1{"type":"atis-latch","atis":"","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:07:26.893Z","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","content":"Review"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:07:26.900Z","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}4{"parentUuid":null,"isSidechain":false,"promptId":"20838864-5fbe-4a95-a35c-7989fd77a0bf","type":"user","message":{"role":"user","content":"Review"},"uuid":"68fe742c-3959-4825-8e22-855e7c27f664","timestamp":"2026-10-30T04:07:26.905Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","timestamp":"2026-10-30T04:07:26.920Z","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/RC0014\nDate: 2026-10-30\n\nYou are an independent scientific reviewer. In the current working directory, `TASK.md` describes a bounded scientific task and the directory `out/` contains the deliverables submitted by another assistant (you have not seen how they were produced and you must not look for their working transcript). There is no network access. Use `~/wp29/venv/bin/python` if you need to re-run or test code. Do not modify any file under `out/` except that you must create `out/review/review.json`.\n\nReview the deliverables against `TASK.md` only. Specifically check:\n1. Does `out/results.json` contain every required key with legitimately computed values? Re-run `out/analysis.py` in a scratch copy if needed and compare.\n2. Are the information-availability rules of `TASK.md` respected by the code (for example no use of future information, no use of forbidden inputs)? Read the code to verify; do not trust the report.\n3. Are the central claims in `out/report.md` and `out/claims.json` supported by the numbers in `out/results.json`, with appropriate uncertainty and caveats? Flag any claim that is stronger than the evidence.\n4. Are counts, exclusions, units, signs and magnitudes internally consistent? Are baseline comparisons present when the task requires them?\n5. Are limitations stated honestly? Is anything declared complete that is not?\n\nYou have no reference answers; do not guess what the \"right\" number is. Report only issues you can justify from the files. Write `out/review/review.json` as {\"verdict\": \"accept\"|\"revise\", \"issues\": [{\"id\": \"R1\", \"severity\": \"critical\"|\"major\"|\"minor\", \"location\": \"<file or key>\", \"issue\": \"...\", \"suggested_fix\": \"...\"}], \"summary\": \"...\"}. Use \"revise\" if there is at least one critical or major issue. Be concise and specific. End with a one-paragraph plain-text summary.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}6{"type":"api-request-blob","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","id":"9354355d-3dcd-40d9-a5cb-5cd54141c95a","timestamp":"2026-10-30T04:07:26.920Z","version":"2.1.314","querySource":"sdk","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["99833769e4310fc124186eb9e97416cea64dc8ececb015cbe8928bf0c2bd9984","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5bd1f98f2de30c336846adc1e6ec8e41792c7031e75f1f0316d843b946641434"}8{"parentUuid":"68fe742c-3959-4825-8e22-855e7c27f664","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"8a9bf8bf-c649-419d-b609-5d25891817a6","timestamp":"2026-10-30T04:07:26.911Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"8a9bf8bf-c649-419d-b609-5d25891817a6","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"dddc83a0-e0de-4770-b8b6-b14d236a7d3b","timestamp":"2026-10-30T04:07:26.911Z","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/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"dddc83a0-e0de-4770-b8b6-b14d236a7d3b","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":"dc96fc8b-4e1d-46ee-b432-2121ed462909","timestamp":"2026-10-30T04:07:26.912Z","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/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}12{"parentUuid":"dc96fc8b-4e1d-46ee-b432-2121ed462909","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmDGGwEBWkfkdMCxwC8","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01ST1VL2b3TPxr2quiww9Rft","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Read task and deliverables"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":716,"cache_read_input_tokens":1504,"output_tokens":104,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":716},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmDFzJzCc8TxpnteRDL","requestRef":"9354355d-3dcd-40d9-a5cb-5cd54141c95a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8af48339-8a62-4b09-9b51-708a5030289e","timestamp":"2026-10-30T04:07:30.949Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"8af48339-8a62-4b09-9b51-708a5030289e","isSidechain":false,"promptId":"20838864-5fbe-4a95-a35c-7989fd77a0bf","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01ST1VL2b3TPxr2quiww9Rft","type":"tool_result","content":"# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 240\ndrwxr-xr-x@ 11 simon-pierreboucher staff 352 oct. 30 00:07 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 00:05 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 6378 oct. 30 00:06 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 2001 oct. 30 00:07 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 329 oct. 30 00:06 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 89238 oct. 30 00:06 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 5735 oct. 30 00:07 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 2029 oct. 30 00:06 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 00:07 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 00:06 state\n-rw-r--r--@ 1 simon-pierreboucher staff 565 oct. 30 00:06 table1.csv\n{\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 rows have negative training_hours (min -7.585), which is impossible\",\n \"handling\": \"excluded from main analysis (exclusions.csv step 3); sensitivity estimate including them reported (sensitivity_all_rows_*)\"\n },\n {\n \"issue\": \"training_hours strongly correlated with pre-programme skill_index (r=0.68), and skill_index strongly negatively related to growth: confounding\",\n \"handling\": \"adjusted for skill_index (selection-on-observables model)\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null,\n \"naive_estimate\": -0.13169790632300882,\n \"naive_se\": 0.014619618827634278,\n \"naive_ci_low\": -0.1603518326928757,\n \"naive_ci_high\": -0.10304397995314195,\n \"baseline_metric\": 3.8601022336733584,\n \"model_metric\": 1.9758571828823268,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"effect_se_conventional\": 0.0098410870694658,\n \"skill_index_coefficient\": -4.624620879345756,\n \"skill_index_se\": 0.07816357249116873,\n \"conclusion\": \"positive_effect\",\n \"corr_skill_hours\": 0.677572028059802,\n \"sensitivity_all_rows_estimate\": 0.25222449623309495,\n \"sensitivity_all_rows_ci_low\": 0.23364628735208254,\n \"sensitivity_all_rows_ci_high\": 0.27080270511410737,\n \"sensitivity_all_rows_naive_estimate\": -0.13518960504279864,\n \"sensitivity_quad_skill_estimate\": 0.25383792381516485,\n \"sensitivity_quad_skill_ci_low\": 0.23454311105575676,\n \"sensitivity_quad_skill_ci_high\": 0.27313273657457293,\n \"diag_interaction_coef\": -0.00032835690944043455,\n \"diag_interaction_pvalue\": 0.9564572077696775,\n \"diag_hours_sq_coef\": 0.00010325698359789468,\n \"diag_hours_sq_pvalue\": 0.8626346335499105,\n \"r2_naive\": 0.06821334219243413,\n \"r2_adjusted\": 0.7558650404794334\n}[\n {\"id\":\"C1\",\"text\":\"The unadjusted association between training hours and next-year productivity growth is negative: -0.132 pp per hour, 95% CI [-0.160, -0.103].\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by skill_index.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one more training hour raises productivity growth by 0.254 pp (robust 95% CI [0.234, 0.273]); conclusion positive_effect.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal only under selection on observables with skill_index as the sole confounder and linear homogeneous effect.\"},\n {\"id\":\"C3\",\"text\":\"The sign reversal is explained by confounding: skill_index is positively correlated with training hours and has a strongly negative coefficient on growth.\",\"results_keys\":[\"corr_skill_hours\",\"skill_index_coefficient\"],\"status\":\"supported\",\"caveat\":\"Mechanical omitted-variable-bias decomposition, not a test of the full causal structure.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits much better than the baseline (RMSE 1.976 vs 3.860 pp).\",\"results_keys\":[\"model_metric\",\"baseline_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; better fit does not by itself validate causal identification.\"},\n {\"id\":\"C5\",\"text\":\"The estimate is robust to including the 12 negative-hours rows and to adding skill^2; no evidence of interaction or curvature in hours.\",\"results_keys\":[\"sensitivity_all_rows_estimate\",\"sensitivity_quad_skill_estimate\",\"diag_interaction_pvalue\",\"diag_hours_sq_pvalue\"],\"status\":\"supported\",\"caveat\":\"Limited set of specification checks; unobserved confounding untestable.\"},\n {\"id\":\"C6\",\"text\":\"12 rows with impossible negative training hours were excluded, leaving 1188 of 1200 firms analysed.\",\"results_keys\":[\"n_analysed\",\"n_input_rows\",\"data_issues\"],\"status\":\"supported\",\"caveat\":\"Cause of negative values unknown.\"}\n]","is_error":false}]},"uuid":"00a53edc-3337-4a61-94a9-82256fbd016c","timestamp":"2026-10-30T04:07:31.031Z","toolUseResult":{"stdout":"# F6-conf-04 — Does workforce training raise productivity growth? A mini-project on simulated firm data\n\n## Scientific question\nA one-year training programme offered firms a variable number of training hours per employee. Using the simulated firm-level data provided, estimate the effect of one additional training hour per employee on productivity growth in the following year. The estimand is the causal effect of `training_hours` on `productivity_growth` (percentage points per hour) under a selection-on-observables assumption: conditional on the pre-programme information in the file, training hours are as good as randomly assigned, and the effect is linear and homogeneous. Report both the unadjusted association (the required baseline) and the estimate that targets the estimand, with uncertainty. The chain required is: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report.\n\n## Inputs\n- `data/firms.csv` — simulated data (generated for this exercise; it is not observed data). One row per firm. Columns: `firm_id` (integer), `skill_index` (standardised index of the workforce's baseline skill, measured in the year *before* the programme), `training_hours` (hours of training per employee received during the programme year), `productivity_growth` (percent change in labour productivity in the year *after* the programme year). Rows are in random order.\n\n## Information-availability rules\n- Use only `data/firms.csv`. No other variables exist; nothing needs to be imputed.\n- The \"unadjusted\" model is the OLS regression of `productivity_growth` on `training_hours` with an intercept only.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `naive_estimate` | number | pp per hour | OLS slope of the unadjusted model (baseline) |\n| `naive_ci_low`, `naive_ci_high` | number | pp per hour | 95% confidence interval for the unadjusted slope |\n| `baseline_metric` | number | percentage points | RMSE of the unadjusted model's residuals, sqrt(mean(e²)) |\n| `model_metric` | number | percentage points | RMSE of the residuals of the model that targets the estimand |\n| `effect_estimate` | number | pp per hour | estimate of the estimand (coefficient on `training_hours` in the model you justify) |\n| `effect_se` | number | pp per hour | its standard error (conventional or heteroskedasticity-robust; state which) |\n| `effect_ci_low`, `effect_ci_high` | number | pp per hour | 95% confidence interval for the effect |\n| `skill_index_coefficient` | number or null | pp per index unit | coefficient on `skill_index` in the model that targets the estimand (null if that model does not include it) |\n| `conclusion` | string | — | one of the codes below, based on `effect_ci_low`/`effect_ci_high` |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — scatter of `productivity_growth` against `training_hours` with the unadjusted fitted line and the fitted line of the model that targets the estimand (evaluated at the mean of any other regressor), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per model with columns `model`, `estimate`, `se`, `ci_low`, `ci_high` (header + at least two data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 240\ndrwxr-xr-x@ 11 simon-pierreboucher staff 352 oct. 30 00:07 .\ndrwxr-xr-x 7 simon-pierreboucher staff 224 oct. 30 00:05 ..\n-rw-r--r--@ 1 simon-pierreboucher staff 6378 oct. 30 00:06 analysis.py\n-rw-r--r--@ 1 simon-pierreboucher staff 2001 oct. 30 00:07 claims.json\n-rw-r--r--@ 1 simon-pierreboucher staff 329 oct. 30 00:06 exclusions.csv\n-rw-r--r--@ 1 simon-pierreboucher staff 89238 oct. 30 00:06 figure1.png\n-rw-r--r--@ 1 simon-pierreboucher staff 5735 oct. 30 00:07 report.md\n-rw-r--r--@ 1 simon-pierreboucher staff 2029 oct. 30 00:06 results.json\ndrwxr-xr-x 2 simon-pierreboucher staff 64 oct. 30 00:07 review\ndrwxr-xr-x@ 8 simon-pierreboucher staff 256 oct. 30 00:06 state\n-rw-r--r--@ 1 simon-pierreboucher staff 565 oct. 30 00:06 table1.csv\n{\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": null,\n \"data_issues\": [\n {\n \"issue\": \"12 rows have negative training_hours (min -7.585), which is impossible\",\n \"handling\": \"excluded from main analysis (exclusions.csv step 3); sensitivity estimate including them reported (sensitivity_all_rows_*)\"\n },\n {\n \"issue\": \"training_hours strongly correlated with pre-programme skill_index (r=0.68), and skill_index strongly negatively related to growth: confounding\",\n \"handling\": \"adjusted for skill_index (selection-on-observables model)\"\n }\n ],\n \"n_input_rows\": {\n \"firms.csv\": 1200\n },\n \"n_analysed\": 1188,\n \"random_seed\": null,\n \"naive_estimate\": -0.13169790632300882,\n \"naive_se\": 0.014619618827634278,\n \"naive_ci_low\": -0.1603518326928757,\n \"naive_ci_high\": -0.10304397995314195,\n \"baseline_metric\": 3.8601022336733584,\n \"model_metric\": 1.9758571828823268,\n \"effect_estimate\": 0.25353820594501253,\n \"effect_se\": 0.009812212326345536,\n \"effect_se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_ci_low\": 0.2343066231767153,\n \"effect_ci_high\": 0.27276978871330976,\n \"effect_se_conventional\": 0.0098410870694658,\n \"skill_index_coefficient\": -4.624620879345756,\n \"skill_index_se\": 0.07816357249116873,\n \"conclusion\": \"positive_effect\",\n \"corr_skill_hours\": 0.677572028059802,\n \"sensitivity_all_rows_estimate\": 0.25222449623309495,\n \"sensitivity_all_rows_ci_low\": 0.23364628735208254,\n \"sensitivity_all_rows_ci_high\": 0.27080270511410737,\n \"sensitivity_all_rows_naive_estimate\": -0.13518960504279864,\n \"sensitivity_quad_skill_estimate\": 0.25383792381516485,\n \"sensitivity_quad_skill_ci_low\": 0.23454311105575676,\n \"sensitivity_quad_skill_ci_high\": 0.27313273657457293,\n \"diag_interaction_coef\": -0.00032835690944043455,\n \"diag_interaction_pvalue\": 0.9564572077696775,\n \"diag_hours_sq_coef\": 0.00010325698359789468,\n \"diag_hours_sq_pvalue\": 0.8626346335499105,\n \"r2_naive\": 0.06821334219243413,\n \"r2_adjusted\": 0.7558650404794334\n}[\n {\"id\":\"C1\",\"text\":\"The unadjusted association between training hours and next-year productivity growth is negative: -0.132 pp per hour, 95% CI [-0.160, -0.103].\",\"results_keys\":[\"naive_estimate\",\"naive_ci_low\",\"naive_ci_high\"],\"status\":\"supported\",\"caveat\":\"Association only; confounded by skill_index.\"},\n {\"id\":\"C2\",\"text\":\"Adjusting for pre-programme skill_index, one more training hour raises productivity growth by 0.254 pp (robust 95% CI [0.234, 0.273]); conclusion positive_effect.\",\"results_keys\":[\"effect_estimate\",\"effect_se\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Causal only under selection on observables with skill_index as the sole confounder and linear homogeneous effect.\"},\n {\"id\":\"C3\",\"text\":\"The sign reversal is explained by confounding: skill_index is positively correlated with training hours and has a strongly negative coefficient on growth.\",\"results_keys\":[\"corr_skill_hours\",\"skill_index_coefficient\"],\"status\":\"supported\",\"caveat\":\"Mechanical omitted-variable-bias decomposition, not a test of the full causal structure.\"},\n {\"id\":\"C4\",\"text\":\"The adjusted model fits much better than the baseline (RMSE 1.976 vs 3.860 pp).\",\"results_keys\":[\"model_metric\",\"baseline_metric\"],\"status\":\"supported\",\"caveat\":\"In-sample fit; better fit does not by itself validate causal identification.\"},\n {\"id\":\"C5\",\"text\":\"The estimate is robust to including the 12 negative-hours rows and to adding skill^2; no evidence of interaction or curvature in hours.\",\"results_keys\":[\"sensitivity_all_rows_estimate\",\"sensitivity_quad_skill_estimate\",\"diag_interaction_pvalue\",\"diag_hours_sq_pvalue\"],\"status\":\"supported\",\"caveat\":\"Limited set of specification checks; unobserved confounding untestable.\"},\n {\"id\":\"C6\",\"text\":\"12 rows with impossible negative training hours were excluded, leaving 1188 of 1200 firms analysed.\",\"results_keys\":[\"n_analysed\",\"n_input_rows\",\"data_issues\"],\"status\":\"supported\",\"caveat\":\"Cause of negative values unknown.