380              4.758  4.010\n2026-05-01                 763705  731415    -4.228              6.650  6.485\n2026-06-01                 768553  732898    -4.639              6.503  5.759\n2026-07-01                 763602  729915    -4.412              4.888  4.431\n2026-08-01                 737763  739322     0.211              5.223  5.407\n2026-09-01                 745021  745021     0.000              6.098  6.098\nobservation_date\n2025-01-01    687058\n2025-02-01    683772\n2025-03-01    694750\n2025-04-01    695464\n2025-05-01    685488\n2025-06-01    691883\n2025-07-01    698280\n2025-08-01    700407\n2025-09-01    700948\n2025-10-01    700790\n2025-11-01    705453\n2025-12-01    706264\n2026-01-01    701860\n2026-02-01    707959\n2026-03-01    719700\n2026-04-01    723921\n2026-05-01    731415\n2026-06-01    732898\n2026-07-01    729915\n2026-08-01    739322\n2026-09-01    745021","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4e20ab17-7989-4818-942e-e6a1bc34dd65","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"c516e1b54688a4d1be330e0e3e0054747e61b4e211f61603c8c275f6c0695131","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01GB2xqLUHGVQ2zCEEopEgp5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nc=pd.read_csv('data/RSAFS_current.csv',index_col=0,parse_dates=True).RSAFS\nfr=pd.read_csv('data/first_release.csv',parse_dates=['target_month'],index_col=0)\ng=100*np.log(c/c.shift(12))\nx=fr.join(c.rename('cur')).join(g.rename('gcur'))\nx['rev_lvl%']=100*(x.cur/x.level_first_release-1)\nprint(x[['level_first_release','cur','rev_lvl%','yoy_first_release','gcur']].round(3))\nprint(c['2025-01':].to_string())\n\"","description":"Compare first release with current vintage"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"0181b1f5-e4e7-47ba-8f22-71c66d6e7391","timestamp":"2026-10-30T05:33:54.694Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"0b66ac60-f7b0-44a9-aeb1-211a26b0c641","keep":8,"tail":["c516e1b54688a4d1be330e0e3e0054747e61b4e211f61603c8c275f6c0695131","71c851b81ccc0cf443c36ed79ffb4a7b900e80b44f3de12d8cf95093b8677927"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5a7e251164c8826584f60f30a898bf2eedd5e8624972aa84c8fdf906e81814fd"}
{"parentUuid":"7115a704-bb16-4744-99ff-d3e07bdcb781","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoYWdgMuoqfBj3YNa3","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":1609,"cache_read_input_tokens":16575,"output_tokens":5707,"output_tokens_details":{"thinking_tokens":698},"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":1609},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6737,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsoYF23pWvtaWcJ7954","requestRef":"0181b1f5-e4e7-47ba-8f22-71c66d6e7391","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6f00d44d-1023-4d28-9bdb-2a177701dad0","timestamp":"2026-10-30T05:34:02.499Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"6f00d44d-1023-4d28-9bdb-2a177701dad0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoYWdgMuoqfBj3YNa3","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01LnuDKd2bEXjZBSXT4sunkP","name":"Bash","input":{"command":"mkdir -p out; cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nRegenerates out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png from data/ only.\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import norm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nD, O = \"data\", \"out\"\nos.makedirs(O, exist_ok=True)\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nSEED = 20261030\nn_rows = {}\n\n\ndef read(rel):\n    df = pd.read_csv(os.path.join(D, rel), parse_dates=[\"observation_date\"]).set_index(\"observation_date\")\n    n_rows[rel] = len(df)\n    s = df.iloc[:, 0].astype(float)\n    assert s.index.is_monotonic_increasing and not s.index.duplicated().any()\n    return s\n\n\ndef yoy(level):\n    return 100 * np.log(level / level.shift(12))\n\n\nfr = pd.read_csv(os.path.join(D, \"first_release.csv\"), parse_dates=[\"target_month\", \"first_release_vintage\"])\nn_rows[\"first_release.csv\"] = len(fr)\nactual = fr.set_index(\"target_month\")[\"yoy_first_release\"]\n\ndata_issues = []\nrows = []\nlast_months = {}\nfor V in ORIGINS:\n    L = read(f\"vintages/RSAFS_vintage_{V}.csv\")\n    P = read(f\"vintages/PAYEMS_vintage_{V}.csv\")  # read for audit only; not used by the chosen model\n    assert L.isna().sum() == 0 and (L.index.to_series().diff().dt.days.dropna() <= 31).all()\n    g = yoy(L)\n    last = L.index[-1]\n    last_months[V] = last\n    # AR(1) on g_m, 1993-02 <= m <= last\n    y = g.loc[\"1993-02-01\":last]\n    x = g.shift(1).loc[\"1993-02-01\":last]\n    X = np.column_stack([np.ones(len(y)), x.values])\n    a, b = np.linalg.lstsq(X, y.values, rcond=None)[0]\n    lnL = np.log(L)\n    mu = (lnL.loc[last] - lnL.loc[last - pd.DateOffset(months=12)]) / 12  # mean monthly log growth, last 12 months\n    for h in HORIZONS:\n        T = last + pd.DateOffset(months=h)\n        f_naive = g.loc[last]\n        f_snaive = g.loc[T - pd.DateOffset(months=12)]\n        f = g.loc[last]\n        for _ in range(h):\n            f = a + b * f\n        f_ar1 = f\n        # Model: base-effect-aware drift. Forecast the level by extrapolating the last published level with the\n        # trailing-12-month mean monthly log growth, then divide by the (already published) base-period level.\n        f_model = 100 * (lnL.loc[last] + h * mu - lnL.loc[T - pd.DateOffset(months=12)])\n        for m, fc in [(\"naive\", f_naive), (\"snaive\", f_snaive), (\"ar1\", f_ar1), (\"model\", f_model)]:\n            rows.append(dict(origin_date=V, target_date=T.strftime(\"%Y-%m-%d\"), horizon=h, forecast=round(float(fc), 6),\n                             actual_first_release=float(actual.loc[T]), model=m, vintage_used=V))\n\nfc = pd.DataFrame(rows)\nfc.to_csv(os.path.join(O, \"forecasts.csv\"), index=False)\nfc[\"err\"] = fc.actual_first_release - fc.forecast\n\n# publication-timing audit\nfor V in ORIGINS:\n    lag = (pd.Timestamp(V).year - last_months[V].year) * 12 + pd.Timestamp(V).month - last_months[V].month\n    if lag != 1:\n        data_issues.append({\"issue\": f\"Irregular publication timing: RSAFS vintage {V} ends at {last_months[V]:%Y-%m} ({lag} months before the origin month).\",\n                            \"handling\": \"Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.\"})\nlm = pd.Series(last_months)\nadded = (lm.dt.year * 12 + lm.dt.month).diff()\nfor V, k in added.items():\n    if k == 2:\n        data_issues.append({\"issue\": f\"Vintage {V} adds two new months at once (catch-up after delayed release); the month {lm[V] - pd.DateOffset(months=1):%Y-%m} is never an h=1 target and its first release is in the same vintage as the following month.\",\n                            \"handling\": \"No adjustment; targets follow last(V)+h. Horizon-1 targets therefore skip one month and h=3 targets skip one month, so the 10 origins are not equally spaced in target time.\"})\n\ntable = []\nfor m in [\"naive\", \"snaive\", \"ar1\", \"model\"]:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)].err.values\n        table.append(dict(model=m, horizon=h, rmse=float(np.sqrt(np.mean(e ** 2))), mae=float(np.mean(np.abs(e))), n=len(e)))\ntab = pd.DataFrame(table)\ntab.to_csv(os.path.join(O, \"table1.csv\"), index=False)\n\n\ndef nw_lrv(d, L):\n    d = d - d.mean()\n    n = len(d)\n    v = np.sum(d * d) / n\n    for l in range(1, L + 1):\n        v += 2 * (1 - l / (L + 1)) * np.sum(d[l:] * d[:-l]) / n\n    return v\n\n\nres = dict(task_id=\"T1-forecast\",\n           model_name=\"Base-effect drift (trailing-12m mean growth level extrapolation)\",\n           model_description=(\n               \"At origin V, using only the RSAFS vintage dated V: let last = last month in the vintage and \"\n               \"mu = (ln L_last - ln L_{last-12})/12, the mean monthly log growth over the last 12 published months. \"\n               \"The level of target month T = last+h is forecast as ln L_T = ln L_last + h*mu, and the YoY forecast is \"\n               \"100*(ln L_last + h*mu - ln L_{T-12}), where L_{T-12} is the base-period level already published in the same vintage. \"\n               \"Equivalently: naive forecast + h*g_last/12 - 100*(ln L_{T-12} - ln L_{last-12}), i.e. it corrects the naive forecast \"\n               \"for known base effects (the months dropping out of the 12-month window). No parameters are estimated; \"\n               \"PAYEMS and UMCSENT are not used (specification fixed a priori, before any evaluation against actuals). \"\n               \"All inputs are from vintage V, so the availability rule holds trivially.\"),\n           n_origins=len(ORIGINS), first_origin=ORIGINS[0], last_origin=ORIGINS[-1])\nfor r in table:\n    res[f\"rmse_{r['model']}_h{r['horizon']}\"] = r[\"rmse\"]\n    res[f\"mae_{r['model']}_h{r['horizon']}\"] = r[\"mae\"]\n\nrng = np.random.default_rng(SEED)\nboot = {}\nfor h in HORIZONS:\n    en = fc[(fc.model == \"naive\") & (fc.horizon == h)].sort_values(\"origin_date\").err.values\n    em = fc[(fc.model == \"model\") & (fc.horizon == h)].sort_values(\"origin_date\").err.values\n    res[f\"rel_improvement_rmse_h{h}\"] = 1 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    d = en ** 2 - em ** 2\n    n = len(d)\n    lrv = nw_lrv(d, h - 1)\n    dm = d.mean() / np.sqrt(lrv / n)\n    p = 2 * (1 - norm.cdf(abs(dm)))\n    res[f\"dm_stat_h{h}\"] = float(dm)\n    res[f\"dm_pvalue_h{h}\"] = float(p)\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{'significant' if p < 0.05 else 'not_significant'}\"\n    # supplementary: HLN-adjusted DM with t(n-1), and moving-block bootstrap (block 3) of RMSE_naive - RMSE_model\n    k = np.sqrt((n + 1 - 2 * h + h * (h - 1) / n) / n)\n    hln = dm * k\n    B, bl = 10000, 3\n    diffs = []\n    for _ in range(B):\n        starts = rng.integers(0, n - bl + 1, size=int(np.ceil(n / bl)))\n        idx = np.concatenate([np.arange(s, s + bl) for s in starts])[:n]\n        diffs.append(np.sqrt(np.mean(en[idx] ** 2)) - np.sqrt(np.mean(em[idx] ** 2)))\n    diffs = np.array(diffs)\n    from scipy.stats import t as tdist\n    boot[h] = dict(hln_stat=float(hln), hln_p=float(2 * (1 - tdist.cdf(abs(hln), n - 1))),\n                   rmse_diff=float(res[f\"rmse_naive_h{h}\"] - res[f\"rmse_model_h{h}\"]),\n                   boot_ci95=[float(np.percentile(diffs, 2.5)), float(np.percentile(diffs, 97.5))],\n                   wins_model=int(np.sum(np.abs(em) < np.abs(en))), n=n)\n\n# (d) revision of h=1 targets\ncur = read(\"RSAFS_current.csv\")\ngcur = yoy(cur)\nt1 = pd.to_datetime(fc[(fc.horizon == 1) & (fc.model == \"naive\")].target_date)\nrevs = np.abs(gcur.loc[t1].values - actual.loc[t1].values)\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(revs))\nlvl_rev = 100 * (cur.loc[fr.target_month].values / fr.level_first_release.values - 1)\ndata_issues.append({\"issue\": f\"Large level revision: current RSAFS levels for 2024-06..2026-07 are {lvl_rev[:-2].min():.1f}% to {lvl_rev[:-2].max():.1f}% below their first-release levels (a benchmark/annual revision between the 2026-08-31 and 2026-09-30 releases shifted the whole level); YoY growth is revised by up to {np.max(np.abs(gcur.loc[fr.target_month].values - fr.yoy_first_release.values)):.2f} pp.\",\n                    \"handling\": \"Forecasts are evaluated against first-release YoY (computed within one vintage, so level shifts cancel to first order). The current file is used only for estimand (d).\"})\ndata_issues.append({\"issue\": \"Real-time vintages differ from each other through routine revisions of the last 2-3 months and through annual revisions; values of a given month differ across origins.\",\n                    \"handling\": \"Each origin uses only its own vintage file; no splicing of vintages.\"})\ndata_issues.append({\"issue\": \"UMCSENT has empty values for 210 months before 1978 (quarterly survey); PAYEMS vintages of 2025-10-31 end at 2025-08 (BLS release delays).\",\n                    \"handling\": \"Neither predictor enters the chosen model; files were audited and row-counted only (PAYEMS) or not used (UMCSENT not read).\"})\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nres[\"data_issues\"] = data_issues\nres[\"n_input_rows\"] = n_rows\nres[\"n_analysed\"] = int(len(fc[fc.model == \"model\"]))\nres[\"random_seed\"] = SEED\nres[\"supplementary\"] = {\"per_horizon\": {f\"h{h}\": boot[h] for h in HORIZONS},\n                        \"abs_revision_h1_targets\": {t.strftime(\"%Y-%m\"): float(r) for t, r in zip(t1, revs)},\n                        \"ar1_note\": \"AR(1) re-estimated at every origin on that vintage only.\"}\nwith open(os.path.join(O, \"results.json\"), \"w\") as f:\n    json.dump(res, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc[fc.horizon == h]\n    a = actual.loc[\"2025-06-01\":\"2026-09-01\"]\n    ax.plot(a.index, a.values, \"k-o\", ms=4, label=\"first-release actual\")\n    for m, st in [(\"naive\", \"s--\"), (\"model\", \"^-\"), (\"ar1\", \"x:\")]:\n        s = sub[sub.model == m]\n        ax.plot(pd.to_datetime(s.target_date), s.forecast, st, label=m)\n    ax.set_title(f\"h = {h}\")\n    ax.set_ylabel(\"YoY growth of RSAFS, %\")\n    ax.grid(alpha=.3)\n    ax.tick_params(axis=\"x\", rotation=45)\naxes[0].legend()\nfig.suptitle(\"Real-time forecasts of US retail sales YoY growth vs first release\")\nfig.tight_layout()\nfig.savefig(os.path.join(O, \"figure1.png\"), dpi=130)\nprint(json.dumps({k: v for k, v in res.items() if k not in (\"data_issues\", \"model_description\")}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py; cat out/table1.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":1609,"cache_read_input_tokens":16575,"output_tokens":5707,"output_tokens_details":{"thinking_tokens":698},"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":1609},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsoYF23pWvtaWcJ7954","requestRef":"0181b1f5-e4e7-47ba-8f22-71c66d6e7391","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"885368ad-7e75-49b7-935a-405c538b3e3a","timestamp":"2026-10-30T05:34:41.214Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"885368ad-7e75-49b7-935a-405c538b3e3a","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"885368ad-7e75-49b7-935a-405c538b3e3a","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01LnuDKd2bEXjZBSXT4sunkP","type":"tool_result","content":"{\n \"task_id\": \"T1-forecast\",\n \"model_name\": \"Base-effect drift (trailing-12m mean growth level extrapolation)\",\n \"n_origins\": 10,\n \"first_origin\": \"2025-10-31\",\n \"last_origin\": \"2026-07-31\",\n \"rmse_naive_h1\": 0.996874361153601,\n \"mae_naive_h1\": 0.8487221999999999,\n \"rmse_naive_h3\": 1.4200403019751233,\n \"mae_naive_h3\": 1.2004486,\n \"rmse_snaive_h1\": 1.674542814799132,\n \"mae_snaive_h1\": 1.3066698,\n \"rmse_snaive_h3\": 1.3160788608225193,\n \"mae_snaive_h3\": 1.0658687,\n \"rmse_ar1_h1\": 0.940524354787796,\n \"mae_ar1_h1\": 0.7976509999999999,\n \"rmse_ar1_h3\": 1.1871176370926342,\n \"mae_ar1_h3\": 0.9526893999999999,\n \"rmse_model_h1\": 0.5502976390310066,\n \"mae_model_h1\": 0.48633190000000004,\n \"rmse_model_h3\": 1.1422196608203694,\n \"mae_model_h3\": 0.9339774000000001,\n \"rel_improvement_rmse_h1\": 0.4479769362367869,\n \"dm_stat_h1\": 2.4289778933188826,\n \"dm_pvalue_h1\": 0.015141455540092164,\n \"conclusion_code_h1\": \"model_better_significant\",\n \"rel_improvement_rmse_h3\": 0.19564278617186803,\n \"dm_stat_h3\": 1.546577321548468,\n \"dm_pvalue_h3\": 0.12196520179653336,\n \"conclusion_code_h3\": \"model_better_not_significant\",\n \"mean_abs_revision_h1_targets\": 0.5482198028388884,\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"n_input_rows\": {\n  \"first_release.csv\": 28,\n  \"vintages/RSAFS_vintage_2025-10-31.csv\": 404,\n  \"vintages/PAYEMS_vintage_2025-10-31.csv\": 1040,\n  \"vintages/RSAFS_vintage_2025-11-30.csv\": 405,\n  \"vintages/PAYEMS_vintage_2025-11-30.csv\": 1041,\n  \"vintages/RSAFS_vintage_2025-12-31.csv\": 406,\n  \"vintages/PAYEMS_vintage_2025-12-31.csv\": 1043,\n  \"vintages/RSAFS_vintage_2026-01-31.csv\": 407,\n  \"vintages/PAYEMS_vintage_2026-01-31.csv\": 1044,\n  \"vintages/RSAFS_vintage_2026-02-28.csv\": 408,\n  \"vintages/PAYEMS_vintage_2026-02-28.csv\": 1045,\n  \"vintages/RSAFS_vintage_2026-03-31.csv\": 409,\n  \"vintages/PAYEMS_vintage_2026-03-31.csv\": 1046,\n  \"vintages/RSAFS_vintage_2026-04-30.csv\": 411,\n  \"vintages/PAYEMS_vintage_2026-04-30.csv\": 1047,\n  \"vintages/RSAFS_vintage_2026-05-31.csv\": 412,\n  \"vintages/PAYEMS_vintage_2026-05-31.csv\": 1048,\n  \"vintages/RSAFS_vintage_2026-06-30.csv\": 413,\n  \"vintages/PAYEMS_vintage_2026-06-30.csv\": 1049,\n  \"vintages/RSAFS_vintage_2026-07-31.csv\": 414,\n  \"vintages/PAYEMS_vintage_2026-07-31.csv\": 1050,\n  \"RSAFS_current.csv\": 417\n },\n \"n_analysed\": 20,\n \"random_seed\": 20261030,\n \"supplementary\": {\n  \"per_horizon\": {\n   \"h1\": {\n    \"hln_stat\": 2.3043307587255466,\n    \"hln_p\": 0.04666749201146114,\n    \"rmse_diff\": 0.44657672212259436,\n    \"boot_ci95\": [\n     0.29334832793401305,\n     0.6721875156424356\n    ],\n    \"wins_model\": 8,\n    \"n\": 10\n   },\n   \"h3\": {\n    \"hln_stat\": 1.1573524918777764,\n    \"hln_p\": 0.2769204775275833,\n    \"rmse_diff\": 0.2778206411547539,\n    \"boot_ci95\": [\n     -0.14490466807245417,\n     0.6274230170892946\n    ],\n    \"wins_model\": 6,\n    \"n\": 10\n   }\n  },\n  \"abs_revision_h1_targets\": {\n   \"2025-09\": 0.5502167925401702,\n   \"2025-10\": 0.6641763167214578,\n   \"2025-11\": 0.4389199822781502,\n   \"2025-12\": 0.3286268165544084,\n   \"2026-01\": 0.9756759757612237,\n   \"2026-02\": 0.40995563089387543,\n   \"2026-04\": 0.7481728291014038,\n   \"2026-05\": 0.16533992600871716,\n   \"2026-06\": 0.7440888135516674,\n   \"2026-07\": 0.45702494497780943\n  },\n  \"ar1_note\": \"AR(1) re-estimated at every origin on that vintage only.\"\n }\n}\nmodel,horizon,rmse,mae,n\nnaive,1,0.996874361153601,0.8487221999999999,10\nnaive,3,1.4200403019751233,1.2004486,10\nsnaive,1,1.674542814799132,1.3066698,10\nsnaive,3,1.3160788608225193,1.0658687,10\nar1,1,0.940524354787796,0.7976509999999999,10\nar1,3,1.1871176370926342,0.9526893999999999,10\nmodel,1,0.5502976390310066,0.48633190000000004,10\nmodel,3,1.1422196608203694,0.9339774000000001,10","is_error":false}]},"uuid":"bf8c64ee-9f82-4676-8526-3c3beb713388","timestamp":"2026-10-30T05:34:42.180Z","toolUseResult":{"stdout":"{\n \"task_id\": \"T1-forecast\",\n \"model_name\": \"Base-effect drift (trailing-12m mean growth level extrapolation)\",\n \"n_origins\": 10,\n \"first_origin\": \"2025-10-31\",\n \"last_origin\": \"2026-07-31\",\n \"rmse_naive_h1\": 0.996874361153601,\n \"mae_naive_h1\": 0.8487221999999999,\n \"rmse_naive_h3\": 1.4200403019751233,\n \"mae_naive_h3\": 1.2004486,\n \"rmse_snaive_h1\": 1.674542814799132,\n \"mae_snaive_h1\": 1.3066698,\n \"rmse_snaive_h3\": 1.3160788608225193,\n \"mae_snaive_h3\": 1.0658687,\n \"rmse_ar1_h1\": 0.940524354787796,\n \"mae_ar1_h1\": 0.7976509999999999,\n \"rmse_ar1_h3\": 1.1871176370926342,\n \"mae_ar1_h3\": 0.9526893999999999,\n \"rmse_model_h1\": 0.5502976390310066,\n \"mae_model_h1\": 0.48633190000000004,\n \"rmse_model_h3\": 1.1422196608203694,\n \"mae_model_h3\": 0.9339774000000001,\n \"rel_improvement_rmse_h1\": 0.4479769362367869,\n \"dm_stat_h1\": 2.4289778933188826,\n \"dm_pvalue_h1\": 0.015141455540092164,\n \"conclusion_code_h1\": \"model_better_significant\",\n \"rel_improvement_rmse_h3\": 0.19564278617186803,\n \"dm_stat_h3\": 1.546577321548468,\n \"dm_pvalue_h3\": 0.12196520179653336,\n \"conclusion_code_h3\": \"model_better_not_significant\",\n \"mean_abs_revision_h1_targets\": 0.5482198028388884,\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"n_input_rows\": {\n  \"first_release.csv\": 28,\n  \"vintages/RSAFS_vintage_2025-10-31.csv\": 404,\n  \"vintages/PAYEMS_vintage_2025-10-31.csv\": 1040,\n  \"vintages/RSAFS_vintage_2025-11-30.csv\": 405,\n  \"vintages/PAYEMS_vintage_2025-11-30.csv\": 1041,\n  \"vintages/RSAFS_vintage_2025-12-31.csv\": 406,\n  \"vintages/PAYEMS_vintage_2025-12-31.csv\": 1043,\n  \"vintages/RSAFS_vintage_2026-01-31.csv\": 407,\n  \"vintages/PAYEMS_vintage_2026-01-31.csv\": 1044,\n  \"vintages/RSAFS_vintage_2026-02-28.csv\": 408,\n  \"vintages/PAYEMS_vintage_2026-02-28.csv\": 1045,\n  \"vintages/RSAFS_vintage_2026-03-31.csv\": 409,\n  \"vintages/PAYEMS_vintage_2026-03-31.csv\": 1046,\n  \"vintages/RSAFS_vintage_2026-04-30.csv\": 411,\n  \"vintages/PAYEMS_vintage_2026-04-30.csv\": 1047,\n  \"vintages/RSAFS_vintage_2026-05-31.csv\": 412,\n  \"vintages/PAYEMS_vintage_2026-05-31.csv\": 1048,\n  \"vintages/RSAFS_vintage_2026-06-30.csv\": 413,\n  \"vintages/PAYEMS_vintage_2026-06-30.csv\": 1049,\n  \"vintages/RSAFS_vintage_2026-07-31.csv\": 414,\n  \"vintages/PAYEMS_vintage_2026-07-31.csv\": 1050,\n  \"RSAFS_current.csv\": 417\n },\n \"n_analysed\": 20,\n \"random_seed\": 20261030,\n \"supplementary\": {\n  \"per_horizon\": {\n   \"h1\": {\n    \"hln_stat\": 2.3043307587255466,\n    \"hln_p\": 0.04666749201146114,\n    \"rmse_diff\": 0.44657672212259436,\n    \"boot_ci95\": [\n     0.29334832793401305,\n     0.6721875156424356\n    ],\n    \"wins_model\": 8,\n    \"n\": 10\n   },\n   \"h3\": {\n    \"hln_stat\": 1.1573524918777764,\n    \"hln_p\": 0.2769204775275833,\n    \"rmse_diff\": 0.2778206411547539,\n    \"boot_ci95\": [\n     -0.14490466807245417,\n     0.6274230170892946\n    ],\n    \"wins_model\": 6,\n    \"n\": 10\n   }\n  },\n  \"abs_revision_h1_targets\": {\n   \"2025-09\": 0.5502167925401702,\n   \"2025-10\": 0.6641763167214578,\n   \"2025-11\": 0.4389199822781502,\n   \"2025-12\": 0.3286268165544084,\n   \"2026-01\": 0.9756759757612237,\n   \"2026-02\": 0.40995563089387543,\n   \"2026-04\": 0.7481728291014038,\n   \"2026-05\": 0.16533992600871716,\n   \"2026-06\": 0.7440888135516674,\n   \"2026-07\": 0.45702494497780943\n  },\n  \"ar1_note\": \"AR(1) re-estimated at every origin on that vintage only.\"\n }\n}\nmodel,horizon,rmse,mae,n\nnaive,1,0.996874361153601,0.8487221999999999,10\nnaive,3,1.4200403019751233,1.2004486,10\nsnaive,1,1.674542814799132,1.3066698,10\nsnaive,3,1.3160788608225193,1.0658687,10\nar1,1,0.940524354787796,0.7976509999999999,10\nar1,3,1.1871176370926342,0.9526893999999999,10\nmodel,1,0.5502976390310066,0.48633190000000004,10\nmodel,3,1.1422196608203694,0.9339774000000001,10","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"885368ad-7e75-49b7-935a-405c538b3e3a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"e406f93ce72d832a12b1d6b8463f2ef7ab4a5aeedfc51b8365c92769bd81ca5a","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSnxIKEAgTGAI4AUIIdGhpbmtpbmcSDEextUU90A/hSGqYThoMRRzJ7JuFwy+suICVIjAFvxrb5im0mmXtiXXn8gW4UaMRWnSUR90+l14mS0jZHTs0Tj9dhoBKyoWrplmaSIgqvBH37TGkf7uwo+Ry+qhTgZ9BSAiUKUjei3hZAiRa5ZOxJVLGfQlKJT9CGNzdBPqY96PhQRxloW+EkZy7iYeg9xtyH089GqvYMZabxFb5EjCsnZJY1llz3w9gCf03cgTZjAFduKrsP6NjPFwcb9oqsz9nHRSTD2NMtmv5+OHK5le48LE1qh1+2cl8dShepuIc6wg7drdsxDAP3oLFa65P2rYjtlKTP1IGrvOrWAoYuYkLYvEVZYCZFF6P7e7YI6cjK6npoQ7SvlYI9q7STl/foZvZK18xhjZKDyW/RU9POyWAP1Y9Ea9sw0WYfaweO35XH2dzOjJaX1JE2aWOkqaws0DS3tpT1wexEwQHbLzq0mr00H6oCBfjP73TYHW78sc1pcJ0iOhL+bt4XniOLOeHlFPXclTc+bMqJn3bd2bIIKYYzkdmV4nEwhsgwnHhey8yKQgB/LuHcygG1V3fY6snhlfC2o4p8ogDfKPHZMVpAAQ0r3BW6ILhtsJ4ZZkeUec0Zh6dtapO/ziHMkRrAgHFSRO5SN8GsjRvI/oxOiE3qShvhBSLL/W1Ckz6ieGJcq3lxvqk3KVVPvK+HM8BtB+spbGvW8daoYZYhyzfR6YdjwC4Ocbic9FWCV7lm9COYWYZscrs5gNFBWbo33fAZWJF/1JEk2M20NLp7M0Eav6U7lvInNd8F93dC320o58uy8elnHwLUl20vsSoKgUwRCSqwY9qoO2sRokCUQi40/Rca2v1aKTtQjpyY+gcO4Puo6wEpseCaLdKszl+Xtg0E+YDu2Mop3AeTvUPQHSK3CX6G/o3CCMBzA/EiJAVstlJRiWHDfIMzUhb+rtaHsfxHh883qvpkctZMyiSMw5X6RZXmv6RNZrRSnzhYyliAqwWtU2OSPik3ezyYYaHlCucB1iOlpT0dv6uEy1XVNzPtJTBXZjNUTKZmdAUgIpvawV7reKC8A3UJBRLo4sll/FTCXIIgYa7uQYi3aizlWdhdi1dP8Wtxwo13tjqN1uzrXsc3cRe8WKRWoDmwAO90YaEAAqXAu6AZnh5QCFHuhn/8nzEWTiR4RL+2myWoN4BK1fLqwSwogN2/n+sjgu5Mw7yHgUQ8hrpUj0hNI1+52sxREoQbRcv02j6KkLWIOq5vfOqFJJ2KoPc0dI2JsiU1M2pWhdMIjuqzMnnFeWx0PwjPbTHNvctxk9pMWlfVP4goWwkyPQLJS4It3bM1vfenoYehTWWpMm2eQYetsxGPugPJQHBp0tFiqxdntgc+CZfZsXH7d0v5Il+4h2jg4TXZgpzCb01LFH3tw9stX9MONKmBPHL6MtOTRHuGkYkIb6QumGC8x0lEyASD+myoAZIDwnr8YVNtr9WePKEUQi0R1Z7kHjSq43DCXsFHRW9tcmnhyEJed2UdeICDBJp3jO1nratyJxSL7aWZmFvOuaSpL7t9m/dzapp0Qu5m6rasF1/7SZzIEYXBTvNa5gX3j39b7wUhYdk6g852/vjPQS0aLQSeQIGtNs/PAHwZFReAsfvk9VA/gF008oK36bSAflUxWMw98VcVyFIKrgSAhLgUDgQ+ul/aSu22Ki0dBh/E/XFIXtTZKz0ytN/twfrPzsCCC7p44QtdBUZOJnIIOExroi5VzOFhYN3eZLqnr+MDCHX7lDzAMScI2aaEL/ycBighvQbki1fo0mNbrfXwMITYnV7pvD8/9MkLMkgsWccyFnYZ+YDX+F1elYeJb8WgZOAXXM5J/3m6BCESjHukcrE6eNjswzWT7Fs7u1YS2zr8Ce6KraO7d6uGan5uy23r15Y+V+cBpSwKjcQwj/SimxLyyiw7b8oguFU9U5afJBhcJBpxqIi/xerUcW9jt+jOTsd+FL12XeqE00AZ2NtGJ5GT/+GICdHaBUfH1KPs/8fXpkeSgEtBjJy+PGJWWNMAJNvTtfpChM4f9KZJ8CQtN7PZzk7+UrPop8hTjfTn4kCHELMO7/QYTd/v6GJyDWY+1HSlFNn2VsNTNL06VowaKm/ajex/WutjNbwse8Gou3sPO6oDnvs5VTt22Til0arah2EsgwSgozOPqIegmbq7eA9BLj1rXc7aiFPUZao/tSfmSc87Wn1SjXqzEfasTbpjYYpg8Ny5HIjkbm7PeA9jGm2rT3qdPE6+vH6Ks4nAkfsrFbXk60FHRGt/bNV/rqdCKK8S56bxIe+PpN7Kk5qghXRdNQvacnLiVWgVoq2D7XjMpyvobEHG/q5jALPN3OpnaExaFXzGOGX5tdUWi1QnoyQ1UL2/EG6cfbprbn4qbc6TO86MjZs1HcDBGDEqAr9E2ZXHQS0n0vRpHB8E/zgJBoDtREn90NZuyZZTpXPKUKn211nvZruzXycbOufCleKJanUF+0DPVNQO1BypbwLCSEWVrmUWxCDRZJPeLXWT2O1ZlbFciHNlHSNRckrwna+PlDbaWbF/gCZ6TSv6gnp2WF7cXdNAyZOQ2OyM7DYe2v2+IAnoQcjl/MbNbKGDcAU+NULA+oBrEMjqaDHT385kYDMNHaYKs5xYhoWVQpKkAKXR+sYQgfxyYlp9+U8Ch8FkUkbjAQcSMZ0T9e6Usv2+6JJHjRd2KghQXpFKoqu8SFO5UzJMFUTtyV2A0+jjcv7aZwb4bC/RC/A9uF7y8F9sfq4qX+z3ee31iDQoHNBAH9fIG9hGsHHYYFQlkrSvgHY9MnNC/bZVsYvDMV5kz9REgu3mRMBFVThUI3nVuqbd1O6qCnR9I3ZPAt4yQ4Z7SRAjuT9gQEX+exdTf4jpY20dHZk/jZrKQewcpXYHoAfEFCmB/47wabbnzV5P1BsaOR+2azddQYe7QvGiIykhNesz+pBXriwoeBuNqwe3DmA6HmnRL/PsfltZhlAoLQXgiOsOwmIGxVeoKoITps6hn70YCYvyKJc5p9++Udt4Ljlle1C4ng6Zs8AWeY6MPW2dftCWgkZAgrpe/Q6LKBS13zLZxSu0Wy49nFXGAE="},{"type":"tool_use","id":"toolu_01LnuDKd2bEXjZBSXT4sunkP","name":"Bash","input":{"command":"mkdir -p out; cat > out/analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nRegenerates out/results.json, out/forecasts.csv, out/table1.csv, out/figure1.png from data/ only.\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import norm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nD, O = \"data\", \"out\"\nos.makedirs(O, exist_ok=True)\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nSEED = 20261030\nn_rows = {}\n\n\ndef read(rel):\n    df = pd.read_csv(os.path.join(D, rel), parse_dates=[\"observation_date\"]).set_index(\"observation_date\")\n    n_rows[rel] = len(df)\n    s = df.iloc[:, 0].astype(float)\n    assert s.index.is_monotonic_increasing and not s.index.duplicated().any()\n    return s\n\n\ndef yoy(level):\n    return 100 * np.log(level / level.shift(12))\n\n\nfr = pd.read_csv(os.path.join(D, \"first_release.csv\"), parse_dates=[\"target_month\", \"first_release_vintage\"])\nn_rows[\"first_release.csv\"] = len(fr)\nactual = fr.set_index(\"target_month\")[\"yoy_first_release\"]\n\ndata_issues = []\nrows = []\nlast_months = {}\nfor V in ORIGINS:\n    L = read(f\"vintages/RSAFS_vintage_{V}.csv\")\n    P = read(f\"vintages/PAYEMS_vintage_{V}.csv\")  # read for audit only; not used by the chosen model\n    assert L.isna().sum() == 0 and (L.index.to_series().diff().dt.days.dropna() <= 31).all()\n    g = yoy(L)\n    last = L.index[-1]\n    last_months[V] = last\n    # AR(1) on g_m, 1993-02 <= m <= last\n    y = g.loc[\"1993-02-01\":last]\n    x = g.shift(1).loc[\"1993-02-01\":last]\n    X = np.column_stack([np.ones(len(y)), x.values])\n    a, b = np.linalg.lstsq(X, y.values, rcond=None)[0]\n    lnL = np.log(L)\n    mu = (lnL.loc[last] - lnL.loc[last - pd.DateOffset(months=12)]) / 12  # mean monthly log growth, last 12 months\n    for h in HORIZONS:\n        T = last + pd.DateOffset(months=h)\n        f_naive = g.loc[last]\n        f_snaive = g.loc[T - pd.DateOffset(months=12)]\n        f = g.loc[last]\n        for _ in range(h):\n            f = a + b * f\n        f_ar1 = f\n        # Model: base-effect-aware drift. Forecast the level by extrapolating the last published level with the\n        # trailing-12-month mean monthly log growth, then divide by the (already published) base-period level.\n        f_model = 100 * (lnL.loc[last] + h * mu - lnL.loc[T - pd.DateOffset(months=12)])\n        for m, fc in [(\"naive\", f_naive), (\"snaive\", f_snaive), (\"ar1\", f_ar1), (\"model\", f_model)]:\n            rows.append(dict(origin_date=V, target_date=T.strftime(\"%Y-%m-%d\"), horizon=h, forecast=round(float(fc), 6),\n                             actual_first_release=float(actual.loc[T]), model=m, vintage_used=V))\n\nfc = pd.DataFrame(rows)\nfc.to_csv(os.path.join(O, \"forecasts.csv\"), index=False)\nfc[\"err\"] = fc.actual_first_release - fc.forecast\n\n# publication-timing audit\nfor V in ORIGINS:\n    lag = (pd.Timestamp(V).year - last_months[V].year) * 12 + pd.Timestamp(V).month - last_months[V].month\n    if lag != 1:\n        data_issues.append({\"issue\": f\"Irregular publication timing: RSAFS vintage {V} ends at {last_months[V]:%Y-%m} ({lag} months before the origin month).\",\n                            \"handling\": \"Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.\"})\nlm = pd.Series(last_months)\nadded = (lm.dt.year * 12 + lm.dt.month).diff()\nfor V, k in added.items():\n    if k == 2:\n        data_issues.append({\"issue\": f\"Vintage {V} adds two new months at once (catch-up after delayed release); the month {lm[V] - pd.DateOffset(months=1):%Y-%m} is never an h=1 target and its first release is in the same vintage as the following month.\",\n                            \"handling\": \"No adjustment; targets follow last(V)+h. Horizon-1 targets therefore skip one month and h=3 targets skip one month, so the 10 origins are not equally spaced in target time.\"})\n\ntable = []\nfor m in [\"naive\", \"snaive\", \"ar1\", \"model\"]:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)].err.values\n        table.append(dict(model=m, horizon=h, rmse=float(np.sqrt(np.mean(e ** 2))), mae=float(np.mean(np.abs(e))), n=len(e)))\ntab = pd.DataFrame(table)\ntab.to_csv(os.path.join(O, \"table1.csv\"), index=False)\n\n\ndef nw_lrv(d, L):\n    d = d - d.mean()\n    n = len(d)\n    v = np.sum(d * d) / n\n    for l in range(1, L + 1):\n        v += 2 * (1 - l / (L + 1)) * np.sum(d[l:] * d[:-l]) / n\n    return v\n\n\nres = dict(task_id=\"T1-forecast\",\n           model_name=\"Base-effect drift (trailing-12m mean growth level extrapolation)\",\n           model_description=(\n               \"At origin V, using only the RSAFS vintage dated V: let last = last month in the vintage and \"\n               \"mu = (ln L_last - ln L_{last-12})/12, the mean monthly log growth over the last 12 published months. \"\n               \"The level of target month T = last+h is forecast as ln L_T = ln L_last + h*mu, and the YoY forecast is \"\n               \"100*(ln L_last + h*mu - ln L_{T-12}), where L_{T-12} is the base-period level already published in the same vintage. \"\n               \"Equivalently: naive forecast + h*g_last/12 - 100*(ln L_{T-12} - ln L_{last-12}), i.e. it corrects the naive forecast \"\n               \"for known base effects (the months dropping out of the 12-month window). No parameters are estimated; \"\n               \"PAYEMS and UMCSENT are not used (specification fixed a priori, before any evaluation against actuals). \"\n               \"All inputs are from vintage V, so the availability rule holds trivially.