\"}\n]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8af48339-8a62-4b09-9b51-708a5030289e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}14{"type":"api-request-blob","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","hash":"3d87ae37fe9e01e578f53a89f841e362e58a88d1dfe21d9343a13153f024d40c","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01ST1VL2b3TPxr2quiww9Rft","name":"Bash","input":{"command":"cat TASK.md; ls -la out; cat out/results.json; cat out/claims.json","description":"Read task and deliverables"}}]}}15{"type":"api-request","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","id":"60e2d46d-b181-403a-b451-2d883dd48780","timestamp":"2026-10-30T04:07:31.036Z","version":"2.1.314","querySource":"sdk","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","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":"9354355d-3dcd-40d9-a5cb-5cd54141c95a","keep":2,"tail":["3d87ae37fe9e01e578f53a89f841e362e58a88d1dfe21d9343a13153f024d40c","2088cf095ac72aad93182406a17f5952868dcca7fd53ef9359fd98c0200d128b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5db9e385ac5d51dd8eeff3409daa0b6783864795b94e1da27f1ae36bf3cea925"}16{"type":"last-prompt","lastPrompt":"Review","leafUuid":"00a53edc-3337-4a61-94a9-82256fbd016c","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}17{"type":"atis-latch","atis":"","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}18{"parentUuid":"00a53edc-3337-4a61-94a9-82256fbd016c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmDRdFaPW5gCsLbaEst","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":4254,"cache_read_input_tokens":2220,"output_tokens":176,"output_tokens_details":{"thinking_tokens":59},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4254},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":420,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmDRJu44HSwPXkatUGh","requestRef":"60e2d46d-b181-403a-b451-2d883dd48780","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3c514dab-22f7-4221-b7cd-cfd003dae8cf","timestamp":"2026-10-30T04:07:32.780Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}19{"parentUuid":"3c514dab-22f7-4221-b7cd-cfd003dae8cf","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmDRdFaPW5gCsLbaEst","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JxV3mLcSHxj6TFdj3cmZq6","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/table1.csv out/exclusions.csv; ls out/state","description":"Read code, report, tables"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4254,"cache_read_input_tokens":2220,"output_tokens":176,"output_tokens_details":{"thinking_tokens":59},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4254},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmDRJu44HSwPXkatUGh","requestRef":"60e2d46d-b181-403a-b451-2d883dd48780","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f3650023-d247-4d02-a666-29a5b3faaa6e","timestamp":"2026-10-30T04:07:33.375Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"f3650023-d247-4d02-a666-29a5b3faaa6e","isSidechain":false,"promptId":"20838864-5fbe-4a95-a35c-7989fd77a0bf","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JxV3mLcSHxj6TFdj3cmZq6","type":"tool_result","content":"\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# ---- exclusions -------------------------------------------------------------\nexcl = []\nd = raw.copy()\ndef step(name, rule, mask, why):\n global d\n nb = len(d); d = d[mask(d)].copy(); na = len(d)\n excl.append(dict(step=name, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\nstep(\"1\", \"drop rows with missing values in any column\", lambda x: x.notna().all(axis=1),\n \"complete cases required (none expected)\")\nstep(\"2\", \"drop duplicated firm_id\", lambda x: ~x.firm_id.duplicated(), \"one row per firm\")\nstep(\"3\", \"drop training_hours < 0\", lambda x: x.training_hours >= 0,\n \"negative hours of training are logically impossible; treated as invalid treatment records\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nn_neg = int((raw.training_hours < 0).sum())\n\n# ---- models -----------------------------------------------------------------\nCOV = \"HC1\" # heteroskedasticity-robust SEs\ndef fit(formula, data):\n m = smf.ols(formula, data).fit(cov_type=COV)\n ci = m.conf_int(0.05).loc[\"training_hours\"]\n rmse = float(np.sqrt(np.mean(m.resid ** 2)))\n return m, float(m.params[\"training_hours\"]), float(m.bse[\"training_hours\"]), float(ci[0]), float(ci[1]), rmse\n\nm0, b0, se0, l0, h0, rmse0 = fit(\"productivity_growth ~ training_hours\", d)\nm1, b1, se1, l1, h1, rmse1 = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity: all raw rows (including negative hours)\n_, bs, ses, ls, hs, _ = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\n_, bn_all, sen_all, ln_all, hn_all, _ = fit(\"productivity_growth ~ training_hours\", raw)\n# diagnostics (not the estimand): quadratic in skill / hours, interaction\n_, bq, seq, lq, hq, rmseq = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\nmi = smf.ols(\"productivity_growth ~ training_hours * skill_index\", d).fit(cov_type=COV)\nmh = smf.ols(\"productivity_growth ~ training_hours + I(training_hours**2) + skill_index\", d).fit(cov_type=COV)\nmconv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\nif l1 > 0: concl = \"positive_effect\"\nelif h1 < 0: concl = \"negative_effect\"\nelse: concl = \"no_detectable_effect\"\n\ntable = pd.DataFrame([\n dict(model=\"unadjusted OLS (growth ~ hours), HC1\", estimate=b0, se=se0, ci_low=l0, ci_high=h0),\n dict(model=\"adjusted OLS (growth ~ hours + skill_index), HC1 [main]\", estimate=b1, se=se1, ci_low=l1, ci_high=h1),\n dict(model=\"sensitivity: adjusted OLS incl. 12 negative-hours rows, HC1\", estimate=bs, se=ses, ci_low=ls, ci_high=hs),\n dict(model=\"sensitivity: adjusted OLS + skill_index^2, HC1\", estimate=bq, se=seq, ci_low=lq, ci_high=hq),\n])\ntable.to_csv(f\"{OUT}/table1.csv\", index=False)\n\n# ---- figure -------------------------------------------------------------------\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.35, color=\"grey\", label=\"firms (analysed)\")\nxs = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(xs, m0.params[\"Intercept\"] + b0 * xs, color=\"C0\", lw=2, label=f\"unadjusted: slope {b0:.3f}\")\nsk = d.skill_index.mean()\nax.plot(xs, m1.params[\"Intercept\"] + b1 * xs + m1.params[\"skill_index\"] * sk, color=\"C3\", lw=2,\n label=f\"adjusted for skill_index (at mean): slope {b1:.3f}\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours\")\nax.legend(fontsize=8)\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120); plt.close(fig)\n\nres = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": [\n {\"issue\": f\"{n_neg} rows have negative training_hours (min {raw.training_hours.min():.3f}), which is impossible\",\n \"handling\": \"excluded from main analysis (exclusions.csv step 3); sensitivity estimate including them reported (sensitivity_all_rows_*)\"},\n {\"issue\": \"training_hours strongly correlated with pre-programme skill_index (r=%.2f), and skill_index strongly negatively related to growth: confounding\" % d[[\"skill_index\",\"training_hours\"]].corr().iloc[0,1],\n \"handling\": \"adjusted for skill_index (selection-on-observables model)\"},\n ],\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(len(d)),\n \"random_seed\": None,\n \"naive_estimate\": b0, \"naive_se\": se0, \"naive_ci_low\": l0, \"naive_ci_high\": h0,\n \"baseline_metric\": rmse0,\n \"model_metric\": rmse1,\n \"effect_estimate\": b1, \"effect_se\": se1, \"effect_se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_ci_low\": l1, \"effect_ci_high\": h1,\n \"effect_se_conventional\": float(mconv.bse[\"training_hours\"]),\n \"skill_index_coefficient\": float(m1.params[\"skill_index\"]),\n \"skill_index_se\": float(m1.bse[\"skill_index\"]),\n \"conclusion\": concl,\n \"corr_skill_hours\": float(d[[\"skill_index\", \"training_hours\"]].corr().iloc[0, 1]),\n \"sensitivity_all_rows_estimate\": bs, \"sensitivity_all_rows_ci_low\": ls, \"sensitivity_all_rows_ci_high\": hs,\n \"sensitivity_all_rows_naive_estimate\": bn_all,\n \"sensitivity_quad_skill_estimate\": bq, \"sensitivity_quad_skill_ci_low\": lq, \"sensitivity_quad_skill_ci_high\": hq,\n \"diag_interaction_coef\": float(mi.params[\"training_hours:skill_index\"]),\n \"diag_interaction_pvalue\": float(mi.pvalues[\"training_hours:skill_index\"]),\n \"diag_hours_sq_coef\": float(mh.params[\"I(training_hours ** 2)\"]),\n \"diag_hours_sq_pvalue\": float(mh.pvalues[\"I(training_hours ** 2)\"]),\n \"r2_naive\": float(m0.rsquared), \"r2_adjusted\": float(m1.rsquared),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\nprint(json.dumps({k: res[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\n# F6-conf-04 — Training hours and productivity growth (simulated firm data)\n\n## Question\nWhat is the effect of one more training hour per employee during the programme year on productivity growth in the following year, measured in percentage points per hour? We assume selection on observables given the pre-programme `skill_index`, and a linear, homogeneous effect. As required, we also report the unadjusted association as the baseline.\n\n## Data and exclusions\n- The only input is `data/firms.csv`, with 1200 rows (`n_input_rows`) and 4 columns. It has no missing values, no duplicated `firm_id`, and its SHA-256 matches the bundle (details in `out/state/data_audit.md`).\n- **Data issue:** 12 firms have negative `training_hours` (minimum −7.585). Negative training hours are impossible, so these rows are excluded from the main analysis (`out/exclusions.csv`, step 3). A sensitivity analysis keeps them in (`data_issues`).\n- After exclusions, 1188 firms are analysed (`n_analysed`). The arithmetic is 1200 − 0 − 0 − 12 = 1188.\n- **Confounding:** `skill_index` is strongly correlated with `training_hours` (r = 0.68 in the analysed sample, `corr_skill_hours`). The skill–growth correlation was −0.79 in the audit, which was run on all 1200 rows. In short, higher-skill firms train more and grow less.\n\n## Method\n- **Baseline:** OLS of `productivity_growth` on `training_hours` with an intercept.\n- **Main model:** OLS of `productivity_growth` on `training_hours` and `skill_index`. `skill_index` was measured the year before the programme, so it is a legitimate pre-treatment control, and it is the only observed confounder. Under the stated assumptions, the coefficient on `training_hours` identifies the estimand.\n- **Standard errors:** HC1 heteroskedasticity-robust (`effect_se_type`). 95% CIs use the normal approximation. Each RMSE is sqrt(mean(e²)) over the analysed sample.\n- **Diagnostics (not the estimand):**\n - an added skill² term;\n - an hours × skill interaction;\n - an hours² term;\n - a refit that includes the 12 excluded rows.\n- No randomness is used (`random_seed` = null). `out/analysis.py` produces all outputs: `results.json`, `table1.csv`, `figure1.png` and `exclusions.csv`.\n\n## Results\n- **Unadjusted association:** −0.132 pp per hour (`naive_estimate`), 95% CI [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`). The RMSE is 3.860 pp (`baseline_metric`).\n- **Adjusted effect (main estimate):** +0.254 pp per hour (`effect_estimate`), robust SE 0.0098 (`effect_se`), 95% CI [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`). The RMSE is 1.976 pp (`model_metric`).\n- **Skill coefficient:** −4.62 pp per index unit (`skill_index_coefficient`).\n- **Conclusion:** `positive_effect` (`conclusion`). The adjusted interval lies entirely above zero.\n- **Sign reversal:** the unadjusted slope is negative because of omitted-variable bias. Training is concentrated in high-skill firms, and those firms have lower subsequent growth.\n- Table 1 (`out/table1.csv`) lists both models and the sensitivity fits. Figure 1 (`out/figure1.png`) shows the scatter with the unadjusted line and the adjusted line, evaluated at mean skill.\n\n## Uncertainty\n- The robust 95% CI for the effect is [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`). The conventional SE, 0.00984 (`effect_se_conventional`), is almost identical to the robust SE, 0.00981 (`effect_se`).\n- The estimate barely changes under the sensitivity checks:\n - **Including the 12 negative-hours rows:** 0.252, CI [0.234, 0.271] (`sensitivity_all_rows_estimate`, `sensitivity_all_rows_ci_low`, `sensitivity_all_rows_ci_high`).\n - **Adding skill²:** 0.254, CI [0.235, 0.273] (`sensitivity_quad_skill_estimate`, `sensitivity_quad_skill_ci_low`, `sensitivity_quad_skill_ci_high`).\n- Neither the hours × skill interaction (p = 0.96, `diag_interaction_pvalue`) nor the hours² term (p = 0.86, `diag_hours_sq_pvalue`) is significant, so the data show no evidence against linearity or homogeneity.\n- These intervals cover sampling uncertainty only. They do not cover identification uncertainty.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n - **Unobserved confounding.** The result depends on the assumption that, once `skill_index` is held fixed, nothing else drives both training and growth. Examples would be management quality, sector or firm size. The data cannot test this. Because adjusting for the one observed confounder reversed the sign, the estimate is clearly very sensitive to confounding. A second omitted confounder of similar strength could move it substantially.\n - **Measurement error in `skill_index`.** If the index measures true skill with noise, the adjustment is incomplete. Residual confounding would then push the estimate back toward the negative unadjusted slope, so the true effect could be larger than reported.\n - **The negative-hours rows.** The 12 rows suggest the treatment variable may be coded with error (for example, noise or unclipped values). Classical measurement error in hours would attenuate the estimate. The cause was not established; the rows were excluded, and including them makes little difference (`sensitivity_all_rows_estimate`).\n- **What was not checked:**\n - non-linear functional forms beyond the quadratic and interaction terms;\n - effect heterogeneity in dimensions other than skill;\n - outliers and influence (no leverage diagnostics were run);\n - spillovers between firms;\n - whether \"the following year\" is the right horizon (persistence or fade-out of the effect cannot be studied).\n- **External validity:** the data are simulated. The number is an estimate of the parameter within this exercise and says nothing about real training programmes.\nmodel,estimate,se,ci_low,ci_high\n\"unadjusted OLS (growth ~ hours), HC1\",-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\n\"adjusted OLS (growth ~ hours + skill_index), HC1 [main]\",0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\n\"sensitivity: adjusted OLS incl. 12 negative-hours rows, HC1\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\n\"sensitivity: adjusted OLS + skill_index^2, HC1\",0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values in any column,1200,1200,0,complete cases required (none expected)\n2,drop duplicated firm_id,1200,1200,0,one row per firm\n3,drop training_hours < 0,1200,1188,12,negative hours of training are logically impossible; treated as invalid treatment records\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","is_error":false}]},"uuid":"7739d556-6888-42e0-b5d8-a59a3f7e2602","timestamp":"2026-10-30T04:07:33.410Z","toolUseResult":{"stdout":"\"\"\"Replication entry point for F6-conf-04. Run from workspace root:\n ~/wp29/venv/bin/python out/analysis.py\nReads only data/firms.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nimport statsmodels.formula.api as smf\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"\nos.makedirs(OUT, exist_ok=True)\nraw = pd.read_csv(\"data/firms.csv\")\nn_raw = len(raw)\n\n# ---- exclusions -------------------------------------------------------------\nexcl = []\nd = raw.copy()\ndef step(name, rule, mask, why):\n global d\n nb = len(d); d = d[mask(d)].copy(); na = len(d)\n excl.append(dict(step=name, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\nstep(\"1\", \"drop rows with missing values in any column\", lambda x: x.notna().all(axis=1),\n \"complete cases required (none expected)\")\nstep(\"2\", \"drop duplicated firm_id\", lambda x: ~x.firm_id.duplicated(), \"one row per firm\")\nstep(\"3\", \"drop training_hours < 0\", lambda x: x.training_hours >= 0,\n \"negative hours of training are logically impossible; treated as invalid treatment records\")\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\nn_neg = int((raw.training_hours < 0).sum())\n\n# ---- models -----------------------------------------------------------------\nCOV = \"HC1\" # heteroskedasticity-robust SEs\ndef fit(formula, data):\n m = smf.ols(formula, data).fit(cov_type=COV)\n ci = m.conf_int(0.05).loc[\"training_hours\"]\n rmse = float(np.sqrt(np.mean(m.resid ** 2)))\n return m, float(m.params[\"training_hours\"]), float(m.bse[\"training_hours\"]), float(ci[0]), float(ci[1]), rmse\n\nm0, b0, se0, l0, h0, rmse0 = fit(\"productivity_growth ~ training_hours\", d)\nm1, b1, se1, l1, h1, rmse1 = fit(\"productivity_growth ~ training_hours + skill_index\", d)\n# sensitivity: all raw rows (including negative hours)\n_, bs, ses, ls, hs, _ = fit(\"productivity_growth ~ training_hours + skill_index\", raw)\n_, bn_all, sen_all, ln_all, hn_all, _ = fit(\"productivity_growth ~ training_hours\", raw)\n# diagnostics (not the estimand): quadratic in skill / hours, interaction\n_, bq, seq, lq, hq, rmseq = fit(\"productivity_growth ~ training_hours + skill_index + I(skill_index**2)\", d)\nmi = smf.ols(\"productivity_growth ~ training_hours * skill_index\", d).fit(cov_type=COV)\nmh = smf.ols(\"productivity_growth ~ training_hours + I(training_hours**2) + skill_index\", d).fit(cov_type=COV)\nmconv = smf.ols(\"productivity_growth ~ training_hours + skill_index\", d).fit()\n\nif l1 > 0: concl = \"positive_effect\"\nelif h1 < 0: concl = \"negative_effect\"\nelse: concl = \"no_detectable_effect\"\n\ntable = pd.DataFrame([\n dict(model=\"unadjusted OLS (growth ~ hours), HC1\", estimate=b0, se=se0, ci_low=l0, ci_high=h0),\n dict(model=\"adjusted OLS (growth ~ hours + skill_index), HC1 [main]\", estimate=b1, se=se1, ci_low=l1, ci_high=h1),\n dict(model=\"sensitivity: adjusted OLS incl. 12 negative-hours rows, HC1\", estimate=bs, se=ses, ci_low=ls, ci_high=hs),\n dict(model=\"sensitivity: adjusted OLS + skill_index^2, HC1\", estimate=bq, se=seq, ci_low=lq, ci_high=hq),\n])\ntable.to_csv(f\"{OUT}/table1.csv\", index=False)\n\n# ---- figure -------------------------------------------------------------------\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d.training_hours, d.productivity_growth, s=8, alpha=0.35, color=\"grey\", label=\"firms (analysed)\")\nxs = np.linspace(d.training_hours.min(), d.training_hours.max(), 100)\nax.plot(xs, m0.params[\"Intercept\"] + b0 * xs, color=\"C0\", lw=2, label=f\"unadjusted: slope {b0:.3f}\")\nsk = d.skill_index.mean()\nax.plot(xs, m1.params[\"Intercept\"] + b1 * xs + m1.params[\"skill_index\"] * sk, color=\"C3\", lw=2,\n label=f\"adjusted for skill_index (at mean): slope {b1:.3f}\")\nax.set_xlabel(\"training hours per employee (programme year)\")\nax.set_ylabel(\"productivity growth, following year (%)\")\nax.set_title(\"Productivity growth vs training hours\")\nax.legend(fontsize=8)\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=120); plt.close(fig)\n\nres = {\n \"task_id\": \"F6-conf-04\",\n \"feasibility\": \"complete\",\n \"feasibility_reason\": None,\n \"data_issues\": [\n {\"issue\": f\"{n_neg} rows have negative training_hours (min {raw.training_hours.min():.3f}), which is impossible\",\n \"handling\": \"excluded from main analysis (exclusions.csv step 3); sensitivity estimate including them reported (sensitivity_all_rows_*)\"},\n {\"issue\": \"training_hours strongly correlated with pre-programme skill_index (r=%.2f), and skill_index strongly negatively related to growth: confounding\" % d[[\"skill_index\",\"training_hours\"]].corr().iloc[0,1],\n \"handling\": \"adjusted for skill_index (selection-on-observables model)\"},\n ],\n \"n_input_rows\": {\"firms.csv\": int(n_raw)},\n \"n_analysed\": int(len(d)),\n \"random_seed\": None,\n \"naive_estimate\": b0, \"naive_se\": se0, \"naive_ci_low\": l0, \"naive_ci_high\": h0,\n \"baseline_metric\": rmse0,\n \"model_metric\": rmse1,\n \"effect_estimate\": b1, \"effect_se\": se1, \"effect_se_type\": \"HC1 heteroskedasticity-robust\",\n \"effect_ci_low\": l1, \"effect_ci_high\": h1,\n \"effect_se_conventional\": float(mconv.bse[\"training_hours\"]),\n \"skill_index_coefficient\": float(m1.params[\"skill_index\"]),\n \"skill_index_se\": float(m1.bse[\"skill_index\"]),\n \"conclusion\": concl,\n \"corr_skill_hours\": float(d[[\"skill_index\", \"training_hours\"]].corr().iloc[0, 1]),\n \"sensitivity_all_rows_estimate\": bs, \"sensitivity_all_rows_ci_low\": ls, \"sensitivity_all_rows_ci_high\": hs,\n \"sensitivity_all_rows_naive_estimate\": bn_all,\n \"sensitivity_quad_skill_estimate\": bq, \"sensitivity_quad_skill_ci_low\": lq, \"sensitivity_quad_skill_ci_high\": hq,\n \"diag_interaction_coef\": float(mi.params[\"training_hours:skill_index\"]),\n \"diag_interaction_pvalue\": float(mi.pvalues[\"training_hours:skill_index\"]),\n \"diag_hours_sq_coef\": float(mh.params[\"I(training_hours ** 2)\"]),\n \"diag_hours_sq_pvalue\": float(mh.pvalues[\"I(training_hours ** 2)\"]),\n \"r2_naive\": float(m0.rsquared), \"r2_adjusted\": float(m1.rsquared),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n json.dump(res, f, indent=2)\nprint(json.dumps({k: res[k] for k in [\"naive_estimate\", \"effect_estimate\", \"effect_ci_low\", \"effect_ci_high\", \"conclusion\", \"n_analysed\"]}, indent=1))\n# F6-conf-04 — Training hours and productivity growth (simulated firm data)\n\n## Question\nWhat is the effect of one more training hour per employee during the programme year on productivity growth in the following year, measured in percentage points per hour? We assume selection on observables given the pre-programme `skill_index`, and a linear, homogeneous effect. As required, we also report the unadjusted association as the baseline.\n\n## Data and exclusions\n- The only input is `data/firms.csv`, with 1200 rows (`n_input_rows`) and 4 columns. It has no missing values, no duplicated `firm_id`, and its SHA-256 matches the bundle (details in `out/state/data_audit.md`).\n- **Data issue:** 12 firms have negative `training_hours` (minimum −7.585). Negative training hours are impossible, so these rows are excluded from the main analysis (`out/exclusions.csv`, step 3). A sensitivity analysis keeps them in (`data_issues`).\n- After exclusions, 1188 firms are analysed (`n_analysed`). The arithmetic is 1200 − 0 − 0 − 12 = 1188.\n- **Confounding:** `skill_index` is strongly correlated with `training_hours` (r = 0.68 in the analysed sample, `corr_skill_hours`). The skill–growth correlation was −0.79 in the audit, which was run on all 1200 rows. In short, higher-skill firms train more and grow less.\n\n## Method\n- **Baseline:** OLS of `productivity_growth` on `training_hours` with an intercept.\n- **Main model:** OLS of `productivity_growth` on `training_hours` and `skill_index`. `skill_index` was measured the year before the programme, so it is a legitimate pre-treatment control, and it is the only observed confounder. Under the stated assumptions, the coefficient on `training_hours` identifies the estimand.\n- **Standard errors:** HC1 heteroskedasticity-robust (`effect_se_type`). 95% CIs use the normal approximation. Each RMSE is sqrt(mean(e²)) over the analysed sample.\n- **Diagnostics (not the estimand):**\n - an added skill² term;\n - an hours × skill interaction;\n - an hours² term;\n - a refit that includes the 12 excluded rows.\n- No randomness is used (`random_seed` = null). `out/analysis.py` produces all outputs: `results.json`, `table1.csv`, `figure1.png` and `exclusions.csv`.\n\n## Results\n- **Unadjusted association:** −0.132 pp per hour (`naive_estimate`), 95% CI [−0.160, −0.103] (`naive_ci_low`, `naive_ci_high`). The RMSE is 3.860 pp (`baseline_metric`).\n- **Adjusted effect (main estimate):** +0.254 pp per hour (`effect_estimate`), robust SE 0.0098 (`effect_se`), 95% CI [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`). The RMSE is 1.976 pp (`model_metric`).\n- **Skill coefficient:** −4.62 pp per index unit (`skill_index_coefficient`).\n- **Conclusion:** `positive_effect` (`conclusion`). The adjusted interval lies entirely above zero.\n- **Sign reversal:** the unadjusted slope is negative because of omitted-variable bias. Training is concentrated in high-skill firms, and those firms have lower subsequent growth.\n- Table 1 (`out/table1.csv`) lists both models and the sensitivity fits. Figure 1 (`out/figure1.png`) shows the scatter with the unadjusted line and the adjusted line, evaluated at mean skill.\n\n## Uncertainty\n- The robust 95% CI for the effect is [0.234, 0.273] (`effect_ci_low`, `effect_ci_high`). The conventional SE, 0.00984 (`effect_se_conventional`), is almost identical to the robust SE, 0.00981 (`effect_se`).\n- The estimate barely changes under the sensitivity checks:\n - **Including the 12 negative-hours rows:** 0.252, CI [0.234, 0.271] (`sensitivity_all_rows_estimate`, `sensitivity_all_rows_ci_low`, `sensitivity_all_rows_ci_high`).\n - **Adding skill²:** 0.254, CI [0.235, 0.273] (`sensitivity_quad_skill_estimate`, `sensitivity_quad_skill_ci_low`, `sensitivity_quad_skill_ci_high`).\n- Neither the hours × skill interaction (p = 0.96, `diag_interaction_pvalue`) nor the hours² term (p = 0.86, `diag_hours_sq_pvalue`) is significant, so the data show no evidence against linearity or homogeneity.\n- These intervals cover sampling uncertainty only. They do not cover identification uncertainty.\n\n## Limitations and open issues\n- **What would invalidate the result:**\n - **Unobserved confounding.** The result depends on the assumption that, once `skill_index` is held fixed, nothing else drives both training and growth. Examples would be management quality, sector or firm size. The data cannot test this. Because adjusting for the one observed confounder reversed the sign, the estimate is clearly very sensitive to confounding. A second omitted confounder of similar strength could move it substantially.\n - **Measurement error in `skill_index`.** If the index measures true skill with noise, the adjustment is incomplete. Residual confounding would then push the estimate back toward the negative unadjusted slope, so the true effect could be larger than reported.\n - **The negative-hours rows.** The 12 rows suggest the treatment variable may be coded with error (for example, noise or unclipped values). Classical measurement error in hours would attenuate the estimate. The cause was not established; the rows were excluded, and including them makes little difference (`sensitivity_all_rows_estimate`).\n- **What was not checked:**\n - non-linear functional forms beyond the quadratic and interaction terms;\n - effect heterogeneity in dimensions other than skill;\n - outliers and influence (no leverage diagnostics were run);\n - spillovers between firms;\n - whether \"the following year\" is the right horizon (persistence or fade-out of the effect cannot be studied).\n- **External validity:** the data are simulated. The number is an estimate of the parameter within this exercise and says nothing about real training programmes.\nmodel,estimate,se,ci_low,ci_high\n\"unadjusted OLS (growth ~ hours), HC1\",-0.13169790632300882,0.014619618827634278,-0.1603518326928757,-0.10304397995314195\n\"adjusted OLS (growth ~ hours + skill_index), HC1 [main]\",0.25353820594501253,0.009812212326345536,0.2343066231767153,0.27276978871330976\n\"sensitivity: adjusted OLS incl. 12 negative-hours rows, HC1\",0.25222449623309495,0.00947885217664965,0.23364628735208254,0.27080270511410737\n\"sensitivity: adjusted OLS + skill_index^2, HC1\",0.25383792381516485,0.009844473118691516,0.23454311105575676,0.27313273657457293\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with missing values in any column,1200,1200,0,complete cases required (none expected)\n2,drop duplicated firm_id,1200,1200,0,one row per firm\n3,drop training_hours < 0,1200,1188,12,negative hours of training are logically impossible; treated as invalid treatment records\nchecks.md\ncontract.md\ndata_audit.md\ngate_receipts\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f3650023-d247-4d02-a666-29a5b3faaa6e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}21{"type":"api-request-blob","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","hash":"dfdf9a4e1208183af7152a6a81e25d079f3225a94b47bc87d0c3e573854a2d29","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JxV3mLcSHxj6TFdj3cmZq6","name":"Bash","input":{"command":"cat out/analysis.py; cat out/report.md; cat out/table1.csv out/exclusions.csv; ls out/state","description":"Read code, report, tables"}}]}}22{"type":"api-request","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","id":"5c470625-9e42-4573-9ca0-dc5b08d9a991","timestamp":"2026-10-30T04:07:33.413Z","version":"2.1.314","querySource":"sdk","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","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":"60e2d46d-b181-403a-b451-2d883dd48780","keep":4,"tail":["dfdf9a4e1208183af7152a6a81e25d079f3225a94b47bc87d0c3e573854a2d29","f3459fc3da52a52b0d71971faf66e9c942dafa21a258f6082c3bc00c04b90751"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0c058fd371dee4d813821b28c11111c65c98c3d86c0f318e5acee2d64e37eb55"}23{"type":"last-prompt","lastPrompt":"Review","leafUuid":"7739d556-6888-42e0-b5d8-a59a3f7e2602","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}24{"type":"atis-latch","atis":"","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}25{"parentUuid":"7739d556-6888-42e0-b5d8-a59a3f7e2602","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmDbpgKoHpyg5M3mr6X","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":5802,"cache_read_input_tokens":6474,"output_tokens":511,"output_tokens_details":{"thinking_tokens":62},"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":5802},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":406,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmDbY3yWK2qv8p8gWph","requestRef":"5c470625-9e42-4573-9ca0-dc5b08d9a991","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b1d797e6-e1df-4087-b380-389d8dfe771e","timestamp":"2026-10-30T04:07:35.580Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"b1d797e6-e1df-4087-b380-389d8dfe771e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmDbpgKoHpyg5M3mr6X","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01L9SSpB7TiCnBAnGgaiJeZL","name":"Bash","input":{"command":"S=$(mktemp -d); mkdir $S/out; cp -r data $S/; cp out/analysis.py $S/out/; cd $S && ~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;a=json.load(open('out/results.json'));b=json.load(open('$OLDPWD/out/results.json'))\nprint([k for k in b if a.get(k)!=b[k]])\"; cmp out/table1.csv $OLDPWD/out/table1.csv && echo tableok\ncd $OLDPWD; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;d=pd.read_csv('data/firms.csv');print(d.describe().T);print(d.dtypes)\nprint(d[d.training_hours<0]); print((d.training_hours==0).sum())\nimport numpy as np\nfor c in ['skill_index','productivity_growth','training_hours']:\n z=(d[c]-d[c].mean())/d[c].std(); print(c,(abs(z)>4).sum())\n\"","description":"Rerun analysis in scratch and audit data"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5802,"cache_read_input_tokens":6474,"output_tokens":511,"output_tokens_details":{"thinking_tokens":62},"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":5802},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmDbY3yWK2qv8p8gWph","requestRef":"5c470625-9e42-4573-9ca0-dc5b08d9a991","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4c24a41b-ae09-46d3-8caf-16a1a0ccb470","timestamp":"2026-10-30T04:07:38.821Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}27{"parentUuid":"4c24a41b-ae09-46d3-8caf-16a1a0ccb470","isSidechain":false,"promptId":"20838864-5fbe-4a95-a35c-7989fd77a0bf","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01L9SSpB7TiCnBAnGgaiJeZL","type":"tool_result","content":"[]\ntableok\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object\n firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\n0\nskill_index 0\nproductivity_growth 0\ntraining_hours 0","is_error":false}]},"uuid":"6e0c2fd9-aa57-4101-bb36-6b363a75bb23","timestamp":"2026-10-30T04:07:40.075Z","toolUseResult":{"stdout":"[]\ntableok\n count mean ... 75% max\nfirm_id 1200.0 1600.500000 ... 1900.250 2200.0000\nskill_index 1200.0 -0.001467 ... 0.680 2.9623\ntraining_hours 1200.0 19.945735 ... 25.502 51.7700\nproductivity_growth 1200.0 7.083012 ... 9.987 19.3889\n\n[4 rows x 8 columns]\nfirm_id int64\nskill_index float64\ntraining_hours float64\nproductivity_growth float64\ndtype: object\n firm_id skill_index training_hours productivity_growth\n127 1276 -2.4212 -0.133 19.1087\n372 1425 -1.6253 -4.006 8.9215\n518 1463 -2.1087 -5.383 10.3419\n521 1755 -1.2527 -1.335 7.7379\n688 1248 -1.2167 -3.000 5.3598\n772 1280 -0.9997 -2.351 6.7451\n880 1927 -2.0138 -6.388 10.4497\n893 2037 -2.9950 -2.887 13.2197\n1009 1483 -2.8599 -5.672 13.5980\n1082 1353 -1.8188 -1.514 10.0230\n1140 1247 -2.9694 -7.585 13.3106\n1150 1886 -2.4104 -2.726 15.8426\n0\nskill_index 0\nproductivity_growth 0\ntraining_hours 0","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4c24a41b-ae09-46d3-8caf-16a1a0ccb470","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}28{"type":"api-request-blob","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","hash":"3b1f7a7b59f91450efb7c480e618a6d448d5f974b84553bd59d326bfade95473","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01L9SSpB7TiCnBAnGgaiJeZL","name":"Bash","input":{"command":"S=$(mktemp -d); mkdir $S/out; cp -r data $S/; cp out/analysis.py $S/out/; cd $S && ~/wp29/venv/bin/python out/analysis.py >/dev/null && ~/wp29/venv/bin/python -c \"\nimport json;a=json.load(open('out/results.json'));b=json.load(open('$OLDPWD/out/results.json'))\nprint([k for k in b if a.get(k)!=b[k]])\"; cmp out/table1.csv $OLDPWD/out/table1.csv && echo tableok\ncd $OLDPWD; ~/wp29/venv/bin/python -c \"\nimport pandas as pd;d=pd.read_csv('data/firms.csv');print(d.describe().T);print(d.dtypes)\nprint(d[d.training_hours<0]); print((d.training_hours==0).sum())\nimport numpy as np\nfor c in ['skill_index','productivity_growth','training_hours']:\n z=(d[c]-d[c].mean())/d[c].std(); print(c,(abs(z)>4).sum())\n\"","description":"Rerun analysis in scratch and audit data"}}]}}29{"type":"api-request","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","id":"76e174a0-8205-4a66-9389-f04384ae3bb5","timestamp":"2026-10-30T04:07:40.079Z","version":"2.1.314","querySource":"sdk","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","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":"5c470625-9e42-4573-9ca0-dc5b08d9a991","keep":6,"tail":["3b1f7a7b59f91450efb7c480e618a6d448d5f974b84553bd59d326bfade95473","6132c2d24257eaed98faf6a67125a0927bf463a8d999005a5a0183b9d50d3d3e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"cfb9dd159bd05edf7895d19a12c506e034ba31beb4ac4f83a7d13e92e72dca60"}30{"type":"tools-used","tools":["Bash","Read"],"sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}31{"parentUuid":"6e0c2fd9-aa57-4101-bb36-6b363a75bb23","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmE6HgvSgaJbj9n6Jj5","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":1009,"cache_read_input_tokens":12276,"output_tokens":317,"output_tokens_details":{"thinking_tokens":236},"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":1009},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2011,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmE5zaax2bmohkiaAkg","requestRef":"76e174a0-8205-4a66-9389-f04384ae3bb5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f0ccc1f3-7144-487d-a348-d80167474886","timestamp":"2026-10-30T04:07:44.584Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"f0ccc1f3-7144-487d-a348-d80167474886","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmE6HgvSgaJbj9n6Jj5","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BacyZC2WruHE5y4K8t9cwy","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0014/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":1009,"cache_read_input_tokens":12276,"output_tokens":317,"output_tokens_details":{"thinking_tokens":236},"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":1009},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmE5zaax2bmohkiaAkg","requestRef":"76e174a0-8205-4a66-9389-f04384ae3bb5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ca9417a5-4e73-4543-9e30-b4b45574b6ed","timestamp":"2026-10-30T04:07:45.021Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}33{"parentUuid":"ca9417a5-4e73-4543-9e30-b4b45574b6ed","isSidechain":false,"promptId":"20838864-5fbe-4a95-a35c-7989fd77a0bf","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BacyZC2WruHE5y4K8t9cwy","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"aee9fad8-8fc7-4e74-bea6-9f1851a40ff4","timestamp":"2026-10-30T04:07:45.029Z","toolUseResult":{"type":"image","file":{"base64":"iVBORw0KGgoAAAANSUhEUgAAA0gAAAJYCAYAAABYRsb0AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAASdAAAEnQB3mYfeAABAABJREFUeJzsnQeYHVX5/9/dzZZstqT3QhIS0gNJKCEQILQAIUGK8BcQOyqgoqKIioAKIvoDBVGRjooNJSEQQgu9lxAS0kjvPduyfe//+ZzkLLM3M7fOrft+nmeyuXPnzpw5c2bm/Z73Pe/JCQQCAVEURVEURVEURVEkV+tAURRFURRFURRlPyqQFEVRFEVRFEVRDqACSVEURVEURVEU5QAqkBRFURRFURRFUQ6gAklRFEVRFEVRFOUAKpAURVEURVEURVEOoAJJURRFURRFURTlACqQFEVRFEVRFEVRDqACSVEURVEURVEU5QAqkBRFURRFURRFUQ6gAklRFEVRFEVRFOUAKpAURVEURVEURVEOoAJJURRFURRFURTlACqQFEVRFEVRFEVRDqACSVEURVEURVEU5QAqkBRFURRFURRFUQ6gAklRFEVRFEVRFOUAKpAURVEURVEURVEOoAJJURRFURRFURTlACqQFEXJWNauXSs5OTnyhS98QdIJynTiiSfGtQ/Oif1wjkpiOOSQQ8yiRMYNN9xg2uSLL74YV5Xxe/bD/tIJbQ+KolhUICmKEhaMGeeSl5cn3bt3l2nTpsnf//73dleDqTKk0lUQpiuIVOorG9G2oCiKkjg6JHDfiqJkGT/72c/M38bGRlm2bJnMnj1bFixYIO+++6783//9X6qLlzYsXbpUiouL49rHLbfcItdee63069fPt3IpSjxceeWVctFFF8nAgQPj2s9RRx1l7hE6WRRFUdIRFUiKokRMcEjM888/L6eeeqrccccd8q1vfUvDlQ4wYsSIuFtVnz59zKIo6QKCxg9RQ+eBH/eIoihKotAQO0VRYubkk082hk4gEJB33nnnoHEKhN8dffTRUlJS0kY8bdmyRa644gqzrqCgQHr06CHnnnuuvPfee67Hqaqqku9+97vSv39/KSoqMsfEY9XS0hJ1aNWDDz5ovuNvMBs3bjRCb9iwYdKxY0fp2rWr6e3++c9/3mbsxLp168ziDDt0hr0Fj0H6+te/btbhcXPjrbfeMt+ff/75nmOQqNfBgweb/z/00ENtjs25zJ8/3/z/i1/8ousx6uvrWw1c/h8Jf/vb32TChAmmLnr27CmXXnqpbN682bV+neNK3n77bTnrrLNM/TnPgeP+6le/krFjxxojuaysTI4//nj517/+1WZf1dXVpl1MmTKlzfra2lpz/dnnI4880ua7P/7xj2b9/fff3xp+9tJLL5nvnHXlNjaspqZGrrnmGuMZKSwslEMPPVRuvfVW064jgfZIeXfu3On6Pfvi2HfddVfrukWLFsn/+3//z9wDHJN7gLr+zne+Yzy0oQjXFiK9Hnh/v/a1r8moUaPMteA6jxkzRm688Uapq6uLeAySrVfOn/0h7Dmn0aNHywMPPBDxGCTbrpqamuTmm2829yH7GTBggPzwhz+UhoaGuNtpJETbHmi/U6dOlfLyclMG2jceYLf7LNT4RLdxh85QyhUrVsiFF15ozjE3N7f1OqxevdrUO+W0zy3KwHNn165dUZ+/oijqQVIUJU6s0RBsiPz2t7+VZ599Vs4++2w56aSTpKKiwqxfs2aNHHfcccaAYQwTRuKGDRvk3//+tzz55JPy2GOPyYwZM1r3g5GBEEOAjR8/Xi6++GLZu3evES3WAPYDwgRPP/102b17tzF2EGz79u2Tjz/+2BhyP/3pT40xS5ghHjPAmLUcfvjhnvu+7LLL5M9//rM8/PDDMmvWrIO+x8iFUGOLMKo479/97nemHs4555w2x2bd0KFDjbFG+TDWnFCvGEvf+973jNEXjl//+tfGKO3SpYspP/vjeiJagvft5I033jDGIdf4S1/6kjGaEQ8Yt9Qv1wxBgUCmfv/zn/8Yo2/hwoXGKAYENcIU4Yg4Li0tNetfe+21VqMT7yWGsIXPQFuhfFwnxAJC1oaGQvDYMcQI5aI9nnHGGdKhQwd5/PHHTXgjIsH5Wy+on+uuu04effRRueqqq1yvL3Xwuc99rlUc0XHAPTNz5kwjdiorK+WTTz6Ru+++W37xi19Ifn5+zG0hkusBGP2Eyh577LFGQHG+1DHtHeP7ueeeM+MNI4Hy0DbYN0Kf68Q9zTEx5qmjSKGeXnnlFXM9EG5PPfWUaY/bt28/SHDF2k69iLY9cN2pXzoeKDdtd968eWY9nRbPPPNMa33Hw6pVq0ybGT58uHkG0llA3dDZdOSRR5r2c+aZZ8p5551nyslzlk4EwiK7desW9/EVpd0RUBRFCQOPCrfHxbPPPhvIyckxy9q1a826n/3sZ2bb4uLiwPvvv3/Qb0477TTz/S9+8Ys261977bVAXl5eoGvXroGqqqrW9b/85S/N9ueee26gubm5df3q1asDXbp0Md9ddtllbfZ1wgknuJYXHnjgAfMdfy319fWBQw45xKz/29/+dtBvNmzY0ObzoEGDzOIF+6EMToYPHx4oKCgI7Nq1q836uro6cx49e/YMNDY2tq7nnNjPmjVrWtfxf7fztdx2223m+zvvvPOg72ydLF++PBCOVatWBTp06BDo3r17YP369a3rW1paAhdddJFre1iwYEHr+j/96U8H7fPmm282351xxhltznPbtm2mLvmONmD56U9/atbNnTu3dd21115r2si0adMC/fv3b11Pu6DdDBkyxPWcvbDHpUz79u1rU6by8nKzNDQ0hK0v2kdubm5g4sSJB3339ttvt7Zfy3e/+12z7vHHHz9o+927d7dp516Eawvhroe9zlzTYH7yk5+Y3/3jH/9os97e2+zbiT3Ol7/85UBTU1Pr+iVLlpjrNXLkSNeysT+36zVhwoQ290l1dXVg6NChpo63bNkSVzsNRbTt4fXXXzfbDxgwoE25aN8zZsww3/H8CvdsiOSeZ/nRj3500G9+//vfm+/uuOOOg76j3pznoShK5GiInaIoEUPPMsuPf/xj00s8ffp040HCkzJo0KA22xLyccQRRxwUwkaPKqErP/jBD9p8Ry823iQ8OP/9739b19NjTA80PcX8tdDrTjicHzzxxBMmlIXefNvL74TQvnihdxsvCl6G4GPv2bPH9ArTWx0PhNcRgoa3ysny5cuN5wZPHj3Q4SA0kjAnvCGEN1nweBAiF8qrgAfj8ssvP2g9oW/8ntBI53kSLoR3Du69997W9XiCnJ4h+/+JEyca7x5tiZAjwPtEu7G/iZbf//73JjTJWSY8fXg9qbtw0D44NiGiS5YscfUOunlQnMe04AlxtvN48boeMGTIENcQtKuvvtr8xQMSKYRMcm2dbYPQPTw5JGQgbDJS8GwRJmbp1KmTuT8IqcXT60c79aM90KbhJz/5ifTu3bt1Pe0bDzrX0dmm46FXr14hvZlubYl6c1uvKEp4VCApihIxjE1gIaTkhRdeMONHCONwy2BHiFQwH3zwgfnL79xCiAi5c25HeBVhR2RyI3wsmHjnGrK8+eab5i8hNYni85//vDGYrMEcTXhdpBBK89nPflYWL14sr7/+euv6e+65x/xlTEIk2PonLCsYhLDTGI3kutvr2LdvX9fB+cHXHSZPnmyMOyuQME7ff/99I0Ts9vY72qJzP9FAGBZjN4Kx54h4jQR7/ZzX1wpiDGzCnyyEFGK8ExpHuyD0khCqROB2PZxjbQhrJESLeqB9Ii5sSNamTZsiPg7jhQj5irceYdKkSRHtJ5526kd7oD16tTs6IhDOhLrZ8OJ4IJTSLTSWTh3C+ghZJbyOex2RHun4OUVR3FGBpChKxPDSZaEnlx57Bnlfcsklrts6e1Qt1lDwys5m1zOewbk9vaeRHiMW7PESmVLbehkYS0WPOjCm4umnnza9/OPGjfPlON/85jfNX+tFYiwIRjtG+mc+85mI9hGu3r3W+3XdgXEbGL4fffSR7Nixw4yJaW5uNnU4cuRI8xsrkPiLYR+LQOrcubPreuvl4piRQN0iEP7617+2/mbu3LnmPsEr6fSaIVoYY0N5GYOFdwmjHPEY7GGMF697hLE2HB9vMGNWEG0/+tGPjJfCeioiTebhZz167cttP/G002iOHe740bRrv68jQpAkHHhVGTOGt5BEG6zHE6YoSmyoQFIUJSG4he7YQdNbt251/Q0Djp3b2b/btm1z3d5rPzZEifCbYNyMFWsURdNjHgs2zMp6Gci+RRmjGcAeDgZyE9pIsgZ6u21yBsLvQg38d2I9AV717rXer+tuwYBHkCOAWAgftJnt+A6BjhGP2CBjGiIwVeDtwnvHuZAkIFx4HR4yBBTXiMQIhBlSr4gpDF2/8MriRkZFDGs8X4hQPA+//OUvTQitV0heuhFPO/WDWNq1zdLnRighFSobHx0G//znP819Tggi4YV0Yn3729+W++67L+LzURTlU1QgKYqSNOyYpFdffdXVSMDgBVL2AtnL6FlHuLiFIAWnG3aO4wCy4wXjHMNgOeaYY8xfsk9FAuFR0fSIW+jltV4GDBgMaHqm3cY9eR0Xwh0bLxJeAUK3MHwxrhgTFst1CoascG71GgquIyGSXMeVK1eGve5u45AIo2OcGiLJfod3hvTehIq5jT+KtL78whlmh9eL9oRnMFSGQ8KmOK+bbrqptcffKx28n+dGyKNtk8H4mR0ykfjdTmM9vttziPplnBxjJZ1eKZ5NbuXiOjKWLh54ljBGj6x+1hNJBj5FUaJHBZKiKEmDMDMmliUhgk2VbSGlM4OuMSCcoWB4PhATvPSd8x4R2+8VQmLHXfzlL39psx5D2y2EiVTkpH+eM2eO6/cYOk4Yo4EBTKrdWLwMCIXbb79dPvzwQzM2JVLPB3WD2Fm/fn3I7RBc9FqT2AJjlzpnQH6k2JCwO++8s40xhzeHMKxYjHLSPfN75pdx/p6003aeKbZxgmDiPBAMjKtwiiAbTsd4OOdnJ3YsTbj68gu8W4zFobx/+tOfTBib29gyxoe5tR3r8SDhgV9twQub7jzYuGdOHe61TCAR7TQabHslLTvPAwvH/f73v2+eV1/+8pcPejZxzUhW44R9IOqihcQgbmOcomlLiqIcTHwpkxRFUaIEwxFDEkMZI4EB2XYeJELjyFpn570B5u2hF5RQMQxm5ighFMVOzoioCQZRddtttxnjGRFCNi0yntGjj/hiX04Y78LxTzvtNGN0MX4HrxJeGMYLIaycHi87logsfpQBLwCDqBFa4SDcisxWGHD2c6QwGJsQOkLKyOrFQHA8CQzUdo5hwihiv1ZARhsyhbcHjwZzuXBejE+x88vgtWEdc/lEAwYj9Y944PcIQ+ZBot4Zi0VWw+DB9pwbiTisR8UpkBhjQTnxLLLdCSeccNAx2Z794yXheAhUfuecP8lvSLpAuByiD+Od6xQMwtUmOcHDwHVFAFI/CJ9IvH2RtgUvaKt4Z0mwQogd3hAMd8L+mBMpWaIyHhLRTqMBzx/tluvJuB8ye5I5jutIohTaM8+54PuA7IBkxaO8ZOtDMNPhQ1v38op7QZIcnlcci/qg/XBPkB2T55JzrjZFUaIgipTgiqK0U6KZT8RrrhQnGzduDHz9618PDBw4MJCfnx/o1q1bYNasWWbOGDcqKioCV199daBv376BwsLCwGGHHRb4zW9+Y+ZB8ZoLZvHixWY+k5KSkkCnTp3M3CMvvvii6zxIlnXr1gW+8Y1vmDmRKBdz6xx11FEHzWXC/CKUv1+/fmael+AyhJrrBA499FCzDftnDqZI50SBlStXmjlW+C3zT3mdy8KFC813ffr0aTPvUDQ8/PDDgcMPP9zUOXPNXHzxxYFNmzYFRo8ebeaEiWRuGye1tbWmLvl9UVGRuTZTpkwJ/P3vf/f8jZ3npaysrM0cO/C1r33NfMc1coPtmTtm8ODBZr6c4OsSaj6rSNqxG7Qh5uvht1wnN+bPnx/4whe+YOYH4ryYM4x5sq666qrW+cQiIVRbiOR6MHfQ5z73OXNfcT1GjRoVuPXWW017cWvDoeZBimZun3DzILkR6r6Npp2GItb28Oijj5p2THumDNQj87zR3t2YPXu2mTOLbbl2F154obnuscx99uabb5pn0bhx48x8alxH5oyifX300UcRn7uiKG3J4Z9oBJWiKIqS/jz44IPGk8YcLTaEzQ8qKytNdjDG1bzxxhu+7VdR/ETbqaIo8aBjkBRFUbIMwgHthKyxZiRjTAVjaIL3S8gjoYeRpgxXlESi7VRRlESgY5AURVGyBLJ5kZSBcQyMK7nyyitNYoxYYJzW9ddfL6eccoqZJJMxHS+//LIZy4X36KqrrvK9/IoSLdpOFUVJBCqQFEVRsgTmz7nxxhvNwO+vfvWrZvB4rJAAgIHfiCLmVwESCjCxKFnOSHigKKlG26miKIlAxyApiqIoiqIoiqIcQMcgKYqiKIqiKIqiHEAFkqIoiqIoiqIoygFUICmKoiiKoiiKohxABZKiKIqiKIqiKMoBNItdDOzdu9ek0iX1bWFhYSy7UBRFURRFURTFJ+rr62XDhg1ywgknSOfOnePalwqkGEAcnXPOOXFVvKIoiqIoiqIo/vL444/LrFmz4tqHCqQYwHNkL8Chhx4a1wVQFEVRFEVRFCU+PvnkE+PAsHZ6PKhAigEbVoc4Gj16dNwXQVEURVEURVGU+PFj+IsmaVAURVEURVEURcl0gfTOO+/IlVdeaTw4nTp1koEDB8pnP/tZWbFixUHbLl26VKZPny4lJSXStWtXufTSS2XHjh0pKbeiKIqiKIqiKOlLxobY3XrrrfLaa6/JBRdcIOPGjZOtW7fKXXfdJRMmTJA333xTxowZY7bbuHGjTJ06VcrLy+Xmm2+W6upq+c1vfiMfffSRvP3221JQUJDqU1EURVHSjJaWFtm2bZvJisT/FUVRlNSSl5cnXbp0kbKysoQfK2MF0ne/+135+9//3kbgXHjhhTJ27Fj51a9+JX/961/NOkRRTU2NvPfee8bLBEcddZSceuqp8uCDD8rXvva1lJ2DoiiKkn4giNavXy+1tbXmhcySk5OT6mIpiqK0WwKBgOzbt0/q6uqkqKgo4Q6OjBVIxx577EHrhg0bZkLuCKmzPPbYYzJjxoxWcQSnnHKKDB8+XP71r3+pQFIURVHagOcIcURIds+ePVUcKYqipAE4POi8YphMv379EnqsjB2D5KUuebF1797dfN60aZNs375dJk2adNC2eJE++OCDFJRSURRFSWcIq8NrpOJIURQlfSDnQIcOHaShoSHhx8pYD5Ibf/vb34wouummm8znLVu2mL99+vQ5aFvW7d6927wIQ6UDRGAFJ3Qgz7qiKIqSvSF2GlanKIqSfuTm5hqHSKLJGoG0bNkyueKKK2Ty5Mly2WWXmXWESICbACJ+0W4TSiDdfffdcuONNyas3IqiKEr6oWOOFEVR2u+zOSsEEhnszjrrLJOp7j//+Y/p+YOOHTuav3iJgmGQl3MbL775zW+aTHluM/UqiqIoiqIoipJdZPwYpIqKCjnjjDNk79698vTTT0vfvn1bv7OhdTbUzgnrGIAbbrZdYtBJ/OBcDj300ASciaIoiqLERmNjo1x88cXmvcacf7wbeV899NBDKa9S3s+HHHKIbNiwIWnHfPHFF01Pc1NTk6SC4447Tm644YbWgeWDBg1ynadRUZT0JKM9SHiBzj77bPPQee6552TUqFFtvifDRY8ePeTdd9896LfMgXT44YcnsbSKoiiKkhiInliwYIGsXbu2dY6QJUuWpEV1My6YqIsBAwZIex1YztQk3/ve9+SJJ55IdXEURclmD1Jzc7OZ9+iNN96Qf//732bskRvnnXeezJ07t03P1fPPP29EVXDonKIoiqJkIqtWrZIhQ4ZEPIEig5yT4V2prKyUv/zlL+1+So3Pf/7zpiNXvUiKkhlkrECiJ2bOnDkmvI5sdEwM61ws1113nRQXF8tJJ50kd955p9xyyy1GGDGh7Be/+MWUnoOiKIqSvSBAGCPLvB38TZQg+cIXvmC8NHQYEl7HexEIa7v33nvN//EsEXJ23333yfjx4817keiKE088Ua666irT4Yi46t+/v/zjH/+Qjz76yHQ8lpaWmmkxli9f3no85hAkfI/tmVaDuQW9eOaZZ6Rz585tIjwIcWd+wl69epn9jxs3znR0OqGsvLOnTJlizol39quvvtomhI75ELt16yZdunSRadOmycKFC13LwLhhUgNTB04ow3e+852w50S0CrbE0KFDzbGmTp3aZpoQrusPfvAD6d27t4la+dGPfnRQGfjdkUceKf/73/8860pRlDQikKGccMIJ5PjzXJwsXrw4cNpppwWKi4sDnTt3Dlx88cWBrVu3xnxs9scx+KsoiqJkF6tWrTJLPDQ2NgaWLl0aePHFFwPPPPOM+ctn1ieCn/3sZ4EpU6a0WTdo0KDAX/7yF/P/NWvWmPfWscceG1i/fn2gqakpUFdXZ96l5eXlgZdeeinQ3NwcuOOOO8y78swzzzS/qa+vD5x77rnmHQo1NTWB/Pz8wPPPP28+19bWtv7fjR/+8IeB6dOnt1m3YcOGwGOPPRaoqqoKNDQ0BO69995Ahw4d2rxTKeu4ceMCK1euNHX27W9/OzBw4MDW71999dXAa6+9ZspXWVkZ+OpXv2q+5zMsWLDA7MPW96mnnhq47rrrWn+/bt26QF5enrkm4c7psssuC5x88smm3OzvzjvvDPTo0SOwZ88e8/0vf/lLU9dLliwxdfqTn/zEnA/XxMkVV1wROO+88yK+poqiRPd89tM+z1gPEr1HPEO9Fif0Cs2fP98MlNyzZ4/xMNFzpSiKoiiJYOfOnWbi8vz8fPO+4S+fWZ9Krr/+ejMWiGyvNkkRoeh4RZhfBG/Uvn375JJLLjEeqIKCAvnc5z5nxu1aOJelS5eac2HKDLw3XhDhQYZZJ3ipzj33XOMZYl9f/vKXjYfphRdeOChShKRIeH+++tWvGk8cdQh4lvAgUT68ULfeeqv53unpcvKNb3xDHnjggVYvHp41EimMGDEi5Dnt2rXLJLr4wx/+YMpNWa688kpzToTvA/ulrJwDdUpyBjxGwfAb6kNRlPQnYwWSoiiKoqQrzPTOggggXIy/dl0qGTx48EHrnJOpk1DAbV1VVZX5P6F5ZIxlPM1hhx1mQt9+97vfeR6PrHpk1HNCRyWCh7IQ0kYIHgklmJjdiTMrrS2XLceiRYtMkiaSMbEPe17B+7DMnDnTiEJC8xFJhBpefvnlYc/JTgx/9NFHm3LahUnpN27caL7jr7NeOc7AgQMPKgP1QH0oipL+ZHQWO0VRFCW9wRilVx5hQG8/4zvohc92OFeW6upqI474a9elErxE8XL88cebhWiNl156SaZPn268J6eeeupB206cOFH+/ve/t1l37bXXmsnd+S3eLAQk46KCoz9CwVhixlo9/PDDxluD6EJ8eO0D0YIou+eee0wdkBYdz1m4cxo+fHirIHMTPYBnyTm+iSRSbinNGddlx4cpipLeqAdJURRFSZg4ogeesCe78DlVc9MkE4QgoXUY4oSF8ZfPrM9kSDZBQgXmNkLY4E3hr5foPe2000xYGeFrTk8KXhsSLFAvJGOINiU5+8BzZMPWCHELBwKJVOg33nijCSW0YjXUOTF/ESnKr7jiClm3bl2rF2vevHmtcyxedtll8tvf/taIPiamJ2FGcCgd+yZMUSeZV5TMQAWSkhUkK1uUoiiZPw4nGWBcM36GkC272PE0mQwelj/96U8mpTiesfPPP19++ctfmkyxbiBgvvKVr8if//zn1nW/+MUvpLa21rQJxjnRJhhTFA3333+/ETWMPzrmmGMi8swQNkio3YcfftgaXhfJOeEBwxOGh4zjcS1JXW69VT/84Q/NmKoTTjjBeJPwlhKS5wRP18knn9w65klRlPQmh0wNqS5EpkFP15gxY2Tx4sUmAYSSHr3UvGRtGA8v3mwwRhQlk7GD5rkf6ZHndcN9ioHpFa6UDqxevdr8xWBW4ofwNyZmf+WVV1J+3REz77//vjz77LNJOyYJomyyKNq+oiiJeT77aZ+r9ahkPM5eamLRifXnM2ESzEuhKEpqSNdxOEpy4blsw9NSLdhJzvDII48k9bgkmAieg0lRlPRGQ+yUjCdds0UpSnsnW8fhKJnHxRdfbJIukLJcEyUoihIO9SAp0t57qdtrli1FSdY4HLy5en8pqeRvf/ubXgBFUSJGrUAl40HQkCGIHmoWOwYpkl5qt/FL7EvHLymKfyJJQ10VRVGUTEIFktKue6l1/JKiKIqiKIriRAWS0q57qe1YJQYR2/FL1puUbmgooKIoiqIoSuJRgaS0azIly5aGAiqKoiiKoiQHzWKntGsyJctWe55wU1EURVEUJZmoQFLaNZky272mMlcUJR057rjj5IYbbmj9jCf+xRdflHTiJz/5iZx44om+7Iv5jAjHJrmPoijZiwokpd1jxy8xwzt/000cBYcCBgKBtA0FVBSlfcOzyS8xcsghh8i9997ry77aAwjTCRMmSHFxsQwePFj++Mc/htz++eefl5NPPlm6devmKvq4lieddJKJWigrK5MBAwbI1VdfLXV1da3b/N///Z9MnDhRysvLpWfPnjJjxgxZsmRJws5RUZKFCiRFyQAyJRTQj7FWW7duNTPe85fPiqIoSmjWrVsnZ511lnz5y182U1U8+OCDcu2118r//vc/z9906tRJPv/5z8vDDz/s+n1hYaH8/ve/lw0bNkhlZaW888478v7778uPf/zj1m0QS3fccYd5XlOGESNGyCmnnCK1tbV6yZSMRgWSomQAmRIK6EciiuXLl7cufFaRpCixeVvwCjz33HOt3gU+/+c//5Hhw4dLaWmpnHrqqbJp06bW7f/whz/ImDFjjLcAb/qll17aZpwj9+IPfvAD812PHj3kRz/60UHlcB4TI71///5tviccj7A8y1133SVDhw415aHT5wtf+IJZf8YZZ5iOkiuvvNKE7Y0ePbr1Nxj048ePN14L1v/jH/9oc4xHHnlEhg0bZvZ57rnnGsEQbUjzN7/5TXOe7IO6vfPOOz235zxtvfH3oYceOigk7y9/+YuMGjXKbIPXZtWqVa3bNDc3y29/+1sZOXKkOSc8Mnh3ooEycF2vuOIKE1lwwgknyJe+9CVTv14cc8wxctlll7WpWyeMdR07dmybSIXc3FzzbLZcd911cvzxx0vHjh3NQjgjYmnZsmVRlV9R0o3ssa4UJcvJ9gk3dU4qJZ2pa2yW9bv3Jf24A7sWS1F+nm/7w6OAJwDOPPNMY+Bag57ny3//+1/T+YLX4LOf/axcddVV8uijj5rvf/3rX8u//vUveeGFF4yo+cUvfiFvvfWW8RjEwsqVK43gevvtt42wIKQLDwXMmzfPCBMM7q985StthMD1119vykk42euvv27OAyGG8OIzwoDvEVnsh/M4+uijW/fx97//3QggL+FEfbzxxhuyePFi46XH4N+8ebPrto899ph861vfMvVKaOGCBQvknHPOMUKHvxYE0vz58004G9ufffbZsmjRIvNc//nPfy6PP/64WRB2s2fPlpkzZ5rvqedIWLhwoRx11FFt1h155JFtxFqsXHzxxaZs+/btM1Ni8H8vnnnmGeOZQqwpSiajAklRlLQgk+akUtofiKPTbn856cd95uqpMrxXqW/7u+WWW4zxDp/73OfaeBjOO++81v8PGjTIhGg5xckDDzwg3/ve94wnxHqD/vznP8dcFsQBYyoZs8IYULwrU6dODfkbxrwQ4jVp0iTzGVF04YUXGuHE/ykj4gIBAvxFQO3atat1H5w3ixd2vOfHH38skydPNsLRq3PqnnvuMWFteIUAscjnP/3pT20E0k9/+lMzhgduv/1285xDhOF94TPCk8gA+MxnPiPHHnusEaYIxEggBC5YlHAM1sfL3/72N3OdEGx467hWbvD917/+dRNyh0hSlExGQ+wURUkLNBGFoiSevn37tv4fI7aqqqr1M14XDHMG2yNWCLHbvXu3CQGDjRs3msH/lry8PE9jORLYFwY3oob94PGw3qpQXidEWufOnVsXfmM9PMFltMeJhksuuUQuv/xyueaaa4wHCU/Ue++957otnrZgLw8eOMIDvcpA2B775bd0AiFiLrjggjbnhCfMGf7ohPLQgcTC/4HrFewR27Nnj1nvB3RaEdZ4xBFHtBHSFryAiMSbbrqpjahWlExFBZKiKGlBe0lEoSiJAKO7pqam9bNXSJgXCAuMdELqMO4x2hnLA3gPgDA2xtRYEE4Y+ZGWya1cs2bNkqefftqE2CJICOdasWJF63iXYPDk3H333UYM2AVvz1NPPeVaRgj+HA6E3/e//30TPohIYWwQ5XQDr5BzPBHwOVg4OstAeTlfyooYKioqkrlz57Y5J+rNKwsdYYPsg4X/w+GHH94aOml59913jaDxE57LzjFIwHip0047TW677TYzZkxRsgENsVMUJa0SUWAwEFaHRwlxlE2JKJTMhbFAhLul4riRQMgZnhQG3SMsCI+LBoztlpYWc89hsOOpIRzPCfsmmQBhZHhEbr75ZuNh8gLjHA/VP//5TyO+Xn75Zfn3v//dmhQAQxsxQVgd3hAb+odAsWIo2Bj/zne+Y8bsIFpIZoDBTmgX58xnyjht2jR58sknZfr06UZ8IZ6Cx+eEgjFWeF7GjRtn6oKy2TIFg7eEBQFFuNxLL70k991330FjfxivhYjp2rWr8YDxrMNbx/ONsDTGYuFJIwscmeEQO5x/pGN5SG5x6623GlFFiB/i7v777zeLF1xvnrX19fXmM//n2CRn4HzxClVUVMiUKVNMPXzwwQdy4403mpBFC2OvqHOOc/7550dYw4qSAQSUqFm8eDHdaeavoiiKkl2sWrXKLJnExo0bA6eeemqgpKQkcOihhwb++9//mvfUs88+a75fsGCB+dzY2Nj6mwceeCDQr1+/1s+33HJLoHfv3mYfkydPDvzud79r85uGhobAd7/73UDPnj0D3bt3D1x77bWBKVOmBH72s5+17sN5TPjjH/8Y6N+/f6C0tDRw0UUXBa6++mrzG1i0aFHg2GOPDZSVlZnvR48eHXjkkUdafztv3rzAsGHDAuXl5YGxY8e2rv/rX/8amDBhglnfrVu3wAknnBB46aWX2pzX0KFDzXl85jOfCVxxxRVmG+fvO3Xq5FmXjz76qCkL23Tu3DkwderUwNtvv22+W7NmjTnHlStXtm7/l7/8JTBy5EhzvFGjRgXuu+++1u/s9vfcc09gxIgRZpsTTzwxsGLFitZtmpqaAnfccYc5JnVB/U6fPj1qG4NrfPjhhweKiooCgwYNCvzhD39o8z37vPzyy9tsT9mCF+oPXnnllcCkSZNMmSg3dfr9738/UFlZ2bqPQw45JJCbm2vqyrlQx4qS7Oezn/Z5Dv+kWqRlGgwoJeMOGW680mMqiqIomcnq1avN3yFDhqS6KBkFIXd4RPCihEu20F4gtA5vGx45vEaKoiTu+eynfa5jkBRFURRFiRsSGRDqFmlqakVRlHRFBZKiKIqiKHHBeKSzzjrLjLXp16+f1qaiKBmNjn5WFEVRFCUumHCWRWkLk93qSAZFyTzUg6QoiqIoiqIoinIAFUiKoiiKoiiKoigHUIGkKIqiKIqiKIpyABVIiqIoiqIoiqIoB1CBpCiKoiiKoiiKcgDNYqe40tTUJDt37pSGhgYpKCiQ7t27mwkAFUVRFEVRFCWbUQ+S4iqOPvnkE1m+fHnrwmfWK4qiKNnBcccdJzfccEPr55KSEnnxxRclnfjJT34iJ554YshtfvOb30ifPn1M+efOnZuUcn3hC1+QSy65xPP7M844Q37+85+3fs7JyZHnnnvO/J865nMk79Tg/fhxnRPB3//+dzMPVnvhqquu8r1OSQl/7733+rpPJXZUICkHgedo27Ztkp+fL7169TJ/+cx6RVGUVIFBuXXrVlm/fr35q502/lJdXR1WjKSbsbdp0yb5wQ9+IHPmzDHlnzFjhqQD8+bNk5/+9Kdps59EUldXJ9///vfll7/8ZcS/efDBB6V///6SqXBN7rjjDtP+son6+nq54oorTNRQaWmpuZ82bNjguf2KFSvks5/9rLmWbD98+HC57bbb2sz9ZTsE6MCwi9e1r6ysNM+OSDsQEokKJOUgCKtjoRHbRm3XKYqipAL1bCturFmzxhhjRxxxRMwVpO+2+Hj00UeNwXv44YdLe6Fnz55y2mmnyd133y3ZxHe/+1155ZVX5L333jPir2vXrjJz5kxpaWlx3X7Pnj1y/PHHy5tvvmnEzT//+U8jHH/3u98dtO3evXtNJwbLxo0bXff3ne98Rw477DBJB1QgKQfBmCMWGjEvHv7adYqiKO3Rs91SXy/1K1cmfeG4kfCHP/xBxowZI2VlZdK7d2+59NJL29QNAhNPC9/16NFDfvSjHx20D2cYmFsPPyFFhGtZ7rrrLhk6dKjpOeaaEHZmw8Lw8l155ZWmg2306NGtv3n44Ydl/PjxUl5ebtb/4x//aHOMRx55RIYNG2b2ee655xqjyov77rtPTj31VPP/zp07m2NZj8YPf/hDGTx4sHTp0sUYcG+99Vbr7+y5UWf0Vnfr1s11/wsWLJBJkyaZsrLNlClTjEHoxv3332/C/F566SXzGU8c4YHxErwfrtGdd95pysL5jh07Vl599dWorjOG7+c+9znp16+fMfT/3//7f7Jjx47W3v5OnTrJO++8Yz5jAxA6d/bZZ7fxCjh57LHH5PTTT2+z7t///rdMnDjR1D/eCIxsxCxggH/961+XzZs3t3oU/va3v3meP+FsF154oWnbXDfazEcffSSTJ0827eSoo44yQwEszc3N8tvf/lZGjhxprh3leP7551u/X7x4sZx88smmfvj+6KOPlhdeeKH1+7Vr15p6fuihh0xb5RjHHHOMfPzxx23KNn36dPnvf/8r0eB1z7jxxhtvmLZLHdKWr732WuPhsdB2f/azn8m0adNMHXL/z58/v80+nnrqKXN+7IP76ve//73n8bhvHnjgARPSOWjQIFPf//d//2fq67XXXnP9Dfvm+nBdqDM6Ki644AJz70TLE088Ya7rNddcI2lBQImaxYsX85Qwf7ORxsbGwNKlSwMvvvhi4JlnnjF/+cx6RVGUVLBu3TrzPPrwww8DixYtMn/5zHq/WbVqlVmc1K1YEfj4sBFJXzhuJPznP/8JLF++PNDc3BxYu3Zt4KijjgpcdNFFrd//8pe/DAwaNCiwZMmSQF1dXeAnP/lJoEOHDoGf/exnrdvwXnv22WfN/x944IFAv3792hyDbadMmWL+v2LFikDHjh0DH330kflcVVUVeOmll1q35Vh/+ctf2vyefQ4YMCDwzjvvmHK+8sorgdLSUvMXXnvtNVOmOXPmmPcNf4uKigInnHCC53kvWLDAlNv5frryyisDY8aMCaxcuTJQX18f+M1vfhMoKSkJbNiwobUceXl5ga9+9aum3DU1Na777tu3b+D+++8PtLS0mP28/vrrgerqavPdZZddFrj44ovNeXz/+98PDB8+3BzPQpl//OMfu9atW5m9cNvPuHHjzLH4/be//e3AwIEDI77OrDvssMMC3/ve98y5cP6XXHJJ4JRTTmndx69//Wuzz507dwZuvPHGwJAhQwJ79uzxLGOvXr0C//jHP9qsmzdvXmDhwoWBpqamwI4dOwIzZswIHHPMMa3fu7Uvr/MvLy83bYu6vuOOOwLFxcWBM888M7BmzRpzXc4999zAaaed1vobznX8+PGBZcuWmd/897//Nb/55JNPzPe0WZ4d+/btM/XB9mVlZYFt27aZ79kv9XzyyScHNm/eHKitrQ2cd955galTp7YpG+2Y7ahD4FlEWW17Diaae4Z9Uebbb7/dnCO/HTVqlLnezu27d+8eePXVV01buPfeewMFBQWB1atXm+9feOEFU57nnnvO1APH7d+/f+Cvf/2ra/m4XpwP5+xk2LBhgd/97neBSKActE/nc8W2d47ds2fPwLRp04xd6YS2RpujjOHuD7fncyLsc/UgKQdBtrpDDz3UuDntwudEZ7HT8QWKonihnu3QnHfeeSb+Pzc31/T+0tv8zDPPtH5Pz/D3vvc9GTVqlBQWFhpvEL3KscL7AHt9yZIlJrSGHuypU6eG/A290T/+8Y+NV4Zy4o3CM4BHx5YRTwPeCvbP3zPPPDOqchEKhGfpF7/4hXlv0W447yFDhshf//rXNtsSCkS5i4uLXffFb1etWmU8HfwfjwXeFQvRFeecc44JRyLEiOMlA87HvpO/+tWvGm8d3tRIrvOTTz4pVVVVZpwI58L5/+pXvzKeQxv2RA/+kUceabwsv/71r42HCA+dF7t37zaemGDvCt6XvLw840G66aabTB1x7FjaNm2LNoPHZd++fSZBBh4UrgvesLfffrt1+9tvv11uvfVWY7vwm8985jNy7LHHmlBAwNOC57Fjx46tdYT3w+llhOuvv954BYuKiuSLX/xiq1fNYs+Z84eBAwcaj6fTyxrrPYNHjfuZkDPOEe8Pbfqee+5p48n7/Oc/b7yJ7PvLX/6yCXO07Zx6+MY3vmGuI/XAeeO5o424QZkg+Fp36dKl9btQUC7239jYaNqgZcSIEbJw4ULjQSThFx5mPI6ss1BO2jJlTBdUICmucLPhoueG528yxJFmzlMUxQuMLEJSePliDPKXz6xXxIT6YAQSMkVoDCF2GG6EGwHGL2E6FgxXnu+xwr4IdcLYYj8Y1NYA9WLlypXGcMIAswu/QYC4ldEeJxoIK6ytrTVhTE4QFAgJC/XkJYwsJH5YvXq1CdHi94QzOQeOY/ATwoThGo/YjJa+ffu2/t8KNis8wl1nrgH3D+W114BQR4SCs34Yi/Lhhx8awRpubBHjVCoqKtqsI9QQwxyBQXs84YQTzPrt27dHfb7sI/h8g9fZ8+fcMOYJ83K2s9dff701oQLnedFFF5l6oWx8z2+CyxZcz7Qr5/W358z5+33PkBjBrQ1TBhsOafcZfAybVIFrzVggZz0ghrds2eJ6TOoCgsNa9+zZ0/qdFzxnvvSlLxmRSbgiIYQWbEjEMnYk60noQcjiv/71L/M9dUJHBJ066YRObKOk3fgCHtz0zPGZG5qbS1GU9o31bPNMSMX8bPkDB8qQJ+Yk5VjBxw0HRjEGIT3H9JbT4/2///3PjOGxvc2MEWBshdOgCZWdCkOmpqamzTorZCyzZs0yC0YjAg2jEzFhPVnB8Cy/8cYbTa+3G8FlhODP4aBNcP4YXM7eaD5jkFrcyhcM43tIXw30dtPrTRnp6YZTTjnFLGT6+s9//mPGgqSacNeZa4CHkfrwAsP/sssuMx4JjFjGhuDN84JrjlfEwv1JneCBefzxx01b+uCDD2TChAmt7TGS+o8Fng9cf9K9e3lnuH54f/AI0clCmbA7vMZYecF4GbxUduxbJIS6Z5wMGDDACHAnXDO8XoydsrjdL9bryrVmfBnXIRI4F/ZPvcycObPVNmOfoZKgMC6K80CAIowjEYxcf1vfTz/9tCxbtqzV1qPzy5afsWS0xVSgHiQlLdDMeYqipJtn20luYaEUDhuW9IXjhoMOJULLrDig5/iWW25psw1GBsYGhggGDSFPNjTIDQwieuXJSsW+GbzPwHsLg+LxnnBsroMNN8JjAVwf58B5IFyIAeAYYOyTcvB/QtRsGfHaEAaGYc9fjhHVdcrNNT3ZGIV4f3i3EGpEhMLFF18c8X74HT39tree8+PcgtscIV+ECCJGox2wnwjCXWfKiQFKmmrrAcFzwnUGjFb2gbH8l7/8Rf785z8bQUtdesE+nckBqDs8HYgOxBHCOjhhBe0D43vXrl2+nj+eMMK8SFSxdOlScz6U5eWXXzYpqYHzRtRQPjoBSGRBO44WDHs6JCIl3D3jhLBBtichB/WJOOKafeUrXzHhgM6kJyRzQHDRDhGitp1/+9vfNr8nQQXfs5Bwgbpww4YScu+sX7/e3P82XJMwPjc4FwQZbYzjuIkj2gbhddzzhEfi1SLpA6GTwP3JudIJwWKnB+C5cP7550uqUIGkpAU6vkBRFCU2iPFHEGHIYpBi4AZPYkpWNwxZQp3wMmB0kYHKC8bskHGLcBh65TGUMZ4s/J55b8iERvgNhhTGmg0LwsiaPXu2+e24ceNaDTbGe2DAYkjxW8a7WE8VYzcYY8F2/I6xRIidaGHiWFIwn3TSSSaUjjE0zz77rOmVjwa8QoSfEV5FvSGG3Hqz6W1H2OGZSPVEn+GuM+0DgxoDGA8Z147QTGs0M3Zn0aJFJpsghjgeCNoSxixCww0McvZnx5QgPqgHQg/5P2NO8HA6wduGJwXPCdfaeur8gOtPuW2YHWOVuD+sZ4JMboQPIpAw/mmH0c7JhHDG8GfOIAt1wPmSpc+NcPeME7x8jCFEuNKGqS/qkTFhTriXGNfHeTKuDM+x3R/j47iO3IvsgwWBFSrzJ+MEEUNHHHGECWNkWzyI1uPHuXGONhyTe4uQOsaA2cmagzNX8h3tkbZH5xZeReb3YiwicB2of7tYDxn15Bzzl2xyyNSQsqNnKLiScd2jxJ2NQIl/DBJhdTZ8Btd3MpJDKIqiOLG95YiE9gIeG561hMiES7agKG5JBRA5eP3aA9/61reMYU/IaKpA+OGZQ/S0J1aHeD77aZ+r5amkBakeX6DELmzpYdJrpiiZDeEs9BK79WYrSjjwIkUTwpjphJpPSMkO1PpU0m58gZK5Xj+y37R3r5+KRiXTuPnmm804AEKiCGtRkge93OvWrXP9jkHvwemzFUVJDu3XilEUJS408+DBqGhUMpHrrrvOLErycWZ/U5RoiDbDoxIdmqRBUZSY0MyDoUUjY+j4y+dQg2IVRVEURUkvVCApihITmnnwYFQ0Zg+av0hRFKX9PptVICmKEhMk0cBLQupUvCT85TPr2ysqGrMD5iVB7AZPlKooiqKkDjufU6ImGnaiY5AURYnt4aGZBw8CcUiiCgQji01X355FYyZC+t66ujoz1wftnJexc3JGRVEUJfmeI8QRE84mI3mJCiRFUbIi82A6ZI9T0ZgdMIkjs8ozGSTtScPtFEVRUgudVIWFhUYc0YmVaFQgKYqS8aRT9rh0Eo1K7NCGNOW1oihK+0QFkqJkoSejvaEpxxVFURRF8Qu12hQlSZ4MUOGU2OxxuN1xw5eUlLReA0VRFEVRlGhQgaQoSfBklJaWSlVVVVqEgGV79jjEEX/tOkVRFEVRlGjQNN+KkoR5cLZv364TiCYQTTmuKIqiKIpfaNe1oiTBk4FY0hCwxKHZ4xRFURRF8QsVSIqShHlwEEsVFRUaApZANHucoiiKoih+oAJJUZLgyQA7HkknEFUURVEURUlfVCApSpLmwXETTpqgQVEURVEUJb1QgaQoybrZdAJRRVEURVGUtEez2CmKoiiKoiiKohxABZKiKIqiKIqiKEqiQ+yYMJOF9MaMtejWrVuiDqUoiqIoiqIoipJeAqmmpkb+/e9/y+zZs+X111834sgJImny5MlyzjnnyAUXXCCdOnXy69CKoiiKoiiKoijpIZB27dolt9xyi/z5z3+Wuro6GTdunMyaNUuGDBkiXbp0kUAgIHv27JE1a9bIe++9J1/96lflqquukssvv1yuvfba1hTIiqIcTFNTk+ls0Mx3iqIoiqIoGSKQDjnkEJO++LbbbpPzzjtPevToEXL7HTt2yGOPPSb33HOPWSorK+MtgqJkrTj65JNPzLxJViAxCS33m6YHVxRFURRFSVOB9J///EdOP/30iLdHQH396183y/z58+M9vKJkLXiOEEf5+fnGG2snmmUuJbd5lhRFURRFUZQ0EEjRiCM/f6so2Q5eIxbEEclOSkpKWr1JipJuaDiooiiKki0kZaLYzZs3y6ZNm0yv94ABA5JxSEXJeAipY8FzhDjir12nKOmEhoMq6YoKd0VR0m4epC1btshJJ50k/fv3l6OPPtqMV5oyZYqsXbs2kYdVlKyABCa9evWSxsZG4zniL581sYmSzuGgtFH+8jk4m6mSPqJh69atsn79evOXz9ks3JcvX9668Dlbz1dRlAwRSIwzYszR6tWrTYY7stjV1tbKl770pUQeVlGyAhIxkJCBBVFUXl5uPEmKkq7hoLRPGw5q1ynpRXsSDSrcFUVJqUD61a9+ZXq3g3n33XflRz/6kfEcERZ0+OGHy1e+8hUjlBRFiYyqqiqT7ZEMkKtWrcpaY0bJTK8Df2mfdH4RNcBnDQdNX9qTaFDhrihKSgXSv/71Lxk5cqSZJNbJxIkT5dZbb5UNGzaYl+bixYvlvvvukwkTJvhxWEXJetqTMaNknteByAD+It737dtnhBPf1dfXazhomtKeRINzHCdzMqpwVxQlqQIJj9A111xjJoE95ZRTZMmSJWb9n/70J5OcYdCgQVJYWGgmkc3Ly5P777/fj8MqStaTrsYMBvPGjRtl4cKF8sEHH5j7XL1a7U+o23m6eL6PGDFC+vTpI8XFxSa0WufrSk/ak2jQcZyKoqQ0ix2G2+WXXy4XXXSR/OxnP5NJkybJl7/8Zfn5z38ur7zyivEgEXrBixWxpChK5mayQwjhJVi2bJlUVFSYdWVlZcaLfNhhh2XUJLaJznCVLRm0vFLOE1bnXE+mUtbTHjLxPNsDtEEmnOY6sdAuszX5ix3HydxxmX4PKoqSXHx9SjCI/I477pCvfe1rcvXVV5sH0w033CBXXHGFpvdWlCwxZjD4yURJSBWGMIYxhvKaNWukW7duGTOJbaJTU2dT6msvod6xY0fTDtJJwCuhaW+igfPKlGeSoihZnsVu1KhRMn/+fHnggQfkzjvvlLFjx8qzzz6biEMpSrswZvDM2CXVBjZGFWNPcnNzjYFcVFRk/s+4k1SH/qXT+K5sGj/mFapEW9RU9JkrGgYOHGj+Zqs4UhRFSalAotfwG9/4hvTr18+EWkyfPl0+/vhjmTlzphmP9PnPf17OO+8885ksXIqiZK4xQ48zoqilpcV4jhBL/J9xKJnkOfAa38U5+TFHTLqOH/NTqNMO0k3AK4qiKEpaCKRvfvObMmfOHLn55pvloYceMgbGmWeeaQwBek1/+MMfmjELiCe8ST/4wQ/8OKyiKCnyJpC6n8H4pHdmHBKG8uDBg9NuHEOoCTHdBqtj2NtMbPHOEZNtg+G9hHq6CXhFURRFSQuB9OSTT5r5ji677DLjJbr33nuNQWKz2QHZjRBPL774oknc4AcYHCSFwGPVtWtX00v74IMPHrTdF77wBfNd8ELWJUVRogMDGE/B0UcfbVL2H3HEETJ58uS0S9AQbkJMt7AxhB4eMT/C4jSDlqIoiqJkJh38Ss7AAG0LA7gRIKwP5qijjpI33njDj8Mao+Wmm24yPZfjx4834ssLwn8QbsHlVhQlehBC/fv3N0u64hwDhPeaDhU+MzjdejqCB6vj/UZEkWzCma0tlrC49jYYXlEURVGyBV/e1ITQEWb34YcfGkNk3rx5cu6558qQIUMkkeCVIn04xs67774rRx55pOe2GCWXXHJJQsujKEr6p6Z2ip3gDFeE1/mZVl0zaCmKoijZTkt9vVQvWCBFI0ZIwSGHSDbgi0BiDqTRo0ebUDt6YP/85z/L//t//08SDV6haNJ3Njc3S01NjUlNrChKehPvHEKxzCGVjmnVFUVRFCXdCAQCUvv++1Lx+GypfPppaamqkq5f+pL0+sE1kg34Futx3HHHmSVdsXO28JceZQTcrbfeagwnRVHSCz/mEIpF7GhYnKIoiqJ407BunVTMniMVTzwhjRs2tPmu4ok50vO7V0tOFoSSx30GCA6yWSX7t9GG4pE5jwHlpCN++umn5e677zYhgYxbCmVwbd++XXbs2NFmHYaboiipGz8UCbGKHQ2LUxRFUZRPad67VyrnzTPCqHbhQvEit2OxNBKqnsbjk5MmkAYMGCDf/va35atf/aoRIpGwadMmE4aHSEnGpIm33HJLm88XXXSRDB8+XH784x/Lf/7zH/PZC8p44403JryMiqJEN34oElTsxB+qqCiKorQ/WhoapPqll6RyzhypevElkcZG1+1yy8ul7MwzpHzmTOl4+OHmnZ0NxP2W/OMf/yg33HCDySY3ZcoUOeWUU4ynhjlRMG6IUdyzZ4/Jckciheeee07efPNNGTZsmBEfqeLqq6+Wn/70p6Y8oQQSyScuuOCCgzxI55xzThJKqSjtk1jGD2W6WEmEkPEjVFFRFEVpH2Cz1334oeydPVuqnponzRUV7hvm50vpiSdI2cyZUnLCCZKb4e9mN+J+Q372s5+V888/30wUyxxEv/zlL82LOFhBUum8nE877TTjtWG+pNxcX6ZhiomOHTuaVL67d+8OuV3Pnj3NoiiJRnv6sztZQiixAokQMn6EKiqKoijZTcPGTVIxZ7ZUzp5jxhh5gYeofNZMKZ0+XTp06SLZjC9diAgdPCos9fX18t5778myZctk165d5nuECJOyTpw40WSeSweqqqqM8dCjR49UF0VRtKe/HSRLCCVWIBFCxhmqSCcVmTwpB3PAZXp9KoqiKLHTXFkplfPnS8Xs2VL77nue2+X372/C58pnnp01Kbwjwfe3IwLo2GOPNUs6UFdXJ42NjVJaWtpm/c9//nNjMEyfPj1lZVMUi/b0e48fsp61zZs3Z7RQCjeuyo8xV8HYsEQ6hFhIOMPzcOPGjVJUVKShdoqiKO2IQGOjVL/6qkm2UP3CCxLweMfklpZK2fTpUn7OLOk4YULWjCuKhsyzMoK46667TCgKxhM88cQT5uUPV111lRn/dMQRR5i03nixYP78+fLUU08ZcTRr1qyUll9R/ExKkG1k0xiacOOqEjHmyoYqrlq1qjVUsW/fvq3tS0PtFEVR2sG4osVLjKeo8qmnpNlraEmHDlJy3HFGFJWceKLkFhVJeyazLAwXfvOb38g6R7zkf//7X7PAJZdcYgyAGTNmyLPPPisPPfSQCTHBuLr55pvl+9//fkrHQSntD69xRtmalCBessmzFm5clfM72gQeHibe3rp1a8xeMxuqyH7wphNSzHxwPPdUgCuKomQvjZs3S8UTc6VizhxpWLXKc7uiMWOkfNYsKTvrTOnQtWtSy5jOZLxAWrt2bdhtHnnkkaSURVFi9YZkY1ICP8gmz1q4cVX2OyuKEDS0l3i9ZvyGKRgqKyvN/xFH2STANbmJoijKfpqrq6Vq/jNGFO17+23cR65V06FPHyk/+2yTcKFw6FCtvmwUSIqSLd6QbEtK4AfZ5lkLNS+T/Q5xRBtgPCcJbvzwmmWrAM+mEExFUZRYCDQ1Sc3rr5txRVXPPy+BujrX7XI7dZLS00833qLiIydJjkZQhUTfIIqSJt4QndS0/Rj2yfaaRZsVMFO8MtkUgqkoihLNuKL6Zcuk4vHZUvHkk9K8c6f7hrm50um4KVI+c5aUnjxNcjt21EqOEF/fePv27ZPjjz9evvrVr8rXv/51P3etKBlPqrwhmWLstpd036lqJ5EK8EzyymRTCKaiKEo4Grdtk8q5c423qH7FCs/tCkeMMMkWys86SzrodDYx4evbrri4WNasWdMu0wEqSjiBwtgSjE3GltTU1CTFG5JJxq4XsXrWMlUYJttrFlxPJLLJFK9MtoVgKoqiBNNSUyNVzz1nRFHNG294jyvq2VPKzp5hvEVFhw3XiowT360FUmeTRvvyyy/3e9eKT2Sq4ZiJBAsUm50MQ7Njx44Jr3u3EKQtW7aYcpHNLFuvfyYLw2R6zdzqiSQOiPhM8Mq0xxBMRVGyn0Bzs9S8+aZUzpkjlc8+J4F9+1y3y+nYUUpPPcWMK+p0zDGSk5eX9LJmK76/cX/605/KBRdcIJdeeqkRSYMHDzaGYDBdNZVgSshkwzETcRMo1Dv3hJ+98V6iNzgECS/vhg0bzKShlCFbr3+mj01J1ng0t3pi7jji2zPBK9MeQzAVRcle6pavkIo5s6XyibnStH27+0Y5OdJp8mSTga70lFNM8gXFf3x/i4wePdr8/fjjj+Xvf/+753aEcSjJJ9MNx0wjGWMkQone4BAktsE7wPWmpz0Z1z8VHksdmxJ7PSGeEdKNjY1p65VRL7iiKNlC044dUjH3SZOau37pUs/tCocNM+OKymbMkPxevZJaxvaI71bK9ddfr2OQ0hg1HLNvjEQo0RscglRfX2/SR/fs2TMp4VOxeCz9MH51bErs9UQIKJ5/64FMN6+MesEVRcl0Wmprper5F6Ri9mypee01kZYW1+3yunc3iRYQRiRe0DH+ycP3N94NN9zg9y4VH1HDMfvGSIQSvcEhSEwWumPHDpMwIhnhU9F6LP0yfmOt9/bmmfCqJ65Nup63esEVRclEAi0tsu/td4ynqGr+fJN8wY2cwkIpPflkI4o6HXus5KTpszjb0VpvZ+ig5uRiBQpiBMOOsR2lpaVJFb3O8SwIAD4na1B7tB5Lv4zfWMamtDfPhBWDdkLaTp06JSVxSLyoF1xRlEyiftUqk4GuYu4T0rR5i+d2xUcdZZItlJ5+muSVlCS1jMrBJOwt+Nprr8n7778vFRUV0hLkOsRQIpmDknx0UHNsxOtZwNDnXrBeHMZ5+GV4RyN6k339o/VY+mn8RpvooD15JtzEIPU1YMCAhLUFv7xz6gVXFCXdadq9WyqffMqE0NUtXuy5XcHgwUYUlc88W/L79k1qGZXQ+P4m3L17t5x11lny9ttvm95yjBz+gv2/CqT2kSErW4jXs5Bowzta0ZOI6+9l/EbrsUyl8duePBPJFoN+eufUC64oSjrSUl8v1QsWGG9R9Suv8OBz3S6vSxcpY1zRrFlSNGa0jitqLwLpmmuukUWLFpkMdkcffbQMGTLEzIvEoN/bb79d3njjDZk3b57fh1WUhBHLOBqnWGC8T6IN71SK3nDGbzTiLZXGb3vxTHC9tm7datooyTrotEq0GPRTkKkXXFGUdIHnZy3RUo/Plsqnn5aWqirX7XIKCqRk2jSTmrvkuOMkJz8/6WVVUiyQnnrqKTP/0YUXXii7du0y65h4ECPpD3/4g5x77rnyne98Rx599FG/D60oKfcsuIkFG76UrYZ3thi/7cEzYdvnxo0bTcjnvn37pEePHqZdJrJN+u2dUy+4oiippGHduv3jiubMkcaNGz236zhpopTPnCll06dLXllZUsuoxIfvVgcGhp0LiZcgYDBZTjvtNLnuuuv8PqyiJGxcRDSeBTexwLxDpE7mGNloeIcyfmMJrUqV8ZuJnolox/XY9sk5sh2fN2/ebNrj0KFDE9Ym24t3TlGU7KV5716pnDfPCKPahQs9t8sfNPDAuKKZUtC/f1LLqPiH72/+vn37mvANsPOtfPjhhzJr1iyzbtOmTRpvqaQFkRrv0XgW3MRCTU2NMfjJEJYphrdfxm+mJT5IN8+EmwAC1hG6ybMWAW6zEyLEbVtza2O2fdJ+uVZMCEvad57biczW1x68c4qiZB8tDQ1S/dJLUklq7hdfEmlsdN0ur7xcys4604iiovHj1c7NAnx/G06dOlWeffZZ+fGPf2w+E2r361//WvLy8kw2uzvuuENOP/10vw+rKFETqfEejWfBSyxgsKaT4Z0s4xfvRCShVe1p/qFIz9VNwNuwZX6/Z88eEyZXXl5uss+tX7/eZEhke+rbin27vc2g6Az3tIk0+vTpk9D6zkTvXCjaU3tNV/QaKAkdV7Rw4f75ip6aJ80VFe4b5udL6YknGG9RydSpZpyRkj34/kT/7ne/awRSfX298SAxceySJUta03ojoO68806/D6soCR0XEalnoT32lIcyfiMJrUrW/EPpYFBFc65uAn7NmjWmrfIZYcRvedZu375dGhsbzYud9fyG39o6d04c3NzcbH6DZzOZ7TPdvHOx0t7my0pH9BooiaBhwwYjisy4onXrPbfrePjhJtlC6fTp0qFLF70YWYrvT/OxY8eaxcKL/LnnnjMvELxIfk+SqSjpNC4i23rK4zV+IxGMyQjDSxeDKppzdRPwW7bsn2SQ/yN0CJEj0QKdUfzFU8m+rdjneHiZnMdDHJGYoaysrN20Tz/JtLDRbESvgeIXzZWVJvucGVf03nue2+X372/C55ivqOCQQ/QCtAOS9lbk5aEo6USivD3Z0lPuB5EIRr8ynIXyEKWLQRXNuboJeIQQv7PrOB8+Mx6Jv3zvFPt4lNzGxCGOBg4cmNbetnSlPc2Xla7oNVDiIdDYKNWvvGo8RdUvvCABj3s3t7TUZJ8rP2eWdJwwQccVtTMS8sYjFv7mm2+WBQsWmAHAjz/+uAmt44V70003yRe/+EU54ogjEnFoRYmY9urtSTbhBKMfnrxwHqJ0MaiiOVc3Ac98csCzFKFjBR4eIZ61JGzgrxX7eOwZdxRN3aaLty1d0Yx8qUevgRItdBbVLV5sPEWVTz4pzXv2uG/YoYOUHH/8/vmKTjpJcgsLtbLbKb6/7T7++GM5/vjjTUIGJorlRcsL177wX331VfNiv++++/w+tJLmpGOvdLZ4e9KxbpPpyQvnIUoXgyrUubpdQzcBD926dTvoWh9yyCGuGe84HmOXCM/Dw4TIClW36eJtS1fa4zjDdEOvgRIpjZs3S8WcJ4y3qGH1as/tisaO3T9f0VlnSoeuXbWCFf8F0g9+8APzIn3zzTdNTy1pvp2cddZZ8s9//lOrvp2hvdL+1qXTEOZ+W7t2bcb2+MfjybN1sWHDBpPVDZHg5iFKF4PK61zBy2vjJkrc1rmJfds5RZ04/4YiXbxt6Yp6nlOPXgMlFM3V1VI1/xmpmD1b9r39tnc76tNn/7iiWTOlcMgQrVSlDb5bTy+//LJcf/31JuTDpqR1Qtw7cyEp7QvtlU6c0GQhtArvQLr1+Efq2YrFk+esC5vyGqGISCJhgdNDlE4Gldu5Mp9RIrw21D0L+7SeMz7jgfLab7p429KZbPE8ZzJ6DRQngaYmqXnjDal4fLZUPf+8BOrqXCsot1MnKT39dJOau/jISZKTm6sVqbjiu3VAaB2ZlbwgPh5DTmlfaK904oQm9xT33ZAhQ9Kqx98vr6GXyHLWxaBBg4w4siKJugn2EKWzQRXt/RGp8IzlvksXb5uiKEq4cUX1y5YZUVTBuKKdO903zMuTTlOONaKodNo0ye3YUStWSb5AmjBhgjz55JPyzW9+0/Wl/o9//EOOOeYYvw+rpDnaKx05oYxfN4OXOXByc3PTrsffD69hKJEVXBd4jtatWyf9+vUzE6dm0jisaO6PaIRnLPddOnnbFEVRgmnctk0q5841wqh+5UrPCiocNXJ/CN1ZZ0mHHj20IpWo8P2N96Mf/UhmzJgh3/jGN+Siiy4y63iRMxcSme2WLl0qd911l9+HVdKc9t4rHWmPfzjj183gZWLQoqIis3061W0470UkdRJKZAXXBamu2QZxlK6eIj/uj2iEZyz3XSYn/FAUJTtpqamRqueeM1noCKWTQMB1uw49e5q5ispmzpSi4cOTXk4le/D9rXfGGWfIgw8+KN/+9rflnnvuMesuueQS4wpl7o2HH37YpPxW2hftuVc6mh7/cMavm8Hbp08f4z1hfTrVbSjvRaR1Ekpk9e3bt7UuyNDGPnnGMIEq/0/1+Sfq/ogmbC7a+06TqSQPFaKKEppAc7PUvPmmVM6ZI5XPPieBfftct8spLpayU08xoqjTMcdITl6eVq0SNwmxIC699FI599xz5dlnn5WVK1ea8RFDhw6V008/3czLobRP0nkMSCKJpsc/nPEbyuBNt7oN5b2ItE5CiSxbF6wnjTXjj0jOgPCqqqrKmCx+lkivYbRhc9G0DU2mkhxUiCqKN3UrVpgMdJVPzJWm7dvdN8rJkU6TJ5sMdKWnnGKSLyiKn/huPVijrVOnTnLOOef4vXtFyTii6fF3M34xcJnskwmYrSBKNzHkRigxF2mdhAsRY18sdMJ07dq1tc7SJYtfpoWrxppMRb0h0aFCNDFoO8xcmnbsMIkWCKGrX7rUc7vCYcOk/JxZUjZjhuT36pXUMirtC98FEgbJ+eefb7xITBirKO2daHr8g41fjH9CxshURxhZJs5x5CZSIq2TSELE2luGxESGq8aS1EG9IdGP42pvbTYZaDvMPFpqa6Xq+RekYs5sqXntdZHmZtft8rp3N4kWEEaFI0ZENJ+bosSL7xYW4uixxx6T++67zwyWZvzRxRdfLCNHjvT7UIqSdT3+wcYvniObGp+5a7LFOxJtndhzdTM822OGxESFVMbinVJvSPSGentss4lG22FmEGhpkX1vvyMVc+ZI1fz5JvmCGzlFRVJ68slGFBFKl5MBHYJKduF7iyMxwx/+8AeZO3eu/O1vf5Pf/va3csstt8gRRxxhvEpktuOFqyjthWh7/J3GL2F1eI4QR9nU0xyLF8TL8CRBBc+U9pohMdXXRb0h0Rvq7T2rZyLQdpje1K9aZcLnKp54Qpq2bPHcrvioo/bPV3T6aZJXUpLUMiqKk4RIcl4Mn/nMZ8xCD/i///1v+fvf/y7f+9735JprrpFTTjnFeJb4vqNO2KW0g5CaWHv8s7mnOdo6oX4Ri7aO6+rqzGcMz1hDzlI9ZiHVx/fjumRzG02Uod6es3omCm2H6UfT7t1SOfdJ4y2qW7zYc7uCIUOMKCo/e4bk9+2b1DIqihcJfxqTdvfLX/6yjB8/Xm699VYTfvf000+bhYx2X/va1+SGG24wSR0UJRNJZOy79jR/CvMcUcdMimvTeJOcAQ9SLAI01WMWUn18v4i1jaajOPTTUCeTIu2Tv0xzQbt1ko6ZJzMZfVamBy319VK9YIGZxLX61Ve50V23y+vSRcoYVzRrlhSNGa3jipS0I6FvI1LvEmbHsmLFChMmdOWVV8rnP/958wIhHO/3v/+9rF692ggnRUl33Iy6RMa+a0/zp9TU1Eh9fb2pZzpe8E43Njaa9bEQ7rol2oDPljETfoZLZpo4dINz37VrlyxbtsykngfaK//numb6+aUr+qxMHXQA1L73ngmhq3z6aWmpqnLdLqegQEqmTTOpuUuOO05y8vOTXlZFiRTfn9S8GP75z3/KX//6V3nrrbfMi2/GjBny61//2kwi63w53HXXXSaRw0033eR3MRTFd7yMOhIoJDIjVab3NPslNPAyU9fUMeIoLy/PLEVFRbJ169ao9x8qFMoPAz6eTGbJ9K74caxYwiWzQRx61QXnQVvlXLiueI84ZzoJM/380plMf1ZmGg3r1u0fVzRnjjRu3Oi5XcdJE6V85kwpmz5d8srKklpGRYkV39+4ffr0MS/cyZMny9133y0XXniheVl4MXr0aOnZs6ffxVAU3/Ey6jB6dAxG4j0FjFckdAuvEdeA/bEPsvxt2rQp6v2HGrMQrwEfTyYzRF+yvCup8uQkc0B9KkL5SM2PQKK9cn70sCcjuUq2hi0q6UPz3r1SOW+eEUa1Cxd6blcwaJCUzZpphFFB//5JLaOi+IHvT87rrrvOZKsbOnRoRNvjXWJRlHTHy6jDs4ERohmpEuspwNijA4bfk6ABYxBDdN++fWaS2Gj3H2rMwubNm+My4OPJZGaN6WR4V1LlyUnWgHrayPLly2Xt2rWmzeBtZMzaYYcdFpNwiFSApCJhQDaHLSqppaWhQapfekkqSc394ksijY2u2+WVl0vpmWdIZ8YVjR+v44qUjMb3pyYJFxQlG/EyevBsECqqGakS6ymwYwzYB+MbGdNB4gbC7TDwWR/N/kONWYjXwI0nk1m84iwTUiNHM6A+Hq8IoZeMBUJEE+bGX4RSeXm59I+yVzsaAZKKhAHZHLaoJB86auo+/FD2zp4tVU/Nk+YD4+kOIj9fSk88wSRbKJk61YwzUpRsQLuVMhANo0gNoYwejX1PziSu1LPNXofXiGNi8BJmhyeP8LRo9u913eI1cCM9b7fjJ9P7kKrUyE5xiMgl0QYhabQfpwCK1yvC/hDSJEmgI4Nj8Zn10QqkaARIKhIG6DxAkaHvzzDtaONGM6aocvYcM8bIi46HH26SLZROny4dunSJqq0qSiagAinD0DCK1MXka5YkSYtJXJ2GIELJel22b99u/u9HT3281zoegZVM70MqUyNTlxyHdkNyH+a0ChZA8XpF6AUHvGPOv3Z9IgVIsjtNdB6g8Oj7053mykqTfQ5hVPvue571l9+/vxlTVD7zbCk45JCY26qiZAIqkDIMDaNI7ctQPUXe7RID1yZQIB13vJO4RmoIspDohfFJeCHcPBHJvtbxCKxkCvFUi377PMPzx3XjmnLPMkdev3794vaK0C7wHuE5ok0iqPkcS2KgdBcgOg9QePT9+SmBxkapfuVVI4qqX3hBAh73VG5pqZSdcYbxFnWcMEHHFSntBhVIGYaGUfj7MtRwi/iw9bdu3TqzMAgeIxSDF/AgJcMQHDx4cBuhlg4D1OMVWMnyPqRS9PM8I0QSjw5jyWzIJHPj4cmKV5Swj5EjR5oxawgkRBhthfXZJkBSLXYzgfb+/jTjihYvkYrZs6Xyqaekefdu9w07dJCS44/fP1/RSSdJbmFhsouqKClHn5wZRrr3YmbSy1DDLSLHTUiC9dAR4sbYDoxQPDm0S7xJVVVVCfHiBRuClG/VqlU6QD3D4NrRTmgTjBEikQKZCRFL1gsYjyihrZCxjlT8bqIhmg6STBAg6uEOTXt9fzbyfJ7zhPEWNaxe7bld0dix++crOutM6dC1a1LLqCjpRvo82ZWs6MXMpJehhltEhpeQJAzKeugIWdq9e7fZlvEkJEzA2GX7PXv2JEy4YExzHRnkz3EGDRrULnuGMxWeW2SUY/wY14120qNHD/N/O89VvKLESzTE0kGiAiSzaU/vz+bqaqma/4wRRfveestzuw59+kj52Wcbb1FhhNOzKEp7wHeBhFFkB8J6QRgOGYROOukkueaaayKeM0nJjF7MTHkZpjLcIpNC+7yEJOM6nMkSyCqHx4jPeAM4L84p1jr2qiNr2BJKx77wWtlB9/wlrI+ytYee4UyH60nIGx4j2geim78IX3vtEiVKtIOk/ZHt789AU5PUvPGGVDw+W6qef14CdXWu2+V26iSlp59uUnMXHzlJcnJzk15WRUl3fH8qXH/99TJ79mxZsmSJnHHGGeZhBCtXrpSnn35axo4dK9OmTTMGzgMPPCCPPvqovPzyyzJ+/Hi/i5K1ZHIvZjKFQbiXYarCLTIttM9LSPJ/Z/0hiqzwoRMEMcp6Qu+ireNQdWQNW9bTIYNw468dx8JYKMqarT3D2QbPMiu6GX+UrF799j4epb2Sye9PN3ju1S9bZkRRxZNPSvPOne4b5uVJpynHGlFUOm2a5HbsmOyiKkpG4bs11rdvX2PAMDnfkCFD2nyHwXPiiSfKqFGj5LbbbjOiafLkyXLdddfJk08+6XdRlDQjFcIg1MswVeEWmdZz7SUkqSeEEGVnHiJCpag/zgGxZOvRnp+zjjlXJvH0Esqh6sgatnbsEVnJEEbsFw8W2c+YuDcZPcOZ5AlMV1LVq99ex6Mo2UHjtm1SOXeuEUb1K1d6blc4auT+1NxnnSUdevRIahkVJZPx/Q2E8LniiisOEkfAS5DvbrnlFvniF78ow4YNk69//evyhz/8we9iKGlIugkDN8OM/yfa4M20nmsvIWmvWTjD1q2O165dG1Ioh6oja8TibWB7xBFZ8xArbI84SkZ7yjRPYDoLv1T06tMOOTfEPWOgEPgkGAnuIFERrKQLLTU1UvXcc1Ixe44JpROP+bw6kN7+7BnGW1Q0fHjSy6ko2YDvb7yNGzeGfJHy3YYNG1o/M16AMQRK9pOOwsBpmPlh8EZiTGVaz3W4Hv5whq2tY1s3S5cuNVnv2J+XUA5VR1awMQaJsU9kQUMgJXvAdboJ/kgINa7LrqcuqV/ndpHeB5kiJignIh2RTRsiRBNvKO8jZ3mzWQQrmUGguVlq3nxTKufMkcpnn5PAvn2u2+UUF0vZqaeaZAvFRx8tOQemWlAUJTZ8f8KPHj1a/vjHP8qll1560FwThNTwHdtYmO8iXY0JxV/SXRjEa/BGakwlI7TPb0M13h5+Z91QLsYlYYjbiV6D06+zYLSSGY+wOTumyZ6HFWwYtGSwI2ueDetLpOHqrFfKhoGdaMHv17X0ap/UodOjR4cVC9c7mvsgk8SEvdeZF4loB86RMlNe5zlmoghWsoO6FSv2z1f0xFxp2r7dfaPcXOl0zDFSfs4sKT3lFMktLk52MRUla/H9rfWb3/ymNTnDOeec05qkgRfn448/bnp777//frMO4+LBBx802yvZT7qnWI3XwxWpMZXoMRepMlRDGfLOuiGNM1nmCG1C2Fjvjx1TZMvO84HrUFxcbIxY2kpw+fktx0mkMLLnRZnp5KFcrLNCAgFH9rVECH4/r6VX+7Sp2e16ogAQsKRuj+Y+CNf+08m7FOm9no5ebyV7adqxQyrmPmlSc9cvXeq5XeGwYUYUlc2YIfkxTHqsKEp4fH87kYTh9ddfl5/97Gfy3//+1xgVQA/wKaecIjfccINMmDChdR2hNkr7IN1TrMbr4YrGmErkmItU9HqHM+SddUNIE9ede5+xH/zfCmW3stsQOufknskSgM5jMc8SwoGkENZzhWDi2Pv27UuI4PfzWnq1T2e6drseEH6My4n0PgjV/tPNuxTpvZ7uXm8l82mprZWq518w3qKa114TaWlx3S6POcNmMK5ophSOGBF2OhVFUeIjIW+mI444QubMmWMMIQwgoDeSkBmlfZPOKVbj9XClizEVbKjigSGEyo7980OUBnsDmLcmlCEfXDcsPBOYD43vbZkiEZnJFIDOYyEWEEkIh02bNpnPeMDwiCHgnOLCL/z0YHi1T0ITEXh2Pc9pRCDpg6O5D4L3T/IMyol3iv/jMSSkLR1C1Zzj2HhHcc5cR8qTSV5vJTMJtLTIvnfeNaKoav58k3zBjZyiIik9+WTjLeo0ebLkpElnoqK0BxJ6t/HSSVdjWFH89nClizHlNFStOMLzARjC8fbcu3kDuNdDjcdxyxhGGYLLEYnITGbYk/NYeLIQgtQl6xBLeMEJr2M96+ycT355RvwU3V7t0yYmcK4fOXKkuUZ0ckV6Hzj3j/CgrIgsrjehiLS9EQd6vlMdqsa5cN5W8HKetF/uFee1S0Y4bLqEHSqJp371apOBruKJOdK0eYvndiRZIDV36emnSZ7PnS6KokRGQp7EvHSYAJYEDPzfznJv4QV53333JeLQihKXERKNh8ttv+kQQug0VK04wiMwaNAgE04Vb8+9mwfH3uduhnykGcMiFZnJ9NQ5jwU2eYT1GHFOnHu3bt0S4hlxE5Z43ijHmjVrokpQEcrYj7fd2nsBDxF1gSBCULJP2h6CiXriHOzEsKkOVaOdcb6cq21HXmMGE9HRl25hh85yqWjzsT7xoD75lBlXVLd4sed2BUOGmLTc5WfPkPy+fX0sgaIoseD7U3j+/Ply/vnnmxc3L0aMhmA0dlZJ1ks4UUZIqP2m2mvqNHhtWB3iiPV+9Ny7eXDohcdbhVEcLGwizRgWXHavtpFMT53zWJwHopB1Xbt2NWXC4Kec1EEsnpFQ94GbsGQbtv3ggw/M79iGY1KPzOET3K7d9u/WPuMRAfZeQAQhxikn+0NE8g6gXhB1CCTOJV1C1VKdgCEdM+QFJ0mxEzF7JUlR3Gmpr5fqBQvMJK7Vr75Kxbpul9eli5SddZYZV1Q0ZozaRoqSRvj+tPve975nHu4kaBg7dqzfu1eygGT2nCbKCElH48bL4CW0Cc+RX94WNw8OHqHBgwe3jiNyGvt+G6LJTPbhPBbeGzK8Wa+IPW/OKRZvVrj7IFhY2rFPiBB+ixjl2NaTFdz+Qu0fQnVQRNOBwXaII/ZNmWhv/LXhh9QV7Q8Dm3E+fE6HcLJUjxlMtUBzw7Y5rgseYVLZ85k25xYSq7QdV1T7/vv7U3M/PV9aqqpcqyenoEBKpk0zoqjkuOMkJz9fq1FR0hDfn3S8kG+77TYVR0paiItEGSHpYtyEM2QT4W3x2ifXzs14isYQjVQ8x+LxiNTo9/K68Bej33neiEJnm46mfsPdB842hrGKQLJpxhFNrKM+ER+U2W4fbv/OcDK3Oo62A8OOvUIU8T3nTkgg5eN3lI99uHm4ork2wdtQTzZMLhbBleoxg6kWaG7YNoQXkMQahG7iCeRzOnUApRMNhDHPmWPGFjVu2uS5XcdJE00IXdnpp0teWVlSy6goShoIpGHDhpkXuaKkg7hIlBGSDsZNJIZsIrwt0e4zGkM0lFHv5p3ys64i2c7tvIFxN9GWLdx94GxjJIFAdLBf6gaDle0QHwgRRJP1zITbv52o16uO8QaRgp3zjKQDwybpwHPEuTP+iHBL9k+WQsIRwwnScNcmeBvWUycY73wXixc61dMOpFqguWHbHO9w6wW0oblcV53/aT9Ne/ZI5bx5Ujl7jtR++KF3fQ4aJGWzZpqECwX9+yftOiqKEj++vwl+8YtfyBVXXCGf+9znzCBsRUmluEiUEZIOxk00E9P63esbzT6jMUTdjHoMdhISMA4n1pDMSOsq3HZe5x1L/Ya7D4LHP2Gw2rE8/J/64C/bY8hGksyC8rNPUm8T7sY+guvYCijEh03JHqoDg2OyL8rFb/E64OEiJJF6CVc3kVyb4G3wpFFmO/YqVi90KqcdSLVAc8O2uVWrVhlBhPhmnR3/lkrvVqppaWiQ6pdeMiF01S+9LNLY6LpdXnm5lJ11pvEWFY0bp+OKFCVD8f1J/Pzzz5uXJWliTz31VBkwYIB50TrB8Pnd737n96GVDCGZ4iJRRkg6GDfReOKc4Uncjxg+0aRwjpdIDVE3o56yY7DjiYg1JDPSukqmdzPcfeA2/gkvEd4ZxAEwxmfgwIEydOjQg0Icg/fPdwgqhAwCiQQT7BvRwXrquG/fvub5jWcKjxUZ8mgvoYxj9svcd8BvaFeUF+ESyT0dSZ0Hb0OZ7X3nFNIs6SI2MnFeONvmqE8EM22C+sVbl2rvVirgOVm7cKEJoat8ap60HJgu4SDy86X0xBP3jyuaOtWMM1IUJbPx/e1x1113tf5/7ty5rtuoQGrfJFtcRGKExJJVL9XGTaSeuODMVITPWKMSz0M6pBYOJRoQBYRvxZopLpq64rMNM7MZ45zb+Zl9MZL7wLYx5/gnBAvGKiKEMVBeY7+C90+9Llu2zLQBBBEiCKGE2GDfCC/qGoHE8QizQ0Tx/3DGMb8/8sgjY6qbSK5N8Db2GPzFiGW8DO3aXp9EJn7JdqgvO4Fze0333bBhw/5xRXPmSOO69Z7bdRw/3kziWjp9unRwydirKErm4vvTjt5DRcmkeTbSdT4SN4I9Qc402pQVQxXDlxAkW6/O8CQEhh1AT7gW+0jm4Otw195NNNB7zfWJJyQzUq8lx+V41J89fr9+/cz6aNpJuPTdsYjxWDoVnCIeMWTHh9qpFuwcdXYcE20DoUQ90z6soZzIDoNIro3bNlwX234JB+OcqB+8aumWVTITSXUHULJprqyUynlPG1FU+957ntvl9+8v5TPP3j+uSIcRKErWkl7Wn5L1pKMYSfeU3aHqDsOR8Co8AjbDGds469UZnkTaXsYTYBAjBPBCJCv7XqwZ6vgdhn08IZmRCgzKg9FNeJgNPeMz6yGSdhIuvXasqbfjNVjpvLLeIzvHDe2AMDpAYDB/HSLJTnqcjPsyUk9a8DbOLHY2HTXiKF1SZre3jqZMJNDYKNWvvLp/XNGCBRLwaC+5pKufPt14izpOmKDjihSlHaBPUyWppKMYSZeU3bHUHevIoGYzvDE4ns/OenWGJyGOMJQxjDH8/UyQEc5gi/Xa+xWSGU5gUH5EJsY23hM7yamzLUTSTkKdJ7h9h2FvRaCfHQfOa4L4cUIboD0gmBBJfEYwM6kwnkjaEr9NlzFqbtvYz9QX42UiCTfNBlERrrMhW84zERhv6eIl++crevJJad6zx31Dsvcdf/z+cUUnnSS5hYXJLqqiKCkk7icmL1ib4tWme7XhG17wPQ9wpf2RjmIkHVJ2x1N3hNRhHGIQYdjb+XFsvTLw3oYn4Tmwk5tyz7plP4t1jppw3qF4rr3f4T5uc+qsXbvWJEKgLqkbxuJQRmdbiKSdhDtPt+8Y68M4Gr86Djg/fr969WqzX+qPdsL+CaGz4EW03kSyz5FUh7928tdEeXj9NuAjCdNLR+91rIQS4ZxztpynnzRu3iwVc54wIXQNq1d7blc0dqwJnyMTXYeuXZNaRkVR0oe4n5bXX3+9edHbB6/9rCiZIkbSIWW3l/FoOxwwYK2hG5y2Ga8H40u8DPtgD0w0WewiNSqtQW23QYjx2RpsfI9nhrEinAfemVRde7dzsmWmvHbcFkkKaAdMV0D9O88Nb4xXOwnXxt2+4xr71XFgz48F4YURTZtADNukF4zf2bRpU6tg5ricC2IaoRhJGGGsAicRQiUSL2M6eq+DiXTsGvcS186tvWTCeSaL5upqqZr/jPEW7Xv7bc/tOvTtI+VnzzTeosIhQ5JaRkVRslQg3XDDDSE/K+lBuoRcpJsYSZeU3V4Z5zBuEDOEYNmEBYgMa6Bj3HoZ9oxNcqaMjsU4itTYwjvBegQd58DxEGB4JJzeK8qOoKP8kXivEoHbOdn01EOGDDHGJl4W1tlz5JrYCUopN+vxtLi1k3Bt3O07jhlJiFg058e1sKIIUYp3kTJTXoxqhF/wudB2wgm1eAVOogz4cG08Hb3XTqIZu8Z9xEJYpk1KYdtLss8zXd4tlkBTk9S8/rpUzJ4jVc8/L4G6Otftcjt1ktLTTzfzFRUfOUlycnOTXlZFUdIX359i9GA7QziU1JNOoSXpJEaCy5UOvatO4xEDFw8ARg7GLWXEKMIbgBeAukOYcG0Zd+Q07K3RjcEbTx1HamwheCgb5aZsGOQ2cQSizhrDGHS0Pc7HzpOT7Gvvdk7UM/VtBQplomyMw+E7Z1ppQFB4tZdwbdztO7BCId6OA3t+tAXaE/c/C5+pd2f7Ca7/SDy88QqcUG0qWmM7mu3T0Xsd69g17i/uLe4lG95u24tNc56M80yXdwudSPVLlxpRVMG4op073TfMy5NOx00xIXSl06ZJbseOSSujoiiZhe9PMAb5TpgwQY4//nizHHfcccZ4U1JHuoVcpIsYSUfcMs5hROLdwNhBiGDcMjkoYCQ5jSHqlglVESerVq2K22iJ1KhkkD9igrJivBHGx0KbQ8RZY5jebgw6ngmpagNu58RzC28K9eUUKNSXm2cM70usbdzrO786DmxYJe2HdoAoxYBkPfMmHXbYYZ77jcTDG6+HwqtNUcfRGNvRGufp6L2OdewazwCeBQhe7iVne0nmeXq9W+yzKNGdYI3btknlE08YYVS/cqXndoWjRkrnWbOk7KyzpEOaXG9FUdIb359Yv/jFL+TVV1+V+++/X/7v//7PPMxHjBghU6dObRVNhN0oySPdQ0vaC5H0djuNRwQGxjjXzHo3gsWJmzFkw+4QLPEK4nDGlj0nwsMQSRhKHNeeI+tsqGAsvdmJCN9xOye8WYgemzbaHouJVd08Y8EZ4dKp48BOKoswot3QBmhLiECWUPUXiYc3Xk+MV5uyGQO9Eg8Et4NoO37S1Xsd69g1rjHtNvhck3mebu8Wxh6uWbPGPLsS4VVq2bdPqp591oiimjfewH3kul0HJlM+e4aUzZwpRcOHZ0yIoKIo6YHvT4Ef/vCHZqHH8qOPPpJXXnnFCKYnnnhC7rnnHrMNvd88QJXkkO6hJe2BSHu7ncYjwoKwKO4lvDBuY3bcjCFn2F28gjiUsRU8XsqOjeCYtqxMNIqhTtgfoWoY6Da0zq86i/Wc8GbZEEbb4x1sbDo9Y4hAyoThx3laj1IiDC63fUAk+7XnQb1R3wgIzs+Os4pXqMXrofBqU17jn2x7Dm4HVogHG+fOZCF+zyXlB17tI5axa151nqzzdHu3cH7cK3iy/YpYCDQ3S82bb0rlnDlS+exzEti3z3W7nOJiKTv1VJNsofjooyUnLy8jQgQVRUk/EvYE4IU1btw44z3i75gxY+SRRx6RFStWyPr16xN1WMWFdA8tycaeveCyMw4nkt7uYOPRmcXOqw6CjaHgsLt4BbGXsRXcgx88vsimzkY8YZjbpAF4alI5mN9CefEIUc82QUKwYcRYI+4VzoHtMda5HhjhiKfg7f0wuNz2QZZCWyeR7JdyU2dWHPnZKeKHh8KtTXl15OCt4/yD24ENLbPbcy25Rvbei9XYTeRzJ1z7iHbsWqqfh27vFjythNFyTeLtoKlbsWL/fEVPzJWm7dvdN8rJkU6TJxtRVHrKKSb5QqaGnyuKkj74/nTlJfXaa68ZzxHLu+++a0JSRo8eLSeffLLceOONJsxOSR7RGjTpIEwyuWfPreyIA6+0vH73/iZLEAeH1wSPL0Ko2d58PBn85XvqxitJQKj9R2No+TVpLb9D7DGey4Y1sc6WJXh7Pwwu5z6oN7xceONpQ6Th5lqGCz9zawOsQ2jTQRXtfe1Wn34bkF7tFk8R7Si4HSBQ7RgxFuu9pE5sZrdo6z7Rz51w7SOWsWvp9m6hjVGHMYfV7thhEi2YcUVLl3puVzhsmJSfM0vKZsyQ/F69Yiq/hp8riuKF75amTcgwadIkI4R+8IMfmEQNvAyU1BHpy9Wr9xpDLZJ5c/wik3v23Mq+Z88eEyqXjDDHZI1BCO7xt94Y2otd70xwwF96+FkwbsMZn7GGhoYzcvkeg5vrREY3mwDDTXzZusRzhMC1GeA4F7ft/TC47D645/gtZadOOSbHZp/hws8oc7AnEi+ZTVcejeGfrM4Kr3brlZXNTmxrtycpBWVEHMVa94l+7mSjQR78bqG9cI9H00HTUlsrVc+/IBVzZkvNa68zg7Hrdnndu0v5jBn75ysaMSLuORc1/FxRFC98t3IxfDCU7MORhdh3FUiZQbCBwLVcunSpMUbsyyQZnpxMNiTcyo7BwHgivKnJCHNMRm+zs8cfwWHnbMLjQbtBULDYsBueA3iQ6GHGK8D2GN4YtExcGuylwCiljqL1hIXKrMWxlyxZYsqIuHCbWNetLvEi2Yl6vRJm+GVw2e0pI/VLmakj6oVzox1RjlDhZ9agt20Abx6/jcXwT2ZnhVu7DeURdW7P+njnkkr0c6c9GOSRdtAEWlpk39vvSMWcOVI1f760eCQ+ySksNKFzeIsIpcvx8b3j5WnlWRSLpzUTSIcIEUXJBHy/K+gpX7RoUWuI3fXXX29ezhgheJJs6m88TEr6EWwg0LuOYYhRFhzak0gDPBmGhF8viuD9kDHMLeMUKZaTkfo2FYYQ9zjij/8jhqzXDKgP2pAFg5/tqTcE1OrVq43nmfFKTi8F7Y3xStF6wrwyaxEmt2HDBiPUnJkB2ZZjcS5e4ivSsMXg7ezEsogxzjmS8tt9MF6TesOTxLkgPtkH5WebUOFnToOeerYCifFh7Ccawz+ZnRVe92QkBrcfoaWJfu5k6nhQPzto6let2j9f0dwnpGnzFs99FB91lJnEtfT00ySvpCRh5XS2LZ5VXB8/pkhIRzI5dF1Rko3vdwQv0PHjx5vlyiuvNOt42Dz33HNyxx13yOOPP2624UZV0g83AwHiCVtJR0PCrxeF237sGBDb827LbscYZKMhxLljuCOOnJOvYnggrvE+IJjsvDxsh/i2Ymn58uWm/uP1UnA9EBUIEoQDgoD/s956jTiGnfMIg4j/k23PGYIXq5EOnDvCj3OzXjTaSKRtzB7LPiMRQZwH3iLEDeOQbCbAcJOC2va5ceNG412JxGMWq2iIt8Mh3D0Zrh34EVqa6OdOqlONp8p70LR7t1Q++ZRJuFC3eLHndgVDhhhRRHru/L59JRk421Y8ntZMIJND1xUl2STsycjL/PXXXzdepJdfflnefvttYyjwMDriiCN8OQY392233SZvvfWW2T8G2AMPPCBf+MIXDtqWMLGrr77apBznxXDWWWeZeZowFhRvAwEjlh5setvtGJpkhIQk2pCI5kURyqhw2w/rhg4darwi2eItCgdCg0HyGOIY0bQX2g3nztgQxBPrEEuIFNbZNNkIGhvOEo+XwhrYNpSP5wELBq7NrEU5bdpuykP7Rvxb8RqPkR78WxbOld/QFqIxRjgWGUBtEgLaFP8ndTK/j9Sgt+2T3/B7PpNOm21oo5EY/pGIBj86HPww3uINLU2GgElVsoVkew9a6uulesEC4y2qfuUVCuC6XV6XLmYCV4RR0ZjRcY8raq+h3ZGQ7eenKH7i+1Px+9//vhFECxcuNA9kDKKjjz7aJGsgvG7y5MlmnR/wQr3pppvMvEp4rF588UXX7TDamKgWg+3mm282L97f/OY3JjMUwiqb4r8TFXIQ7A1JRkhIIg2JSF8UtGG8G8zbhQDAuCZU7rDDDmsNl3PbD4Z3Mo2gVMaVc2zaCPWDlwIQJMOHDzdeFOoOrxH1w1g2/tpsY9QnHScICRvyxjZ4e9gf4slrvqFgbBtln4gL9mETK9jxdBwH2DcLYyb53rZnfo8RSVms0HMa6dGIZZ47HBPvTyzGiPNetCF6bt6oUAa9bZ/csxyfZy8CEi9UpIZxJKIhnLiJpH2mQyifPd9s7E1PhveAcUW1779vRFHl009LS1WV63Y5BQVSMm2aSbZQctxxkpOfL+lAto8Ry/bzU1JDU5aOa/P9DB566CGZMmWKXHjhhUYQTZgwIWEVRZgJYTQ83EknfuSRR7puhyjCo/Xee+8ZMQVHHXWUnHrqqfLggw/K1772tYSUL1MJNhAwrrLNGxLpiwIDAu8jhinGsvVM8JnEAqxL5QvHji9BhCBObPhYMuPKeTCy0GYQA4ghvI0seCv4a0PqaEP8ZbFj3GhPdlwMogVvEvULfM/+8DpzXqEINrDtZKkc245nYr/UDd/jjcGLwr6t94jxUAgrjsW1tCGD7DdcD7xb2nOuDfvBCI2lbdh7kf2wb8RfsDcqVGdFcDu3E5Ly7HRrG14vunCiwXnuXDP2gxBDIK9bt84kkrBzeXm1z2QZb+11HEYiBWjD2rUm2QLCqHHTJs/tOk6aaDxFZaefLnllZWlnbGX7GLFsPz8l+TRl8fPU99LzUkwWGAuR9Hw99thjMmPGjFZxBKeccorp4f7Xv/6lAikM2dijGumLwmZks+FivLj5HaIJA85rvFEyXjj2wcQYP2cGJrx+yYwrDza8bHpq1iEoWRCSGMiMQbLz+7BYLw3fDRkyxIhPhB6CiX1R19YrRQdIqAduKAOb3+H145hcK/aPmONaOT1AXGvKx284PuuoR3vtQ/XABx/f1gWCId62gQeJumF/1BX7p9MnVJpvK4YiNYgiSY/uZbjac6f+OH/uG67bpk2bTF1TB3iveAbbsEG3OaeSYbyl8ziMRIoDvwVo0549UjlvnlTOniO1H37ofdxBg6Rs1kwpnzlTCvr3T2tjK9VjxBJNtp+fknx2pvHzNF4Seld8/PHHpvcQBg0aJKNGjZJkwwual7Vb1jy8SE899VTSy6RkzovCxsNj5NlQMGv48kDg4cB+UuFhsw8mykNnAT3zNuOgFS3JwMvwIlQO8ApZkYJAQhDhvaG89jsMYRaMf2Abtmd/nCcdL9ZL5UU4A5v9kYyBxQ3qi20IuaMeKaudj4h94A0L1QPvdnxC/Whj1nsSS9uwXkIEB/u3SS/YL+UklM96rIJDAqMxiEK96PhNJEKMbXjecr8g1PlrryciiWNQTu4lO4kw++IY/N56yAh9pP34cS8Fiw7u4XQch+E1B1287cdPAdrS0CDVL71kki1Uv/SySGOj63Z55eVSdtaZRhQVjR8f8biidDC2srFDsD2dn5JcGrJ4XFtCrLjZs2fLd7/7XZO21wljN0iMMHPmTEkWvISBkJJgWMdgcTu2xA1e9sFeMV5iSvt4UWA8YCDjBaGdcNPzALATdvIgwHgh3C7ZUBYMTQxPvAnWU4MBjRGarDA/L8OLkDYMPNYhNlgweikfoW3UX7DRzv85B4xY1lHnbG/D8xLZO2rDv9geA92GCtr07OF64BPVO4vRyHWmHVIfXGdeRHjAbL3beaWcIYHRGkShXnThDFd77pSTMrKdTczBdbfhlOwLocd2VrjwW+4hBBXrrJhmElg/xFGw6GCftC9nQpF0GIcRXMe0v2XLlplryxKvNyXW9sk9ULtwoQmhq3xqnrQc8OgeRH6+lJ54ggmhK5k61YwzipZsNrYUJRspyOJxbb4LJDwy5513nvEYMfZn5MiRZj0hSffcc4+ce+65MnfuXJk+fbokAzso200A2TENbOMlkO6++2658cYbE1xKJV3B+MMLgNgnxAljAe8HxmqqHwQYlBibiHwEkvXOYGBh1Hv1DPsdxhPK8GI9Xg7bCWHnBeJB6ma08zs8ONS1nRTVhuRFUs/x9I46hR7ngUiy6dkj7YFPRO+sHf+E4KTNcZ257tQjHUBW2NE2ESW0z1jaZKgXXSSGqz13ysb15rMV7TbLIULIJuSgvdhxWnYsKZ1WfnoN3EQHnkDb2QGISt5TqR6HEVzHCErqkjrwaw66aNpnw4YN+8cVzZkjjevWe26Hhyh32jSRKcdKh+7dpWP37jFP5prNxlY6kq2D65Xk0T2Lx7X5fif8/Oc/l3Hjxpn03hgYFrxGzIvEJLEIjmQJJGeYTzB2ILjdxo1vfvObcsEFF7RZR4/kOeec43tZM51MethGWlY7doWwH2cmMQzRVD8IMIgpvw1TwwgEjGUEhdcg/ETE+HsZXtTPsGHD2hwvVJ05pwGgjm2aeTvvTyIJ18Oeqvh9ayAiNuwkvBjRVgxTBpvtD/HENrHUlX3RIVbwnLN/xKoNf4vEcHXug+8QRlxDGy6JV8iGTdq51TgHW5985i+h2dxnNoQ1XIKOaEQHIsmmfrdeQq/7JZkEiwPKBnY8WzK8Kc2VlSb7HMkWat97z3O7/P79Tfhcp7POlPWNjfvLxTXftSuu50k2G1vpRqrHeynZQYcsHtfm+xksWrTIeI6c4sjCOuYouu666yRZ2NA6G2rnhHX0tnp5j4AwFhYlex620ZbVafxj4KWLCMTYw3DE0OTewqBFLFmjNB1i/GN5eHJOJGRIRT2H62GPpAfe744CL6OR644w4nrjaeNact1JdhFrCBZeKrx3GOfsC5GC95T1HDOc4eq83vyG/dixXWxL3VE3lNUKAVtPVuwvXrzYeE4oBx0SLHSsxSKSvEQHdUcZbUIRr/slmQRfZ5v9MdFz0AUaG6X6lVf3jytasEACHgIst7RUyqZPN6m5O06caEQb12bb8uW+PU+y2dhKN9JhvJeSHXTI0nFtvj91eIkR8uMF38XaGxgLjA2hF5Q04MEwB9Lhhx8umQYvy7tfXCXDe5XKqL5l0re8KKWT62XawzaesqbTg8CGVtkJmG1qbdZ5GVGpiPGPpc7SqZ5T3VHgZjTyf8Z3YTwjJuy4KZvsIlYoK8fAKLWeIntvOOdkIqSTjiXupWADNty1cxN8PKcReitXrjTng1efzi0EDYl2qNMxY8ZkjOjw4zrba5uIDJkm6QxClPmKnnxSmvfs8SqUlBx//P5xRSedKLlBnYmJeJ5k6r2faeh4L0VJskCaNm2a/O53vzMhdEwK6+Stt96S3//+93LaaadJMmFMFPMzbdiwwXgA4Pnnn5cVK1bI1VdfLZnGloo6uW3+8tbPnYvzZXTfMhnVp0xG9y03omlI907SIS83aWXKpIdtJpU1lGcCQ4qxRozvs6mw6RGn597LiNIY/8zsKHAajU4RhjjG2MWDRFuwCRMScW9YLxDHRpzZMLpoBaCX4LPiDM8R4gjBhJjhOIiyWDxzyRQdfhAsDvi/nxkyGzdvloo5T5hxRQ2rV3tuVzR2rAmhIxNdh65dPbdLt+dJJoV5p5p0u3aKkm74/uT49a9/bYQRIRGk0Wb8Bixfvtx4bAhXu/XWW3073l133WVerAy8hSeeeMJkJ4KrrrrKGIyE9P373/+Wk046Sb797W+bB8Ftt90mY8eOlS9+8YuSaXy8ubLN5737GuW1T3aZxVLYIVdG9MbDtF8wIaD4XFyQmJdFJj1sM6msoTwTGHZkg8P4Y8wIBq0NY/IyCjTGP7HXCGMeAw2vNWFbeEK4NnTO2PqPxGBD+NCBw28RW4hevCz81k2EMfbITugaj1FJyB778Lo3/BKAbl4CG35H2BaeI8QR5eHYeKti9cwlWnQkklDelEjFQHN1tVTNf8aE0O17+23PY+X07CkdTp4mBaedJrkDBkj1gayD3ZuaMuJ5kklh3ulAOl07RUlHcgJ2ogof4aV+yy23yLx589rMg3TmmWfKtdde6+uYHgwHe4xg1qxZY76HJUuWmNTjr776qnkQnHXWWfLb3/42pnAU9kW4B7Hyo0ePlmTz+Aeb5JdPLZUdVQcnnghFbo7I4O6djGj61ONUJt1KvMdgxWvAp+PLKZPKasFopJMBw9QarhjFdEBE65lIVC9ruP1mY++uPSebwMPO2cT5Mb4RoYOxT0cNgiKSdsZvXn75ZdNG2S+PaPbHs2z8+PFGePEd+0IU8z1tmbZgJ8OOtK6D7wW3lNvOMq9fv954LPFY2e1IHkEWOOdE3LHCufOMJqzOlh1hSKIPxkJF2v6zsa1F8wwLNDVJzeuvmxC6quefl8CBhETB5HbqJCWnniqVEyfK9u7dpK6hwbRX6z0kXDdcm02XuvbzGdleSJdrpyh+4ad9npA7AQF0++23myXRBM+15AUVNX/+fMkGzjmin1m2V9UZb9LHWyplyeZKWbq5UtbsqhEvydsSEFm1o8YsT3y43+MGvcoKTWieM0xvQNeOUY1ryqTBtZlU1kSEBSYixj9c722m9u6GMiCc50RYGKFbeD2oW0LQEBMICLxJiBuERCTeFvZJpw8CBGOP3yEcECZ4VOy8TE4vD5/5zh6TurXltqnVOWbw5KtuHiESJVBmziX4nAlRYxub5Q6xhlji/35AOYk+sOKQ8tJGOF6k7T9T21o0uHrytm6Vkh07JP/V16SCcUU7d7r/OC9POk051owrKp02TbZXVMj2A8IiJy/PCHxEN+9x2lK4NpsuY4YyNXQ6laTLtVOUdCQ73hbtlJ6lRdLzsCI58bBPPXLV9U2ybMsB0bRp/9/lW6ukodk7S9O2ynrZVrldXli2vXVdaWEHGXkgNM+KpkN7lkhBh9yseNh6lTVde9TChQWmutzhQq8yKYlHpIa285zwEPEdPdZ4jsiShgcbAxNxxN9IDTaEgd2GMgAGn51Al0Q3XF+2YX/W64NhS4gfAoeFeqVcdCIhnNiWuneeg5tRSQIGxJGbR8h6rPhrF/vZLxBJwQkZogmLTae2lqj7ss11271Hyl55WVpeWCBVLtlaLYWjRppxReVnnSUdevT4dF87drTui7ZlE1jQpmyWv3hERrKeTZkYOq0oSvoS91PqS1/6UtS/4WV63333xXtoxYWSwg4y6ZCuZrE0NrfIqh3VRjDhafp4S4XxPFXW7Te+3Kiqb5K31+w2i6UgL1eG9SppDc0jVG9kn1IpLdo//06mk849z6HixdOh3OF6b6Pp3fXboIp1f+EMbec52fFGeHv4P79BKHGurIvEYLPlRKAAYouF/WG08jsraqw3CMFEOJrN/EavPyKJz/zfeoTsXD+Uy3kO0RqVGM2IP/Zty0UZWJ8u4yXSxZOQyPsyv6lZyt5/X+SttyVv6VJi5SXPZbsOvXpJ+dkzpGzmTCkaPtx1X842YL2CtBdEfbwiI5nPJh1ToyiKn8T9hHrhhRei7j1MdUrq9kZ+HgkbSNJQJudN3L+OF+DGPbWt4XkmVG9zhWyucI9VB7xQbMvyb8ccgoO6FbeKJhuq16O0MO2uczhDOZ16nqMJCzRzkaS43OEM7UgNcb8Nqmj352wjhMkR2uZlaAefE4kE2B5xwm8IhYNIMqY5y4ngYF82cxv3KteWNN4YrXxnQ+X4Db3+eI8QQDajHTCWxIoo1tnJWp3nEK1RaVPL231x7qHSyvuBvSacN8kVqIfgUMF09CRE8jyJRrwHmpul5s03TbKFqmefk7LaWtftcoqLpezUU818RcVHH23C5kLhbAO0X66nFfZ2DFKsA/eT+UzNxNBpRVHSlw7JGgOkpBe8AAd0LTbL6aM/fVHtqWkwognBtGRzhfn/J9urzfglL9bt2meWeYu3tq7rXlJwUDKIQ7oxmWlqRFMkhnK69DxHGxaYDuUOZ2hHaoj7bVBFs7/gNsKCuMAgJ+Qs2NB2npMVKJyTc6wPRJIxzVlOkhJwTJuowHqUuLY2nTf7sb/BiKV8lJ9xSHauH/4i1vidc+C68xyiNSqT3Uvvdt9SNqZrSJcyehHuvoxUvNctXyEVc2ZL5RNzpWn7p2HQbcjNNWKo82fOkdJTTpHcAyI5EoLbACKctoMnKV6RkexnUyaFeSuKkt5o14rShi6dCmTKod3NYqlrbJZlW6vaiKalWyqlrtF7XNPO6gZ5ecUOs1iKC/JkZJ9PBRPpx5nstig/dA+nH0RiKKdLz3O0OMuNAc15EVaFsYwRlowe1HCGdqSGuN8GVTT7C24jeGDoUcdoRSgFG9qRnlMkBltwOdkn15D9Ux7KZgfOUwbn+CHW8R3lRBAhmMgqh2AjRA8PI+fBPtzEQjRGZby99NGGO9prYj1ntHFEBWF+CEmvffM91zrYyE/mWL1wz5NQz6TueXlSMfdJM19R/dKlnscoHDZMys+ZJWUzZkh+HBMEJ0pYZOozVVEURQWSEhYEzOEDOpvF0twSkDU7qz8NzzsQqre7xtuQ3dfQLO+t22MWS15ujhzao6RVMJk5m/qUS3mxv+OaIjGU4+l5TmWSBFtuxp4w3w7GMMYkXg1