\"),\n           n_origins=len(ORIGINS), first_origin=ORIGINS[0], last_origin=ORIGINS[-1])\nfor r in table:\n    res[f\"rmse_{r['model']}_h{r['horizon']}\"] = r[\"rmse\"]\n    res[f\"mae_{r['model']}_h{r['horizon']}\"] = r[\"mae\"]\n\nrng = np.random.default_rng(SEED)\nboot = {}\nfor h in HORIZONS:\n    en = fc[(fc.model == \"naive\") & (fc.horizon == h)].sort_values(\"origin_date\").err.values\n    em = fc[(fc.model == \"model\") & (fc.horizon == h)].sort_values(\"origin_date\").err.values\n    res[f\"rel_improvement_rmse_h{h}\"] = 1 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    d = en ** 2 - em ** 2\n    n = len(d)\n    lrv = nw_lrv(d, h - 1)\n    dm = d.mean() / np.sqrt(lrv / n)\n    p = 2 * (1 - norm.cdf(abs(dm)))\n    res[f\"dm_stat_h{h}\"] = float(dm)\n    res[f\"dm_pvalue_h{h}\"] = float(p)\n    better = \"model\" if res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"] else \"naive\"\n    res[f\"conclusion_code_h{h}\"] = f\"{better}_better_{'significant' if p < 0.05 else 'not_significant'}\"\n    # supplementary: HLN-adjusted DM with t(n-1), and moving-block bootstrap (block 3) of RMSE_naive - RMSE_model\n    k = np.sqrt((n + 1 - 2 * h + h * (h - 1) / n) / n)\n    hln = dm * k\n    B, bl = 10000, 3\n    diffs = []\n    for _ in range(B):\n        starts = rng.integers(0, n - bl + 1, size=int(np.ceil(n / bl)))\n        idx = np.concatenate([np.arange(s, s + bl) for s in starts])[:n]\n        diffs.append(np.sqrt(np.mean(en[idx] ** 2)) - np.sqrt(np.mean(em[idx] ** 2)))\n    diffs = np.array(diffs)\n    from scipy.stats import t as tdist\n    boot[h] = dict(hln_stat=float(hln), hln_p=float(2 * (1 - tdist.cdf(abs(hln), n - 1))),\n                   rmse_diff=float(res[f\"rmse_naive_h{h}\"] - res[f\"rmse_model_h{h}\"]),\n                   boot_ci95=[float(np.percentile(diffs, 2.5)), float(np.percentile(diffs, 97.5))],\n                   wins_model=int(np.sum(np.abs(em) < np.abs(en))), n=n)\n\n# (d) revision of h=1 targets\ncur = read(\"RSAFS_current.csv\")\ngcur = yoy(cur)\nt1 = pd.to_datetime(fc[(fc.horizon == 1) & (fc.model == \"naive\")].target_date)\nrevs = np.abs(gcur.loc[t1].values - actual.loc[t1].values)\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(revs))\nlvl_rev = 100 * (cur.loc[fr.target_month].values / fr.level_first_release.values - 1)\ndata_issues.append({\"issue\": f\"Large level revision: current RSAFS levels for 2024-06..2026-07 are {lvl_rev[:-2].min():.1f}% to {lvl_rev[:-2].max():.1f}% below their first-release levels (a benchmark/annual revision between the 2026-08-31 and 2026-09-30 releases shifted the whole level); YoY growth is revised by up to {np.max(np.abs(gcur.loc[fr.target_month].values - fr.yoy_first_release.values)):.2f} pp.\",\n                    \"handling\": \"Forecasts are evaluated against first-release YoY (computed within one vintage, so level shifts cancel to first order). The current file is used only for estimand (d).\"})\ndata_issues.append({\"issue\": \"Real-time vintages differ from each other through routine revisions of the last 2-3 months and through annual revisions; values of a given month differ across origins.\",\n                    \"handling\": \"Each origin uses only its own vintage file; no splicing of vintages.\"})\ndata_issues.append({\"issue\": \"UMCSENT has empty values for 210 months before 1978 (quarterly survey); PAYEMS vintages of 2025-10-31 end at 2025-08 (BLS release delays).\",\n                    \"handling\": \"Neither predictor enters the chosen model; files were audited and row-counted only (PAYEMS) or not used (UMCSENT not read).\"})\nres[\"feasibility\"] = \"complete\"\nres[\"feasibility_reason\"] = None\nres[\"data_issues\"] = data_issues\nres[\"n_input_rows\"] = n_rows\nres[\"n_analysed\"] = int(len(fc[fc.model == \"model\"]))\nres[\"random_seed\"] = SEED\nres[\"supplementary\"] = {\"per_horizon\": {f\"h{h}\": boot[h] for h in HORIZONS},\n                        \"abs_revision_h1_targets\": {t.strftime(\"%Y-%m\"): float(r) for t, r in zip(t1, revs)},\n                        \"ar1_note\": \"AR(1) re-estimated at every origin on that vintage only.\"}\nwith open(os.path.join(O, \"results.json\"), \"w\") as f:\n    json.dump(res, f, indent=2)\n\n# figure\nfig, axes = plt.subplots(1, 2, figsize=(12, 4.5), sharey=True)\nfor ax, h in zip(axes, HORIZONS):\n    sub = fc[fc.horizon == h]\n    a = actual.loc[\"2025-06-01\":\"2026-09-01\"]\n    ax.plot(a.index, a.values, \"k-o\", ms=4, label=\"first-release actual\")\n    for m, st in [(\"naive\", \"s--\"), (\"model\", \"^-\"), (\"ar1\", \"x:\")]:\n        s = sub[sub.model == m]\n        ax.plot(pd.to_datetime(s.target_date), s.forecast, st, label=m)\n    ax.set_title(f\"h = {h}\")\n    ax.set_ylabel(\"YoY growth of RSAFS, %\")\n    ax.grid(alpha=.3)\n    ax.tick_params(axis=\"x\", rotation=45)\naxes[0].legend()\nfig.suptitle(\"Real-time forecasts of US retail sales YoY growth vs first release\")\nfig.tight_layout()\nfig.savefig(os.path.join(O, \"figure1.png\"), dpi=130)\nprint(json.dumps({k: v for k, v in res.items() if k not in (\"data_issues\", \"model_description\")}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py; cat out/table1.csv","description":"Write and run analysis script"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"b6fd88df-3796-455f-b329-4e885282cc2f","timestamp":"2026-10-30T05:34:42.183Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"0181b1f5-e4e7-47ba-8f22-71c66d6e7391","keep":10,"tail":["e406f93ce72d832a12b1d6b8463f2ef7ab4a5aeedfc51b8365c92769bd81ca5a","680fbf2c742cbaf28c9bf7a71d1fdd18f0d9381187aebd5b88ea6158bb09f077"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"15dd9170fdd943c4c7fb4dc41d8485bd4f6ccce76a6ce47d9c217c4a6693ceb5"}
{"parentUuid":"bf8c64ee-9f82-4676-8526-3c3beb713388","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXss3ZiD329u51yDohE1","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":7791,"cache_read_input_tokens":18184,"output_tokens":1093,"output_tokens_details":{"thinking_tokens":285},"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":7791},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3161,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXss3JLdxXWrLDqK1CEX","requestRef":"b6fd88df-3796-455f-b329-4e885282cc2f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d0a5fb4e-e00c-458c-83dc-d5c04306fe9f","timestamp":"2026-10-30T05:34:46.368Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"d0a5fb4e-e00c-458c-83dc-d5c04306fe9f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXss3ZiD329u51yDohE1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0122GpPQeoNS6tYR8MQGRnyW","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''cur = read(\"RSAFS_current.csv\")''','''cur = read(\"RSAFS_current.csv\")\num = read(\"UMCSENT.csv\")  # audited only (not used by the model)\nn_um_missing = int(um.isna().sum())''')\ns=s.replace('''\"UMCSENT has empty values for 210 months''','''f\"UMCSENT has empty values for {n_um_missing} months''')\ns=s.replace(\"PAYEMS vintages of 2025-10-31 end at 2025-08 (BLS release delays).\",\"PAYEMS vintages also show irregular timing (2025-10-31 ends at 2025-08; 2025-12-31 adds two months at once) due to delayed BLS releases.\")\ns=s.replace(\"or not used (UMCSENT not read)\",\"(PAYEMS, UMCSENT)\")\ns=s.replace(\"files were audited and row-counted only (PAYEMS) (PAYEMS, UMCSENT).\",\"files were read, audited and row-counted only (PAYEMS, UMCSENT).\")\nopen(p,'w').write(s)\nEOF\ngrep -n \"UMCSENT has\" -A2 out/analysis.py; ~/wp29/venv/bin/python out/analysis.py >/dev/null && md5 out/results.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && md5 out/results.json; ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));[print(d) for d in r['data_issues']];print(r['n_input_rows']['UMCSENT.csv'])\"; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;f=pd.read_csv('out/forecasts.csv');print(f[f.model.isin(['naive','model'])].pivot_table(index=['horizon','origin_date','target_date','actual_first_release'],columns='model',values='forecast').round(2))\"","description":"Patch script, rerun, check determinism"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":7791,"cache_read_input_tokens":18184,"output_tokens":1093,"output_tokens_details":{"thinking_tokens":285},"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":7791},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXss3JLdxXWrLDqK1CEX","requestRef":"b6fd88df-3796-455f-b329-4e885282cc2f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"49180641-a8cc-4a8f-aab6-a2b054b8bef5","timestamp":"2026-10-30T05:34:52.510Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"49180641-a8cc-4a8f-aab6-a2b054b8bef5","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0122GpPQeoNS6tYR8MQGRnyW","type":"tool_result","content":"164:data_issues.append({\"issue\": f\"UMCSENT has empty values for {n_um_missing} months before 1978 (quarterly survey); PAYEMS vintages also show irregular timing (2025-10-31 ends at 2025-08; 2025-12-31 adds two months at once) due to delayed BLS releases.\",\n165-                    \"handling\": \"Neither predictor enters the chosen model; files were read, audited and row-counted only (PAYEMS, UMCSENT).\"})\n166-res[\"feasibility\"] = \"complete\"\nMD5 (out/results.json) = 0b1165c26b2629ef76abb9dd51a0294d\nMD5 (out/results.json) = 0b1165c26b2629ef76abb9dd51a0294d\n{'issue': 'Irregular publication timing: RSAFS vintage 2025-10-31 ends at 2025-08 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2025-11-30 ends at 2025-09 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2025-12-31 ends at 2025-10 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2026-01-31 ends at 2025-11 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2026-02-28 ends at 2025-12 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2026-03-31 ends at 2026-01 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Vintage 2026-04-30 adds two new months at once (catch-up after delayed release); the month 2026-02 is never an h=1 target and its first release is in the same vintage as the following month.', 'handling': 'No adjustment; targets follow last(V)+h. Horizon-1 targets therefore skip one month and h=3 targets skip one month, so the 10 origins are not equally spaced in target time.'}\n{'issue': 'Large level revision: current RSAFS levels for 2024-06..2026-07 are -5.6% to -3.8% below their first-release levels (a benchmark/annual revision between the 2026-08-31 and 2026-09-30 releases shifted the whole level); YoY growth is revised by up to 2.02 pp.', 'handling': 'Forecasts are evaluated against first-release YoY (computed within one vintage, so level shifts cancel to first order). The current file is used only for estimand (d).'}\n{'issue': 'Real-time vintages differ from each other through routine revisions of the last 2-3 months and through annual revisions; values of a given month differ across origins.', 'handling': 'Each origin uses only its own vintage file; no splicing of vintages.'}\n{'issue': 'UMCSENT has empty values for 210 months before 1978 (quarterly survey); PAYEMS vintages also show irregular timing (2025-10-31 ends at 2025-08; 2025-12-31 adds two months at once) due to delayed BLS releases.', 'handling': 'Neither predictor enters the chosen model; files were read, audited and row-counted only (PAYEMS, UMCSENT).'}\n887\nmodel                                                 model  naive\nhorizon origin_date target_date actual_first_release              \n1       2025-10-31  2025-09-01  4.173540               4.44   4.88\n        2025-11-30  2025-10-01  3.410194               3.91   4.17\n        2025-12-31  2025-11-01  3.277601               3.12   3.41\n        2026-01-31  2025-12-01  2.398715               2.78   3.28\n        2026-02-28  2026-01-01  3.107200               3.45   2.40\n        2026-03-31  2026-02-01  3.886121               3.27   3.11\n        2026-04-30  2026-04-01  4.758475               4.43   3.89\n        2026-05-31  2026-05-01  6.650342               5.96   4.76\n        2026-06-30  2026-06-01  6.503056               6.03   6.65\n        2026-07-31  2026-07-01  4.887817               6.00   6.50\n3       2025-10-31  2025-11-01  3.277601               3.97   4.88\n        2025-11-30  2025-12-01  2.398715               3.19   4.17\n        2025-12-31  2026-01-01  3.107200               3.78   3.41\n        2026-01-31  2026-02-01  3.886121               4.16   3.28\n        2026-02-28  2026-03-01  3.892690               2.30   2.40\n        2026-03-31  2026-04-01  4.758475               2.39   3.11\n        2026-04-30  2026-06-01  6.503056               4.91   3.89\n        2026-05-31  2026-07-01  4.887817               5.14   4.76\n        2026-06-30  2026-08-01  5.223092               5.94   6.65\n        2026-07-31  2026-09-01  6.097870               6.47   6.50","is_error":false}]},"uuid":"3ec63701-c840-4bec-b4a8-490a748dae39","timestamp":"2026-10-30T05:34:54.553Z","toolUseResult":{"stdout":"164:data_issues.append({\"issue\": f\"UMCSENT has empty values for {n_um_missing} months before 1978 (quarterly survey); PAYEMS vintages also show irregular timing (2025-10-31 ends at 2025-08; 2025-12-31 adds two months at once) due to delayed BLS releases.\",\n165-                    \"handling\": \"Neither predictor enters the chosen model; files were read, audited and row-counted only (PAYEMS, UMCSENT).\"})\n166-res[\"feasibility\"] = \"complete\"\nMD5 (out/results.json) = 0b1165c26b2629ef76abb9dd51a0294d\nMD5 (out/results.json) = 0b1165c26b2629ef76abb9dd51a0294d\n{'issue': 'Irregular publication timing: RSAFS vintage 2025-10-31 ends at 2025-08 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2025-11-30 ends at 2025-09 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2025-12-31 ends at 2025-10 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2026-01-31 ends at 2025-11 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2026-02-28 ends at 2025-12 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Irregular publication timing: RSAFS vintage 2026-03-31 ends at 2026-01 (2 months before the origin month).', 'handling': 'Per task rules the target is defined relative to last(V), the last month present in the vintage, not to the calendar; forecasts use only that vintage.'}\n{'issue': 'Vintage 2026-04-30 adds two new months at once (catch-up after delayed release); the month 2026-02 is never an h=1 target and its first release is in the same vintage as the following month.', 'handling': 'No adjustment; targets follow last(V)+h. Horizon-1 targets therefore skip one month and h=3 targets skip one month, so the 10 origins are not equally spaced in target time.'}\n{'issue': 'Large level revision: current RSAFS levels for 2024-06..2026-07 are -5.6% to -3.8% below their first-release levels (a benchmark/annual revision between the 2026-08-31 and 2026-09-30 releases shifted the whole level); YoY growth is revised by up to 2.02 pp.', 'handling': 'Forecasts are evaluated against first-release YoY (computed within one vintage, so level shifts cancel to first order). The current file is used only for estimand (d).'}\n{'issue': 'Real-time vintages differ from each other through routine revisions of the last 2-3 months and through annual revisions; values of a given month differ across origins.', 'handling': 'Each origin uses only its own vintage file; no splicing of vintages.'}\n{'issue': 'UMCSENT has empty values for 210 months before 1978 (quarterly survey); PAYEMS vintages also show irregular timing (2025-10-31 ends at 2025-08; 2025-12-31 adds two months at once) due to delayed BLS releases.', 'handling': 'Neither predictor enters the chosen model; files were read, audited and row-counted only (PAYEMS, UMCSENT).'}\n887\nmodel                                                 model  naive\nhorizon origin_date target_date actual_first_release              \n1       2025-10-31  2025-09-01  4.173540               4.44   4.88\n        2025-11-30  2025-10-01  3.410194               3.91   4.17\n        2025-12-31  2025-11-01  3.277601               3.12   3.41\n        2026-01-31  2025-12-01  2.398715               2.78   3.28\n        2026-02-28  2026-01-01  3.107200               3.45   2.40\n        2026-03-31  2026-02-01  3.886121               3.27   3.11\n        2026-04-30  2026-04-01  4.758475               4.43   3.89\n        2026-05-31  2026-05-01  6.650342               5.96   4.76\n        2026-06-30  2026-06-01  6.503056               6.03   6.65\n        2026-07-31  2026-07-01  4.887817               6.00   6.50\n3       2025-10-31  2025-11-01  3.277601               3.97   4.88\n        2025-11-30  2025-12-01  2.398715               3.19   4.17\n        2025-12-31  2026-01-01  3.107200               3.78   3.41\n        2026-01-31  2026-02-01  3.886121               4.16   3.28\n        2026-02-28  2026-03-01  3.892690               2.30   2.40\n        2026-03-31  2026-04-01  4.758475               2.39   3.11\n        2026-04-30  2026-06-01  6.503056               4.91   3.89\n        2026-05-31  2026-07-01  4.887817               5.14   4.76\n        2026-06-30  2026-08-01  5.223092               5.94   6.65\n        2026-07-31  2026-09-01  6.097870               6.47   6.50","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"49180641-a8cc-4a8f-aab6-a2b054b8bef5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"4139557feae17564ce9d1ff1f3727060fc44019b9dcf2147c18bb379c68a43b3","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_0122GpPQeoNS6tYR8MQGRnyW","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace('''cur = read(\"RSAFS_current.csv\")''','''cur = read(\"RSAFS_current.csv\")\num = read(\"UMCSENT.csv\")  # audited only (not used by the model)\nn_um_missing = int(um.isna().sum())''')\ns=s.replace('''\"UMCSENT has empty values for 210 months''','''f\"UMCSENT has empty values for {n_um_missing} months''')\ns=s.replace(\"PAYEMS vintages of 2025-10-31 end at 2025-08 (BLS release delays).\",\"PAYEMS vintages also show irregular timing (2025-10-31 ends at 2025-08; 2025-12-31 adds two months at once) due to delayed BLS releases.\")\ns=s.replace(\"or not used (UMCSENT not read)\",\"(PAYEMS, UMCSENT)\")\ns=s.replace(\"files were audited and row-counted only (PAYEMS) (PAYEMS, UMCSENT).\",\"files were read, audited and row-counted only (PAYEMS, UMCSENT).\")\nopen(p,'w').write(s)\nEOF\ngrep -n \"UMCSENT has\" -A2 out/analysis.py; ~/wp29/venv/bin/python out/analysis.py >/dev/null && md5 out/results.json && ~/wp29/venv/bin/python out/analysis.py >/dev/null && md5 out/results.json; ~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('out/results.json'));[print(d) for d in r['data_issues']];print(r['n_input_rows']['UMCSENT.csv'])\"; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;f=pd.read_csv('out/forecasts.csv');print(f[f.model.isin(['naive','model'])].pivot_table(index=['horizon','origin_date','target_date','actual_first_release'],columns='model',values='forecast').round(2))\"","description":"Patch script, rerun, check determinism"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"50fd1cca-b95d-43a9-be2e-46b893fdc154","timestamp":"2026-10-30T05:34:54.556Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"b6fd88df-3796-455f-b329-4e885282cc2f","keep":12,"tail":["4139557feae17564ce9d1ff1f3727060fc44019b9dcf2147c18bb379c68a43b3","86f3e949132e44b3969cdfea2d899e78e82a735fc2daa9785f9af76fea15f303"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"76c655ff00255a370604945a2622481b88bad4d4f1267193ad98bf16e460e0b2"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3ec63701-c840-4bec-b4a8-490a748dae39","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"3ec63701-c840-4bec-b4a8-490a748dae39","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXssxTACZm3g3kppTpKj","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":3130,"cache_read_input_tokens":25975,"output_tokens":1027,"output_tokens_details":{"thinking_tokens":611},"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":3130},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":5319,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXssxAYR2H45dfGz7MzW","requestRef":"50fd1cca-b95d-43a9-be2e-46b893fdc154","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"46606c48-9855-44c4-b2f0-71f1137fbb0c","timestamp":"2026-10-30T05:35:00.759Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"46606c48-9855-44c4-b2f0-71f1137fbb0c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXssxTACZm3g3kppTpKj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WAmCHg4BE2VYjQkMQzkfpW","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace(\"are {lvl_rev[:-2].min():.1f}% to {lvl_rev[:-2].max():.1f}% below\",\"are {-lvl_rev[:-2].max():.1f}% to {-lvl_rev[:-2].min():.1f}% below\")\ns=s.replace(\"(a benchmark/annual revision between the 2026-08-31 and 2026-09-30 releases shifted the whole level)\",\"(a benchmark/annual revision that first appears in the 2026-09-30 month-end vintage shifted the whole level; the 2026-08 and 2026-09 first releases are already on the new level)\")\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null; grep -o \"Large level[^;]*\" out/results.json","description":"Fix wording 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":3130,"cache_read_input_tokens":25975,"output_tokens":1027,"output_tokens_details":{"thinking_tokens":611},"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":3130},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXssxAYR2H45dfGz7MzW","requestRef":"50fd1cca-b95d-43a9-be2e-46b893fdc154","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4cb4891d-bbdd-4a0f-a400-4908d8a0bc8a","timestamp":"2026-10-30T05:35:03.467Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"4cb4891d-bbdd-4a0f-a400-4908d8a0bc8a","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WAmCHg4BE2VYjQkMQzkfpW","type":"tool_result","content":"Large level revision: current RSAFS levels for 2024-06..2026-07 are 3.8% to 5.6% below their first-release levels (a benchmark/annual revision that first appears in the 2026-09-30 month-end vintage shifted the whole level","is_error":false}]},"uuid":"1f703328-81af-4cd2-b6a7-475c3c4fab1b","timestamp":"2026-10-30T05:35:04.410Z","toolUseResult":{"stdout":"Large level revision: current RSAFS levels for 2024-06..2026-07 are 3.8% to 5.6% below their first-release levels (a benchmark/annual revision that first appears in the 2026-09-30 month-end vintage shifted the whole level","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4cb4891d-bbdd-4a0f-a400-4908d8a0bc8a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"fc7032dafce60cf86920f3c1c30f6a42b20e1d4c573da235d834ee4e4a7b3176","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WAmCHg4BE2VYjQkMQzkfpW","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace(\"are {lvl_rev[:-2].min():.1f}% to {lvl_rev[:-2].max():.1f}% below\",\"are {-lvl_rev[:-2].max():.1f}% to {-lvl_rev[:-2].min():.1f}% below\")\ns=s.replace(\"(a benchmark/annual revision between the 2026-08-31 and 2026-09-30 releases shifted the whole level)\",\"(a benchmark/annual revision that first appears in the 2026-09-30 month-end vintage shifted the whole level; the 2026-08 and 2026-09 first releases are already on the new level)\")\nopen(p,'w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null; grep -o \"Large level[^;]*\" out/results.json","description":"Fix wording and rerun"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"69179ed1-826e-43a5-b24b-a936cfbf48c0","timestamp":"2026-10-30T05:35:04.413Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"50fd1cca-b95d-43a9-be2e-46b893fdc154","keep":14,"tail":["fc7032dafce60cf86920f3c1c30f6a42b20e1d4c573da235d834ee4e4a7b3176","0de6b9812a88f2094fee035d58b9bde32af856f4f798bc7e2e06a4e99ba48c56"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b266a7e94e9418f9ecede752b3cbdd57f9b45f913a1d3b14bc485fd391c2f483"}
{"type":"tools-used","tools":["Bash","Read"],"sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"1f703328-81af-4cd2-b6a7-475c3c4fab1b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstgahgu6DpUJv16BsB","type":"message","role":"assistant","content":[{"type":"text","text":"Quick look at the figure, then the report."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1115,"cache_read_input_tokens":29105,"output_tokens":94,"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":1115},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXstgKLRwrvL7GQeMZ35","requestRef":"69179ed1-826e-43a5-b24b-a936cfbf48c0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"42bbd6c9-5f04-44ba-9676-0a303d80bf2b","timestamp":"2026-10-30T05:35:05.096Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"42bbd6c9-5f04-44ba-9676-0a303d80bf2b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstgahgu6DpUJv16BsB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_018Q7xaoGvKfF7eAQdJo7hgT","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0011/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":1115,"cache_read_input_tokens":29105,"output_tokens":94,"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":1115},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXstgKLRwrvL7GQeMZ35","requestRef":"69179ed1-826e-43a5-b24b-a936cfbf48c0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"85290339-556f-4943-8cef-1ee130177a48","timestamp":"2026-10-30T05:35:05.528Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"85290339-556f-4943-8cef-1ee130177a48","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_018Q7xaoGvKfF7eAQdJo7hgT","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"iVBORw0KGgoAAAANSUhEUgAABhgAAAJJCAYAAABYjz3AAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAT/gAAE/4BB5Q5hAABAABJREFUeJzs3Qd4FFUXBuCTSkhCCYTeS+i919CUXhQVuwIiKlLFAkhRQVG6gtgVxP6DSlNEqaH33kLvJbRAetn/+e4yy26ySXaT7fne51mYzLbZ2dkp99x7jpdOp9MJERERERERERERERGRFbyteTAREREREREREREREREDDERERERERERERERElC0cwUBERERERERERERERFZjgIGIiIiIiIiIiIiIiKzGAAMREREREREREREREVmNAQYiIiIiIiIiIiIiIrIaAwxERERERERERERERGQ1BhiIiIiIiIiIiIiIiMhqDDAQEREREREREREREZHVGGAgIiIiIiIiIiIiIiKrMcBARERERERERERERERWY4CBiIg8Rvny5cXLy8vkFhgYKGFhYTJgwAA5cuSIU5dv3rx5apn69u1r09c9ffq0el18fne1Z88e6dKlixQqVEi8vb3V51m7dq2zF4ts4NSpU/LYY49J0aJFxcfHR323+C1kBt+9Jdu09ptq27ZtuvuSk5Pl888/V/cVLlxY/Pz8pEiRIlKzZk15+umn1X0xMTHiiTLaJ7jqvgLfkav85qOiotS2iuVZtmxZpo999NFH1eP69+9v8eu/++676jlNmzaVlJSUDB+3e/dutc3mzZtXjh49atVnyE20Y72nwPaH7alUqVLi6+urPts777xjco6D33FuY6/zJyIiIrINBhiIiMjjdOrUSZ5//nl1a9Omjdy4cUO++eYbqV+/vqxbt07cDS6oLWmUdVd3796VHj16yIoVK6Rq1aryzDPPqO+uePHizl40l4eGJ+MGKFeTmpoqjzzyiCxcuFBKlCghTz75pPpuK1eubNf3vXPnjoSHh8srr7wiGzZskGrVqknv3r3VPJ1OJz/99JO6D8EPZ8vNjYauKDQ0VObOnaumX3rpJbl165bZx/3vf/+TRYsWqYbgmTNnWvz6Y8aMkXr16sm2bdtk+vTpZh+D4BgamfH/pEmT1H4xN3L1/Zs9oDPEd999pzpH9OnTR+0vsb04kqefcxAREZHt+drhNYmIiJxq1KhRJj2ab968Kb169ZKIiAjVYOTskQy2hgauw4cPq96u7ggNbefPn5fWrVvL+vXrnb04ZENoNEdPbDSi43+MTnGE8ePHy+bNm6V27dqqF3rZsmVN7sf2Nn/+fAkODhZP5O77BGfDyASMukEQYcSIEarB19j169dl8ODBavqrr76SAgUKWPza+E7QcNu4cWOZMGGCOjalDSBMnjxZjepq3ry5en/KHRITE2X58uVq1Ar2l2n3T6tWrZKkpCT1+yYiIiJyJRzBQEREHi8kJESmTJmippFq4uTJk+JJ0GCFHtqVKlUSd4TGXqhYsaKzF4Xs9N2WK1fOYcEFQMMwoId42uAClC5dWt5++22XSxVkK+6+T3AFn376qUqphWDA33//bXLfkCFD5OrVq9KvXz+V2s1adevWVdtffHy8eg2M9NEcOHBAjVoICAhQgQ1H/m7IuS5fvqxGrSBFl7ngJ37P+F0zcEhERESuhmesRESUK9SqVcswfeXKFbNpej744ANp0KCB5MuXT6UnQFqCadOmqV6FaZ05c0Y9HimY0FiZJ08elVoD6ZmyytttDaQpQE9rQEOUcX0JLX2BJfnWkesbQZbq1aur3pGYh96zaMzQPg/SIiCNDRq2sB7QkzIj1q6vzPLsIwUE4HNqny1tTv19+/apvPnouenv7y/FihWThx9+WDZu3Jhl2pnffvtNWrVqpXoZY55xyhM05uFzoxEa3yFy9Xfr1i3TXPBIv4MexuiBjNfEZ0fKn+eee042bdpk8th///1XBg0aJHXq1FH1JbBuEUh5+eWX1To3B8uHBkY0QiI4hu+rTJky0rFjR/nyyy9NPiPyuRvnddduxilFjh8/rkbuoJd0UFCQ5M+fXzVUPf7446pHrDXQqDpy5EipUqWK+iwFCxZUaYe+//57lXoo7baH3wcgNZm2bI5o1MdyAhrq7FEn4L///lPfB75TzENvcw2+11dffVVtE9o6ateunfz+++9mt39tO6hQoYLJd6ilTML29sUXX0jPnj3V94btAd9hkyZN5OOPPzb8hu1ZawHfH3ra4/W03wlqWSDN1IkTJ3K8zWcGje8//PCDtG/fXr0e3h+vN2zYMLP7cli8eLE8+OCDhn0ztgPsn1577TW5du2aRe+L4AKCDDBw4EC5ffu2ml6yZIn8/PPP6VIjId0WHme8jjI7HiBVEn7jGGmjvQ7200iNhH3oxIkTrU6NdOnSJZViR9uPY3//0UcfqdfNKBWXpftKrFNtm8fnw/Zq7jvFd4LnmgtuYd+h1UZKe5z47LPP1H2jR4+2av9mbMGCBdKoUSP1+lhOjERJu31mRlu+cePGZfgYrE88Bp9dExcXJ7Nnz1bHBGw3WPclS5ZU+0YcJy2B10QgFrBOjT+vJiffIbaNN954Q/1usf9AAAPvh981UthZc86RGW2/hv0lzhPeeusttS/ENvPQQw/l6HedGWuP5fY8NhvDOQpGQ2F7wLkLUj8i9ZXxMYOIiMgj6IiIiDxEuXLl0MKpW7NmTbr7Lly4oO7D7fjx4yb3nT17Vle1alV1X/HixXVdu3bVdevWTVe4cGE1r23btrqEhAST50ycOFHdFxYWpuvYsaOuT58+uiZNmhjeY8qUKemW4bvvvlP3Pf/88xZ/Jjy2UqVK6nktW7ZUf2u3iIgI9ZhTp06p+/H5jRnPf/TRR3XBwcG6Hj16qM8WFBSk7hswYIAuMjJSV7RoUV3lypV1jz/+uK5Ro0bqPh8fH93q1avTLVN21pc5hw8fVp8DnwvPw+fUPtvkyZMNj1u0aJHO399fPaZu3bq6J598UtesWTP1t7e3t27u3LkZbguvvPKK+r958+bqeQ0bNtTdunVLPWbBggU6Pz8/w+tiHbVo0UJ9bi8vL91nn32W7nVPnjyp1hOeU6BAAfW58d03bdpULWPa7xafKSAgQL1v79691fovW7asen6hQoV0R44cMXn83bt3ddWqVTOs2549e6rvpFWrVrqCBQuq9a4ZOXKkWm5t+Y23jT/++EM9Zu/evep7x2Nq1Kihe+SRR9RyNG7cWH32l156SWepo0eP6kqWLKleq3Tp0upzd+7cWZcnTx4176mnntKlpqaqx167dk0tR6dOndR9xYoVMywbljsr+A2b26Yz+k21adMm3XrH/BdffFGXkpKiswW8B14T6wzbR7169dQ2he8G6xn+/fdfXb58+dTj8F1hXeN52AYwb/To0em2f+23iO/G+DvEOgT8zrXtAa/1xBNP6Nq3b294ze7duxvWu8aSfYKlvvnmG8NvDb8PvD9+89ieMP/nn3/O0TZvvG7T7rsTExN1vXr1UvdhO8a+Ba9ZsWJFNa9UqVK6EydOmDxn3Lhx6j5s3+3atVPfEbZD7Xe7efNmnTUee+wx9bwXXnhBd/PmTV2JEiXU38uXLzc8ZuPGjbr8+fMbjglYR1hW7Eswb9SoUWZfe/fu3Wo58+bNqzt27Jjuww8/NOyvrN1uz507pytTpox6Pn6n2u8T3wW2LW2fiG3A2n3l66+/bjgmYJ3i8+FzYh72S1u2bDF5TW3bOH36tMl8bX+F29q1a03uwzJi/sqVKy3ev4H2evhtYV126NBBvRa2DczH9xUVFWXROsTvGM8pX758ut+UpmbNmuoxmzZtUn/je8J3ra0LHBOw/jAPx1XsHy2Bz6WtA+wTjD+vJrvf4cWLF9U+GPdVqFBB99BDD6ntGo8LDAxUvw9rzjks2XfjfKhBgwbqd4F9AI6v2vEmO7/rzM6fsnMst+exWYPfM94f+06sD6xzvB9eA+cLS5YsyXJ9EhERuQsGGIiIKFcEGL766it1Hy4QjRsOMI3GYdyHBo34+HjDfWhM0hpI0WhlbNu2bbpDhw6le5/t27erhmdfX1/VEJ/TAAPg8Xgenm9OVo2JuFWvXl136dIlw30HDhxQF7i48MV9+OzGDVpoENOCBcayu74yk9l6QcOI1mD7+eefm9z3+++/qwYErGutgTfttoBGh3/++SfDhj18V//995/JfWiARIMB7jduZMD60Rq80HgTHR1t8jw0CKdtgPnzzz8NjXSa5ORk3fjx49XrGDfswLx58wyNxklJSSb3YV2vW7fOZN6ECRPU4/G/OX379lX3o6EjrevXr+t27typs5QWeML3ZBxAwjrSAg9pgz1aY1PaAIC9AwxTp041bPtoUBs6dKjuxx9/NNu4bSmtETyj3yKCmNp2k7bRHcEEbZtctWqVyX0ZNRoaNxwj0Je2wfPy5cuqAc9cI78tAwxobM2oYR7BSQTdcrLNZxZgeOONN9T8Bx54wGT/hd/imDFj1H2tW7c2zI+Li1ONhmi0xLKltWfPHt2VK1d01rh69aquSJEi6r20wCZ+V8bviYAb5mOZjL8nBB60AN9ff/1l9vW13zACVlh23LKznaKBVAtUYZmMA4NaUCSzxumM9pVLly41BFS3bt1q8h1o3w8aZo2PBYMHD1bzv/32W8M8NPKjsbV27drpjhFYZwhQ45gUGxtr8f4NtM+F72j//v2G+Xfu3DEcq959912L1yO+B3MBENixY4chiKTB4zAPDcdohE673af9vWcmq99nVgGGjL7Dd955xxCASAvrSQuWWHrOYcm+W1snWqA0J7/rzM4TsnMsd8SxedmyZYbfRtrjLAILOG/BMuM4TERE5AkYYCAiIo8OMKAxCReGuMhEQ/WGDRtMnoNeqFoDpbkei2jgRqMHGj8y6tGYlnaBPGfOHJcJMKBndVroxag1wKYdcYBggdZggd6G9lxfma0XNAxpDRGZrRv0Lja3LWTUQ1/rlWzcAGZs+vTp6v4RI0aYBDQwDz0VjddJdqGXJgI8xoEKjHzBe8ycOdOi18iqAQ49zXE/GmFyAo0nWs/OtIEV4+8QvUJdIcCAbQ8NRVovf+Mbep+igcvSXs1pG8HNNZAbN5rhfc3BSBzc//DDD1sVYMgMenvjueixa68AA3o4Y/9pC+a2+YwCDPh+8P2FhISY/a6MA35agBHBAK0Xsy399ttvhu0HnwH7R838+fMN+wVzow603yh61puDfYlxz34Ex6yF7xWN9+gtb9xgq0HgL6sAQ0b7SoxYwP2TJk1Kdx8aWrXe7uhFnnZf+cwzzxjm/e9//zPsc/Gdooe5Bvsn3BceHm7y+tYEGMz1UtfeM22gPDMzZsxQz+nfv3+6+4YNG6buwwjGtNsG7supnAYYMvoOBw0apO43HvmRGVsFGMwFJbPzu87sPCE7x3JHHJsxShCPNzcKFIYMGaLu//jjjy1eLiIiIlfGGgxERORxkO9cyxmMXP3Iy4uczLt27ZKWLVuaPFYr3olczca5jjXIZR0WFibXr1+XyMhIk/uQdxl51ZFLG7m38T64aTl/jx07Jq4ABSGxTtLScmQjVzJyAxtD3njkME5KSpKoqCibrK/sWL9+vfpfq9OQFvKVaznizTHO+Wyc+/mff/4RHx8f6d27t9nnIXc2bNmyxTBvxYoV6v9nn33WqiKbyOc8d+5cGT58uLzwwguG7QTrFsuCGgka5A8H1Mv46aefDHnfs0t7PeSaRr0FS+tjZPQ9oO4Fam6k9cwzz6h1gnznFy5cEGfDtom87WfPnlX1C5566ilDPnsUUp06darKyY+8+dYyt00Z/zaQb9vSbcpSaEfFNo783/gukRsd29Dnn39u930NtiHkHsf77d2716TWhi22+YxgP4oiyMjRjn1RWih+jFzzxusU+e+Rgx3L+eabb9psveA7bdiwoZpGjQDsH9P+NvAbMFeQWdtHIRc7aiGkhd8NvldArQjUibBWRESE+l6wjSHHe1rY/rOzXaO+h1ZXxtw+2NfXV9WeSbsPxjEF62L16tWGedr0Aw88oO7fvn27ytFvfB++6+wyV2xb+81fvHjR4tdBrR98LtQlwDHeeF2g9gb2LTgGaOrXr6+OJd9++636PWr1X5who32TdhzAtosaIrGxsXZfFpx7NWvWzCa/64xk91hu72MzzpmwfaMuV9p6UpYsFxERkTvydfYCEBER2RoKa6KRBReI586dU40vaGBAIwsag1DMT3Py5En1/5AhQ9QtMygOiuK2WmMRCvVl1nARHR2d5bJu2LBBvv7663TzUahTu8jOKawLXICnhSKPgEKo5uB+BAoSEhJyvL6yS2usRkFRc1CU0fhxaWlFM43hM2nfjXFDoTnGBWHRWA3WFF4dO3asfPjhh2YbFs1tJwgEoREIjRho6EJjCwq1olgyijJrjRKWQiPrtm3bVHAEDXsofomGUjTuoGEQwSBbfA9okEPDrhZgQAHcnDAXvDJHa+zO6PFocEbwDzfAsn333Xfy/vvvy/nz51VjvRYYsJS5bcr4t1G7du1Mn29pkWENAiJoONy6dWuO9jXZheK7aLxD4VfcUNwUDYfYz2Ibwt852eYzoq3PRYsWZbk9GK9TFI594oknVBAJNzR0tmjRQrp27aqOAQg2Z4e2v0ShdGt+G9i/IoCLRlXse8wVHtdeG0VjzQUpsqItQ0bbJgr+4pZZo2hG+0rs/7H8Gf2mze2DsU0ggIeg/pEjR6RatWoqwIlivyiKi/3PH3/8oY7H+F60YvM5CTDgddPSgqHGx7Cs4Pvp3LmzKs79559/ypNPPqnmYx+K4AEajI3XFT4Tiq2//vrrqug5bpjXunVreeSRR9Tns3R/llMZff8IDqFh//vvv1dFnbG/RqFifBYExvBdOWpZsvu7Nie7x3J7H5u1wDUCDVn9nq09HhAREbkqBhiIiMjjjBo1yqTX2OHDh9XFIXqUYbTBjBkzDPdpF5do2DDXQGFM620XExOjGtzQ2PDiiy+qBgWMBkAjES4mv/zyS3nppZcs6umLHnJotEsLy2+rAENWF7jWNGhlZ305ExrsMvoMaDTTGo8ygh6IGmsbidADFg3Z+fPnl1mzZqltECM80MgPaPTcvHlzuu3kgw8+UA3iS5cuVT17EYRCL0vc0KBrbnvJCBpD0YC+Y8cOWb58uepljB6T6JU8efJk1XiMbdjVaI3A+K1lRrtfa6DNChpJ0bCEx48YMUL+/fdf1UvZ3HaSkYweq21XaMS2ZoRLVhBsRHABDZYYlVGnTh3VWIxGQvTQR8DLkn1NdtWoUUP279+vGoHRyIqALXoNY7t67733ZOXKlYbe/dnd5jNbn3j/xo0bZ/rYmjVrGqaxnjB6CsuIG5YXjdm4YXnxd0aNn+4us31UVvt5a34DlsAxAgEG7MPQ0I9tFcdF6NChg/of21THjh3Vd4LfvLke75bKTmAmI9jPIsCABnntGLFgwYIMR3K8+uqrKpiA5+Az4fMgkIkbPit+N/i92ltG3yHWDY4bb731llrGNWvWqGPAzp07Zfr06TJu3Dj123DEsmT3d53Za1l7LLf3sVlbrkKFCkmPHj0yXS4E34iIiDwBAwxEROTx0Mvsq6++kp49e8qcOXNk8ODBhl6XWiM5GgUxRN4SaDxAcAGNaggmpGVJ+g+NNiTfXWRnfeUEGoTRAxa9HtOmtzLuDWlNj3k0NGAUC9IgIH2O1qiQFfTQB0vTrqARA9CQgZQ21mwn5cuXN4wSQSMHGsLRKxsNXlj36D1uDaR30FI8oCc1tlukhRg6dKgaiYMG68xo61db32khfYg2wiOnoxeMtzP0AEWv64yWT1uHGY3CyYjWwImGoJs3b9qkcRXLjOVBQ52WfiynEEBBQz5GIKFRK+16sGZfkxMImKBXN26A/R9Gx6BBDftTNMbldJvPaBto0KCBzJs3z6rlRWM10nnhpqVCefnll1VDLwLQSHVjK1n9NjBSBqnJsM9Bg6M9lCxZUv2v/QbN9cTGdm4tBImxf8QIAHwOc0HljPbBCDBMmzbNEGDQ5mnHZDTo4j4E/u/cuaMCDbYMzOUEzhUwCgP7XYwgwv4BqYUQsEV6wIxGCiIYiBsgKIhGbwQcvvnmG0NwxZnQqI8bfrvYZ+P3ivMPpOjCccURjd05+V3b6lhu72Oz9hmxH8rpZyQiInIXrMFARES5AnqRoZcaLkS1fNegNZhpF5yWuHHjhvrfXGMLGpJQl8GWtPoIaBBwtuysr5zQ0g7g4t0c9BAFpCmwFHqSIl0QGpeRAsNSaADTerJiO8rJdoJGJ0tTI6BXMt5ba9jat29fjrYNNMggsIA0Hgg2WBIw0b4HrC80Bqb1448/qnWChnVbBBjQWKelolq8eLHZx+Azo9Ed0ua5zqqHvFYfBA1Sxj1bnfHbyOw7RHAFqd7QQGsuyGLLhnJrII0MevOm3R5ttc1rQSA0OCMooOXqzy6MWEAv7bTLawvabwO/AXxXGe2jECC1Vy92bbQbRihduXLFZtsJlhe9uTPaB2MfqvXsT7sPxkgSfH9IzfPff/+p/ZhxLSBMo1bGb7/9lmF6JGcd+7BfQNobfD58r1hG7CsRsLJ0tFTTpk0NwQZbb3O2gO8WDePYfrG/xCglR6x3W/6us3sst/exGcfAWrVqqaBcZqntiIiIPAkDDERElGtMnDhR/Y8GES1HLhoMUKQRF7tImWIuN/jp06dVXm+N1ssPvS+PHj1qmI8GVvQKRx56W9IabJHqydmys75yAul70KCDBiqMQjGGHqV4HzQyoMHcGuPHj1fPQw5+cw0TaLBAGgnjAozIXY30NBhRgcKtaRtH0NseKRPSbidYbuOABNYP0mqZgzQueI20DeRoaNZeWxtJYcm2gdQN5optozEJvbqROsOS3v9ohMKIHTTMYF0bfx68/ttvv62mR44cKbaivRbSeuzZsyddIA+/NfSeRu57rae6BqlWsN7NbZ8HDhwwFNJFbYO0Bc6zCznYEQh45513VI/ltLm98Z2itzZ6vBrL7DtE/QDkFkeR5bSNxNj20fhpTygGO3PmTJNC7xqkWkm7PWZnm88syITn4L3x/ZobIYD1gp7LWkMotmmse3NBMHPLa6sC0PgOcSyYMGGCyW8XjYtIQQPZKd5sKYzIQ65/NIKjZ7VxzQFtVE12YT8PqGeBVGsaBFOQbgyvj3Watrg59ttIgYM8+WigR20S1EQxbmjGutIKlZsLMDjz2KcVr0ZgJbP0SDgPwCijtI3x2Edpv3Vbb3PWwmfYvXt3uvloAEeQx9rjSk5k53dt62O5I47N2m8Oo1iMC6Abbx8IkON8goiIyCPoiIiIPES5cuVw5adbs2ZNho/p3LmzeswLL7xgmHfmzBldjRo11PwCBQrowsPDdU899ZSuZ8+eurCwMDW/adOmJq/TtWtXNT9Pnjxquk+fPrrSpUvrAgMDdUOGDFH3Pf/88ybP+e6778zOz8ru3bt13t7e6taxY0dd//791fJv3LhR3X/q1Cn1uvj8xjKar5kwYYK6H/9ntj7xOsays74yk9V6WbRokc7f3189pn79+uq9WrRoof728vLSzZ071+JlN/bDDz+o7w+Pq1Spkq5bt266J598Ute+fXtdSEiImv/ZZ5+ZPOf48eO6ChUqqPsKFiyo6969u+7xxx9XnxfLaPwZIiMjdfnz5zd8B4899piuU6dOuoCAALXOtM9gvL0OGzZMzStatKjaVp9++mm1fWmv07JlS11iYqLh8ZcuXVLbHO5r3bq1rm/fvmrbWLx4sbq/bt266r7KlSvrHnroIbXu2rRpo/P19VXz33jjDYu/p6NHj+pKliypnlemTBn1ubt06WJYh1h3qampJs/BZ8N9eM/sGDBggHo+tv3mzZur5cfnKFasmGE97dy5M93zsF3ifj8/P13jxo3Vun/kkUd0DRs2VPNxq1mzpu7y5csWLws+Q1b7l3///VdtF3gc9gf4vrHM+F9b5rfeesvkOR9//LGany9fPrWM+P5wi4qKUvdPmTLFsMz4/rGete911KhRVv32s9onpHXz5k31eB8fH12DBg3Ufg7fe7169dR8bEfatpbdbT6zdZuQkKDr3bu34bts0qSJWoZHH31ULY+2HcfFxRn2ldp+uVmzZronnnhCPbZKlSpqfnBwsG7r1q267NCWEfurtDZs2GD43FWrVjXsR7DetO8pM9rvxNLvxRzsl0uVKqVeB/9jPWHfgXX/8MMP68qWLavuu3DhgtX7ypEjRxq2A3wufD5tnWJ737x5s9nnjR071rDtDh8+3Oy2qB1HkpOT0z0/q/0baK9hjrXbe1raZ9R+zykpKekeM3PmTMN66NChg+FYWKRIETUfr4HfkSWyWt6MvqusvsNevXoZ9ts4ZuG48uCDD6ptA/OxrVhzzpEZS/b51v6uszpPsPZY7ohjM3z00UdqHeJ+nDPh2IV9ErZl7Isw/++//85ynRIREbkDBhiIiChXBRh27NhhuKg9efKkYX5sbKxu1qxZ6iIRDQW4H42paKRCI8nevXtNXic+Pl43ceJEXfXq1dVFKS46cYF86NChDC+EsxtggP/973+qEVu7KDVu6HJ0gCE76yszlqyXPXv2qAaD4sWLq/cKDQ1VjSYRERFWL7uxY8eO6QYNGqQagfLmzasLCgpSjfE9evTQffnll7rr16+ne86tW7d077zzjq5OnTqq8Qs3PAfLn7ahDQ0ZaDTBusF2gsZHrG9sP+YaVdGw8+abb6rG9BIlSqigBT4z1vMXX3yhnpfW6tWrdW3btlWNdAi4GH+nS5cu1Q0cOFA1SBcuXFg1wmDdoJHpr7/+0lnrypUruhEjRqjPi2VDo3irVq108+bNSxdcsEWAAZYsWaIa7LA+8N3jN4DPM3r06AwDBPv27dNNmzZNNQDhu8Vy4rlo5Ecj4Jw5c8yuy5wGGAANuPgOa9eurbYnbFcISqFBD7+ZtA28aLTEvqRatWqGRrK02+4vv/yiAiX4HPie8X0vX77c6t++tQ2uSUlJKoCHfZu2HvGZsB2j0XH//v3pnmPtNm/Juv3999/VNovvT/v94/f38ssv61asWGF4XHR0tG7GjBlqe6lYsaJaVjQAonEPDdxZ7Q+yG2CAEydOqIAYGvKxjGjYxHdu3BhuzwADYNvC94L1hG0J39mkSZPUusfvFY2dxo221uwr//jjD90DDzxg2N/jc2LfktnzsG/Stmf8jtPCd4T78H1l9hoZ7d/sHWDAutNeP6MgEbb38ePHq2VEEALrHcGFRo0a6aZOnaq7ffu2xe9nrwDDunXrdEOHDlXLhHMVbAtYVuwLf/75Z7PBnczOOTJjzT7f0t+1JecJ1h7LHXFsBgTAsczly5dX2wb2R3gvBDUQGLl7926W64mIiMgdeOEfZ4+iICIiIiIiItvbuHGjqtNQs2ZNlSKMiIiIiMiWWIOBiIiIiIjIjSFfvbk8+6gNMXDgwAxrCBARERER5RRHMBAREREREbkxFJ1HkfHy5curIrb58+dXRa937typgg8o1P7ff/+Jn5+fsxeViIiIiDwMAwxERERERERuDEGEcePGyapVq+TUqVNy69YtCQwMlOrVq8sTTzwhgwYNEn9/f2cvJhERERF5IAYYiIiIiIiIiIiIiIjIaqzBQEREREREREREREREVmOAgYiIiIiIiIiIiIiIrMYAAxERERERERERERERWY0BBiIiIiIiIiIiIiIishoDDEREREREREREREREZDUGGIiIiIiIiIiIiIiIyGoMMBARERERERERERERkdUYYCAiIiIiIiIiIiIiIqsxwEBERERERERERERERAwwEBERERERERERERGR/XEEAxERERERERERERERWY0BBiIiIiIiIiIiIiIishoDDEREREREREREREREZDUGGIiIiIiIiIiIiIiIyGoMMBARERERERERERERkdUYYCAiIiIiIiIiIiIiIqsxwEBERERERERERERERFZjgIGIiIiIiIiIiIiIiKzGAAMREREREREREREREVmNAQYiIiIiIiIiIiIiIrIaAwxERERERERERERERGQ1BhiIiIiIiIiIiIiIiMhqDDAQEREREREREREREZHVGGAgIiIiIiIiIiIiIiKrMcBARERERERERERERERWY4CBiIiIiIiIiIiIiIisxgADERERERERERERERFZjQEGIiIiIiIiIiIiIiKyGgMMRERERERERERERERkNQYYiIiIiIiIiIiIiIiIAQYiIiIiIiIiIiIiIrI/jmAgIiIiIiIiIiIiIiKrMcBAREQZ8vLyUjd3EhMTIz/++KMMHz5cWrZsKUFBQeozPProo85eNCIiIiIip3PHc/xDhw7J0KFD1fl9qVKlJCAgQJ3n165dW0aNGiVRUVHOXkQiolzL19kLQEREZEuRkZHyzDPPcKUSEREREXmITZs2yezZs1VwoWrVqlKsWDG5deuWbN++XT766COZP3++rFu3TqpUqeLsRSUiynUYYCAiIo+SL18+6d+/vzRq1EgaNmwou3fvlpdfftnZi0VERERERNn0wAMPyNGjR9MFEGJjY2XAgAHy888/y5AhQ+Sff/7hOiYicjAvnU6nc/SbEhGRe9CGTrvzoWLevHnSr18/eeSRR2ThwoXOXhwiIiIiIqfyhHN8Y+fPn5cyZcqIr6+vJCQkiLc3s4ETETkS97pERGSRBQsWqFEBgYGBUqhQIVXT4MSJE1x7RERERERuyhPO8RFYAH9/f7erLUFE5AkYYCAioiyNGTNGXnjhBSlYsKB07dpVXYAsWrRIWrduLdevX+caJCIiIiJyM55wjp+UlCTjx49X0126dGGAgYjICRhgICKiLH399deya9cu+e+//1SaoSNHjkjTpk3l0qVL8umnn1q8Bk+fPq1O+q29Ic0RERERERHl7nN8LFvfvn3VrUePHlK2bFn56quv1HLPmTPH6tcjIqKcY5FnIiLK0nvvvSe1atUy/B0cHCyvv/66PPbYY7JmzRpDr6Gs4HnPP/+81Wu8cuXK/JaIiIiIiHL5Of7t27dl/vz5JvPatWungiXFixe3+vWIiCjnGGAgIqIsYbhxWlWrVlX/X7x40eI1GBoaytEIREREREQuwB3P8atVq6aKU+N24cIFWbt2rbz99ttSu3Zt+emnn6RXr14OWQ4iIrqPKZKIiChLZcqUSTcvX7586v+EhASuQSIiIiIiN+PO5/hIsVS6dGl55plnZOXKlSrg0K9fP7l586azF42IKNfhCAYiIsqSt7dt4tFRUVFq2LW1BgwYIK1atbLJMhARERERkeec42PURbNmzVRap4iICOnZs2eOX5OIiCzHAAMRETnM3bt30+VMtUTbtm0ZYCAiIiIickGucI5fpEgR9f+1a9ds8npERGQ5BhiIiMhhypcvr4YvExERERGRZ3D2OX5iYqJs2rQp24WjiYgoZ1iDgYiIiIiIiIiIXNbHH3+sijqndfXqVenbt6+cP39eFYBmWlUiIsfjCAYiIvI4Dz/8sFy6dMlkmDRysiI3q2bu3LnSoEEDpy0jERERERFZZubMmfLaa69JzZo1pUqVKuLr66uCCrt27ZK4uDgpVaqULFy4UHx8fLhKiYgcjAEGIiLyOLt375YzZ86YzLtx44Zs3brV8Hd0dLQTloyIiIiIiKz1/vvvy4oVK2THjh2yatUqVfchf/780rBhQ+nRo4e8/PLL6m8iInI8Lx2TYRMRERERERERERERkZVYg4GIiIiIiIiIiIiIiKzGAAMRERERERERERERETHAQERERERERERERERE9scRDEREREREREREREREZDUGGIiIiIiIiIiIiIiIyGoMMBARERERERERERERkdUYYCAiIiIiIiIiIiIiIqsxwEBERERERERERERERFbztf4pnu3ixYuybNkyqVixogQFBTl7cYiIiIiI7CImJkZOnjwp3bt3l5IlS3r0WuY5PhERERHlFjEOPs9ngCENBBdeeuklu694IiIiIiJX8MUXX8jAgQPFk/Ecn4iIiIhymy8cdJ7PAEMaGLmgfQG1a9e2+xfgrpKSkiQ6Olry588vfn5+zl4cj8J1y3XqDridcj26Mm6fXKfuwtnb6v79+1XHGu3815PxHN89tklPxnXLdeoOuJ1yXboybp9cp+4kKZed5zPAkIaWFgnBhebNmzvkS3BHiYmJcuPGDSlUqJD4+/s7e3E8Ctct16k74HbK9ejKuH1ynboLV9lWc0NaUJ7ju9c26Ym4brlO3QG3U65LV8btk+vUnSTmsvN8FnkmIiIiIiIiIiIiIiKrMcBARERERERERERERERWY4CBiIiIiIiIiIiIiIisxgADERERERERERERERFZjQEGIiIiIiIiIiIiIiKymq/1TyHQ6XRy+/ZtuXPnjiQkJKi/c5PU1FRJSkpS68Dbm3EqrlvX4eXlJcHBwVK4cGHx8/Nz9uIQERERERERERF5LAYYsgHBhIsXL0p0dLT6Gw3sua2RHY24aLzF/8R160qSk5Pl5s2bEhsbKxUqVOA2SkREREREREREZCcMMGQDeu0juJAnTx4pUaKEBAQE5LpGTIxgSElJER8fn1wXXLE3rtucr78LFy7I3bt3VaChUKFCNvpmiIiIiIiIiIiIyBhbhrMBaZEAwYW8efPmuuACkStDwKtYsWImv1UiIiIiIiIiIiKyPY5gyAbUXEAjJkYuEJHr0dJ3IV0SEZGr6DxrvVyPSbTosYWD/GXF8HC7LxMREREREZEr4XWT+2GAIZs1GBBg4MgFIteE3yZ+o0iXRES591jtahBcuHYnwdmLQURERETkllzxHJ9sj9dN7ocpkojIIzEASJT7IC3a+PHjVYH3kiVLqv/xN9OlERERERG5J57jE7k+jmAgIiIij7jwaNu2rezatcsw7+LFizJx4kRZvny5rF27VvLly+fUZSQiIiIiIsvxHJ/IPXAEAxEREbm9qVOnmgQXjGE+7iciIiIiIvfBc3wi98AAA1nk1KlT8tBDD0mRIkVU6pl+/fqp+T4+PtK3b1+PWovo5YrPOG/ePGcvCplx+vRp9f288847XD9EZPDtt9/m6H4iIiIiInItPMcncg8MMJBFEERYt26dvPXWW7JgwQIZOHCg3dbcrVu3VOMxGvrJtSEIM2vWLGcvBhHlcij2duHChUwfg/v/+OMPiY6OFneQkJQit2ITnb0YREREREQufY7/+eefq46IlDvdjU+WDZFRkpCc4uxFydVYg8HFd6auUKg2ISFBIiIiZPDgwfL666+reampqZKSkiIxMTHi5+dn8wDDu+++q6aRT5tcO8CAA/nw4cOdvShElIvhWFmqVKksL0B69+4tvr6+0rJlS+ncubO61a1b1yWOtWlFxydLg4n/SoOyIdKuWlFpV7WoVC+RzyWXlYiIiIjIWef4r7zyivq/WrVqhnP88PBwyZs3L7+UXCAuKUWe+War5PXzkRaVCkubqkWkTZUiUq5wkLMXLVfhCAYXLGAzfvx4KV26tHh7e6v/8TfmO8uVK1dUsKNQoULp7gsICLAowOCs5Y+Li5Pk5GSnvDcRETlO//79LXocjgkYkTd69GipX7++lCxZUo3S++WXX+T69eviSlJ1IjvO3JSp/xyVrp9ESPPJq2X07/vkn4OX5W4Cj21ERERE5NksPceHI0eOqAwLCDCg/apLly7y8ccfy9GjR1WbFnl+oGHVkasyfvFBaTN1rbSdukZmrDzq7MXKNRhgcCFohEeP/YkTJxoitPgff2O+Mxrp0ehSrlw5NY1RBYgg46alLzJXgwH3Y96qVaukVatWEhwcLD169FD33bhxQ0aMGCGVKlVSwYnChQtLw4YNDcU38boVKlRI937ly5e3aFnx2GvXrqmDULFixSQoKEjOnz+v7r99+7ZK8VS5cmXJkyePqifx5JNPysmTJy1aFzggffbZZ2p5AwMD1edq166drFmzJt1j586dKx07dlTRdn9/fylRooQ888wzZoftLV++XNq0aSOhoaEqwo7P+thjj8mxY8dMHnfp0iUVmS9btqx6TTSKIVXV1atXLVr+bdu2qXVUpUoVtfz58uVTvXiRMsScy5cvy9ChQ6VixYpqfRUtWlQefPBB+ffff9X9WE400p05c8bwPRlvG7jf3AgUczUusG2PHTtWmjZtqtYD3g/f06hRoyQ2Ntaiz0dEudsbb7wh+fPnN3sfAgn//fefTJgwQe1njEcBYF83f/58dTzAcaFZs2YqTd+WLVvUSD1nCfL3kUblQsTbaMDC5eh4+XnbOXlpwU55/be9Tls2IiIiIiJHneOjDcScBg0ayN69e1X7S8+ePVX7jyY+Pl5WrFihsi1gZAPaNdCesnjxYqd24CXbK5DXTwa0qiBhRYNN5p++HitnbqRvTzp+9Q4DTnbAFEkuBI3su3btMnsf5uP+9957z6HL9NJLL0m9evVUUODhhx9W6SWgevXqmT5vx44dsmjRInnxxRfl+eefN8xHw/n69evl5Zdfljp16qgRBocPH1aNzjhw4HVnzpyZ7v3QmG8pNIIXL15cxo0bp1I44bkILrRo0ULOnj2rgg81a9ZUDfY4EKGxCcurBVIy8uyzz8rPP/8sjz76qCpyjdRRP/74o3q/33//XR3QNNOmTVONVGigR+T8wIED8vXXX8vq1atl//79KrACaKDH82rVqqV60xYsWFAFldAQdvz4cXUgBCx38+bNJTExUV544QUVoMH9CHggwIHlL1CgQKbLj0ACIvp9+vRRnxU9ddGohnWMz/HUU08ZHotACIIPGL3y3HPPSaNGjdS6RIMblg2fGT0DsMxRUVHqO9NktW2Yg8+M9fPII4+o5UAKE6ybKVOmyO7du+Wff/6x+jWJKHdBYDIpKUlNYx+CkQoIxGKfieMLgqodOnRQwQPs/xAsxUUHbtjXaYHkrVu3qhuC3CEhISpYjF5QnTp1UsFiRwnM4ysLX2mh6jCsO3ZN1h7F7arcjNV/xrZVi5g8/kp0vHy29oSa36xiYQnw83HYshIRERER2QPO4Rs3bqzaRDRpz/HRtoTgAdpLNm7caDjH37dvn0kbB2o14GacMhWjHPB8piF1X/6+3jK2ew0Zi7alW3Gy/tg1WXf0mmw8HpXumul0VIw8MGO9FM8foNIo4f4WlUNVkIJyhgEGG3vggQdUj+7sOHXqVKb3f/DBB6qBOzvQoIyGYWuhURsNKmjwx04XvfCNazBk5ODBg6rxButDg0Z+NLBjxz979myzz8Oog4ceeijd+1kDjfU//PCDybxhw4apkQpoIEe+bQ169NeuXVv1ajXuUW+ucR6N8F988YVJgWu8LgIJ+B+jNLSDEoIIxtFzQCAB6+Obb76RN998U81D9BzrEusKIwQAf6PhHqNDNEOGDFENZ2hsR9os44AN3h8N/Gg0ywxGCEyePNlkHgIg6Nk7adIkkwDDoEGD5OLFi+qgjEY1Y1g+wPeEIAOCRNn5noyhN8G5c+dM0m29+uqrKkiEZcPoiyZNmuToPYjIs23evFntjwBB7DFjxqhgLkZ8pYX5TzzxhLphn4aLD+1CBBclWmq9mzdvyq+//qpugOOHltcVQWtzr52ZwkH3Hq8TuXY3QU36eHtJIW2+mccWDPSXXvVKqVtKqk72nr8la49clfbV9McMDYIP8zadVrcAP29pWSlUX7uhWlEpVZD5Z4mIiIjI/eBcHZ0PoUyZMqpNB1kPzJ2HYx6yTOD20UcfqY6MK1euVOf4+B/1Po1TpmppU9FBVTvHR5uN1iGUnMdw3SQisQnJEpOob3/MH+AredJ0pDJ+LK57nmxSVt2SUlIlNU1qrPWR1wwjw3/dcU7dcD3WoGxBFXBoU6Wo1CyZX7yNh5GTRRhgsDEEF9Cz3B7QoG+v17Y1NMIYBxcA6X/QwxQ9QxE9tiTtUXZohag16JGK4ACK/CBlEXrcaxAEQAM9DjaZQcACkXE0qhs/HxBYQON+ZGSkSj+kva52MMTwOwQHsE4wygCfX6ONOtBGeyCSnhYCM8uWLVOjJpBWyvj9sQ6RSgjLn1WAwTjggbRDaIjDumnfvr2K4kdHR6v0IkhjhQOw1mM3LdQGsTXjkwMc7LHOsL1jG0KAAeuMAQYiyoxxEB0jFSzthYR9Gkbq4Ya0bNgXIhiO/eDff/9t0lsKQ7BxwwULRsfhfbSLEUuOaSuGh6v/IyKvybPfbFPTL7SqIGO6WjbyS3/yG6JuaW04fr9+RHxSqso/ihtUKRZsKBTdsFyI+PkwQyYRERERuT50BNLaQHDubU17BNp/0I6CG9oZtm/fbuhUhGmtLgNSpqLDKW54fbQ9aOf4yOZg3PmTHEO7boInvtwsW07eEFzerXujnYSY6ZxljrlrnspFgqVXvZJqlIM2MhyduLafvqlu01YeUwGLl9tUkhfDK9rwE3k+BhhsLKs0O1mNYMhsVAB2alp9AkcuV3ZoDe1pG5HR4x29/fE5atSooRq30WiPA4UlUF/BeB1hnSBndmbvjecgHQYa4dM+VpPVQQppnNDojREWGUGKDe290TiFdFZoGEfuP2PoEasZPHiwGsWAEQOoD4GaFWjUx8gERNEBBYkQqMDIB9wyGgGQFdRqwCgGvJ+5ug2I5iPAgCAWDrQY2eBISFeFQAdGv2ijJMytMyIic7T6MAjUtm7d2pAuyVrYD+K4hBv2hdgHaxciSOeH9Hhw9+5dtT/FDapWrWq4EEFdHQTVM4ITWk14mPnjkrWmP1ZXnmpSVtYcvSprjlyVyKt3Dfcdu3JX3b5Yd1JGdammTpgz03nWerkek2g6U6dT+2Z1vDQK3uAE3PgCgIiIiIjI1uf4gPaj7MI1AjJ04IZUqAhaGKdM1dpIcL6LURK4oRMnUl5rKVPxvyNTppJITEKy7Dyjbw+qU6qAxcGFjCAdEm4IKhy4cFulosVt99mbknpvsAOug3x9TDur3Y5LkmNX7kj9MgXF10zgojOvnxhgsLXspCHSjB8/XhV0zgjSPTi6BkN2oYiwOUhb0atXL1XYGMPRFi5cKHPmzJHHH39cfvnllyxfF7n3jFNQIXCStnBy2vfWotLoDY9G/OzAayA48dNPP2WamgkQCceBByMLPvzwQxVMQUMTetNq6Tg0GHqHx0dERKiDG+pTvPbaa+pAhlELyAuoLT/SEBnXszCWWUOWtvxYJgRKEOBBFB6jJxCg+e6779TnStuon1MZ9R7WUo8YmzFjhowcOVItI9I2IaciAlIY0og0VrZeNiLyLAiQYl8KuGjAiDOMxrLFfgy1cHBDgTiM/sJ+WrsQQfBBg2ncPv74YzXaDEEGLeCA4IPxPnH9MX0vLKQyalQ+RO2jc5r3FblHm1cqrG4YEXHuRqxKm7T6yFXZdOK6JCTr96Np85BuOXldNp+4rkY44KQdw4FxUn3tjj6QQkRERETkCm1sSH1kK0iz9OSTT6ob2hswSlk7x9+0aZOh3QLXFGir0tqrMOpZO8fHdUdmKVNtcY6f2+E6JSlF3yYWXsU2HbO0keF1yxRUt6EdwuR2bJJsOB4l645dVQEHpEsyhuuqYb/skXwBvtI6LFTdj+UpUUDfFned108MMLgSFKhBw7u5Qs8NGjRQ93sCRHwHDBigbhiNoBVPRgMzAgiZ7YCR6kjLsW1JwzogMIDiyUh7kTZtk6XCwsLk2LFjKp1SVgWn0ViPz4XUGsYjTlAk2VxPfDTyt23bVt1gz549aj28//778tdff6lABdYJChZld/kxrBAHTASxEK03huLKxrT3w3JkJbPvCpF+cw18qIWR1oIFC1R6Eawz49EkOLgTEWUFxe61QGR295OWQABbu6DQRh6iCD32VatWrVKjGgAj1zAfN9QUQjBce169pq3k2NU76nGFkm9I5QrlVDAVQ7j79+9vKFaXU2UKBcqzzcurW3xSimw+eV22nbohVYuZvvafuy/IL9vPycerItVohDZVi0hCUsajKYmIiIiIHAHn1OjcA0g5jbqVtuhElBbaIJDBATfUZNDqh2oBB+OUqWgnwQ2dSXHOrqVMRSYKtGkg88XUqVPl22+/tcs5fm6j1UywdYAhrQKBftKtTgl10zr5GkPQAe7EJ8tf+y+rG+DaCtdPSfc6c92nk97eEWrq99TWaD0TT8ckvC4EOxukX0BhW+yEAP/jb8x3950Ren7ilrZxHcWcQTtQaA345g4c6NGPxiPthr8tOVg8/fTTqlAwRkyYYy5lkLHnnnvOUHw5o/RIxp8J0u6UUKQ7bU/8tPUcAD1lETjRghEY5dC1a1f5/fff1TC9tPA+SAOVmYyW6cCBA6qAddrAQJcuXVRjv7kROcavge8Ky2luB4x0UUeOHFEHVQ1Si3z66admlw/BCuPXQY8BHLSJiKwZOv3ggw86bIUhiIyReX/++adKxYdAB0bK4QLIGEbeffHFF/Lwww9LWNkSUnzLx5K84RvZ/esMwz4S/2MUI4LNuDCxpQA/H1V/4a3O1UwCw9jnoqeOBj1vft91QaLj0480IyIiIiJypI0bNxpSTjvyHB/ZHnDejvN3ZMw4dOiQyrqAjAuoK6rBOTuuA3A9gOsCtIGgwybO6R1xjp8baKll8+XxlXplCjrkPXG9lLYzbe/6peXZZuWkTCHTTs5Hr9yRL9eflFtxpul5W3gflBn+n6tbc+9DkhuwBoOLQRABaZBw87ThVBgBgJQR2FEjnVBISIhK2fPZZ5+pnTFyZmsN6tgpYwhapUqVVN0DFChGMeXswmgAHJz69OmjbhiJgKFsaPTBKIGGDRuqgj4ZefTRR1VhIKRzwgiT7t27qyF158+fl82bN6u6BVrPfHy+mTNnqqDAwIED1fug8QujCPAcYyjsjNfAgQo9XDE649dff1UHHqRE0mAdoT4DClUj2IHIOoIVeE/k/8a8zIo8V69eXWrWrClTpkxRQR6k68D3gQNm7dq1ZefOnSaPx+ds0aKFCjQgLRPWD5YNNSUQlUeBU8B6RCon1JLA4xEoQF5E9CzAPHyHCAThgIsRGBipYC59FtYvgjd4v969e6vRJhgJ4ufnZ8W3TES5lRYMRf0EjABzRlo17Ou10WgIjl68eFHV/kGvJ/yvBY0RPN2y9n5AJC0cY9DryREpEXGO8few1rLxeJSsOXJN1W+4ytRIREREROQCjDs8OjLAkPZ8Ge0puGFkMtpTkO5bG92AdhVNZGSkS5zje4rklFTp3aC0CjIUyx9gtmizo7QKC1U3tNOevh4r647qUylhlHh8UvrRC8N9Fxn+wvTmxBoeP4qBAQYX5knBBShTpowaGoYenojyojc7RmigkR09Po0bnpEKCTtv1J3ADhyN7zkJMCACjQDD9OnT5bffflON8ijyU7p0adVwj3RNWcEQN+T8+/LLL2Xy5MmqwRyFmJG+Cn9rMKpi0aJFKkqN0ScYjYBGdhyEECAwhvRQCGzMnz9fjUJA4xiKX6NhHoWejdcdggBo2Mey//DDDyrHN+ZjvSBokhk0/CP91uuvv67eC+maEOTBNFInpQ0wIOCzY8cO9RkQgPn+++9VQAi9chE00eA7QpADI0NQoBmNevh+EWDAesBnw8gNDAfEd/3KK6+o+g9pi3rjfuyoUcQaNSKwXlGXA0EdrA8ioowgUKydzGMfjX079s/OhloyqCGDG9LmoUaEdiGCYG1WxxtHXXzkC/CTzrVKqBv2wwcvRsvjX2yWmESmSSIiIiIi549SRkcetNu4ArRboWMkboD2EC1l6tKlS81md3DGOb4nQDFl1EfALVWrwOwC7bQVQoOkQmgF6duygkpFu/30DRn4/U6Ju5dmFqMXmnjfr9XX1PuIGsWwObWmeDIvXWZbfy6E3ujoiY2iLijYYo7WkIG8/LkVGpLRYIKGa+Oc+cR16yqMf6dobETKLaR/yqwIE1mO69Q2uB5zDoFJLUiM0VevvvqqS69XnHZZctzEcdZZHQ0av/+fxUWei+TLI9vftl/dC0/n7G3VkvNeT5GbPqs7b5OejOuW69QdcDvlunQVSD+Kepo4d0aWBNQ7c+Xt0x3O8c1x5XXqThobrp908pv/eyYBBtiaWk0eTxynRjE46vrJ0ee+bBkmIiIij6i/YM8Cz7bwdcRJeWH+Dind/hnx8k+fLk6DEV+udOFBRERERORIKLKs9Yd29XN8wLm7Vks1IzzH93wt0oxeSDuKwZMxwEBERERuCT2A0JsJkDIOhdVc2T8HL8vqI1fFt/HjmQYQkE6QiIiIiCi3Mu5E5Kz6C9bK6hye5/iWO3ntrqw6fEViEpLFfehkhO/CDO/V12Xw3CRCDDAQERGRW0INmaioKEPPJlfu9R8dnyS7zt5S03VKFZB6NauafRzq+qAuDRERERFRbi/wjFqQ9evXF3eAc3icy5vDc3zr/L7rghr5Xe+9lbLzzA1xB62890tj7/tFv3PbKAYGGIiIiMgtuVPPpk3Hr0vKveJk7aoXk7Vr18q4ceOkRIkSJsOmMT9fvnxOXFIiIiIiIuc5ceKEnDp1Sk136NBB1f50BziH187x06ZL+vHHH3mOb4X1kdcM09WK5xdX55WaIjP95mb5ODWKwUNLITPAQERERG7ds0m7+HCXk+TWYUXUBcZ7770nFy9elDZt2qj5Fy5ckDt37oizFQ7yV8XHTG7B/lI40Ff9bzwfjyUiIiIissc5vqt3IkpLO8c/f/68fPzxx4b5WlpXytqNmETZf+G2mm5UrpAE5fF17dWWmipzvD6UIl7RWT4Uoxja5zkinsjFvyUiIiKi9OLj4yUiIkJN161bV4oWLeqyqwkF6tYf0wcY8gf4St3SBUzu7927t6xbt05NL1myRF5++WVxphXDw9PNS0xMlBs3bkihQoXE359BBSIiIiKy/yhldyjwnJGHH35Yhg0bpqb//PNPefXVV529SG4hIvKaoZN/eJUi4tJSU0WWDZcmybssfspHZbeJJ+IIBiIiInI7GzduVEEGd+jZdPp6rJy/GaemW4WFiq+P6elXr169DNO4+CAiIiIiyo1SUlJk9erVarpixYrq5q7KlCkjDRs2VNNInXTz5k1nL5JbWH9MX2MPwquEistCFOSvkSK75t+flzdEJLiYuumCikpKYBH1vzZP3Zq8KJ6IIxiIiIjI7bhTzyZt9AKEh6XvhVOuXDlVvG737t3qgur27dtSoIDpKAciIiIiIk+3a9cuQ0O8q5/jW+Khhx6SnTt3SnJysixfvlyeeeYZZy+SS8PIb4xggNDgPFLdVesvqODC6yI7vtX/7Rsg8uQvIpXaGR6SlMtGgHMEAxEREbltgAEna61btxZ3CTAkBGyVuGT9aIa0Q6gh2StZPlz6oUOXj4iIiIjI1ToRufooZUto5/jAkcpZO3rljly9k6CmW4eFire3l7hkcOHvN0W2f63/2yePyBM/mQQXciMGGIiIiMitREVFqd7+0KpVKwkMDBRX7oWjpUcqVeaATNv9ngxZNSRdkAG9m7z8vaTc8HKyLGWZLD6+2ElLTERERETk3ALPXl5e0r59e7f/GmrUqCGVK1dW0ytWrJC4uPQdjSiDkd+umB4JwYUVo0W2fan/28dfH1yo3EFyOwYYiIiIyK0gjRAa7t1h6DQujlYMby2rR7aRDzs9K02LN5Wtl7emCzJUqlZJqo2uJsE1giXuaJy0Kd7GqctNRERERORIsbGxqs4aoHYBUsu4O1wLoCMRxMTEGAIolHX9hdZmUss6Fa4//3lbZOtn94MLj/8oEuba16OOwgADERERuRXjE3N3GDqNC4uKRYKldeWSMrvD7HRBBtyGrh4qPhV85O6hu3Jy+knZtH6TsxebiIiIiMhhIiIiJDEx0W3O8S3FNEmWG9S2kgxoVUG61ymhajC4VHBh5ViRLZ/q//b2E+mzQKRKR2cvmctgkWdyqrZt28rp06fVjYiIKCsYuaDlZg0JCVHFkd1JXt+8KsiA4AKCDC+ufFHN33ttr1TNW1V+n/W76BJ1Kkdr165dnb24REREREQOr7/g6qOUrdG0aVMpVqyYXLlyRZYsWSIpKSni4+Pj7MVySS0qh6qbS0Fw4d/xIpvnGAUXvhep2tnZS+ZSGGBwAZ1nrZfrMfoobVYKB/nLiuHhdl8mIiIiV3Ty5ElDULpDhw4ufXKelJIqPl5e6YqTaUEGBBcQWIC6RerK5x0+l/UF1su1a9dk8eLF8tlnn7n05yMiIiIisnWAIW/evNKiRQuPWbE4n+/Zs6d89dVXqpYc0kCFh7Ndzy0guLDqXZFNn+j/9vYVeWyeSDV2BEuLKZJcAIIL1+4kWHSzNBDhLlauXClHjx519mIQEZGbcKeeTUv3XpQmH6ySEb/ukcgrd9LdfyfxTrqLjweffFAqv19ZfDr7yE9rf3Lg0hIREREROQd69+/bt09Nt27dWgICAjzqq2CaJDcNLqyeKLJhpmlwoXp3Zy+ZS2KAgZzK399f8uRxobxqRETkNgEGV8/NGhEZJVF3E+SP3Rck5V5RakDNhVdXvSonb59UfxfMU1CNZEDapDKtykhAqQAp3L6w/L3lb5PXS0hJkHN3zhkKXBMREREReYJVq1a5zTl+drRv316Cg4PVNFKh8nze1KXbcTJ95VHZfvqGJKekiktY84FIxHT9tJePyKPfilTv4eylclkMMJBF5s2bp4pUrl69WqZNmyZhYWFq51itWjWZP3++yWN//fVXNfyrbNmyKngQGhoqDz30kCEanbYGQ/ny5Q1/P/744yrocP369XSPxUgHLMPw4cPTvV+rVq0kX758EhgYqPLbLVy4kN8sEZGHQb5SHIegYsWK6uaqUlN1EhF5TU0Xy59HqhbLZwguIJCw/fJ2w2M7le9kKPy8x2uPpMbpT6q3/7Hd5OJj5+Wd0vX3rvLAwgdkxekVDv9MRERERET28N9//3l0gAFtY1p9tVOnTpltH8vN1h29JrNXH5fHPt8sP2876+zFEVn7ocj6KUbBhW9EavRy9lK5NAYYyCpjxoyRBQsWyMCBA2Xy5Mni7e0tffv2VTnkNHPmzFHz8ZhPP/1UXnzxRYmIiJCWLVtKZGRkpq///PPPS1JSkvz888/p7vv+++8Nj9GMHTtWnnjiCRVcmDhxonz44YcqyPDYY4+p9yYiIs+xc+dOuXXrllukRzp0KVqi7urTGrYOK6IC5FpwAYGE+kXry2sNXpMGRRtI1wpdVU0GBBkuxFyQ4JhgOTHxhBzfeVwOHjxoeM0dV3ao/6/GXpX8/vlN3u9KzBVZcGiBHL5+WFJSUxz8aYmIiIiIsgcdarRRykWKFJHatWt75KpkmqSMrb/XMQtahRURp1o3RWTtZP20l7fII1+J1HzYucvkBljk2Q6+23hK5m/SF6DMzDPNysmA1tb1vrxxN0Ee/2Kz/PpSc5P5Ly3YIUcvp8/vDM+3KC/9WlYQW0hISJDt27eLr6+v6kmKhvzKlSuroAICCLBixQoJCgoyed5zzz0n9erVk5kzZ8rcuXMzfP1OnTpJ8eLFVTBh8ODBJgecH374QR1o6tevr+bt2rVL3n//fRk9erR88MEHhscOHTpUjZjAfLwvgg9EROT+3Klnk/FJcngV/UnyytMrVXABgQQEFFDsuV/tfobHYZ4KQMhWyVM8j8SdiFNDqGvVqqXurxVaS7qU7yJ7ru2RekXqmbzf5kubZcp2fS+bsU3HyuPVHnfQJyUiIiIiyj5kqzh//ryhExE6rHqiLl26iJ+fn+pUi3P8CRMmOHuRXAJSIm2IjFLTZQrllfKFA523MOuniqx5/35w4eEvRWo94rzlcSOe+at1sluxSXL6emyWt5ux1hdsTtGJnL8Zl27+pdvxGb4PlsdWBg0apFIYaUqVKiVVqlQxGZmgBRcQFIiOjpaoqCgVha5ataps3bo109dHgcunn35aBTGOHDlimL927Vo5e/asyeiFH3/8UfUIxTy8h/ENKZru3LkjmzdvttlnJyIi59J6NmHf365dO5f+OtYf0wcYvLxEWlcOVdO9KveSSS0nGYILaWEe7htTf4zc3XpXzfvjjz8M97cv216mtJkiKx9dKYF+pifeu67sMkw3KNbA5L591/bJgJUD5LO9n8np21l3gIDFxxerERcZwX14DBERERGRrToRufoo5ZwoUKCAqsUAe/bsUamSSGTv+dsSHZ+sVkX4vZHfThExQ2T1pHt/eIk89LlIncf4FVmIAQY7KBjopyJuWd1CAu831FvKx0ukdEj6RokSBQIyfB8sj62Yy3dduHBhk5oJu3fvlu7du6uRA9iBIriA2/79++XmzZtZvocWRNBSImnTWvBBc/jwYRXEQB0I7T202wsvvKAec+XKlRx/ZiIicr6YmBhDOr6GDRuqY4+riklIlp1n9Me7OqUKSEjQ/eM9ggzmggsa3PdknScNFx8YrYcAe1ZerfeqfNj6Q3mq2lNSqWAlk/u2Xd4mWy9tlbl75sqJ2ydM7otPjpe7ifpghgaBg7Ebx6rRFOaCDFqqJzyGQQYiIiIiskUnIncYpWzLNEmLF7OzjnHHLOOR3w63YZbIqneNggufidTliHBrMEWSHSAdka1SEqVVKDhPuvRI8MWzjcQR0MhvjlaEEo0g4eHhkj9/fhk3bpwatYARDVpx5rt3TRsxzEEaJKRTwggFpECKi4uTRYsWSceOHVX6JOP3xOv+/fffGS5XzZo1s/1ZiYjIdaCWD4YTu8OFx5aT1yUJQw7v1V8wlpyaLF/u+1Lalmkr1QtVz7CHDlL9rVy50nDxMWTIkEzfs1hQMelWsZu6pXU55rJ4iZfoRKdqPhhbd36dvLn+TalWqJqMbDhSmpRoIh3Ld5SlJ5aqdE4IJGBUhY/4GIILIyNGGlI94bFERERERNmRnJwsa9asUdNoPypTpoxHr0hk23j55ZfVNNIkoZ0st9NSy/p4e0nzSk7oRLZptsh/WroqL5Fen4rUe9Lxy+HmGGAgm0IqBwQRlixZki59BUY55MmTx6LXwSiGESNGqAPNpUuXVLoj4/RIEBYWpuo9lC1bVqpXr27Tz0FERK7bs8nVh05n1gtn55WdKlURbv1r9ZcRDUdkePGBtITasTWrAENmxjYbK0MbDFUFoEMCQtItT6ouVQ5dPyQBvgEmqZoGrhyoAgkv/fuSzG4zW+JT4mXM+jGy/cp2kzoSRERERETZsW3bNtXe4w7n+LZQokQJadasmWzZskV1oLp27ZrKwpFb3Y5Nkr3nbqnpBmULSv4A22VgscjmT0VWjr3/d8/ZIvXvZ04hyzFFEtmUNpJAG9Gg+eqrr+Ty5csWv85TTz2lCkkjNRJuSLXUq1cvk8c8++yz6v8xY8aogtNpMT0SEZHn5WbNmzevtGjRQlxZHj8flZ4wOI+v1C9b0OS+/87czzHbrESzDF8DNY6aNm2qptevX2+SijA78vvnl6Yl9K9nrHLBytKoWCMJyRMi1QvfD9YjcNChbAc1vfvqbnl6xdPy1o63GFwgIiIiIrvUX3D1Ucq2TpOUmpoqy5Ytk9xsw/EoSb3XfIj6Cw615TORf8bc/7vHJyIN9O2MZD2OYHABhY1yM9vysc7QpUsXCQwMVI3/gwcPlpCQEJUz+6+//pJKlSqp4W+WKFq0qHqthQsXSnx8vKqpEBCg71mpady4sbzzzjvqhpRKjz32mJQsWVKNeNi5c6d6z8RE6wtpExGRa0HAeN++fWq6devW6Y4HrmZM1+ryVudqcu5GrPj5mPblwIiFRsUbScT5CPV/ZpAmaevWrSqIvnz5cnnuuedsvqx9qvZRN6Ru8vU2PS3cF6Vf53Dmzhn1f53QOhy5QEREREQ2HaWMzqpt27bNFWsV5/hvvfWWIU1Sv379JLdyWv2FrV+KrBh1/+/us0QammZNIeswwOACVgwPF0+BIAJqImBUwQcffKAOEi1btpR169apgMPp06ctfi2kRFq6dKmazqhRZcKECdKoUSP55JNPZNasWaoIKIITtWrVUvOIiMj9rVq1yu16NiGHaPnQoHTzA/0CpVP5TupmycXH6NGjDWmS7BFg0KQNLsDAOgOlRqEasuDwArkRf8Nu701EREREuQ9SIyFVEDRp0kRlrsgNqlSpotJ8Hz58WNVcQzsWapfmRqO6VJNWYaGy9dR1qVXKQd//tq9E/n7j/t/dZog0yr1BHlthgIEs0rdvX3UzZ+3atSZ/o8jzhg0bsnxcRvM0jzzySLpUS+Z069ZN3YiIyDO5U/0FW6pWrZoqdnf06FH5559/JDY2Vo0SdJRy+cvJtEvTVHABIxcwChGjGrTCz6y/QERERETZhY6oWpaL3HSOr3UkQoABGTtwnt+7d2/JjUKC/KVH3ZLq5hDbvxH56/X7f3edJtL4Bce8t4djDQYiIiJyWQg0awEGFECrU6eOuKqklFSVFskeOVrj4uJMAi32FpccpwIJKPKMgs5z282Vjxp9JI2LNVbzcB8eQzlnSWcKIiIiIk9jfG7rLqOUbX2Or6VJIgfY8Z3I8tfu/91likiTF+36lrpcdJ7PAAMRERG5LPTev3DhgqFnk7e365667D57S1pPWSPtpq2V5fsumdy379o+eXvD27Lu3DpJTEm0qneTBmmSnBFc0EYrBPgEyMzwmWoegww5Twkwfvx4qVChgqofhf/xN+YTERER5aYCz8HBwdKsWTPJTRo2bCilSpVS00gNnpSU5OxF8mw754ssG37/784fijR9yS5vdSeXnue77lU6ERER5XrulB4pIlJfpOxUVIzk8TU9xfr71N+y5MQSGbx6sGy+uNni12zcuLGUKFHCcPGhDSO3p5WnV6YLLmgwjXlakAGPJevg4gJFDCdOnCgXL15U8/A//sZ8T7/4ICIiIkIHokOHDqkV0aZNG/Hz88tVKwWdpnr16qWmb926JevXr5fcJD4pRV6Yt12+jjgpJ6/dte+b7VogsnTY/b87fSDS7BW7vNWdXHyezwADERERuXzPJncIMKw/pg8w+Pl4SfNKhU3uQ+0CCPYLluYlm1t18aGNYrhx44bZGke21qtyL5nUclKGdRa0IAMeg8eSdaZOnSq7du0yex/m434iIiKi3HKOn9vSI2lyc5qkHadvyqojV2XS8sPy87az9nujPT+JLBmCZEX6vx+cKNL8Vbu93dRcfJ7PAAMRERG5JAwVXrNmjZquUqWKlC1bVlzVjZhE2XfhtppuWC5EgvL4mty/oMsCdRvTdIz4+/hb9drGaZIcdfGBwEFmRZxxH4ML2fPtt9/m6H4iIiIid+dOnYjsBSM3ChQoYDjHz035+tffG/kN4VWK2OdN9v4i8ueg+8GFB94VaTlU7OnbXHyezwADERERuaTt27cbhpG6es+mDcejRLsmMHeS7O3lLfWK1pMelXrcn4kn7PlZf8vkggLDabWLD9RhyE0XH54G351WUyQjuJ/fMREREXkqnOdoAQakAq1Ro4bkRkgL1b17dzV9/vx52blzp+QW2sjvAD9vaVy+kO3fYN9vIn+8fD+40GGCSCujGgx2oMvl5/kMMBAREZFLcqf6C9pJMoSHWdgL59Q6kT9f1t9OZZx31d/fX7p166amz549K3v27Mn5ApNTeHl5GQr6ZQT343FEREREnujgwYNy+fJlwzl+bj7vyY1pkq5Ex8uRy/pOZE0rFJYAPx/bvsH+hSJ/oIDzvYb89mNFWr8m9uaVy8/z3T7AgHzEr7/+ulSuXFkCAgKkSJEi0q5dO4mIiHD2ohEREZENAgw+Pj7q2O6q0AtFK/BcOMhfapTIb3JfBk8SWfvh/b8xnUlvFmekSTLQ6cR7/68ScPTPTJeRLNO/f/8c3U9ERETkKZ2IXH2Usr116tRJ8uTJk6sCDCYds2ydHunAIpHfXxTRper/bve2SPgb4igNGjTItef5bh1gOHPmjDRs2FDmz58vjz76qMydO1fGjBkj5cuXz3JYChEREbmu6Oho2bJli5pu0qSJIUWQKzp65Y5ciU5Q063DQsXb+36vlDl75sjAlQPlf8f+J3HJcaajF85uvv/32U2ZjmLo3Lmz4eIDaZIc6tQ68V06WAqueUu8zti/yLSnq1mzZqYXJW+84biLICIiIiJHc6dRyvYWHBxsCLJgZEdkZKR4uvWRUYbpNlVCbffCB/8QWWQUXGgzSqTNm+IoN2/elI0bN+ba83zTCoRu5plnnpHk5GTZt2+fyttGREREnmHdunWSkpLiFhceGfXCweiFv0/9LefunJM91/ZI94r6HKuSnCTy37vpX2jFKJGec0QC8ovkySfiHyziH4TxtpIvXz61HpYvXy779++XEydOSKVKlez/4dKMtPCJmCIS1l4tE1kvLi5ORo8ebfi7cOHCcv36dSlZsqS88MIL6qID3zURERGRJ0pMTFTn+VqnC7bl6dMkLVu2zDCKwZMboVNSdbLh3sjvkgUCpFKRYNu88KHFIgtfENHprx8l/E2RtqPEkcaNG6ey7ECjRo3k4sWL6pZbzvPdNsCwfv162bBhg3zyySdqh5SUlKRugYGBzl40IiIiyiGt8JvVQ6e1dD53Y0Sa9XPI91C2UKAaubD99A1pFRYqkpIsEn1Bbl87JPkQTMDIBq8gyfvDYyK3zojcOi8i93rWGLt6SOTr9mlmehmCDQuapcix4kESnaCT1J+fEqlZ/34gAv9rN/X3vXn+2vxgEb8gEW8rB6+mGWnhfW6LfqRFxTbZWle53ZQpU+TUqVNquk+fPrJgwQIVYECgAbU2iIiIiDzZ5s2bJTY2Vk3n9vRImh49eoi3t7ekpqZ6fIDhwIXbcjM2ydAxyyb1CA4vFVnY/35wofVIkXZjHNohavfu3fLZZ5+p6dDQUFm5cqUEBQXlqvN8tw0w/PXXX+r/smXLqh/j33//rXo6hoWFyfjx49XoBiIiInLvodM4MWvatKn16XxEJKlEmEiVDrZfuOREkejzIrfOidw6K51xK3ROUr3OiPfXb6jgAobmYhl+FZHzvj6S6HVRJCk5G2+mE0mIVrcQFEIrfa8IWvIRkb1HrHwtrzTBhywCE/h748z0L4MRDRXCOYrBSidPnpTJkycbtuvp06frvxWOBiEiIqJc2InI1UcpOwpqybZs2VLVkkUABgWwixcvLp5o99mbhunWYTaov3Bkucj/+oqk3rvOajVCpP04h16nIDD06quvqv/ho48+kpCQEDVaJzed57ttgOHo0aPq/xdffFEFFVCHAV8eLtaeffZZNZqhX7/Mey6eO3dOzp9HL8L7kHYA8Hy8njnYaLCRaBtPboS0D9rNketh3rx5amjRqlWrpG3btlY/f+3atdKhQwf55ptvpG/fvuKKnLVuPY22DvE7xu8Z6dTwP9kG1ynXoz3h2Hz48GE1HR4erv7P6JhsQqcT39UfGApMea//SBLLtbL+BDM5QQUQvG7jdla8EEi4fU687t3kziXxQsN/GhmNDSidrO9No/P2EwksJF53r2T69ilVu4kEFBCvhDsiiXdFEu6q/70S78qdqIsS6JMsvkZ1HiynE0nEa95RnyHbzm6SpMjVoivfOvuvkQsNHTpUEhL0tTpQM6xo0aJO35d66nExu+f4xOO7PTn79+6JuE65Tl0Zt0/z0LMb/Pz8pHnz5lYdkz15naLjNAIMaMP4/fffZcCAAQ55X0ev06cal5LwyoVkw/Hr0qRcfsu/f4xSP/Cbmkyt1Udd33lF/iO+i/qJ173gQkqzwZLSejQ+lDjS999/rwJDWu3Ap556yiXaoRz9vm4bYLhz5476H/mr1qxZYxhu8tBDD0nFihXVhdvzzz+vhhllBI3M7777bobFJbXcWea+JOwMtdzQNqfTidd+/Q9HV1v/w3E12Olpn9+RETm8L6DhPTvrX2uwN15+V+OsdetpsB7xW8XvGP/fvXtXzcNvl3KO69Q2uB7N03KQAi48Mjoep+V/frMUOr/V8LfP+a1y+8BfkliquekDk+PF5+5F8blzQXzuaP8b3WKvZuv7RAAhJV8p/S245P3pe7fUvKFSaOlz4p9VgCH6itxoO93s8f/zzz9X5y4BviIzJr8nj/boKF5JMeKVGCPeSQhCxIjXvf/v/43774r3vf/V30kx4q09VuvxY81nXfOB3Oj5g0ueo7jqiBzUzwDUzsBIW1c4PuF81xNl9xyfeFyyJ2f/3j0R1ynXqSvj9pne7du3ZceOHWq6YcOGqhHWmmOyJ69TrVMVLFq0SHr37u2Q93XGOkVi+46VAiUl7o7ciBPLr/OWDVbTNyRYvJLjpeA/Q8QrVd+IHlO3v9ypOxiVlsXR2/SoUfpaD2i/e++99+TWrVsusb06+jzfbQMMefPmVf8/+eSTJrmsMAylZ8+eKoKEUQ7Vq1fP8DXQE75Tp07peje99NJLkj9/filUqFCGGxA2HB+fe2kKbO3kOvFe+qqaTC1YWp+GwMVoDf1YB45sBNfeC4Gj7Kx/LeBk1+/PTdetp8G6w04cv2Ps2PE39g+ediLiLFynXI/2tGXLFpPePBkdj9ONXlimz3tpLGTDu5KKEQFqNMK9UQgx2Qwg+AaI5C8tuoJlRFegrOgKlJaDsQWlTPkqElysokhwUREvbyQikrjEO5IPaYaMeJ1aL36Xd2b5Pv6XdkjhO4fMjhB4/PHHVcNpfLLI0tWb5YWhb1n/Oe7dVMgdx5yUhHujJO6oAASmvc5tFt91k7O1jGQqPj5eJkyYYPgb9cO0Ye/O3pfifNcTZfccn5y/TXoyrluuU3fA7ZTr0p7QQ1/r9InjtLXHY0/ePrEuateurc5XUG/W19fXIedpbrFO01znFdz8oXjdOGEILqQ0eVn8OrwnhZzQfjZx4kRVZ0HLsNOuXTtxlXXr6PN8tw0wlC5dWv1vLi+ZVoX+ZhaRqzJlyqibOfjyMyrCoTVSZzY6Ittwob/+o/vvte4jfSFFF2to1tJE4WaX9ZAB43WfnffN6fM9ed16Gm0dar9jHKAz+12T9bhObYPrMX2QdfXq1Ybjed26dS0Ltp5cK2I0ekHjdfOU+GyZY9mX4RcoUqCMSMGyRjf8XU5NewUV0Q/Hvffwi7fipNeHq8UrIkb6t7wr47qXNbzUC3+9oP7vXqm7DKh9b4jznvmWLQcWZfc8s/Uj0HFCu/jAekLKHYzmzJk8IoH505yLTM56GTdMEwlr73LnKK7mww8/NBR2fvTRR6Vr164usw9w2QvJHMruOT7p8bhkP1y3XKfugNsp16W9IPuIpnPnztk6Hnvy9olRCzjHx8gOpAVHxyJHcPl1muY6zzvKqA5d01fEp/Nk8XHC9ciePXvU6HIoXLiwqrWWdh3mpvN8t229RF4rSJtf1Xgectu6nVPrRM7qc3cpZzeJnFovzobaB2jgwU4OQ34qVKigomFIXaH1NF23bp20atVKFS5EoxAieWn9+eefqngNHhMcHKymFy9ebPY9v/rqK6lWrZrkyZNHKleuLLNmzTL07jc3quStt95Sj8PjUSQHo1tQUJGIiNzHgQMH5MqVK4bCbxYFF3BsQOHhrPgFiRStIRLWSaTxiyIPThR5bJ7Ii6tF3jghMuaiyOBtIs8sFOk+Q6TVcJFaj4iUbnRvdILpsqw/ds3w9mVC9CMr4eStk3Li9gl123t17/0nNHlRJLiYZTc8NgNIBwkILvzzzz9i93ORjLjIOYorQ2BBK+wcGBgoM2bMcPYiERERETm1wHOBAgWkUaNG/BYyOMfX2s48Cdryes7ZIK/+tEuW7r1ozRMzvs7D9VznyU7p7ITPM3jwYMOInA8//DDXj5D1decf3rBhw+SHH36QsWPHqsZquHTpkvohVqlSRTU2u5WMfjiYhzRJLtBDELnFUB8AhQox5B+N/h07dlQpqTAcfeDAgfL000/Lb7/9JuPHj1eBCOQZhrlz56rK6gga4D4tcIHv8osvvlDP1eB1R4wYoXqufvDBBxIbGyvTpk0zGzRCcKFFixZy9uxZ6d+/v9SsWVNtB3i/pk2bqhx/5cqVc+BaIiKinF54wIMPPmi7BvHHfxSp1s2mx9L1kfoAA4RXKWKYTkpNkral28rGixulY/mO95+AY/nrx3L8vjhuakH8P/74Q/WKt6nt31jx2K/1Iy3JLJzL4HwJcL6aUa96IiIiIk925swZiYyMVNNII4Oe3WQK7V9ou8K6Qu0udCZCB1pPcPp6rOw7f1vd0Djfo27JnF/nVe/utHbSBQsWyMaNGw0d4Pv37++U5XAlbvuLRg4rNDgjl2qzZs3Ul4lhRJ999pn6f/bs2c5ZsPk9RW6fy95zk+JE7lwy30NwRnURv/u9I62GlA/PL5GcQnABIxZwMMA0GvMffvhheeyxx1TVdC0KjWADdoyffvqpCjAgXdWbb76pChtu3brVkAvslVdekfr168vIkSOlT58+UrBgQVUQ5e2331ZpIDZt2qR6/EG/fv1UcCItBCswUgHLhR2ypm/fviqNBPIeI5BBRETuUQxX06FD+hRB2R69sPlTfYDBRpJTUmVDZJSaLh2SVyqEBhnuq1qoqszuMFvuJt4VX2/bn2rhuFm2bFkVWMfFB857bDrsFqMnzpmmm8KFQKpOJ9730s+ZPJbM+uuvvwyjNNHx5bXXXuOaIiIiIsntnYgwSpnSwzk22tfQ4fbOnTsqpRRSSXkCbeQ3hIfd75iVo+u8tR+JVHB8Snm0Wb7xxhuG7wztnt5Mb+6+AQZAj/fQ0FCZMmWKjBs3Tn2hSNnz008/qdQ7ToHgwg07pOUxF3hwAgQE0IihDQNq3Vpf3BEjBYyHuOExiOJpET00GMXExKiRD8aFRjCNecOHD1cHHPTCXLlypRqxgNEOWnBBq7uB0RFffvmlSYPHjz/+KOHh4VKqVCmJitI39gDSMCH4hNcjIiLXh146SLcHCGCXLFnS9ul8bNTbft+F2xKNSsv3Ri+YS+UU7K8fXWlreC+MYkCxYIziwzqzeLSHJcyMtEhKTJQbN26oob8um5/VhWDUAs5vNOj44ik90IiIiIhy0onIpuetHgbn+AgwALKzeEqAIcJo5Hdro5HfObrOs/H1naXQifnq1auGdmmm+/KAAINWBAU3l4GRArYcvWAsX4nsj2LI7nKlUbFixXQjSQCpkNLCfVo1da24IRqM0tLmafUStP/NjVaoUaOGyd/Xrl1T74EgAuoumMNIIhGRe8BINASYrbrwcFI6n2z1wrEhLcCgpUnihZprwSjbEydOqGmcpyKdJBEREVFuhA6qqOcJGIUbFhbm7EVyWegsjYLBaOfCSFik/nb3Nq3E5FTZfELfNlipSJCUKpjXdqPUHZxSft++fTJnzhw1jY5X77//vkPe1x24fYDB5WQnDRF+ON91yTrAEFJBpN9fTq3F4OPjY9V8e9OKPmOIHYo8ExGRZ/RssnjotJbOJ/62SLI+170ub4ikevnaNZ2PFmDw8faSFpULG+bvubpHaoXWsktqJGMYQYiTWowqwMUHTnTd/eLDU5w+fVrVj4K8efPKzJkznb1IRERERE6zd+9eQ7YJnOObG/lLekhH3rNnT/nuu+/k8uXLKsU4MrW4s51nbkpMYkq6unWuOEo9q/ZHZFrRMrpMnjxZBYNIjwEGV+CCPxxb00Y+HDx4MF1O7UOHDpk8Rvv/yJEjGT5Wg1ELqNsQHR3NPH5ERB6SmxUn1m3aWHisQ4+V4QdEplXWBxjylZCkwXvkxs1bdkvnczs2Sfacu6WmG5QtKPkD/NT0uehz8uzfz0pInhB5qe5L8nT1p8VesI569Ogh8+fPl4sXL8qOHTtUakJyjcLOcXFxhsLO6KlHRERElFsxPZL1I5URYNDSJLl7gGG9UXokiwMMThqlnhmkZ9+wYYOabty4sao9S/exq5srsPaH44aQugE1EZCDGMVqNJjGvODgYEN6B/yPHn8olKKlyoDz58+r+hrG0FsTdRm2bdsmCxcuNPveWm40IiJyXTdv3pTt27eraZxE47hgVaAeIxigek8RL/ue3mw8ESWpuvTpkf49qx+BcTPhpgT4BIgjLj40SJNEzrdixQp1IQgY/j9y5EhnLxIRERGRyxR4bt++vVOXxR2gTUyrR4pzfC1zh7vSRn77+3pLswoW9viv8zgqz93/O2+ISHAx8zcbjlLPCOrevf766yaFnZ2VycVVcQSDK9DSO1j6WDeEUQYoxo3hRCgI3bdvXzV/3rx5cvz4cfniiy+kQIEChtoNEydOVD/eFi1ayHPPPacCDZ9//rm6WN+9e7fJayPnGYpJ9+nTR91Q2Bk9Vs+cOSN//fWXNGzYUL0PERG5rrVr1xqGm1pdT+CgvkFXqdFL7K1a8XwytH1lWR8ZZdILp3GxxtKnSh9Ze26ttC9r/4sn5PVHQB695dGojWG65Nwi5UOGDDH8jRoZLOxMREREuVl8fLxERESo6Xr16knRokWdvUguD+f3KO78+++/S2RkpBw+fDhdPVJ3EXU3QQ5ejFbTTcoXkrz+FjbKH8L13b3ASsO+Ij0+Fmd655135MqVK2p6wIABagQDmWKAwRUgvcPrx8TTDRo0SEqUKCFTp06Vd999V82rW7euisga98IE9PhD79UZM2bI6NGjpUyZMirggCBE//79TR6LeQgwTJ8+XX777TeVixqpI0qXLi2tWrVSP34iIvLQodMpSSJHlumn0YOlbDORZH2OT3upWCRYXutYVd2M1S5SW93GNhvrkNyy6NnUqVMnFVxAWkHcqlWrZvf3pYwLO6PTBDz88MPqwpCIiIgoN0NbDYIM2epElIuhjQwBBsC5vrsGGM5cj5HQYH+JupsorcNCLXvS0b9F9v9PFgcHSUfvgpL3wffMPiwuOU5Wnl4pvSrbt4PZ/v37VeYVQAperdYamWKAgSyCEQfaqIO0MhquhVEDaUcO4IIbN0u89NJL6pZWv379zDayjBs3Tt0y07ZtW7cfXkZE5MkBBgSNGzVqZPkTTyI90q376ZG80SvGvgGGrDiycB0uPrSUPPh/1KhRDntvug+jJjGiEljYmYiIiCh9JyIUeCbLdOvWTaXgSUlJUZ1yx4wZ45arrmG5QrJtzANy6FK0FM2XJ+snxN0SWTZCBRfGFiksS/NXltm+/pI37cOS42TIqiGy9bI+G4y9ggxoPxw8eLD6HgDBhdBQCwMluQxrMBAREZFTnT592tDzu127dmoUmsXU8Nl7apqOhssNunfvbsj/qQUayPFee+01Q2FnXACWK1eOXwMRERHlelqAAWkjW7dunevXh6XQUx4dZGHHjh1y7tw5t1133t5eUqtUASma34IadSvHity5JB1jYqWpTwHZGn1cBRIQUDAXXGhavKl0LN/RbsuOOrDr169X00i/zgwpGWOAgYiIiFym8JtVPZuM0yMFFRUp21zs7aetZ2XdsWsSn3R/lMS12Guy5MQSiU7U5xd1pMKFC0t4eLia3rp1q1y8eNHhy5Db/fPPP4Yh7JUqVTIUgCMiIiLKzaKiogw1NFu2bKlGeZLljFOJL1myxPNX3YnVIrsXqMm8gUVkds/fVAABgQQtyJA2uDC7w2zJ62uf7So6OtrkvJ6FnTPHAAMRERG5TIDBqtysp9aLxN3UT9fQ0iPZD4IK7y07KM9/u00e+3yzYf4/p/+Rtze8LW1+bSNrzq4RZ158oA4ROa+wM/KzBgRY0DuLiIiIyMOtXr3akKKa9Res16vX/bQ/SJPkbu4mJFueojzhrsiSYff/7jZd8uYvqQIIWpDhxZUvqpsjgguA2rGXL19W0y+88II0bdrUbu/lCRhgICIiIqdJTU2VVatWqekyZcpIWFhY9tIj1bB/eqQdp29KfFKqmm5WsZBh/r9n9EO/U1JTpGZoTXFmgIFpkhxrxowZEhkZabgI7NKli4OXgIiIiMjDRimT4dpIq023du1auXnzXscqN/Hi/B3SesoaGfvnfklNzSLQsOpdkdtn71/XofMYRjL45lWBhJqFa8rea3vVrW6RuobgwqaLm6T3kt7yxro3ZM/VPTZb9gMHDsjHH3+spkNCQmTy5Mk2e21PxQADEREROc2ePXvU8GmtZ5PFBZKRHumwlh6piEi5FmJv6yOvGabDqxQxTE9oPkFerfeqPFT5ISkaWFQcrWzZstKgQQNDT7Fbt+4VvSa7Onv2rEyaNElNY9TCrFmzuMaJiIiI7hXH1eovoJ5A/fr1uV5y0JEIRYaXL1/uNuswJiFZdpy5Iedvxsnec7dVHYYMndkksu1L/XTeQiJdp6Z7SFSc/noR7ibeNUxH3oxUtxWnV8jthNsmzzl1+5QMXzNcPtn1iRyMOpjtws7vv/++FCly/9qPzGOAgYiIiNwvPdLpCJG4G/rp6j3snh4J1h/TBxjy+HpL4/L3RzBULFhRXq77srzX8j1x9sVHcnKy/PXXX05bjtxk5MiREhsbayjsXL58eWcvEhEREZFLOHHihJw+fVpNd+jQQXx87H+u7omMRyq7U5qkLSevS1KKftRCeJXQjB+YGCuy+NX7f3f5SCT4foct1FwYvGqwXIm9ov72Fm85cfuEoSZDUmqS5PfPr+6rWKCiyUsfvXFUVp1dJV/t/0oOXjcNMKB23oydM+TP43/K6dv67VTzyy+/yLp169Q0OnENHDjQos+8+Phik2LUaeE+PMZTOTzAcOXKFVUBnUUIiYiISOvZBO3bt7d8hRx0bHqkq9HxcuTyHTXdtGJhCfBzrYukhx9+2DDNNEmO2W4XLlxoKOz8xhtvOOBdcwdeKxAREbk/pkeyjRo1ahhSyK5YsULi4jJuwHYlWscsCA/LpPf/2g9EbpzUT1fpLFL7McNdWkHnbZe3SYOiDaR/rf4yoM4Ak8LPT1d/WjY8sUHW9FkjpfKVMnnpC3cvGKbTBh9O3Doh3x34TsZtHCdLTtwvoH3nzh0Z+fpICQkPkcDKgfLRxx9ZFBxbfHyxjN041hD4SEv7LHiMpwYZHBZgQK6w7t27S8mSJaVJkyYqlxh6KuIigoiIiHIfnCBHRESo6Xr16knRohamF0pJFjlyLz1SYKhIuZZib+sj7w/LDQ/LpBeOk9SsWVM1dMPff/8t8fHxzl4kj5WYmGhS2Bn5WVnYOed4rUBEROSZnYhY4Dn7kD5WG8WAkbPGgRtXpl07BefxlQblQsw/6PxOkc2f6qfz5BfpPhMf2KRBXivo/PmDn8uIhiNkSP0hJoWf8Zj4lHgJzRsq3l6mTdwv1H5BBR++7/K91Chcw+S+k7fuBTXQWaig/hpKK+wclRAlpfqXkopjK8oaWZNusVHrASmbjAtYdyzf0WSZjIMMaT8LHuuJHBZgGDp0qFy7dk1WrlwpR44ckV9//VUOHz4sr7zyiqMWgYiIiFzIxo0bJSEhwfrCb2c2iMRev58eycdXHNkLp829+gsYcvvN/m/kbPS9gmQucvFx9+5dQ+Fssr2ZM2fK0aNH1XSPHj2kW7duXM02wGsFIiIiz4Dc9agLBhUrVpQKFSo4e5HcmrulSTp3I1ZORcWo6eaVCoufj5mm5+QEfWokXar+707vi+Qvabh75emVhgZ5raCzRiv8rDXo47EZKZCngNQvWl8C/QJN5nep0EV+6vqTTGw5URoWa6jmHTp0SHUcylMyj9ngAySmJMrzK56Xdr+1k2FrhqVbpgZFG5gEGRD8GLF+RIafxZPY/Ip827ZtaoRCWqh4jh+CVgG9SpUqcvnyZRk3bpytF4GIiIg8uf6CcXqkmvZPj5SaqpMNx/W9cEoUCJDKRYPV9C9HfpEtl7bIrF2z5L9H/5NiQcXE2WmSpk+fbkiTxIZv2zt37pxMnDhRTWPUAi5CyDq8ViAiIvJsO3fulFu3bqlpjl7IuWbNmkmxYsVUBpglS5aommu+vvbvYJVd6yON0iPd65iV/kHTRK4d1k9XbCtS/1mTu3tV7iU60Umb0m3MNshrDfoILuCx1kLAoXaR2upmXNgZ6zb+bLx0iO8gFRtXlCbFTdu3T0efltR7QZESQSXSLdOZ6DNqJAUCCoPWDFKvd+jWIY8PLthlBEPr1q1lxIgREhOjj1ZpkPZg+/btJvPwt8XpEIiIiMgjh07nyZNHnT9YnB7p8FL9dGBhkXKtxN4OXoyWGzGJarp1WKgaLRCTFCO7ruxS82oVruX04IJ28aGdV+HiA73HyPaFnbVz3FGjRrFHXjbwWoGIiMizMT2SbXl7e0uvXvpG9OvXr8umTZvEfeovmEkte3m/yIYZ+mm/IJEeHxtSIxkrFFBIev3ZSz7b+5ncitcHrIyhsT47wQVzfvvtN1mzRp8OqVaFWjJ9wHQZ2mCo1AqtZfI4FJQeVG+QdC7f2TDyQXM74bZcj7+uAhAF/AvIvqh9KrhQJ7SOxwcX7BJg2LBhgxqtgFzAyAGsGTNmjIoGhYeHy9NPPy1169aVH374QUaPHm3rRSAiIiIXFxUVJbt371bTLVu2lLx5LTzhOrNRJDbKoemRMGLh276NpG+L8tKtjn7obpBfkPz32H/ybot3pV+tfuIKUICsZ8+eavrq1auyefNmZy+Sx424+d///qemMdT/zTffdPYiuSVeKxAREeWOUcrolNOuXTtnL45HcJc0SUkpqbLpuD6VbbnCgVKucJDpA1KSRP4cJJKarP/7gXdEQsqbfS0UYb6ZcFPm7pkrJ2/fr5lgayjs/Nprrxn+/vTTTzMs7Fw8qLi8UvcVmdpmarpaCvHJ8dKjYg+pVqia5PXz7GCCQwIMjRs3lh07dsjLL78sjz76qDz11FOqEeGRRx5RUbbq1auroVJIo4ScbH379rX1IhAREZGLwzmAVhjLqqHTh4zSI9WwTY+VrOT195H21YrJOz1rGuovQEhAiPQO6+1ShbqQJkmDNElkv8LOFgfFyASvFYiIiDwXRnqizhogRXqhQoWcvUgeoX379pIvXz7DOb5xgWFXcis2SZpUKCSB/j4SHmYmPdKmT0Qu79NPl20u0niA2ddJSk2SKiFVJMAnQOoWqavqKNgL0p9evHhRTaONukWLFtl6nWJBxWRc83Fq9MLlmMtq5EKNgjXUSIa0hZ89kV2KPCPSg2Hje/fuVTnCqlWrJvPmzZOmTZvKF198IcuXL5evvvpK2rRpY4+3d0uLjy/OdGPDfXiMO0NBxNdff13tGAsWLKii2e+8846zF4uIiJw8dNriAs+pKffTI+UtJFI+3E5L575wjA0ODnb5iw93M2vWLDly5Iia7t69uyruTNnHawUiIiLPFBERIUlJSdad41OWkFK2a9euavr06dOyb9+9RnoXUyRfHvmmb2PZM76jjOxYxfTOa0dF1n6on/YNEOk5B/mfzL6On7efjG46WlY+ulKNGEf7oT0cPnxYZs6cqaYLFCggH330UbZfKy45TgUStILOc9vNlY8afSSNizU2KfzsqewSYNBUrlxZVq1aJVOnTlUNy9i5nDxpv2Et7gqBg7Ebx2a4sWkbKR7jzkEGpGqYMWOGKpDYsKFprjIiIso90OitBRjQq6l+fQt7pJzZJBJzL6dn9e4OSY/kblB4uEuXLmr6xIkTcuDAAWcvkts7f/68vPfee4aLOxZ2th1eKxAREXkW1l+wH3dJkwT+vt5SMNDftKPY4ldFUvR17aTdGJHQylm+DkaMVypYyW7XpBihjELM2kiG7NYJjksTXNBqLmAExszwmWqepwcZvO05lDw6OlpN9+vXTw4dOiRFihSR2rVrq4gQCw/eh9QKGW1saTdSV0rDYOkP9u7du2oaeaFv3LghkZGROYoKEhGRe0PD95kzZww97jPKcZl5eqT7J9j29M2GU/LJqkjZffampKbqRwNM2DRBJm+dLDuv7HTJEQJMk2Rb6CSjFXZ+6623pGLFijZ+h9yJ1wpERESeW38BqSSzm2qGzMMIBj8/P/dMhbr1c5Hz2/XTJRuINHvV2UukaquhUzygTvArr7yS7ddaeXpluuCCBtOYp7X74rGeyOYBBtRbQHXzoKAgCQkJkVq1asnWrVtVFOjnn39WX+Bnn32merCjVgOl39i0IENGETBHQ8GTsWPHqhRXoaGhqvdelSpVVOHu2NhYw+NQ3BvDlpAOC0VRatSooXpSTps2zdBLFamRiIgod8tWzyb0ejm0RD+dN0SkgmPSI83fdFpm/HtMnvt2m6TqdBKdGC1LTiyRn478JO9vfd9uw3Vz7cWHC9YK+fXXX9V0+fLlVQpQyhleKxAREXkmpEjXUveEh4ertiOynfz580uHDh3UNFLSnzp1yqVW77kbsXLtTkL6O26cFFk1UT/t7SfS69MMR6JHxUXJD4d+kNik+22N9oCO0GkLO/v6Zn90fK/KvWRSy0kZtttq7b54DB7riWweYMDwkm3btqkaC7///rtqUEaBZ/RS0i56Dx48KG3btpWWLVuafKG5Wdogw4srX1Q3ZwcX4MKFC/L111+rAj3jxo1TaY6QzmL69OnSu3dvs3mKP/zwQ3niiSdk9uzZKjBBRESUtmeTVQGGs5tFYq7qp6shPZK+Ad2eTkfFyNkb+pPblpVCxdfHW07eOmk4Hj9Yzori1A6E/KHt2rVT07t27TKMFiHr4Nx18ODBhr9Z2Nk2eK1ARETkmbJ1jk/ZTpPkah2JPl4VKY3f/0+6fhwhV6Pj9TNTU0WWDBXRMrW0eVOkWI0MXwPBhY+2fyQdF3WUXVd22W1ZJ02apNo64bnnnlPt0znVq3KvTNttcZ+nBhfA5smLV65cKRMmTFCVtwEFnqtXr66CClqOZYxuQCP0U089JQMHDhRP8+PhH+Wnwz+p6RltZ0jVQlUN9224sEGlVYChDYZKp/KdDPfdiL8hF+5eEH9vf9l7ba+ah2rpWnDhoT8fUpXUMe+D1h+YvOfwNcMl8mak5PfPLz93/9nkvmux16RIoJnq7RZCKgDUTdB6QwKGDmFUw+TJk1VAqUmTJob7zp49qwohZjd3GREReS6kSESvcO34UqFCBcueeNDoBLqmY9IjrY+8V+8BvbCq6I+j9YrWk3V91smWS1vslg/UVmmScE4GixcvlqFDhzp7kdzOJ598ogq/aR1kWNjZNnitQERE5PkBBhZ4tg9kjEF7HNK0IsAwYsQIcQVYnoh7105XouMlNPje6JWd34mcjtBPF6sl0irj5U1KSZLfI39X08mpyRIWEmaXZUV7JTpOa6NCpkyZYpf3yW1sPoIhMDBQrl27f0F+/fp1lT4A89NCo/TOnTvF09xOuC1n75xVNwQEjCHtkXZfTJI+n68GP6Dzd89LYuq9oidpnLtzTj3vauy9HpxGLsdcVvchQJFWii4lR5/H39/fEFxA8ZObN2+q4e3a0CykwDKG6B+DC0REZA6O+7du3bI+PdLhe+mRAgqKVGjjkJW7/phxgCHUMO3n4yetS7eWksElxVWh7pGr9m5yBxcvXpR3333XcB6E0QuumA7LHfFagYiIyPOggVlLg4r2INRfJdsrXry4NGvWTE1v2LDBpP3VmY5duStXovXpkVqFhYq3t5fIrXMi/47XP8DLR6TXnExHoeMa67cev8lzNZ6T52s+L/n889mtsHNSUpKhsHOxYsVs/j65kc1HMDz77LOqgC+GmiDn/k8//SSNGzeWqlXv9+I3ZnFhRzdSIE8BKZuvrJr2Q34xIxiJoN0X5BeULsCQxyePJKQkSPHA4lIsqJgayYA6DBjFUCZfGRWwKBqYfmRA8aDicifxjhrBkJYPfsg5NHfuXPn888/VSJRUDHEygoCDMdRnICIiyqr+gsU9m85uEbl7xaHpkRKTU2XzietqumKRICkdkr6jhCsrWbKkSlGITgDr169XHT4KFy7s7MVyq8LOyM2qFXauXLmysxfJY/BagYiIyPMcPXrUkHIGnVG9vW3en5mM0iRt3rxZtc0tW7ZM+vXr5/R1Y9IxK6wIWvJFlg0XSdSfT0vLYSIl9VltMoO2zTcav2G35Vy0aJFhpE2dOnVk0KBBdnuv3MbmAQZEf1Dc+Y8//pC4uDi14Ws9wHKLp6s/rW7mtCrVSpb3Xp5uPkY2IHUSggtazQXQijzjf6Q+yiif16x2szJcnpykRwIMHRo5cqR07NhRpVhAowWKnyBt0oABA9IFHMyNViEiIgLthA69wdu3b2/ZSjnk+PRIu87elJjElPsnyRi2m5qUruOAK0OaJAQYkJYKFx/PP/+8sxfJLaxZs0Z+/lmfbrJcuXIs7GxjvFYgIiLy7E5ErL9g/3N8dIABtL26RIDBKLVsa4z83vuzyPF7KbNCq4i00S+vM8XExJjUAZ4zZ06OCjuTKZuHFDEi4Y033pBNmzbJ7t27Vc/3IkVy1sDt6RBc0AIJxgWd0xZ+xmPwWEdbsGCBlC9fXv7++28VUEAeYvQ65TAiIiKy9qRu48aNarphw4ZqpGOWEMQ+pKVHKuCU9EhtqhSR2KRYaf9be3lt7WuqnpI7cOUicK4Kw6WNCzujZhg7TtgWrxWIiIg8T7ZGKVO2hIWFSY0aNQy1rbRRt84Sl5giW0/dUNPVS+SXonJLZMWoe/d6ifT6VMQvIMPnp+pSVf0Fe3v//fdVR2ltRG3r1q3t/p65CccsuYCVp1emCy5o0gYZ8FhnXAiipylylWlQi2Hq1KkOXxYiInJfSNWj5bu0uGfTua0idy/fT4/k6y+O7IXj7+MtTSsWkogLEXIr4Zb8e+Zf2XVll7gDpKesVq2amv7nn38kNjbW2Yvk8mbPni2HDh1S0507d1aF9IiIiIgoYzi/X7t2reH8s0yZMlxdDupIlJCQoIIMzrTt9A2VXhbCwwqLLHtNJP62/s5mr4iUaZLp89efXy+df+8s8w/Ol7taSiU7pPCaNm2ammZhZ/tggMEF9KrcSya1nJQuuJA2yIDH4LGO9uijj8qpU6ekS5cuqg4DKqyjQDd6olrj9u3bMmnSJHX79ttvDY1N2rx9+/bZ6RMQEZErpUeyKsBgnB6phmPSI92OTZJDF6PVdKPyIRLo76t61mg1lDqW7yjuNIQakLbS2Rcf7lDYecKECYbCzp988gkLOxMRERFlYdu2bXLnzh01zfRIjj3H19IkOZPxyO/e/ttEjt5LCx9SXqT92Cyf/92B7+Rq7FWZtmOaHL913ObLh87SSPeudXRDGn8UyybbYrIpF5FV4ABBBmcEFwApr/CD/Oabb2TYsGHqh9inTx81pKhu3boWvw6KQY8bNy5dnmPcoHTp0qrIChERefbQ6bx580qLFi0sTI+0+H56pIptxREKBPrJtrcfkA2RUVIgr77mQpcKXaRz+c7qpLdywcpu1btp8uTJhjRJxmmTKP35jjbEHNMYfk5ERERElnciYnokx0C62VKlSqnC2qi1hsZzPz8/pwYYSvrFSJVdE+/f0XO2iH9Qps9NTEmU8gXKy76ofVI7tLbUK1rP5suHAIzW0apWrVom6VDJdhhgIItSJI0ePVrdNCjsjKKRuHl76wfCtG3b1iSNUlqo45DZ/URE5LkuX74s+/fvV9Ph4eGSJ0+erJ90fpvInUv66ardHJYeCUKD88hD9UuZzEO6wLAQ92p0btSokZQsWVL1zl+6dKlKcchiZumtW7dOfvrpJzVdtmxZGTNmjMO/KyIiIiJ37kSEtiO0C5H94boEHYc+/fRTuXXrlsoO0qFDB4ev+tRUnfSoW1IFGd64+7V4xUTp72jUX6RCeJbP9/fxl3dbvCuv1ntVbifcS6tkQ8i8MmLECMPfWF+8FrIPpkgiIiIiu1u1apX1PZsOGqdHYi787EAnAK2OwI0bNyQiIiJbr+PJWNiZiIiIKHuio6Nly5YtahqptAsUKMBV6SDGI5OdlSbJ29tLhnYIk4XtbkrTmNX6mflLizzwrlWvUzSwqF06cn3wwQdy9uxZNf3000+rjm5kHwwwEBERkevVXzBOj5Qnv0ilduIMGLZ7OeZekWkPyNGKNElkas6cOXLgwAE13alTJ6aRIiIiIrJiFCgyWwDrLzhWmzZtpGDBgoZzfKdlDIm7pS/srOkxSyQgvzhbZGSkobBzvnz5ZOrUqc5eJI/GAAMRERHZFU52taHTRYsWldq1a2f9pAs7RO5c1E9X7Sria0FKJRuYt/GU9J+3Xb7beEpuxyXJxgsb5cGFD8ozfz0j2y9vF3e9+NB6kzn14sMFXbp0yVDYGXlrWdiZiIiIyHLaOT4wwOBYOHft3r27mkYthp07d4pTrHxb5O69Dll1nxIJy7ozGYo6Lzy2UBJSEuyySFph58TERPX3O++8IyVKlLDLe5ELBBj69+8v48ePV/nCiIiIyDMdOXJEnfQCcoNqtXssTo9U03GFiVceuiKrj1yVd5cekqSUVPn3jP6iae+1vSpHqDvy9/eXbt26qWkMEd69e7ezF8llvPnmm3Lnzh01/frrr0uVKlWcvUhkhNcKRERE7jFKOTg4WJo2bersxcl1nJkm6cz1GNm9ZpHI7h/0M4KLiXR636Ln/nD4B3l387vSeVFn2X9NX6fPlhYvXiwrVqxQ0zVr1pQhQ4bY/D3IhQIM8+bNk0mTJknlypVl1qxZzlwUIiIictn0SO0d8t3EJibLjtM31XStUvlVoefGxRtLo2KNpGRQSakdasHICxfFNEnpoRjeDz/oL4jKlCkjb7/9tsO/F8ocrxWIiIhc1/nz5+Xw4cNqGsWd0aOeHKtz584SEBDglFSoy7dHSpG1b96f0W26SGChLJ+HUQsYvaCmkxOkYsGKNl2u2NhYGTZsmElhZ26bHh5gWLNmjSxZskSee+45+eabb5y5KETkYZgChMg1h05bVOD5wk6R6PP66apdHJYeacvJ65KYkqqmw8OKqP8fDntYvuv8nSx+aLF4e7lvZknUFsiTR78eWYdBJDk5WQYPHmxYPzNnzpSgoCAnfkNkDq8ViIiIXNeqVausO8cnm8P5q9aB69ChQ3Ls2DGHreUKe6dKaa8oNZ1UrZdI9R4WPS+PTx75udvP8liVx+TZGs9KkJ9tz8EnT55sKOz85JNPqnSxZH++zlzJ2pes5QxzF15eXqqIDRowMU1ErgW/zdTUVEapiVxAUlKSrF27Vk1XrVpV9RTP0iGj3jc1HJceaf0x/QkyhFfRBxg0Ab76nkHuCoXNcOG3fPly2b9/v5w4cUIqVaokuRV6MmE9AC7Kevfu7exFIg+6ViAiIsoNWH/BddIkLV261NCRCClA7e3u0bXSJW6Zmo72yi/5u0+36vnl8peT8c3H23y5jh8/LlOmTDGk7dKKPJP9uW9XPCdCD0A0XsbHxzt7UYgogwZNBBl8fZ0aQyUiEdm2bZshx71FPZtQgFhLj+Sfz2HpkWD9sWvq/yB/H2lQNkQ8DdMk6V2+fFnVAAMMl549ezY7jBARERFZAdfbWhrUkiVLSvXq1bn+nKRHjx6GGncOGamcGCteS4Ya/txU5U2RYNPOWc5grrAztk3ywADDyZMn5YMPPpBXX31V5s6dK3FxceKuvQDh0qVL6jMwFQuR60Dw78qVKya/VSJyo55NSI90+5x+umpnET/HjBw4dyNWTkbFqOnmlULlfMxpORh10KOO8bj40EZe5uY0SW+99ZZER0er6ZEjR6qRNeQaPOVagYiIyNMdOHDAcN2NTkTM7uE8RYoUkVatWqnpLVu2qLZKu1rzvgTFnFGT/6Y0lOItn7Hoaam6VElJTbHbYiEF/99//62ma9SooYIN5Dg2796LWgqffPKJalAoWrSoYT7+xvBzFNvQUgt9/vnnsmnTJjVsxZ0UKFBAYmJi1MXp6dOnVaQQnyc37VDxHWrfY2763I7AdZuzdYcAA/7HSKOQEM/rgUzkbrSeTT4+Pqr4m6umR4qIvJ8eqU2VUPn+4DxZFLlIFXf+ptM3UjpfaXF3OC9r2bKlbNiwQTZu3KguCosVKya5CT77999/r6ZLly4tY8eOdfYi5Tq54VqBiIjI0zE9kuulSVq/fr06h0JD+0svvWSfNzq3XXRb5gpaAaN1gTLFd6CsKF3QoqeuPbdWpm6fKn1r9pVelXvZNAUtOqUMHz7c8PecOXOYMtvdRzAsW7ZM9Ro2vmDABo6NGxcMo0ePVht73759VcQTRfXcDS54MMwGN1zwoNEktzWy4zvV0tAQ162rwO8QaZEQWECe99z2uyRyNQjEoxcNNGnSRAXoM4VjykEtPVKwSOUO4uj0SNCycoisOqsvWhefEi8lgkqIp6VJwvFby9Wamwo7o2e8ZsaMGSzs7AS54VqBiIgot3Qigg4dHHfOThkHGDR2G6mcnCCy+FXx0qWqPycmPyNVwqqIj3fW7S441/v2wLdy/u55mbR1khy7adti1B9++KHqAA6PP/64tGvXzqavT04YwbB3717p06ePyTz0PMIX/dxzz8mkSZMMxdowDxv+uHHjxN2g4RINJVk2lngo5DS7ceOGFCpUSPz9/Z29OB6F65aIPMW6deskJSXF8vRIF3eJ3D6rn66C9Eh5xRFwwnvuZqyaLlc4UMoUDpQJzSfIyjMrpVhgMfHx9hFP0atXL5UWCHAONmDAAMktPvvsM9m3b5/hQvjRRx919iLlSrnlWoGIiMhTJSQkqPN8qFWrlpQo4TmdcdxVhQoVpG7duuo8a9WqVaqjV/78+W37JuunikQd1U+m1Jb/pbSRKWGW1V5ISEmQksElZX/UfmlQtIHUKVLHZot14sQJ+eijj9R0UFCQTJ9uXcFpctERDNeuXZOKFSuazMMwfDTIp72Y6Nq1q6rwTURERJ49dNqiAs8HjXrb1HRceiScoywb0krWvt5WPnqkjvh5+8kD5R6QKeFTZGQjfWO8p6hUqZLUrl3b8P1oBbg9HdJBaemQUNgZw6Y5ys05eK1ARETk3jZv3qxGHVp8jk8OHcWAbCN//fWXbV/80l6RiBlqMs4rr4xOQiclL2ldJdSipyMdEq6tlj+8XEY3HW3TRRs2bJgKesGECROkVKlSNn19clKAAelJtIrdmu3bt6v/mzdvbjK/cOHCho2AiIiIPHPoNNIJNmvWLOv0SFr9BZUeybEXK2hsLh8aJM0qFhZPp6VJwvnaihUrJLcVdh4xYoRUq1bN2YuUa/FagYiIyHPSI1k0Spkceo5v8zRJKUkqNZLo9CPTLzV+S7q2biKdaxaXEgWsG3GOunZVQqrYbNGQ8nX58uVqGuf3CDaQhwQYypcvr4Y5a5AaISIiQsLCwtIVXL1+/bqEhloW7SIiIiL3cf78eTl8+LCaRnFn9BrP1MXdIre09EidHJYeKTdySI5WF4Lz0vnz56tp9Ghiuh3n4rUCERGRZ4xSxvl9eHi4sxeH7qlTp446zwKMYLBZh+6Ns0Qu79dPl20hFTsPk7e71ZDPn23o1HWPws7GAQWMUGYKdw8KMDzyyCOycOFC9cUeOnRIRo0apYZC9+7dO91jt23bpvKEERERkef2bLJo6LQ2egFq9BJHSU5JldRUneHvJSeWyOqzq1WeUE9Vr149KVeunJpGj5+0I089vbAzRtSQ8/BagYiIyH3dvHlTduzYYchSwvMq14ER2VpHIqRBXb16dc5f9OoRkXVT9NO+ASK95oh4W96UfCXmiiw/uVySU5PF1qZMmSKnTp1S00jJz2LjHhZgGDp0qIqYIYqEHL8orlG6dGlDQUHN7du31UUtK3sTERHl8qHTKj3SYv20X6BIZccNtV5x8LI0+eA/Gf7Lbjl06ZbM3DlThq0ZJj3/6KmKP3v6xQfOx9auXSue6vPPP5c9e/ao6fbt28tjjz3m7EXK9XitQERE5L7WrFkjqampaprpkTw8TVJqij41Usq9zkjtx4oUrmTVSyw4tEBGRYySbr93kyM3joitnDx5UiZPnqymWdjZQwMMqFK+c+dOFUkaOHCg+h9VzFFvwRjSJvTr10+eeOIJWy8CEREROREa5rUAQ8mSJaV69epZFw27efp+eiT/QHGU9ceuSdTdRPlzz0U5fP2ARMVFqflNSjTx6CLAuSFN0tWrVw2FnZH3n4WdXQOvFYiIiHLRKGVyqBYtWhhS0S9evNgQDMqWLZ+JXNCPVpFSDeVazRdk+sqjsu3UDUlKyfp145LjZGHkQjV9N+mulM1XVmxl+PDhhhRQSH+Kju3kXL72eNF8+fKlG7GQFoo9ZlnwkYiIiNzOgQMH5MqVK4YLjywb6k3SI91v+HZEIGT9MX1AoXCQv/Sq3lwqF/tB/j39r7Qp00Y8WatWrVTnD9TDQoABje/eVgx3dnX4bpGmEyM0tIuQLANd5DC8ViAiInLv+gsFChSQRo0aOXtxKA10qunRo4d899136npsy5YtKuhgtesnRFZP1E97+4n0+lTWH78hs1cfV7dx3WvIC60yT3mf1zevfN/le5l3YJ6UyVdGAjFS3Qbn+KgvgeLOULVqVRkxYkSOX5dyzuZXkoMGDTLkY9N4cm5fIiIiMn/hYVHPJqQhOngvwICTzrCODludkVfvyuXoeDXdKixUfH18pG6RuvJ649elcfHGkhsuPuDSpUuyfft2cXfINTt+/HjVgwnBElxYQfHixdV8cg28ViAiInJPp0+fluPHj6tppDvH+SR5YJokjHpYMkQkWX+dJG3eEilaXdZHXjM8pHWYfpREVqqEVJEPWn8gr9R7RWx1jt+r1/16fbNnz2ZhZ08NMCDX7bFjxwx/o2dc3rx5bVNchIiIiDxr6PTlfSI39cW5VHDBwemRNOFhRSS38aQ0SbjwaNu2rUycOFEuXLhgcl9AQIDTlovS47UCERFRLqixRk6D66/AQP011R9//GF9Xbmd34qc2aifLl5bpNVwSU3VSUSkfuR38fwBElY0WJx1jp+SkqL+L1iwIDPjuBCHjIX31CKJREREZAq5MNetW6ema9WqJSVKlMh8FWmjF6Cm49Ijwfp7J8nW9MLxJLgwRCcQ7eLDnU2dOlV27dqVYW873E+ui9cKRERE7jVKmQEG14Xz+86dO6tpjDg5dOiQ5U++dVbk3wn6aS8flRpJfPzk4MVouRGjz04TXiU00xS4qbpUdbP3Of6tW7d4ju9CPCfZLhERETnd5s2bJTY21vL0SFr9Bd+8Dk2PFJ+UIltPXlfTVYsHy7Q94+XXI78aijznBujZpF18HD16VI4cOSLu6ttvv83R/URERESUMRQLXrVqlZouW7asVK5cmavL09Ik4dps6TCRxLv6v1sNFylRV00ap0cKr5L5yO/VZ1fLI0sekSUnlkhSSpLkBM/x3QcDDEREROScodNXDojcOKmfDntQxD/IYd/EtlM3JCFZ37OmdoVo+fvU3zJp6ySZsn2K5CaekCYJvd/TpkVKC/ezlzwRERFR9uzZs0elQNfO8TPrwU7O161bN/Hx8bHuHH/PjyIn7qW3D60qEv6m4a5191LLenuJtKqc8chvnG9/e+BbOX7ruLy94W05dvN+Cn1r8RzfvdglwGBuR8OdDxERUe4ZOu3n5yfh4eGumx7JqP5C/pD7jdOdynWS3KR79+6Giw93TZO0dOlSVfAtM6VKleK5qAvhtQIREZH7pkfKcpQyOV1ISIiqXQA7duyQc+fOpX+QTife+3+VgKN/ikRfEvlnzL07vPSpkfz0dczuxCfJrjM31XSd0gWlYKB/hu8blxwnhfMWVtNNijeRmqE1s/0ZTp48KXny5Mn0MTzHdx12Kfk+atQomTx5sqH4Bi4iBgwYIEFB6Xsm4r69e/faYzGIiIjIgW7evKlOYKF58+YSHBxsYXqkAJEwxzbs+/t6S0ign8QnpcpbLV6UAQ16yn9n/pOWpVpKblKoUCFp06aNrF69WrZt26Z6+uNE3R1cvnxZhg4dKv/73/+yfGz//v0dskxkGV4rEBERue8o5Q4dOjh1WcjyNElaWqvFixfL4MGDTR9wap34Lh0sBZEC69hCkfjb+vnNXxUp09jwsM0nrktyqr62bngWdesC/QJldvvZcvLWSUlKzV56pOTkZJk1a5aMHz9e1ffLDM/xPXgEA3KxoRcZKn3jhjzMmId8bdo841t0dLStF4GIiIicYM2aNep4b1l6pIMi14/fT4+UJ5NghB282bma7Bj7oPw1rLXk8fWRksEl5bmaz0kAgh25jHGapCVLloirU0Ovv/1WqlevbhJcQLDEnAYNGsgbb7zhwCWkzPBagYiIyL3ExcVJRESEmq5fv74UKZJ5Dn5yDT179jRMp0uThM5eaz80/Ol9Ybt+IqSCSLu3TR4aERllcf0FTcWCFaVqoapWL/Pu3buladOm6twd2x0EBJi/PuM5vmux+QiG06dP2/oliYiIyNOGTmujF6CGY9MjaXy8vaRCqOPqPriqXr16qZEAWpqkV155RVzV8ePH5aWXXlIjLjTlypWTL774Qlq0aCFTp05VwQdtJAZ6NeECJV++fE5dbrqP1wpERETuZePGjYae5EyP5D7KlCkjjRo1UiPM165dKzdu3LjfIefUOpGzm9M/qedsEf9Ak1kjO1aRphULqZEM9cpgvIPtoXP6u+++K9OnT1eZcMDf31+NYnj55Zfl448/5jm+i3N6keeshrsQERGRew2dLlCggDqZzRB6zGj1FzBioEpnBy1h2sXQsfDvvR7lDRs2NIxCuXXrlrgaDJWeMmWK1K5d2xBcwIjZESNGyIEDB6RTp04qiPDee+/J+fPn1Uga/I+/GVxwb7xWICIicp1ORFmOUiaXS5MEaLRfvny52dELBsHFRMq3SjcbNRe61ykp7z9cW3x9zDcjX465LKvOrJJUnX40uzVwbl+nTh11rq8FF1q3bq3S6b/99ttSuHBhnuO7AacFGHbu3CmDBg2SkiVLOmsRiIiIyIa9ktG7HNq1aye+vpkMkrx6SOR6pH668gMOTY+UkqqTczdi1XTkrUjp+WdPmb17tpyNPiu5mZYmCQ35f/31l7iSXbt2SZMmTeStt96S+Ph4NQ+Bhs2bN8uMGTPM1vowV0SY3AuvFYiIiFyrExEK7rZqlb4BmtwjFaohTVLkv+ZHL9y9InJqfbbe5/tD38vwtcOl15+95PjNe2lwLajf98ILL6iaHidOnFDz8ufPL59//rkacVGtWrV0z+E5vutyaIABw3E++eQTqVevnrpQxEbD3G1ERESeVfgty55NhxY7LT3S/gu3pfWUNdJ26hqZvXWRnI4+LV/u+1IOXj8ouZnxxQfSJLkCDJV+88031Tkj8rFqF7bvv/++anzGfPIsvFYgIiJyLVFRUYbzMAQX8ubN6+xFIiugZllYWJia3rp2hST9977IL09m/ASMbMAIByvEJMXIQhSJRtAg4aaqbZfVKHLUUcOyIbWp8fXIoUOHVDpUjFQm9+KQb+yff/6Rxx9/XOXCxVB2DHWeMGGC7N+/X44cOeKIRSAiIiJXqb+gpUfyySNS1bHpkdYfu6b+P309VlJ08ZLHJ4/4e/tLeOlwyc1q1qwplStXVtN///23YaSAs6xatUqNUkBNBW2odHh4uBoqPWbMGPHz83Pq8pFt8VqBiIjINeGcDA3CwPoL7gc9/vv2flBmdMojR17yEb8NU0RSkzN+wtlNhlEMicmpMmD+Dvk64qScuHY3w6cE+QXJ1x2/lgfKPiBPV3taAv1MazgYQwpTBBL69OkjV65cUfOKFy8uixYtUp2c0G5M7snmRZ6NUyUgEjV//ny1AYWGhsqjjz4qP/30k+p51rt3b3u9NRERETkQ8t3j4kPL56/1kjHr6mGRqKNG6ZHyOSXAgALPk9uOFT/ft+TwjcPqxDi3X3zgZH/atGkSExOjvs9u3bo5pQf7yJEjZd68eYZ5qOmBQAOGULM3k+fgtQIREZGHjVIm13LlkMimT2RU3t/Eu1key5+HUQwVwmXX2Zvy3+Er6nb+Zpy807Nmhk+pU6SOzGw3M8P6drheRBabUaNGyZ07dwzzX3zxRVV7oWBB+xSPJjcewfDjjz+q/FnoBffRRx+pIo+IQl24cEHeeecdFlMkIiLyMHv27JHr168bLjwyzY2pjV6Amo5NjxQdnyS7z+kLGNcrU1AK5PVTPWwaFtMXOM7tzOZodRBcjPz6669qqLRxcAEdUjBUGhcfDC54Bl4rEBERuQecn2mjlAsVKiT169d39iJRVtDAf3qjyI99RD5rLrL3Z/HW6UcD3463sADzvVEMWscsaFOliEVPNXcdePjwYTUS+dVXXzUEF9Ahbc2aNfLll18yuOAhbD6C4dlnn5WKFSvKrFmz5Mknn1TVvomIiMhzWZUe6ZBReqQqjk2PtOl4lCryDOFhlp0k5ybNmjWTYsWKqeHKixcvVr2MfHx87P6+586dk0GDBsmyZcsM80qUKCFz5szhiFcPxGsFIiIi94DCu2fOnFHT6EjMzh4uLDVV5OhfIhtniZzfbnpfgTLy67ki4n9xqzxczcJ+5tu/loirL6lJfx9vaVqxULqHaKMVMupclpiYKB9++KHKYoNpwLUFaqyNGzeO9Tw8jM1HMKD4HoY848J0xYoVEhcXZ+u3ICIiIhcdOo2LjwxdPSJy7V7tpcodRALyiyOtOxaln/BKlBaVOQw3LZzw9+zZU01fu3ZNNm/ebNfvA0OlP/30U6lRo4ZJcGHgwIFq1ALTaXomXisQERG5XycipkdyUckJIru+F/m0icivT5sGF4rWFOn9lcjQ3VKg41vyydZEuXQnVaJT84oEF1M3XVBRSQksov7X5uF2u3ZfOXDxtnqZRuVDJNA/ff/0f8/8K08uf1L+Of2PpKTqR0locB3RoEEDVX9XCy4gw83OnTvlgw8+YHDBA9k8wHDp0iU1egGpEtBDCcU6kDN3/fr1Nk+PhCiZuVtwcLBN34eIiIjMQ0eCiIgINV2vXj0pUqRI1qMXoIZj0yPhHEQb5pu/2GYZsflhGbdxnFyOuezQ5XB1jkqThABCq1atZPDgwXL3rr5oXJUqVWTdunXyxRdfcKi0B3PktQIRERE5aJQyOVb8bZENs0Rm1RFZMkTkeuT9+8q3Fnl6kcgrG0Xq9BHx8ZN27drJzuuBUnLGXam7IK/oRh4Vef2YJA07KNee26D+x9/abW1iNZVtCcLNpEfCOdu3B76Vg9cPyuvrXpfIW/r3RwqkoUOHSsuWLeXgwYNqXmBgoEyfPl0FHerWreugFURunyIJhTlwsYjbrl275JtvvpGff/5Z5dNFowMCALdv66NgttC6dWvV082Yn5+fzV6fiIiIMrZx40ZJSEiwrGeTVn/Bx1+kqmPTI52MipELt/SjKgNDDsrtxNuy7MQyeb3R6w5dDleHESjoqIFGf9TQQnHlTGtqWAnbijZUOikpSc3z9fWVt956S8aOHSsBAQE2ey9yTY6+ViAiIiLrpaSkyOrVq9V0pUqVpEKFClyNruDOZZEtc0V2fCeSEG10h5dI9R4iLYeLlG5odgRpt27d5JdfflFZZ/bu3as6h2VknVH9BXOpZe8m3ZV8/vnUdLMSzaRaoWqyfPlyeeWVV1T6U03Hjh1V2lVuP57P5iMYjGE4DIa+o6fSggULpGZNfcXxAQMGqA150qRJhohWdqHewzPPPGNye/zxx230CYiIiMgmPZuuHRW5dlg/Xam9SEABh67Y+0XKUqR6SB0JzRsqTUs2lQJ5HLscrg4XH127dlXTJ0+elAMHDtjstTdt2qTODd955x1DcKFx48ZqqDTOCRlcyH0cca1ARERE1tuxY4ch4M/RCy4gKlI/UmFWbZGNH98PLqDjVsO+IoN3iDy+wGxwwdqRyhidEBGpTy1bJF8eqV5CH0gwhuDCVx2/kl+7/yr9KvaTp556Srp3724ILqAo+Pfff69S5zO4kDvYNcBgfLGKjW3VqlWqSMzbb78tN2/elPHjx9tkeAzyeWnD64mIiMjx9RdwrMeowgwdWuy09EhQOiRQ2lQpIgF+fvJBm/Hy36P/yQetPnD4cuTGNEnR0dGqtzpSIiE1kjZUeubMmWqodJ06dXL8HuTe7H2tQERERNmvscb6C050brvIL0+LzGmsr7WQoq9nIOgk1WqEyPADIj0+FgmtnOVLdenSRfz9/bM8xz986Y5cu6Mfod46LDTD0cwIRGxftl16NO2hRqNqcE53+PBhlQrTliOhybU5JMBgrHz58vLee++pITl//fVXjgv4LVy4UF2k5suXT4oWLSpDhgzhsGoiIiIHiIqKkt27d6tpNB7nzZs36/RI3n4iVbs4/Pt5sEYxmd+/ieyd0FFKFMgrPt4+UiigkMOXwx1gBIOWbhJpknICxZvRKx291LX8+p06dVK90ocPH64KSxPZ81qBiIiIsj9KGQ3E7du35yp0JJwzH1sp8l1XkW8eEDmyDDP19+UrIfLgRJERB0QeeEckXzGLXzZ//vwqHSogRdKpU6fMPm73uZuZpkfSRjoj/VHfvn3lxo0bal7ZsmXVuduPP/6o2mcpd7F5DQZLYSfVuXNndcuuJk2ayGOPPSaVK1dWveOwIc+ZM0cVCMQw/KyKPWPozvnz503m7d+/X/2PoftapXNKD+snOTnZkOKAbIfr1va4TrlOXZW7b5v//POPodEYhcMyPG5ePy7+V/VpTlIrtpVkn0AMP3TKekUfmsTEFLu9tydAoKht27bqwhIBpMjISClZsqRV2+qVK1dk5MiR8r///c8wr3DhwjJt2jR58skn1Xkgz7Ocvw9w5X1PTq4VeI7vvtukJ+O65Tp1B9xOuS4BGULQpgYNGzaUoKAglzhv8/jtMyVJvA/9Id5b5oi3llr2Hl3hMElpNlhSaz4i4ptHPzMb3wnSGP3999+GDtuDBg1Kt04fq19CmpcvKBtOXJdm5QuYfPcXoi/IrAWz5Ku3v5K4uDjDORteBx1E0A7rCtuKK0jKZef5Dg0wIMKFgiIXLlyQGjVqSP/+/TPv7ZiFrVu3mvz93HPPqWH2GFb98ccfq/8zg6Jy7777rtn7ELDQonBkfkPFQQcNSyyqbVtct7bHdcp16qrcfdtEYF/TqFGjDI+bQbt+Ef1gXJHoMh0k3s7H14zW6+m7p6WQfyHJ75/fru/vCdC7Seu59uuvv8rzzz9v0baK+/F4nF/dunXLMP+RRx5RtRdCQ0NV6htyjX0Aznddia2uFXiO777bpCfjuuU6dQfcTrkuASkLtcbJFi1auEzbmKdun15JMZL38P8kaN888bl7yeS+xGL1JabeAEko317Ey1skOkZEcMsejDpHQADr8Pfff5cnnnjC7DoNRIHmioEiCXflhj5bkqrNNmLpCJEGIiVHlZRzc89JhYIVZPr06SoQhcCCq2wrriApl53n2zzAgBP6Tz75RF2UGg+Jwd8Y4hwbG6tWLjboL774wqKRBtZ444031EUtqpdnFWB44YUX1DD9tCMYXnrpJTV0CEVJKOMfCr7DkJAQj9qxuwKuW65Td8DtlOsRx/KNGzeqFYHjZXh4eIbpbnzP6HO46rz9JLD+oxJo5wLPabfPtceuSd3SBeTjHR/L4RuHpVmJZjKz9UyVJonMw8XGqFGjDDl4R4wYkeVxH7nzX331VVmzZo1hXrly5WT27NnpzrfI/LbqaDjfdTRHXCvwHN99t0lPxnXLdeoOuJ1yXcK2bdsMK6Jbt24u0zbmNtunTifeB35Tk6m1+qCLv/nHxVwTnx3fiPfOb8Qr/n7HHPW8sE5qxIKUaSZB6LBlo0XDd9msWTNVBw3fc0pKiko5n9k6xUiFSZMmycdffCxh08LEW7zFr5CfvDnoTXnrtbcMdR0od5/n2zzAgFy7Wj0EDS4S0GiPC4bRo0erjRk5fb/77jtV4G/cuHE2e398aRjGj7zQWSlTpoy6ZfQ6/JFkztfXl+vJTrhuuU7dAbfT3L0ejx8/LmfOnDH0ds+wl3HUcZF76ZG8KrUT//zm83jaa73eSkiVgT/sEW+/WxJU+YC6Lyk1SfIGZH8EZW6AwADO17Zs2SIRERGqB0xG2yqG/uJ8bsKECSZDpYcNGyYTJ060aUcST+TMfYAzLnYcca3Ac/zceVxyB1y3XKfugNsp16XWWQT1Ttu0aeNSxwO32D5PrhVZOlg/HVJWpGIb0/tvnBLZPEdk9w8iyfH353v7itTuI9JyqHgXrW63orkPP/ywCjCkpqbKypUrpWfPnhmuU2wLAwcOVNd+cGbmGQl7Okz6NOsj4x6wXVuup/LNRef5Nt9eUSgEQ26MoecRCrWhgjiiXsj5hd5LyNecWeXy7IiPj1d1FYoVs7zQCREREVlHS58DDz74YMYPPGR0nK/Ry+GrOeKYvsOBLtVXmoc8I9ULVZcHy2WyvGTw0EMPqf9x8WGcDssYajQ0bdpU3nzzTUNwoXbt2uqiBQ3DDC6Qq10rEBERUcYuX75sqE2KEcp58tzL90+WQX26tR/e/xvT92rWycU9Iv/rJzK7gcj2r+8HF/yDRZoPFhm2V+Thz0SKVnfIOT4sWbLE5L5HPtskr/64S37aeExefPFFVeBbCy6gg8i0YdNk55id8naHzDPGUO5j8xEM165dk4oVK5rMQwoF9GTr06ePyfyuXbuqIiDZcf36dVUsMC30cEJPuh49emTrdYkcqfOs9XI9Jk0BHJ1ONeZ4e3ubDKUrHOQvK4aH8wsiIpcLMDzwwANZBxjQI6dqV3G0iMhr6n9dSrCMbDJIqhbPZyhMTVn3btLSJC1evFidt2nQ0xwpKZFzFUOrAReg48ePV+kqXXrYOjmVo64ViMiz8LqJyHH1Fyw6xyfzTq0TObv5/t9nN4ls/ETk5Gr9yAZjQUVEmr4s0vgFkbwhDlujYWFhUrNmTTl48KBKhYo6AUiddP5mrOw8o6+VtmT5bjn/89eG5/Tq1Us+/fRTKVWqlMOWk3J5gAHDP9JWDN++fbv6v3nz5ibzESBISLhXLcRK6N2EYfvo2VS2bFn1g0DvOgzfQU+6IUOG5OBTkKfRcvm6GgQXrt3J3m+AiMhZ0KC8evVqNV2pUiWpUKGC+QdePyFyWd8DSiq2FQl0bP7W1FSdRETqRzAUzx8gVYrpU/W44vHAFVWpUkXdjh07JkuXLlU3pKFETyY0CJ86dcrwWPRw+/LLL6Vq1apOXWZyfY66VqDcw1XP88m2eN1E5GKjlCnr0Qua/8ab/h1SQaTFEJF6T4n4OSdta5cuXVSAAedZCDjgHL/xE8NF/Gqo+28d2aL+L168uKqn9sgjj/BYS45NkVS+fHk1zNm4EQK5e7HBorBF2lEIoaGh2Xqftm3bqoIV8+fPl+HDh6u8v6hW/v7778vatWszzgVNucadO3dUT8rSpUur0QD4H39jPhERZd+OHTvk9u3blo9egBr3h+I6yuHLdwyjxFqHhfKk2Eo4Xmrfs+bixYvyww8/GIILOBdDIV508GBwgVzpWoE8G8/ziYjsE7DVAgyolVSrVi2u5pyMXkirRD2Rx+aJDNmpH7XgpOACjqGoiZX2HH/jSf3oBYg/tUsGDBgghw4dkqCGQdLvn36y/vx6jgQnx41gQFQLQ5lbtGiherihOBuGQvfv3z/dY1GxPMNej1nA8BzciDLaYSIItWvXLsO8CxcuqGKTy5cvV0Eo5I8jIiLrYSitRT2bDhqlR6rWzeGrOuL4dfW/b4GdUqOsY4pLe5KpU6fKlStXMrwfAQUMo+dQaXLFawXyXDzPJyKyjyNHjqiGZq0TkUrbTDkbvaApWkPkxTUiLrBOcY6P79qEl7fkLVdXTaZGX5GVv/+oMsYg6PTdhu/k8I3DsvPKTvm95+8SFhLmnAUnl2bzLXvo0KGqZ9KwYcNUkT/k5kXP8ZEjR5o8Dj3i0NCLDZbIHjtM4+CCMczH/URElD1azyakpMjwOH7jpMjlffrpCm0cnh4JNhy/Ll4+dySgxEKZceQFeXsDi5FZ49tvv830fqSnZHCBrMVrBcopnucTETm5xhpZP3rh6iGR0xEue46fp2QV8Q7Qp5PVXTpsuMa7nXBb/H381XTLki0ZXCDHjWDAUPmdO3eqPLyoNI7czBhWU7BgQZPHHT58WPr16ydPPPGErReBKMtGEdzvKkUD0bM2Obq2iE6/007HK1F88+8XSW3h6EUjIkonJibGkN6kUaNGqiBYpqMXoOb/2TsL6KiuLgrvuAuQIIEEgru7u7u7FlooWqylWNHiVqC4Oz8QpLi7W3BPAgQixF3+de7LTBIiRMZzPtZbuU9m5vIymbn3nnP2Vr08UnBENO65+cHQ+gn09CRT52LZ2B8grVC2ElX+pQadZ+1zJr3wXIHJSuN8hmEYnaxSZtJXvSCDrnGuS1laGjfGN3WuKG/7uF6Wj/FtTW2xrcU23P96H6aGpiruLZOlAwwESc98X7HwPdWrVxcbw2TlRZFo81swy74PUTb3EOreL2mQQS8CZo5bYGjxBtG+9OfKWQQMw6iXS5cuITIy8scTj6cu0k89A6B4a6iaex6BiIqJBQLKolHxvNC3fITG+fkzNK3Q9yNVJ6T2fUrn1f09ymgnPFdgssI4n2EYRpug8T1JSRPFixcXSiSMgqoXZLhdA95dAgrW07gxvlkBKcAQGx2F7FHeib5DqV0xV3wAgmGSQ63iX1RaT5r4DKOMD8zU0JRFEf3Q8ogKLiQCCBRIoIBCcsEFuoauZRiG0YrSad93wOcHUpuydNQgj1Qguyl+rV8Q5fM6YHCFrljVeBUcLB1U3g9tJjlN/PScZ5jMwnMFRpvH+QzDMNrEzZs3hccNwfJI6eT2hnRcux7q5vsxvL6JBYzzSL4K4Z+eY2CfnmrqGaPN6KtrsjBnzhzh1TB9+nR1dIHRcX606NG3b19oAnqxxqJyIUmQ4bvgAl1D1zIMw2hK6bSZmZkwaU21ekFN8kiEo60pRjUshEO/1kKl/KoPcOgC48ePR8WKyWcr0XE6zzDKgOcKTGrUqVMn1fMc/GQYhkk/LI+UCaoOBixzAcZW8ceMLaRj3290rYaN8Q2z50VMSIBoZwv3FOc/B33GvS/J+5oyjMoCDLt370a5cuVgbm4uyqr++OMPxMTEiHPkzVCwYEFMnjxZaLCuXr1aGV1gsjidOnVK9byfnx80hu+CDOZO62Gef22i4EKK/gwMwzAqxNPTE48fPxbtunXrwsTEJPkLnx5KII/URoU9ZBQtY0Ol8lOmTIGDg1T9QT9pn47TeYbJCDxXYDIKSR+9ePEixfP0vTR06FC+wQzDMBmsUjYwMEC9euqT8NFKqGJ77AvAKpe0r28IjLgHjHuZdKNrNWyMH/H5JWIO/o7Who9xZNmf4vwG1w3od6If+vzXBx6BHuruMpMVPRiOHDmCnj2lcho7OzuxGDF//nxRpvrt2zesWbMGhQsXFsf69OkjPrwYRtEsXbpU3raxsYG/vz9y5colAgvh4eEisNW0aVO0b6+ezNqUggwUXDAwdxOHosNycXCBYRiN4uzZs/J2iv4L394Dn+5Lbec6gEUOpfap+dJL8AlOIC9HxMYiGkGIsT0J/bDy0A8vCD3oI4eFMU6MVv+gXpugCQaZpVJiiI+PD3LkyAFjYw56MxmH5wpMZjh69Cju35e+Y6ganjTDSUeaAgs0xqft999/x5YtW/hGZ2FiyIOJYZg0ExAQICSSiGrVqok1FCadkLeCz2upXbwVYJVb425hknmTSV04DK2D3DEx0NfXx009PfTY/ACx+kEIz3MA0APcAt1gZ2anzm4zWTXAsGzZMuTMmROnTp1C2bJlRVChY8eOYsGXBoBz584VBtCGhkrxl2YYvHr1Ctu2bRN3wtHRUezTYggFufbv348uXbqIcwMGDECFChWQP39+td01WuySEaunhwijcMiGwwYmXtAzCEJslCTtYWHMwTiGYTTHfyHFAENCeaSSyg/i0iDZKzA8yXFDm4cws7qKaKurCPvSEpG+HFjILKxpzigCniswmalemDZtmnyfxvu1a9cWx798+SIq6L9+/YqtW7eiYcOG6NevH99sHSLhvElObKxQSqCFscCwKIRFSaoJYZHRIsigr89eHAyTFiibPTo6OvUxPpM6dxL4MFTWTJ+ylOZNSTFEduP+KFfqPqrnqQ5TQ1MV9I7RdhQukUQZJT///LMILhDZsmXDrFmzEBYWhpEjR2LixIkcXGCUChmHy74c//zzT5HRJFsU6dy5M4YNGybaVM3QvXt3EfhSF5RJe/vPxrg0sRbKVzqAWKMvsDWxlU7qxaBk2RNy42dKxAkMU19fGYbJupDhG5XQyoK3NJHft2+f3AguEU8SyCOVUJ88kqHlS3k7KrCk2vrBMExieK7AZBQXFxd59QItgFFwgaBxfu7cubFjxw75mJ/G+0+fPuWbrUPQvGlyt2Axb6L5E21XJ9TDsSHlxM+7U5qggJ0RDG3uIjgiGpuvvVd3lxlG46Gx/NSpU+UqJMT79++TH+MzqdxIT+D5MamdozDgrO0SU3owCCuJTc034acyP6m7M0xWDTDQom2hQoUSHSNJJKJBgwaKfjmGSQRpstLkgqDKBKpS+J5FixaJDCfixo0bQvZBnYRGhWLE2RG46XkT1XJXw8FWBzGzwkxUyVUFbqGPkLfYLhFkiIyOwUe/ULX2lWGYrAdNMOrXry+SBWR+SvST9ul4ogmInxvwKc4MrEBtwEI15bS0mCALxsoI+9gdIW6DEO7VCLFR1tI1DMOoHZ4rMBmBvnemT58u3//rr7+SXNO4cWNMmjRJtENCQtCtWzfxk9ENXF67YPLVyWLeRPOn79E3iETuojtg5rBPfOe/8w5WSz8ZRtvG+JSgGRwc//dCEnNJxvhM6tzbBsRExVcvxAW7dQEDfVbSYNQUYKAS1e/lj2T7ZPrMMMqEvhxlC2AUOEhOJ9rU1BR79+6FpaWl2Cc/kOPHj2tEcGFFoxWwNrFG9ZzVsaTuEnEsQO8ZCpTag4O/Vkbx3NZq6SfDMFmXBQsW4N69uKDBd9BxOp+8PFI7FfQOiDa/JRYTzBy3fBdkMEB0cBFE+NQT5+gaupZhGPXCcwUmIxw6dAgPHz4U7ebNm6NGjRrJXkdBiDp16oi2q6srRo8ezTdcR2haoKmYG9G86fsgg2xO9eTbPTiZlcXCln0ws31ptfaXYXRqjM+kTEw0cHez1CYpoXI9+G4xWRKFBxhkJVX0gSTbHj16JI6TFn7C47KNYRTBs2fPsHPnTtF2dnZOVXe1aNGiwnBcRt++fYVBnKo59f5UouCCmaGZ/By16Rid84l+gkX3Z6m8fwzDMBs3bkz7ebk8kj5Qoq1Kbp5+aHlEBReCocWbpEEGvQhxjM7RNXQtwzDqh+cKTHqg5KGE3gvJVS8kTGyj+QAZ0hPr1q3Drl27+IbrAAnnRgmDDGHRYRhzaYx8TrW/43q0L+es7u4yjG6N8ZmUeXkSCPCQ2qU6AuaSh6Y2Ymj9AGaOm2Bg/gaxcndQhkkbSnFaJp1m2r5Hpn3/PTK9fIbJDDNmzBBZcbLqBSMjo1SvJ53Bc+fOYcOGDfD29hb7Z8+eValHSLvC7eQZOQmDCzLoGJ277XkbJ96fQEOnhmjh3AKhEdEwNNCDkYFSYoQMwzAC+kz9UfCVztN1ev4ewMc70sH8tQBLe5XcRb1YY4S695MHEugn7RMJgwt0zNIyGYNIhmFUDs8VmPTwv//9T1QjEK1atULVqlVTvT5fvnxC4qN169Zif8iQIahcuTKKFCnCN15HggyyCvBh54chIjICz/2fJ5uwJYN87KxMU58bMkxWIl1jfB2S+1G6uXOVQdBeYmGc4yIMTD/D0PIFYj3/UHeHGC1D4SupCbNLGEZVPHnyBHv27BFt8gDp06dPmh63fPlyXL9+XZjAXbp0SQQpaFMlsiBDShgbGCMGkuwTBRrym9TCyN330aJ0boxtWkxFvWQYJitCE4o8efLg8+fPKV6TN29eaeKRUB6pVHuolO+CDBZF5iI2yhwGJj7y4AJdwzCM+uG5ApMeKBEtofdCwnZqUCBi3LhxWLhwIYKCgoQfw7Vr14RUKqMbQYbBpwbjoZckm2VlZIW5deYmCS5ERcfgn/Ovse36BxwdWRt5bJIGHxgmK0JjdxrDpxZkkI/xmZTxfQe8Piu1c5cF8lbS2rulZxDvwxEVVAymUTnV2h9G++AAA6MTUKm0rHqBsuJ+VL0gg3xByI+hSpUqCA0NFaal9erVQ6NGjaAptC/cHu6B7jA1MEWPov1Ra955+IdGisFyrcJ2qF5QKgFnGIZRBjS5SC3AMHDgQKnxVPXySMkFGSyLzIG+QShgEIrosDwcXGAYDYMDDEx62Ldvn0gEItq0aSMqEdLK7NmzcfnyZdy8eRP379/H+PHjsWLFCv4F6CCBkYH4/fLv2NAsQSYxgE1X32PpmVeiPWbPA+z4qToM9HnBlGGIBg0aYPv27T8e4zMpI7wXYuOrF7QgIGNocxdRAWWSJF/FRlsi5N1IGFg+g4HpJ7X1j9FeWF+F0XoeP34sJh8ElT736tUrXY8vVaoUVq5cKdoUpKDHf/nyBZrEiAojMLjsYFiaGuGPFsXFMYqn0EDZPyRS3d1jGEZHuXv3Lu7ciZM9SoaKFSuKBRuQPJLH7QTySOrKeIlGbKxB/G4MyyEwDMNoc/VCQr+F1LwXksPY2Bi7d++Gra2t2P/nn39w4MABhfeTUS0yQ2eqXihiWwSGelLOZHBkcCLjZ6J39fwoktNStG+89cW/F9/wr4thAISHh4vg6w/H+EzKRIUD97dJbWMroHRnjb9b0ea3YOawL6lvnQy9SBhnvwoT+zPiWoZJDxxgYLSehJONqVOnZshDoX///ujdu7doU3CB2mQop4l0q+KIlmVyQ8/wGz77B+OPg4/k1RsMwzCKgj4DE3onUeYoVTMQ9JOqxS5cuAArKyvg6eH4B5ZMXfZNaQhD5+3QNwxGdLgdosNywsDcLeUBNMMwDKPRkPzp8+fPRbt9+/aoUKFCup+jQIECiYxKKSP33bt3Cu0no/rggszQeVOTTdhUexOK2hbFE58ncuNnGWbGBljeowKMDaVlj8WnX+K+2zf+lTFZnsWLF+PVq1fyJM0Ux/hMytD8J8RHapfrDphIwUxNRj+0vJCPlfnWJZojiblUvH8dXcsw6YEDDIxW8+DBA2H8RhQrVgw9evTI0POQtuCqVatQtGhRsX/mzBnMnTsXmgj1tXvtKFgWWgGT3Ifw3+PP2HvHXd3dYhhGx1i/fj1u3ZIyV2rWrIlDhw7Bw8NDBB7oJ/nVyCceMnkk6KlcHimHhTHsrPVgU2CbGBDrhxWBudc4mH4dLdp0jM7RNXQtwzAMo/lERUUlSiJKq/dCcnTo0AEjRowQbX9/f3Tv3h0RERx41vbggszQObd5bmxsslEco3N0DVUzHHh1AFExUSiRxxqT4irAo2NiMWr3AwSFR6n7v8MwauPDhw+YOXOmaJMvzcmTJ1Me4zM6Ze5sZ24JvS8D5UEGq/xbkcPWD7a27onmUhZ+Q8S1DJMeOMDAaDUJJx6k6WtgkEAaI53Qlyj5MZiYmMirIUi3VdMIiQzBlBsTAP0QGGe7DUPr+5h++CneeAWpu2sMw+gI3t7e+OOPP0RbX19fBGDpJ5HE7M3/I+AeV2KdvyZglUulfT04vArKVtqPGNNXYnHhxqAduDa+Cf4bXAWX+mwSx+hc+UoHxLUMwzCM5rNr1y68fPlStDt16oRy5cpl6vkWLFggJD8ICp5PmjRJIf1kVMep96eSBBe+N36WBRkmXJqAademYfjZ4QiMCES/mgXQoJi9uNbNNwRTXVz5V8dkWUaPHi38Jwn6LHR2dhZtNnROB1+eAm7XpbZTTSBnCWgDJ0bXxdO/2mJTi9XIZVQaMHsNS+e1iM6zUpov2ZcXc6k7k1qKaxkmPXCAgdFa7t27JzJqiRIlSqBr166Zfk6avCxdulS0KYJPFRG00KZJmBuZY26duTDQM0BB09qICiyD0MhojNx1H+FR0eruHsMwOgAFF3x9fUWbsj5TXdh5llAeqT1USVR0DLY/3Y7bnreFDvOPFhxocYJhGIbR/OoFyqBVpDE4JRCR5JIsK3fRokU4evRopp+XUR3tCrfDrFqzknzXf/+dP6HKBNzxlPyj7ny5A/dAd7FwuqBLOdhZSolkB+59hMuDj/zrY7Ic//33n3wNpXDhwuyzkFHubNS66oWEVHfOgyNdN6KsfVn4hklzPvKz+afRP8l+vjKMygMMW7duxfv37xX5lAyTIglLpTNbvZCQn3/+GV26dBHtjx8/Cn8GTfNjqOlQEzta7sC+Tv+ggqOUjfPkUwAWn5IyvRiGYTLKjRs3hDwSkTt37h+baj5JII9UUnXySFS1VXfBGex9Ji0QvfJ7hRufbqS44ECLErQ4wTCM+uC5ApMWtm/fjtevX4s2jcnLlCmjkBtHi2lr166V7/fr10/IgTDaA32Pp7b4Ref6lOyDrS22wsHCQXz3l8xRUpyj4MKirvEJE5MPusLjW4hK+s0wmkBYWBhGjhwp3yfje5JIYtJJeBDwcLfUNrcDSrTR2luoR/O3OOzM7GBswHKyjIYEGAYMGIBr167J92nBd+fOnYp8CYYR3LlzB0eOHBHtUqVKyQMCioAyXNatWycvFTx27JgwQdI0StmVgrGhAZZ1qwBLE0MUsrdAm3IO6u4WwzBaTHR0dCJjZ8rwtLGxSfkBAZ8A97hFfacagFVuFfQSwth+xpGn+OQfArdPOcUxKumtm69uigsOHFxgGPXDcwXmR0RGRsq1wWlMrojqhYSQ/8KQIUNEmyr1qFqZKiYY3aJY9mJwae+C5s7NEx2vW8QOP9WW5ng9qzshpxUvrjJZh3nz5uHNmzdy6blmzZqpu0vayeN9QESg1K7QGzCUKqM0mcce/ph34jmC4/xnZJ42D70eoqxdWRSyKgTPEE9xjM4xjNoDDBYWFggJCUm0AMAwyiDhZIMqGWTa4IqCFtSojNrIyEguF0JZvZqIUw5zbBlYFWsGOGPTqxkIimAvBoZhMsbq1atx//590a5fv75YeEmVpwnkkUqpTh7p3POvuPjSC4g1Qn70xooGKzGnzhwY6Cumko1hGOXAcwUmLVUub9++Fe1u3bqJRCJFQ3KopUuXFu0rV64oPIjBaAamhkmDByvur0BsjoPY/XMV/NGiBIwNWTGayRpQYGHu3LmibW5ujiVLlqi7S9oJrXHK5ZH0gMoDoOnQuuy0w65YfeENGi66gAefPgh/GpmnzaoGq7C02lJUyVVFHOMgA5NRDKFAaAC4YsUK2NvbI1u2bOLY8+fPcenSpVQfV7cum4cwaefmzZtCO5AoW7YsOnbsqJTbV6VKFcyfPx9jxowRmU2U8UQLb7L3tiZhZvkZg04PFfp5wVHB+KfhPzDUV+ifN8MwOs6XL18wefJk0TY0NMTKlSt/bPb21CWuoQeUUI08EnnNzDz6VL4/rU0p1HKyU8lrMwyTOXiuwKRGREQEZs2aJdqUPKSshX8zMzPs3bsXlStXFslxtOhWr149NG3alH9BOsyxt8ew7vE60f4a6olqBZazqS2TJaAFZpJGCg8PF/tTp06Fo6OjurulnXy8C3g+ktqFGwPZCkDTOfTgI+65+Ym2vW0wBp/rjLDoMFTNXVXIyBrEGCDUIBRL6i7B2Mtj5UGGlPxuGCYlFLoCOWfOHFFqJVvwpYWJ2bNniy2lDzq6hiQZGCYj3gvKqF5IyKhRo3D+/HkcPnwYHz58wKBBg/C///1P4waj9mb2MNKXqi0CwgPwOcAPb77EoH4xSTqEYRjmR4wfPx7+/v6iTYHVkiUlzeIUCfQE3K5LbafqgHUeldzkjVfe4/03b8q/QovSuVGrMAcXGEZb4LkCkxpbtmyR+/lRBV3x4sWVdsNKlCiBVatWCa81mpP26dMHDx48QJ48qvkuY1SPhZEFzA3NERIVguYFmieaz1FVZPl8trAxl+ZTDKNLuLi4yBM06bOPxvlMBrm9Ib5deaDG38ag8CjM/e+5aOvpxSA4xz/Ci4OonLuyCCBQcD+hbx0FFyjIcOr9KZaYZdQXYGjQoIEoab19+zY+f/4sBmykcVmjRg1FvgyThbl+/TpOnDgh2uXLl0f79sqV5KCB56ZNm8Rrubu74+DBg8IMacSIEdAk7M3tsbLRSmx7ug0t8vyK7v8+gldQOA4Pr4Xiua3V3T2GYTQcqjTctm2baOfLl09kNv0QIY8UJ4VYUjXmyV8CwrDixiFYFt6FaK/2+KMFT5AYRpvguQKT1uqFNH0PZRIyeaZEIgpsfP36Fb169cLp06eFjyCje9R3rI9tLbfh5uebaFWwlTgWFhmNv48/x+Zr79GqbB7806OCxiWSMUxmoCotSpqUQRXKxsZs5Juxm+kLPDkgta3zAUU138Pin3Ov8TVQqlzpWik/WlWfgpHnRiK/dX50K9YtyfWyIAMHF5iMoHANFVtbWzRp0kS0qay1ZcuWaNtWNbIJTNbzXlDFADB79uzYvXu3kPKiaptx48ahZs2aqFSpEjTNzGxW7VlYef41PvpJxjwjd93H4eG1YWrEEyWGYVI21Pz111/l+6TJamlp+ePb9fRQfFtF8kgz/rsJPft90DMIh2HuPfCLaQsnlFXJazMMoxh4rsAkx8aNG+Hm5ibavXv3RtGiRVVyoyhxiORXSdaXgg1Uea+K4AajHopmKyo2GRRgOOHqCX1Tdxx7BNQrao+ulVk6htEd6DNN9tlKlWEU6GcyyMNdQJSU/Y9K/QEN93575x2MDVckTyMrE0OMb14MdpYmWNd0HZxtnJHdNHuyj6MgQ7vCqkkeY3QLpboavXv3joMLjMIgEzbKKiIqVqyo0vcWBRRkUl+UYUWmcwEBAdBEfqlXCNWcpS+Ll17e+P3IGXV3iWEYDYa8k1xdXUWb9KdJ6vCHkDzSh2tS27EaYJNXyb0E7rz3xbGH3xDlXwmI1UPbgh1Q1p6DCwyjzfBcgSFIF1w2zqbqgSlTpqjsxlBAfc+ePTA1lQyB//rrL1y4cIF/MVkEW3Nj9GjoAwvnlTDJ5YLphx/hrVeQurvFMArhxYsXWLBggWhbWVlh4cKFfGcVYe5MXpcV+2j8vSTPusjoKNEe3aSoCC4QVXJXgZ0ZS8wyWhZgkEHZIGQq07p1a7FRm44xTEarF2jwr+ryVdInb968uWi/efNGyH+RZqumYaCvhyXdysPaMgjm+f/Fad8Z2P9AWjxkGIZJyMePH+WfrVQuTZmcafpsfXYkgTyScqXqZBx99BmINUL415YYUnQBJlWfqJLXZRhG+fBcIWuzfv16eHh4iDZ5IRQuXFilr1+2bFksW7ZMtGNiYtCzZ094eXmptA+MevAN88WON9Kiq3H26wg3eolRux8gIiqGfyWMVkPrFMOHDxeVyrL1EwcHB3V3S3t5dxHweS21i7cCrHJDkzn//CvOvXCHWf61cHC6g7418qu7S0wWQKkBBhqg0SCxcePGYtGCtPNpozYd69u3r0Yu0DKax8WLF3Hu3DnRrlKlClq1knQzVQnpwW7dulX+xUzZTjQh0kQcbM1QqfxtGJh6Qt8oADOuzxTa5QzDMAkZO3YsgoKkTL0JEyagSJEiabtBTxLII6nIf2Fam5L4t3cldKyYF8NrNBVmjQzDaDc8V2DIbJLMv9VRvZCQwYMHiwplgrwEaZ5K709GtyGJkIX1FooxhW1Ec0QHF8Xjj/5YdPqFurvGMJli3759OHNGUjIoU6aMxnlIare58yBoMjExsZj13xOYOW6GofkHBFrsx6E3/1N3t5gsgFIDDIsWLcKOHTvQuXNnPHjwAKGhoWKjdteuXcW5xYsXK7MLjI6g7uoFGfb29ti5c6cINhBUjfPo0SNoIv80+wvW+k6IDs2LwI/tMXbvQ/FlwzAMQ5w9e1YESon8+fPjjz/+SNuNCfoKfLgqtfNVVbo8UnRMNDwCPcTnfvPSubG4a3k2YGQYHYHnCszatWvx6dMncSP69++PggULquWm0HcM9aVQoUJin5LiZNIijG5TN19d7GuzD1s7TIWliWRRuebiW1x55a3urjFMhggMDMSYMWPk+6tWrYKhocLtV7MOAZ+B58ekdo4igHNdaDL6+npY2bMSHI1riP2c5jlRPU91dXeLyQIoNcCwefNmoedMCxhUempkZCQ2au/atUuYQZOhF8P8qGyeKhiIatWqyWWK1EW9evXkAQ/KuqJsJ1kGsCZBmTi7225AruAxiI2yxpXX3lgfZ/LDMEzWhvSuExo7L1++HObm5ml78LPD8fJIpZQvj7TpySZ0PNwRe1/s5apHhtExeK6QtaHEs7lz54o2LX5NnjxZrf2xtrbG3r17hWQg8eeff+LatTi/IUancbRyhLOdFWa2LyU/NvLIJqx7sJXHHozWQQmZssBtv379ULt2bXV3Sbu5vw2IjZbalQdSRBqaTvHc1jg56HdMrTYDG5ttFJ9xDKPVAYa3b9+iTZs2KZ6nc3QNw6QESWhpSvVCQmjC0bBhQ9F+/vy50DdUCLGx0H+8B6YvDklGQpnE0SY3VnSvDiMD6Z6tuvAGgWGSDiPDMFmXJUuWCOM3gryR2rZtm/YHJ5RHKpGOx2WAM68fYMW9lQiNCsW8W/PgESRpdDMMoxvwXCFrs2bNGnh6eor2wIEDUaBAAXV3CRUrVpQboUZHR6N79+7w9fVVd7cYFdGhQj60L+8AfVMPRGTbieUPF2DWjVkcZGC0BldXVyxdulS0bW1tMX/+fHV3Sbshk+S7m6W2oSlQrju0BVo361K8A/Jbs/8CowMBBgsLC3z58iXF8zSgpGsYJjUJj8uXL4t2zZo1RUWMJkAasdu3b0fOnDnF/pYtW8SWad5dhOGR4bA9PxF6H65k/vkAlM5rg4nNi6NcPhvsGlIBU66Px2UP6Z4yDJP1cHNzw8yZM0Xb1NRUVC+kCQp63lwLvI/7bMpbGbB1VGqAeeOFIIR61QNi9TGw5K+cfcMwOgbPFbIuISEh+Pvvv0WbKtwpeUdToMSh9u2lCj13d3cMGDCAF5izEDPal0YuO2/o60seHBbGFhqR4MYwaRk7U4UyBUeJ2bNny9crmAzy6iQQ8FFql+4EmGfXyFsZGROJYafG4NhryXeDYXQuwFCnTh1h6PzkyZMk554+fYqVK1eibl3N1i9j1IemVi/IyJMnjwgyyPo0bNgwPHv2LONPSIt3F6SJFmFweb5CqhiIgbWcseWncph6exjOup3FuIvj8MKXzcsYJisyevRosbBDTJo0Cc7Ozml74LuLwPHxKpNHOvnEE9de+yPCuwlyBf6BIeX7KfX1GIZRPTxXyLqsXr1anoj2008/wcnJCZoCje1Jxpf8iYjDhw9j2bJl6u4WoyKsTY1w8Zc/8E+jFWhdsDVGVRjF957RCsjj9NKlS/JqrJ9//lndXdJ+7mzUeHPnqJgoTLw4EZc/n8HvV8Zh2uk97L3JqAWlOr3MmDED1atXR4UKFdCuXTuULFlSHKeAw5EjR4S+JS0aM0xynD59Wq57ShPQRo0aadyNIh8RMkadM2eOWLAj8/Jbt27BzMws/U9Gi3du1+W7+u43gHeXgIL1FGL0Y2NiibJ2ZfHc97nwZ4iW6QgyDJNlOH78OA4ePCjahQsXxvjxFDBIfwBU2fJIYZHRmHk0PmA7p3VTGBkYKO31GIZRDzxXyJoEBwdj3rx5ok3zQQp2axrZsmXD7t27xRwkKioKEyZMQK1atVClShV1d41RAcaG+sL8mbbv8Qvzg62pLf8eGI3Cz88P48aNkwdJydiZVBeYTOD7Dnh9VmrnKQfkraiRt9NAzwD+QZKXXmyMEe69i9UGmwhGB1FqBUOZMmWEOS8NxP73v/8JSQbaDhw4II5duHBBXMMwyVUvTJ06VWOrFxJCfZMZJ5HmIWUHp5vkFu8IOqagKga6f39U+wO9S/TG8robseJ4KDy+SVnMDMPoPmRKP2LECPn+ihUrhERSRgKggm/voQwCIgIw98x5fPQLFfttyzmgqrNmliMzDJM5eK6QNaEqdi8vL9EePHgw8uXLB02EEuVkJtSRkZHo1q0b/P391d0tRg0cvO+BeSee44nPEzQ/0Bw7nu1g2SxGo6C1k4RVYdWqVVN3l7Sfu5viK7c12Nw5MDwKDx7WRbhXI4S5D8K81i01du2M0W2UWsFAVK5cGVevXhWDyHfv3oljJMdgb2+v7JdmtJgTJ07g5s2bol2vXj00aNAAmoqhoSF27dqF8uXLw8fHB2vXrhX9JVO4NJPc4h3hdk1hVQyir/qGaJNvKHqvuwnf4Ah4B4Vj95AaMNDnLyCG0XUoW/TNmzei3bFjRzRv3jzzAVDnugofbE++PBPnPM/AKHszGAbWxR8tiyv0+RmG0Sx4rpC1CAoKwoIFC0TbxMREVAJrMr/99hvOnz+P//77T8xlaeFu7969vHiThZjq4oqt1z8A+qE44rsSwZHB+PvW38hlnguN8zdWd/cYBvfv3xeBWyJHjhzywCiTCaLCgfvbpbaJNVCmi8bezuVnXsEnKBIIaoLe1Z1Q0sFa3V1isihKrWBICAUUqlatKjYOLjDp9V7QdCjzKqHJ85AhQ/D69evMLd4poYqBKGhvgZxWJqJ9+/03/HPuJS55SFqNDMPoJm/fvpVPNszNzbF06VLFBUAVyNWPV3He4wT09KNgnP0yfqrngDw2GZCcYxhG6+C5QtaA/Pm8vb1Fm/TB8+bNC01GX19fjPFl/dy/fz/+/fdfdXeLUSHVC+aQGjGmCPxaG/rQR7189dDAUXMT4JisQ0xMjDB2pp/E33//LYIMTCZ5ehgI8ZHa5boDxhYatV62+M5iPPV5itdfA7H5mlRVbmNmhLFNiqm7e0wWRmUBBoZJK8eOHcPt27dFu2HDhqKCQRto1aoVxo4dK9qBgYHCjyE8PDzji3dKWsQzNTLA8h4VYGKoD+hF4N/n0/Hr2V+x/+V+hb0GwzDQqEHoyJEj5Z9HVELt6OiY1gcD52arLACK0CII/9ocsTEGsArqhV/rsYwiwzCMrhAQECCvXiCJvt9//x3agJ2dnahWpmADMWbMGDx48EDd3WJURMsyedC9Co2b9ODvWR3O0b9hbu2/YaDP+vaM+tm8eTOuX78ul3UbOHCgurukG9zZEN8meSQNmtdRBdWmJ5vw06mfMPHIMUTFSHOxcU2LIpuFsbq7yGRhOMDAaBT0gTl9+nStql5ICJk9U5WOrFTxhwaqP6pekHFhrkIX8YrmssLk1iVhYP4ehlau4tiC2wuFaRnDMLrF4cOHReCWKFGihFgYSTNvzgMet1QSAI2JicXMo88R4VMfwW8mYkaTjiIgyjAMw+gG5P3j6+sr2kOHDkWePHmgLZDZM5mSExSwJz8GSihisgZT25REQTspg/nBSzvsvvk10flnPs9EFSbDqBL6PJ04caJoUwCUjJ1lgVAmE3x5Ep8A6lQTyFlCY25nVGwUPgd/Fu3QyDA8+OQp2sVzW6FHVSc1947J6vCnD6NRHDlyBHfv3hXtJk2ayM2TtQVjY2Ps2bMHNjY28onUwYMHM169IIOuUbAUSe9qTmjgVEdkC8dEWaIExsHGROo3wzC6QUhICEaNGiXfJ31W+pxKExTUdBn24+sUVMWgr6+HSS1LoJC9BWo7F0STkrky/ZwMwzCMZkDmyIsWLRJtMzMz+aKYNkEVF40bS5r7L1++FEESSo5idB9zY0NRAW5kIPlOzT/5HK4fJcNv71BvjDg3AsPODsP2p9v5PcGojEmTJskl54YNG4YKFSrw3VcEdzbGt6sM0qh7aqRvhEX1FqFZ/hYw8R2A6OAi4vj0tqVgaMDLu4x64XcgozFoo/dCchQoUAAbN8Z/KVGZ4vv3ki5eEm4nKL37EScUW0aup6eH+Z3LwiaiKULejsaFx2Y4eP+jQl+DYRj1Mnv2bHz48EG0e/ToIQzo08yJiUCglCGTKpmsYnjn/w5PfJ6Idt2i9jgxui6WdCvPBpoMwzA6xLJly/Dt2zf5QliuXNoXRDYwMMC2bdvkfd+xY4eQJ2GyBqXz2mB8M0nfPDI6FiN33UdIRBSOvT2GLyFfEBMbg2ufriEWHHRilA9JSq9du1a0c+bMiZkzZ/JtVwThQcDDPVLb3A4o0Ubj7quRgRF+rzwTpbNVF/uty+aJ94phGDXCAQZGYzh06JBcz7RZs2aoUaMGtJWOHTti+PDhou3n54fu3bsjIiIi6YVVBwOWuRJtsRY5EW1uL34iYUXB16fA7fUK7Wd2C2Ms7VYBiLEU+1MOueK9d7Bo0yCZYRjt5cWLF3KtaysrK3nmaJp4dRq4uSbt12fwsykyJhK/X/4dvY/1xpqHaxAVEwUjA33YWUpG9AzDMIz2Q2PhxYsXi7a5uTkmTJgAbSV37twisECJOgSZqz55IgXJGd3np9oFUbuwnWi/9Q7GjCNP0bdkX/xe9XcUzVYU8+vOh76ePlxeuyA0KjTF56FzdA3DZITo6OhEFVQ03re1teWbqQge7wMi4uTvKvYBDNU/J9n9fDc8gyUpJBk0V1rfrwo2D6giKsAZRhPgAAOjEcTExOhE9UJC6IteVqZ48+ZN/Pnnn0kvcq4LjHuZaIsc9QRefa+In/jDDWizPP76Y2OBB7sU2s9ahe0wpG5B0TY21MdHvxCsuL8CEy9N5CADw2gpNOGgIGdkZKTYJ93oNGtdez4G9vWP3ze2TBIITbJRsDQDHH1zFE99ngo90UseipWBYxiGYTSDJUuWCIkkgr6bKNtWm2nUqBEmT54s2qGhoejatauQJGR0H5JzXNy1nEjSIvxDI4XBaq8SvbC79W5YGluKwMHkq5Mx4uwIBEdKiVvfBxfoHF3DQQYmI1DlgkxWmvxh+vTpwzdSEVDARm7urAdUSjAfUhMbXTdi9s3Z6H+iPz4GJVWbqF8sJxxszdTSN4b5HkOoYJHjzJkzePXqFXx8fJJoElL2x5QpU5TdDUbDOXDgAB4/fizaLVu2RLVq1aDtmJqaYu/evahYsaIwgVu4cCHq16+PVq1ape+JKvUDIkPiJZJIE93IDCjVXmF9HdukGMIjYzC0fiGse7oQe15IZYGOVo4YWXGkwl6HYRjVsH//fvHdS5QpU0ZeUfVDAj4DO7sBEUHSfuVBQKtF9GWtlH62LdQWKy88xVfDI2jj8BsM9NjUmWGyGjxX0G1IFmnp0qWibWlpifHjx0MXmDp1Ki5evIhLly7h6dOnGDlyJNavV2ylMaOZ5LQ2xcIuZfE1IBzdqjjKq1lIG51oWqApjrw5gpueN9FgbwPMqT0HjfM3ThRcoHPVclcT1zJMevDy8hLeCzLZNvJXk70HmUzicUdKtCIKNwayFVDrLY2IjsDJ9ydF+1PQJzz2fgwHCwf+fTNZM8BAQYX27dvj+fPnKZodcYCBoeqF6dOny29Ewra2U7hwYZFhQNrnRL9+/YQMVL58+dL3RNWHAhHBwLmZAEkX/W+QFGQo2kwh/aTKBTIGIloXbI2Drw4K/dDCtoUV8vwMw6gOCmiOGTNGvr9q1SoYGhqmTXN0Z1cg4GP8wLrFfKUFF4hjj7/g9ZvygF5J7AoORddySn05hmE0DJ4r6D4kjRQQECDaI0aMgJ2dJC+j7dD36s6dO1GuXDmRRLdhwwbhc9SrVy91d41RAQ2Lp+whYmZohkX1F6H5/5ojKDIIYy6Mwfw681HfqX6i4MKKRivEtQyTHiZOnChk54hRo0aJRCJGQcirFzTD3NnYwBjrmq7DsDPD0KlIJzR2bIqua66jcYlcGFDLWazhMEyWCTDQIPLNmzeYN28eGjZsiBw52HiEScq+ffvk2qVt2rRBlSpVdOo2kf/CuXPnsG7dOjEBoWDD+fPn07bgl5C646Qgw5XFQEwUsKcP0GsfULCeQvtbPmd5/F33b9gaZ0fxbGUV+twMwygfkkP6+PGjPKhZu3btHz8oJhr430+A5yNpP1dpoPMmwEB5wwQyRpxz7Jm0E2ssgpwkPcAwTNaB5wq6DY17ZdUL5AU0duxY6BJ58+bF1q1b5dXJv/zyi5jHFC1aVN1dY9SAX0gEbM0l6SRzI3M0zd8UB14fEPtbn23Fjuc78NDrIQcXmAxz9epVbNq0SbQdHBx0KjFT7YT4Aq7S3yus8wFFNKO6yNrYGluab4GBvgG23fiA2++/ie2NVxDmdy6n7u4xjOoCDJcvX8bo0aMxbtw4Zb4Mo+UGRQn9FnT1S5ImV9evX4erqyuuXLki/p+zZs1K/xM1mirJJd38F4gOB3b1APocBJwUKylVxKImRu2+jzw2j7C6d0Uuw2MYLYGCtbLFHDJ7mz9/ftoeePJP4OVxqW2ZG+i5BzC1Vkofb3y+ARMDE5y9bw7PgDBxrHOlfKjglE0pr8cwjObCcwXdZtGiRQgKCpJn2upishlJu5LsE3mv0f+V/Bhu3LghpFKZrAEpNWy+9h4LTr7A9p+qoaJTNiGX9Fetv4Txs8sbF7h6u4pry9mX48oFJkNERUVh2LBhiarDKHDLKIgHO6X1FYK8F/TVI9t6wf0CquSuAgsjC/kxCi5QAHPRqRdx+3oYXEfy0GQYTUKpNTUmJiZwdnZW5kswWg55FDx7JmWwtmvXTvgV6CLm5ubi/0o/iTlz5uD06dPpfyLSDmk2F6gQZ+RExmE7ugCfHiisrzExsRiy7Q4eevjjxBNP7L7tLo6f+XAG38K+Kex1GIZR/ASXJh40ASFmz56dNiPNm2uAm6ultpG5FFywSaeMWxqhz5DfL/2O/sf7Y8PTlfSJA0sTQ0xoXkwpr8cwjGbDcwXdxdvbG8uXLxdta2tr/Pbbb9BV6Pu2evXqov3w4UOdq9RgUuf00y/468hThEREiwStwLBI+bmORTsKmZOE+If5wzPYk28rky7Ia+HRI6nSmNRBKJjJKIiYGODORqmtbwhU7KuWW0veLSPPjcSQ00MQECFJC8pYfPol/EKkz5a+NfKjSC4OLjFZLMDQrFkzUcbFMFm5ekFGiRIlhBa6bCGwd+/e8PTMwOBSXx9oswwo3UnaD/cHtnUAvsZJjWQSkiiZ3aEMZEolfx1xxU/HfxX6oaPPjxZmQ99DhmUur10U8voMw2SMHTt2CLNJolKlSvj5559//KAXJ+IN5KEHdN4IOJRX2q/g0OtD8AnzQQxiEKvvL4YhIxsVRk4rzvRkmKwIzxV0F8roDw4OFm2qaM+WTXer1IyMjLB7925ROUjQeH///v3q7hajIpqUzIXGJaSEDnffUEw55JrI0JlkkahygTZqdzzcET2P9sQLXykbmWF+xOfPnzFlyhT55w0bOyuYdxcB3zdSu3hrwCpljxVlER4djpUPVgofzEdej3De7bz83LPPAdh+44NoZ7cwxujGLMPHZMEAA5VtkSwMlcdGRCRdlGSyNrt27cKLF9LAqmPHjihfXnmLWpoC6aH37StFxL9+/SqM4CjQkm6oZK/DGqBYS2k/1BfY2h7wiftizCRVCmTHiIZFRDvK4jpufpUWLe99vYdLHlJbhmzwPPnqZA4yMIya8Pf3l8sR6unpicUNA4MflPZ+fgjsHygZxxPN/waKtVBqP/uX6o9eBcchOiwXwr60RUE7C/SvyZWODJNV4bmCbkJj3H/++Ue0bWxsMGbMGOg6+fPnl2ujE4MGDcLbt2/V2idGNdC4i7TQc1qZiP1DDz5hz93XiQydyaiVNgdLBwRGBsIrzAt/XvlTJJ0xzI8gGbbAwEDRpgqp4sWL801TJLLqBTWaO5N87IZmG5DXMi9GVBiBdoXbieP0GTH98BPExH1UTGhWDDZmRmrpI8OoNMBQsGDBRFutWrXEoseECRNgYWEhBl7fX1OoUCFFdoHREkjCg4xIZUybNg1ZBco4KFZMkgMh82eSS8oQBkaSCWvBBtJ+kCewtR3gJ0kaZZYRDQujUv5siPKviKgQJ3GsoE1B1MpbK0lwQTZ4blpAM8yQGCarMXXqVHz58kW0f/rpJ1StWjX1B/h/BHZ2k2TWiKo/A9V/UXo/o2JicfpWfoS8GwXEmGJqm5IwNlRqrgPDMBoEzxWyTvVCSEiIaJM0kiyzX9dp3749Ro4cKdoBAQHo1q0bJ9llESireHHXuGQ5vQjMvD1ePj9a0WgFzAzNxLar5S7YmNiIy0wNTREWLXlRMUxKXLhwQVQpE05OTpg8eTLfLEUS8Bl4fkxq5ygCFKijtvtLwYV9bfZhSNkh8mPHHn/GzXe+ol0mrw26VHZUW/8YRqUmz/SBRxF8hvkR9CX56tUr0e7SpQvKli2bZW6apaWl8GOoVq0awsLChDRU3bp1Ua9evfQ/mZEp0H0nsL0T4HYN8HcHtrYFBhwHrHJnqp+GBvpY2q08Wi67jEC3n2DmuAlv8VYEFGigTCQMLsgGzwzDqJYHDx7IM0XJQHPu3LmpPyA8UAouBH6W9os2B5r/4DEKwjsoHObGNPTQF3IC9YulwSOCYRidgecKug/Jf1IyDUGBBTJ3zkrMnz9fSATfvXsXd+7cwe+//y4qdRjdp3YRO/xctyA2PNwHPbPXMIsqhsX1lyWaH2U3y47jHY/jl9O/CLmkU+9PyTOVGeZ7IiMj8euvv8r3ly5dKhJ3GQVybysQG6coUXmg5HmpIp74PEGxbMVgSL4PcVgZx3srhEREYc6xeBns6W1LCoNnhskSAQaKrjJMWr4oZ86cKdoUkMpK1QsyKKCybNkyoZEeExODnj17ikVCe3v79D+ZcZwpKwUWPt0HfN9KckkD/gPMs2eqn47ZzWFlZojAcGOEug+AmeMWKaCwUTKVijV5D/2wInhwtyPq3rmKHBbGODG6bqZek2GYtEOfH2TsTD+Jv//+WwQZUiQ6SpJF+vJY2s9dFui0QZJdUxL7X+4XGTk1HGogj40ZXH6thX133VHNOZV+Mgyjk/BcIWsssIeGhoo2SfeRRFJWMy7fs2cPKlSoICRNlixZgvr166Nt27bq7hqjAsY2LYYt16og9BMQGFAG1WdfhoVJ0iWXWL1eMDIrhdVHs6HdaCAyOhI7nu1ArxK9YERV6gwTF1B4+vSpuBctWrQQVVKMAqF50d3NUpsCgeV7qOz2Xvt4DSPOjUA9x3qYV3cejPST/t2ff+6FT/5SlVPHCnlRKX/m1nYYRtkoVZeAzCa9vLxSPO/t7S03pGSyDtu2bcObN5JXAJUOlypVClmRwYMHi/8/8enTJ+HNIFskTLcep6k10PsAkDPuXno9k4yfw8hENXNERsf1JZaCDP0QHeIkAgtiizFEgEdbeAfEwiswHD7B7LXCMKpk8+bNwuuIqF69OgYOHJjyxfS5cmIi8OqUtG/lIAUnTSyV1j8yMJxzcw6GnB6CxXcWy43ku1VxQgE7zsBimKwOzxV0z4h09erVop09e3aMGDECWRGSAF6/fr18v3///nBzcxNt1tzXbUj20dzEEFH+lcTcKSQiWsyRvt9o7uT7pZyYOwmN9evTsejuIgw9MxSBEZLWPpO18fDwwF9//SUPXC5fvpzVQhTNq5NA4CepXboTYJYNqoBkpiddmYSImAic/nAaR94cSfa6VmXzYN8vNVDVOTsmtmDfDSaLBxgaNGiA06dPp3j+7Nmz4homa1UvzJo1S169QLrhWRX6/69du1buQ3LixAk0bdoUzs7OcHBwED/p/sgMnX4IVSv0PQTkKCztf34A7OgCRAQr7/+gHwWzfDuE1ijDMKrF19cXEydOFG19fX1h7Ew/U+TGauB23IKHsSXQay9g7aDUPp76cAqRMZGind2Us24YhkkMzxV0C6qiI/lPmSmptbU1sipdu3YVlcrEt2/fhDdhhsf4jFaRXgmTj0Efcd79vGg/9X0Kr9CUEzSZZJJnHuySNh0zzB4zZgyCg6V5PI33CxeOm+MziuP2hvh2lVSStBQMyaataLgCVkZW6Fq0KzoU7pDitVUKZMfen2sgl7WpyvrHMBoZYPhRhkZ0dHTqiyGMzrFlyxa8e/dOtHv06IESJUogK0MTLyqjNjQ0lAfdqJqBoJ8kJUVl1WmegFjmBPoeBmwlU2a43wR29QAiFWAgphchJJIMzN0QHeKI2BipjE/PgJ5bqrxgGEZ1TJo0SVQCEiSTRHIMKULmZScnSW09fckgPncZpfdxRIUR+Lv238iOirCJbMiZmwzDJILnCrrDx48fsWbNGtG2s7PD8OHDkdUheSRZpTZlI2dqjM/oLPms8mF7i+0oYF0AyxosQ0Gbgurukvbw7iJw6Bdpe6c7yhinTp3C/v37RZsCkuTlwigYkpV+c1Zq5ykHOFTM9FO6vHYR1QkpQefoGqKMfRnsabMHf1b/kytTGJ1B6av7qZk+X7t2TQxAmaxBRESE3HuBAktZuXohIZUqVUKjRo1SPH/v3j0sWLAg7U9okxfo6wJY5YkfeO3rB0RLWcSZCS4YWrxBVHAhhLgNRvDbkYgOywl9Iz+YOW7jKgaGUSG3b98WFVBErly55J+tyfLxHvC/n2gpT9pvMR8o2lRFPQVC/crhw7OuGLPnMf46IunIMgzDyOC5gm4wd+5chIeHy6sXLC2VJ7+nLZiZmaFu3bqKG+MzOktB24I42O4gquSuou6uaA+UzHrh7/h9autAFQN9jiYM0K5YsUJ8ljAK5s6m+HblQZk2d6bAweSrkzHi7Ihkgwzv/d9j+Nnh4hpZkMHRyhH6lPiVgMjoGKy//BahEXHG0wyTlQMMZFxbsGBBsRGjR4+W7yfcsmXLJjQ6W7dureguMBrKpk2b5PqjvXr1QrFixdTdJY3B1dU11fMbN25M3xNmLygFGczjAngvTwAHBgMx6f+iiv0uuEA+DKQpGhtpj5D3w8UxOkfX0LUMwygXqv6jigVZ5i8tTtja2iZ/sZ87sKs7EBki7Vf/Fag6WGW/osCwSPx9/Llo07i9c6V8KntthmE0E54r6B7u7u5Yt26daNvb2+PXX39Vd5c0hsOHDyt2jM/oLIb6ic2gaZxHPlb7X0qZ7Mx3UBKdm+RDJnC7phNVDAsXLsSrV69Eu127dmjVqpW6u6R7RIUD97dLbRMboEznTD9l0wJNUS13Ndz0vJkkyHD/6320d2mPW563UDV3VXFtSmy7/gGzjj1Do0UXcPOtT6b7xTCqJPG3mAKgRY78+fOL9vv375EjRw6RXfl9plLp0qWFISVpyzG6D0XiZ8+eLdoGBgaYMmWKurukMdDgkcrKU4PO03WpZfklwb4Y0OcgsKW1ZPb85CBgZA60/YdKSNL8NDFmD5IEF+I7Lxk/ywMQURfw1r84l/YyjBKhRZw7d+6Idp06ddC7d+/kLwwLAHZ2BYK+SPvFWgFNU6l0UBALbi8QGXj1HetjxbnX8A6SMlq7V3FC6bw2Sn99hmE0G54r6Gb1AlUqy7TCLSws1N0l3R7jM1mCja4bsev5LtH2CfXBz+UkTw8mmeoFGXTMuW6ms9HVBa2fydZMqGqBAvKMEnjqAoT6Su1y3QFjC8X4KjRaIYILsiAD7YdGhmLgyYGIjpUSPVs4txDXJgfNmZaceSnaXkHhsLcyyXS/GEaVKDzA0K9fP7HJ9OLI7Ktt27aKfhlGy9iwYYPIbiL69OmDIkWKqLtLGgNNKPLmzZvqBITOZ2jikacs0Ot/wLb2QEQQ8GCHFGRouSDNAy+DkKoICItCVECZxMGF74IMJjmPw9j2LEade4YdrXbA2jjrGvsxjLLw8vIS3guyYO3KlSuT/2wgSTSSRvsaJ0mUpzzQaR2gb6DUX87pD6ex9elWsXUq2Bfbr0ja09amhhjXtKhSX5thGO2A5wq6xYcPH7B+/XrRpqSyoUOHqrtLWWOMz+g8MukUAz0DlLYrre7uaBavTieuXvi+iqFgPWgjo0aNQmiolPk+efJkeeIuo0Rz58oDFPa03wcZBp+SqsajYqKgBz3UyVsH7Qq3S/HxC0++QGBYlGgPrO2MgvYsNchoF0r1YCAzXw4uMGFhYZgzZ458QYy+LJnEDBw4MFPnU8WxCtBjN2BoKu3fXgecmZYujcoo/0rJBxdkxBpC3+QLoB+B9wHvsePpjoz3l2GYFKHM0G/fvsknIWXKJGPUTH/b/40H3pyT9q3zAT33KCQ750c88nokbz94lR1RMdLnzG9NiiKHJWfhMAyTGJ4raD80xo+MlHy+yIjU3Nxc3V3KOmN8RqcZUHoAFtRdgGk1pqFW3lrq7o7m4OkK7Oub8nkt9WI4evSoXFKtaNGiGDt2rLq7pJt8eQK435Da+WsBOUso9OkpyLC4/mKUsy+Hh14PxUbttU3XYkmDJTDSN0r2cY89/LHnjpSQS5ULIxpyQi6jfSg1wEB6cYsXL8b9+/eV+TKMhkNZTbLMHcpaK1SokLq7pHGQGV7FihWTPUeVQHQ+UzjXAbrtAGRfaFeXAZcUaSqnj7CPPYGobBhQagCGlB2iwOdmGIa4evWq8LIhHBwcMH369ORvzLUVwN044zJjK6DXXsAqt0pu4tjKY7GswTI0ydMTD15Kr1k0lyV6V+cMLIZhksJzBe2G5DxkHgJ58uTBzz+zhEt6xvgkF5bpMT6j0zR3bo4ORTokOe4f7o8sR0wMcH0VsLYeEJnURFebvRioamHkyJHy/X/++QcmJpyYoxTuJPC9qazYAO/Lby/x55U/0eVIF8QicZCLggzGBsknbJJM3rTDrvK42B8tisPSROFiMwyj3QGGu3fvYty4cahcuTLs7OzQqVMnIefw7NkzZb4so2FflrLqBUNDQ65eSAErKytcuHBBeFPQwmFC/P395aWSmaJIY6DLJkAvTiLl/Gzg2j9QFLHRljD6PA6/Vf4NBkqWYWGYrEZUVFQi00wK3tPnRhKeHgZOT5Xa9LfedTOQS5IpUhW1HOrh7sPq8v1pbUrB0ECpww2GYbQUnitoN7NmzRLfT7LqBdIMZ348xqeKbsLPzw8nT57kW8aki+1PtwvD2Kc+cTKYWYGAz8D2jsDJP4AY6TMnVbSsioFkxamij+jSpQuaNGmi7i7pJuFBwMM9UtvcDiihWCn3bU+34fCbw/gU/ElUdVNQQVbJ8L3xc0IOPfiIe25+ol3RyRbty+dVaL8YRlUodcbv6ekJV1dXLF26FHXr1sXFixcxYsQIYfBMA6xevXrJs14Y3WTt2rX4/PmzaA8YMEBk4zMpT0BmzJghBhefPn3CkCFSFYCvry+GDx+umNtWog3QfjWtPEr7p/4E7sRlOqdADgtjUaaX0mZmFB9MiIg0ERH4hHy/zzBM+lm1ahUePnwo2o0bN0bXrl2TXuRxFzhAnxtxf3OtFgGFG6v8dh99+BkffEJEu0Xp3KhV2E7lfWAYRjvguYL28vbtW2zevFm0aV4nG7cyPx7jy2RQiGHDhsHb25tvmw6R2tyJziV03DA3Tl9S1rVP1zD/9nx4h3pj0MlB8AuTFiV1mmdHgNU1gbfn0/4YLapieP36NebNmyfaFhYWIomIURKP9wIRgVK7Yh/AMBUJ6B8QGRMptoR0L9pd3i5sWxjrmq4TW7Xc1eTGz98HGYLCozD3v+eiTXY809uWgr4++/Iw2onS625KliwpNgos0ELjgwcPcP78eRFY2LVrF3bv3s3akzpKSEiIiMYTRkZG+PPPP9XdJa2BzN6o8oOymsg8b9++fWKjjIZMU64bEBkCHB0t7R8dIxk/0/FkODG6bqpPFxIRhZbLLuO9T4j4gtx7xx3dqjiJcy98X2D2zdlCh9DOjBcZGSYjUJCWMh9ln6UrVqxIagj57QOwqxsgG7TWHKFQ07KUINOyEedGoF2hdqKMn+hYMS9MjPSx+NRLTGqpWF1ThmF0D54raG/1QnR0tGhPmjQJpqZxXl9MqtD3NyUKDB48GOvWrYOXl5eYJ9O8mNENfjR3ornShP2SZ1VMbKyYP6VVDqW8fXnUy1cPFzwuYESFEbA1tYVOZ5tTxcK9rfHHjC2BiKC0Pf72eo03e6b1Mfr7Dw8PF/skf5ovXz51d0s3oaTH27LkZj2gUsbmScGRwfjfy/9h+7Pt+KXcL+hYpKM4ToGDJfeWiHaV3FWwstFK4cdAJDR+pp+0Lzv3z7nX+Boo/f67VXZE2Xw6/DfN6Dwq0yz48uWLCCaQRBJpyj19+lRI5tSoUUNVXWBUzL///isy04hBgwYhf37W4E5vttOGDRvk+ySPQpMQhUALj80k6SqR7XxoqCStkgHMjQ2xqGs5yALtc48/F0GHu1/uos/xPrj/9T7GnB+DiOgIxfSdYbIYpM8cEBAg2mT4Vrx48cQXhPoBO7sCwV7xlUqNZ6ikb+ser8OVj1cw/tJ4rH64Wr540rqsA878Vg+O2dnsk2GYtMFzBe2BMm63bpUW/Wgx7KefflJ3l7SOhQsXwtHRUbRpjnzgwAF1d4lREV0q5UPjErlE2903FBsuS9I4acHcyBxLGyzF0vpL0bNET+gsVJW7pk7i4ALp5XfeDFjmSryZWMdfY2IVf7zqYGg6Bw8exIkTJ0S7VKlSGDVqlLq7pLt43AG+PJbaRZoA2TK2NuUV4oWFdxbic/BnbHmyBTGxMeL4qfenRACBqhUSBhcIalNQQVbJQNfKaF02D6oUyAYrU0OMa1Yss/9LhtHdCgYXFxecO3cOZ8+eFQEFWnQoV66c8GJo2LChkE2iMjBG9wgODpaX+hkbG4vMJib9NGrUSBjmrVmzRp7hRJMQhVDjVyAiBDg/iwwUgP0DgR67pC/cdFIpf3b8Uq8Qzj77isXdyomgQ7FsxeBg4YA3/m9gYWwhAgwpGRsxDJM8pNu8Y8cO0XZyckrqYxMdCezrB3hJpbVwqAh0WAvoqyZ/ICgui8zUwBTNC0gVDDK4vJdhmB/BcwXtZObMmfLqBapQZjPS9GNtbS0qGJo3l747hw4dinr16iFHjhwK/m0xmgaticztWAYPl/uha+V8GFq/ULoeT153jfI3SnL8xucbqJizonbPt2KigcuLgQtzpfmpTCu/3T9AsRbS/riXiR/j5wYsLSO1C9YHum2HtqyXjB4dpygAiERcqlRmlMSd+MRNVB6U5oeFRIaIwJ6MAjYF0MCxAS59vITSdqXFeUtjS7Qr3E6cb1qgaaLgwvdBBgouyK4lSue1wd6fa+CddzDsLNnYm9FulBpg6NChgzCx6tatmxiI1q9fH9myZVOqJA/5O5C+JWV7U6UEoz698K9fv4o2ZTXJMnSY9DN//nwcP34cbm5u2LNnj5BJoiCdQqg7TiozvboUIA3BPb2BXvsB5zrpfqrRjYtiVOMiMDGUtETpi3Z5w+VweeOCYeWGsfEzw6STyMjIRMbO5GeUKChPpb4kcfb2grRv4wT02A0YK65qwOW1S4oDZWJ4heHQhz4K2RbG4/cmcCoTCwPWDWUYRkPnCkzmefHiBbZv3y4PfA8cOJBvawZp1qyZqPKmimWaN40cOVKeVMDoNuTHcH5c/TRLI/2ISx6XMPLcSFTIWUFUONiY2EDrILlP8hJzvxF/rHAToN1KwEqq+EgWWycgWwHg23vg/RUgJkZliTaZgb7z3N3dRZu8SSnAyCiJEF/ANa5KzMYxTQmVtz7fwsYnG+ER6AGXdi6J1jLGVR6HSdUmIZdF4vdlwsBBctB8KrlrKOhY0N4y7f8fhtFQlPrJW6RIEZHdsnfvXpHNTqWgVM0QFhamlNebOnWq4iRkmAwTFBQkFsUJymj6448/+G5mMsNp/fr1yjGDIx33xtOBKnElpFFhwM5ugPvtdD+VsaG+PLggw8naSeiDJvxCZhgmbVBAgar/iBYtWqB9+/aJL6DA4P1tUpvKw3vtTX0CloHgwuSrk5M1JCPoGJ3b/HQzbr7zwchd99H2nytw/eivsD4wDKPbqHquwChmUSyGFvAAUVVHlcpMxlm0aJFcc33nzp04dOgQ384sgqKCC5HRkZh1YxaiY6Nx58sdnP5wGloFJcw83AP8Wzs+uGBoCrRYAPTal7axbYG45LjQb8AXV2g6z549E3/7srk+ffcxSuTBDiBa8jlApX5AGtYm9r7ci6sfr+JDwAecd09sMO5o7ZgkuJAeIqJiEBCW2CCaYXQBfWVnuFBUlrIySpQoITIymjRpIjKTGjRoIAaoV69eVchr3bt3TyzG/PXXXwp5PibjUHmfbAF8yJAhbFSkAOjvhszgCFmGk8KgIEOL+UD5XtJ+ZDCwoxPwWTIfyyj+IZFYePIFIqOlSagM3zBffAr6lKnnZhhdx8PDQ/59RoHaJMbOTw4CZ6ZLbX1DoOtWIKdiDZWpckGmFZowyBAdEy0PLtC5Sjmr4MQtaZD97HMADA2+M6BmGIbRgLkCo5hFMZkZcYECBdC/f3++rZnExsYGa9eule//8ssv8PX15fuaFmJjof94D0xfHJIWqbWc88+/4uQTyb8wPRgZGGFNkzXIa5kX3Yp1Q6ciCqp0VwXkI/a/QcDBIUC45DeGXGWAIReAakOkeWpacE5grP3+MjTd2Hn48OGIiooS+/Q9lzt3bnV3S3ehgPidjfFzpgp9kzVujoqRfh8yBpSSTKBJ9tncULGecpuuvkODBRew57YbYmK0/7OLYWQovXYsb9686NOnDzZt2oT379/j1atXIhBAi6TTp09XSCkYZT7R4itpWHbsKLm4M+ohMDBQXr1gamqK33//nX8VSjCDo8kdmUIpDCojbbsCKBX39xPmD2xrD3i9yNDT3f3gi2ZLL+Gf86+x4txr+fHnvs/R42gPDD83XOgVMgyTPL/99pvQZiXoc7RQoQT6vO63gAM/x++3WgwUaqDwW/m9IRkFFDyDPNH2UFt0O9pNbmSWL2I4vklWDOhTPT+K505gtscwDKMBcwVGMcyYMSNR9QLrhSsGqlIcMGCA3OycjV7TyLuLMDwyHLbnJ0LvwxVoK7TgPOngYwzYfBsT9j/Cl4D0V3A52zhjd6vd+L3q74kTUjQZkjNaXQtw/V/8sZojgMFn0580I6tgIN5pdoCBJI/Jp5QoX768UCdglMi7i4DvW6ldok2iihifUB8svbsUTfY3SVL5U8quFHa23Il9bfahZt6aCuvO14AwLD/7Cj7BEZji8gSf/JNWiTOMtqIycTqaLJBRLZn9TpkyRWTA0Jdp9uzZM/3cS5YswfPnz9lzQQOgLFtZ1g1l4Dg4OKi7SzpnBieDzOB8fHwU9wJUKthxLVA0zkArxAfY0jb+Czkd5LAwgX+oVPa38vxrPHD3E+0FtxfgU/AnvPr2Civur1Bc3xlGhzh16hT27dsn2gULFsTEiRPjT/q+A3b1iC/zrT1GKvVVEt8HGTof7Qy3QDe883+H/Fb5MbL0XOy6KWXbZTM3wpgmRZXWF4ZhdBtlzhWYzPPkyROxMCb7burbN2kWKJNxFi9eLJ83kcfF4cOH+XamBlUsXPhbvmtweb7WVjFQQMAozr+K5k8UZKDPvvRia2oLQ8rQTsDNzzex98VeaBRREVIV7ubWQICHdMzKAejrAjSdBRhmwOjWOg+Qo4jU/nAViE6cja4pBAQEiCSihL6VhoZKtUVlEpk7J/YM8g71xgbXDQiMCMQm101J/u7K2JdReMDu7xPPERwhGZj/XLcg8mVTbHUEw6gTpX6abdmyRURnz58/j48fP4o/WFokrVu3Lho2bCi2smXLZuo1yNB52rRpwn+BSnUp8ymtUEk2yVAk5PHjx3JzzYiIiEz1TZeh+0NlffQz4RemTD/QzMwMY8aM4XuooHsrg+QCKMOJsvwow2nEiBHYvHkzFEr7tTDc2wv67y8BQZ6I3dIWkX2OANZ50/wUDtZGmNisCKYffY7omFiM2XMfLkOrY0a1Geh9qjeK2hbFTyV/Utn7I7V7yvA9VSffvzfDw8MTGTuTPisZoIq/lVA/GO3oAr0QSYIuunhbRNf5HVDy35EBDLCozlJF3tMAAMh7SURBVCIMPTcUj32k70gjfSP82+BfjNv7WvyNE2MaFYa5ITTiu5P/5vmeagvqfq+q+3tRWXMFHuMr/j1J1SSyxRfyV6O2Jnze68rfu7m5uZCZJeNz4ueff0bVqlU5wJYCeu8uwcjtunxf3/0GIl+dQ2zCTHYt4rdGhXDppRfe+YTg4ksvbLv2Dt2rSN4cGeW132uMPj8aQZFBcPN3w/Byw6Gvp6/e7yWf1zB0+Rn6nvFSvDHF2yCqxSLALFumxrQGTrVg4PNKSC1Fut9FrEMFqJvv7yUFzz9//izaJDFXqVIl/hzN5D1NlcDPMHr+HyhEEJOjMLxyFEO2BO8xZ0tnVM9dXcxvquSsguCwYBgbKM9X6L6bHw7c+yjaua1NMKimk0b8/tU9FtVlIrPYOF+pAQZaCKWF5lq1aonSL5okVK5cGfokx6IgKEuesmgSRoLTCum9puTZQIvlrH+Z+huVzJxpciErj6bMm2/fvol2v379hOkb30PF3NuEkFzKyZMn8enTJyGV1LRpUyEPpkj0Gi1DtmODYOx5D3r+7tDf1h6+7XYgxtwuzc/RrJA5jjtZ46ZbAN55h2D2EVeMqe+IxZUXI6dZTkQGRcIXvhpxTxm+p+ri+/cmyYK8fi3JijVr1gzVq1eXPkejI5Dt2E/Qo4kTmYPlKg/f2jOBb1J1kLIJiw4TcoQy8prnxbnH3rjxTvobLmpvhkbOZhrzmc9/83xPtQV1v1dpvKtOlDVX4DG+Yt+TVE2yf/9+0XZ2dhbjTk35vNelv3f6zu/ataswPff09BSea8uXL1dLXzUaqmw6Pyfp4fNz4Nt2e9p1+zWMPxs7YsjeF6C8jbknXqBkDgPks81ANn8cNzxuCG154rP/Z3zz/ZambGylfC/FxsLs6W5YX/8belGSBFSMkTkCa01BaLEOQGgsEJq5zxTTHOVgG9cOe3YKwab5oW4S3ksa31MQkbC1tcXYsWP5czST9/RH70+LO+tgHBuNExbmWJ/DEuGnf8LammsT/R0MKzIM1qWsYWFogSD/OM1XJRATG4tph5/L93+t5YCwIH+kXxBN98aiukxkFhvnKzXAcOHCBdSoUUNpN5LKR0+fPo1Lly5l6DUGDRokFnC+r2CgjBHKnuKS7NT/UOiDmUz46N77+fnJ5XsoA+fPP//k+6ege/s99L5cvXo12rVrJ88io4meYt+v2YGe+xCzsyP0PR/C0P897I7/hKheh0R2ib6rVGobU7prqoP4BV0s0HrldQSERWHPg69oWd4RNQqWgqbdU4bvqbpI+N6k7F3ZQgItuJHknPi7jo2FwbGRMPh0U5yLtc0PdN+J7Bb2Su1bTGwMTn04hToOdTDpyiQ89XuKsnZSJvEj70dY7DMD0OsDxBpjettSsLfLBk2B/+b5nmoL6n6v0nhXnShrrsBjfMW+J+n7SAZl4ObMmVMBv6WsR1r+3mkccPnyZZHlTHKJPXr0QKtWrVTeV42vXvC8m+S48ec7yBH4VGurGOpmz46f60Rg9aV3CI2MwZxzHtgxsDIM4uST0kvv7L2R2zY3jr0/hhm1Z4jqU7V8LwV7w/C/0dB/dVJ+KCZvZUS1XQWzbM4wg4Io1Qw4IzUtvO7BRAPk9WT3kgIK9NkpS9YhY+eiRVlWNDP39Ifvz5goGL2QAuNHrazwItIXiPTFi/AXqOkQ76mgqjW/fXc/4vlXyYOySn5bdK1eSGP8UtQ9FtVlIrPYOF+pAQYqb1YWJCNBVQstW7ZE7ty55RmftEBD+Pv7i2N2dnbiAz05yDBXZpr7PfTLpwx8JmVIL1B2n2jBm4IMBMl75MuXuZLOrE7Ce5scbdu2lUslUYbThAkTsHXrVsV2wtgO6HsI2NwK+PoU+l7PYLy3O1B3AnBkuHRNNiegYMrmi072xpjZvjRG7X4g9icdeorjo+vA2jT+w9U3zBcLby/EhCoThHaouu4pw/dUXcjem/R3HBoaKjfPLFIkTkv20gLg0W6pbWoDvV77YJwt7ZJlGcE90B3t94xEhNFr6EXaIdbIG/phRfDiYS9xPjZbCKLNX8HMcQtiPg/AjGMvcGK08r7zMwL/zfM91RbU+V5V90RSWXMFHuMr7j358OFDHDx4UBynBTEy5GbNcMXc2+TIlSuX8CKhsT4xfPhw1K9fXyxOMHHeC1clSd7kMLqyECjSUGurGMY0LY6Lr3zw9HMA7rn5YetND/xcr1CGn69l4ZZoUahFkoVMSiJJTS5JYd9Lr04Dh4YBwV+lfXrNuhOgX3c8jA0UvBRlnBfIWVKat7rfhLGBHmCg/sVSupdUlXT16lWxT1V65KVIEqhMxu9pSu9P8lXIbpod+s9PCYkkor9dFVwMfoQaeWogh0UOpYy3mi+9JIybk4Oy1xOe8w6OhIlJxquTlAHPm3Tz3hqpeJyvdJPnmJgYsQhKg6TSpUuLjdqkG0/nMgotwnh5eeHYsWNiEUa20QBMVt1A++vXr1fg/4ZJDpJFInkkwsLCAuPHj+cbpWIzuG3btuHIkSOKfxHz7ECfQ0D2gtL+p/vAwSHx58lc7QcmZG3LOaBlmdyi/dEvFDOOPJWfe+v3Ft2PdseRt0cw7tI4RMVopiEXwygTGnT+999/cHFxkS/gUNm04PF+4NwsqU3Gfd22A/bFlP4LCYsKQ4ShZPBOwYWoYGf4v+8D74BYsQW59UVUcCEYWryBfp5N8A5RXkkxwzC6jbLmCoxiIO8FGeR5x8EF5dOmTRsRyCFIEjUjUsA6y7uLQALvhSS4XQPeXYK2YmyojyXdysPYQFqmWXTqJZ57Zk7i4vvgwnv/9+jg0gGu3q5QGpGhwH/jgR2d44MLVIE78CTQ4A9A0cEFGbLqFZKG+ngPmgAlYZLigOx3QYmZHFxQTnLUtGvT0HR/U1x0v4iE5s6Vqo+BSzsXrG26Vhg3KwMKIHgFhie7eQdFJFoyCQrnNQ9GN1FqgIGCAI0aNcJPP/0kFk+oqoA2alPpcuPGjREWljHVMVrIprLR77dVq1aJ8yQZQ/uy7A9GeSxZskSu7UWmw/b2ypXtYCSoMmft2rXy20HSXjIPDIVilQvoexiwiav2CQ9M1yCeBlKz2peBnaUUpT/++DM++UlZ2jnMcsCQFk0BfAn+Ap9QH8X3n2HiFvE1icDAQLFQQ1rWFCjs3Lmz/Bzps4qslg/XgUND4x/UZjngrJoqgSLZikA/tLRoR4fmQ6j7ACGFJCfWGKHu/eRBhhgzqUqJYRhGU+YKTOa5d+8eDh06JNrFixdH9+7d+baqCPJkoip9goJt9DeR5aGxHCU3/Yg0JEBpMsVyW2FsU0k+JyI6BjtuuCnsualyfOiZoXjr/xYDTw7EY6/HUDifHwFr6wO34uepKNcT+OUK4FhVueN85wTyWO8vacQ4v0SJEvj6VQqykAIBVTAwiofe2wdeHUBkTCQ2P1wNvDknnchTHnr5KqOgbVzCJMMw2hlgmDVrFi5evCgyManawN3dXWze3t4YN26c0F2dPXt2hks9aEHm+61FixbifKFChcQ+a9spFzJ4owEwYWlpKX6vjOogTVYy1CZIq3XMmDHKeSFbR6mSITntzjQM4rNbGGNepzKoWiA7jo+qCwdbSW3TxsQGyxssR9P8TbGj1Q7kssilnP4zWRLZ4J4k28gwlH7SPh1Xd7+o2o70VykzkZBpslLgsFq1aoDPG2B3T2HuLKg7HqggyRMpmuiYaBx8dVAMyBNi5NsXoZ86IeTDkMTBhe+CDKGfusAgRDkTRoZhdBtlzhUYxVYvTJs2jbNuVQjpgpNUkowhQ4bI5WizLD+qXtCRKgbipzoFUaeIHaa0Lom/2irOv87M0AxFs0nBi5I5SqJYdgVWxVLF2bUVwPpGgFecmS3J33bZDHRYDZhaK32cP3fXZcQirmJDTe+B5Mb5Mu7cuaP2eYguQHOXryFxlTFxlLMvh4o5KyKneU7Uj9SHNLMiw4NB6ugiw2RJlBpg2LNnD7p27Yr58+cn0o2kBZR58+aJc7t27VJmFxglQ8EF2ZfkqFGjkCNHDr7naqggyZMnj2hv2bJFyIYphQAP4LsFyPQM4huVyIU9P1eHUw7zRMcLZyuMRfUXwdpYvUaTjG6RcHAv8+ahn7RPx9U5uF+wYIHICk0OWjz4Z8EMYEcXINRXOli6M9DgT6X0xS3ADf1O9MPUa1Ox4XF8KTGhBwNE+VdJPrggI9YYUf6VlNI3hmF0H54raC53796Vy2+WKlUKXbp0UXeXshxUid+rVy/5GEYun5hVub0hHddqt0wyGTtvHVgVg2o7Qz+DJs8pBRgW11+MkRVGYlmDZTA2MIbLaxeERknV5clB5+iaVAn4BGxrD5yaHJ8cQ3JFQ68BpTpAVeP8STMX4IV/3LjV/RYQFQ5NGuc/evRInGcyXqmy++Vu9L/SH+OujEtSoT6v7jycaHMIA17dhHC4MLEBSnfi280wKkKpJs8eHh6pZrTXq1dPXnarKAoUKKBxUhjphfqvKY7yqeHj4yOkPGTu5KwPqh4oeJfQDI4ynJ48eZKiublSSpLpHEm3/OB9m9b3dWR0JAIjA4VBE8MoenBPx9u3b48GDRqIyoGoqKgf/kzLNWm9VjYRSg5jA6DBlw2AflzejWN1oN1KpZoVvvB9IX5udN2IHsV7iMoihmEYVaCOuYI60ZYxPkELdzK4ekF9LFu2DGfOnMGXL1+wceNGEeghKeAsSdXBgPvNJH9TMbGxoDV4vRAfIDbOtyVvRWg7yvqsMNA3wOCyg0WbAgeTr07GkTdHMLXGVFFNrierAIgLLow4OwI3PaX73q5wu6RP+OQQcGQUEBZXYUMV742mADVGAPr6Kh/nH3sagOI1TICoMGycOQxvonIrdBz/o2s9PT1T7Tv9Hc+YMUMp90XXob+JCx4X4BnqKbZ7X++hUq74RKfcFrmBh3vik7TKdQeMLdTXYYbJYig1wEALnK9fv07xPJ1T6CKoFkNRePqipC8cWnzKmzcvBg4cKAyTraysoImQQVFQUJC8eoFKeRn1msGR2bPMDI7eSyo3VCtYL81P+dlfMnye3Lok8sZJJsn0E3+78Jswmd3cfDNMDU0z23smC/Kj9/+5c+fEpmmsb2OK6nniggvZnIHuOwEj5f0NOFk7YWTFkTj29hhm1prJwQWGYVRKVpgraOMYn6oXjh8/LtplypRBp06cAaouqDr833//RYcOUhb44MGD4erqChubLJgMQMlM414mOhQZESEke2keavz2tCQvKat2qPITYKKZf2PphQIpB+59xBuvIExoXlxhz9u0QFMRXKAAQqfDnVA8e3EsqrNIHlwYe3msOFctdzVxbSLIl+/478CD7fHH7IoBndYBecpBXeP88++iMbaG1Ha7uANzLqq+iiE16HtAm4LN6oQqrR2tHBPdqz7F++Du17to6tQ0+WTEBObOqDxQRT1lGEbpEklNmjQRGe4nT55Mcu7UqVNigbpZs2ZZ/jehyVIeKWkd5s+fX169QGakZM7HaI4Z3KZNm+QTQ000VHvs4Y9mSy7huKsnJux/iJiY+MdNuzoNd7/cxROfJ1hwm0tImYy8ZWNTrRJQNIaGhjA1NYWFhYWY8NMkN2fOnEK6zNHRURi8FS5cWBhkkswEeQglx9R6xuhTzjhes7bXfsBCcbJzUTFR2PtiL8KjE0+0ehbvie0ttwtjZ4ZhGFWi63MFbRzj03dW69at5ccnTpwo9M0Z9UFVlz169EhT1U+WpngroFRHqe3vDpzVnSzx3//3GGP3PcSqC29w+ZWXQiWTVjRagWwm2RAWHYYHXg8w7/Y80R5zaYw8uEDX0LVy3G8D/9ZJHFyoMhgYckHpwYUfjfMvfYhCVNzcsqGzEMrJMAYGBmKtw9zcXCg2kHKAvb29mHOT5wOtiZD3J/l+lixZEmXLlk1xnC+DgswcXPhxdTVVzrQ62Ao3Pt9IdK5mnprYVmcbZtecDWcb58QP9HSNr3LKXxvIqbhgHMMwaq5gIOM2mjC0bNkSFSpUEAsrBMm33L9/H3Z2dlwelgYpj9GjR2PYsGHiC44WsuhnaltK12T2i0w2Sfq+r+Hh4SKrhoz4NDUTKyuZwbVr106e4UR/a5nOcEqvoVoaqhiK5LJELmtTBIQF4eprH2y9/h79a0kDhIlVJ4rBra2JLXqVVI6pLaPb0GcdDd5Tm3zQ9w/JbtDnpewzMz0/Ze2MLLrQAk5C6QmiVxkj/FVfqlSIitWHIVUu2BWGovgQ8AG/X/odrj6u+BT0CaMrjU5UKp8cEVFxMgMMwzBKQtfnCmkZ4w8dOjTTY/zMBgBSGuMTixcvFjKcPMZXL8uXL8fZs2fx9etXrF+/XkglNW36XUY5A7SYD7y9IEmk3ForBRzyx6WzazG1i9hhzx130R6/7xFOjqkLG7PUF7LTCgUO1jVdh17/9RJJKB7BHph4ZyKe+j0VwYU+pfqIcWR+6/ww0zMCLi8CLs4DYuMqbi3sJTnPos1UNs6nRB76W0iOwAjgoZc+KuWKRe0Cprh/6wz0TSzSPeanz9WMrJ8kN85PCFWwManjF+4npJCILU+2oIZDjcS/f7OcyT/wToLKlsoDVHqbEyZMMkxWRakBBoro3rlzB3/88YcwCZMNWmmASlkYc+bMgZOTE7I6P5LyoPOKkLuhD+MfTVBSm8SQ9ufnz5+TfW763dIkSpsngbpkBrdjxw65GRxNQlRmqHbz3zQFGEyNDLC4a3l0WHVVZJj8feI56hS1RyF7S+Szyoc1TdaIn2z8zGRGNowkBVKCFnRq1aqllhtMshhkxi77TqzjZICN7eJlkCJbLoFhAcX2zVjfGO8C3on2zuc70bdU3xQ9TmiAvPzcK/iHJmPqzjAMo0B0fa6gqjE+kdkxfkq64TzG1wwo2EYVPTK5KqoeJ6kkyqpmEmBpD7SYBxyQPAZweDjwyxXAKEH2vRbSppwDTj39giMPP8EzIAx/HX6Cxd3KK+z5i2UvhsPtD2P0+VF46vtUHCubo6yoXGj+v+ZCwraQpSMO+UUl8sF4Xbg+LJvORS77EgmcG5RLZGSk+NxKjZCc5MFxF/qxUSifPQwoVENt4/yEVKxYUZxnEvyuIkPE+4vm/jKq5q6KEtlLIDImEi2cW6RNUookux7tiQ96lZD8KVXB9Tc++BYSZ27OMFkYpQUYZEaWlpaWYrGTPhS8vKRyPior47Iw1Ut50GvJzIio6kDRsGGR5pnBbdiwAV27ds1chlMyhmqJIEOvqLj3k8xYLQ2UyWeDEQ2LYMmZlwiLjMFvex/if7/UgKGBPkrmKJnx/jJZHvqMu3kz5fesugf3tHBGFV8UlL2wfx0OtQmGsYE0aA6v8RvMqvVX+GvmscyDsZXH4tDrQ8JrIaXgQmBYJEbtfoBzz5PPCmMYhlEUuj5XULVcH91P2iIiFL/IwWN8zaBjx47o1q0b9uzZA3d3d0yYMCHVZIosS5kuwOP9wKuTgM9rSca1yV/Qdma2K4Wbb33wNTAcB+5/RNNSudC8dB6FPX8202wwjkywRhAegIDwALH4SxTwegPIApEkl9RsFiZ5nsKz492Q0zwnznY5m+j5vEO9YWlkqXA/vV9W/AJPn5SNlCtUrQDPBvWAC3elA1RhX6gB1DHOp7k4+SM6ODhg0KBBGu29o2pIuvXfh/9i94vdKJqtKDY2iw+20/f/qsarkMM0R9rHAo/2AhGSPygq9AEM42RnlQglZa2++AaLTr0AFzAwjBIDDBRZLliwIObOnSs+SGWlbEz6pTzoS4hMlGnSQAtnsglEcltmz6d0DR2jBevUYMMizTSDy3SGUzKGaokI9gZWVgNCvIGXJ4A359M8iBvWoBDOPf+Chx7+eOjuh38vvsHwhkl14COjI7HedT36lOgDS2PLjP0/mCzDvHnzhLQGQZ+vhKYZa9Lrz5g4CrE5XKD37b10sGw3mDSdmunnpmyf3c93o1ORTjA3Mpcf71ykMzoW7piiJBJhbKgPn2BpcYqG85amhqLi6EfksFD+IJ5hGN1C1+cKaR3jk0ySusf4KVUvyOAxvuawYsUKnDt3TgTjSBq1c+fOaNy4sbq7pVnQgmTrJcCq6mKRHNdWAKXaAw4VoM3YmhtjXueyGLDpttifdNAVlfJnh72VSaafmwydR5wdjoeB71AuTAoyPMR7/H5hLP4wzIePPk9RNCKusjV3WaDTesTaFcX7nWvFoVzmuZI851/X/8JF94twsHSAS3sXmBjE95OkmKi6Nr2B5BXnVuBWjlvIPzo/vqz+ggF9BsDFxUU+zu87qC8+VfuEGR/2w9jKCu3I5+b9ZahlnD9jBiZPngwfHx8xPzc25rFyQgz0DHD983X4h/vjtudtPPF+glJ2kkwiYWdml/YbTj6QdzbF7egBlRSfrJX0JWPx6857wlNShomhPqxMDX/4vuZ5E6OrKC3AQIaXVMpJppdM6tCCV2o6fTTx0ATpITIySm2SxIZFmmcGt2vXLpHhRBN3moQoBQs7oPViYG9faf/wCGDYdcDkxwu4Rgb6WNS1PFotv4zwqBgsPfMK9YvlROm88b4RlDXz24XfJONn7ydY1mBZqgukTNbm0aNH+Ouvv+TfQzQJJ+O1NJXWqpLIMGB3T3lwIcaxBvTbrpAmxZmANHLHXxyPZ77P4BHogT+q/ZFYJk8v9b8dE0MDrO5VEUO338Ws9mVEpRHDMIwyyApzBR7jM4qGqntWrVolPBhkiUSPHz9We+KExmGTF2gyAzg6WvIKcBkODD6vkqxmZdKgWE70rOaEnTfd4BscgT8OPMK6vpUzNcaVggsjcNPzFqqFhmHFF6mSbEQue9z0fggDOvbNH2YkMV9rFNBgsriPkdER+KnMT3jv/x6O1o5JnpeOxyJWJIolDC4QC24vwNG3R1HAugD+afRPosXklMbsVJ21fsJ6BDUKgmVJSxRdXBQL+y/EypUrxWPImJr+H3c97wrviKZRH4DAW8DHe5J8ThrmpspAo+YfaoJ+P899n6NEjhKJ7kv/Uv3x55U/RVJUugIK3+NxG/jyWGoXaQpkyw9lQ/2vW9ReBBiMDfQxtU1J9KrmxL9vJkuTOUewH0CGbUePHlXmS+gEtPhLkh2aKOWRHkMiNizSPDM4WSbg2rVrhWyS0ijZDiglVUzA3x04nfYs7MI5LTGxeXHRJj+G3/Y+QFhknGkYLbzGxoiFUoKCDLSAyjApZcP269dP/CQoK5aCCxo3uI+JAVyGAe43xG6UTQFEdd4CGGY+A83CyAIfg6RA8MHXB0V5empERsfg9dfARMccbM1w6NdaHFxgGEbp6Ppcgcf4jDKgqgVZgOHDhw+YOHEi3+jkoCzmAnWk9hdX4OpSnbhPf7YsAafsUoXqmWdfse+uNE/KXHDhJqrFmojggllsrNioTQGHm2amGJE3H0J775eCNnFBGmMDYwwpOwRz6szB0HJDkzx3fcf6qJW3FqrmqZps8CE4MlgsOtsYJ05m2eC6Qfg+/HLmF3GdjNmzZ+PR3Uf4sPQDDD8Z4pPRJ9F3+j/Iggvi/5G7mvCOMHOO8wWkAJObNOZmVM8dzzvofbw3uh7tigdfHyQ619CxIU53Po2JVScil0XSKpgMeUZWVp2JdvcqjhhavxD+N7QmelfPr1nzTYbRtQDD/PnzhSkwLfhQZkVYWJgyX05rken0TZkyRS7nQT9pn45rSkaKtkySmMRmcDJI9zGQykSVRcuFgHkOqX1nI/D2Qpof2r9mAdQoKD3WJygC77yD5ecom2FZw2Uonr04drbaiYK2BRXfd0YnIDPQBw+kgWudOnUwcuRIaCQX5gCu/xPNWLPs+NZyLWCWTSFPTX8vVLVQMWdF7GuzL9VsIK/AcPRafxNd/r0Oj28hic7xAJlhGFWg63MFHuMzyuKff/4RY32CxvtUscl8By32tV0u+QUQF+cDX59r/W2yMDHEoq7l5EWvt95JHgkZ4dT7U9KivE1RrPjwWgQWZMiDDLEmuGmkh1OIn5+lBfL++rfxv5hbZ26Sc0WyFUGpHKWEubSRgVGic2/93opkmasfr8r9G8gwmQIM1lWsUWhSIdQoWwNl7MqIvg8+NVhsiYIL9DsnmV8Z7y6m/+YwCiEoMgiPvB6J9pYnWxKdI1UCG5NMVkuH+AJPDkptGyegSBMoA/KpW3/5rajGSDhfokRJrvhmGBUEGCh7muQqtm3bhvLly4sSaAMDg0SboaHSVJq0CplOn4eHB2JiYsRP2teU4ML3kyQyKiLop6YFQpjEZnBk8ky4ubkJMzilQVJJrRbF77uMkMpR04C+vh4Wdi2H9uUdcHJMXZTIk9gvggage1rvgbONs6J7zegI5Lkwa9Ys0TY3NxeGlPr6Sv2Kyxj3dwCXFkhtA2NEdd6KaJuMlfFSyfmGxxsQGJH476yVcytsar4J+a1Tft57bt/QesVlMSn9FhKJ8fukgT/DMIwqyQpzBR7jM8r626EgQ8JEoqCgOINTJp7sBYGGk6V2TCTg8isQE18pra1UKZAdvzUuiiXdymFB57IZfp52hdthVq2ZWOEbmCi4kCjIEJNdXEPXKgrKWN/dereY330PLTg7WDiIqlwyjw4PDxdBaPKMMXMyg2kBU1z2vozRlUajnH05PPR6KDZqy4MLRL6qgEya6Z3qfRiyIiRt7BbgluhY3Xx1xRy+Su4q6Fiko+Jf9MEOIDrOnLxSP0AJUsrPPgeg7T9XMevYM2y48k7hz88wuoJSR+x9+/blLMgMoMmZo2xYpH3Q5IOymry9vYX5M5VVN2rUSDkvRjJJTw4BTw8B/m7A6WmSP0MayGtrhqXdUzZf09dLulgcFhUmz2xhsi6kyUoTDzKqlJk8Fy5cGBrH24vAkQRVFe1XI9axGuCb/swzKhn/7eJvePXtFdwC3fBXTcl3QvYdQv+Sg7Judtx0w19HniAyWppIFrK3wMz28aZqDMMwqiKrzRU0+f/KY3ztg5KI9u7diwMHDuD9+/f4/fffEwUdmDiqD5UynD/ekbab/wI1ftX62zOiURGFPE87fVvA7WaK583cbqKd/p9QFRR8oC0iOkLM/yjp0tXVVZxzKugkVrBIFim/Vf4kY9yE2eUwMgUcq0omz56PgFA/wMxWZf+PrAT9PhbeXgiXNy6olqcaVjZaKT9Hv8PtLbfD2jhxAqHCZGdJOUG8kCFQMc4TUoHsveOOKYdchV8ksenqeyGHZGrEnpAMo9IAw+bNm5X59Iya0eRJEpPUDE5WyUAZTko1gyOpJBrIhfgAdzZI/gwF4zQw00lMTKyobkguc/vvW3/jtd9rrG+6PklpLZO1mDlzpnhPE/Xr18ewYcOgcXi9APb2AWKkIIgwyCvTmaIjGXo6WxNb+IZKgYnj745jWLlhP9QuJW8TGiAn1OptVioXFnYpBytT/htiGEb18FxBM+Exvvb8nmiMT5Xkvr6+wuyWEoloLMQkgDKa2/0D/FtHqmI4OxMo1kKqbtAxUpo7pQgtyF/4+8fX0TUkOaTC+T95PNy+fRt//y31z9LSEnuH7UX+/PlFljyZA8sqF6Jjo/HI+xE6HO6AQ+0OxVcxkAcHzUtjY4AP14DiLVXW/6yEqYEpHng9QHh0OC55XMIbvzcoZFtIfl4pwQXi3QXA963ULtEGsJT8JxUBzZumurhi7534eVPNQjmwrHsFDi4wTApooH4EwzCKhozgaMIhM4OjDCelYWkvBRlkHB4OhKe/ZPv11yB0WH0N559/TXJu5o2Z2PtyL+59vScCDUzWhSYeZOZMkLSGRkojBXkBO7oAYf7SfrmeQN1xmXpKW1NbTKkxRZQb/6/t/34YXCCPhc7/XpMHF2juSZqh//auxMEFhmEYhtFScuXKlahqYeDAgQgOTp9WfpYgZwmgXpxUbFQocHiktLiuI0THxGLdpbfovvYGIqOlTOs0Qd4Ebtd/fJ3bNeDdJagS8uShCmWSjyYWLlyIAgUKCENnmgvKPBfI5yEqLoHnU9AndDvaTWTUCxL5MKi2/7pKdEy0MG7+PtjZv1R/4f02quIo2Jvbq6YzicydBynsackPsv3Kq/LgAsXVRjYsjG2DqsHeKk52i2GYJCh1FYY031Pb3N3dhWxLolI2hmGUAmU15cghGSlTttP58+eVd6dLd5QqFwg/N+DMtHQ93N03BK2WX8ZDdz9M/N8jfAtOnOU9oPQAWBlZia2eY8aqIxjthyYe/fv3F5qssomHs7OG+XREhgK7ewB+H+IzqdosS1cGGJWIr364Gt/CviU63sipETY03QBHK8dUH3/3wze0WXEFrh8DxL6tuRG2DKyKofULcZYqwzBqhecKDJN5unfvjvbt24v2u3fv8Mcff/BtTY7aY4BcpaU2ZbXf1R21hZlHn2L2f89w670vVp1/k/YHnp+T9mtvr4cqmTp1Kp49eybaTZo0wZAhQ0TgYMTZEYkMnS2NLTGg1ABxnbG+Md75vxPXiCBD3kqAkXn875yR4/LaJT4Qkwx0jq5JyFm3s2jn0g4DTg7Ac9/EhunNnZvjRKcT+KnMT8qrWEhI4GfgxXGpbVcMKFBbIU/73+PPYt703FPyuMtmboRN/avgt6bFYJCe6iCGyYIoNcBAEWZa7Elpo/OUdWFtbS0GRQ8fPlRmdxgGWd0MjoIMKjODa7kIMMsePyBNR9aIY3ZztCqbR7S/BoZjioukuymDjKKWNFiCHa12COMoJmsyffp0PH36VLQbN26Mn3/+GRoFZVwd/AXwuC3t5ygCdNsGGBqn+Sk+BHxA1yNdserBKsy9KVVqpFfGwjGbGYwMpK/70nmtcWR4bdQpoqLMIoZhmFTguQLDZB4aC6xevRrZsmUT+ytWrMDFixf51n4PSaqSVJJenHb6qSmA/0eduE99a5AmvDTWW3HuFR57xFXNpobHXeDTg/h9Y0vAMhdiLXIi2txe/KR9+VZ1MFTFtWvXROIQQWtFGzZsEO/zU+9PJQouyKSQWhZsiTm15wh5JDpH19C1YsxNfmfEF1cg2Edl/wdNhgIHk69Ojg/EfIcskEPXJAwykEwxzU2ILU+2JHqMkb4RTGSm2ipA/8F2IDbOsL3yQIXId7l+9MewHfcQFC5VxFR0ssWxkXVQv5jipJcYRpfRV3bUuWLFiuLLoHnz5hg1apTYmjVrJo5VqlQJv/32m9CJPHbsGGrXro379+8rs0sMk6UhH4aOHTuqJsOJpJJaJZBKcvk1XVJJ09qUQh4bycD56KPPOPzwU6LzZCBFgQYma3Ljxg0sWLBAtMlPRDbx0CjOzZAMzwlzO6DXPsBMmvynlRymORAcJUkdXPS4iM9Bn9PdjZzWpljduyK6V3HE/l9qigAewzCMJsBzBYZRDLlz5xaBhYSJRCyVlAwOFYCaI6R2RCBwdIxOSCUVtLfEHy1KiHZUTCzG7H0gNORTxOcNsLMrEB0u7Vf7BfjDAxj3EpGjnsCr7xXxk/blW0K5ISUSEhIiKpRlKhdLliyBo6NUrduucDvMqjUrUXBBRptCbeBo7SjO0TV0rcC5TvxFXMUgaFqgqTwQ832QIWGVCPlb0LUyGudvDCcrJzQr0Ay9SvSC2oiJgsGDbVKb3gfluivkaUvntUHv6k6iPai2M3YPqQEH28TvM4Zh1BRgKFmyJN6/fy8qEyiAsHjxYrH9999/IpDw9u1bVKtWDUeOHMHdu3fFY2bMmKHMLjFMlkZmBpc9u1RZQJqtSs1wKtVRMlySSyVNT/NDbcyMsKBzOfk+mdN+CQhL9TH/vf0PIZEhGe8voxWEhoaKiYdMk5UmHk5O0mBQY7i7BbiyRGpTNk+PXUD29AfEqOx7eo3pqJGnBg62O4g8llJlz4/8Sz74JNZfrpQ/O/7uVJZNyRiG0Sh4rsAwiqNnz55o27ataL958wZ//vkn397kqP87kD3OgPbVSeDxfp24T32q50ftwnbyseDCky+SvzDYG9jRGQjxlvZprtZsjkoNnFNj8uTJePXqlWi3aNECAwZI8kcyKHDwfXAhIXSOriFfhiV3l+BLnrLxJznAIL9HFIj5PshA29DTQ8Uxws7ULtG9NtQ3FN5vC+stRGm7OLkxNWDy4Tz0SCKJKNMJMLNV2HNPaV1SSMnST2NDDfP1YxgNR6l/MXPmzMGvv/6KUqVKJTlXpkwZDBs2DLNmzRL7ZcuWxeDBg3H5MmvjMYzOmMHRQLXV4gRSSeuAd2n/G69dxA79axYQbf/QSEzY/yhZzxYq15xxfQYmXp6IKVensK+LjjNlyhS8eCFNmqg6jt7DGsWb81JGnIwO/wKOVX/4sLCoMCy/txxfQxIbm9fKWwtrmqyBg6XDD5/jhKunMCX7edtdhEakkrnGMAyjAfBcgWEUm0j077//wtZWWmxbvnw5z62Tw8hMkkqScXwCEOSl9W9FfX09zO9cFlamhmJ/w9V3uPH2O0mgiGCpcsH3rbTvWB3ouA7Qj5ONUjO0FrR06VLRtrGxwbp16zJUoUwJZ6POj8JG140Y+mQ1AkziPAHSMQ/NakGGwacGi+3u17swNZBUBM57nId7oHuix5kaSufUifmT3Zk2d46KjhFBuOVnpWCWDBNDA9QrylKyDKNxAQZaALK3t09VE162SESUKFECgYGSmQrDMKoxg6NKokmTJinvxSxzAi0lKZuMSCVNbF4cBe0sRPviSy/svOWW5Jpv4d9wzu2caJ/+cBoPvdjPRVe5evWqqITL7MRDaXx9BuztG68J2miaZHr+A9wC3dDlSBese7wOM2/MTBIk+9H/MTomFvNPPMcv2+8K3VAyJttwJW7yyDAMo6HwXIFhFEuePHlEYIGgsQQlYZDkDPMd+WsCVeI8BUJ9pSCDDkByLn+1lZI7aSg5bt9DBIZFSiejo4D9A4GPknIE7IpKFbYUcNEAKOGNqhVkY2B6H+fNmzdDzxUTG4MvwV9E+1PwJ3xwjKuK934BBErHmfggA0kh0fyZNmqPrjgaBawLYEr1KchprmH+A75vYeJxJV7yLG/FdD/F18Aw9N5wE/+cf40lZ17i8ivtDzAyjM4HGChT+tChOP3p76AvjoMHD4prZHh5ecmlWxiGUZ0ZHA3gLl1KuwlzuindCSjeWmr7fQDO/pXmh5oZG2BR13LQj1tfnX3sWRL5Fxr4kOlzdtPs+KfRPyifs7xCu89oBt9rsi5btgz58uWDxhD0FdjRFQgPkPYr9AFqJ6hkSAV7M3tExwUl7nrexcegtJsOfguOQP9Nt7Dqwhv5sQG1CuDnenHl/wzDMBoKzxUYRvH07t0brVtL4+7Xr18LyRkmGRpPA2wkbX88OQA8P6YTt6lDhbxoXiq3aHt8C8Wso8+kaMN/44CXJ6SLyLS5137AXHPWXsgbkKS9iDZt2qBPnz4Zfi6SGF3deLVYLN/SfAvKFGwWf5JlkuR4h3rj90u/CzmphLQt3BYu7V3QuWhnlRo3pwWD+1vjd8jcOZ1QVU+r5Vdw462v2Dcx1IdfSFwQjmEYzQ0wkLnU2bNn0apVK5w6dUr4MdB28uRJcezChQviGhnk01C+PC8MMow6zOCUmuEkl0qKM7i9tRZ4H5d5kAYqOGXDrw0Ki3Z2C2Mhl5TkmpwVcLzjcdTNVxcur10SmVV9D52jaxjtgiYeNFEmaOLct29faAwRIcCu7oB/XIWNcz2g9ZI069lSBtHMWjNRL189HGh3APms0hY4cf3oj9YrruDyK0lH19RIH8u6lxcm6UYGrBvKMIxmw3MFhlFOItGaNWvkUkkkOUMVoMx3mFgBbZbF7x/9DQj104nf/+wOpWFnaSz2DQ30EHNpEXB3k3SBsSXQax+QLT80hfPnz8vnpZQAR+/fzFYo25vbY1uLbSiWvRhQIIHR8zslJtVpEW/83qDr4a44534OT3yeoKxdWXklw5jzYxAuMwDXJCLDoP9ol2jGkuwVJTGmkZiYWKw8/xo9192AV6D0fytobwGXX2ujTbkfy9AyDPNjJIE+JUHGUp8+fRJfECdOxEXL46AM1CFDhsgzKsLCwsRiUcWK6S9xYhgm42Zwe/fuxeHDh+VmcGSYqxSscgEtFwL/GxQvlTT0GmAsyR/9iBENi4gF04G1nWFpkvxHl7mRuQgcTL46GUfeHBElnzINyYTBBTKykplXkQkYo/mQGbms5F9REw+FQWbTB4fEl5zbFwe6bgUMjFLUhV39cDV6FO8BO2PJjI+olKuS2NLK/rse+PPgY4RHSWbXTtnNsaZPJZTIE6czyzAMo+HwXIFhlIODg4MILMgqP0l65uHDhzAz0ww5HI2hcCOgfC/gwQ4gyBM49SfQbiW0nRyWJljYRZIFqh96Fjg0Uzqhbwh03QLkiZMM0gBIIjuhn9rKlSuF1JcikM8VcpcBTG0QG+aPJ+6XoD57Ys3BxtgGgZGSPLmZgRnm1J6DnBY55fNk+klz6dQMtVXO00PQI0kzmn6V6QaDNK4j+IVE4Le9D3HuebzPHQUV5nYsk+K6AsMw6Uep6Y36+vpChsXV1RVz584VAQXayNCNjpEJlexD39TUFD///DOqVKmizC4xDJOKGRxJzly5kvbKgkxJJX17D5xJu1SSsaE+RjYq8sNBQNMCTeVmVV2PdMXQM0PlZZ8Jgwt0DV3LaD5BQUFiYiyDMpxo4qwxnJkGPDsitS3sgZ57ATPpb+p73ALc0OlwJ2x+shnTrk3LsCH50jMvha6uLLjQoJg9jgyvzcEFhmG0Cp4rMIzyoOS9li1bivarV68wZcoUvt3J0Wy2JBlE3N8OvDmvE/epfrGcqG/oChweHn+wzXKgcGNoEhMmTBAqF0THjh2FV6DC0TdAjFMtzMueDT0so3HUNYHMThaE5sS/X/4dYdFhsDOzw/FOx5HfJn8S42eaN6emCqBy7myUN6Mr9k/TQx64+wlJJFlwwchADzPalcLy7uU5uMAwCkYl4bqSJUuKjWEYzTWDo0mIzAzuwYMHMDc3V55U0oerQOg34NYaoGRboEDtDD1daEQ0DPT1RPBBhmxg1MGlA94HvBfbkvtL0MupFyZdmoTbX26LQZPGZWQwKTJx4kS8e/dOtMmcnCpvNGqge02qrIChKdBjT6ol57ktcsu1TJ/6PIVHkAcskLbsm4Q0KJYTq86/QUR0DEY1KiI2fZlRCcMwjJbBcwWGUU4i0dq1a1GqVCn4+/tj8eLFYgG3Zs2afLsTQhKurRYBe3pL+0dGAkOvAyaW2n2fPj8C9vQFZPr6DSbDv3hX2EBzOH36tEh2I+zs7ERyqrIqlG/mKogdka6iPf3eElQv1FIsrmcVvoV9E35v9H8+9f6UPOHu+zmxbC4tS8qjazWi4t/TFXCXFAgi8lSVTMrTwMknnvjoJwVJ8tqaYVWviijnmHwiGMMwmYMFmhmGSWQGp/QMJ5JKarEgft9lOBCR2LQ5Ldx3+4ZWyy9j2dmXSc7RwGh+nfnQ15M+4i54XMDEOxM5uKCFkI/PqlWrRDtHjhyJKt/UzuszwLFxcTt6QMe1QL7UJY6MDYwxq/YsNHJqhEPtDsHRKs5cMJ3QwJjKejf0q4wxTYpycIFhGIZhmCTkzZtXLn8qSyQKDdWgjGRNoUQboGTcIqqfG3AuTlJIW6H/w47OQIQkgRNdoS/mhbRG/QXn4ekfBk0gICAgkR8njfdz5syptNerUbonhn3zg2lMDBaaFc1SwYXnvs/R/Wh3jD4/GhHRESJgMKvWrBQT7mRBBrpGI4ILxJ0N8mZIqR5pftjYJkVRtUB2NCqeE8dG1ubgAsMoEQ4wMAyTxAyOJiLXrl1T3p0p0xko1kpqf3sHnJ2RrocHhkWi78ZbeOsdjNUX3uCe27ck15TNWRZ/1/4bzjbO8AzxxFO/p8K8igZLs2/MxtpHa/Hg6wNF/Y8YJU08Emqy0sQjV664EnZ18+UJsLc/EBst7TeZET8xjSM4Mhhzbs7Be3+p7FtGabvSWNpgqTCfSwu0ILD3jjuCwuMy0OLoVCkfGpXQkPvBMAzDMIxGQj4MzZs3F+0XL15g2rRp6u6SZkJecVTNQNxcA7jdgFYS4gts7wwEfZH2izTDOqvhWH3xLb6FRGL8/ocZluhUJGPHjoW7u7tod+3aFV26dFHuC9qXwC8RRvjfR0/U93hCA2xkBeh3/de1v/Ap+JMwcF7zaI04ToGD1Kr56ZzGBBfCA4FHe0Uz1sIeYc4py3x5ByU2pzY00Mf6/pWxrm9l2JpLxucMwygHDjAwDJPIDI6QmcEpLcOJMtBbLwZM48oTb/4LvL+a5odbmRphUssSoh0TC4zd+xAhEYkXX4n6TvVhbZzY8NYrxAsub1yw4v4KbHmyJcljPIM9NWLQzQDjx4+Hm5ubuBU06aDJh0YQ6Ans6CrPCkOlAUDNEYkucQ9wR0eXjtj1fBemXpuK6Ji4QEQ6off16D0PMGH/I4zfpxkTQoZhGIZhtE8qydpaGhMvWrQIN25o6eK5MrHMCTT/O24nVqqyjtSMbP80Q/3d3QvwfiHtO1QEumxC/zqFUchekuS8/Mob229K42t1ceLECaxfv160qWqBjJ2Vjr4+9ArUhlNUFODvLvkBxpHRcbq2/P3PqzsPVsZWqJW3FvqV6getg4ILEUGiGVOuF2CQfKBg/10P1Jl3XsgiJcTa1IirvRlGBXCAgWGYZM3gXr58ialTpyrv7ljlBlrMj993+RWICEnzw7tXcUT9YlIG+DvvYPx9/Hmi8zJDZ8rUoMqFkrYl8cj7EX678Jv8mnL25RI9hsyg2x5qizp76mDerXkZ/78xmebUqVNiMkzY29urZuKRFkjOa2c3IMBD2i/USMp4+062KbdlbtiYSCq3VMHgFpj+idwHn2B0XHUNLg8+if1TT7/gkYe/Iv4XDMMwDMNkIRwdHYUHAxETEyMSicLCtGzxXBWU7QYUbiK1fV4BF7VoPhATAxwcArjFVaFnKwD03AsYW8DUyABLupUX3nXEnGPPxPxJHfj5+eGnn36S75P8KfkvqATnuvHt95fFj93Pd6PfiX4IiUz7PFTbcLJ2wvaW27Gy4cokyXcaDyVXyc2d9RBdvk+SS8IiozFx/yOM2/cQoZHR4qfMd4FhGNXBAQaGYZJkONnYSAujNBG5fv268u5Q2a5AsZYZkkqivs7vVBa25kZif+v1D7j8yitRcEFmXrWqwSrMqzwPVXJVwYtvL1AxZ0UsrrcYjfMnLq989e2VeKx/uD8iYyKTvCZVPRx8dRAfAj5k7v/N/HDikVCTlQzfKMigdii76X+Dgc9x0lo5SwFdNgMGhkkuNdI3wsxaM9HCuQUOtjsopLrSw/nnX9FmxRU895SqJOwsjbF9UDXWDWUYhmEYJkOQ7GTTpk1F+/nz55g+fTrfye+hhJE2SwFjK2n/6jLgk5ZIqp76E3jqIrXNcwC9DwCW8ePnsvlsMbxBYdGmRdixex8gmkrBVczo0aPx8eNH0e7Zsyc6dOiguhcvkCDA8O4ydjzbgdk3Z4uEtHEXx+lEJcMbvzf4/fLvwmshIQVtCsJA3wBah/st4Itkzo0iTQFbp0SnKVDWYdU17LkjyW0R/WoUQG5rU1X3lGGyPAoPMPz3339Z/qYyjK6YwckynJQrlbQEMLWJl0r6kHbvh5zWppjVvrR8f/y+R/gSGJAouCAzrzI1MMWSukvEsXtf72HPiz3IYZYjyaJw20Jtkd86f5LqBgo6kG8Dyd3MvTU3SV/CoxPrPaYFl9cuIqCREnSOrslq/Pbbb/DwkCoEevTogU6dOkEjODUFeHFMalvmAnruAUytERgRiBnXZ+Dlt8SG48WyF8P8uvOTvM9SIyYmFsvOvMLALbcRECbJfpV3tMWREbVRo1Dan4dhGEZT4bkCw6gHSs5Zt24drKykxfMFCxbg1q1b/Ov4Hpt8QJO/pDZ5bR0eDkQnTTzSKK6vBG6sktqkq0+VCzkKJblseMPCKJNXmnfdc/PDmktvVNrNI0eOYMsWSaI2d+7cWLFihUpfH3ZFpDE88f4y6uerJzd7rp6nunYuwCfg2qdr6HmsJ469PSYCJzohrZrA3BlV4hPQiOOPP4uErGefA8Q+JR5uGlAF45oVk1frMAyjxQGG1q1bY/DgwQgKkjTSGIbRfjM4pWY4JZJKik23VFLrsg5oU85BtD0DwjDqyJYkwQUZ1KZjdI6uOfX+VKLnKpytMGbXno2jHY6idcHWic499n4sb38ffIiJjUHjfY3RwaUDVj2IG9z/AAocTL46WQRDkgsyyKow6JqsFGQ4duwYNm3aJNpk6KzyiUdK3FoH3IiTaTIyl4ILto7wCPQQv/d9L/dh8pXJyVa+pBX/0EgM3noHS868lPvO9azmhD0/V0cem5RN2BiGYbQJniswjPpwcnISHgwESyWlAvlr5a8ttT0fS5UMmorrAeDkJKmtpw903gjkq5zspUYG+ljctRyMDaVloCWnX+LpJ2lxVtn4+vpiyJAh8n2qms+ePTtUCiW3FagjtQM/I294KP5t/C8W1FuAvqX6QtvJZ5lPHiShOUpGEuA0imAf4MkhqW3jBBSW1Acio2Mw5/gLDN1xD0Hh8QlZx0bWQYNiOdXZY4bJ0ig8wEB6ehs2bEDZsmVx8eJFRT89wzBqMINbuHAhbt68qVy906ItpLbvW+DcrHQ9fGa7UshpZSLaNx4VRNf845IEF74PMsyqNQvtCrdL9R4kpEaeGvhf2/9hao2paOTUKNE5kkzyC/fDa7/X+BgklfwmZO+Lvbj68SoCIuIH8E0LNJUHOr4PMnwv8UTXahSxsdB/vAemLw5JupgK4tu3byJALWPNmjXIkUMDsvZfngKOT4jb0QM6rQccKoi9PBZ54GApBbi+hHwR5s4ZgUrUu625jrPPv4p9mviRBNicDmVgYqjd2VQMwzAJ4bkCw6j/b7BxY2mh7unTp5gxI+0SpVkGfX2g7XLAME5mhbwYvOKMkzWJ91eAgz/H75MvWPE4+dkUKJLLChOaFRPtyOhY/Lb3AcKjlC8NNHLkSHh6Sua7/fr1Q5s2baAWEvowvLskKo6bF5AS63TBa2Fh3YXoXaI3/m3yL0xl719t5cEOQBYkqdQP0DcQCVnD9r/E5uvx/nYDahXA3p9rIK8tJ2QxjE4FGGhR8vjx44iMjESjRo2Exh4bSDGM9pvBkW6r0v6Wv5dKohLfD2n3frA1N8a8zmVFu3huK3Qu1iHZ4IIMOpdacCE5KBukaLai6FK0i/iZEMoOoQCEpZFlkuoGMgybc3MOfjnzC0aeG5kk0FE1d9VEQYbvgwspBUrUyruLMDwyHLbnJ0LvwxWFPe2oUaPw+fNn0e7Tpw/atUvf70gpfH4E7B8AxMZI+83mAMVbJXpfzKg5Q0hrHWp3CAVtC2boZaiM9+d60mMdbEyx/5ca6FrFUTH/B4ZhGA2C5woMo14oiWb9+vWwtLQU+/Pnz8edO3f41/I9JDHU4E+pTXr2LsMlPy5N4eszYHdPqW9EnbFJJGRSYmAtZ1Rzzi7Gn01K5oIeJdAokYMHD2LHjh2i7eDggKVLl0JtOMdVMCQwev6eax+v4ZzbOWg67oHuSbwWauatiYlVJwrpX62GTMtl5s70f6koVZhYmRjCwlhKvrI0McSqXhUxrU0peVUOwzDqQyl/hc2aNcOTJ0/EAtHy5ctRoUIF1ndkGC03g1N6hpN1HqD5vAxLJVE55Jo+leAyvBZK5JEqL1RF8ezFsbbpWlztcRXtC7dPdO6JzxNEk35rMtJK5AvhFeIFa2NrEVAYfGqw2DQ6uEAVCxf+lu8aXJ6vkCoGFxcXbNu2TT7xWLZMA0rRAz4BO7sBEZLkn3+l/pgS/RmPveLlsogCNgWEtFY202yZerkOFfIJTxHyWyAjPoZhGF2F5woMo17y588vKpSJ6Oho4bkWHq7lcirKoPowwKGi1Pa4BdxaC42AxqjbOwNh/tJ+2e5Awylpfri+vh4WdiknElrGNi2m1MVZb29v/PLLL/J9Cm7Z2qpxnJvNGbDOJ7XfXU4yjzny5gh+PfsrJlyagPtf70NTufLxCrod7YZZN2bphtfC97w9D3x7J7VLtAEsc8rfu9ObO6NBUTsxZ2pZJo96+8kwjBxDKAmSViEd7S5duqBv376oUaNGihkUUVGSbhrDMJppBle6dGkEBgZi3rx56NChA6pUqaKcFyzXHXhyEHh1EvB9A5yfDTSbneaHNyuVG82XXoJPcOJMDho4UhWGPpU7J5A+ymFhjBOjE5TJZhJ9PX0YGxgnOlYqRymh7fnQ6yFqOtRMdI4kdd4FSAMnGxMbcY0sEKGRwQXi3UXALb66RN/9higvRsF6GX5KHx8f/PxzfHk3veeyZcvcYn2mCQ8CdnYFAj+J3U+FG6B36CN4+XoLP469bfYm+V2nB++gcGy9/gHD6uRPdLx39cT7DMMwugrPFRhGvZAe/t69e3Hu3Dm4urpi1qxZmDlzJv9aEmJgCLRbCaypC5DP1tkZQNHmQHZn9d2nsABgRxcgwEPaL1gfaLsi0RwnLThmNxfeX8qeNw0fPhxfv0oSoIMGDUKLFnGyuOqC/k8kk/RwJxDiLVWC5CopP/3C9wWiYqMQFR2F827nUSGnJIuqSQRHBmPS5UkIjAjEwdcHRdWCrsg8yZFVLwB4lKcTJK0CCVszQ6zpXQHGxhmfizEMo0UBBoKyIE6fPi10tXPmzInixYsr8+UYhlGiGRxNQmRmcHfv3hVf6N/7FGQaer42y4BV1aSMnOsrpYwFp+ppfgoaJHsFak4GlrmROWrlrSW27/EJ9UFh28LCu8HC0AL+4XFZSJrKd9ULcugYDdQz+H4YMWIEvnz5Iq+aadkyde1YpUPl7/sHSqZ+RK4yyNN5KwpdGguvUG/hpeEW4CZMwTPCfbdvGLr9njAl14uNQY+yXK3AMEzWhOcKDKM+aBxP3omUSBQcHIy5c+eKRKKKFSuKjGiFj/O1FVp8rjsOuDAXiAwBjowC+rpkeNybKaIigD29gS+ucX0rA3TdBhhmbKFV2fOmffv2Yc+ePXL5XZnBuNohmSQKMMhkkhIEGH6r/Bu+hn5FQZuC+LlsAn8LDcLCyAJ/1/0bQ88MRYfCHdDQsSF0CqrQeXFcNN8iH7qdNMDhIoHCP4RhGM1FabVwt27dQvny5YXMRY8ePfDs2TOcP38+2Y1hGO0xgyP5M3t7e5HVki9fPkydOlVUNyhWKkm2iB0LHBoGRMYbIOsSpexKYWernaiUqxI+BX8SlQu0USXD98bPmli9IMftmuSbkQFd2v/973/YtWuXaNP7Seb7oVZO/CFV0RBWeYCee6Bnao2/av6FzkU742C7gxkOLuy86YZua26I4AJx9LEnwqLi/B0YhmGyEDxXYBj1U6BAASxYsEAulUTZ5Xnz5lXeOF9bqf0bkLNU/Hj4viTrqfJEn8PDpdcnbByBXvsAU9VKw6YVqloYNmyYfJ+CWTY2cX576qZAAh8GqsT+riL97zp/45dyv2h0kI0q4/e23ovpNadnqqpaE4m9sxmIkxjeGtkQoZExmH9SA03WGYZRboCB5I4mTZqE2rVrC9kLilpv375dvTp7DMNkChpckRmXKJUF5BONjx8/ilLq+vXrK3byUa4HUKSZ1CappHOzoIvIDJ3vfrkrPBfWNV0ntvL25YUPw9DTQzUnyJBS9YKMk5OARSWA4xMBtxuSMVcaJh4JNVk1YuJx41/43VmH3+1z4LaFjQguwCavOOVg6YBpNaYJOav0EhYZjYn7H2HSwceIiJbuTdOSubBvcFWYsikZwzBZCJ4rMIxmQTKVderUkY/NPn36pNxxvjZCFQLtSIYobvnk5GQg4LNq+0DyTI+kagCY2gC99kuJWRoIVcDQGJ/8FwhqN2nSBBqDrSOQrYDUfn8lybyFggzfQ9XL3xsqq4pbn29hwe0FSbwWimUvBl3DPzAEflfXi3ZIrAkORNdBq7J5sLhrYi9DhmGyQIChUqVK+Pvvv9GqVSuR6dypUydFvwTDMGqAyltJIik57t27J89+UpxU0lJAtpBLUkluN6GLwYXvDZ2f+z7HG7834pq7X+9i+NnhmhFkSKl6ISHBX4Cb/wIbmwFLSwMn/wQ87iRrAk0DZMpqkk08SIJLZiiuNp7/B8/Tf6Jdvjw4ZmmBaY4FEWpfNNNP+9EvFF3XXMeeO+7yt/f4ZsXwb+9KsDRVqlIhwzCMxsFzBYbRLCiBiJQHUkLh43xtJW8loMZwqU2ypsd+S3aMqxRurweuxFX5UrZ6911ATs2Vn969ezcOHjwor5KZP38+NA6SdyXC/IAvcbKoKXDvyz30ONYDk65MQkysaiuP97/cjyGnh2Dr063Y9Vyq+tZVHnn4Yd6KpcgW7SP2j8bWxNi2VfFPjwqwMjVSd/cYhlF1gMHNzQ1btmwRXygko8IwjG6wcWO80VJyrF8vZRooDGsHoPncuJ1YwEW3pJJOvT+VJLhAkN6nmZHUNjMwwy3PW+JatUKTp/NzfnydnkF8O+AjcP0fYH0jYFlZ4PRU4NN9+USMTAVJHonInz8/Fi5cCLVCffvfIOSKjkLZMEmLNsLAEB6BcQZ6GeTqa2+0WXEFjzwkfw1bcyNsGVAVvzYoDH19zS27ZhiGURY8V2AYzePAgQOZmgdkGer/AWQvKLVf/Ae4SmNZpfL8GPDf+Pj9jmuBAkm93TSFz58/49dff0303rGy0kDt/AIJDKvfXU7xMqpaGH9pvPBgO/n+JPa92AdVktcyL2JpLgzgme+zJFUMugD9n7Zdf4/Oq6+jeeh/8uNl249Bv5oFNFqqimGYeBSeOunq6ip0GxmG0a0vfSqT/tFgsmzZsmjYsCEaNGiAunXrIlu2bJl74fI9gScHgdenAZ/XwPnZQFPFySWpc4DWrnA78bNpgaby4AJB8jtzas/BObdzGFpuKC56XJRfq9bqBfc0VJCQVmbDqYDPK2kyFB4gHfdzA64uk7bsBRGUvylWTl2XSBpJrRMPfw9gZ3dh3EfD16lOreFgnxvDKwyHlXHG+/XOOxh9N95CdIz0PivlYC2qFhyzmyuw8wzDMNoFzxUYRvvG+XS+Z8+e8nF+wYIFs+ain7E50PYfYHNLaf/4BKBgfcDCTjmv534b2D8IkGXNN5sDlOoAdRASHpWm9xJJbn379k3sDx8+XLxfNBIyepZBRs8146pTvoP8DRbVW4TBpwajoVNDdCzSUXV9BFDDoQbGVx4vKif6lOyjk393W669x/QjT1FA7zPqGknVJFG5y6N4xXrq7hrDMOoMMCQXXHjz5g1cXFzw9u1bsU8Dknbt2qFQoUKKfnmGYZQADWTob/tHk4/Hjx+Ljczd6TFUbk2DStpI2zXd+vpCKmkZsKqGVIpMUkkl2gKOVTP3H5I/feIB2t7b7rC3NkHVAtlhYaJ86ZqUAgfV8lQTW2rXqJQzf6X92s8PgG7bgMgw4M1ZKUD04jgQESSd930LS99/cakH8NzbAm/NyqNRGcUGpV1euyQJ3CSEJKeoKqR23tqYc30GOry6jtpBntLJoi1g33Ix/tBPUI2RQZztLDCotjPWXnqLjhXzYk6HMjA1yvzzMgzDaDM8V2AY7Rzn79q1S2yEo6Oj8GaQjfNJBifLQNUDlQcBdzYAIT6S/1jnDYp/He/XwM6ugEwqtfqvQI34ygBVY/Bd5e1bryAcuv8R1QvlQEWnbGKMS96bR44cka/5kHS2xmKVG8hRREqMen8ViI4CDJKf/5XPWR47W+1EIdtCyfozKJIPAR/gZOWUaJ7au2Rv6DIdK+XD5mvv0cv/nPyYYdWf1NonhmHSj9JX0KZMmSK+WKKjJRd4GRMmTBBm0DNmzFB2FxiGUQADBw4URm8p4ezsDE9PT4SGhsozWO7fvy+2xYsXC31X0l2mSQhNSMgIPk1Z62Sw23wO4PKrlL1zaBjwy2UgTkZIUURFx2Dm0acIDI+CkYEeyjvaomYhO9QqbCfaxmo24qX7qZaMlc+PAM8EuqSmtoChiehPTGws9PX0Ever6mDpp5EpULyVtJG01atTItgQ9fQoDGMjxSXF7QxQHI+BVdUA+xJA6Y5AqY6AXeFMBRcmX52MI2+OJJKeSs77wtzQHCFRIXhoGIVDenqwzFUG6LQeUEBwQcaEZsVQ0ckWzUrl1smMI4ZhmMzCcwWG0fxxvqWlJYKCguIT693dsW3bNrERFGCQjfHpJwUgdJrG04GXJ4EAD8B1P1CmM1CsheKeP+grsKMTEOor7Zdsr9Aq7oxgZJB4LnThhReWn3stNponlcpljuuHzsEkXylEeL7E5s2bYWFhAY2GfBgowBARCHx+COSrlOKlRbIVUfr87H8v/4dZN2dhXOVx6FWiF7IK1qZGWN2tFApvvwpExJmYl2YvV4bRNpS6YkZ6e7Nnz0a1atVw6NAhvHr1SmzUrlGjhjhHXzwMw2g+48ePR8WKFZM9R8cfPnwIPz8/XL58WQQOaXJhYmIiv4YMom/fvi1Mvlq2bCnkk+hzgAKNp0+fRnBwcMovXr4XULix1KZBYFr8ANLJ44/+IrhAREbH4vb7b1h29pUw5y0/4xT6bbyFtZfewPWjv8qlldwD3THg5AC4eruq9HUR4gvs6Q3ESAEB1BkH/P4BGPcSkaOewKvvFfGT9uWbzDAtIRQMKtkOn2rNQYGV0ei2PwQHnkUiRj+BWZfXM0kC659KwOrawOVFotohvVDlAvlaUACBAgkJDbITG2tXRW09S/kX4SdbB6DnXsBEOpYRTrh6YuX514mOGRroo3npPBxcYBiGSQaeKzCMdozzqbrh+fPnWL16Nbp27YqcOXMmuub9+/fYtGkT+vXrBycnJxQuXBiDBw/Gzp078enTJ+gcptZSlbWMo2OAUD/FPHd4kFS58O29tJ+/FtBhDblxQ5187x12461kxEtERMXg/scgmFbpjNy95sH5t/3494UR/jn3Cq+/xgemNFsm6VK6Huoe4I5uR7vhqc9ThXTlnf87zLwxE1ExUVhwewFe+L6ALhIWGY0ph1zxOM6fTkaJb+dgFBH3N1SupyRHxjCMVqHUb6mVK1eK4MKFCxfQtm1bIYlEG7XPnz+PqlWrYsWKFcrsAsMwCoKqDehvmTINZfIG9JP26TidNzY2FpUJdOzcuXMi4EDnpk2bJjwZ6LwMqmq6ceMG5s6di6ZNm4qAQ8LHyioh4qWSlgMm1tI+mQeTJqkCKZHHGjt/qoZfGxQSFQsJx9AhEdG4+NILc/57jiFb70CVvPV7i86HO+Pul7v44/IfCIkMUc0Lx8QAB4YAfh+k/UKNgAaTMvx0FJQZMmQIPnr5Ye+TKFzKMwT6E98BHdcJWSIYxL838OUxcHYGsLwCsKae5N1APg5pgCoWqHLh+yBD4uBCNaywKI3Jr++hv18ADn4NQNFuewDrPBn6v5HHwvwTz/HL9rtYcPIFTj2Jk1tiGIZhUoXnCgyjHeN8a2trFCtWDL/88gv27NkjqpafPHmCf/75B506dUKOHDmSSCSvX78evXr1Es+T8LFfvnyBTlCkMVCuh9QO/Aycnpr55ySZnv0DgE/3pX27YkD3HVJlsIaxqGs5bOpfBUPqFkQek0jExsQrVkTrGeDqax8sPPUSt97FVWEkWGCmynGNoECCAMO7S+lK/up9vLcwXR52Zhg8Aj0y3RVnG2eMrTwWetDDr+V/RdFsRaFrfPAJRsdV17DtxgcM23kX/iFxSWzE7QQyY5UHqKV/DMNosETSs2fPxOKhoWHSl6Fj3bt3xx9//KHMLjAMo+DJB1Un0JaWklBTU1PUq1dPbNOnTxdBg+vXr4sAI203b95EVFRc1UBkJK5evSq2WbNmiWBE9erV5dqu1DYhY7PDwyWpJJdhwM+Xkwy4c1gkWKiWQXI+MTFCpkkEK5K5lnRDaxa2E9v4ZkBAWCRuvvXF1dfeuPbGGy+/SNk3dD7h/5vuQ/tV11AkpyVqFc4hZJVyWf94EtB86SX4BFMNaOrEIhbIVQAweioWz/3D/WFupIKMjot/S+bahK1TpqWDtmzZgmPHjok2ZbXNmTMHMDEHynaVNsr6evEf4HoAeHseiImK93SgjSZteStLMkpUJk7SWT8IMsgCCgNODBATgYCIACm4kLcFzPYPghliMdYvQKpcyF0mQ/+vb8ERGLn7Pi6/8pYfe+jhh6b/b+8+wKMo2jiA/9M7oYQWeu+9I02aiggCKlUQEVEB6QgfKFJsNClKUYoiXVFAOtI7hN5bKKHXQEJ6st8zs7lLAgnJJXu527v/73lO9vr6Zu5udt+ZecvlSdfrERHZEx4rEOmzny/uK1u2rLz07t1b9rNFwsHQx9+xY4ex0K9w4cIFeZk9e7a8XqZMGWMfXyyr5OdnpiLJ5iaOTS79Bzy7Dxz5XV3WpWg6C9OKGdJrB6jLigreeYAuKwCPbDCX9B43CT7uLni1dC4U84zADx27ISQyFh4FK6Dr4LG4Gu6Gs7efysfVLpo9yfNWHbuJsWvOokbhbKhTLAfqFPVDWf8sL9R4yMjxk2F/N/RPZmZ1YqI4d65ywL3TwPX9QEwU4JxMTJ6T1ysvKvpVxPYb21HApwC8XdI/AzqxLmW6oFruaiiboyxszYZTtzHkzxPGFQNCImIQ+CAUVQpmU5fjvXEwIemTs5Rld5aIrC/BIE4QJl6r8XkhISFJRjQTkX6kZ71JDw8PNG7cWF4EsSySSCiIkVHiYEQsoWSo1xIVFYWdO3fKy+jRo2Wyom7dOphdvzCK4yrw4AKw/VugWdI6Lsl1JMVrPXz4UI6uSut3jlgLslnZ3PIi3AuJwL7LD5E/W9KT+2La7/GgYHn567A6eqW4SDYUyyGTEbWL5ICvZ6KlgOKJzvH9kMg07Yuf43v45I07+LjCx3BxevG1NHd+A7DjB3Xb2R147w/AM+nBgSlu3LiBfv36GduNWBrP0/O5JIlHVqByJ/UilmY6t0YtEB24A1DiR0TdDFAvG/8HFKgdn2xorRZpSyHJ0G19N5x+eFr9X3Fwxrhi7eGx9H2ZupFaTABKNEvX/5dYLkvMWrjxWJ1t4+7iiO/aVkCbKvnT9XpERPaGxwpEttHPFyejK1SoIC+ff/65PEEtlk819PFFf/7JkydJkoviMmPGDHldPM+QbBADk7JnT3u/M7OXLk1C9I9bTAT+7KZeX90X+Gwf4JqO2gM7JwBHFqjbrj5A5z+BrOatZZHScdOjR4/k3yC14yYR+48++ghPn6rJhN5v18f4j5saB+EcvvYYRfySxkIcT4VGxmDb+fvyIvi4O6NWkeyoXTSHTDqUyZPlhSWZTD1+MmmZJJFgELPEbx0BCtZO9SnOjs4Y33A8fj3xKz6u+DHcxfGSiUS9uNDoUHQs3TFp4s7GkgvRsXH4fv05zN19xXibWC3g585VkS9rfK28gHkJT6j+oQX2koisPsFQo0YNOUpB/Ojkzq2epDO4d+8efvnlF7mEEhHZJ1H4SyyPJC6GpOPu3buNByOHDx+WByhCREQEtm7dhlcDHHD6M29kcXNA7O6pWHjwMUo27oTq1avDxSXpyXfxehMmTMDcuXPl+q/+/v7o0aOHXGc2TQWmE8nl447WlV8cNX8zOBzZvVzxKNFoGpF0EJff912TSy2Vz+cri/z2fjV9xYsd4nzRu3ImFbp6eFldGsngzcmAf+V0v9zzBx4DBw7EK6+8kvrBWtWu6uXZA+DsajXZcHW3OntFCNqvXtZ/ARSuB5R7GyjTGvDOmeSlnBMtKeUIBfdW90YeQ12GOn2AGh+l6/9LJJNG/HMSkTHq/hTI7oHZXarLEVhERJQ2PFYgsk0i4VClShV5GTBggBxAdPToUdm/F/18kXBIPBDx5MmT8jJt2jR5krVSpUrGGQ7169dH1qxZzdbHzzDRBz31FnD2X3Vp0a3jgNe/M+01ji5Ua5EJjs5A+wVA3oqwdr/++quspSeULl1azn4xyObliqbxA7USK5TDSw7GSlybQYxm/+/sPXkRsnq6YHy7ipkzI1iMmD8wS92+sitNCQbDYKbPq36errecfHgy5p+aDycHJ7k0Uu28aXtPvbn9JBx9Fh+ViSaDD+oWxv9alJGFwaXIEODEcnXbKxdQuqWF9paIrC7BIIo+iaSCWE9drNnYpEkTOQVS/OCLKZSCmD4pikCJjsGiRYu03gUi0ilxQPDGG2/IiyBGOomi0Ybp1seOHcONpwoGbozAnFYecHIAatyaj6r1f4KLh7es4WA4GBHL8DRt2hRHjhwxvr44ABk7dqxcqsdQNyKjGpXKhYARTXHuTohcSmnv5Yc4EPgQz6LUUfdxCnDixhP4+8aP0NBIdGy0HD2TnpkkKYoKA5a9D0Q+SRhBUqVzhl5SHPht3LhRbov1d0X8TSKmLov9EJeQu2qyQSyjdH1f/CwEBbi6S72sG6IWmS7XBuElmqPvvi9xMuQaKkZE4oGTE265ANM8FUwPcYBHqTdfmP2SFqKI3dg1Z+TaoQYNS+bE1A6VkdWTM/KIiFLDYwUi++Pk5CQHA4mLSAKIJVLFQCJDH18MMAoLCzMOThF9fnH58ccfjckKQx+/cuXKeOutt8zexzdJi0nqyemIYGD/TNkXRYGaaXvuxf+A1YlOVLf+GSimzva2ZqKw96BBg+S2+BuJ5VDFjPPUDGhWUl7E7PD9gY/kjAZx7BT44JnxMcFh0fA3jG6Pd/jaI4THH19pqrAY+CSOpxTgyg6g4ZB0v9TSc0sRGhWKHhV6JHuMJmrCbbq6Cbk81CLpsUqsLBJtiwmGnRfuo/+yY8ZBeN5uzvihXUW8WfG5mncnlgFR8cmmqu+naYkqIrKTBMPff/8tOwhidkLLli3l9T59+mDSpElJHlewYEH5IyRGJBARJcfX11d+j4iLINZyFSOetm3bir13l6Ju7giUzemErxu5YfiWUGzYsEFeBDGlV0zxTY44IBGjnhKPsskIMYVXjFwXl4/qF5VTQU/cCJbFzUQNh6PXg2V9hsTiROYhnQKfBGLYzmF4u/jb6FSmkwb/B/Hrvv7bT50iLIh6B69/n6GXvHbtmpyxkPjAQyyTlW4+uYGaPdXL01vAmVVqssGwZqeY3RC4HeFXdqBv7lw44OGGWuERmH5XnX7dN3dOHPBwR9+CRTC91TR4pKOmxPKAoCTJhc8bF0e/piXTtG4sERHxWIGI1HqMYiUDcRk2bJjsswcEBBgTDmIJVTF7WRCzmUUyQlwmTpwoT9ymtCyS1n18k/qoYtbCyk/VE9Wr+gCf7AKc3V7+vFvHgOVdE5YDbfIVUKkDrJ34m4gBpIZZKF988QVq1kxjQiXR7PBWlfzlRbjzRCQcHsqEw+nbT1Amb9JZwSuO3JRLK2lO1LgQs0VuHweCDgLREekqqr3g9AJMCJggt0OiQzCg2oAXkguG+nBjXxmL9qXao1beWmhWKH1LtVqz2DgF360/Z0wulM7jgxmdq6JozudqVYjP8SHD8kgOQLUPMn9nich6EwxixMAHH3yA1q1bo1u3bpg6dSquXLkiOwTiX6Fo0aKoWrWqWjiIiCiNxMwo8d0iLggejLifa8MxOhRDX3HHscgCWLb7kvGxKSUXDObNm2e2gw8XJ0dUK5RdXj5vUkKOtol77kAoKjZ+qR8TiSLPndd2lmt2Bh4OlB3TYlmLZXynD/4CnDRMT80JvLcg9YOilxAHfuLAQ8xUE4YOHartknhZ/IHan6qX4CDgzEqZbAi/fRTv5MuD6y4uxuSCR3zsxXbfPLlwwB3ou+sLWaNBTG82RceaBbHpzF0cvfYYk9tXNtboICKitOGxAhE9TwwMqlu3rryMGDECkZGROHDggHHZ1H379snb0lJzwZx9/Jeq1BE4tUIt+vzgPLBjPNDky5Qf//gqsOhdIDp+5L6YrVtPHZhj7WbNmoWtW7fK7XLlymHUqFEZfs08vu54u0o+eUnO/ssPYdZlkkSCITYSuHFIrctgoqJZi8IBDlCgYNHZRXi/zPvI4qwmSS4FX8Lko5NlcqFWnlp4rfBrcqCYrRIDr37qVAWtpu9Giwp5MaZ1eXi4JjOwK+hAwuC2kq8BWQtm+r4SkXY0P8MvligR6yd+9tlncrSqKNgkOgZijVUxJVpcxNRIJheIKEOyFoDj6+papY4OCpZ2yI67N69j+fLl+OSTT1J9+s2bNzOtKJzoUHm5Jc3nOqdzxLuvmy+6l+8ut0tnLw1XJw2mkV7bpxZOFhycgHfmA77Jd+7TSiyVt2XLFuOBx9dffw2zEQXw6vYFPt6G0a+8L5MLLgrw+aPHxuSCILan37mHWr4lZQdfTFFOT4d5WofKWNXnFSYXiIjSgccKRJQaNzc3NGjQAF999ZVMMAQHB8sT2iNHjrSqPn4SYkmcllMA1/hR2numALdPJP/YsEfAwneAZ2rNAZRqoRaL1nLpUzMJDAyUy1wZlr4S53zE38vcfv+wpiwGbRZiiVWDKzvT9RL18tWTMxM8nT0RGRuJYbuGISw6DL+c/wXt17c3JhfSM8BJDyKiky5fVSyntywiPuHdSsknF14o7tzDzHtIROZmlm9osQTG9OnT0a5dO3z44YeygOvHH3+M2rWTX1uua9eu5tgNIrJ1VbsBp1cCgduA++eQ68xcvPvu13j33Xfx77//ygOMlOTLl0/b+gUmcnZKf363R/keyOGeA62Lt5Z1GDIk5A7wZzcgLn7KcbPR6Rq18/yBx+DBg40HHr/99lumHHhEx0XjaoS6HFI0gAfOzkCU2ELSJMOjUGxqMFbG72XEzJP//XMSjUvnwlvx07cFUWuB9RaIiNKPxwpEZAqxtr+hBoOo5Wi1fXwx6KXp18C6wWrfenUfoMcW4NRf6v1i+aOYCGBJB+Dhxfgdrg60mwukY+lOSyyN1L17d2O9DDHbpFq1apny3gWye8LdxUkWhNZcwTrqICuxVJWo65ZO4tiiccHGGLBtgEwodNnYBddC1KVVRUHnb+p9Y3PJBZHM+2VnIBbsuyYHYPl5uyX5m6Xo2UPg9D/qtm9BoHiTTNhbIjInM6WAVY0aNZLrJ1aqVEmOZhUXw2gCw9qJ4l8mGIgoXcTBQ6vpwIw6QFQIsGcqUOYtIF81mdx8WUFhcb9eOTk6oV3Jdhl/odho4M8PgNC76nVRkK5OnwwfeIjYPnumTvcePny4nLWWGVwcXTDvtXkYtL476l/cjcZh4ck+zuP6frR2jJ+xkYLrD8PQa+FhnL39FBtP30HJ3D4olSeTCwYSEdk4HisQkamsvo8vRmKLGmHX96rL7qwdABz9Q73PJw9waI66NIyQvSjQaRng+pITsVZEDCIV9fAEcY5HJBhsgnsWwL8KcDMAuBEARIWl+2/i4+ojZyn03NQTx+8fl7eJpZO+qvMVcnvZ1tKqT8KiMejP4/jvrHos2W/pUSz4sFbaatMdWwjExi9pXP0DXSTYiMiCCQYxnVH8wD948EDOYKhTp445346I7JEYKdR8LLCmv1rkd+VnQK+dcuru2rVrZbG355UtW9Y4tddWRMREyBH8olObZptGAtf3qds5SwOtfsrw1Oyff/4ZO3bskNsVK1bEl1++ZO1ZM/B09sDPD4LhGKIWnUvR9u/V6dDJ/P9uO38P/Zcew5NwdfaDh4sTnkYknQlBREQZx2MFIjLVy/r4/v7+lu/jizqTYgDUrFfU2QpHFybct/ITdfaw4OkHdFkBePlBDy5cuCAHDhmKdIulkUTtDJshZnCLBENcNBC0HyjWWLOXLp61ON4o8gZsyckbT/DZ4sMIeqQO6HJxckDTMrmRplWA4+KAgPnqtqMLUIUrmhDZArMkGMLDw2VBz5kzZ8of+Y0bN6JZs2bmeCsiIqDaB2qR38DtcqkkcfLYp+koWf9lwoQJmDt3Lm7dumWMVJ48eeDtHb8+qg04/+i8XOezqG9RTGw4MW3Twk/8CRyYpW6LpET7hYBbxmJy6dIlfPHFF8YDD7E0krkPPB5HPIabkxs8XeJHGV3ZAcfr+1N/ohhVJtZYLdrQeFNcnIKft13C5P8uwLB0b6UCWTGrS1Xk9bWt6cxERJbEYwUiSi8fH58U+/iiVkNoaKh8jEX5FQcaDQf+E8WPE9WDMCQXRL+183J1BoMOxMbGyqWRxHe3IGpjiBkMNkUUet79o7otjhHSmWAIjwlH3y195eyFin4VERMTgzPBZ+RttlB/QaxCsvDAdYz99wyiYuPkbf6+7vi5c1VUKZgtbS8iljd+fEXdLtsK8M5pxj0mIt0Wed67d6/8sRGjWDt37iwLPjO5QESZslRS4qJqNw/Lg4sxY8bgypUrCAoKkkXnBVEkTox8sqQcXq7I6eP24sXbDX7eSe8Tj01JTFwMBmwfgEvBl7Dp2ib8G/hv6m9+5xSwum/C9TazAL8SGT7w+OCDD4wHHqIIX5UqVWBOogPfe0tvdN/YHQ/CH6g3Hpqb9hcQU9TjiRkKH/8RgEmbE5ILnWoVxPJetZlcICLSEI8ViCijEvfxRYLhf/9Tl74UtQEM2xZXuzfg4pX8fe/Ml0u66sWUKVPkd7dQtWpVDBs2zLqOn5K5vOz4KVkFa6uj6YUruzKUXDAUdJ7x6gz8UP0H1MhdQ94m7hOP0atnkTHov+wYvlx5yphcaFQqJ9Z+Xj/tyYUXijvrd9liIjLzDIYGDRrAz88P//zzD1q3fnkBTSIizWQtGL9U0oD4pZJ6A712AM5uxhH1EydOxGuvvSavDxgwQBagt9TU3g39G2jyOqLI89d1vsZHmz5C9TzVUTNPzZc/ITwYWNYFMHRu6w0EyrTM8H5MmzZN1twRKleunCkHdz8c/AEnH5yU2yP3jMSsprOAmj0T1rVNjXismAFyJwSfLDyMKw/UuhGuTo4Y+3Y5tK9R0Hw7T0Rkp3isQERaEjN3Bw8eLJfsEcWfxQzazz77DDVq1LBsoK/vAaLVvuULXPQziv3cuXPGWgsuLi4yzuJfaz1+EjOSrz0KQxG/FJI7KXH1AvJXV5ePvXUUiAwB3HzSnVwQsxWc4pwQ7hSOHxv8iEG7BhmTDHqcyXD5fih6/XEYl+6py9CKpZAGNiuJzxoVh2Oa1kWK9+QmcH5dwhK9hV4x0x4Tke5nMLRp0wanTp1icoGIMl+17uq6+sL9s8CO8WIeJxxPLoP7+ZVo1LAh2rZta1zOR5wUt3aik3zq5pOXPqZm3pqY+9pczGk+B3m88rzsxYB/eiVMSS3aCGg8MsP7eP78eWNCQRxwLFiwIFMOPHpV7CXXNM3hngNf1o6v9SD+/oMvpO0S31Z+2nbJmFwQU3z//KQOkwtERGbCYwUi0pqXlxd++OEH4/V+/frJpVwsRry3qPeVEnGfJfcvjcTyPt26dUNkZKS8Pnr0aJQvXx7WavfFB3jrp91oN3MvQtJTP00skyQoscC1+Dp1abTp6qYkyYXECQSxLW4T94nHiMfqjZuzI+6HqO3Az9sNCz+qhT6NS5iWXBCO/K4OBjTMXshg/T8isuEZDH/++afWL0lEZMJSST8BM+sCUaHqOpo+eeC8bjCyAojOW0Ku1yqWRxId5bFjx+L9999H7ty5rbZ41perTuHM7afYPKABCuVIeSROjTxpGKW1cwJwYYO67VsAaDcPcHTSZGmkiIgIef3rr782LkVlbnm98+L3N37H3Wd3kc87n7zt9Sk78fBZVJqeL6ZOi5FQ37QpL5M4eX3dMb1jFeTwVme9EBGR9nisQETm0KlTJ7lM8759++RlyZIl8jaLuLJDHQlvQi0wazRp0iQcPHhQbtesWdPyBbRT8d/Zuzh966nc/nVnIAY2L2V6oeed4xP+hiWbp/mprYurq3c0L9w82dkJhiSDSC4YHmsp6Tleyp/NEz+2r4RfdgZiWocqyJXF3fQ3jo0GDv+eUIekUgfTX4OI7GcGAxGRRWUrBDQbkzD6ZHP8yHYATrvGo2iRIhg0aJC8/vTpU1krwFrtC3yAY0HBiIqJw5h/z5j03LDoMFx9cjXhhoubge3fqdtObsB7CwCvHBnaPzEy7Mcff8T+/WpR5erVq2Po0KHITFlcs6BEtoT6EaKzLEbXpOVi6FhncXfBkp61seDDmkwuEBEREel0qaSpU6car4s+6bNnKSxRZMnZCzqYxSD6+KdPn5bFnAU3Nze59JRYctaa9WlcHF6u6uCpX3ddwb0QdQBUmuWvqR4nCVdNr8MgEgcvW/pI3Gfp5EJ6j5eExqVzy2OmdCUXhPPrgdD4Qufl2wHuvhr9HxGRNWCCgYhse6mk6IRCWo5B++VooeHDhyNv3rzytrlz5+Lo0aOwRh/ULYJiOdVZC1vO3cOWs3fT9LwT90/g3X/flQWQRaIBj64AK3qIwwX1AW9OBPJVTdc+hYSEyIONIkWKwN/f/4U1Wc154BFwJwBf7PwCETEmHiykQR5fdzg78SeRiIiISK9E3QWxpI8g6jGMHx8/Gt2aZi88P4vBSjzfx69VqxaiotSTy+PGjUOZMmVg7cTSPR83KCa3w6NjMX3LJdNewMUdKBBfz+72CSD8sRn2UmeUFxN56RYwN2G7hjg2JSJbwrMpRGR7HB2Bt6YBDsl8xW3/Ht5eXvj++++NI3Qsvk5rClydHTG6VcI6p6P/PYOI6NhUn/fryV9xPeS6vEwPmAwsex+IiK/jULUbULVrug88GjVqJJeWunXrVpL7cuXKhQIFCsBcAoMD8fm2z7Huyjr03NRTTZxkkDX+zYmIiIgo/b777jt4e3vLbZFguHbtWuaG89BcEx47B9YguT5+dHS0sb7FRx99BL34qH4R+Hm7yu0lB68b66ylmWGQmjizfnUP7F14dIw2L/TwMhC4Xd32rwr4V9HmdYnIajDBQES2KfhaQgGpZEYLdenSRa4lKuzatctq14SuV8IPLSqohZuvPwqT616mZlSdUcjmlg318tVDj5uXgbsnEzpzLSake19E/YojR44ke58YJSbuN5ewmDC4OKqFo/P75H/p9GMiIiIisk9ilrJhhq2oEZbZy3eiZk/AO3faLuKxVuBlfXyxzNTkyZOhF15uzujXRF0+NSZOwcRN59NX6DmdyyTZGg8XjWanB8xL2ObsBSKbxAQDEdme1NY+3fYtHJ9bp1UULQsPT1hOyZqMeLMsPFzU9UR/3nYJQY9ePnrfz8MPi99cjBk+VeB36m/1Rs8cQPs/AOf0FzCeN29ehu7PiPJ+5bHwjYVoW6ItxtQdk7HpufG0eA0iIiIisi79+/eXS/0Iy5cvl4OJMo0YAT/4QtouxtHylmXJPr45dKhZEIVyeMrttSdu43hQcNqfnK+aWoBYuMIEA7Q4XBJLFh9bpG6Lugvl2mrwokRkbZhgICLbk9rap6IWw6E5qF27tpzJIFy/fh0TJ06ENcqX1UMWLRMiY+Iwbm3qBZ/zP74Jh43D1Stiqah35gO++TO0nJCYpfAy4n5zLjtUIEsBjK47Gi5O6kwGIiIiIqLnubu7Y9KkScbrYjnU2NjUlxm1R9bQx9eai5MjBjcvZbz+w4Zzad9/Z1egYG11+95p4NkDM+2lHTm9MqGeRaVOgGt8AoeIbAoTDERkX7MXDNYNBjZ9he/HjYanp9rJEXUZbty4AWtdT7Rw/EicjafvYseF+yk/OOQusLwrEBe/ZmaTUXiavwr23NyTodH++fLle+ljxP1azQoQBwFbrm/R1cEMEREREVmHt99+G6+++qrcPnr0KObPn2/pXbJKmd3HzyxvVsiLCvl85faNx+F49EwtWJ0mXCZJW4mLO1f/UOMXJyJrwQQDEdnX7IXE9k5Fvn87YPqwbvJqWFgYhg0bBmvk5uyEUa3Kye382TzglFInPzYa+PMDIPSOer1MKwQUfwXvrH4Hn2/9HBceX0j3PlSvXv2l93/4oXYdRlGouv+2/vjf7v8hWvw/ERERERGlkTghPmXKFDg6qqc8RF2GJ0+eMH7JaNeuXab18TOLo6MDRrxZBqNblcN/Axsih7cJy8QWaZiwzWWSMub2CeDGoYTETc6SGXxBIrJWuk0wnD9/Hp07d0aZMmXg6+srRyCXLl0aAwcOxO3bty29e0RkKYcSjZBIiwfn0T1uCWa2zQk3J2DRokXYu3cvrNGrpXJhaofKspMsij8na/NXaiFrwa8k8PYMHLt/HLef3UZUXBQmB0xO93fu5s2bU7y/atWqso6FFm6H3sbs47Pl9oYrG3D20VlNXpeIiIiI7EfFihXRq1cvuX3v3j2MGzfO0rtkdWJiYnDgwIFM6eNnttpFc6Bb3cJwdTbxtFfeSoCrj7rNQs/aFXfm7AUim6bbBINYxkQkEtq0aYPvvvtOjk5o1qwZfvnlF1SrVk12IIjIDtXsCXjnTnJRvHIh1jOn/Nd4u6cf4F9FPsVBicMnFSJxtJcXauZzkuu0xsXFwRq1rpwP7vEFn19w8i9g/wx129UbaL8IcPNB93LdUTVXVTQr1Azf10/D8lHPiYiIQPv27eUMD6Fu3brw9/eX2+LfL7/8Etu3b4ePT3xHPIPyeufF7GazkcU1C76u+zUq5qyoyesSERERkX0ZM2YMsmbNKrenTp2KixcvWnqXrMqoUaOMCYZcuXIhb968Zuvj64aTM1Corrr94ALwlANY0yXiKXBiubotjsNLt9Tub0REVscZOtWkSRN5eV6DBg3w3nvv4bfffsPQoUMtsm9EZEFFGgCDky4DFB0VhUePHiF79uxwdXVNuEOs73/0D2DjCCDyKcrkdMLeDz0xad9JLPp9Ht7v/hGsXVycIqcA4+5pYHXfhDvenmGcgurk6ISZTWfCw9kjXeunDho0CMePH5fbderUkQcaojbCw4cPkSNHjqQx1Uj1PNWxru06+Lqpa6emVQ4vV7M8loiIiIj0x8/PD19//TX69++P6Oho2a9dvXq1pXfLKojZyWKwpiBWhNixYweKFi1q1j6+pYhjl50XHyAkIhotK6oDpV6qSH3g4kZ1++puoOK7sBWZdrx0YhkQ/UzdrtpVLaBNRDZLtwmGlBQqVEj++/hxfJV6IqKUiJPtorNTrDGw+nPg8hY4OTpg6CtuuHhsMJ6dLw6vUo2sNn77Lj/EqNWnMPb1gqi1uQsQrc4wwCv9gLKtkzzW00UtEG2qFStWYMYMdVaEGP21ZMkSuLi4ICoqStNib5GxkXBzSro2qqnJBVG8bWXvV1Ke4UFEREREduezzz7DrFmzcO7cOfz777/YtGkTmjdvDnt2584ddOnSRZ54F0R/Xyw5rXUf31oGZHX/7RB2XLiP7F6uaFgyJ3zcXVIftGZwdafNJBi2nL2LxqVzYWCzknB2MuOCJqJdBcQXVndwBKp9YL73IiKroNslkhIv3fHgwQO5ZJLoKBjWWGzRooWld42I9MI3P9BlBdBqOsLj1M5miWwKPBa/DWwaCUSHw9qcuBGMjr/ux8W7TxG74mPgUWBCZ7jxV6k+/3HEY/x++nfjQUVyrl69ih49ehivz58/35jE1VJIVAg6re2EX0788tL9eZnYOAWfLjyMtjP2IvB+qOb7SERERET6JAbH/Pjjj8brAwYMkLMZ7JVYCvb99983Listtrt16wZbJWZ7F/HzMg5I+nXXldSflLsC4J7Vpgo9334SjkF/HseM7ZfR/pf9iIiONd+bBR0A7p1Wt0s0B7IWMN97EZFV0P0Mhjlz5qBv34RlQQoXLoyFCxeifv36qT43KChIJiYSO3nypPxXdDhE9p6SJ+IjCkLZc8fMXBhbC8a0fAcEe5bB7u+aolkRwNFBAfZOh3JuPWJaToOSvwasRamcHmhYwg/lA+egbsxBeZuSJR+iW80WZ9uB2JS/vw7dPYSR+0biQfgDeDl5oVXRVi88RsRK1F148uSJvP7pp5/KxK3he1GrdhqnxGHAtgG48PiCvChihFHZ7ia/zrStl3HgyiO5PWDZMSzvWUMXo6/4eWdc9YJt1Tbjaqv9OPbx9dsmbRlja9mYNm7cGG+88QbWr1+PM2fO4KeffkLv3r1hj3744Qf8999/crtEiRKynqXWfXxr06teIfwZEIRnUbGYsysQ7avmRU6fpLOnn+dcsC4cL6wDHl9B1P1AdVCaCawpljGxcei7+AiCw9R9KebnCUclFlFR5kkyOB34FYY55dGVu0LR6NyaNcXUVjCmthvb6Ex+X90nGN5++205lS80NBRHjx6V6ymKGQ1pMXfuXIwePTrZ+54+fSrXbKeUG6qIuRhtLEaEkHYYW8vG1CFrAewp0h9LVn2HH19zh6+7AxweXYLzgjcRVqk7Qmr0A5zdYQ3+V/QSSlz/U25HKc4IemUivCIdgciXf3eFhoTiYfhDuS1mMdTxrQMnh6TLCo0dOxYHD6qJi/Lly8uaNom/E7Vsp/Vy1kPAvQDkcMuBetnqmfzdezgoBDN2qDM43Jwd8MWr+XSzTB4/74yrXrCt2mZcRX/XFrGPr982acsYW8vHdMSIEbLugDjhI4o/v/baa7JGmz0RBZ1FTQrBzc1NLo0kkguG/rettlMx7Khj1VyYs/82wqJiMXnjWQxpXPClz/HMWQVZRIIBQNiZjYgo1cak97SmWM7eexMB14LldtEc7visdi6zne9yCH+EXGdXye0Yn3x4mLUyoNF7WVNMbQVjaruxfZrJ/XzdJxjy588vL4ZkQ7t27VCjRg2EhYVh+PDhL32uWPpDdCqen8EgllnKkiWL3XU2TP2giNHB2bJl4xc7Y2tz7XXw4CGoungJys24hF/f8sAbJZzhAAVex+fBM2hH/GyGmrCo4OvIfXAEHMQsCwBfxXyAsMA8mFgl9e+tV7O/im6h3XAv/B6GVhsKH1efJPdv2LDBWHfB29tb1l3w9/c323dAp+ydUMSvCHJ75kZR36ImPVdMcx696STi4ldW+vLN0qheIh/0gt+ljKtesK3aZlxFf9cWsY+v3zZpyxhby8dUHN+LWQtTp05FcHAwpk+fLrfthSje3KdPH7lEkjB+/Hg0aNDAbtrpZ02y4J+TD/HwWRRWnXqAT14tiUI5Uq5T51DmNWDPN3Lb58FReNZJWDo2LawllnsvP8Rvh+7IbXcXR/zUsQr8c3mb7f0c9y+GQ1z8yOlq3ZHdL6dmr20tMbUljKntxjZLJvfzdZ9geF7FihVRpUoVeXIstQRDgQIF5CU54o/v6soq9y/j7OzMOJkJY2vZmIrHiHVaW7ZsiRaLwzCyZRGMqRsNh8incHh0GS4LWgJ1egONRwIuHsh0oibE392BcHWU/mrHJlga2xg4fhtdahdGzSKpJxkG1BgAR1Fw6zm3bt1KUndBFMQTMxjM3U4bFmqYroJtw1Yew70QdcrtW5X80bl2EV0sjZQYP++Mq16wrdpeXG314Jx9/IzhZ918GFvLx1SM3l+8eDHu37+PX375RSYcUurr2hIxgvaTTz4xLhEtBmaKpaaT6zfbajvN7uqKfk1L4KtVpxETp2DqtkD81Klqyk/IVxHw9APCHsDp+l44id9ME48zLB3L+yGRGPL3aVlzWRjTqjzK5jfjQFqRvDq6QN12dIFz9Q/EwbWmb2HpmNoixtQ2Y+uSyf183Rd5Tk54eDiXNyKiDBH1BgwznMatuYI/fHqrBaokBdj3EzCrHnB9f+ZGWvQO1w4C7pxQr/tXgVuryca7v1p1Sq6xmZrkkguxsbHo3LmzcZm57t27y+ta231zNzZf25zh1/l1VyC2n78vt8Xoo2/blNddcoGIiIiIMk/WrFkxbtw4uS1G8vfv31+efLd106ZNk8tJC4UKFZK1LO2x39yhRkHjrIU1J27jxA112aBkifgUrqduPwmStRj0RAzGGrj8mEwyCK0r++Pd6qbVkTBZ4NaEOJVtBXhrN3uBiKybbhMMd+6oU7yet23bNpw6dQq1a9fO9H0iItshOtxiFoOTk1qbYODXE/H4jdlA6xmAm6/6oIeXgHmvAxtHAFFhmbNjAfOAY4vUbY/swHsL0LxSIdQr7idvOncnBAv3XzP5Ze+H3UebmW2wc/9Oeb1MmTJy2rjWzjw8g4HbB2LQ9kH448wf6X6dI9cfY8LG83LbxckB0ztWgY+7bY7EJSIiIiLtiNm6lSpVkttbtmwxnni3VQEBARgyZIhxNO3SpUtlosUeuTo7YlDzUsbr368/9/IEU5FES0hd2QU9mb0zELsuqgPHCufwxDdtKpg/qXRoXsJ2ddOWlCIifdNtguHTTz+VSYT//e9/mD17tlw7sWvXrnLEsY+PDyZNmmTpXSQinRMn2cU6pYY1S0ePGQNU6Qz03m+Z2QxBh4D1X6jbYgbCO3OBrAVlR/HrVuXg7OhgHI1jykisY/eO4a0Vb+GKzxXk7ZQX7u7uWLZsGby8vDT/X9h7ay/CY8KhQMG1p9fSNWJMzNAYtPy4nNosDH+jDCrmt8+DJCIiIiIyjRhAlLj2wqBBgxAZqY7ytjWiyGeHDh3kWuDCN998Y/eDMVtWyIvy+bLAz9sVr5fPY1w+KNUEw1V9JRiiYuLkJAxXJ0e5FJS3m5lXSH9yA7iwXt3OWQYoVNe870dEVkW3CYaOHTvCz88Pf/zxB/r164dhw4bh4MGDskDziRMnULlyZUvvIhHZgFGjRiFHjhxy+6effsLZs2eBLP5Ap+XA2zMTZjM8uqzOZtjwP/PMZgi9ByzvChgKZon6D8UaG+8unssbfRuXwMg3y2DJx7VNGp3iGeWJkKch6nZJT4yfOh4VKlTQ/v8BwEcVPsKIWiPQuEBjDKs5LF2jaJydHDH5vUrIn80DTcvkRvdXCptlX4mIiIjINjVs2BDvvPOO3L58+bJNFnsWA3nE+RHx/ye8/vrrGDx4MOydo6MDfupYFTuGvIqudQrL6ynKURzwzqNuX9mpLlerE6LexKKPamFcm/Iony/+mNWcjiwAlPileqt/aHK9CiLSN90mGN577z2sWbMGQUFBiIiIkHUXzp07J5f0KFiwoKV3j4hsRLZs2TB27FhjjYIBAwaoo+5Fh6lyp/jZDK8lzGbY/7M6m+HaPu12IjYG+OtDIOSWer10S6DewGQ7kR/VLwoXp7R/tcu1Zz/uj+u/XMej7Y9Q6Xgl9Ompztowlw6lO2DKq1Pg7Jj+UTRVCmbD2s/rY+K7Fe1y/VgiIiIiypgJEybAzc1Nbov+fkrLMOvV3Llz5XJIQt68ebFgwQI4Our2FJCmCvt5wSstI/rFcUaR+up26F3gwUXoSd1ifnivegHzv1FsNHD4d3XbxROo1N7870lEVoW/LkREqejZs6dxRP/GjRuxbt26hDvlbIZlwNuzAPdEsxnmvwFsGK7NbIb/RiVMyRWjaMTMCY1Oqk+ePBnr169H6IlQuO90x5yZ2hZ8i1Pi5FJIz9PiPXw9XJDV0zXDr0NERERE9qdw4cLG2gShoaEYMWIEbIWoS9m3b19jv3vRokXImZMFd1MiBpCJosipL5Ok1quzVkGPMqku4PPOrwNC4xN0Fd5JOC4mIrvBBAMRUSpEMbQpU6YYr4tZDFFRUQkPkLMZOgKfHQBKvp5oNsMMYNYrGZvNcOpvtcaD4OIFtF8EuGdJUyd585m7+Pd4/KyHZBw4cADDhw9XX9rFRY5w8vXVtjM45fAUvPvvu9h5I2Od8WeRMfhu/VmERsZotm9EREREZN+++OIL+Pv7y+358+fLgsh6FxYWhvbt28uVHoQvv/wSr776qqV3y2odDwpGp18P4I/9Lw6KkgrHz2Cw8kLPp24+QZNJOzBy5UlERMdm7psfmpuwzeLORHaJCQYiojRo3Lgx2rRpI7cvXrwo6zG8IEteoONSoM3sRLMZAtXZDOuHmT6b4d5ZYFWi5Yre/hnIVTrVp4nRNx//cRg9FwTgy1Wn8PhZomRIvODgYFnwLSZGPWH/ww8/oEaNGsb7b4feRq/NvXD+0Xmk146gHZh/er4s6jx4x2A8jnic7tf6cuUpzN4RiLem78ale2q9CCIiIiKijPD29pb9YMMAnf79+6vLoerY559/jjNnzhhrTXz11VeW3iWr9SA0Eu/M2ot9gQ8xbcvF5AczZSsM+MYvMyRmlcfF1xmwImK/+yw+gqjYOCzcfx1/H7mZeW/+4BJwZYe6na8a4M96qET2iAkGIqI0mjhxIlxd1SV5Ro8ejXv37r34IDGboVIHoPdBoOQb8TcqwIGZwMy6wLW9aXuziCfAsi5A9DP1ep0+QDk1wZEaUaisQDZPuR0cFo0Jm5ImCcRBk1j26erVq/J6y5Yt5cGUweXgy2i3uh323tqLYbuGITI2EulRL189dCzdEQ5wwDf1vkE292zpep2/Dt/A30fVTnJIRDSyeLik63WIiIiIiJ7XqVMn1KpVS27v2bMHy5Yt022QFi9eLGsvCH5+fnJpJCcnJ0vvltXy83ZDp5pqDc+Hz6Lw687A5I/vDLMYwh4C98/Cmohju5H/nMTVh+pgtvol/NChRibUXTA4PD9hWxR3JiK7xAQDEVEaFS1aFAMHqsWVnz59Kqcbp8gnD9BxCdDmF8A9q3rb4yvA/BbA+i+AqPjEgYEYKXVsiXqJjQVWfgY8vKTeJzq0TUeb9Hfq36yE7DALSw5ex4kbwcb7Zs2ahb/++ktu58uXT04HT1wToXCWwiiVvZTx+sPwh0gPJ0cnDK85HEtbLkWzQs3S9RqX7oXK2QuC2MUf21dGLh/3dL0WEREREdHzROHjqVOnGq+LugximSG9EbOse/XqZbz++++/y74+vVzfJiXg5aomYX7dFYj7IZEvr8NgZcsk/Xn4BlYeU5fFzenjhsnvVZYDzjJFdDhwdKG6LWbwl2ubOe9LRFaHCQYiIhP873//Q548eeT2r7/+imPHjqX8YDmboT3Q+wBQqkWi2QyzgJmvAFf3JDxWTCtd+Yl6WdMPOLdGvd3HH3hnPuDkbNLfKYu7C4a/UdqYu/hq1Wm5dNLx48dlDQnDwdSSJUvk6KbnEwPf1f8OH5b/UCYH/L3VdWnTQyQuyuYom67nirVDxVTf8Pg1RD9tWAz1S7A4HRERERFpS8xg6Nq1q9y+ceMGxo8fr6sQR0ZGyuVPRbFqYdCgQWjRwnD8QS8jBmX1bFBUbodFxeKnrRdffFCRRHUYxDJJVkIsHTtq1WnjoeeU9pVlkiHTnP4HiIgfyFa5M+CqzqInIvvDBAMRkQl8fHzw3XffGaej9uvXL/V1WsVshg6Lgba/Jp3N8FsLYN1QIDIU2P59wuOP/hH/De0CvLcA8E7fSfU2VfKhWiF1WaJjQcFYuPeSLPgmDkAMyzzVr5+os5xIHq88GFBtANyc0t5BFTUWemzsgQuPL0AL49aewbk7ar2F6oWyYWCzkpq8LhERERHR80Qf38vLS26LBMP169d1E6ShQ4fiyJEjcrtmzZr49ttvLb1LuvJR/aLI4aUuhbvowHVce/jcbHPf/EC2IonqMGRyEeUUBmP1XnTUOBirz6vF8UrxpAPHzC5gXsI2l0cismtMMBARmUiMbqpevbrc3rlzJ1asWJH6k8SQkorvPTebAcDB2cD0qsD1fS8+540fgAIJhZdNJabGjmldDoYZsmNXn8TFqzeMRauHDx9u0uvFxMWkmEyJiIlA3619cfDOQXRb3w3H7x9HRqw/eVsWKBN8PVwwtWMVODvxJ4uIiIiIzMPf31/OVhbCw8PxxRdf6CLUq1atwrRp0+S2r68vli5daqwbR2nj7eaMz5uUkNsxcQombrqQ8jJJolbenZMWD+3of8/g/F11MFbNwtnRL37/M83tE8CNQwlL+vpl8vsTkVXh2RoiIlO/OB0djZ14YfDgwfIgJE2MsxnmAB7xRY9D7774OK+cQLXuGf7blPP3RedaheR2tKMbfOt3Qc6cObFw4UKTCr7NOzkP7697H/9c+ifZ+8Oiw+RF8PPwQyEf9T3TI+hRGIauOGG8PvHdSsiX1SPdr0dERERElBai3lrhwoXltjhRv3v3bqsOnJhl0b17wjHDnDlzUKRI/Eh7MknHmgVRMLu6xM+/x2/h5I0nKddhsPAySfsuP5R19oRsnmIwVuXMH4wVoBYTl2r0yNz3JiKrwwQDEVE61KlTB506dZLb165dw6RJk9L+ZDmb4V3gswNAgdrJP+bZfc06rq2KOiIu/Knc9qnSAj/MWoC8efOm+flLzi7Bj0d+xKmHp/Ddge9w7em1JPeHx4Rj6M6huBh8Ea/4v4IZTWcgq2EpqHQQyyJFx8bJ7Q/qFkazsrnT/VpERERERGnl7u6OiRMnGq+L5VDj4tR+qbWJjo5Gx44d8fjxY3n9k08+wTvvvGPp3dItV2dHDH6tlPH6rJ2Xkz6gcL2E7Ss7YUm1i2bHyDfLwNXJUQ7GyuubyYOxIp4CJ/5Ut71zA6VbZu77E5HVYYKBiCidfvjhB3h6ehrXbL1586ZpL+CdS002pETUZUitvkMqIiIi8NH7HfF4+2+IDXuCWo6B6Pb2aya9xtsl3oa/l1ro2dHBEZExag0HQ3Kh75a+OHDnAGrlqYUfX/0RBXwKZGifRUJhdZ96aF3ZH8NbqIWqiYiIiIgyQ9u2bdGoUSO5Leoa/Pbbb1YZ+FGjRmHv3r1yu2LFipg8ebKld0n3WlbIK0/eD2pWEuPbVXxxJrpffE24a/uA2BhYioODg6wbsWNoIzQpY4HBWCeWAdHxdSqqdgWcXDJ/H4jIqjDBQESUTvnz5zeuzRoWFoZhw4aZ9gJXdiRfe8Hg+t4Mj44ZNGgQTpw4gdATm5Hv6K9YNLa3rM1gCg9nD/zZ6k8UylIIYTFhGH9ovEws7L23F3229TEmF6Y3mS4fq4WSuX0wtUMVuDmnfRknIiIiIiItTt5OmTJFLosqiLoMT5+qs4GtxebNm/H999/LbTHgadmyZfDw4JKiGSWOk5b0rI2+TUrAy835xQcYlkmKCgFuH4OlZfrMBUEMgDMUd3ZwBKp2y/x9ICKrwwQDEVEGiPoLBQsWlNuirsH+/fvT3jETMxRSk4FZDKL49IwZM+R21qy+WLbwN7i4pG90SRbXLPjzrT9lIkEkFLpt6oavj36NYw+OoaJfxQwnF0IiolMsIE1ERERElJkqVaqEnj17yu27d+/im2++sZo/wJ07d9ClSxdj31n090uX5qxfLRNMKRLFjC20TNLWc3ex9OB1yx8zXd8P3Dujbpd4DciasdnrRGQbmGAgIsoAMWJowoQJpq/TmtrshQzOYrhy5Qp69EgotjV//nwUKpRQeFl0TF8oXJYKkUAQiYRKOSvh8pPLUKB2bmvlrZWh5EJsnIKPfg+Ql8fPotL9OkREREREWhk7dix8fX3ltpjRcOnSJYsHNzY2ViYX7t27J6+///776NaNI8jN6XhQMKJi4iyaYLgVHI6By49j2N8n0W/pMcTE16uzCBZ3JqJkMMFARJRB7777LurXVzubBw8elDMZUnVobtrf4NCcdBV8e/JETSD07dsXb7/9tvH+M7ee4r3Z+/D2jD24cDcEGZHVLSt6VEhIZKTHtC0XceDKI2w5dw+fLz2aodciIiIiItJCzpw5ZZ0DISoqSs5ctjSxLNKWLVvkdsmSJY2zlUl7QY/C8OnCw2j98x4sOXhdvdErB5CrXPwDDgAx5h8cJZIJ/ZYeRXBYtLoLbs5wdrLQqbxnD4Azq9TtrAWBYk0ssx9EZHWYYCAi0midVsN0WlGLITQ09OVPqtkT8M6dtot4rAlGjBiBAwcOyO0qVaokmWEhHLn+GIeuPpYzB75adSrN02wNBZ2P3z8ul0Uq7VsawZHB6Le1n7wvPfZefoBpWy/KbTdnR4x8s2y6XoeIiIiISGu9e/dGqVKl5PaqVavw33//WSzIu3fvxldffSW33dzcsHz5cnh7e1tsf2ydOFbafOaucUBUaGRM0joM0WHAzcNm34+pWy7KYzehVG4fjHrLgsdLRxcCsfFJlWrdRdEKy+0LEVkVfhsQEWmgatWqxiWJbt++je++++7lTxAd08EX0nYxdGLTYP369caEgjjgEAXfxAFIYh1rFkT5fFnk9v7AR1hz4naakwuGgs4zXp2BCTUmoEbuGvI2cZ+pSYYHoZHov/SYscTE6FblUCqPj0mvQURERERkLq6urvjxxx+N1/v374+YmPgTzZno4cOHcoayYSnWyZMnyzoRZD6F/bzQqZZaa+/hsyj8ujNQvaNI5i2TtOfSA/y0TV2ay93FET91qgJ3FydYhGh7h+er244uQJX3LbMfRGSVmGAgItLIuHHj4OOjniCfNGmSrIOQmW7evImuXbsar8+aNQslSpR44XFOjg4Y3aq88fo3a8/imWFEThqSC4aCzu5O7vixwY/Gws+mJBni4hQMWn4c90Ii5fW3KvmjfQ0WCCMiIiIi6/LGG2/Ii3D69GnMnj07U99fzDb+4IMPcOPGDXm9Xbt2+PTTTzN1H+xV38Yl4OmqntD/dVcg7otjl0J1xRx29QFXd5ntvcV79Us0GGtMq/IokduCg7EubwUeX1W3y7YGvHNabl+IyOowwUBEpJHcuXMbpy1HRkZiyJAhmV7w7cGDB/J69+7d0blz5xQfX61QNrxTLb/cvvM0wrhMUXI2Xd30QnLh+cLPhiSDeGxaiA76jgv35XahHJ74tk154xJTRERERETWRMwYcHZ2ltuiv//o0aNMe++pU6dizZo1crtQoUKYM2cO+82ZJKePGz6qX1Ruh0XF4idxzOSRDcgbP3sk6CAQHaH5+4rBWAOXH5MzvoW3K/vj3erqsZvFBMxL2K6RsRp8RGR7mGAgItLQ559/juLFi8vtFStWYNu2bZk2e2L79u1yu0yZMpg+fXqqz/ni9dLwcVcPlObtvoJL95KvG9G6eGuMe2XcC8mF55MM4jHisakRNSAmbDwvt12cHDC9YxX4uLuk+jwiIiIiIksoXbo0+vTpI7dFcuHrr7/OlPcNCAjA0KFD5bZIcCxduhRZs2bNlPcmVc/6RZDDy1VuLzpwHdcePktYJik2ErhxUPNQzdp5GbsuqgPHivh5YVybCpZNKj25AVxYr27nLAMUrGO5fSEiq8QEAxGRxuu0ihFOiddpFbMLzEkkFsaMGSO33d3dZcE3Ly+vNI3IGdispNyOjlUw+t/TKRZ8FomD5JILBuK+tCQXIqJj0XfxUcTEqe8z7I0yqJifB0lEREREZN3EzAU/Pz+5PWPGDLlckjk9efIE7du3R3R0tLz+7bffonbt2mZ9T3qRGAjVt7E6gEwcw0zcdAEo3MBsdRjE8djle8/ktquToxyM5e2mDgqzmMO/A4pa/wPVPwQ485yInsMEAxGRxlq2bInmzZvL7RMnTshpzOZy//59dOrUyVjwTUyhLl8+ob5Cat6vXQil4wsri1EyG07dgTmJomT/a1EGPm7OaFomNz58pbBZ34+IiIiISAvZsmWTs4YFMYBowIABKQ7OySjxur169UJgoFpYWNSAGDRokFnei1LXqVYhFMiuDrb69/gtnHYuBzjEF1u+om0dBjFTYeK7FTH+nYoY1aosyufzteyfKDYaOLJA3XbxBCq1t+z+EJFVYoKBiEhjolP4448/wslJ7XSOHDkSwcHBmsdZJBW6deuG27dvy+vvvfceevbsadJrODs5YnSrcnLb39ddJgDM7c2KebGuX31MeKci148lIiIiIt346KOPULFiRbm9efNmY20ErYkBSsuWLZPbefPmxe+//w5HR56+sRRXZ0cMbl5KbovZBJdDHIB8VdU7bx4GotQZB1oeT75XvQA61yoEizu/DgiNH4RW4V3A3cIJDyKySvyFIiIyg7Jly+Kzzz6T26LwsmEJIy2JpZjWr1fXwixatCh++eWXdJ2wr1U0B37qVAX/DWqIV0vnQmYokN0T2eLXMiUiIiIi0gMxgGjKlCnG6wMHDkRkpFqIVyunTp2Sdd0EkVRYvHgxcubMqel7kOnequgva9jtHPoqWlXyBwrH12GIiwau789wSB8/i7LOP8uhuQnbYnkkIqJkMMFARGQmovhb9uzZ5bYounzu3DnNXvvAgQMYPny43HZxcZEjnHx90z+apGVFf3i6mmdtz2eRMZizKxCx8XUXiIiIiIj06tVXX0W7du3k9qVLl2Q/XythYWGy7kJERIS8/uWXX6JRo0aavT6ln6OjAz5tVAzZDYOkDIWeNajDcOrmE9T7YSt+2XkZcdZ0zPTgEnBlh7qdrxrgX9nSe0REVooJBiIiMxHJBcPMhZiYGDnCSQtiuaUOHTrI1xR++OEHVK9eHVoSyQCt1pT9cuUpjFt7Fh1/3Y+7T9WDJSIiIiIivZowYQLc3Nzktujv3717V5PXFTMXzpw5I7cbNmwoEwxkpQrUBhxd1O2r6a/DEBoZgz6Lj+BZVCy+XXcOa06qy99ahYB5CdvVe1hyT4jIyjHBQERkRqI4W7lyao0DsZzRunXrMvR64qS/WPv16tWrxoLS/fv3h5YCrj5Cy+m78d/Zexl+rb8O38DfR2/K7cD7z5COFZyIiIiIiKxKkSJFjEWXQ0JCMGLEiAy/plgKae5cdTkaPz8/LFq0yFjTjazP5SdxuOpRVr1y6ygQ8SRdx3Yj/jmJqw/D5PX6JfzQskJeWIXocODYInVb1F0o39bSe0REVowJBiIiM3J2dn5hndaoqPSvrzlr1iysWLFCbufPnx+//fabpoWSL94NwTuz9uHs7acYs+Y0IqJj0/1al+6FytkLgtjFKe0rI5ePu2b7SkRERERkKWK5UlGAWZg3bx6OHDmS7te6ePGiHJhkIIo658uXT5P9JO0tO3QdzX/ciVVPiqk3KHHAtX0mv86fATew6tgtuZ3Txw2T36ssl2KyCqf/ASKC1e3KnQEXD0vvERFZMSYYiIjMrGnTpmjdurXcPn/+PH7++ed0vc7x48cxYMCAJAXfcuTIoem+lsjtgzcrqgdKQY/CMWvH5XS9jkhMiKm+4fEJis8aFUO9En6a7isRERERkaV4e3vj+++/N45E79evX7qWGBVFosXyp6GhofL64MGD0aJFC833l7RTs0gOiDTAvrj4GQzpWCZJDOz6anXSwVgiyWA1WNyZiEzABAMRUSaYOHEiXF3VgmCjR4/G/fv3TXq+OOAQBd/EAYjhNerXT1RYTEMjWpSBh4s6HXvm9ssIeqRO2TXF2DVncO5OiNyuXigbBjQtqfl+EhERERFZUpcuXVCzZk25vXv3bvz5558mv8bQoUONsx/Ea33zzTea7ydpq4ifFzrWLIijccURobiYXOhZHYx1FBHRcfJ6n1eL45XiVjQY6/Zx4GaAul2kAeBXwtJ7RERWjgkGIqJMULx4cWOthCdPnphcsK13795y9oPQuHFjOSXbXPyzeqBvk+JyOzImDmPWqIXm0mrtidtYdOC63Pb1cMHUjlXg7MSfGyIiIiKyLWJW8dSpU43XhwwZgrCwtA/OWblyJaZNmya3fX19sXTpUuOgJLJu4njJydUDh+PUgVTKnZNA2KM0PXf0v2dw/q46GKtm4ezo18TKTuAnmb3A4s5ElDqe8SEiyiSi+Fvu3Lnl9q+//iqXPEqLBQsWyIuQK1cuLFy40OwF33rUKyJH5gibz9zFtvNpK/gsZjsMW3HCeH3iu5WQLyvX6yQiIiIi21S7dm05k0G4fv26nLmcFuKxH374ofH6nDlzZPFo0gdRW+6j+kWNyyQ5QAGu7Un1eVvO3sWSg+pgrKyeYjBWZesajCWKVZ/8S932zg2UftPSe0REOmBF32JERLYtS5Ys+O677+R2XFycnNGQ2jqtYtbCZ599Zrz+xx9/GIvJmZObsxO+blXOeH306tOIjEm94POuiw8QEhkjt7u/UhjNyqoJFSIiIiIiWyVqMXh6ehq3g4KCXvr46OhodOzYEY8fP5bXP/30U7zzzjuZsq+knZ71i+C0WyXj9adnt6b6HLEUUrc6heT2xHcqIa+vlQ3GOrEciH6mblftCjjFLwFFRPQSTDAQEWWibt26oVq1anJ7+/bt+Pvvv1N8bHh4ON577z08e6Z28IYNG4bmzZtn2r42LJkTzeMTBFcfhmHOriupPqdTrYJY8GFNvFoqJ4a9UToT9pKIiIiIyLLy5ctnXMJU9OFFv/1lRo0ahb1798rtihUrYvLkyZmyn6QtH3cXNHr1NTxT1OLMoee2pfocdxcnjG5dHhv610dTaxuMJQa/GZZHcnAEqn1g6T0iIp1ggoGIyILrtA4ePBgRERHJPnbQoEE4cUJdbqhOnToYM2YMMtuXLcvCzVn9qVh/6jbi4l4+40JoUDIn5nevKWdBEBERERHZA9F3L1RIHZm+ePFiYwLheZs2bTLOahazHpYtWwZ3d/dM3VfSToc6xXDKSV0myT/qCs5eupym55XOk8X6/gzX9wH3z6rbJV8HfPNbeo+ISCeYYCAiymSvvPKKnBItXL16NdkRSytWrMDMmTPldrZs2bBkyRK4uGT+9NQC2T0xqHlJORvh709fgaOjwwuPiYqJy/T9IiIiIiKyJh4eHknqL/Tr108ui5rYnTt38P777xuvi/5+6dKc9atnYlCVd+lXjdcLPDn8wmO2n7+H3RcfwOoFzEvYZnFnIjKBsykPJiIibfzwww9YuXKlnEL97bff4oMPPoC/v7+878qVK+jRo4fxsfPmzTOOhrKEv4/cxMNnUZi7O9ESSYoiD5gcHB3xJDwazo6O8HZzRg5vV2zo38Bi+0pEREREZCnt2rVDgwYNsHPnTgQEBGDBggWyny/ExsbKYtD37t2T17t27SovpH+zr+fDtPjtDWv/xA8bshuPlxQHBzx+Fi1KQMPT1QkFs3ta5/HSswfAmVXqdtZCQLHGlt4jItIRzmAgIrKAAgUK4IsvvpDbosaCYc3WyMhIdOjQAU+ePJHX+/bti7ffftuifyORXLgfEpn0EhqFh2ExeBAahehYBeHRsbgfGikfS0RERERkjxwcHORyqOJfQfTxQ0JCoCiKLP68ZcsWeXupUqXw888/W3hvSSsHIwrgqaIWa64SczLJ8dKj+OSCEBYVa33HS6LuwrElwNpBQGz8vlXvLtb2tfSeEZGO8BuDiMhChgwZIhMNghjdlCtXLrn+6sGDB40F3yZMmMC/DxERERGRTlSuXBkfffSRcUkkMUtZ1GEbOXKkvM3V1VXWXfD29rbwnpJWYh2ccDBOXeqqmONt5MJj/QT3yg5g5SfAmZXqdSdXoErCMl5ERGnBBAMRkYWIom6jR482Xr9//36S+8U06qgoKxvhQkRERERELzVs2DCZVBBCQ0OT3Jc7d24ULVqUEbQx++LUQs9CHcfT0AUxe2H790lvK9MK8PKz1B4RkU4xwUBEZEGBgYEp3nf69GnOYCAiIiIi0pnffvvthQLPBkFBQezj26B9ceWM23Ucz0A3sxeu70t6W75qltobItIxJhiIiCxo/vz5L71fFHgmIiIiIiL9SK0Pzz6+7TmrFMRjxVsfCYawR8CVXcC//V+87+xqdWYDEZEJnE15MBERaUcUe7t58+ZLHyPuF48zFIojIiIiIiLrxT6+fVLgiANxZfC60yEUcryHfLiPm8hp2Z2KegbcPwfcOwvcPQPcE5ezQOidlJ8jZjRc2QkUbZiZe0pEOscEAxGRhYikQb58+V6aZBD3M7lARERERKQP7OPbdx0GkWAQ6jidwV+xmXSSPjYaeHgZuHc6aTLh8VWZ+jCZqMtQpIFozObYWyKyQUwwEBFZ0IcffoixY8e+9H4iIiIiItIP9vHt095EdRjaO21DnOKAv+Pqi7STNm8g6no8CYqfiXAmIZnw4AIQF52GF3AAshcFvHMC1/en/LDrezmLgYhMwgQDEZEFDRkyBGvXrsWRI0deuK9q1aryfiIiIiIi0g/28e3TRSUf7itZkNPhKWo4XkAN1wu4HZUjSQHoNAu9nyiREJ9MEJeo0LQ938cfyF0WyFUGyCX+LQvkLAU4uwPz30j9+ZzFQEQmYIKBiMiCfHx8sH37dkyYMEEWexPLJYllkcSoJ3FgIu4nIiIiIiL9YB/fXjnIOgwtnQ4Yb+nvvAL7osqmPIshMgS4d+7FZMKz+2l7S3dfIFe555IJZQCPbMk/PnC7WmchNZzFQEQmYIKBiMgKDkDGjBkjL9ZY0DmHl+uLNyoK4uLi4OjomGRtzmQfS0RERERkZ6y9j0/aSXwM9DTGL0nZg1qO5/CG10UccyiNwriJSi63gP/2JCQTgq+n7U3EzIOcpdUEQuJkgk9e02olHJprwmPnsNgzEaUJEwxERFbEGg88NvRv8MJtUVFRePToEbJnzw5XVyYViIiIiIj01McnMxwvKQrwy1jgdtL7Zzr+AMREAUosEANg90tezMEJyFE8IYEgkwllgWyFAUenjO9szZ5A0IG0P5aIKA2YYCAiIiIiIiIiIsqIKzuA28devD06PPnH+xZIWNLIkEzIUQJwcTff36FIA2DwBfO9PhHZJSYYiIiIiIiIiIiI0kvMXhCFkVPilgWo2CFhRkKu0mr9BCIiG8AEAxERERERERERUUZmL7yseHLkU6BMS9Y0ICKb5GjpHSAiIiIiIiIiIrLJ2QsG4jHisURENoYJBiIiIiIiIiIiInPMXjC4vhe4spMxJiKbwwQDERERERERERFRehyaa8Jj5zDGRGRzWIOBiIiIiIiIiIgoPWr2BIIOJLlJURTEKQocHRzg4OCQ9LFERDaGCQYiIiIiIiIiIqL0KNIAGHwhyU3RUVF49OgRsmfPDldXV8aViGwal0giIiIiIiIiIiIiIiKTMcFAREREREREREREREQmY4KBiIiIiIiIiIiIiIhMxgQDERERERERERERERGZjAkGIiIiIiIiIiIiIiIyGRMMRERERERERERERERkMiYYiIiIiIiIiIiIiIjIZEwwEBERERERERERERGRyZhgICIiIiIiIiIiIiIikzHBQEREREREREREREREJnM2/Sm27dmzZ/LfkydPWnpXrFp0dDSePn2KLFmywMXFxdK7Y1MYW8ZUD9hOGUdrxvbJmOqFpduqob9r6P/aMvbx9dEmbRljy5jqAdspY2nN2D4ZUz2JtrN+PhMMzwkMDJT/9urVK1P+AERERERE1tD/tWXs4xMRERGRvQnMpH6+g6IoSqa8k07cunULa9asQdGiReHl5WXp3bFaIhMmkjCzZ89GhQoVLL07NoWxZUz1gO2UcbRmbJ+MqV5Yuq2KEU3ioKNly5bw9/eHLWMfXx9t0pYxtoypHrCdMpbWjO2TMdWTk3bWz+cMhueIoH/88cdmD7ytEB+SOnXqWHo3bBJjy5jqAdsp42jN2D4ZU71gWzU/9vFNwzZpPowtY6oHbKeMpTVj+2RM9aSCnZw3ZZFnIiIiIiIiIiIiIiIyGRMMRERERERERERERERkMiYYiIiIiIiIiIiIiIjIZEwwULrkz58fo0aNkv+Sthhb7TGmjKm1YttkXPWCbZVxJfvAzzpjqydsr4ypNWP7ZEz1gO2UsdWKg6IoimavRkREREREREREREREdoEzGIiIiIiIiIiIiIiIyGRMMBARERERERERERERkcmYYCAiIiIiIiIiIiIiIpMxwUBERERERERERERERCZjgoGIiIiIiIiIiIiIiEzGBAMREREREREREREREZmMCQYiIiIiIiIiIiIiIjIZEwxERERERERERERERGQyJhjI4o4cOYJr165ZejeIiIgoE5w/fx6PHz9mrInsAPv5RERE9oF9fPvGBANZ1JIlS9CgQQMEBATI67GxsfyLmImiKIwt42hVgoOD2S7NiN+nGbd161YcOnRIg1eixL/7devWxeXLl+X1uLg4BsdMGFuyNPbzMwf7+IyjNWI/33zYx8849vG1xz5+5rHWPj4TDGQxv/32Gzp37oywsDD8/PPPiI6OhpOTE/8iGti/fz+mTZuGfv36YfTo0bhw4QJCQ0MZ2wy4ePEinjx5AgcHBx7IaWDhwoVo2bKlHNlIGSfiOG/ePPmZnzhxIp49eya/T3kAkn7z589H06ZNcerUKcTExLCZavi7L2YvTJgwQcbV0ZFdUa2+AxYtWoRx48Zhzpw5uH//PmNLFsV+vnmwj6899vG1x36+dtjH1x77+NpjH998dNXHV4gsYP78+YqDg4PSt29fpXHjxnJ79erV8r7Y2Fj+TTJgwYIFSrZs2RQ/Pz8la9asMrbZs2dX+vXrp5w4cYKxTYfFixcrBQoUUCZMmKA8ffpU3hYXF8dYptPGjRtluxSX+vXrK8eOHWMsM2Dp0qVK0aJF5efe1dVVxlV8r4aHhzOuGfyN6t+/vxIUFMQ4ahjTzz//XKlSpYqSM2dO42efv/sZ88cffyi5cuVSvLy8FEdHRxnnggULKlOmTFGuXLnC9kuZjv1882AfX3vs42uP/XztsI+vPfbxzRdT9vG1p7c+PhMMZNEv9dDQUOXgwYOKp6en8sknn/CvkUHr1q1T3N3dZeImICBA3rZo0SKlbt268gtJnHTcvXs342yCbdu2KR4eHrLN5s+fX5k2bRqTDBlw6dIlmVQoXLiw8tlnn8mT4jVr1mSSIQMHxs7OzjKWO3bskImvDh06vJC0ZUIs7ebNm2f8jbp+/XqKj2NMTf/dF4nux48fK8uWLZPXv/rqKxNehZIjPucisdinTx9l586dSlhYmPL999/LpKOPj4/y4YcfcnABZSr2882DfXztsY+vPfbztcM+vvbYx9ce+/jms1qHfXwmGChTzZkzR3FyclIGDhyo3Lp1S9528+ZNpXLlyvIEuDhBRqYTJ7rEaOUuXboo5cqVU86ePWu8T9wuRj+IWQwi+fDKK68oR44cYZjTQJxcfO2114yJBTHqVpwQZ5IhfWJiYmTCS5xYFLNBRLudPn264uvryyRDOg+MCxUqpPTq1Uu5du1aks6zGB2+adOmdP6l7NeKFStk+/z666+VGzduGG+fO3eu/N3q1KmTMmTIEPm7Ren/3T937pwcjSMuJ0+eZCjTQXx/PnnyRHnrrbfk9+eFCxeM9z179kwZP368bMvi+7Vz587ypA+RubGfrz328c2DfXztsZ+vHfbxtcc+vvbYxzePOB338ZlgoEz7kIiT3oZlkW7fvp3k/t9//13eN27cOHmdyyWYTswGKVu2rNKyZUvjbdHR0cYvInEiUizzI+Lco0cP5dGjRxn8q9q+vXv3Kt7e3soXX3whr586dUqpWLEikwwZsG/fPvmjaPDw4UOZsBHLeT0/k4HfAykTS3V17dpVadiwoXL48OEk94kTuVmyZJGdkm7dusmZSxs2bJAdFUrZgwcPlKZNm74wsl7EUcwSEVNTRVzF/eL7VMRU4EyGlIlktmHK9PO/+yLJKAYWiKQjP+/pI2aDiLYovgue/90Xn3eRaMybN6+M89ixY+XJH7ZXMgf2882LfXztsY9vHuznZxz7+NpjH1977OOb12Od9vGZYKBMJZbnSTwq1HACUYwGrVSpkpIvXz6ODE2ne/fuKaVKlVJKlCihXLx4MckXkRg1KkbfL1++XGnTpo08aX7o0KGM/jlt3p07d5SVK1car4sv7ePHj8u2+vxMBvGlTmkTFRWVJGbBwcHK1KlTkyQZEsdTJMjoRWJm0owZM5Lc9uuvvyouLi5Ko0aNlIkTJ8qErvheELFdsmSJfAwTNy//jXr99dflSfGZM2cq3bt3l6PsxayQq1evypM8Ys1LMTVVzGwyjCixhg6dNRJxEYmYxDM+DO1PLOMnvkfFrDvx+0WmCwwMlPWWRBLx/v37xnYofvdF2yxdurRsu2LmojgQedmSX0RaYD/fPNjH1x77+ObDfn7GsY+vPfbxtcU+vnkF6rSPzwQDZYq0nHwdPHiwPKkjTooJPAlmuuHDh8sYjho1Sp4MEyIjI+WIZrFOmzjJs2XLFnkCUiyrIvDEWNrabuI4PZ9kECfIDUQCLfF1elFybe75JIOYLSKIk5Nt27ZVTp8+zVC+JH7itj179sjP/7Bhw5Kc0BUdanEyXHREQkJCGMdU2qSoC9SkSRMZS5FcEOtfGg6WBbEtEjni/nfeeYfxTONnPDliVI6Io5i2LjBRazqx/qqbm5tcxsvw2yPiL2qI5M6dW84cEfeJOH/zzTcm/X2I0or9fPNjH1977OObB/v52saOffyMYR9fW+zjZ54PddjHZ4KBMt3zjd5wXYzOKVKkiNKgQYMUH0svJ9a1fuONN+SXTLVq1ZT3339fqVWrlvxiEstQCWLEvTjRKGYyUPolTjL8/PPPcmTz9u3blebNmyuzZs1igkxRlAMHDsjCT0OHDlXWrl2bpDZIcsQPpxgdLpIMot3+8ssvMtkg2rNo2/Si578jV61alWyCSxR+9vT0NCZuKPUp/m+++aaxKLGBIfEtimyJJenE96xI4pJp7dQQRzFbSXze27VrxxCmkxg0IGYoenh4yDiKAQXNmjWTv/uG5afu3r2r5MmTR/n0008ZZzI79vPNg338zMM+ftqwn29e7OObB/v42mIf33y26LCP7yD+AyIz2L17NwICAnD69GnUqlULFSpUkP8mRzTD8PBwfPrpp/jjjz8wd+5cdO/enX+XNMa2fPnyqF27trzv4sWLmDlzJubPnw8PDw/kzp0bkyZNQv369eHi4iIfI/4WZcqUwfLlyxnjeHfu3EGePHlMisexY8dkO7127Rq6dOmCPXv24OjRo/LvIuJrz8TneNCgQYiJiUF0dDSePXuGwoULY9SoUejWrVuKzxOPmzdvnnxccHAwsmTJgl27dsk2a88OHjyIM2fO4OzZs2jYsCGKFi2K0qVLG++PjY2Fk5NTkufExcXB0dFRbrdp00Y+d9++fciWLVum778eY3rgwAH5/SnabeLfKgcHB7ldqVIleHt7y+9jw232LrWYPu/hw4do27at/IyvWbMGLVq0yNT91XNsixQpYvyd+e+//+T35tKlS+Hl5YW8efNi6tSpaNKkCVxdXREZGYmSJUvi9ddfx+zZsy39v0I2gv38zIkr+/gZxz6+9tjP1w77+NpjHz/zY/o89vHttI9v6QwH2aYFCxbIUYli6o64iBHI7u7uyvfff29csz6lkRBi+Z6OHTvK65zBkPbYfvvtt0nWqr9y5Yos5Pz8kiibNm1SChYsqEyfPp0xThRTUcQ1cb2FtDp58qRc4178HcTf5cSJE4q927p1qxwtP2DAAFlET7TDn376SdYHEXH68ssv5QjwlIhR+GItwezZs3NppPj2KeIhZsuI+ikihmK212+//ZZiDBMvMbdjxw5ZM+Djjz9WIiIitP5z23xMDb9DiX+PNm7cKAtrjRgxIlP329baqbB+/XrFyclJLu1FpsVWrL2amFhKTqzB+nxB93///VfWuBKvI7BvRRnFfr55sI9vnpiyj68t9vO1wz6+9tjHt2xME2Mf3/76+EwwkOZ27dol1/sfNGiQrC4viOLCTZs2lR+YHj16KJcvX37heeLDIIqWGNZkFtPXyLTYinXaEhd4fv5EoyjsLJZQKlasmHLt2jWGN37qmYipiJ+vr6/JSQbRyRYJBvGjYO91Agw/aOJEYaFChV5YEknUAhBLc4lYf/HFFy88T9i2bZss+iqSNSJ5Y+/ScxCXeC1s8T0qlu3y9/d/4bvBXmU0pvv375fTU0WiVhTgovSfbBCffbF+aL169RRHR0cmaNPRXkeOHGkcXJBcMuzw4cOycLlYGlHUCCLKKPbzzYN9fO2xj68t9vO1xT6+9tjHt46YCuzj22cfnwkG0tyECRNkFk6srZzYmTNnZEESMVJR1AYQJxWSIwq9ig8UT4ZpG9tJkybJ9cLFGm1ibVFSZJLltddekydfRfE8saa6WOMurUkGcTBYvHhxmVzgzIUE7du3lydfDRIXyBVxEveLz7iot5CYeJwYCVGgQAHl6NGjdt1E03sQl5jooDRq1EgWKuZnPuMxFc8XM78aNmwov4cZU21ONgj/+9//5GOY+Nb2O0C01zp16sjvAP5GkVbYzzcP9vG1xT6++bCfnzHs42uPfXzriSn7+Pbdx2eCgTTXp08fOb0nuZOLQUFBsuCr+LAMGTIkyfMSfxmllHywd+mJrYjrhQsXZOGX9957j8VyE1m9erUskvPNN9/I63///becjZDWJIP4Mi9ZsqTMHlPCjBmxFI8Yjbxz585ks+0BAQFyxLJYDk1k7hMTn31R8J3SfxAnlqETbVosnVa/fn2ZgKSMxTQ8PFwWbxfLLNStW5cx1ehkg2GGnYiv+A0j7WIrBiK0atVKadmyJdsraYr9fPNgH19b7OObB/v52mEfX3vs41tHTAX28e2zj88EA2lu7Nix8oOwePFi4xdL4pOLYkmJzp07y8f89ddfKS7nQ9rG9v79+y/UY7B3Yg27n3/+Ocltf/75p5xm9nyS4flsvCH+L6slYK9ELRURP7EcWuJ4JY7hP//8I5MQffv2fWEJGsp4skbMAFu3bp1y9+5dhlOjmIrvT1F7gQlwbU82kPliK9ZqDQ4OZohJU+znmwf7+NpiH9982M/POPbxtcc+vnXFlOyzj88EA2lO1FcQxVnFWv937twx3p74wyI+RH5+fspbb70l6y5YuhiJLceWJ26T93wyS8QqtSSDcOvWLc3+nrbq4cOHygcffCATXWPGjEnSThO31datW8sZIImz9ZTxgzjSPqb8jdI+phxQYL7YJv49I9Ia+/nmwT6+dtjHNy/287XBPr722Me3jpiyj2+/fXwmGEhT4gMhGv3o0aPlycXPPvssyQnuxF82vXr1UnLkyPFCJXRibC0lcfsUM0AMSYY1a9bI28ToZXHbokWLLLaPeiEKitesWVN+D3z77bfJPkasLVihQoVM3zdbP4jjyXDtY0qMqaWwvZI1YT+fcdUr9vG1xX5+xrGPrz32mRhTPXlog8ekziDSkKOjo7x07NgRp0+fxsyZM+Hs7Ixvv/0WXl5e8j4DBwcH+Pr6wsXFhX8DxtYqiPYZFxcn/23Xrp3cHjVqFN59913873//w/r163Hp0iWULVvW0rtq9apXr47x48fj888/x4gRI/DgwQMMHDgQ+fLlk/eL74cbN26gfPnyiI6Olt8T4juBksqePTt69+6NM2fOyLYo4jR8+PAXYiXarJubG79P04Ax1R5jaj6MLVkT9vMZV71iH19b7OdnHH/ftceYMqZ6kt0Wj/MtneEg23X06FFZfERk5Dp16iSnABmcOnVKFsoUhUlEcUdibK11lNOKFSuUokWLynbs6+srC+7Qy5eMSXzf3r17lRYtWsipfWK2gpjeN2zYMKV27dpyua+zZ88ynGmwfft2pWLFirIdDhw4ULlx40aS79MaNWooHTt25AwGEzCm2mNMzYexJWvDfj7jqkfs46cN+/mZh7/vjKkesJ0ytmnhIP5j6SQH2a6zZ89i+vTp+O2335AlSxbUr19fZuoOHz6MwMBA7N69m6PBGVurtn37dnTt2hWhoaFsr4CciZAtWzY4OTmlGDPxsyIy7yJm3t7e8rO+ZcsWTJw4Ebdv35bfBaVLl8bUqVNRrlw52DtDvFK7b9++fRg3bhw2bNgg49aoUSM5M0y00QsXLmDPnj0yrsSYsp3qC78DSK/Yz2dc9Yx9/Bexn68t/r5rjzFlTPVEsbfj/DSlIYjipWW2gWHEw4MHD2T9BVHdfP369UqdOnUUf39/ORpcFCA+ffo045oIY2v5mD59+jTJfWL0vRh17+3trZw8eVKxd6tXr5aj5CdPnpxi8SZDPPfs2SM/82J0vUFISIhy7tw55dq1ay/E2h7dv38/1SLshniK2BmKQP7yyy9yHUYfHx8lX758SpMmTZLE2Z4xpoypnrC9krVhX5Rx1Qv28bXHfr52+PuuPcaUMdWT+3Z6nM8EA6XZrFmzlI8++kgJDQ1N9UMiTsxWrlxZ2bp1q/E+UZTk3r178kRuWFgYI8/YWlV7rVq1apL2Ku5buXKlPEkulgGwdwsWLJA/dG3btlX+/fffZKdQG7YPHjwoC7g3btxYuX37trwtpYSEveJBHGOqB2ynjC3ZD/bzGVe9YB9fe+zna4d9J+0xpoypnqy240GZCRV3iV7i999/x6effioLi8TGxqb4ODHF59ChQ3jrrbeQM2dO4zQekcwSzxW35ciRAx4eHow3Y2tV7VW0yzJlyiS57/XXX8fatWtRuXJlu26vmzdvRp8+fdCjRw+MHTsWLVu2NN5nmNZnmOInlj+rV68eGjZsKP8OefLkkfcnLvBu7/744w907twZkZGRKFGihDE2iVcsNMRTtM9WrVrJ70zRRgVRfFwsPVWqVCkULFgQPj4+sHeMKWOqJ2yvZG3Yz2dc9YJ9fO2xn68d/r5rjzFlTPXkD3s/zrd0hoOs3/z582Vh0cGDBytBQUHJPsaQmRMjvZ2cnOQo55QeS4ytHtrry4qb2QsRAxGrXr16KY0aNVLOnDljvG/JkiXKTz/9pHzzzTfKpUuXlIiICHn7qFGjlC5dusiMO71o06ZNSpYsWZT+/funuEycoe0FBAQorq6u/D5NBWOqPcbUfBhbsjbs5zOuesE+vrbYz9cWf9+1x5gypnqyicf5XCKJUp8uKU7WDhw4ULly5Yrx9kePHikXLlww1lkQIiMjlXnz5ik9evTgycU0YGy1x5hqT3y+xTqAvXv3Nt7Wpk0bxdnZWXFxcZHfD35+fsq4cePk94JYkkrUXaGkeBCnPcaUMdUTtleyRuw3Ma56wbZqHuznZxx/37XHmDKmesL2moAzGChFGzZskCcPRWGRxDUTBgwYoJQpU0belzt3buXNN980rrMuTiw+e/aMUU0FY6s9xtR8RfQKFSqkjBw5Ul7v3LmzkjNnTjl74ciRI8qMGTOUBg0ayGTDV199xc//S/AgTnuMKWOqJ2yvZE3Yb2Jc9YJt1XzYz9cGf9+1x5gypnrC9qriotiUooiICBQqVAjHjh3D+vXr5W1vvvkmZs+ejeLFi2PkyJEoW7Ys1q1bhwYNGuD69evw9fWFu7s7o5oKxlZ7jKn2xBqATk5Ocg3ANWvW4L///pPfB+PGjUPPnj1RpUoV+e/MmTPRqFEjTJs2DVeuXDHDntiG6OhouR5jtmzZ5PUuXbpg9+7dmDJlCg4cOICff/5ZfqeOHj1a3ibWZhTfqcSYsp3aBn4HkDVhv4lx1Qu2VfNgP187/H3XHmPKmOoJ22u8+EQDUbLWrl2rlC5dWsmWLZtSvXp1JW/evMqqVatkZXNBzGz49ttv5WyGevXqyWWSKG0YW+0xphmTuO5E4m0xW0F8xrt166Zkz55d2b9/v7w9Ojra+O/y5cvlY4YNG5bBvbBNopZFVFSU0rx5c6Vy5crK5s2blXLlyimzZ882fm+KOIq6DM2aNVOyZs2qnDp1ytK7bdUYU8ZUT9heyRqx38S46gXbasaxn28e/H1nTPWA7ZSxzQxMMFCynQ7DiUNhzZo1ckkkf39/Ze7cuUlOhgniuiiSK4rlHj9+nBFNBmOrPcbUfJ4vcC0Sii1btpQJBHER6+AaiJPmgqi94OHhoQwZMsSMe6YfPIhjTPWA7ZSxJfvBfhPjqhdsq5kXX4H9/PTHjwOytG+TjCljau3YXlPGJZLISCzHET+rBc7OzsbbxbJI3333HV599VW89tprcHV1lbeLx0RFRcnr7733npxmeevWLUY0GYyt9hhTbe3Zswdjx46Vn/FWrVph06ZNePr0qbzP29sbffv2RePGjeX18ePHY9euXXLbxcVF/rtz5065PFqxYsWM3yP2LHH7NGwL3bp1k9+pCxYswOPHj3HhwgXj96mYWin+bdGihYxlbGysxfbfGjGmjKmesL2StWG/iXHVC7ZV7bGfrx3+vmuPMWVM9YTtNWUJZ5EJ9t7p2Lp1q1wPXCQMxMnE2rVrI0uWLPL+1q1byzXWE68HLk6cGZINhw4dgo+PD8qUKWOx/wdrxdgyptZu8eLFGDhwIBwdHeHm5oagoCCZQJg0aRJ69OghH9O8eXOEhYXJH9QtW7agf//+GDFihExIiOSCqL8gEhFvvPGGfHzik+r25mWfeUOyJjw8XD5GJGsKFy6M+vXrvzRZY8/xFBhTxlRP2F7J2rAvyrjqBduq9tjP1w5/37XHmDKmesL2moqXzG4gO7Fo0SIld+7csr5C4cKF5VJHvr6+ypw5c5IsgfL8Gm4GBw4cUKpVq6a89tprSnBwcKbuu7VjbBlTa7dy5UrFy8tL6devnxIQECBv+/fff5WqVasqBQsWVB4/fpzk8QcPHlQ+/vhj43JJ7u7uio+Pj1KgQAEukZaGz7zBP//8ozRt2lTGUMR6xYoVcpmpdevWKa+//rqM57Vr1zKzKVgtxpQx1RO2V7I27IsyrnrBtqo99vO1w9937TGmjKmesL2mjgkGO2dqp+N527ZtkyfJROHXM2fOZNJe6wNjy5hau8uXL8vi7B06dFACAwONt4u6KmPHjpUnv0Ux4ueTisLq1auVb775Rvn000+VWbNmKVevXlXsHQ/iGFM9YDtlbMl+sC/KuOoF26r22M/XDvtO2mNMGVM9YXtNGyYY7JgpnY7nRUREKD169FDKli0rR+meOHEiE/fc+jG2jKkeLF++XM4+WLJkifE2QyLh7Nmz8jtg3rx5FtxD/eBBHGOqB2ynjC3ZD/ZFGVe9YFs1D/bztcG+k/YYU8ZUT9he044JBjuWkU7H+fPnZYJBJCcuXryYafusF4wtY6oHGzZsULp162a8HhcXl+SHVHwHzJgxI9kZDM8/3t7xII4x1QO2U8aW7Af7ooyrXrCtmgf7+dpg30l7jCljqidsr2nHIs92TBQcbdu2LTp06CCvi4STKPIqGIo3R0REyH/j4uKM9wklS5bEhAkT5OO8vLwssv/WjLFlTK2ZoWiwKNBcrVq1JLcZPu/isy2KDsfGxsrbDJ//e/fuyfvz5Mlj94WHtfrMPx9/YkzNhe3UfBhbsjbsizKuesG2qi3287XF33ftMaaMqZ6wvaYdEwx2KKOdjpiYGPj7+yNbtmwW/L+wTowtY2rt7VN8pp2cnIy3+fn5yX8Tn9wWn3dPT0/5+GfPnhlvP3PmDEaPHo0iRYpgzJgxxhPn9owHcYypHrCdMrZkP9gXZVz1gm1V+3iyn69tPDkgS1uMqfYYU/NhbE2XdAgl2fwHRCQHEjP15GLfvn0xbdo0REVFZeKeWz/GljG1dhs2bMDnn3+Opk2bomvXrliwYAHCwsKStOHExAGKuM2QRDh9+jSGDRuGv/76C126dLH75IJWn/kpU6bw+zRRG2RMtcWYmg9jS9aGfVHGVS/YVrXHfr52+PuuPcaUMdUTttf04wwGO+p0rF27FidPnkSBAgXQrFkzvPPOO/LEV3LLcyR3cnH48OHyNY4fP273JxcZW7ZXPVm4cCF69uyJYsWKySl+GzduxKJFi/DPP/+gT58+aNKkifz8G5buEZ9/sZyP+PyL2wMDAzF48GDs3r0bR44cQfny5WHP+H3KmOoB2yljS/aDn3fGVS/YVrXHfr522D61x5gypnrC9ppBJtRrIJ36448/FHd3d6VcuXJKnTp1lJw5c8rirW+//bby33//GR9nKOIaExOjXL9+XfH09FR+/PFHWez19ddfV7y9vZVjx45Z8P/E+jC2jKm1O3r0qJI7d26lX79+xoLsJ0+eVL777jvFy8tLKV++vLJ06dIXCjffuXNHcXNzU7p27aq0bdtWPpaff37mzYHfo4ypnrC9krVhm2Rc9YJtVXvs52uH7VN7jCljqidsrxnHBIONY6eDsdUTtlftrV69WiYKNm7cmOT2qKgoZdWqVYqvr69SsmRJ+bjEHj16pOTPn19xdHRUfHx85N/G3rF9MqZ6wHbK2JL94OedcdULtlXzYD9fG2yf2mNMGVM9YXvVBhMMNo6dDsZWT9hetffTTz/JGUtiJpIhsZDY+vXrZQKhfv36xhkO0dHRSmBgoJzFlDVrVuX06dNm2DP9YftkTPWA7ZSxJfvBzzvjqhdsq+bBfr422D61x5gypnrC9qoNJhhsHDsdjK2esL1qb+vWrTLB0KdPH+MyaIZlkAzmzJmjODk5KSNHjkxy+4oVK5SzZ8+aYa/0ie2TMdUDtlPGluwHP++Mq16wrZoH+/naYPvUHmPKmOoJ26s2mGCwcex0MLZ6wvaqvSdPnigVKlRQ/Pz8lH/++ceYXEicZLh165ass5I9e3YlKCjImIggtk9z42eeMdUTtleyNmyTjKtesK2aB/v52mD71B5jypjqCdurNphgsHHsdDC2esL2mjGXLl1SduzYoUyYMEE5ePCgcvPmTXn7rl27ZPKgVq1actuQXEicSJg1a5ac6XDq1KkM7oXtYvtkTPWA7ZSxJfvBzzvjqhdsqxnHfr75sH0ypnrAdsrYWjsmGGwIOx2MrZ6wvWrrzz//VKpUqaJ4eXnJREGWLFmUXr16KdeuXZP3z5w5U95Xr149ZfPmzUpMTEyS50+aNEnJkSOHsQ6DvWP7ZEz1gO2UsSX7wc8746oXbKvaYz9fO2yf2mNMGVM9YXs1HyYYbAQ7HYytnrC9amvp0qWKh4eH0qFDB2X+/PnK33//rbRo0UImGkRiQbh//74yZcoUxdfXVyldurQyefJkJSIiQt53/PhxpXHjxkrNmjWV4OBgxd6xfTKmesB2ytiS/eDnnXHVC7ZV7bGfrx22T+0xpoypnrC9mhcTDDaAnQ7GVk/YXrV14MABpVixYsonn3yiXL16NUldhaJFi8plkaKjo+VtISEhyl9//aXkz59fJh9EoqFRo0ZKqVKl5OyFkydParx3+sP2yZjqAdspY0v2g593xlUv2Fa1x36+dtg+tceYMqZ6wvZqfkww6Bw7HYytnrC9aisyMlIZPny4UrBgQWXPnj3G2w21Fdq2bav4+/srt2/fTvK8O3fuKEOGDFGaNm2q1K1bVy6ldP78ecXesX0ypnrAdsrYkv3g551x1Qu2Ve2xn68dtk/tMaaMqZ6wvWYOR5BuRUVFYeXKlYiOjsb777+PQoUKydvj4uKQN29eVK5cGUFBQXjw4IG83dvbG+3atUNAQAAGDx6M/Pnzy9do1KgR9u7di/Lly1v4/8h6MLaMqR6IJPHt27fRpk0b1K1bN8ntQoUKFfDs2TOEhYUZ7xPfD7lz58b48eOxefNm7Nq1CzNmzEDJkiVhz/iZZ0z1gO2UsSX7wc8746oXbKvmwX6+Ntg+tceYMqZ6wvaaeZwz8b3IAp2OLVu2pHhy0XBdcHRkromxNS+2V+25ubnh22+/lUlGw+dZfJadnJzkdU9PT/mD6uyc8FUv7o+IiIC7u7vxOrF9mgM/84ypnrC9krVhm2Rc9YJt1TzYz9cG26f2GFPGVE/YXjMPEww6xk4HY6snbK/mIWYrGRiSBYZEg4i5IBIKBufOncNvv/2Gzp07yyQksX2aCz/zjKmesL2StWGbZFz1gm3VfNjPzzi2T+0xpoypnrC9Zh4OXbWBTkfBggVfOLkopHRy8euvv8bJkyctsr96wtgypnonZi6I7wPDjIYzZ85g4MCBmDVrFjw8PCy9e1aHn3nGVA/YThlbsh/8vDOuesG2mvnYz087tk/tMaaMqZ6wvWYOJhhsGDsdjK2esL1qx5BsjImJMS6ZdPnyZXzxxRey5sL27dtRvHhxDd/R9rF9MqZ6wHbK2JL94OedcdULtlVtsZ+vLbZP7TGmjKmesL1qh0sk2WGnQ1x4cpGxtRZsr+YjPvtiBsOJEycwb948mVjYvXs3KlWqZMZ3tS1sn4ypHrCdMrZkP/h5Z1z1gm3VvNjPzxi2T+0xpoypnrC9ao8JBhvGTgdjqydsr9oWMnJwcJA/miLROHToUAQFBWHPnj1MLrB9Wg1+5hlTPWF7JWvDNsm46gXbqrbYz9cW26f2GFPGVE/YXrXDBIMNYqeDsdUTtlftieSC4OnpKWcw3L59G/v372dR53Rg+9QeY8qY6gnbK1kbtknGVS/YVs2D/XxtsH1qjzFlTPWE7VV7rMFgR52OypUrW3rXdI+xZUz1pHHjxmjZsiUOHDjA5EI68TOvPcaUMdUTtleyNmyTjKtesK2aF/v5GcP2qT3GlDHVE7ZX7THBYMPY6WBs9YTtVXsFCxbEX3/9hdKlS5vh1e0L2ydjqgdsp4wt2Q9+3hlXvWBbNQ/287XB9qk9xpQx1RO2V+04KGJeCNmsqKgouLq6Wno3bBJjy5iSfeFnnjHVA7ZTxpbsBz/vjKtesK2SNWP7ZEz1gO2UsbV2TDAQEREREREREREREZHJuEQSERERERERERERERGZjAkGIiIiIiIiIiIiIiIyGRMMRERERERERERERERkMiYYiIiIiIiIiIiIiIjIZEwwEBERERERERERERGRyZhgICIiIiIiIiIiIiIikzHBQEREREREREREREREJmOCgYiIiIiIiIiIiIiITMYEAxERERERERERERERmYwJBiIiIiIiIiIiIiIiMhkTDEREREREREREREREZDImGIiIiIiIiIiIiIiIyGRMMBARERERERERERERkcmYYCAiIiIiIiIiIiIiIpMxwUBERERERERERERERCZjgoGIiIiIiIiIiIiIiEzGBAMREREREREREREREZmMCQYiIiIiIiIiIiIiIjIZEwxERERERERERERERGQyJhiIiIiIiIiIiIiIiAim+j/tsR0TxyYQbQAAAABJRU5ErkJggg==","media_type":"image/png"}}]}]},"uuid":"9af0e9d6-6658-4b7b-8de3-eb1bfe166498","timestamp":"2026-10-30T05:35:05.551Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":117019,"dimensions":{"originalWidth":1560,"originalHeight":585,"displayWidth":1560,"displayHeight":585}}},"sourceToolAssistantUUID":"85290339-556f-4943-8cef-1ee130177a48","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"aee091ca02cfb53f1bd47f3f9f4ccc11ed2056296d5ce256759c315080401a17","message":{"role":"assistant","content":[{"type":"text","text":"Quick look at the figure, then the report."},{"type":"tool_use","id":"toolu_018Q7xaoGvKfF7eAQdJo7hgT","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0011/out/figure1.png"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"45c8e4d4-743b-4e0f-8c74-1c8f69e14c44","timestamp":"2026-10-30T05:35:05.558Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"69179ed1-826e-43a5-b24b-a936cfbf48c0","keep":16,"tail":["aee091ca02cfb53f1bd47f3f9f4ccc11ed2056296d5ce256759c315080401a17","43892b08c5b7f230f7971e323ac238b9d3548355f56c8176cee870c6ccb5f575"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"bbd501ba013db053e5799b92a97b6f152e7d7624e1a6f4ed58e01aa8b25cc500"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"9af0e9d6-6658-4b7b-8de3-eb1bfe166498","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"9af0e9d6-6658-4b7b-8de3-eb1bfe166498","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstmaqoiSNXnHdNdnoZ","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":1289,"cache_read_input_tokens":30220,"output_tokens":4171,"output_tokens_details":{"thinking_tokens":85},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1289},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":588,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXstmFk1wyc1DHwKzjdW","requestRef":"45c8e4d4-743b-4e0f-8c74-1c8f69e14c44","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"66383a52-262a-4c1e-a96d-2c40ef225cf3","timestamp":"2026-10-30T05:35:07.224Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"66383a52-262a-4c1e-a96d-2c40ef225cf3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstmaqoiSNXnHdNdnoZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01H9V2mgUB8pjUTw7WFwPDt1","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth (T1-forecast)\n\n## Question\nCould the year-over-year (YoY) growth of US retail and food services sales (RSAFS), g_m = 100·ln(L_m/L_{m−12}), have been forecast in real time 1 and 3 months beyond the last published month, using only data published at each of 10 month-end origins (2025-10-31 … 2026-07-31)? Does a simple model of my own design beat the no-change (naive) forecast when errors are measured against the first-release value of each target month? And how large are the revisions between first release and today's data for the h = 1 targets?\n\n## Data and exclusions\n- **Real-time design.** The forecast made at origin V uses only `RSAFS_vintage_V.csv` (ALFRED vintage dated V). The target at horizon h is last(V)+h, where last(V) is the last month in that vintage; the actual is `yoy_first_release` from `first_release.csv`. `RSAFS_current.csv` is used only for the revision estimand (d). PAYEMS and UMCSENT files were read and audited but do not enter the chosen model.\n- **Vintage → targets** (last month, h = 1 target, h = 3 target):\n\n| origin V | last(V) | h=1 target | h=3 target |\n|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2025-09 | 2025-11 |\n| 2025-11-30 | 2025-09 | 2025-10 | 2025-12 |\n| 2025-12-31 | 2025-10 | 2025-11 | 2026-01 |\n| 2026-01-31 | 2025-11 | 2025-12 | 2026-02 |\n| 2026-02-28 | 2025-12 | 2026-01 | 2026-03 |\n| 2026-03-31 | 2026-01 | 2026-02 | 2026-04 |\n| 2026-04-30 | 2026-03 | 2026-04 | 2026-06 |\n| 2026-05-31 | 2026-04 | 2026-05 | 2026-07 |\n| 2026-06-30 | 2026-05 | 2026-06 | 2026-08 |\n| 2026-07-31 | 2026-06 | 2026-07 | 2026-09 |\n\n- **Publication delays observed.** The vintages 2025-10-31 through 2026-03-31 all end two months before the origin month (instead of the normal one month), reflecting the delayed Census release calendar in late 2025/early 2026. The 2026-04-30 vintage catches up by adding two months (2026-02 and 2026-03) at once; therefore 2026-03 is never an h = 1 target and 2026-05 is never an h = 3 target, and targets are not equally spaced in time. PAYEMS vintages show similar irregularities (not used).\n- **Revisions.** The current RSAFS file is 3.8–5.6 % lower in level than the first releases for 2024-06…2026-07 (a benchmark/annual revision first visible in the 2026-09-30 vintage); first-release YoY values are computed inside one vintage, so they are internally consistent, but YoY growth has been revised by up to 2.0 pp.\n- **Missing values.** No missing values or gaps in any RSAFS/PAYEMS vintage or the current RSAFS file; UMCSENT is empty for 210 pre-1978 months (irrelevant here). No observations were excluded. All data issues are listed in `results.json → data_issues`.\n\n## Method\n- **Baselines** (from the vintage dated V): naive g_{last}; seasonal naive g_{T−12}; AR(1) by OLS of g_m on a constant and g_{m−1} for 1993-02 ≤ m ≤ last(V), re-estimated at every origin, iterated h steps.\n- **My model — \"base-effect drift\"** (specified before looking at any evaluation result, no estimated parameters). YoY growth at T = last+h is ln L_T − ln L_{T−12}, and ln L_{T−12} is already published at the origin. I forecast ln L_T = ln L_last + h·μ with μ = (ln L_last − ln L_{last−12})/12, the trailing-12-month average monthly log growth. The forecast is 100·(ln L_last + h·μ − ln L_{T−12}) = naive + h·g_last/12 − 100·(ln L_{T−12} − ln L_{last−12}): the naive forecast corrected for the known base effects of the months that drop out of the 12-month window. It uses only the RSAFS vintage V.\n- **Evaluation.** RMSE and MAE over the 10 origins per horizon against first-release YoY. Diebold–Mariano (model vs naive, squared loss): d_t = e²_naive − e²_model, Bartlett/Newey–West long-run variance with truncation lag h−1, no small-sample correction, two-sided normal p-value. Supplementary: Harvey–Leybourne–Newbold-corrected DM with t(9) reference, and a moving-block bootstrap (block length 3, 10 000 draws, seed 20261030) of RMSE_naive − RMSE_model.\n- **Revision estimand (d).** Mean over the 10 h = 1 targets of |g^current_T − yoy_first_release_T|.\n\n## Results\nTable 1 (`out/table1.csv`), percent points of YoY growth, n = 10 per cell:\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 | 0.849 | 1.420 | 1.200 |\n| seasonal naive | 1.675 | 1.307 | 1.316 | 1.066 |\n| AR(1) | 0.941 | 0.798 | 1.187 | 0.953 |\n| base-effect drift (model) | **0.550** | **0.486** | **1.142** | **0.934** |\n\n- Relative RMSE improvement over naive: **44.8 %** at h = 1, **19.6 %** at h = 3.\n- DM (model vs naive): h = 1 stat 2.43, p = 0.015 → `model_better_significant`; h = 3 stat 1.55, p = 0.122 → `model_better_not_significant`.\n- The model has the lowest RMSE and MAE among all four forecasts at both horizons; AR(1) is only marginally better than naive at h = 1, and the seasonal naive is the worst at h = 1.\n- Mean absolute revision of first-release YoY for the h = 1 targets: **0.548 pp** (range 0.17–0.98 pp), i.e. about the same size as the h = 1 model RMSE: today's data differ from the first release by as much as the best real-time forecast does.\n- Figure 1 (`out/figure1.png`) shows actuals and naive, AR(1) and model forecasts. The largest h = 1 miss of every method is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %); at h = 3 the model, like the naive forecast, missed the surge to 6.5–6.7 % in 2026-05/06.\n\n## Uncertainty\nWith only 10 origins, inference is fragile. At h = 1 the DM test rejects equal accuracy at 5 % (p = 0.015); the HLN small-sample correction with a t(9) reference gives p = 0.047, just under 5 %; the model beats naive in 8 of 10 origins and the block-bootstrap 95 % interval of RMSE_naive − RMSE_model is [0.29, 0.67] pp (excluding zero). So the h = 1 gain is reasonably convincing, but it rests on 10 points from a period dominated by publication disruptions and should be read as indicative. At h = 3 the point gain (0.28 pp RMSE) is not significant (DM p = 0.12; HLN p = 0.28; bootstrap interval [−0.14, 0.63]; model wins 6 of 10). In addition, h = 3 errors overlap across origins, and a lag-2 Bartlett long-run variance estimated from 10 observations is itself very noisy; the asymptotic normal reference is unreliable at this sample size. The bootstrap with overlapping blocks of 3 out of 10 observations is also only a rough guide.\n\n## Limitations and open issues\n- 10 origins in one unusual period (delayed releases, catch-up vintage, a large benchmark revision just after the sample); results may not generalise.\n- The model was fixed a priori and not tuned, but it is the only model of my own I evaluated; PAYEMS and UMCSENT were not tested as predictors, so the question of whether they add information remains open.\n- \"First release\" is defined at month-end granularity by the task designer; for 2026-02/2026-03 the first observable value came in the same catch-up vintage.\n- The revision estimand compares with a current vintage that includes a level-shifting benchmark revision; future revisions may change it further.\n- The DM test is reported exactly as specified (no HLN factor); supplementary corrected statistics are in `results.json → supplementary`.