r0CZLJIUysiIxwvw2qKLZX3Abwchme9oA44ncrmu0hqVXO3GW086dhEDCezRixAjp37+/57kRCmWnK+C3Q4YMMamNbTmZdNWZFY6kEfG0h1gTnMQSPsl2djJcK/j5vHr16lah6LXv4PTUbtsQRokgYQxVJPdtNPd5uOfJQc+k/HypfOllqbz3PtnD+CKPcV15PbpL+VkzTAhd4YgRaRfK7IRzpY6JNOH5hHgPNZG1oihKuhC31cSgzljGINnsTEpmYoRNz1KzzDp8f0+umY+lsn6/l8khmtbv3ue5H4TW8m1VZvnvB5ta1/fr3LFVNDGuib99y/fHxifKUI61dzzVSRJsuSkHXg/Kj1cBgzhdxlBFit/hUdHsz62N2PTYftRfqHZiy0lY3cqVK1tFLqF2TpHrNNB59tpQO8QwZWW+uWBRgHGKkcpvEFOJEM2R3AOxhE+yH7xg7AtxxzkjZhBL7M/+LpJ9u3kIly1bZuqZJZLxadHc5+GeJ6a9deggde+8K53eeVty3nxLutXViZssyikqktKTTzbeok6TJ0tOho2rsdMtJmDaRd9IdSZQRVHSi7jv/uuvvz6te7CU5EE76F1eZJaTR34a7lFZ12jmaNqfQW//35XbqqQpxMCmTXtrzfLMx9ta13Uuzm8TnodwGtK9k3TIy/XNUI4l1CQdkjtQbsadYETaCUTTbQxVKgZaR7O/SNpIPEYU+8TABq4PHiKMdBsuZie9RhzxPYKH7+l5N2FXB5IyOA101nF+Xh6QZLVNt+NQburLzqdk05dHEz7J+RAqiEfNjqVijib+7/xdJB7i4G0IvyMkkXrgOruVOdycUbHOEVS/apXI/x6Xno8/zo49z59xRaTmLj39NMkrKZFMgzpjwQNrOx34zLi8dOq0SXUnl6Io6Ufcd/4NN9zgT0mUrKWsKF+OHtLNLJb6pmZZua26TUKIpVuqzDxOXuzd1yivr9plFkthBzL0lZqEEPtFE9n6SqW4oEPSMhylQ5KEWMLTEt1jGuv+/R4PEen+wrWReIwofktYGL9FzOAVwdBmbI0NF2NfiCa8GRzXzmeEEc/xGEu0atWq1vA/vCnW2Awej5Psthl8HIQ6cy/ZTHq2HTonuMULZLMFerUPPpOUgm3tefPXCsJo2n7wNpQN+L9XmcPNGRVNXTbt3i2VB8YV1S1e7LldwZAhZhJX0nPn9+0rmUy6PBszoZNLUZT0QrtGlJRQ2CFPxvQrN4ulpSVgwvGcczXx/+1V9Z77qW9qkQ83VpjFQqK8wd07HZRFr1tJYVoNRLYCgp51xpqES1/sZzhZontMM7VH1oope202b97carzHY0TxW5thjn0jjOxfGy5GPeHVINEG/0coWWMdMcTEsxzPJivAyxHsSUnVIPng49gxVHgOrHfGppCmvHhqWEd9sC11ENw+7DWwk+/yexa3dh1J2w/exmb7sxOjupU5njmjoKW+XqoXLJCK2XOk+pVXOCnX7fK6dDGJFvAWFY0ZnTVRGYluf3518mSKkFMUJXkkxFLhZXf77bfLk08+aUJGgNj4GTNmyHe+8x3zUlKUYEgBfkj3TmY5a1yf1pff1r01snZvk2zalyNLt+73Oq3ZWSNe4exE7q3aUWOWJz7c3Lq+V1lh6zxN+0VTuQzo2jFuYySWcTNWQGAo2qxzGL78jkH1sQiJaLxkie4xzeQeWS9xx/WJ1YhiG64D4WJ4gqwXBI+I9U5wHL7nWIgC6zWxIWV4ktgGkYFBz7gjmzwikrZJW2O/HINzjDfDodd4KGd7ZiycrSs6AWwKdOqAstAebAp1Z/sIvgaU044Hc+tEiKTtB29DmanTUGWOZc6oQEuL1L7/vhFFlU8/LS0HPFXB5BQUSMm0aSbZQslxx0lOfnZMuJ2slOt+dsJotj1FURIukOhxPf74401vJ9mXpkyZYtYvX77chOM9/PDD8sorrxgjUFEiffl1KSiQEX17yeVTx5mXX019kyzbasPz9o9tIhV5Q5N36nESSGyr3C4vLPt0LpHSwg4y8oBgGtm7RPoUNUu/0lzp1LEoqpAwN+MMMATdDDZrlFlDDSGBUYbRGI+QCOUBcZ5LontMM7lH1kvcEcoWa2+4U9jgMeQ64ylCINmJVrlG9rlo03Ujjo444gjj3aA8bGOzubEPxEUoY9O2TY5DKB+/JVEDoXqU388JeJ3joTgOAo5jOesKcUP75Dd8b71gwe3D7Rrwnf2917mGu2eCt+H/dp4qrzLb6xtOhDWsXWvC5xBGjZs+TTgTTMdJE42nqGz6dMnzqbMwXRMMJDK02c9OmHSZO0tRlPTB9yfoD3/4Q2MUzp07V84888w2382bN08uuOACufbaa+Whhx7y+9BKhuL2cg/38utU2EEmDupqFktjc4us2lHdKppsNr3KOu9xTVX1TfL2mt1mseTliPQryZURvTrJ0Yf1k7H9u8jIPqVSWpQfseHlNCAJC7IDv0nBzIvXCgjO136Hgcb52u9irUvuPzooMLLZH4Z2cM9qontMM6lHNrj9eSUTsBnlvIyoUEaqMxU73yGUuC4sdh+hjEkrsAjJQ1hRn4Tj0Z7CGZt8z+/YnnOy18PvCXid46Gsd8qrrsK1j2QJbOd9G67Mwdub3+zZI7vnzZPK2XOk9sMPPY+TP2jg/nFFM2dKgUvK9mwOZ03UHEt+tpFECjlFUTIT3+/+p59+2oTRBYsjOOOMM+Rb3/qW/OUvf/H7sEqG4mc4U34eCRtI0lAm507Yvw5DdOOe2lYvk0k/vrlCNlfUee6nOSCyvqpF1ldVyTOfLGtdP6hbcZvwPJJC9CwtdA3RswYkL1jKsHv3bvMZ0cKLmPPhXBFPbIM4wojl/KxHIda6xDtgDTxe8uw32BhOdI9ppvTIurW/4GQCTu/HgAEDXI2ocEaq0wAjW53XmDMvY9JZn+yf31Kfdv6jUOdHW2R+rD179phjx2pMOgUg7Zm263V/hjM4w7WPVAjsSI3kloYGqX7xReMtqn7pZZHGRtf95ZWXS9lZZ+4fVzR+fMLGFWVyOGs8+N1GEiXkFEXJTHwXSLz4Q720eQCxjaIkKpzJCUbJgK7FZpk+5tOX356ahjYZ9D5cv0vW7q6XULN0rNu1zyxPfbS1dV33kgIZeUAw2fTjg7t1au3dJHwO8YMhjFDhM+dHyBP3CR4FevYJl+L7eISErUvOGYGJ0OLYdtC/0xhOdI9ppvTIurU/ZzKBYOPdy4iKxEiNxwCLpT6dog1xhDhnTiREEmFk0dxPwQLQZtizacq95hULFQ4Xj4BKFF5lNqGRCxdKxezZUjnvaWmp+DQpTBvy86X0xBP3jyuaOtWMM0o0mRzO2h46YRRFyUx8t1ZGjRoljz76qHz9618/6OWLEch3bKMooV7u4cKZ4qVLpwKZcmh3swBhaR99vEy21ubKlvoOsmL7Plmzt1E2VYvUhRjXtLO6QV5ZudMsluKCPBnarUh65gekV2GllLe0yKDOeeZ8OD8MS8ZpROJRiKUurcFqM6bxf/YdfD8GhxdFM4Yhku0zoUfWrf05kwlEMqbMhjVSHwzwp94TYaRGW59O0UaSHMSRFUmcbzT3U7AARHhzzhioVmxFkpgkuM3EKqCSRcOGDfvHFc2ZI43r1ntuh4eo82fO2T+uqHPnpJYxk8JZ/SRd2oiiKNlJQsYgXXjhhXLUUUfJN7/5TRk+fHhrkoY//elPsmjRIvnnP//p92GVDMXr5R4qnClW3Aw0sKm2SzoWSv+cOuldUC9Hd8Pg6y+DhwyVDXvrD0xwu39ME8uuGm/Dd19Ds3y0xeklLZVcCUjvTjkyZFudDCjNkYbO9VLWvcVXAWHrEi8VY5oYcE6nBB6qUMZrtGMYotk+EYPH/dxnqPbnNabMec6IWwTHxo0bjfhALJBYwYZQBhupyRxMHyz+7ES0jBHi3orm2MH7on0hJBGE1tsban+xjJNJtMD2uhbNFRVS+fR8I4pq33vP8/d1nctl7/jxkjdtmvQcP15KDz1U8iKoT7/bQHv2pGRCJ4yiKJmJ729mkjDw4iQRA14kG3dNryov0/vvv1/OP/98vw+rZCihXu5+vvzcDDQmqARrrHilEj60Z74c2rNEZo7v29qWyYjHXE1LNu0f28QYJ+Zw8qJFcmRzjcjmmv3jFR5dtkLksRXSr3PH1gluzdimfuXSt7wopvEKzrrk96SAdiaG8DLC2J66QVhh2NswQGd4mNOos9m+COMLNeYhEYPH2SedLYgSGwqH4X/YYYeZ76M1PCM1Lr1C6CgP7Yhz51g2cyD7GDp0aJv9+FkfkRjZweKPTgDKjjiK9r5yE5LUPVn3ItlXqsbJeNXTQdciL0/2bNwkJe++IzUvviQBD89fc1GR7Dv8cNk+epRU9u1rBBHnE+m5BCdvsWnXmQyX38ZyX6gnRVEUJQ0FEsYS4TuMn7B84QtfkEsuuUTefffdNvMgTZo0Sd3fSkrCJNwMNIxsxA5CItJUwoD46F1eZJZpIz4db1dZ1yhLHWnH+btyW5U0MTGTB5v21prl2Y+3ta7rXJxvxNJ+wcTfchnao5N0yMtNyDgV0j+TRhqD120C0mBjEkMbTwlp/EONeUiEUUxY17Jly8zxEXL8xdC0AiBa8RFpnXmFgtqMdwgi1jHeC/HYt2/fg47tV31EKrT89Cx4zadEuOimTZtMyGio9paKcTKh6slci61bpWjTJun2zjuS8+prItXVUu22o7w8qR892oiiTX36SEmXLua8O5eXR5150rYB3pc8eyiPnSg3nrTr8XYmpWuacEVRlFQR9xOQF94jjzwin/vc58znL33pS3L55ZfL0UcfLcccc4xZFCXWl3siZ0rH0AP+74fRVlaUL0cP6WYWS31Ts6zcVt0mIcTSLVVSXe+denzvvkZ5fdUus1gKO+TKYb1LDySCKN8/b1OfUikuiG/cD3VrjTzql3pgHUa7DQ8LNuypNwb9Y9hxLK8xD4kwiikLoWyIOIQsAoXPpDXnGLGIj0jqLFQoHiLNrmdfdj6jSEVWcH2Ea/ORCq1IxV+k48mC51PiuHSCYejb+Zy8RGkqxsl41VNZfb3se/pp6fLUPMnf9mnHRDBFY8dK8/HHyaKyMmns2NEI8rza2tb7JZbMk7YN4H21yVtoCyypyjyX7mnCFUVRUkHcTz8epvSmWR588EE55ZRTjEBSlHSeKd1O3JlIo62wQ56M6VduFktLS8CE49lxTcbjtLlStld9eh8FU9/UIos2VphFZINZRxTekO6djGD6NP14mXQrKYxYWNrQQsbNYLDhGWAd3gHraQg27AmVRSDhuQnlmUiEUcz12n/uOW3+4sGw8/zEIz688PLG2LTZCDSEI4Yv4VLBdcFxqV8EHdtRh/w/uD4iafOhvFmMheL8bEgz44PYJ2m5WUc9OcMto73HuO4sVhBwLNsmbFIVNyM/FeNk2tRTba2UvvOOND33nFSs/MR87zarWU7PntL1nHOk/JxZEujbV5566ikTBZGzd68RRXZCZ+qN+nTLPBmqjTnvCbazk0QjMLmfUpF5rr2mCVcURUmoQCLM5t577zWGAkYVELr0/vvvh/zdhAkHJqpRlBTNlE6bdR4nWYObc3Nz5JDuncxy5tg+ret3VB2cDGLNrho5oAkOgvWrdtSY5YkPN396rp06yODO+dK7qEn6FQdkSJcCGTu4twwbNsy1Zx9jl/WEypK2GcMPI99rUlkMceoJUYUnx0toJMIoxhDnmJSBjhlEEZ/tsUKJsXgEt5c3xhIs2JzY4xJ6h7fJigzqAk+Tcz+RtHk34Un5GPtECCIeNeA76oZrygJ8HjlypBmzZcdM2ePxHb9fuHCh+cv52nEx9hzwHhkvTFmZMe45X/5yHZyi1E0kJDvjWH5unpSsWCGBv/5NOnzwgeTQGeCyXUtRodRPmCgdzzhDhs6aKfkH2szixYvNOVBGQifpPLDjuEaPHm3EcHDmyXBtzLbTFStWtHqgCPHlnktV5rn2miZcURQlFHG/nW655RaTtQ6vEfCA/elPf2oWN3gRsA09mUr24Wcsu58v7lAGLr3s6RB736O0UE4o7SEnDO/Ruq6mvkmWbT0wrunA2KZlW6ukIVTq8Zoms3xKk3R8fbWM6LVdxg/q3jpf07CepZ4TkDoFqJvQwbCPRFjQM45RyfWzaZ3jqV/KhoGPxwaBZD02JESgYyaUGItXcLuF4tn03uzPihU+06bstny243YQlQgYGw5I+fnetrtQbZ57i/9zTBLh8AxF+CBwWdgPAsyOIeOaIcr4js4r1nEtqDtbPns8fkMZEVkY7gg4kk/QAYaYsnVHedkXZbFJBtg/IsmKUox+L5EQSRKDeJ4fvF/qly2TisdnS9XcudL5QCKWg8jNleIpx0rOiSdJ4MhJ0u2AyHYei7oC2gfnCtQ512b8+PGu5QrXxvgNHTPUrU2Rzl/KTbtORea59pomXFEUJRRxW4LTp083L9x33nnHvAhI0PC1r31NJk+eHO+ulQzD71h2v1/cXmNN0jmMpFNhB5k4qKtZLI3NLbJ6R02rp+mDtTtl2bYqOZAgz5XaJpEPNlWbxVKQlyvDepXIyN6lMrCsi/E6DelTJoP6tc14F+8kpfY3GNLxwjEx2N1EbbgyhhMfsRjmbI/xjEAgjA1xEBwqZZNH2I4hKyasYHHeJ/we4UeoHF4LvkeE8L3T84BBjVghIx2/43iIG/aNR8NZPraz6+yYrQ0b9odp2hAxxpPZdPdsi2DCeEd02rpmsfM82TFIVpzxO/4iSk2WxxiEaLjnR6hr1Lhtm1Q+8YRUzJ4j9StXeh6jcORIM4lr+VlnSYcen3ZEuEE9UHdcJ0QhYpQ2M3DgQM+2EUmnDufEuSDq8bxxPag/2o1TLCeL9pwmPJVoYgxFSW98eQoTInD66aeb/z/wwAMm1ffJJ5/sx66VDMLvWHZ9cbuTn7c/YQPLuRNE1q9fbzK75ZZ2lzV7Glsz6G1ryJeKxk+zSwbT0NxitmNxMqhbcet4pv0pyMulZ2lhzJOU+j2uwUvoBq+3E7hag9qKgWDBHcrjEc5QtWIHgWFDzRA2/N+CtwfRY8PY8OqwDuGBIYrhvWrVKrMOQ5nFjldiP9Qf42Aok/WaYXzb8XOUH2MegYKosR47sIk3WGe3Z59knmNb7jEWjs8xrdcPQYDhbsWe7Ziw4ZXs06ZY5zycWewQarEko7AeMrc2w36Dr9GeLVuk15q1Uj13rtS88cb+mFO39tKrl5SfPUPKZs6UogPz8kUC15/2Q11RFxzTzs3GPRcs0pzjzPgd9cL5cc1Yz/fBXkKuCdedNoAY5ZyTnSBB04QnH02MoSjpj+9P4AULFvi9SyVD8DuWvT29uIONRc4ZQymS8+Z7jOb8QJ0c3b9ERpY1ysTCbVJRsVUq65tlr5TI7pZi2d5YYJZttTkSIvO4rNu1zyzzFm9tXde9pEBGGtFU3jpv0yHdOklebk5C2kK8vatuBogVA8FjzoI9Hhiz/BZxgOAKdWwrVGwmMudnC2GLXB+ECfu22yGW2BbjmONbzwIChXIR8sZvCGe0oXv23BBFiDH2izGOoKHNIHqcQodJYdk/66gHfoMXCGHDtuwTTwZzZfEZYx3hw7mzrQ2fswkF8JJRT6xn6gbuT7DXir9sF87z63Z9+B3HdWszrYKbMTvbtknz8y9Iy/vvyzZHgqA216W4WMpOPdV4i4qPPlpyHNNQRArneNxxx5lyInqoa0DIBAtpcI4zo54QUXZuNdbb55nTM46w5Ds+E34ZKtFFIgi+z0hPn43P13RDE2MoSvqjT0IlrWPZ28NM6cHGIueM4YQRzHfhPBpunjZ6uk0YVn29HFpeajwMGMmFhQEZd8REqcnvfGBM0/4sesu2VElto/e4wJ3VDfLKyp1msRQX5MmI3qWtXia8Tni1ivLz4moLfvSuuhkgVgwEh+c5PR6IAusRoucfz0GoY3OdECKIDn6LkY8x7RxjSd0jeFo9H3v2tP7WTrrLegQTY1MIqeMzwspm7WO/NjyPc2Ibyof4IRzPGuAYuFbU2Cx2nDcL++Z8EEO0LStAKLed02rp0qWtAgvRRTviN/we8cI2eMjs5MMQqRANNx4MUcH+3dpM3fLl0vFf/5aS99+XnD173F9cubnSafJkKZlxltQffrg05uVJFZ0HgUDMLzrqcsyYMeb/CFEmKXbzcIEdo0UIKGHnXBPqHzFqwyytN8zer9QD15LrZhNfxNKpFEuHgnoxUocmxlCU9EcFkuIbGhIXG27zDGGM4Tmw8wyF6lV287Rh/DiNTpvxDQOutLhIhvXuLIcP2G/YQXNLQD7ZViELPlgpizbskbUVTbKhWqSqwdvVtK+hWd5fv9csFjxKh3QplCFdC6VXQbP06dgo/YqrpUunwojHNdj64LwwGG0IGkZz//794zJAqIPgOgxOvczxuRYIDISE07ANNkKdWQCd6ePtNbDjeuz4K9ZRJoxh9o0QswayndcJLw7w1woG6oDtqQ87qN+m7WZflI/t2BdeI1tW9k9ZMPL5jIGPhyNYgNixXeyH39ikGvxFADlFAcegLPyGduomRGmPoZKfuF0fztFmi2OfRbW10nPpUtl3+x0m8UKpx7UuHD5cymfNkrIZMySnW9f9gm39et/n9Aln1Dq/4y+ClPq0bcPZAWLvV0QoApfvnYkuoulUilXoqBcjdWhiDEVJf1QgKf41pnYUEucnwYYX9cZnO+dKJOFpbuNv7BgSm/YZQ9ptjh4rbMpz6mRkp30ybmxJq8G6o7pBmsv6ypba3P2Z9LZUmvA7LxBaq3bVmcVJ79IcGdO/SkZvWN06tqlf5/2TZLrVB+W2yQCst4Re+Uiz4EVjgAT36HN826NvJ/BEuLgZoXgHEH7BA9y5B5zb2zA1DGLKw+8oEwLDGsgIJMa7cM7UvZ1vh2MjSKwociZ7sELY1H1zs7nWdhxLpGW17YF6RVyxWAgTCycK3L6nLM79RHJ9EJGD+/aVljfflNp586SZqSJaAuIWRNeMwDzxRBn4+c9LpzGjW9e7CTa/QtbCtSnnd7beabt27Bf1y7V1jl9i4bzjSZAQq9BRL0bq0M5ERUl/1HJV/G1Q7SAkzm+CDS834yqWUEUMJIxijG3CwLguzklCwxlM/Gbfvm1yWL+OJnOXpbKuUZYeEEs2/fjK7VXS2Oztbdpa1SBbl26X55Zub11X3jH/oGQQQ3t0avW+4P2yyQeoBxvqFUn7sgYI3jibQIExHjYcykvYI4oIuePcrfeG8uDNwSPgZoQGdwpYccScQZQdTwpZ42y2Mn5vj2kNZMqJOGK/nCueFJsdjnbA9qy3HgjqBdFEeTC4+WzFE942ymHTiLNPysM5RduBEYkoiCWUso2BuGWLdFq3Tnou/FBq3npLWg540IKlc05RkeQfN0VyTjpJOh59jPTofXBbTkSmQtcyu4iZ4O8QiNYDacNmCbvjWju9PPF2KsUqdKK5du0t41qiz1c7ExUl/cneJ5yiZAjBhhcvTzwNhEJhZPP/4AlFow25sfMbOV/ywUaAV5a3YIOprChfjh7SzSwW5mV6+cOV8uriNbKzuaPJprd6T4PUNnmLporaRnlj9S6zWAo65MphvUqkW26+dKzvIINKm6V/yafhXqGMvuDzIRyP8T4IRELr8EoxwN4t9MgKe46D2Ag2ghEaCBjKgHCzCQUQMMHJNTiGc0JV6pHvETBcS4SLs4ef8lB2G0aHOLJjxvgd3jPaAgY2+7DhfwgnzgvhZrOJ8p0N02M/NnsaZaVMwXNcxSsKYu0Jp74H5uRK4csvS/0zz0pgxw6z3m12r8YRI6T2qKNk4IWflT5Dh8Zk9MeTqdBZ5lBixk0o20QrdqwZ7QjBHOzliadTyReRGuLatbexSsk6X+1MVJT0JvueboqSYTgNL5siGDCYMcRtOuV4EhQEh9xEk+XNaTB59awibMb0K5f86o7muCUlXaSyqko2VzRIU2lv2bQvx3ia8Dhtr3LPPGaF1kebbNrxMpHt+z0JvTsFZGBZjkxs2C3H1HU0HqfuJfuzinmdjxncX1dnymgNx3ChR15GML8zIYc7drSm88bYxdvEsYOP6ZxQFXGDmHEbj+Icp8Q+8XLxnfUW2fTctAG7PduxTwQQIKbwVrB/9k1KcLZlG76zCR5oVx999FGr2I6kPQXXhw3147xt3UTjAWnavVsq5z4pFXPmSN3ixZ7HbezdS3JPOkkCx08V6d5NKrdtk8b8/LDl9TL6Y52bya0+QrWd4O/sZ7x8eI4QR35k+HQSj0iN5Npl01ilSDxD2XS+iqJkkEDiZU18/09+8hP5yle+kpU9UIoSLda4svP2YNhiLFvvAwZQpC/nSEJuosny5pznJVTPqpuhNm5In4N6XndU1ZvwvP2Caf9kt2t21XhNYyOs3lLTYpa3tmySu1/bZNb3Kis8EKJXLn2LW6RD1VbpW14gvQ6cD2IGMUHGNVsPNgFG8PmFM5xs+JodB8SCZwdvEvXVJeiYpMC2Y6ioExsO5+zhBybY5jdOLxPb4BVC1NiU4PzWZrSz1xiBxMK+beIH9oMwY/+cJ7/lPNiGsuBFsmUKTtHtZTDatkkdkeSBsWB2PiZCL4PnQQr+fUt9vVQvWGAmca1+5RUakut1zuMcZsyQpilTZJUEJL+gIOoMiF5Gf6RzM6XroPxQ7TOecK1IvBjZMlYpUs9QtpyvoijxkXR1MnXqVBP+8a1vfUt+/etfmxe2oij+vZwjMcaiyfIWac9qpIZaj9JCOaG0h5wwvEfrupr6Jlm2tUo+3lwh767aJos27JaNVS3S6BZzdYBtlfWyrXKHLFi+PzwLivNrZXDnWhncJV9KmwIyoDRXulZWSeeyUiMMbBY2m1rbJi8gLC6U4US9UEeEttkU7HZ71ts6tOOdnBOqsj8EL/vCu8P3iAr+z/PPeojYlnFKCB3C5djGltmGSdpkBniBhg0bZv5vx2ZZUcp3zjFJ9tohaJxz7SCuCBu0os6GcgYbjNY4J5kEExKzX84fDxW/payss+O8jjjiCClkUtn33zeiqPLpp6Wlqsr1GuYggqZNM/MVlRx3nOTk5+9PPHHAkI0lcYGb0Z/qrGHxDMqPxLBPZLhWquvOLyL1DGXL+SqKkmEC6cUXXzR/eei8/PLLyT68oqQ1frycIzHGMGYxtjB6bUKCcMeJRLzFaqh1KuwgEwd1McsJ/XJl+fJKyS8olEVrt8mWug6yoSog2xsLZdM+kZpG7/3sawzIkh31ZrGPt7xFe6Vvpwrp1ykgvQpyZSyT6ZaXSvWenbJixYrWuWgQEF6GE/WCGEEYICTYxooQ57XiOzvRqhVL1D1i5r333jOiAmzSCRtWh0fGrmfuIRaOT8IFRAnXE9FlQy5ZMJzt+JVgrx+wPR4zrjG/Z392IlrCBRcvXmwEjk0KwTbgTGluQz45HyumEHDsg44uzsHOBcW2+1atkqL//c/MV9S0cb+nz42OkyZK+cyZUjZ9uuSVlSV8AHuqs4bFc06pDvlKdd0lu/MpW85XUZT4SFl8Gw+nM888M1WHV9IAZ9iIHduAwdgesiR54cfLOZwxZlOAY9DiocAAxrBnstBQx0lWz6rdZ01NtXTr0CD9uufKEV2apXfv7sZQ79xviOyVEjOeiWXplkrZtLfWc38k19tQHTDzOokUyOwNZEmrka4FLdIzv0EGlGyTfsUtMnXcECluaTEGP+2SOrH15nZd8DxBsPeG5BCM9bHJIRBFr776aqsAQVjxHQIDrxDXCHHGOrwxiCNr+DI3EeXAg8B1skYx+ww3yJ/yEapHnXEMxA3HwEDkuHZ8E+fG94hE2y6sx4IkF6yjDAgjztWmj0fUsTTs2iXdly+XrosWSdG69ebYbkF0BYMGScnZ+0Pomrt1k/qCAgkcGEcVTDweEa9wtEROQRDJ2JZYzynVIV/ZknEt0udXtpyvoijxoXe8khKcYSMYW3beF15c9I5nc5akUMTzco40NS3b2HTZhIxhKGDI2yQCXiSrZ9UeB+8JBrg14vGemHEv3UrkqN695bTRnxqbe2oaZPHGPfL2J1tl+bZqMw/T2j31Zl4mL3Y35Mruho6ybH9WaXlwzVYpzRfpVdAoPQuaZXjlRtlRlytTJ4yUwoJ81+sCwd4bew1scgg7Nw/tm/GXnBNtHuxcRghVvseb5KxPrgeCi+uDgLFhe5EYydQhAoc6Q5QhyDgOx+e6A3XLdogfvuPec6Y0RxjxPb/hmOwLgZTb0iJ9NmyUnh9/LL03bTKf3chhvqITTpCO06dLt2Mnm7BCU+6dOxOSHSyScXL2+vDXD8M30VnP0iHkKxsyrkXz/MqG81UUJT4SYn3Onz9f7rvvPhNfzwvaObgY7FwdSvvFGTZCe7ChPhhudnxHNmUNimZejVheztEYabZH2hrb1LOd3DMUyepZtcfBGCQhAAa5nRzVy6Dp0qlAjj+sl1ksdY3NspxxTWa+pgpZsom5myqkPkTq8apGlnz5pCZfXt8j8uDyDVI0d5OMNPM0lcmoPuXm72HdSqVDhzzzm+BrFdzjTxun7ISxWW8RYgQvDgKE7xAmdvyOW33GYiTbFOG0DcpAGJydtNaG+tkse9Qx5aEM/CU0j/LbcrNN927dpNfevTL47bel75q1kn9A5AUTICHF5MnSdNxxsm1Af2nAK9whTzYsXNia4S9RoWKhwtFoN4kQMokOgdOQL39IJ89Qe5tXSlEyEd/vyNtuu02uvfZaY8gcddRRMnbsWL8PoWQBTiPSziuDQMIgw2jMpqxByZhXIxojLZ4e6WT1rFrPCceK1ZAoys+T8QM6m8VS39AoC95ZLG8s3yhb6zrItoZ8Wb27QSobvEVTXVOLfLB+r1kseTkig7oWydj+XWRs/84mmx6pxzsXFxxUvzbjHMLAeoto72QMJAwuVAY4C9/h1UEwIl7Y1+DBg816Z6pwG7Zn03uzHfu3Y6xs3dqxSPyf8nDvER6IQKNtOstfTFjem29K94+XSt8Dcy65UdGnj9RPPkZ6fuYzUty3r2nzpj0eaGNuWQX9vs9DhaMlSsgkOgQuEsNeDe7EhDkmol7b27xSipKp+H43/u53v5Np06bJU089ZV5EiuKG04i088rY7FjZljUoGYOsozHSMqlH2m9BRqjcKUePlUO67Z8Mdv/4tyLZta9ZPtlZK8t31Mr2xgLZ3lAgO90dJK3jmlbvqpPVu7bI7A+3tK7vXVogQ7sVSu/CJulb3CD9OlZLz5J8I/a4LoSSOr1F/D8aQ8xmpbN/+R0Z+BBNnI9Nv831xBtLGm68+DZ7H6KI/XMcxjpxv9mxR8OHDzflMWJs/XrZOecJKXznHRm6bp1nPdR36WwmcW3GW3RA9A0bM8Y1rbZNWpHIULFQ4j9RQsbvEDi3tpAogzseARDLbxMl5BIhOhIlZFKddENRlBQJJF7G559/voojJSROI52wG5vmmFAe/p+uBnssJGOQdTRGWqJCTdKxFzuSAftm/M+OHdKnc1c5ovf++aAaGvZIWbdeEijvKxW5ZbJsW7UsWr9LVu2sNeLIi61VDWZxUlbYIiP7lMngzh2kV2GRDCkrkD799qdFj9QQs+PGaEP2+vKZTgU8S4gcG85nMxTyPfs44YQTTMY6zpN9sw3fs28EE/tiv0X5+VL1wgLZ+/j/JGfBi9Kz0T1dYG5ZqTQdfbRsYh6lESOkZ69e+0PwGhtb0727tUeb4Y9j+y3MnV409sszBW+a8xh8n4ixPKE6HKK9J9zagp0Ti8lmrQDGe0gCD/YVq8Edr7CK9reJ9JwkQnRkqsdRURR/8N16IayOyQQVJWTDCzJSszmLXTIGWUfrFfLbMxNs/LB/jGGOQbhXKnqXwxlk9vwxPPHAkGzBhJQVF5twsCED+8rIkSNNmSaVVcmurgHZtadeOnTtL+sqm01o3tJt1bKxhjA873JU1jfLW2v3yFuOdfm52+WQLsvliEO6y8CyXCmq3SlDuuL5cTfEvIwqBAHr7Tgnm2zBekxYhxeJ5BDOjJHUgzEAt26V4i1bpOeij6Tq9ddl75495nj7/VOfEsjNlQLC5y74rJScdKK05OVJ3oG6tXNKOdubW3skhI+QQtYnMmTJq+0lynPq1eEA0QoCN6Ocsbz8jutu59haunSpOV6/fv1iNrjjEQCx/DaRnpNEiI5M8TgqipIYfLdA7777bjnjjDNk0qRJ8rnPfc7v3StZRHvJFJSMkLZUD0B2Gj8Y6YR9YaizDgMjFb3LXgYZRgn7tMfB6HQaLNaYJkTNOQ8RXhIzb1FDnUw97DA5umdA9vQSkylvT0OOLN9eI9saCmRTTY5sq8+XPfXeriYmwF25q15W7vp0rqAcqZW+ZdUypHO+9MhvkGPzdsmJJV2ke0lhSKMKrwIhcniR7Pghzg2RYI0ue69ZEdqxulq6v/iS5L36qgQ2bDDbuKXoCAwdKi0nTJVthx4qwyZNkrKBA836XBFPUUDWPtbhnaKswZ0ewfd8vGFeXB9EBOfLNeM6sS/EkfNYibxH3M7LZi+MRhC4GeWcG7/l3OwcW1xvQhYRSLEa3PEIgFh+m0jPSSJER6KETDTvg3T0yitKeyHuO23cuHGuN/Wll14q3/jGN0zsPT2WTng4fvjhh/EeWlEygmRmfwsXUuM2mN+PsjiNH2us4xEkrAoDMVm9y06DguQfGJNOgwxPEYkOMNqd18KGYDkNFsqP0HNO7krdMfEqogRvCGKQ7weXd5SOzTWSl9dsjsl5V9YHZHNtrpl/aV1Fk/m7u7GDeMkm1m+qbDIL/HfVWpG5a6VXWaGM7F0qvQrypKRpt/TM3yp9ygrkkEH7xYoVSBzXZiV0M7rq9+6V1X/7mzTMf0YKVqwwIsetLC3dusm+IydJ8/HHS/GwYeZadGhsPMgwDG5vbiKXMiRKGNvfIiD4PdeCa8Qx8Wq5Gd6h7hG/jdFYBIGbUU4Z+L3NBmv/2nFokRrcwefHezlWARCLeEik5yQRnVDJ9jgGtzVN5qAoqSVuC42JDe2D2kKoCjPHK4qSHt4y+7J1G8xP6FO84wCcxo9NHY34QvAkq3c52KCwE5mSGMGOtbGT5PLcskLMjtVxzmeE8YJngvEfnAv7IVzNZltknRWA7JP1diJVO3cTSxfSqXcqkKk99qfKbgzkSKC8n2ysFlm9t0F2NBTIJ7vqpKHJfR4h2FZZb5b98KwtlKI8kUFLN8uAkhwZ0qWLDOjVTbq1VEt9bY1JAGHHKgWamqT69delYvYcqXz2WSpa3MzRQFGRBCZPlpojJ0nNoEFSdCAleVUUhmGyw67sb2nH9jrYyXid3rNISIQxGosgcDPKbTINxDltC3FvJzGOJstd8Pl5dQxEIgBiEQ/O3/AcohPFXjeWeJ4/ieiESrbHMRhN5qAoqSXuO/3FF1/0pySKoiQM+7K18+DY+acwUvwYB+A0fuy8RRiu8fYuYxjakK1wBkqwQUGIH7+14XH83np8OIZTiCF+CFdyGpN4itgWgWVDtmxPPh64TZs2tc7PBNZ7Q/2yjs92PBD7ZGwTddO5abcc2r+7XDhxkDHAJCdXVmytlLdWbJKlW6tl9e56WbmzVipqvQc21TWLLN/dLMt3M4hq/3YdcnOkZ2FHGbChWiY2rpYjPvlAKhe/LzkVn6YnDx5XVH3ooVJx+HjpdfbZ0pSXJzu3bpWdmzYZzz8Z6TiHUPXu9EogJoM9dokUxva3hJ5xTahr6pfrNGjQoKh6+hNhjMYiItyMcv7PgjfTJrTBexkcPhiqnG7nxzqucfBEx5EIgFjEg/0NnRV4/bhe3F+EsVKeeDtpEtEJlcqOLU3moCipxfdg1ocfflimTp1qHuBuMJP6Sy+9JJ///Of9PrSiZDyJijm3L1trrNvB/DajWSzjAILLyj2PwURPN8IEY85tAH+kxqRdx1gLDF+ER3B67FDGNiGEdi4gjEAMaUD8hOrVt8akFTt4kui157xsSnrrSbLjfSgXdcpntuMYHBcDkLJQV5SHeiBhAl4757Ud1a+zWSzse3NFnSzZVCGLN+2VV5esk1W76qWiqW24spPymgo5dvn7Mm3DezK4cqvndnX9B0iHaSdJ9RGHy64DQm7vgdBBrhfijmvHeR533HGude3mlWDh3DlP6iKUMLZthzBIvCK0RfsbOzcTyTOsQHBL7GD3zTHtpMeUlXmWojW2E2GMxuqBcDPKyVgXi5AJd35c41gEQKzPKbaxYpZy0GnAvdQe0lxHW2eazEFRskwgffGLX5RHHnnEUyC9+eabZhsVSIoiSYs5ty9bDF9rgOKdCR7MH2k5KSNlRbwAhg73vE09TFhQNMaAmzHJcVauXGnEEUY0hjAGNWVnzp7g8VNOg4Lv6HHH+2M9ZqyjjKwL1atvjUnWY0jaRAAYkzbbojX0WGcFJ9niAKFhQ/zYHm8T22AQ0mNvvEYHhJhb/VhDqrmhQcZ1K5BR5SUyvKFR9vaolEB+R9lYkyPrKpplV0tH2V3VJIes+NCIosN3fCK5HiOcdhaVyYIBE+T5ARNlXVkfKa0VGbg4R0b0LpchXQpE1m2Quh3bpCC/Q2vYNB4yrvGYMWMi8kpQr7Qv2qxNt+01Fsa2c7annhDUNi03Ag2hxvHtteAYCE7aqr0nnKKa3/IdnqNo7hdb13i/TEihIxzTj/Exfnkg4t2Pn8Z2vOPGGANoQyMpB/cO7S2b01zHUmeZNF+domQjvgskO4DUC15kmoVFSWdSlTkoEWE+wfPD8BmjntA6O0g7mpeufdEjXPAGsy8MHQxdm5yA8KxYDLrg3+BBsOKI7zDcN2zYYIQP5xOcHc9McLprl/meEB67DQvPHcqN8RuuVz/YmOS41JEVldQd6/k/BjUeE2to2jFOHJvteR5SPwgjFnt+XsaS23dA3fL/iordUl5fL8dtXifDN22W0iVLyNLgWp+1eQXyWt+xRhQt6nGotOSQlmE/VY0iS3Y1y5JdlQfWdJQOOYdK3+KADGrOlX4lIh1rd8qh1fs874lgr4QVFtQVdeZ177gJK84fDx/rrNeR644At94lQiCpc+c9EcnYm1BC1CnUuGb85RyybS42P43teMeNcX9wfOqY+4PrbdtLthJLnaU6M6mitHd8udMWLVokCxcubP38yiuvmJdPMDyg//SnP5neX0XJtJ4+SKRw8jvMx21+GDw9pODHEIwli5190dtEBNQDHhrKi+HD9wgkP7D7xnC1Bh5wrODseHyPF4LjI4bwQnD+1jthw8YQThiGoQw5N2MSccMk2BybfXIM6tRmTbOGpp3Qlf1j8GMIISJpP3aMU6j0zxA8jooed+ogf/MW6bNkifRd9Yl03FfrWvYA12HQQKmadKTsnXCs7KlskeJt1XJoMxn1RKrd5341NAVyZX2NmGU/PeShzTtk6OsvyYASkZ4FDdK3Y4sM7VooQwf0Nu0z2Cth5x8KVb9uwopQRELIgAH81svp9NQhlmivzpDQcFnpQvXaBxut3A94KDkH2hfn5FlXaZ5+Obh8tC3qmXZEnVNeO6lvtMQ7boz65vhcX8pJhwMCOFvEqJ91lurkPorSnvHlif6///1PbrzxRvN/bv4///nPZnGDBzXjlJTMIN0NgWT19GFc2NAsv8PfEhVz7nYulJ19W8EX64serwiwbwwcDNhIPMjRQFtjbA/ChHOxYEw5s+PZMT94tQjLwsuAIc1ffofhjdGLSLJzM9nwQrc27TVQHs+UrU+bOW3w4MFtDE1neJ5N2mCTQERiLLEd58u++X9g927p9trr0nPJEum0Y4dnXTUjvk46USrHj5fdOTlGpI7r3VuGknCh5UMpL+8ghYV5sr2qTlbsqJXcbgNlT6CTfLylUtbt2u8lcqMlILJye7Ws3B9JeYAm6Vq0Wkb1KZVBZfnSLa9W+hZVS++yAlMX4QzdcO2cvzYxBteWZxCCFIGLV5E6xVMYbdKO4F57tzFrhEfaa4TgN0k1Onc218IeDxIVCusHbh0j3KMIextSS51YwzuZY2Os54j7j84a24HAuLFk1V0q3mk6nkhRMg9fngpf+9rXZMaMGcY4Ouqoo+Smm24yk8U6sS8gemLT4SWihKc9zsPgZbzaUJ9EzAKfqJjzRHikqAOMVmto2TmCbMpemwgh2v3aOg7u3SYhAxCGg5EMHNdpmLGe7zFmKRfGlx3/w75teBpii2cUXiTnPEjBbdrLgIok3CUSQyhUxj4EXtXOnZL3+uvS6+OlUrJqlfTwEJ31xcWyc+RIaZl6vOQPGyZNB4z4Qx1zD2HYWw8UdVLQ0iKT+hbJ5MlDWz1alXWNsmTjXnl96QZZuHaHrK1sli01AQmReVx21wXk1TWV8qpjXVlhi4zqu0fGfLJCRvUtk9F9y2VQl0LZu2f3QamlQ7VzviOzGdeVMluxy/+tF4/f0BZDPY/Ctf/g60D74xg2pBKRxtgzxDCLbSt0lvgdCusnwcJw8+bNpg1YccI9a8NhKW8yx8Y4f8vxbOISlmx+p+l4IkXJPHx5IpCRiQUWLFggI0eOjMlQUtILv8fEZII3yst4tYOIw4mNeM7Rj5hz5/FtiJKfA7MRItbAAgxHjoH4oBc4WkOH/S5fvlyWLl1qygsYbiNGjDAJHzDojjzyyNZxVG7Z8SgDZUMM0FZZ7Hwx/B6Pk022YD0SeJXc2nQ4Ayq43buFMlGmUMajm7HUs0cPafzgAyl47DE54v0PJM9jXFFzhw6y7ZBBsmHoUNnWq5fksf/iYhlSWCiH9O17UMgkx+Z5jIFs577C6+W8TsUdcqRL0y6ZVFYl40bkSkFBkXTt3lMCZb1k+bYaeeeTrfLhup2yvqpFQmQel8r6ZnlzzW6zWPJzc6R/aY707yQyuHO+HH5Idzl54oiQ7ZzvuF5cPwQjRjTClnWIJn7H+ybc8yicWA2+DrZ+eHdxj3N8RDf7pn0joBBMlNNmzmMbPzLe+UmwMKTzwmYXtFkmbTgs55LMsTGpHleTrLmF3N4DOp5IUTIL359KvEB4wahAynz89EBkijfKq6ePc8eooFcZo4i/GG2MkfHzHOOJOXcLrUE02DEzfgzMxoBEuGAs2rFBeCLsvEr0Vkdj9LBfjHfbo20nYSWcDRFjPUm2Ttyy4/HZpt+2hjD/t8KNfSKsgHXUE/txa9NOAwphxXmuWLHC/AbRFm7yTerXpjsPZQByXCMyN26U0tffkJYFC6R261Yp9qin+uHDZduIEfJJzx5SdWB8J+IPbwbQzpxJICwcN1yKaDejcffO7XJYty4ybtIA+czhffZPMrx1q2yuaJAtdXmys7lIttXnmxC9TyexPZjGloCsqWAReWVzvTz88SbJeWqTDO7eqdXLNKpvR+lQ0izdS/aXibIRIsj1YeHaUl8IaIx9PjNWiL/UodfzKFyvfbCxzv5tBwDH4x4HhAW/x3tFe6Bt0aZ4HpCy3aZ3T0aSgUg6YIKFIfe/rUewE7tzDqkYG5PNcwtxfXjW8EyjfXBPOTMvpoOHUVGUyPDdMv3GN75hHjyEKTCHxvHHH2+WiRMntjEmlfTHz7jpTJkV3KuHE3jh0QHAX8Awsj3MboO+k32ObsfHOHLO0RNNlq9QhgU9+ByL1NYYibEKQ5sOm2eDnW+Hz16Gr5tx5RyrhCDEoCUky2Y+Q7SxznogMHJZ2E9wm7bnyW85Hzv5qD22M1kHhhBjVqzXKJLrbVKXv/uuVM2bJ4VvvCkF69eLl2nW3KeP1B5ztPT+7GelS58+Uk6ihjVrTPgZ++EZyzgOyhhKKIQzSMMZjc57YqhLO9lZXS8fb640YmnJZpYKWbOzRryGo7F69c4as8xdtKV1fc/SQhndt6xVOA3vWSJDhg6VHQdC3+z8U4w/on1ZDyHX2uu8w/XaO+uGOrUeFRYEBO3AelwQTjZdux3PRrm4B/Ce8p2duymSDoJovc2RdsAEC0M7Xs56xPjLedGJaTNZ+jXuMd1J5Fgge324P51zuQVnXlQUpZ0KJIyGl19+WV599VWTze4HP/iBedFgoBxzzDGtgunEE0/0+9DtkkSGrfFAZ5/0qmJQ8pK1E1ymW89dMuqR+sDY4CVH+THWbBIAt0HfyT5Ht+MjCJxz9ASfc6TCJpRhEY8w5PfUqU2xbDOWec3N5HWdnGOV+L1tq+wbg9omTcDjgpHIsdy8Cvac7JgzO8cR5WF7e+7836Ys5visd7vetrz11dWS8+67Uvf0fAm8/baUHkhqcRBlZbJv0kSpmjhRcoYOlV69e0sfx/UghA5DnevEOmcoYaxGXiRGYyiR1b2kUKYO72EWy76GJnlt8Vp5ZfFa2VgTkA1VImv3NkhjiHFN26vqZfvyHbJg+afJKDoV5smh3TrKod1KpW8xE/82SOcWJuwNmLbCdeSdgxHqzCTobB