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\": \"C1\", \"text\": \"The base-effect drift model has lower RMSE than the naive forecast at h=1 (0.550 vs 0.997 pp; 44.8% improvement) and the Diebold-Mariano test rejects equal accuracy at 5% (p=0.015).\", \"results_keys\": [\"rmse_model_h1\", \"rmse_naive_h1\", \"rel_improvement_rmse_h1\", \"dm_stat_h1\", \"dm_pvalue_h1\", \"conclusion_code_h1\"], \"status\": \"supported\", \"caveat\": \"Only 10 origins; HLN-corrected p=0.047 is borderline.\"},\n {\"id\": \"C2\", \"text\": \"At h=3 the model improves RMSE over naive by 19.6% (1.142 vs 1.420 pp), but the difference is not statistically significant (DM p=0.12).\", \"results_keys\": [\"rmse_model_h3\", \"rmse_naive_h3\", \"rel_improvement_rmse_h3\", \"dm_stat_h3\", \"dm_pvalue_h3\", \"conclusion_code_h3\"], \"status\": \"supported\", \"caveat\": \"Overlapping 3-step errors and n=10 make the long-run variance estimate noisy.\"},\n {\"id\": \"C3\", \"text\": \"The model has the lowest RMSE and MAE of all four forecasts (naive, seasonal naive, AR(1), model) at both horizons.\", \"results_keys\": [\"rmse_model_h1\", \"rmse_ar1_h1\", \"rmse_snaive_h1\", \"rmse_model_h3\", \"rmse_ar1_h3\", \"rmse_snaive_h3\", \"mae_model_h1\", \"mae_model_h3\"], \"status\": \"supported\", \"caveat\": \"Differences versus AR(1) at h=3 are small (1.142 vs 1.187) and untested.\"},\n {\"id\": \"C4\", \"text\": \"The mean absolute revision between first-release and current YoY growth for the h=1 target months is 0.548 pp, about the size of the best h=1 forecast RMSE.\", \"results_keys\": [\"mean_abs_revision_h1_targets\", \"rmse_model_h1\"], \"status\": \"supported\", \"caveat\": \"Current vintage includes a large benchmark level revision; future revisions may change this.\"},\n {\"id\": \"C5\", \"text\": \"PAYEMS and consumer sentiment do not improve real-time forecasts of retail-sales growth.\", \"results_keys\": [], \"status\": \"not_evaluated\", \"caveat\": \"These predictors were not tested in this project.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'))\"; wc -l out/forecasts.csv; ls out","description":"Write report and claims, verify outputs"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1289,"cache_read_input_tokens":30220,"output_tokens":4171,"output_tokens_details":{"thinking_tokens":85},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1289},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXstmFk1wyc1DHwKzjdW","requestRef":"45c8e4d4-743b-4e0f-8c74-1c8f69e14c44","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ed015c6c-29ef-4c35-a55b-68a500b59097","timestamp":"2026-10-30T05:35:40.159Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"ed015c6c-29ef-4c35-a55b-68a500b59097","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01H9V2mgUB8pjUTw7WFwPDt1","type":"tool_result","content":"      81 out/forecasts.csv\nanalysis.py\nclaims.json\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\ntable1.csv","is_error":false}]},"uuid":"70161533-f2ff-4d2e-bd9d-bae296bc1964","timestamp":"2026-10-30T05:35:40.215Z","toolUseResult":{"stdout":"      81 out/forecasts.csv\nanalysis.py\nclaims.json\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"ed015c6c-29ef-4c35-a55b-68a500b59097","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"23bec059e4bc47e29bf46da4c7ab00ed7197545a4fe4287f0ac98012ca80a8ea","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01H9V2mgUB8pjUTw7WFwPDt1","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; cat > out/report.md <<'EOF'\n# Real-time forecasting of US retail-sales YoY growth (T1-forecast)\n\n## Question\nCould the year-over-year (YoY) growth of US retail and food services sales (RSAFS), g_m = 100·ln(L_m/L_{m−12}), have been forecast in real time 1 and 3 months beyond the last published month, using only data published at each of 10 month-end origins (2025-10-31 … 2026-07-31)? Does a simple model of my own design beat the no-change (naive) forecast when errors are measured against the first-release value of each target month? And how large are the revisions between first release and today's data for the h = 1 targets?\n\n## Data and exclusions\n- **Real-time design.** The forecast made at origin V uses only `RSAFS_vintage_V.csv` (ALFRED vintage dated V). The target at horizon h is last(V)+h, where last(V) is the last month in that vintage; the actual is `yoy_first_release` from `first_release.csv`. `RSAFS_current.csv` is used only for the revision estimand (d). PAYEMS and UMCSENT files were read and audited but do not enter the chosen model.\n- **Vintage → targets** (last month, h = 1 target, h = 3 target):\n\n| origin V | last(V) | h=1 target | h=3 target |\n|---|---|---|---|\n| 2025-10-31 | 2025-08 | 2025-09 | 2025-11 |\n| 2025-11-30 | 2025-09 | 2025-10 | 2025-12 |\n| 2025-12-31 | 2025-10 | 2025-11 | 2026-01 |\n| 2026-01-31 | 2025-11 | 2025-12 | 2026-02 |\n| 2026-02-28 | 2025-12 | 2026-01 | 2026-03 |\n| 2026-03-31 | 2026-01 | 2026-02 | 2026-04 |\n| 2026-04-30 | 2026-03 | 2026-04 | 2026-06 |\n| 2026-05-31 | 2026-04 | 2026-05 | 2026-07 |\n| 2026-06-30 | 2026-05 | 2026-06 | 2026-08 |\n| 2026-07-31 | 2026-06 | 2026-07 | 2026-09 |\n\n- **Publication delays observed.** The vintages 2025-10-31 through 2026-03-31 all end two months before the origin month (instead of the normal one month), reflecting the delayed Census release calendar in late 2025/early 2026. The 2026-04-30 vintage catches up by adding two months (2026-02 and 2026-03) at once; therefore 2026-03 is never an h = 1 target and 2026-05 is never an h = 3 target, and targets are not equally spaced in time. PAYEMS vintages show similar irregularities (not used).\n- **Revisions.** The current RSAFS file is 3.8–5.6 % lower in level than the first releases for 2024-06…2026-07 (a benchmark/annual revision first visible in the 2026-09-30 vintage); first-release YoY values are computed inside one vintage, so they are internally consistent, but YoY growth has been revised by up to 2.0 pp.\n- **Missing values.** No missing values or gaps in any RSAFS/PAYEMS vintage or the current RSAFS file; UMCSENT is empty for 210 pre-1978 months (irrelevant here). No observations were excluded. All data issues are listed in `results.json → data_issues`.\n\n## Method\n- **Baselines** (from the vintage dated V): naive g_{last}; seasonal naive g_{T−12}; AR(1) by OLS of g_m on a constant and g_{m−1} for 1993-02 ≤ m ≤ last(V), re-estimated at every origin, iterated h steps.\n- **My model — \"base-effect drift\"** (specified before looking at any evaluation result, no estimated parameters). YoY growth at T = last+h is ln L_T − ln L_{T−12}, and ln L_{T−12} is already published at the origin. I forecast ln L_T = ln L_last + h·μ with μ = (ln L_last − ln L_{last−12})/12, the trailing-12-month average monthly log growth. The forecast is 100·(ln L_last + h·μ − ln L_{T−12}) = naive + h·g_last/12 − 100·(ln L_{T−12} − ln L_{last−12}): the naive forecast corrected for the known base effects of the months that drop out of the 12-month window. It uses only the RSAFS vintage V.\n- **Evaluation.** RMSE and MAE over the 10 origins per horizon against first-release YoY. Diebold–Mariano (model vs naive, squared loss): d_t = e²_naive − e²_model, Bartlett/Newey–West long-run variance with truncation lag h−1, no small-sample correction, two-sided normal p-value. Supplementary: Harvey–Leybourne–Newbold-corrected DM with t(9) reference, and a moving-block bootstrap (block length 3, 10 000 draws, seed 20261030) of RMSE_naive − RMSE_model.\n- **Revision estimand (d).** Mean over the 10 h = 1 targets of |g^current_T − yoy_first_release_T|.\n\n## Results\nTable 1 (`out/table1.csv`), percent points of YoY growth, n = 10 per cell:\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 | 0.849 | 1.420 | 1.200 |\n| seasonal naive | 1.675 | 1.307 | 1.316 | 1.066 |\n| AR(1) | 0.941 | 0.798 | 1.187 | 0.953 |\n| base-effect drift (model) | **0.550** | **0.486** | **1.142** | **0.934** |\n\n- Relative RMSE improvement over naive: **44.8 %** at h = 1, **19.6 %** at h = 3.\n- DM (model vs naive): h = 1 stat 2.43, p = 0.015 → `model_better_significant`; h = 3 stat 1.55, p = 0.122 → `model_better_not_significant`.\n- The model has the lowest RMSE and MAE among all four forecasts at both horizons; AR(1) is only marginally better than naive at h = 1, and the seasonal naive is the worst at h = 1.\n- Mean absolute revision of first-release YoY for the h = 1 targets: **0.548 pp** (range 0.17–0.98 pp), i.e. about the same size as the h = 1 model RMSE: today's data differ from the first release by as much as the best real-time forecast does.\n- Figure 1 (`out/figure1.png`) shows actuals and naive, AR(1) and model forecasts. The largest h = 1 miss of every method is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %); at h = 3 the model, like the naive forecast, missed the surge to 6.5–6.7 % in 2026-05/06.\n\n## Uncertainty\nWith only 10 origins, inference is fragile. At h = 1 the DM test rejects equal accuracy at 5 % (p = 0.015); the HLN small-sample correction with a t(9) reference gives p = 0.047, just under 5 %; the model beats naive in 8 of 10 origins and the block-bootstrap 95 % interval of RMSE_naive − RMSE_model is [0.29, 0.67] pp (excluding zero). So the h = 1 gain is reasonably convincing, but it rests on 10 points from a period dominated by publication disruptions and should be read as indicative. At h = 3 the point gain (0.28 pp RMSE) is not significant (DM p = 0.12; HLN p = 0.28; bootstrap interval [−0.14, 0.63]; model wins 6 of 10). In addition, h = 3 errors overlap across origins, and a lag-2 Bartlett long-run variance estimated from 10 observations is itself very noisy; the asymptotic normal reference is unreliable at this sample size. The bootstrap with overlapping blocks of 3 out of 10 observations is also only a rough guide.\n\n## Limitations and open issues\n- 10 origins in one unusual period (delayed releases, catch-up vintage, a large benchmark revision just after the sample); results may not generalise.\n- The model was fixed a priori and not tuned, but it is the only model of my own I evaluated; PAYEMS and UMCSENT were not tested as predictors, so the question of whether they add information remains open.\n- \"First release\" is defined at month-end granularity by the task designer; for 2026-02/2026-03 the first observable value came in the same catch-up vintage.\n- The revision estimand compares with a current vintage that includes a level-shifting benchmark revision; future revisions may change it further.\n- The DM test is reported exactly as specified (no HLN factor); supplementary corrected statistics are in `results.json → supplementary`.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\": \"C1\", \"text\": \"The base-effect drift model has lower RMSE than the naive forecast at h=1 (0.550 vs 0.997 pp; 44.8% improvement) and the Diebold-Mariano test rejects equal accuracy at 5% (p=0.015).\", \"results_keys\": [\"rmse_model_h1\", \"rmse_naive_h1\", \"rel_improvement_rmse_h1\", \"dm_stat_h1\", \"dm_pvalue_h1\", \"conclusion_code_h1\"], \"status\": \"supported\", \"caveat\": \"Only 10 origins; HLN-corrected p=0.047 is borderline.\"},\n {\"id\": \"C2\", \"text\": \"At h=3 the model improves RMSE over naive by 19.6% (1.142 vs 1.420 pp), but the difference is not statistically significant (DM p=0.12).\", \"results_keys\": [\"rmse_model_h3\", \"rmse_naive_h3\", \"rel_improvement_rmse_h3\", \"dm_stat_h3\", \"dm_pvalue_h3\", \"conclusion_code_h3\"], \"status\": \"supported\", \"caveat\": \"Overlapping 3-step errors and n=10 make the long-run variance estimate noisy.\"},\n {\"id\": \"C3\", \"text\": \"The model has the lowest RMSE and MAE of all four forecasts (naive, seasonal naive, AR(1), model) at both horizons.\", \"results_keys\": [\"rmse_model_h1\", \"rmse_ar1_h1\", \"rmse_snaive_h1\", \"rmse_model_h3\", \"rmse_ar1_h3\", \"rmse_snaive_h3\", \"mae_model_h1\", \"mae_model_h3\"], \"status\": \"supported\", \"caveat\": \"Differences versus AR(1) at h=3 are small (1.142 vs 1.187) and untested.\"},\n {\"id\": \"C4\", \"text\": \"The mean absolute revision between first-release and current YoY growth for the h=1 target months is 0.548 pp, about the size of the best h=1 forecast RMSE.\", \"results_keys\": [\"mean_abs_revision_h1_targets\", \"rmse_model_h1\"], \"status\": \"supported\", \"caveat\": \"Current vintage includes a large benchmark level revision; future revisions may change this.\"},\n {\"id\": \"C5\", \"text\": \"PAYEMS and consumer sentiment do not improve real-time forecasts of retail-sales growth.\", \"results_keys\": [], \"status\": \"not_evaluated\", \"caveat\": \"These predictors were not tested in this project.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'))\"; wc -l out/forecasts.csv; ls out","description":"Write report and claims, verify outputs"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"e87acf3c-1970-447a-b356-62639542c408","timestamp":"2026-10-30T05:35:40.218Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"45c8e4d4-743b-4e0f-8c74-1c8f69e14c44","keep":18,"tail":["23bec059e4bc47e29bf46da4c7ab00ed7197545a4fe4287f0ac98012ca80a8ea","742712ddc75aed2045d8af34cfc742fd9599af2e33f47b6c4373a614fd26fdc0"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a1b28592349fc834abcca599b49b7a15a25998882d4a8a0587223fd2c18135f8"}
{"parentUuid":"70161533-f2ff-4d2e-bd9d-bae296bc1964","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswKeTZCLUFjwWLLZuj","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":4227,"cache_read_input_tokens":31509,"output_tokens":516,"output_tokens_details":{"thinking_tokens":195},"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":4227},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1377,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXswKPpQvs1EH4uXqw4w","requestRef":"e87acf3c-1970-447a-b356-62639542c408","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"04f93318-424c-468e-821a-5844737d7cff","timestamp":"2026-10-30T05:35:42.600Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"04f93318-424c-468e-821a-5844737d7cff","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswKeTZCLUFjwWLLZuj","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Y5xJTa85HiNjzr3TuCY9r1","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python - <<'EOF'\np='out/report.md'; s=open(p).read()\ns=s.replace(\"The largest h = 1 miss of every method is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %)\",\"The model's largest h = 1 miss is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %; error −1.11 pp), while the naive forecast's largest miss is 2026-05 (+1.89 pp, the surge to 6.65 %)\")\nopen(p,'w').write(s)\nEOF\ngrep -n \"largest\" out/report.md","description":"Correct a statement in the report"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4227,"cache_read_input_tokens":31509,"output_tokens":516,"output_tokens_details":{"thinking_tokens":195},"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":4227},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXswKPpQvs1EH4uXqw4w","requestRef":"e87acf3c-1970-447a-b356-62639542c408","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3a8a63d9-5ec9-435d-ab6a-fc050fec15e4","timestamp":"2026-10-30T05:35:44.803Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"3a8a63d9-5ec9-435d-ab6a-fc050fec15e4","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Y5xJTa85HiNjzr3TuCY9r1","type":"tool_result","content":"47:- Figure 1 (`out/figure1.png`) shows actuals and naive, AR(1) and model forecasts. The model's largest h = 1 miss is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %; error −1.11 pp), while the naive forecast's largest miss is 2026-05 (+1.89 pp, the surge to 6.65 %); at h = 3 the model, like the naive forecast, missed the surge to 6.5–6.7 % in 2026-05/06.","is_error":false}]},"uuid":"0891d424-0ee4-4686-8492-d486b94df4cc","timestamp":"2026-10-30T05:35:44.854Z","toolUseResult":{"stdout":"47:- Figure 1 (`out/figure1.png`) shows actuals and naive, AR(1) and model forecasts. The model's largest h = 1 miss is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %; error −1.11 pp), while the naive forecast's largest miss is 2026-05 (+1.89 pp, the surge to 6.65 %); at h = 3 the model, like the naive forecast, missed the surge to 6.5–6.7 % in 2026-05/06.","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3a8a63d9-5ec9-435d-ab6a-fc050fec15e4","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"bde5a6068c677dbe5959a0e331c1266aa7bdde04f1e387a043efe7ea41c57593","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Y5xJTa85HiNjzr3TuCY9r1","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; ~/wp29/venv/bin/python - <<'EOF'\np='out/report.md'; s=open(p).read()\ns=s.replace(\"The largest h = 1 miss of every method is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %)\",\"The model's largest h = 1 miss is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %; error −1.11 pp), while the naive forecast's largest miss is 2026-05 (+1.89 pp, the surge to 6.65 %)\")\nopen(p,'w').write(s)\nEOF\ngrep -n \"largest\" out/report.md","description":"Correct a statement in the report"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"928df810-69b3-4809-915d-4094bc900478","timestamp":"2026-10-30T05:35:44.857Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"e87acf3c-1970-447a-b356-62639542c408","keep":20,"tail":["bde5a6068c677dbe5959a0e331c1266aa7bdde04f1e387a043efe7ea41c57593","d21e89166a3b799178e4ad09b31bed2d2de6c994bb4ed430106a4a347e888991"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"22e6b4fb5fb8df03f18efe9a9cde114cb6c60620d2e9fa1a08f1e8c96417cf8b"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"0891d424-0ee4-4686-8492-d486b94df4cc","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"atis-latch","atis":"","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"parentUuid":"0891d424-0ee4-4686-8492-d486b94df4cc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswfWoQYpZ72rJNfWvV","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":696,"cache_read_input_tokens":35736,"output_tokens":409,"output_tokens_details":{"thinking_tokens":75},"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":696},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":423,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXswfERwW5cCmwkCRcNQ","requestRef":"928df810-69b3-4809-915d-4094bc900478","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bd1f3fa2-e3ef-4d94-aa0f-3ada5b06601a","timestamp":"2026-10-30T05:35:46.220Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"bd1f3fa2-e3ef-4d94-aa0f-3ada5b06601a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswfWoQYpZ72rJNfWvV","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UrnTz1FAz5yjU8Q5voXZxq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; sed -i '' 's|missed the surge to 6.5–6.7 % in 2026-05/06.|under-predicted the 2026-06 surge (actual 6.50 %, model 4.91 %, naive 3.89 %) and over-predicted the 2026-03/04 targets less well than naive.|' out/report.md; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;f=pd.read_csv('out/forecasts.csv');f['e']=f.actual_first_release-f.forecast;print(f[(f.horizon==3)&f.model.isin(['naive','model'])].pivot(index='target_date',columns='model',values='e').round(2))\"","description":"Check h=3 errors to verify wording"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":696,"cache_read_input_tokens":35736,"output_tokens":409,"output_tokens_details":{"thinking_tokens":75},"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":696},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXswfERwW5cCmwkCRcNQ","requestRef":"928df810-69b3-4809-915d-4094bc900478","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4f8bf23b-312f-4b8f-a6c8-2fd7048b617c","timestamp":"2026-10-30T05:35:48.435Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"4f8bf23b-312f-4b8f-a6c8-2fd7048b617c","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UrnTz1FAz5yjU8Q5voXZxq","type":"tool_result","content":"model        model  naive\ntarget_date              \n2025-11-01   -0.69  -1.60\n2025-12-01   -0.79  -1.77\n2026-01-01   -0.68  -0.30\n2026-02-01   -0.27   0.61\n2026-03-01    1.59   1.49\n2026-04-01    2.37   1.65\n2026-06-01    1.59   2.61\n2026-07-01   -0.26   0.13\n2026-08-01   -0.72  -1.43\n2026-09-01   -0.37  -0.41","is_error":false}]},"uuid":"155edc89-ffdc-4318-b8a8-796e661371ba","timestamp":"2026-10-30T05:35:48.646Z","toolUseResult":{"stdout":"model        model  naive\ntarget_date              \n2025-11-01   -0.69  -1.60\n2025-12-01   -0.79  -1.77\n2026-01-01   -0.68  -0.30\n2026-02-01   -0.27   0.61\n2026-03-01    1.59   1.49\n2026-04-01    2.37   1.65\n2026-06-01    1.59   2.61\n2026-07-01   -0.26   0.13\n2026-08-01   -0.72  -1.43\n2026-09-01   -0.37  -0.41","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4f8bf23b-312f-4b8f-a6c8-2fd7048b617c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"5dc26c26695291b9b747659dfcceb3aa490cf2a88d8fff273c58b57a550558b7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01UrnTz1FAz5yjU8Q5voXZxq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; sed -i '' 's|missed the surge to 6.5–6.7 % in 2026-05/06.|under-predicted the 2026-06 surge (actual 6.50 %, model 4.91 %, naive 3.89 %) and over-predicted the 2026-03/04 targets less well than naive.|' out/report.md; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;f=pd.read_csv('out/forecasts.csv');f['e']=f.actual_first_release-f.forecast;print(f[(f.horizon==3)&f.model.isin(['naive','model'])].pivot(index='target_date',columns='model',values='e').round(2))\"","description":"Check h=3 errors to verify wording"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"1ed2e41e-ea04-46a7-8e24-d9da4da5cc2b","timestamp":"2026-10-30T05:35:48.648Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"928df810-69b3-4809-915d-4094bc900478","keep":22,"tail":["5dc26c26695291b9b747659dfcceb3aa490cf2a88d8fff273c58b57a550558b7","05c355014e736fa3b645e03f18f70b09f0da3ae3276da1e6b6fb8f410dcc692c"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9cfc6eaae89897247d5b5c4471948b7d9c0aff97029f16b23a91fb1f3a3b7d25"}
{"parentUuid":"155edc89-ffdc-4318-b8a8-796e661371ba","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswwkMvfZsnyGKu9bUa","type":"message","role":"assistant","content":[{"type":"text","text":"My replacement wording was garbled; fixing it precisely."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":587,"cache_read_input_tokens":36432,"output_tokens":242,"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":587},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXswwUEjX53obGduouxH","requestRef":"1ed2e41e-ea04-46a7-8e24-d9da4da5cc2b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cc78f4ac-ca6e-4367-b2a5-8c0eff030aee","timestamp":"2026-10-30T05:35:49.547Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"cc78f4ac-ca6e-4367-b2a5-8c0eff030aee","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXswwkMvfZsnyGKu9bUa","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DHqHDEDa7nPuA2wjrpthVU","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; sed -i '' 's|and over-predicted the 2026-03/04 targets less well than naive.|and under-predicted the 2026-03 and 2026-04 targets by more than naive (errors +1.59 and +2.37 pp vs +1.49 and +1.65 pp).|' out/report.md; grep -n \"2026-06 surge\" out/report.md","description":"Fix h=3 description in report"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":587,"cache_read_input_tokens":36432,"output_tokens":242,"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":587},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXswwUEjX53obGduouxH","requestRef":"1ed2e41e-ea04-46a7-8e24-d9da4da5cc2b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c54a2f2e-efba-497d-bebb-7c8e88b9deea","timestamp":"2026-10-30T05:35:50.930Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"c54a2f2e-efba-497d-bebb-7c8e88b9deea","isSidechain":false,"promptId":"57fbc69a-7f9f-4ff7-acd0-a445d21d3a03","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DHqHDEDa7nPuA2wjrpthVU","type":"tool_result","content":"47:- Figure 1 (`out/figure1.png`) shows actuals and naive, AR(1) and model forecasts. The model's largest h = 1 miss is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %; error −1.11 pp), while the naive forecast's largest miss is 2026-05 (+1.89 pp, the surge to 6.65 %); at h = 3 the model, like the naive forecast, under-predicted the 2026-06 surge (actual 6.50 %, model 4.91 %, naive 3.89 %) and under-predicted the 2026-03 and 2026-04 targets by more than naive (errors +1.59 and +2.37 pp vs +1.49 and +1.65 pp).","is_error":false}]},"uuid":"7b09aaa7-207d-45be-a324-0294ff7a7800","timestamp":"2026-10-30T05:35:50.961Z","toolUseResult":{"stdout":"47:- Figure 1 (`out/figure1.png`) shows actuals and naive, AR(1) and model forecasts. The model's largest h = 1 miss is 2026-07 (first-release YoY dropped to 4.9 % from 6.5 %; error −1.11 pp), while the naive forecast's largest miss is 2026-05 (+1.89 pp, the surge to 6.65 %); at h = 3 the model, like the naive forecast, under-predicted the 2026-06 surge (actual 6.50 %, model 4.91 %, naive 3.89 %) and under-predicted the 2026-03 and 2026-04 targets by more than naive (errors +1.59 and +2.37 pp vs +1.49 and +1.65 pp).","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c54a2f2e-efba-497d-bebb-7c8e88b9deea","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","hash":"40a0c45da74956f7fa085aaaea7cc3591bbf5b042ccdbc0e82416d668901834e","message":{"role":"assistant","content":[{"type":"text","text":"My replacement wording was garbled; fixing it precisely."},{"type":"tool_use","id":"toolu_01DHqHDEDa7nPuA2wjrpthVU","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0011; sed -i '' 's|and over-predicted the 2026-03/04 targets less well than naive.|and under-predicted the 2026-03 and 2026-04 targets by more than naive (errors +1.59 and +2.37 pp vs +1.49 and +1.65 pp).|' out/report.md; grep -n \"2026-06 surge\" out/report.md","description":"Fix h=3 description in report"}}]}}
{"type":"api-request","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","id":"e6507a31-7ea5-497d-95d9-743c12597357","timestamp":"2026-10-30T05:35:50.964Z","version":"2.1.314","querySource":"sdk","shapeHash":"0980364f748b2b384245c8eb2dadbcb42070d731946f58efd8afe5772ecd0691","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":"1ed2e41e-ea04-46a7-8e24-d9da4da5cc2b","keep":24,"tail":["40a0c45da74956f7fa085aaaea7cc3591bbf5b042ccdbc0e82416d668901834e","4df2adcfd09af0faefd2db6a27ede6165bf58107530d1b1ed02ba1d7c1cef846"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e1393c1619344b754c876569915247f33d52302f704029b2d54c295023dc3879"}
{"parentUuid":"7b09aaa7-207d-45be-a324-0294ff7a7800","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsx7fR2ezLzYJwUrcaM","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":497,"cache_read_input_tokens":37019,"output_tokens":1082,"output_tokens_details":{"thinking_tokens":33},"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":497},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":6482,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsx7N49ckFMWw3mLYMv","requestRef":"e6507a31-7ea5-497d-95d9-743c12597357","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3083f854-6a69-4552-8e29-b198222cac67","timestamp":"2026-10-30T05:35:58.829Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"3083f854-6a69-4552-8e29-b198222cac67","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsx7fR2ezLzYJwUrcaM","type":"message","role":"assistant","content":[{"type":"text","text":"I've finished the project: all required files are in `out/`, and running `out/analysis.py` regenerates them from `data/` (two runs gave the same `results.json`). My model beats the naive no-change forecast at both horizons, but the gain is statistically significant only at one month ahead.\n\n**My model.** I call it \"base-effect drift\" and fixed it before looking at any forecast errors; it has no estimated parameters. Year-over-year growth for a target month is the target level divided by the level 12 months earlier, and that earlier level is already published at each origin. So the model projects the latest published level forward at the average monthly growth of the past 12 months and divides by that known earlier level. It uses only the retail-sales vintage for the origin date.\n\n**Results** (percentage points of growth, 10 origins per horizon, errors measured against the first published value):\n\n| | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 | 0.849 | 1.420 | 1.200 |\n| seasonal naive | 1.675 | 1.307 | 1.316 | 1.066 |\n| AR(1) | 0.941 | 0.798 | 1.187 | 0.953 |\n| my model | 0.550 | 0.486 | 1.142 | 0.934 |\n\n- **One month ahead:** the model's RMSE is 44.8% lower than the naive forecast's. The Diebold–Mariano statistic is 2.43 (p = 0.015), so the improvement is significant. It beats naive in 8 of 10 origins, and a bootstrap 95% interval for the RMSE gap is [0.29, 0.67].\n- **Three months ahead:** RMSE is 19.6% lower than naive, but the difference is not significant (Diebold–Mariano 1.55, p = 0.12; bootstrap interval [−0.14, 0.63]).\n- **Revisions:** for the one-month-ahead target months, growth in today's data differs from the first published value by 0.548 points on average. That is about as large as the model's own one-month error.\n\n**Data issues** (all listed in `results.json`):\n- The vintages from 2025-10-31 to 2026-03-31 end two months before their date instead of the usual one, because of release delays.\n- The 2026-04-30 vintage adds two months at once, so 2026-03 is never a one-month target and 2026-05 is never a three-month target.\n- Today's retail-sales levels are 3.8–5.6% lower than the first published values. This comes from a large revision that first appears in the 2026-09-30 vintage.\n- There are no missing values in any of the retail-sales or employment files.\n\n**Limitations:**\n- With only 10 origins, all in a disrupted period, the test results are fragile. With the standard small-sample correction (reported only as a supplement), the one-month p-value rises to 0.047, which is borderline.\n- I did not test payroll employment or consumer sentiment as predictors, so whether they help is still an open question.\n\nFiles are in `out/`:\n- results.json\n- forecasts.csv\n- table1.csv\n- figure1.png\n- report.md\n- claims.json\n- analysis.py"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":497,"cache_read_input_tokens":37019,"output_tokens":1082,"output_tokens_details":{"thinking_tokens":33},"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":497},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsx7N49ckFMWw3mLYMv","requestRef":"e6507a31-7ea5-497d-95d9-743c12597357","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cf9beacf-6e04-484a-b10b-76651b3f0b6b","timestamp":"2026-10-30T05:36:01.485Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0011","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"cf9beacf-6e04-484a-b10b-76651b3f0b6b","sessionId":"ded65219-c074-4c13-896e-0601969d5f59"}
{"type":"cost-state","sessionId":"ded65219-c074-4c13-896e-0601969d5f59","totalCostUSD":0.5665070000000002,"totalAPIDuration":144472,"totalAPIDurationWithoutRetries":144469,"totalToolDuration":4761,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":149381,"startTime":1793338412129,"modelUsage":{"claude-opus-5-5":{"inputTokens":28,"outputTokens":16463,"thinkingTokens":3076,"cacheReadInputTokens":285375,"cacheCreationInputTokens":36012,"cacheCreationEphemeral5mInputTokens":36012,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.5665070000000002}},"hasUnknownModelCost":false}