+RGqXBgor7m+uLwWtTttu2ZcWUnQAY2C7SDoJYvM2R3mf8Hi+mDSnlHsAjR7iiW5hle5prJ5Fjgez14Tlj5+yi3dCJ4cy8qChKOxVI9Eqdf/75ZgHCFF5//XUjlv7zn//IDTfc0DqzvBIfiQxbY9+EOWGA2J5bHvi8eGPZdzpn8Ym0Huk15sVnjW0MplCDvpN9jtEePxphE8qwwEMTqzDk9xhrjEGynhoMUNpZqAlGg6+Tc6xScPids07s2BEvr5o9T8LqKA/bUB881xBfVhRRZ6xDrLAOI4h9OOu7saFBPnlirtTOe0oK33tfcmv3p+beH+D0KS0dOkjD+PFSevYMKTzmGCnLz5cejqxp1hC347CoZ+vVCFVfkRJ8bTke9WnHfMXS6VJc0EFOGneIDCjen4DDJM/o0EkairpKdX5nWb6t+oC3qVIqar1zj9fUN8uHm6vNsp+OkpfTUfqW5EivgibpmlMjmxvXydg9VTKwz36B5mwD8Ya48n+bmdHOb8VzgO1synHbURJNB0EsnQqRdsDYZ7ed/Na2o8MPP9w8y93GfLWXuXYSOQbKXh87HxjthmvB/51zpSnpQyaMi1ZSR0JbAj1qCCMWvEp85kExefLkRB623ZDIkC7nmBPCR2yKaAyOWPadzll8Iq3HaAd9u52jXw9kt/1EW8fReLxCGRbxCEM7Rob9umWxC046YVNm20QMzJljr5NX+F1wneBZ8jKa7XnaDhyEghVC/NaO26DO+D9CC4GIeOJY1HcZWfV+/3vZ/d//4VKXjh7nXjNokGwfNUrW9+8neWVlwmiiXmvWHFQ+t7FlhDXa8LJ45rQJvrYIAM6HOuev7RThGoXyhri16UiMUepw095aE6K35ECYHv9nnRfNAZENVQHZIITWlckzZIBfXiPdCqtlQEmODOtRJCN6lUmv3EYJbN0a1/OQstqxZ6SRt5kS7SSnCGgMYsZERdNBEIu3OdL7zO155vR0u51jewr9StT52muBYKZd8EywUyCky7suUWSi0MiUcdFK6vC9Fdx1112toojeRzsWibFJhNZNmDDBM2ZciY5EhnT5ve9UZy/y41yjHfQdfI5+PZBD7SeaOo5W2HgZFvGKX/bLWCGbdtqC9/KDDz5oDZvDIOUljEHKZ/scwYD3s905jWLOx5kxj2Mj1GydsbC+b2mpdPn4Ywncfbes+3CR577runaVnWNGyyYmni0oaPXW0HGEYUUZg8W5m8GL4UV9xWvoBRs2lIHnNoKQ/ztTQrtNAByuTYczRrnf+ncpNstpoz/dbu++hjbjmvj/JzuqpZmJmTzYVZ8ju+pFFu6qE1m2P8tiab7IYYuXy8She/YnhOhTZhJE5OUG+/EkbBviWtuxaZQbDxLeT+qGaxJNB0EsnQqR3meJfC9koiGcLJzXx47Dpr3Y7J7ZWk+ZKjRSPWZYSX98b73f+ta3jOFy3nnnyTXXXGOSMyiJIZEhXYnYd7r2VEZ6rtEO+k7UAzncfiLdl19evUSIX166iCNC3RBGhLBhrDOmymans1nN7PxIfra7UMk67ITB2zZulJIVK2TIBwtF3ntPaj3ChhsZizBurOwcM0b29ughvfv0kW5M3Ll5s/neJpTgfDhO8HgFp8GLMLRGKr+Jp57dDBvqkjaB0Y8AcKaEdhNIiTIyOhcXyLGHdjeLpa6xWZZu3itvrdgsC9ftMmF6m/flSP2nc/AeRFWjyLsbq81i6ZifJyP6lO5PCNGn3Pw9rHepFOV7d9zZzHqcU7BAAHvekd5Hsdx7kd5niXovZKoh7CehBGI6dwImkkwVGqkeM6ykP77fuVdccYVJ0MB4o8cff1wmTZrUmphhypQp5sWr+EMiw9bSOSTOb6I513hEnl8PZL/24+cL3W/xy0sXzw3iiDJRPjtInnO2czzZsXF4Pfw2StzOiTL0w+B86impf+EFkapqrx9L3ZgxsmvsGNl9yCGyD0HEAPmcHLNPRBbig3bnPB8bvuU0Zq1xaz1X1kAjBA4RE6uB6mbYWNFpU0E7U0K7GYuEOLIfBGui5wRCwBwxqJtZrLFO6vGNe0k9nivbGwtl9Z4G+WRnvVQ2eHuaahub5YP1e81iwaM0pHsnGdK1QIZ0KZBRfUrlmBH9pUdZcUTtPBYvZSz3XiT3WajnWTweoEw1hP0iEoGYrp2AiSRThUaqxwwr7VAg3XnnneYvL1qEks1md/vtt5sHzJgxY4xYstspsZPIHqv21BuWrHP164Hs54M91S90L4ONzxjcCACbeQvDHU8SnhNexnY8DkKKDF3R9GpHayg2bNggFXPmmKVx3XrP7ToefriUnzNLKseMkY1bthjhUHAgVTjl5Dzw0nDd7KS2nJcVRowT8ZpYFuOMcVr8hjFIhPvFY6AGGzbUtU3IwvEoK9iU0MH1R3kQaTZ5AeXkvCJpi/GGajkztZV0qpUjHEKRet6yd5+s3dskG2tElh1ICLFu1z7P/RG6t3J7tazcbtcwb9ZK6VNedGCuprIDHqcy6d+lY6twjNdLmYh7L5T3M5yBH+q6ZIIhnMgQwPYuELNNaLSnTmAlNhJm7fJSPfPMM83CpGnPPvusEUmLFi2Sjz76SAWSTyTSwE218ZxMknGufj2Qs+XBHqpHlv/jbcb4RiDhcWEdxohNs4yg4LphuBCmhmDAuA9ntESctbCyUiqffloqZs+R2vfe8zyP/P79pXzmTCmfebYUHBgPVb91qxTs2mWMBUIDOQ+8MCSYwNtlxy8xvscmo6D8CMDgTJHW4GVb6gKxwvMVIzUeA9Vp2CCOyHxm6wPRxoJgYwJamxI62Fiknql7RAliibJR1lBtkXNdvny5eS84006HSgThtg9npjbq2NYTSS769BGZELT9uk3bzJimNXsbZX1liyzdWiUrtlVJI1kfPNhSUWeW55Zua11XVtShda4mO2/T0B4lkp+Xm9bPM9pdKAM/3H2RzoYwZafcq1evbvXGOido9TNLXToLxFSQqe+j9tQJrMRGQlrCxx9/3Jq5jr/07gK9nhdddJHxIClKtuPWm+nHAznTH+y2XkJNtMqCgWMntrTbjB07tjWjIoY5Bp31zLDeCodQRkuonuBe3bpJ9SuvSsXs2VK9YIEEPPaTW1oqZWecIeWzZkrHCRMO8ii4eX1IqkAyBs7JpiBHIADCCHGHCHLLFGkNXn7LeXO8eA1Up2Fj532iDgYMGGCEB2VhgLmbcHEaixiKnBf7YJxOsEEafB/wl7Tu7J9zxvvEZ44dnKjDj958p+Ff1NAg4zsWyGmH9JJDzx0jLZIrn2yvllcWr5G3V26WrfX5smZPg+xr9BZNlXVN8ubq3WaxFHTIlRG9S42HyYqmEb3LpFNhdJn/Eu2VDWXgh6vTZBjCsdSLvb7Oew3PrU2y4peHJ50FYirJ5PdRe+oEVqLH9xbMjcGM9vSWkgnqjDPOMFnsEEWhsk0pSjYRqjfWjwdypj7YnfXiNdGqHZuDAQ0Y3xg8TAaLaGI7QGBZz5JNu4xYInsU6yI2FDt1kt3vvCNVT82TypdfluY9e9wLTzmPP17KZ82SkpNOlNzCwtaea68U125eH9Yhcqw44jf8n8WmkXbDGqiM+8EQRFxQLxgm8Ro2GzZsMOt4RlM22hbnRZndDJ1gY9Er3bhXIgjO04pg6oPPnBMCKRIjOZre/HCGP2Kma24vGVG412zTqVMPWb29UlbtbpCa/M6yrrJFlmyukG2V+6+XGw1NLbJoY4VZLGjmwd06mf1bjxMCqkvHvIQlOwjO/GgnTLZe2VAGfrg6TbQhHGsSCHt97XhEO16P50ZwwpP26ClJBpn6PlKUpAqkyy67zIghRJE+OJT2SjbFq/vZ2+2sF6+JVjGg8WCEm4OLdeyH8mAQUU7CwuzkrmYQ/5Ytxvi2YgKRZY3CfWvXSsn7H0jOiy9Kr61bxWvq6sZDBkn+KafK4M9fKkWOsTiRprh28/rYhBOcN7/lXBF7hLp59UjbcTd0QLEtv8cgJtQsVuPaadhwLVgi6R2P1FgMlQjCJn6wf+0E4pEYydH05kcipoK9aV0LCmTk+H5tjruzuj4o9XiFrN5ZIy75Kw6cl5jvWeYu2vLpsTrlS7/iFjmkc76M6FUqvQKN0hLnfE1emR85J/j/7Z0HmBXV+ca/LbDLLuzSexGQDioKYgXsIAhqrLHExKhRo4nGJKbYY2LsxhI1/wRj7wpWYsEuNkRFaQLSe9kC7LLl/p/37J67s8PMvTP3ztw7d+77e55huXPnzpw5c2bme8/3ne9g3/GumZM69dMQTvSZqa+vLjOuMdoX7hEvJ2jNZE8JIcQ9nt/Zt912m9e7JCTjiGWUZdJcIl6n9jXWi91EqxALEDa67mDoQQRoL4dxglo9WSq2gXEE0QBRpT0t+AtjCYY/hIXs3Cl7btggnZ99TmTePPvzbtdOag46SPKPPEIqS0uVd6duwwYpqaqKXjMnBh22g9hD+VEePfEqtkHZdPkgGnCuqA9tsFq1E2yPzzohglfC223vuFNj0eo+wLa4XvAUol61p8Npnbotr1PDP975dGxdIGMHdlKLvj7z5i+SL5asU9nzkBAC2cRXVtTLrhjjmjZtr5FN20W+2lgn0xc3eEkL80QGfjVf9u27WXmZ4HEa0KW1FOQ7mzMQZVmwYEF0XJceU4S2pb2S8c7Raw9lqsb4mCdo1fcMni9ee3j8EIiZ9D4gJJvw7S5899135ZVXXpHly5erz3369JFJkybJuHHj/DokIYHBzijDSzyT5hLx2hNmrpfoRKvdu6tQIG0k6220OIKRByB0dH0ZjWTUJXqLsS8sOrsaDMT8nBzpvXGTtPjoIylZvFg22cxXVNeypWwcOEDWDx4sFb17y0iMLSookFa1tbJixYpmHh6d5c2pQWf2liD5Ac4XoJwQTtrDpZM2WLUTN8f0u3fcibFodR+g7PAe4rzhAdOiEfvCdXNyfm7K61RMuTV+VYjolo0yqGNL6d82V4213VGwQ9oN7CjVLUtlS6RYVm/PkUUbd8j3m6qkPMaETVV1Il+v3SFfr/0huq5FXo7s2bn5uCYsJYUtmv1WtxUkKMB5QnCibNqzakwbH+sc/fBQuhECiY7xMU/QqhO5IPGHOeQzaHBuKUKCi+dPDjz8Tj/9dDUHEowB3fuEBxi8SyeccII88cQTyuAiJKzYGWU685jfoXde9Up6nbnJql6QJc1ogKEusB5eJYTboUccBg86WeB1MNaXnZGM+m21dq2UfPSRdFqwQPLt5ivKy5PI3nvJkl69pHLoUGnToYNUbdokO8rKlCjC/tGbjjJgbJMxmQRETjyDDtcAC36rt8Fn/DaWgW8nTJ0cM0i941bXG8IQhrj2hqHTAG0L4khnINPnh8+o+y1btuxWR07L61doFPYFAYH3HNoIBB+yFKKt9u7UQgrWr5R+bVrJYe3ypaZvndS0bC3VrTopT9MXS9bL4k07ZdNOe08TsuvNX1uulufmNK3v1b6VDOvWlHq8U4tq2bJunRLPaGeoM3QkrGtcZ/RKxkNfE7QzCCQIpSVLlqhrYTVRsNPnEO5blAf1hXVWHUOJjvHJ5NC3MIViExI2PH+CXHfddfLCCy/IFVdcIb/5zW+i6WHxAoFAuuWWW+T666+XG264wetDExIY7F7aTnvIg9Ir6XXmpnjGjE7fDEMKBhqMT9QTMqvpZA7mgeNGQ6Jm/XrZ/NJLsmP6dOm9+HvbchQMHSJtp06VkkmT5Mtly2Td3LnSrUMHZazDOIRhiDLgWDoVNbwexmsGj5XOlGVn0MUSmLEMfLvfOTmml3gxX5Hd9bZKLY31EBk6tTsW3akAAZJoO/ZD/OFc4KHU43xQTqxDu0G5tfcGbXjr1i1SU7NeOneukMl77im/HH+g+t3m8p3yQ1mtrN6RIwvWVarxTZiPCfMy2bFyy061vP4t5mpqoHULkf7tC6RzyxLpkJsvxXVbpG9xa+nfr2/UK+lW9OmxYrgWCN1z640xXlt4pXD9EAIHcWzu6EhW6GRqkgCmDickiwTS448/rhI13Hzzzc3Ww7j4+9//rh6KjzzyCAVSimB8c/qwemmnIlWsl72S8Xp1E2lfsYwZXXadoAG9zhgTgXE88DxY1Vf99u1S/sYbUj5jhmz/eHbD6HgL6jBnz2GHSe+zz5LiIUOi61thzqLGzFcw4GDcYk6i3r17qwXr4c0yJzBAuB2EWyyDLtHrbfc7J8cMmtB2cr2NbRUGObweMM5RBpwrrke8VN6pHseBY8BbhM4/LZAgiCCy0YYA/q+FEs4HHlHUKc4HGftwGsNM+62qqZPFanLbsoZkEI1epB277EP0KmtEvlqvs+y1EpEeUrAhRwZvrZPh6xZHs+ghFXlhC/txTag71CU8dmhrWuBB3KB+3YYg6muLetLj7XAd8dkudDIThU6ipOJ9QAhJDM/fIDBmxowZY/s9vnvyySe9PiyxgPHNwSMVqWK97JWM1avrR/sylx0dK+h9htFsrK8OMKY//FDNV1TxxpsS2bnTcn85rVpJi7GHSu7hh0vhqFHSqUuX3cqG8kKIYQwJnl84BsKJRo0aFU1DDYMXIgnGsE6dbPSExAot0l4FGMdOr3esdpIqIzIV4T+oH1xf1Ck8R2irqCcIVV0GiIlY7ThdzznsG+NcIIAgItBGUXadlRDnBC+obtM4V5wHtsF4IVxPq/JBwIzoWaoWTfWuGvlqyWolmJZtrZFlZTUyf22FbKq0v6er6yLy1aoytWhyc0RNajvMnHq8uMEgR/tC3aMukfwE5cO6eHOLxbuXUQ8QXOhkwPWiEIh/n7Nzk5D04vnbA4bFO++8I7/4xS9skzckEstM3MP45uCRinh5P8LirAxiP9qXuewwqCCS4FGA4Za3apXkvjhdfnj1Valt7LnfjdxcKT7gACk9fqq0OfJIyS0qinlMiCBMSwAjG0YsDDlcI6w3h/zpuVYQJmR3zazCxvAb1An27dTLlu5xFU6FdqKGHH4HYapD55CQA21Jj0EDTtpxOp9z2L8+HgQF2giuNd5x+IzMizpNPYQeQiQhpCCqnHpkUE/Lli6RnRvWS8/6XdKvU0vpMryL9O+/n2zdWadE0zertsnc5Rtl4fodsrrcXsggcg8hfFhenLsmur57aWFjEohS6VbQXvJKOktpqxxVZrR5iFe3zw/zvQzRqOe8wnXiHEL29znIpGQ+hIQRX+ZBuuaaa9QNf9lll6kbGi/XxYsXy5133inPPPOMGqdE/IfxzcHEbw9AqiY09KN9WZW9a2GhdPzkE6l46WXZvmCB7W8LBg5Uk7iWTJ4sLbo0zVdkh9mwx8TWZuPDHPJnNydTPIMdv4E4cnPd0x1u5ERoazEIzxs8QThPCNlhw4apELJ4E3zCYIanBaIBYhjtCOese9B1sg6z5y4ozzlt4OKYGKcDIYHrDgGEcg4fPlyJJngndWIiiH03Hpl4ArBzSaEcNhjtfaDavqKqwbv0nSFEb9H6CpX0wY41ZVVqeXO+7nTIkaJ8kV6tK2WPtvkyomc76VhbIB3q6qVFXq7rexnXENcPzyE3HQXZgNV9jo4DJm8gJL14/nT64x//qLLePPjgg/Kvf/1L9T4BPeAaAgrbEP8Jc3yz217rbApXSJX3wY/2pcteWlgoO995R+reniW1n38um+rrLbfP69RRSicfJ6VTp0jh4MGOj+M0LCsR49v8G7t5nIKOMZugnUDBPaXFEcatoA3gM/6P5ACDBg2yPVc9Jxi8cfidnrNHG4tOPXe6zUGUYFs9HxY8OPHw4rmgJwXGMa2yFaIedKY+HS7oxiPjtg22KWwh+/dtr5boPmrrZfGGimYT3c5fUy4V1XbTI4vsqBVZuC0iC7fVyMwfNsitH2yQlvm5MqhLG0OIXokM7loixQX5gfSCZirs3CQk/Xj+pMJL6aGHHpLLL79cXn311WbzIB177LGy1157eX1IkmZPQqpxO+YgG8dipcL74HX7itTXy45PP5Wy6TOkfOZMiezYYb1dixaSc+CB0v3Hp0vJIYdITgLX0GlYViIi0PibWPM4OW176RD3sUILdQ83ygMhpOfNgcCBAECYIhb8HgLBLqECEm9gH3rMkZ4jCd4FLbzwPYSZzq5m5bnTk/HOnz9fiSSgkwLYjfPx+rkQy6DFHF+6feEc3N4nTj15xjaiJyI2thmMN8KiQYclsuF9t7bR07SmQTitK6+yP8/aevlmdZlaNDk5In07FMuQRsHUMG9TqXRqU5B2L2imEubOTUIyBU/fsnj5H3rooXLeeeepMUgUQ+klrD14bscccCxWsNtX9fffK1FU9vLLUrt2reU2kZwcqR00SHIOP0wqhg2Tmvx8aTdokJR6lAzCrldei0AY6/CiQCggRErP7xZPOGpxBAFgNY9TPBI14pMVVXahhViv7zd8RmgcPusEBDC68Rt0lEEMxEqogO/xO/zFPiDAtHCAtw3boL7xG+2h0QLNCL6DIIKwgiDV42a0B8dNKGSiY5diGbTJ3idOMklapUrHNbCbcwgoL1ZNuQwtqZF9OpZKx8P7q+83V1ZHvUwNoqlMlm7abpccUq3H91he+brp/u3cpiDqZRraDeKsRHq3L5JcZIogSV1zQoj/eGop4+WEOGy8KEkwCGMPntvwA4YrBK991W7eLOWvvKqy0FV9+63tdpEePWTrPnvLsl69pPe++6pr3joSSWiMiVE0mCckNffQGreF4Y31MLphpMOgh/CxEylGg1iH1UEcWc3jFI9EjHgvPCN29wzKA8Gny4N6hAdJZ2uDONKiAIInXkIFJC3Qnh499gi/1RMEYzuISz0nD9ZbgeNrI1ILNWM9W3lYIHqxDoIXv09m7FI8gzaZ53A8gWWuU5wXPHwIhzQmkTC2mVhtpEPrAjl0QCe1aHbsqpVvV2+TTxetlQXrK2XJ5iq1VNdah76CDRXVsmHhRnln4cboutYF+TKkW5uolwkCakCX1lKQHz8c0glhCaUOa+cmIZmE53fbhAkTZObMmXLBBRd4vWtCEgo/YLhC+oHhsnH1Gtn53rtS//Ysqfn0U3RhW29cWioV++wjBcccLRWdOsmWrVtl+9q1KowLBkMi4SaxJiQ1p982b6vDwOCZgNGPzzBCY4kUo0EMzzo8JfGEmJURlIi498IzYnfPQHgYywPxgjLjM8LtcK4AwgfenngJFfB71A3G7hjLht9DbGEbiCN4Q7BgvZvy6nl9rK49jguxhzKjcw/Ha5jUdWt0n1ZGqd0189OgdTOpMI6Nz7j+dm3GbRtpmSvSpnqTDC/cIgO77ZKWfVpKx057SE5pN1m0YbvyMmmv07YdNbbnUVldK5/9sFUt0XPLzZE9O7eOCiZ4moZ0K5HSVg1JLZwStlDqMHZuEpJJeP7UuOqqq+Tkk0+Ws846S4kkzBOBHlgzeCESYkcsw9Ft+AHDFdIHxhVVfvaZrHr0Uan/4EPJtZuvqGVLaX3E4SoLXSXmJVq8WNaUlUn1mjXKgIVBC8NVeybchpvEmpAURrqxjZkzSK1YsUKF18GgxrpY4V5WngqU1W6ek3gGXSLiPlmPKcqFBR4ziB4IU13nEIkQLMbyQFygzAD1hGPi/GDc2SVUiHc+eGfgePAaoc51/Vi9S+Ld43YeFqSPRxlxfbENzlGnokabwGfz9Yh3zRLypibp9TDXqd4P6g6Cz6qO3bYRq/tn08YNMqh9Ozl+ZA+1ABzvq8UrZdbcxbJqu8jq7TmyZEu1bNxh72mqrY/IgnUVanluTtP6Xu1bybBuTaIJf7uWFNpGqDCUmmQCYfFyZgOeXxWkdwXfffedPP7447bbweBJFZiX6bDDDrP87uOPP5YDDjggZWUh8YlnhLjtrWW4Quof9rsw9mbGDDW2qGb1arWtVXLgVqP2a0jNfcwxktc4OWgrJAhYuVIleDEKDRji5lAsp1gZhDo5QO/evWNuC6EAYxPnijEtduFeVu0W5YWQQvkhsPBb/O6bb76JChAY5Xa9+ImI+2Q8puYxQjoLH8Yh4bgAggnfQ2igHjD+B4YxyozU3slmxtPnjfW6LuOJ4lj3uJ2HBfuEVwqiC+uNySBwLvjOfD28NsK98HpYtRFcB11+qzbjto04FVT4rn2hyPB29XLE4KZwx6Wr1klOu56yfldL+fKHhvmalm+tkhiZx1UCCSyvf7suuq59cctoIohBXYqlW6s66VqUK60KC9T9la5074Rko5cz7Hh+Ra6++urAjkG69NJLZfTo0c3W6Z5PEhycGCFue2sZruD/w75g1y7ZunCRFH4yW6q++tr2d5Fu3aR835HS9ZRTZY8x+1teK3h2Fi5cGA3rAgiHgvGaCG4MQvO2enwLyhUr3CtWu4VxivNZtGiRyriGc8L+ID7QqWRn0GnDH54b7Z3BdrGEKoSX0XNiZSDbCVurc4AIwvnqFzjKg3LPmzcvmrwB+8P/Y73o3Uy6m0inht09HsvDAnAtdPY8PR0FOvAgmMzXw+vxjG4El901s6orqyx2xrpzK7zd3D9oK/DOrlq1Sm2L69yuuED27F2qxPUg2SW7uteL5BVLVct2Up5fKgvWVaoQvflry2XHLvvO0y3bd8n7izepJVq2XJFebXKlb7sW0r0oInvu2qZC9GqqdjDzGwkU9HJmuUC69tprJaggw95JJ52U7mKQODCpQgY97FetkqL5C6Tjp59Kzpw5alyRlYSpLy6WXfvvL/lHHC4V3bpJTW2tFPZp7rkxor0XMBwhDuCtQA8xksDA+PKil93OIDRvCxCOhXLA22MX7hWr3aKuli5dqsQRjHAsOh02zg09/rGMThiWEGfYF4SiUYxY9UriHBDejOOZRVWsXkwnczgBTHwKLxDEBAxg/B7E8qS4nXTXq06NWB4W1KVuZzgXfR4QRzi++Xp4PZ7R6bPOiVfdXFex6s6tADXXoQ51RftFuKL+LcqJ7XCP6tT28NIOGTIkmjjDKAZb1myT0Xt2kTMOaAhXrauPyPLNGNPUNF8TJrzdVBlj3rF6kSVl9bKkrLpxTY3kSIV0a50rgzoXyZhIhQyvyFeep3bFwUqTzXCr7IK2TWaRdT49GBowbOjODC5MqhBsYOjsnDtXKh57XDq+/bbk2sxXJBA348dL68mTZG337lK+ZUuDMVZbGzdMzDhIX/eaa88SDCynYU1GAwQCx+gRsjMIzcYjDGkYfXo/duFesdqtzpyHvzg37Y1C+WBIamPcar/xeh2tvoe3SR/PLKpg0GIybz1xKQSO3p+TOZzwGy2OUFbsX0/yGsuTki7jIJaHBQb+mjVrlLdDjzMDEOKo26FDhza7Hl6PZ3T6rPOj59mtANVzXOlMjlgg2oxiDeXEgv2iUwHvW7QTCE79O1x7hJai3ZlTwefl5ki/Tq3Vctze3aPrN5RXRUUTUo/PXbFZVpfZtxv4nNdU1suaykqZtXRRdH330kI1lmkoEkKoTHol0rNdQ4hlGMKtKLiCDW2bLBdI119/fczv8SCCgdGzZ08ZO3Zs3Jh1L/npT3+qXiwweOBNuuWWW2TUqFEpOz5xBpMqBOtFqI9VtXy5RGa9I3VvvSU1jR4Fq3FFecOGSaeTT5KSCRMkr3G+oNa1tdLORXmNg/QhlPAXPdEwEHV5dAY1NxOBYp9ODBCz8YjfYfxRrPLHSxSA544O4cL5GHv+4VGx2288YWH1PYx9GKc6w5w2qPEdjH/tycF61CN+pyc1jTeHkzaScY3gKcB+IMas0nqn0ziIdY/gO4BrAsMf1wTl1/Nb6VBO7Unyazyj02ddIuLS7vzdPjussjqiDaDd4p4wijVzOXWYItoL6hptEuJap8zX48Di0bmkUC2HDe6sPkPkz523QNbszJV1VXmycMMO+aGsVlZXRlTSBzvWlFWp5c35G6LrSgrzG0RT41xNw3qUSP9OraVFntXTzTuCOJ6N+Attm8zClxA73Rujxw5ozOvxYMSksvfcc496YPoFHhQ/+tGP5Nhjj1UNFAkkbr31ViWSPvroIxk5cqTtb2Fo4IFuBA8h4h9MqhCcF2H15s2y9NHHZNf//ictlyyxL1OHDlJ9wAFSPOlY6Td2rOWYEjcvfeMgfXgu9Pw6SHCA3mecN3r+YaTbnbeXBoiT8sdqt/jbq1cvVXbdSYNyIZvngAEDlFGM8uKczEarUVjgfPFMgjDRHigr4aENUHy2mscI28M4xbMYzzeUQ4+zijeHkzZ8sR+UA0YvwDUyh1yla/LLWPcIMH6HMqONoW7RTgC21XXoZ/plp886t+LS7vwx3gvC182zw3wfwduGtgcPkVmsxSonyqSTNuhFf3YL6miPnl2l1fr10qtwhxzcGW2pl/Teo5/8sKWqWdrx+WvKpaK6QRBbUV5VK7OXblFLtL7zc2VQl8b5mno0JIXAuKbiAu+er+kcz0bSA22bLBdIeHhOmjRJiY5LLrkk+kJavHix3H333fL111/LU089pW7eO++8Ux544AHVa/nnP/9Z/OKggw5Si2bKlClqLNJee+0lf/jDH+T111+3/e19990n1113nW9lI9YwqUL6XoSRXbuk8oMPVAa6irffFqmpESszLLekRFofc7REDh0rdYMGKqMfL3orIz+ZF4k2umHI4y/OG88M9PzHOu90hHTZtVus32+//dT/ITxgLMIz079/f9ULH0vwamGBsUpISa29NqgPfA+j15xKHKGI8IJYzWOE+sM+tcDS3jmrSU2t5nDCdhBXACIJZdG/M4dc+el9MWL2iuCz3T0CdAY+7ZHEgrpBneGv9m4k4t1y66Fx8qxzKy7tnhEoG8aluXl2mO8j3He4D/Fb87xkscqJ5wLaEYQVkmDgeYH2ZSVC4xGrLQ3t3lJ5hDS4nsiG993assYxTQ3CaV25fcKXXbX18s3qMrXI5w3r0L+7R4fiprTjjZPddmrT0P7dkq7xbCS90LbJYoF00UUXyeDBg+U///lPs/X77ruvTJs2TU477TS58sor5dlnn5WHHnpI9YY+/PDDvgokK/BwnTp1qjz//PPRh7Xd+WBeJyMwAo4//vgUlZRkS0ib02P48SJUxuG8ebL1hRek/JVXJdI47mS37fLypGrIECmZMkWKx42TmpzGCTXbtnXdM+30RaK9JPAewRhHWK4+91jnHbR4bxjcY8aMUaLIeI3jCV5tDEIYYT3GMEEAGdNQW42x0dfDaKjqeYzwW5QHx4anBB4hM3bGrjak9fGwP4g1XBvUMzxKGOMEYaVTeOs2kKxxYHWPALPA1ONbrO4RPO+1Jwz/x7b4P8qmx1uhPqwmuvXbu+smU12sZ5B+RkD44pz0WDedZMTNs8N8H2kPIoSNWQTFKqf2WqLt4ffYX6Ii1E1bQnl7dyhSy4Th3aLrN1dWGxJB4G+ZLN20XewcWli/bNN2tbzy9droeggkPZ6pQTyVSp/2RZKbG3tcU7rGsxFC0iSQ3n77bbn55pttvx83bpwSSBqEvV1xxRWSDhDygoe4ng/FCvR2YSHZSypC2twcQ7/0YIjCSNEDoRMJU8UcRWUvvaS8RbuWLbMvX9++knPYeKnYa2+pKmgp1YWFsvqHZc3CamCQxprTJ9l60Smn0fsPw9YYXuaXAeK1MLYy6pwIXpQDmeMQoqfHcuCZhUQKOoGFeb9WhirAb1GHOIb2RsGrgHo2trd4Rrk+Hrxa2B88YWiHep4ktAeIJ6/uFbt7RNeXUWCinlCXVsYirifOG9ujDlFG/B9Z/yAgY01066d3N5FMdXbocEmIZNwz8NTgvBBG6NaItrqP0AmKc8J9aG4XduUM2viLDq0L5NABndSi2bGrVhauq1CiSSeFWLC2XKpr7b1cGyuq5d2KjfLuoqZQ/OKWeSokzyiaBnRpLQX5eWkfz0YISZNAwsv2k08+kV/84heW38+ePbvZwxgvBat5PVIB0u6iBytdxyeZQbJGjxMD280xsA8YtAsWLGiWShf/d2LU1VVWSsXMmVL24nTZ8dln9tt1aC87R4+W+rFjpcqQoKDQQgzBgwCxhmQDRiNfh8clagAY6wWJXWAAwOu8detW5UmBN0mHTZlJ1gBJ1ViveD2/KMeXX36pwpd1SBJEEgx7iBI7YWxnqKL82CeEDMYeoQMI+7Vqb0YvnpMxUjCY0RZ0mB+28Sr80+4e0ZnQjAIT5wbxCHFgNhbRJtF2UW+oQ5QR/0eHGURSMiTj3fUydFaHQeL8IFohjHDOOj03yuPGiMZ56PBD3easxFGmj78oapkvI3u3U4umtq5eeY2aUo83hOpt29Ewj5YV23fVyefLt6pFg5wPAzq3lmHd20bD9CCiUj2ejRDiDM/vnNNPP13uvfde9RC98MILoy8cZE7CeJ5HH31ULr744uj2s2bNUqlU/QQvbLysjXz11VcyY8YMmThxoq8JIkjmk6jR48bAdnMM/BYvQRg8eLnqyRhhYOG+s3rhRmprZfuHHzaMK3rrLYlU6zlDmlMHoxzj9caPk/rBg2Xbxo2qvDCw9DnAwMR54VjGrGkog9HIRzm1OEpUYBjrBQJQG3cw6lEmnYLbzshIJqQrVYOe4/X8ohw6UQzKAqMfIgntC3/dpihGnUBQ60yB8dpbvHZsLD/KivJhjBiOoVOIezEOwu4egdFuFphoJxDr+A5lwl94h4A+b30udvNapTrMycvQWd3u8XuEs6HdYH9oR1hvvJ/dZILEduicwX2nPbjJdBpkQlrq/LxcGdCljVqOH9mQdRftaW1ZVbPwPIinVVsb0sRbUVcvakJcLM/NaVrfq32r6HgmnRSia0lhQqnHOb6FEO/w/EmE8Do8TG+//Xa54447ouJDp7dFNjkdgoceKQxcNiZQ8INTTz1VvRBwHBhWyGL34IMPqh7Gm266yddjk/S9JL3ab6JGjxsD2+0x0HsLgaQNXD0Jo9GYUuOKvvtOymfMkLJXXpW6TU2zzxuJ5OZKZO+9ZcteI+SHTp2kS+/eqny6DLh3jOWF6DGXFUaYuWcan5MNuzPWC64n9odj4VrCAPdzELLT0Ldk21i8nl+s03M34f+4HjrrGsqEdW69dG7am7Edo84hhhctWqTOHaFWxvLj2sDTpUW7l+Mg7MqsxbJZYELA61TleqwUPEsYW6QzJMaa1yrVYU5ejyHRWfm0OLK7n908wxBKibaG+tPPiERDCNFu9PhfL8RWKsHzoHvbVmo5amiX6PqyHTVRL9Ocpevl61Xb1HxMMTKPqwQSWGZ+2zApNWhf3FKJJWNCCMwNhXmiCCGpwfOnEF42yFKHcUbIDrd8+fJoqthjjjlGJWswbnv11VeL3yChwmOPPaZEG16S8CadeOKJcs0110Sz7JH04FcYk5f7TdTocdMj7PYYsYypmvXrpVyNK5ou1YvtU9Ln7rmnbBkxQoonTpCcdu3UXEUtFi5UIiRWGazKCoMJhifWx/I0WZ1/LJFhPBYMXexHJwPwYxCysSw6/CpW6JsXbSyeyMI6CA9cF4yXRL1qsYL1iXjp3LQ344B/bIt60aGdWhzpnmsd2mW132TFpF2Z9WIWmLE6KNyEIpnLrSeZtfptMmFOXo8h8WJ/5meYFumo02RDCJMRW0GltKiFHNi/g1pW9MmXhQsrpV3HzrKyrFaWbKlWwmljbaEs3VItO3bV2e5ny/Zd8sH3m9SiKWyRK4O7NhdN+NyqZfx5pAgh7vGtmwZpvmPNL5RKLr30UrWQ4OFXGJPXc+AkYvS46RE2p7XWGdtwHk7mlCmor5fOS5dK1bSH5PtPPmlIuWR1Ll26SOlxk1UWum0lJbJu4UKJYI6bSEQdFwYUOhBgDJvP02goIlwJ56Q9G3q7eJ4m8/k7GZhuTvcNoaDHuXg5CBn7xVgfPZ5KTyCKAf24Hlahb8Z00dgOn920MSciS88JhTLhGNorB88JvOCJeOnctGl9zeA50qnB0T60EDIey26/IFkx6TRphJMOCqehSHZeD+wP3ih4yXC/4F2nU58nGubk5po4EZtejEkxP8P0ftDmcW8kE0KYjNjKBHS97Nq5Xfq3by1dWlbL6A5FMmjQIOncuYv8sNk4rgmhemWyqdL+3Ktq6mXuym1q0cChhEltjckgIJzaFTNzHSHJEmw/Ngk9Xsbd+7nfRIwetz24ejwHDDLE+cPYtjMk8f/+fftK8fffy87XXpe6Dz+EhS9WEfA5RUVSctRRUjp1ihSNGSM5jSntO9bWRsuHY2nDF3WGchqPZ2XIY5tYBq6T83ciZHW9YFusg1hBggaECnkZjglxhNAxGH4QHhADqA87wQjBZkwXracKgCfNKU7PXxu6GFdjPH+nXjq3bdpogEME4LyRuhueI9QFygKBBjFpPpbVfiFsUzGey+uQNSuvBxad5AH1j4QhYPTo0Um3xXjPGVwX1CXG9OJaoFwQZnZi0+1zy8pbZp5jC4lRdIp5fU9ju3hhnl6KrUwg1vMPKcARMofluL27R3+zobxKvl3bMK5Jj236YfMO22MgdG/xhkq1vDh3TXR999JCJZiG6nFN3UukZ7tWCY1rIiRboUAiacXruHu/9+uGRHpwnRjMVQsXSdmM6VL+0stSu2GD9Y5yc6X4wAOVKGpz5JGSW1RkWz7Ujza4MLYFBjd6x40GVyIeOSfn73Scj1mcYR/IOubVWAWdCAGGGsqI48BwQz0MGDBAevfuvdtvIFTM6aLxG6z3Wsibs8np73FsYztHGfAdBHaiY6Ks6hvnB6NYZy9DedFWEvUeJNJh4Tak0TjBrk4iArFrl/XQSblxTJw32omeXFe3HQgElMOvhAP6/CFUtcGNYxjnw3IrNo3tSSc8MQokGPQQ/OY5towhhsY5t2JdFyvBYCW2wpKWOpHnf+eSQrUcNqhpapHK6lqZv7Z5MohF6yplF7I+2LCmrEotb85vej+UFGISXYTmlUY9Tnt2bi0tkF6PELIbFEgkrfg1d0NQ5oRw24NrZ0hWrVsnm197XcpmzJDq+fNtf18wcKCUTp0qJZMnS4su8efv0mFsCN9CymctJs0GV6IGbrw00U6EbCqyyelECPDK6LmBIDZiTWQJL45Vumisd4rV+WM/2B/mFzLWlZVAwHfaSIcQwO9hvOtwuETGRJnrG8J57ty5SvwhnA/HgAiENwsGbqoSELhtBzhnGPfw8Og5w1B+GPNO68TK6wGDXodVon6BnhwXeDmW0ur89Tg8ncZbz4Xl1jtubk9o91hQl3b1axXa5/S6WAkGo9jSE/ZapZLPVLzIKte6IF9G79FeLZpdtfXy/YZKJZaMwqmiqtZ2P+VVtTJ76Ra1aFrm5crArq1lWLfS6Nimwd1K1DEJyXZ4F5D0NkCf5m7I1DkhmhlkGNfy/gfS6cMPZef8+bKz3rrHMK9TRymdfJzyFhUOHuz6mE7ETzIGbqyefydC1q8wTCM6EQLEAIxEGLw4FjwOdgLAi3TR5vPXY1zgkTCHWFoZoliH7xBiBw8GDHe0eXg3EhWS5vpGXaAM2CembYB3SotIpwLAj4QBTtqBNr5xHDvxn0i5IbpWrlwZ3Q7XBIIW9YPv/RLxevyfFsK4t/B/iHK33nFze0L2QbR/hE5a1a/dfYx24PS6WAkG3YGSijnHwkLL/NzGELoSkf0a1qE9IM24Hs+kxzchHbkd8ELNW12uFg2i8PboUNw8i173EuncpmGMHSHZAp88JO34NXeDk0kug0YHTNy5YYPsfPU1yftyjrSusp6vKKewUIXOwVtUfOABkpPE+TgRP8kYuNoQQ887jCnsH8YQDD14IOyErL5uMMjxHQx1bRx6HS6pEyEAGIkQOXrwfawxVsmmizYLeXgEII5QTxA9RkPbTiBAUKEe8R1+CyGTjJA0twfUu55HCNcQ56fH4XiVYCGRchnbgV3SgmTFtVW5sY8PP/xQeaKwT9Q3jg/RqOelMh7HafY+J9kMscDTgmPiWus5sRLxjlvVDdAZCvV111N12HmK0E5T7R0ku4Nr2Kt9kVomDG+qs82V1TJ/bUXUywThtHRjpW3qceT3wcS4WF75Zm10fac2BdHseSoZRPcS6dO+SI2nIiSMeG4lYnLYs846y/e5jQhxQqb0TFZ//72axLXs5ZdF1q4VSx9ETo5KslA6ZYq0OfpoyWvtPJQrFk7ETzIGLrZHaBOMLZ0FDZ+XLl0aTQZhNoKM1w3bYjC8Du+CEMGxIQyswtASSSWdyPl55aU0nj/OB+LDKulCPCHr1bg7c3uAgYw618Y4rqFbT5n5PL1sp6h/u3vcizoxlxttTIeW6VTraNsIsUPdABwHdQWcPH+cZjPU54+2gZBYHB+hjuakKk4w1w2uM0QwjoEQTYD9QzDh/O3EJrxXOHaqvYN+kQmT17qhQ+sCOWQAlqbrsXNXnSxY15g9r1E0LVhbLtW19uOaNlZUyzsLN6pFU9wyT4Y0JoHQWfQGdGktBflMPU4yH8/v+scff1xNworY7zPPPFMtGORMSDoIcs9k7ebNUv7KK0oYVX37re12Lfv3V56i0smTpEX3poxHXuHU0E/UwNWZqmB4wajWA/1hTOrMdPGuG4ww/F4bXjDaYFAajUk8c5wMFo9VD4mkgPeyHcUy6OMJ2US8fHbGoLE9wPhfuHBhNIObHlyf6jnk7Nqpua3o8UAQ1QgXM26T7FhELWQQzgiPkc4kh3FAEBcIvdPiAsIJghdtP14adrfZDL0w3q3aS/fu3WXLli3KU6hFE8qmvURWbRP3NBKm+OUdTCWZ0qGWLJg7aWTvdmrR1NbVK69RU9rxhrFNW3fU2O5n+646+Xz5VrVo8nNzVPIH7WWCeIKIKm3VwvfzIsRLPL/j8XKYMWOGPProo3LTTTfJX/7yFxk1apScffbZcuqpp4YmQw3JDILUMwnq4QWZNUvKXpwulR98IFJnPVlgHnqHJ01S3qLC4cN8T8/qV5gjwD0PYxHPBpwHjECEr+H/dtfBfN3Qkw2DF73mKCuMNrMxCeMG4Xh2RmYm9AzHEjnxDGS3BnQ8Y9DYHmAgI1GDTjG+zz77ROf9SSVW7dTYViDmIJC05xEiHHXQv3//3ebscgvqa8GCBcrzif2gHGhvCN2FEDOKC4gliAt8j+PCyxPr+eM2m6EXWLUX3GPI0oc2h3KgPnU5cH6x2qYf3kEre8HP+zjIHWp+k5+XKwO6tFHL1H16qHW4/hjD1CCW4G1qGNuEsU521NZHZMG6CrU8N6dpfa/2rZrC8/C3R4l0LSlk6nESWDy3DtBTdvLJJ6sFvWlPP/20PPbYY2qi1ssvv1yOOuooJZamwPBLwwuWZBd+90w6eVlH6utl5xdfqAx05a+9LvWVlZb7ysH4hiMOV96i1gcfLDktwtHjhvrA4HUYqzC6YDzquYPsrkOs62ZnTMK4szMynfYM+y2i4u3fiQiKNwGsU0POqTGIMmMAP66X9v7hcyp71WPVm7Gt6AQX+AwRrsU0BF4yBq5uPxBHqCMIdizwnEAE9ezZU3UCmMUFyoI6i/f8SZcHxc3kzn4mvnG6b789PEHrUEs3qIPubVup5cihXaLry3bWNMzVpLxNZer/yKoHcWTHyi071TLz2/XRde2LWzZPBtGtRM0NlcdxTSQA+Pp2w0PmggsuUAtCDX7729/KM888I6+99poykk466SQlnPbaay8/i0GyGC/TfVtNohgrpKsacwtBFM14SWpWr7bdb9GoUVIydYqUHHOM5JWUSBiBEaYNcPTsx7sOsa4broFdqA8MVCvjzokY8Nv4crp/48S42A5//fB2xRKaetJPGPfw/GECXRwfoiOZeXf8qDdjW0FdIaQN3g4IGJTfCwNXtx90AEIIoUwQ/HoSXV0P5naJbdERiOPHev4EZVqCeOXw09PsZN9+e3iCEuoXdBAud2D/DmrRVNXUyeL1SD3emEFvTbmavwlheHZs2b5LPvh+k1o0hS1yZVDXJsGkUo93LVFhgYSkEt+7/5AKFR4kLN9++63qyUOoHR44CMN76KGH5O6771bJHUjmEtTwJa96Pa2MNCww9o3jCzYsWSKF77wjkVmzpOqrr23317JPHyk9fqqUHHectOzZU8KO2+sQa3s7Iw5jkOwGiyMMKl7PsN/GlxuPTSrGQVgZg9i/Fkc6RA3l1pPCYswNMvdBJKWqV91JvaHDDcIOXhuUU4+f8crA1WISoXQ4Bq4HPEfwWME7irKg7sztEnWFdmmcWNVufF+s+yNVz9egT4/gt4cn1UI1qO/NRChskScjepaqRVNfH5HlW3YoL1PTuKZy2VRpnZ0VVNXUy1crt6lFA+9tzokAAFv2SURBVIcSPEtaMOnxTfBAEeIXvtyJeMDo0DqkQ8UNP2nSJLnhhhvUX7zowN/+9jc5/fTT5frrr6dAymCCPrDVi15PKyMN4TNqfEGvXpL76adS+u57kjNnjuy0G1dUWiolk45VIXSFe+2VdbHX8a6DlbFgNwGonRFnt95Jz7DfxpfT/adqHISVMQhvhxb9EBgIpYPwQFmwoKxI1ACjMVW96rHqzfzswbWGJxFepEQNXKt2qNuKHgeHOoA4QqIGiEc9+axd+3My3YDd/ZHq56ufXqKge3hSKRCD/t70AqQA79uxWC2T92pKMLShoioqmHQyiB8277DdDyL3EMKHZcZXa6Lru5UWRkWTzqLXs12rrHu3En/w/C484YQTVAgdbvgxY8Yo79Bpp52mXm5m8BJGmN2LL77odTFICsmGga27GWnFxVL+2WdS+uVcyfvma8ndbv1wxzii1uPHq0lcW48dq8YZBQWjIQiPAHrGkx3IHusYsfbr1liwM+Ls1jvpGfbb+HK6f6+Fmt01sBukj+sATz8SDuh5cHRKbyRpAAgdc9urnmhveax6s3r2QLQgFBAhdm7bsl07hBcI7QXCaPHixcqzhmOiXpAUAuv18y5RkWNXP9nwfA2ShydVAjGbrysmne08qFAOG9Q5uq6yulaF5GnBhPFNi9ZVqsls7UACCSxvLWjIHAnaFOY3m6sJ4glZ9VrkNcznRUjaBNKXX36pxhohEYOT9N5I2jBr1iyvi0FSSDYMbNUG2Y6ly6T1F59LzrvvSZ/GdL5WtBo5UomikgkTJK9tWwka5nmGYOTpawcvghc9mW5EjxfGQiwD3EnPsN/Gl9P9eynU4l2DWIP0IZqBngdJ98qiDhFW5qZtJCMQYtWbVegkRBzEUe/evV3XV6x2iLKijBBDEEaoN3iqdLrvWM+7eO07Vv3E86CFJUQrDCGAbsiG96YbWhfky+g92qtFs6u2XnmNjMkgsFRU19rup6KqVj5ZtkUtmpZ5uTKwa2sZ1q1JNA3uVqKOSYgdnrcOhBq4AT1948aN87oYJIWEfWBrHeY6mTVLOj/9tMj8Bbbb5XbrJm2PP17aHT9VjTEKMkaDDS9nhAvCW4AxFm4G4ccy0NyInmSNBScGuJMMcH4aX07376VQcys8jceGcIanCAIJ5dWTkw4ePNh1D3cyAiHZ0Ek3xGqHOB6EF+Y8wv9RZkRBoHMBginWMeO171j1Y3eOuE+TDdHKRIEV5BBAN4T9vekFLfNzlaDBctJ+DWN18Z5CmnHzuKZ15VW2+4EXat7qcrVo0N+zR4fiaBY9LZzg3SIEeP4kxEMbyRcwtsiKp556Sn784x+r+G0SDoKSgclLIrt2qXmKMIlr5dtvS6TGerK8XKT7nTBBJVyA1yhTYp+NBhtCqWAE48WD+xJGsRNxEs+odSN6kjUW3CRAiJdm20/jy8n+vRRqboWn+dhoFwi7REIC/F6PC3NblmQEgj5eoqGTbojXDvEX9weOCe+RTl2Pjr5Yx4y331j1Yzf/kJ6jyI3X1dj+cW3h+TLeD2EbAxNkwvjeTAW4P3q1L1LLhOHdous3V1YrT1PTnE3lsnRjpRq/ZEUkImpiXCyvfLM2ur5Tm4LdxjX1aV+kxlOR7MLzpyAe2ljsgAGWKUYkya6wB7Tbqnnz1CSu5a++KnVbm2YHb0Z+vhpPhElcWx82XnILCiTTMBps2gjG+aODw6k4iWfUuhE9yRoLTsKQdPpqeEawLtUGoZveeq+Emq5vGPK4xrgG+KvD55we2xyu5tbzkIxAiAe2xTXVHlC0m0SvZ7x2iL/ITAcgLhB6CHE0cuTImMeMt99Y9YP9YgwU6hxtGN4qfEb6dTd1Zu7QwIL94VqjLNk0BiYIhOW9GRQ6tC6QQwd0Uotm5646WbCuSTDh74K15VJdaz+uaWNFtbxbsVHeXbQxuq64ZZ4MMYmmAV1aS0E+U4+HGV/uRDsBhJf0zJkz2UMSQjI57AFzFJW99LKUTZ8uu5Yts90OmecgikqOnSj57ZvipDMRcyiVHmOCjFz4vxNxEs+o1eFBCN+DMYeedxiXVvtN1lhwEoaEiath1CJMCgYmjEM/DUJzEgzUd6p761GH8P7Mnz9fPX+B9oAkKiQSyb6VqECAeNdpx81tQpcDY4JwXbEt2jISTCRap04m6k2kncb7Xaz6wXkidB3XEb/FPYrfIbW5G6+ruUMDcxPqOcUgLvX4rWwdA5MOMvm9mQlg7qSRvdupRVNbV6+8Rlow6VC9bTuso0QA5nL6fPlWtWjyc3NU8gctmHSoHuaIIuHAkzfzddddp1J1AxhKZ555plqswIMYk8MSkk7qKiulYuZMFUK349NPbbfL795NiSIsBf36SVgwG2yJZLGL1eutjToYrNinHuiv5yry2liwMzCNYUjG0Cg9iadfg6LNIgID+bHg/LzKWOXEi4PPOE94HTB2BkY1rgV+ByGRyLETSaiRiEDAulghYFgPcaSvKYQDRDAYPXq0bbZEJ3UWb6yacXJhL7yCseoHAtGqvnHPoY079boaOzRwT6I9opMAdYj7FPvXnRrEHzJxzFfYyM/LlQFd2qhl6j491Dq8J5ANT4fn6Sx6GOtkR219RBasq1DL83OaJoLv1b5VUxY9/O1RIl1LmpLckMzBkztz//33l4suukg1svvuu09lphs4cGCzbdA4iouLZb/99pMTTzzRi8MS4opIba1s/+gjFUJX8dZbEqm2nqwut7hY2kw4Rs1X1HKffWTzli2yHi+0detC9UJLtvcyVq+3NqIxiL1fv37KqINRgO396DG1MzCNWc5gFEIowJCGoeLnoGhtvMNwh+EJQx8LQsC8St3t1IujRS+uDY6tRWOix040HM6tQEA4Ns7RSojh2qJ+V69erbbDu0W3O3gs8dd8LDd15sSQ9XoeG7v60fUNoQsvINoU2hL+uvFmGTs0UHZ4i3A/oOMC9wSuJY7PMTD+kA3zHmUqaPvd27ZSy5FDu0TXl+2oacqg1zi+afGGSqmzG9gkIiu37FTLzG/XR9dhQlvtYVJhet1K1MS3eRzXFGg8uSsnTpyoFoCH7i9+8Qs1BxIh6QbGYPX8+cpTVPbKK1K3aZP1hnl5UnzIwcpT1ObwwyW3VSu+0OJgNGrRE417H4JIj/dJdQpbKwPT7OVC+dBbDgMTZXM6zsltz68O38O5w4CHMauPC0M3WXHmxovjdbYsr/YXb2JghIBZtSE9VxPELzLIwRMCrxiAwQ9BaNXO3CTyMKbAx2eEZULoG8MS7fYHLx08svHaitM2pcchwSOrvT6oD3iWevXq5bjDwdihgePi+BhbhnpFG0XbTCQBB3FGNs97lKmUFrWQA/t3UIumqqZOFq+vjIomeJwwf9OOXfaJx7Zs3yUffL9JLZrCFrkyqGuTYFKpx7uWqLBAEgw8fxJOmzbN610S4pqa9eul/KWXlDCqXrzYdruCoUOk7dSpUjJpkuSbDGW+0OKj56mBQYkxEujVNw4uT3cKW6NRCM8CxAmMXBgkMKadeAQT6fmFWIQxC2MIxjW2h1GrhVOyGavceHG8zpblxf6c1KmdEEPdoq3BsISAWbVqlfqMusD1xWLVzpzWmb7vUQ50sCDLIz5DQKB8sbI0ov0vXbo0KtLs2oqbNoV6hZcHghHlQagk2hXO3cpT5qRDA20SAhN1BUGHusV56AmBifdw3qNwUNgiT0b0LFWLpr4+Ij9sbhrXpEP1NlVaR6mAqpp6+WrlNrVo4FCCZ0kLJj3ZLTxQJAMF0sMPP6z+nnXWWeoloT/HAxPJEuIl9du3S/kbb0j5jBmy/ePZDXk8Lcjv0kVKj5ssJVOmSKEpFNQIX2jOsBKSOowNPfzxEjQEPVNUIkIZIV/wVsGzgbAoHBfbwwuBrGfJjj9w48XxOltWqurUToihXiFEjAY92pgeb2XXzpzWmb7v9bXDMeARwud4WRp16m+ULVZbcdOmtGcU3+P88BnH094nt9dOh9HhvJhiOnV47cklwQEpwCFssEzeq3t0/YaKpnFNOkQPCSLsQOQeJsbFMuOrNdH13UoLd0s93rNdK45rCrpAOuecc9RFOu2009SNjs/xwPYUSMQLInV1SgyVzZguFW+8KZGd1oMqc4qKpOSoo6R06hQpGjNGcmKkOdbwheYMs5CE4YXebvR6AycJGoI81ioRoYw6gDGvBYT+26NHD0/Cadx6cbzOlpWKOrUTYjrzmjY0tWjq2bNn1Pi3amdO60zf9xD3EDxou1qUwCuoy2i1PwgYdA5g21htxW2bQnvCthBUXhjXTDGdejjvUfaBSWc7DyqU8YM6R9dVVteqVOPK27S64e/CdRVqMls7kEACy1sLNkTXtSnMN4xrakgIgdTjLfIawo1J8iRtrSxrTIusH9T6MyF+UrVwkUrLXf7yy1K7oemh0YzcXCk+4AA1iWubI4+U3KIiz19oiWQlClsmI7OQRG8+DMn27dsrg9XvBA1+k4hQ1vPlaKPXaep0p20lSAZuIu3ZaZ1aCTGr+9IY+maH0zrT+1+yZIlqxwhrwzoIfWMZrfaHusDv4p2X2zblh3HNFNOpJUj3LEkfrQvyZdQe7dWiqamrV16jJm9TQ+rxiqpa2/3gu0+WbVGLpqXK0Ne6aVxTj1I1fxOOSdyTdK316dMn5mdCvKJmwwYpf+VVJYyqFyyw3a5gwAAlikomT5YWXZoy0nj9QktkbEo6Mxn5JczMxhuMSvToe5WxLdWY6wnX30065Vhp1DHuw42QNiYLgDcDHoq+fftGB9OnW3Am2p71/ExIPIBwOe1hdGLwJ2NoOqkzvX94bdB+ETIHrxDatDl8z7w/nR0xXltJxANI4zrzCcI9S4IHvD4QMlh+tF/DOrwvkGa8YUxTU0IIeJLsgBeqIU15w5x3mj06FEXHMymPU7cS6VzSEOFB7PHcIvvd734np59+uppZnJBkqd+5UyrefEuJIqTolnprN3Rep45SOmmyCqErGDzYs9jcWC+0RMampCvxg5/CzGy8waBEQgQdamTuHQ+yB82qnmC4wnhPZHJQXNNE6163FS2u8Bt451C/qNMgpAdOtj3jvIx/U21oxmqLSKgBkaTHIzkJE8V32Ab71b+3+k0igofGNSHZA2yYXu2L1DJheNdmGfEaPE1Nomnpxko1fsmOHzbvUMsr36yNruvYuqBZ2nH83aNDsRpPRRrw/O169913y2233aYGI2Nc0imnnCIjRozw+jAkxETq69XkrchAh8lc63fssNwup7BQhc5BFBUfeKDkxPDa+GGQJzI2JV2JH5ASGKE/OKaeLDQZYRYrRTO+Q/1a9Y4HfS4QoyiBxwAGP8qLOsP4oVSKCN1WUA6dLADXD0tQ0gMn2p5RJ1gQhqlFdDKT1yZCLA8dSGQeLz1BMrxj2B6dBFoMuZ2QlhBCzCCj3SEDOqpFs3NXnSxY15QMAn8xzqm61n5cEzLsvbdoo1o0RS3zlBerSTSVqpA9ZO7LRjy3SNDD+cILL8hTTz0lN998s/z1r3+VwYMHR8XSoEGDvD4kCQnV33/fMF8RxhWtberpaEZOjhTtv7+axLXN0UdLXuvimPv00yBPZGxKOhI/oA4wNlAbfDgm0vzCoE1EmMWr01i94xBqQZ4LBOWFsQyPBkQJzhWfkbrZOAdOKkSEsa2gHBC1qDeINZQp0WvnZWdBou3ZWCdIia3LhXaZKo9iLA8dyoE6TkT4Bbl9+0WQvcKEhB3MnTSydzu1aGrr6lXGvOapx8tk644a2/1gLqcvlm9ViyY/N0f27NyQerwpRK9UzREVdjx/guHljQx1WPDCee655+Tpp5+WG264Qa699lrlTYJYuvLKK70+NMlAajdvjo4rqvr2W9vtWvbvr0QR0nO36NbN8f79NFgSGTidjkxGqAPM4YJjIUwIxiBC4NB7n4gwc1Kndr3jQU+djvqAJwHXCB4biBJMogmjGeets6j5kZDArq1AjMJYRzmQIhz1loiodtNZ4NTgTbQ96/LrcEF9LIzRQr2nwqMYy0OH+wV/3V4zhNVt3bpVeaIg/PBb3Gu6fYdRSATdK0xINpKvEja0UcvUfRqiH/DuX1depbLn6WQQEFArt1hn/wW19RFZsK5CLc9/uVo0Pdq2ajZXE/6PdOReDW8IAr4+vWAwnXvuuWpByMEjjzwi11xzjfzpT3+iQMpi6qurpXLWLCl7cbpUfvAB3rCW2+W1by8lkydJ6ZSpUjhsaEI3np8GeaLjCFI92BrHgZjBcbRXBCJA99anok61YahDj5BCWU9QGaS5QFAfMG7hScC5od60KEFZ4YmDwQvjV8+54yQhQSIiQrcV1BM8WLh2KAeEUiKi2mlngRuDN9H2bBR/qGuUqXv37upcU+VxieWhQ2gcJmTFfeL0mmEf8JBCXGmBDfGlJ64Nq5DIVq8Z8ZYwdh4EDbw/upW2UsuRQ5sSWJXtrJH5Jk/T9xsqlTiyY/W2nWr533fro+vaFbVQYunfPxkdirA831sfXjCvvfaaCrl76aWX1MOzV69efh+WBHBc0c45cxpSc78+U+orKiy3y2nZUlofcbiUTpkirQ85RHJaJOfG9SqkLVa6ZbdGQKrHHmjPEUKJYPShDmDgY2xFIi8gt3VqHuuBXnb8xe8STX/tF6gPjEHRYgTGMv7iOYYxXDCA0QuHeoRxC+IZgslmXcPYJ9RRssaDU2Hr1uBN9B5AnaAdIOshMh7qsM9UeRRjeejQLpGRFe0gVrIFc71hPzgPtBeILHzW7TuThUQs4zXoXmESfMLaeZAplLZqIQf066AWTXVtnSxeX9mQDKIxMx5E1PZddbb7QfgefhMGcQTy/Wrs//vf/5Qomg6DuLxc9bT+9Kc/lVNPPVUOOuggPw5LAkj1smVSNmOGlM94SWpWN7lnzRSNGiUlU6dIyTHHSF5JiedGEFIJo6cavcQwgmCUJPvwhsGEv0Hv8TJ6MFDW4uJiZbRhSXZ/Vr3rZmMKhqfRMMTx8Xv8JtbEnulCz92kBZ0WmPAM6DlxcG4wgrHOiSEYS0Q46Tn1QlQ7FbapMnj1OaEOId61ly5VHsVYHjpcA3g5nSRb0Ndv5cqV6lzQAQhRhfX4rFOyZ6qQiGe8Om1X9BAQOzK58yCsFOTnyfAepWrR1NdHZPmWHbtl0dtYUR3dBqF2YcFzqwThdC+++KKKw8ZLBim/MeZo7NixoYpNJPbUbt0q5a+91jCu6Kuvbbdr2adPw3xFx02Rlj2dZwhz86LVaXfRHmHwwHMCoxeZppz2Tlk9vCG4sE9t9AS5x8vrsL5Y+7MypiBKjQPe0cMOA1JPJBsEzG3KnNYb5cU5wZOg53mCQQ3hlIwxb64v1CH2iXrBsRK5Tnb3h9NQPz8TiXgxx5SX2Hno9ISvbsIR8TzQIhrtB20G4XXbt2+XFStWqPaC46UyQUsqjFenE2rTQ0DsyNTOg2wjNzdH+nYsVsukvZrGgm+oqIp6mXq3L5Kw4LklB3F0wgknKE/R4YcfrnoGSfip37VLKt95R3mLKt99D7GVltvllZZKyaRJKjV34V57uRbNibxotZcHL2xtmLjpnbJ6eMMbBcGFfWZCj5fXYX12+7MypmA4wmgMqmFoN/eRsU0htA7GLgxgCCRce7QFeCOTMeaN9QXhCOEOQxrrUH9uRXe8+8OJUPYrkYhdWu3evXurcsFzky5PrLk9Q9C4DUeEKML1QxtZvny5OjecE8asoUMFx8BntB+IJrf1mi4PTDzj1diuIApxbuhA0ElN8L3XHgJ6o8JFOrK7Eu/o3KZQOg8qlPGDOoeqWj1/uuKhF7QedOIPMHp3zp3bMK7otdelvqzMcjuMI2o9frwSRa3hSUzioZfIizbZ3imrhze8IjpLFXu8Ytc1xITbAe+pMJD0PiB+Vq1aFfVmWLUp7B9hwgAGMLw7EEeYEDuZ552xvrBf1BHuKxjXaONujUg7byfOFQIsnYlEYqXV7t+/v2feVy/aRqLhiFokwSuFNgJxBLGA+Z2wD4gjtBun1yIIHhgndaE9lCgjwhLR5oxl9NJDQG9U+EhHdldC4uH5k5XiKPzsQqw95it6aYbULF9hu12rkSOVKCqZMEHyXIz5iXnsBF60yfZOWT28YeToRAPs8Ypd1wgZQ+IDPQ4jWYPbCwPJuA+dBh2/RZmt2pRfosGcSQ1jXWBYQ+AkYkSa7w8IU4yNgUjFfp3WlR+JRFIx8a1XxrPxnjcKTHiA9ETIVu0d1w91j3FIOD5+C3Gkn1XwrmA/8JplyhgNp8ZrrDJ66SHgeJXwkY7sroTEI+nWB8MHvekLFixQD0Z8jhc2he8R300yh7qyMpV9Dt4iZKOzo0XPng3zFU05To0x8ppEXrTJ9k5ZPbzxf/QUG/eJ/cF4QnhOtj7g7epaD1T3Ai8MJOM+kEENhi3WQVAYB577LRqM9aXn3oGASNSINN8fOpwtlncsVfgx8a1fxrO+51GHSO2Oa4M2AvEFsakFV6xnC8riVfKCdI7RcGq8xiojUrh75SHgeJVwkursroTEI2mLZdy4cephiJed8TPJfCIYV/TBB8pbVPn22xKxGVeUW1KivERIuACvkZ/XPxGx40XvlNXD27hPhA2hXBD+QU/a4CfJ1nWqjEXjPhDuBY8gJilFSBSOmarwDvP4DYT7QSygHIkYkeasjTDq9fp0h4LapdVG/aM8CM1KtmPBS+NZp/FHKC0SiliNX4zV3r1MXpDuMRpOjNdYZfTSQ5DuujDD8VCEhJOkLbeHHnoo5meSWcBYqZo3T03iWv7qq1K3dav1hghHGju2Yb6iw8ZLbkFBSsqX6IvWj94p4z5h2MKwZ5rSxOs6nrHo5WSzZiMLC4xX9HRjrFEqvX/G+kJoVjLjZ8xZGyEScE8jzA7rIZjSZUxapdVG2SAG8VePR0qmYwEddag7jCnTc1glc75OBJdde3fyrHLq8cqEMRrxyujVMzhIdcHxUISEF88tgIcfflil9MbL2Apk93n33Xfl7LPP9vrQJAkwR1HZSy+rELpdy5bZblc4YoQKoSs5dqLkt2+fljoPoiueYR/JE8tY1APAvZps1srI0okCdFm8ioV3m5Y+2bZtzNoIwaUzq+Ev6jWdxiTqAZ4jTFIMUYTPOkEGxuYkEwKo5x1C24DQ0pkHBw8enPD5JuutiHc9nT43MmGMhtMyJutxCVJdcDwUIeHF8ycKJoN95JFHbAXS7Nmz1TYUSOmnrrJSKmZiXNEM2fHpp7bb5XfvJqXHTVEJFwr69UtpGTOFoIV9ZCKxjEWzIZLsZLN2RhaIF/LkxsBLRw+zVWY1dEwhsxoEU7y68iNkyC6VOgQMPEgQR8mGxKHMWNAeMK4M9yDC43CNEzXS/fZWuHluuBXP6Qj9ildGr+6HoHSSsWOMkPDi+dMSvYKxQBafIPV6ZRuR2lrZ/uGHShRVvPWWRKqbZkA2kltcLG0mHCOlU6ZK0ehRktM4xowEP+wjU4llLJoNES8mm7UysuB1iBXy5NbAS0cPs7keUU86s1q8Y7o9P6dGuF09IMObVx0Luo3gvkMbQR3jGPBYJXqOfnsrUjHnVJDGRIbN48KOsfTDMWDELzx5Un799dcyd+7c6Of3339fNVozeEDff//9MnDgQC8OS9yMK/ruOymfMUPKXnlV6jZtst4wL0+KDzlYjStqc/jhktuqFes4A8M+MhUvMoL53SOMciABAuYrgpGHeW3w2Wzg6Zc2xv5gPFCfPn1SliQhGaPbjQHrxgi3q1d4ArGtFwLBqbHq1kj301vh9XPDPLcXPHQIQcV4NCSQQb307NlT0kXYPC7sGEsvQe0IIOHAkxb0wgsvyHXXXaf+j4feAw88oBYr8CLAOCXiPzXr1knZSy8pYVS9+Hvb7QqGDpG2GFc0aZLk0+ORMEEJ+8hkMLAeHg88R2B86ExhqTJE4hnZKBuOj/LBM4HshcAYUmx8aUMcYVwMkhLAW4IkCQj70r/zo8c0GaPbjQHrRmjY1SvmQoJnKxmBoOsD1wa/x9g0RCrYtZFY5xjEsDSnmOf2wv2CsVhIXIG2CjGPlOVeptzPdo8LO8bSS9g8kiRYePKUPP/882Xy5MnKU7H//vvL9ddfLxMnTmy2DV5E6C3EQGgqe/+oq9wuFW+8IWUzpsuO2Z/AfWS5XT7i/4+bLCVTpkghPXokgD2B6Pn2wxCJZQTHE2IwvGFo4oWMMD8YoPAmYb3VSxvCCeIIPfo6dTd69fX4Kbfld9pjmqjRrY1VeBwg5PAXz3U9jUOiYipWvSYjEMz1gX2h3WB/EF9WbUSnncY1wTXS9YhztKtbkGrh5Bbz3F4oO9ocwlAxvxeuI8S6HqflN1b3WRg9LuwYSx9h80iSYOHJEx5pcbGAWbNmydChQ9X8FiQ1ROrqZPvHs5UoqnjjTYns3Gm5XU5RkZQcdZRKtlA0ZozkJNGLTUiqewK9METiCYxYyRtgUEMIacEAcYTt8X90/ti9tOE5QgprfEYacWyP88V6t+fjd48pzhVp1DHxN4xpACGI/5s9D27ElF897Vb1gf1DHNnVB8oAjwpCI3VZkMAC66zq1jj/kZswnlR7o8xze8Ebi+uGdZh8WM+FlQrjMdZ9xlBk4hVh80iSYOH503rEiBEq9tlOIH3zzTcqBhoPcZIcVQsXKVFU/tLLUrthg/VGMN4OPFCJojZHHim5RUWsdpKVPYEw2mD4w6MDLwN62RHyFk+ImUPmAAxQ9HzjOx0qZvfS1uFeEEc4Dn6b6Ln5XU84d5QRBjXqAPu3E3RuxJTet9eei0TqA4Y6QhxRFp0ABJ9xba32hXPHObkRpekYG2Fud7gWEEnwWKKt61C7VBiP8YQ8w5+IF4TRI0mCg+dP6ssuu0wWLlyo0nlbccEFF8iQIUPk3//+t9eHzhrKX39dNj3woFTPn2+7TcGAAVJ6/PFSMnmytOjSOaXlIyRoPYHaYIU4wosUxqMWOQhDimVQm0Pm9LxC8JhYzStkfmnDuwIjFQYqjpnMuaWixxRGtPY4YP8IIdTzCyUqpvwikfrQY40Q9aAn0sV1wl+rfWG9WxGWjrER5naH69K3b18l/hAWmkrjMWyhT8yUFkw4BoxklEB6++235cILL7T9/rjjjlOZ7Eji1G0rsxRHeZ06SumkyVJ6/FQpHDyYVUwyBqNxh9AnGCQQMTDW8X+nKaaBVViTNlhhNEKs4Lc4HoA3KZ5BbZ5XCCLJbl4h80sbBiqOpcuQjKGaih5TPUYH5whxBC8bzhshhjhf47lqMaVTayfjHUuEROrDTlTBywJPoHlf8MIgnNKpCEPbQl3hemOfqJNUCAQrYxH/1xMHp3LsVJhCn5gpLdhwDBjxC8+flOiNjfVy0vH4JHFKJk6Q9TfeKJGaGskpLFShc6VTp0rxgQdITsAGDhPixriDMYVMW/BYwDCH1weeGnNokpXRgnAvs0DSYU1a5GiDFQYvjgGDGCm43RjUKFe8eYXML20Y2nj2JWuopqLHFPuDaEQdoa5QRxBByA5nHuCfbkM4kfqwE1V6sRp/hjaot9eJIOBRgxAyHk+3S4SZ6zaMcHPUTSrqxcpYTEc4W5hCn5gpjZDsxHNrGmELX375pe33X3zxBRM4JEleaal0uPAX0qJbd2lz1FGS17ppgDghmYpOkoCQNGTeMg6ON4cmWRktEFbwYuCzOaxJG6cwarW3A0Zuv3794o4L8cLY87KX0+8eU71/nCu8bahjXAurUMQgGMJu6yOeqLLal95eiyKIRQgh89gi3S6xrf68evVq5Q3VEw1rj2g6wrZSdcwwhT6FLVyQEOIMz59Wxx9/vNx7770qzfeUKVOafTd9+nSZNm1azBA84oxOF13EqiKhw6kxYrUdQvMA/m/+LRIkaEMeSRMgjuA5cjJoPkzGnlPgNULdanFk5xnK1LpJRFRhe4gdeCox1kqPuTIKeN0uIRLxPdoZhDtCEeFNwmStqEsdppnKJA6pDhULS+hTur2khJD04PlT8dprr5U333xTTjjhBNl7771l+PDhav28efPkq6++Ugka9KSyhBCSiDFitR3CwCCMrH6brCGfrLGXaYO83XiGwmIIO7mGSPKBEHEIH7QveIaMqbON7RIic8uWLeo7eOJQfzprIvYFoZXKJA4MFUuMIHhJCSGpx/M3NF4EyGB38803y/PPPy/PPvusWo8JYq+66ir57W9/22zOEEIIcWuMWG2HjF3ALhlCugz5TBzk7bVnKNMEohUoP8ZlQdTgHCCMsE6HcBrbJbyZK1asUOOQkEEO543rr7MmIlQv1WFbDBVLjEz1khJCksOXOxwCCF4ieooIIX4YI7EmdPUiGUIQe+5TITL8OEbQBaLTc8b3WI+kCxBKyPCnvUNGEY7zwj6R2AFeTQgkjKszZk2EdwnepFSGbQUlVCwTxXK2eEkJIU0E+6lECMk6nBojdtsFzZDxouc+FSLDr2MEObTLzTnjO4gbrEcnIAQQsvzBc2lO847QO4ggGP/YtzlrIsYgYbtUhm3F886mSoAHWSwTQojG8yfSz372s7jbwEjgRLGEBJtM7OkNYv1hHAq8CDCSYTgn0nOfCpHh1zGCHNrl5pyNAgNlh0iCwLCqGydZE1MdthXrmF4IFyfPiyCLZUII8X2iWLwMjCCDD2Ky8RfhCRyDRDKVbBENYe3pTdX1M9YfUkJDICE9tM6g59ZbkAqR4dcxghLalew5uxE1RjFllzUxHWFbdsdMVrg4fV4EWSwTQogRzy0DpC61AvHaDzzwgNx5553yxhtveH1YQnwnrKLBijD29Kby+pnrD+FYOBYmqsVccW6FWSpEhl/HCHIWMLfn7Cb8M5MG9icrXJw+L4IslgkhxEiupAg8OH/5y1/K0Ucfrf4SkmkYjQAYePiLz1gfNrTBZJxTSK/LVFJ5/cz116ZNG2UEIoEEDEa3hjKMa5QZHU0oM/5qkQHhB+8UsqbhLz4nQqxjJIMWC4MGDYouQelU8OucjWKqd+/eCV3zVGIULhhX5Va4OH1e+FnfhBDiJSl/YmNupEceeSTVhyUkabIpPCQvL0+Fha1atSo6IWam9/Sm8vp53VMeK2ufV14xP70eQc0ClkmeHj/DQ5P18jlt75lU34SQ7CblTyWE1xUVFaX6sIQkTbaEh8AQg7EEgYTMWwDJBTDJc6b29OKckCQBg+YxHhKhbvi/X9fPj7AyK5EBj5EfKcS7d+/uyGhNxGgP2ji+oIq3VIaHJitcOLEwISRseP5Wuv766y3X42H+3nvvyZw5c+TKK6/0+rCE+E6Qx1J4CYxXLDAaISR0OmPM95KJPb3auMQEnZh7ZuvWrWrBtdPjgbwmVT3l6Uwhnsjv9G8gUiG+4ZlE4p6RI0eqRAbE+zGBTgVpMkKRniFCSNjw3Nq59tprLdfjod6/f3+5//775bzzzvP6sIT4TrYYAWajG8IIxhgmu8xk4xKTdg4ePFg2bNigMsvBMPdzLEwqPBNeeDUTNb4T+R1+A3EEIYXxJ1qwgtGjR4fuXkq3EE5lYpJM8MQRQohTPH8bZaoRRYgTssEICFsoodm4xPWDwYiwwXQZ5F6EmWEfmDoBXhiIDHj6UplCPJHf4Tt4jiCOcL4oJ+oB3j3ttSTe3ZNhzEZJCCGpgN11hJBQhxL6Lfjcih1zrz62hbCBwdqqVSvH43iM8ywhBBJjO/v27es6Y1qi9ZPI7/AdBB08RzhPjHPDOaNjLYzJTtJ9T2ZTYpkgEbRxdoQQ9yR9xyK1bCIg9SkhJHiELZTQT8GXSAiTsVcfXizMHYcEElgHQ9ZJCJSVZ0B7ZRJJIZ5I/STyO3yH0EZ4vHAOEEcIfUQYZ6Z6KIN8T4bNG5wJZNN8eYSEmaTv1j322EP1TLkFoSGEkGASplBCPwVfIiFMxl59HW6mk2DouZnihUB56RlItH4S+R2+Q0IGgLA6eI5w3n4ly8j2ezJs3uBMgGGNhISDpC2E//znP80EEl54d911lyxfvlzOOOMMNSkgWLBggTz++ONKUF166aXJHpaQUMMQjcwQfIkIFWOvPq4zws3gSYE4cip0/JhnKZH6SeR3CCdEQoYghCCF/T4Lmzc4E2BYIyHhIOmn5DnnnNPs84033qhi4uFixqzx5gx3hxxyiJq7gxBiDUM0MscgTkSoGHv14UGCsEKYmRuhkwrPgLmuYGTjmF7UXRA8lKm4z2K1t1SJs3h1HXaRmGoY1khIOPD8KYg03pdddtlu4ggg9hwpvv/xj3/IH/7wB68PTUgoYIhG5hjEiQgVY68+JqtFhxE6lRBy5lTo+O0ZsEokgbDovLw89V2qxlX4abz7fZ/Fam8gCONU2BnjPQxrJCQceP4k3rx5swoZsQPfYRtCiDUM0fAHPwziZMbv6GP26tUrIRHgpxfGXFeYuwhCDmOFcMxUpIv223j3+z6L1d5ArLaYKq8OO2O8h2GNhIQDz5+4BxxwgNx5550yceJE2W+//Zp99/nnn6vxSWPGjPH6sIT4TqqMFoZo+INfBnGyQiUI4Wbx6gptEp9h0KcqXbTfxrtf95l+TqxcuVJl6+vTp49lndm1xVR6ddgZ4w9BvKcJIe7w3Lq75557ZPz48bL//vsrsTRgwAC1fvHixTJ79mxp37693H333V4flhBfSaXRwhANf6DwTLyudJvXGfeQlhzrEA3gV2eBlfGuPVledFLY3WcQYIkew/icgDjCGDOkcUdyIoRTGgWYnThLpVcHc1LhPFetWiVt2rSJiuEwpAFPx9gqjuciJDx4/rQYOnSofPPNN3LTTTfJa6+9JnPmzFHr0Yv2q1/9Sn73u9+xZ4VkHKk0Whii4Q8Uns5Bu4ZRiXFRGzZsUMZzjx491BgkiBS0fwglfAex5EdngVmk4Th6vic9Xss4psetMWx1n+H/EDSJdoQYnxMQRdgXRBKyuuK5YRxfZjd2bc2aNSmZ3BXGPMoG4Ya6hShEyvXBgwdnfBrwdIyt4nguQsKFL08KPOjvuOMOtRASBlIdisIQDX/qlCmPnRl6MOyROALTNsDLUFRUJCNGjFACBYY0RArEBCa69auzwCxoca9BlJmPC/FWUVGRkDFsvs9wbsl0hJifE1okQVxirJlRuNm1xVR5OiHmsOC8OnfurI6D640yZXoWu3SMreJ4LkLCha9PQTyUEIcN8HLAw56QTIThWeGAwtO5oYfU4/369VPPcRjx+AvjEv+HBwcixWr8jFdhTWZBi3A+eKzMx9VeLC+M4WQ7QszPCSQlwr7w/jOXxa4tpsrTqc8V+8a5or5wvDBM4p6OsVUcz0VIuPBFIH322WcqlO6DDz5QPVIAvZCHHnqo3HzzzTJq1Cg/DktIXBI14BieRbKFeIaeXWcBwu+8DmsyigjsT4fZGY+LMnplDOMcqqur1Zgc7AfvLTfeGy+eE6nydIa50ycd5xbm+iQkG/FcIH3yyScqSQMeCj//+c9lyJAhav38+fPliSeekLFjx8o777yjkjgQkkqSiRFneBbJFuIZenYiAOFvfoY12R0XZcRYmmQNUzwfsH8IJOwPwFuFd5hTgZPIc8Ku08bvLGhh7vRJx7mFuT4JyUY8F0h/+tOfVLw1vEfmB/y1114rBx98sNrmjTfekFSCl97VV18tjzzyiMoutNdee8lf/vIXOeqoo1JaDpI+ko0RZ3gWCSpehrbFM/TsRIDfyQXsjgv0vZyMYWoek4NxTRB9SFzgpi7dPCfSObA/zJ0+6Ti3MNcnIdmILx4kCBGrFwReWueff77ccMMNkmrOOeccefbZZ+XXv/61Sj3+0EMPybHHHiuzZs2SQw45JOXlIamHMeIkUUER5PS9boxsJ+fhxNCzEgGpCDGyEx9eGKbm5wOEEepUh4mHcWB/mDt90nFuYa5PQrINz9/wiNnGS9gODADFNqnk008/lSeffFJuueUWueKKK9S6s88+W4YPH67GSn300UcpLQ9JD4wRJ4n02gc9fa9TI9vNeSRi6KUzxMgLw1Q/H+A5gijSHiQ/31fstCGEkGDi+ZP/oIMOknvvvVfN+2BmxYoVct9996kwu1QCzxEG38J7pSksLJRzzz1XPv7442imPRJuYKjBYEOKYhhw+MsY8eADwx7pl/H8wN9YHTBuBQWuP/7iM9Z7sX2q0UY2vDY6tE2vS+V5aM/ToEGDoktQRKTT5wMWtDFMbI6/mCMI45GSbXNOOm0gxjiwnxBCgoHnb66//vWvKlsdJps74YQTZODAgWr9woULZfr06epl+be//U1SyZdffqnKgQG3RnSiiLlz56o0rCTcMEY88/DDe+O21z7ovfxOPaOpOI9MDjFC2eF1Q3pznIPOYgcB2aFDB1/OiwP7CSEkSwTSyJEjVUgbEjHMmDFDzQMBMNHghAkTVGKEoUOHSirBzO/dunXbbb1eh8HFdmCODcz5YQQGG8lMMtmAy0b8GKPhNtQy6KGZTo3soJ9HEEAIOASSnhtIZ+bzc0JoDuzPnPF+hJDsId/rTHEzZ85Us4e/8MILKo5bi4tOnTqlfOyRBmESeOmZQZid/t4OhARed911vpaPEGKNH14Pt732Qe7l18Yknm/wchQXF0urVq0sjcogn0dQSIeI1J02+lqiwy5bhUHQx/slCkUfIZmHp08cPMxOPvlkueuuu1QabQgivIDTDQwGiDczVVVV0e/tuOiii9Q5GcED/Pjjj/ehpIQQvw1Wt732Vtvj/372cjsxqKyMSWyDcGGrstBbEZ90iciwCoNMy+rnB7y2hGQmnj550cOLFNpBGbxsDKVbvXq1Zegd6N69u+1vMR8GFkJIeAxWt6GWxu39Nnic7j8RY5IhpsEMeQujMEiEoI/3SwReW0IyE89j3v74xz/KPffco5IyBIV99tlHFi1aJOXl5bvN2aS/J4QEjyBmRvM7G5zT/TvNXkfcoUVk79691d9UtDXjtURouvYgohMP//c6k2NQCWNWP96nhGQmnj/5Z8+erWLhMcfQ+PHj1XgkcwgbXuYIw0sVJ510ktx6663y4IMPRudBQsjdtGnTZMyYMcxgR0iACZrXw0kvdzJjDpz2oqc76QLHVXiHvm7oxMN11G1Hj0cCxvYU1vC7MI6TS/d9SghJDM+frvAead566y3LbVItkCCCMI7oD3/4g8pKhxfLf//7X/nhhx/k3//+d8rKQQjJfOIZPMmG4Dk1qNJpTBrPEWM5MadYaWmp9O3bN2VelzChryXqFO8oeA0R+t2mTRtZtmyZemdCMIc9/C6M4+TCKPoIyQY8f+ogPCCIPPzww3LVVVfJI488Ilu3blVJJF5++WUZO3ZsuotGCAmRwZPsmAOnBlU6jUl9jpiAG6FQKC8Me+0BCaN3w0/0tYTYRHQDxr1i3j4II4TUAWMoZaaPy4lF0DzGyRJG0UdINpA1dyhSet9yyy1qIYQQvwyeZAeauzGo0mVM6nNEenGIIoRR41yxhNW74Tf6WpaVlSnhibqE2EQd6/8zRCszCZvoIyQb8E0gzZs3T1599VUVxgYwFmnixIkyYsQIvw5JCCFpN3i8GHMQdIPKeI4It8OUDvCYISQMXhA7MchxS+69hwhbNHrtsiFEi+2EEBI6gYTwgAsuuECFsiH0Qk8Oi9A7jAE644wz5P/+7/84QJEQEkqCOObAa4PTOGYGgqiurk5NBg5Ph50Y5HwwiXsPAZIfZUOIFtsJISQIeP6E/f3vf6/G+2CC1UsuuUT69++vXpp4kf7jH/+Qf/7zn9K+fXu58847vT40IYSkXWwEbcyBHwanPkd4jJYuXarC7PCch1CyE4OZOh9Mqr0Zdt7DINeRl2RqOyGEhAvPn/KPPvqonHXWWc2y2QHMX3LvvfeqFym2oUAihGQaTsVGkELk/DI4cY49evRQgsiJgNi5c6dKkINsd4goQPjhxo0bdwvHC1J4Fb0ZqcftGL4gtRdCSHjw/CmCdK8HHHCA7fcHHXSQvPTSS14flhBCQtW77ZXhl2zSiHg4EYN6olMkIICgRFIHJB+AWDKG4wVNkNCbkXrcjOELWnshhISHhgFCHnLMMcfIzJkzbb9//fXX5eijj/b6sIQQ4jtabBhTLut1XqINv4ULF0YXfMb6ZAxOjAtNx0SVEBoYq4TU1UVFRcqbBLGE7KLGcDyjIIFnCn/xGeu9QAu1FStWqL/x6jNV15s0gfaAa4/OVlx7/HUStulHeyGEZC+ed7HccMMNcsopp8iJJ54oF198serJAYsXL1YhdsuXL5ennnpKtmzZ0ux3GJdECCFBxosMdan2XAQhaQQEBcQIspnqzHcQSOZJZf30diXibUjV9SaS0Bg+v72jhJDsxXOBNGTIEPX3m2++kenTpzf7Dr2XYOjQobv9DoN7CSEkyKRKbHhp+AUhaYQWFfAcIawOQgPnhlC7VAmSRERnEMRlNuJ0DB8FLCHELzx/Q1599dXqhU4IIWEjVWLDa8Mv3UkjnAoNPwVJIqIzCOKS2EMBSwjxC8+f8tdee63XuySEkMCQCrERNsPPqdDwU5AkKjrTJS6ZnS0+FLCEEL9gNxghhASMMBp+ToWGX4Ikk0Qns7NljneUEBJOMvdtSwghIYaGX/aKznSmF6fnihBCKJAIIYRkCZkiOtOVnY2eK0II8WkeJEIIIcRr3M5hlMmka+4qzitECCENBC+2gBBCCMliz0a6xktxXiFCCGkgfG8WQkgo4diI7CWdY3KyabwU5xUihJAGKJAIIYEn2zwIpDnZ6NlIx3ipTMr0RwghfkLLghASeLLNg0CaQ89GasikTH+EEOInfOoRQgJPpnkQGA7oLfRspI5MyfRHCCF+QoFECAk8meRBYDig99Cz4Q0U7oQQ4gwKJEJI4MkkDwLDAYPj2chGQWB3zhTuhBDinHC/KQghoSCTPAiZFg4YVrJREMQ6Zwp3QghxTjjfEoSQ0JEpYyMyKRwwzGSjIIh1zhTuhBDinFwX2xJCCIkDPFsI/6upqVHGKf4GNRwwzGhBAJGqPXl6XTaes1G4RyIRCndCCIkBPUiEEJKl4YBhJhs9ebHOOZPG8RFCSLrhG5sQQrI0HDDMZKMgiHXOFO6EEOIcCiRCCCGhIxsFQbxzDpJwz8YMg4SQzIFPI0IIIaEkSIIgVWTCOWdjhkFCSGbBJA2EEEIISUu2PYQA4i8+Yz0hhAQBdtUQQhKCITKEkERgynFCSNChQCIkjWSqyGCIDCEkUbIxwyAhJLMIviVGSEjJZJGRjkk4M1VMEkKak40ZBgkhmQWtC0KySGRkaohMJotJQkhzsjHDICEks+DTiJA0kclx+KkOkclkMUkIycxse4SQ7IVZ7AgJgMiIRCIZFYeP3l6ExNTU1Cihgr9+hshoMQkxpsWkXkcIIYl4pdetWycrVqxQf/GZEEI09CARkiYyOQ4/1SEyHNRNMo0wjpkLyzkxZJcQEo/Me7IREhIyPQ4/lSEymSwmSfYRRgM8TOfEkF1CSDwy66lGSMjIljj8ZHue3YjJsPRyk8wljAZ4mM4pk8d/EkJSA60GQkhG9Dw7EZOJHouiinhJGA3wMJ0TQ3YJIfFgkgZCSMp6nhEWh7/4jPVBOJYWVQsXLowu+MxB2yQbE7BkwzmlOskMISTzoAeJEBKanudEjhWm0CESDMI4Zi5M55Tp4z8JIf7DpwEhJDThLIkcK0yhQyQYhNEAD9s5Zcv4T0JIYmTmk40QkjGksuc5kWNxPEL6CeMYsDAa4GE8J0IIsSKz30CEkMCTyp7nRI4VptChTCRM6aMJIYSEA759CCGh6nl2e6ywhQ5lGhwDRgghJGjQAiCEZD0MHUofHANGCCEkaDDNNyGEkLQRpvTRhBBCwgEFEiGEkEDNSYN1GJu0YsUKWbduHeekIoQQklIYYkcIISRtmMeA5eXlqSQNS5YsYdIGQlJAGLNIEpIsvAMIIYQEZgwYPEYw1jhxLyH+wyyShFjDEDtCCCGBS9qACXv1xL16HSHEvyySCHXFX3zGekKyGQokQgghgYFJG8LhlYAnkGPIgg87JAixhiF2hBBCAgMn7s1sGLKVuR0S8NYyiyQhDVAgEUJSAgcCEydw4t7Mvmc48W9mwQ4JQqwJ9pOWEBIK2KtM3MCJezP3nuHEv5kFOyQIsSa4T1lCSGhgrzIh2XHPxAvZykSvWNhhhwQhu8OnEiHEd9irTEh23DOxQrYy1SuWTVDAEtIAn0iEEN/hQGBCsuOeiRWyhcx2megVyxYoYAlpgmm+CSG+AwMJvcg1NTXKIMJf3atMCAnXPaNDtnr37q3+au8QU0oHG86JREgT9CARQnyHA4EJ4T2TqV6xbCFTwzoJ8QMKJEJISuBAYEKy+55hSulgQwFLSBMUSIQQQgjxHXqSgw0FLCFNUCARQgghJCWEzSsWJihgCWmCAokQQgghhFDAEtIIs9gRQgghhBBCSCP0IBFCSADhhI2EEEJIeqBAIoSQgMEJGwkhhJD0wRA7QggJGJywkRBCCEkfFEiEEBLQCRsxUaOesFGvI4QQQoi/UCARQkiAJ2yMRCLqr15HCCGEEH+hQCKEkABO2NilSxepqamR9evXq7/4jPWEEEII8RcmaSCEkIDBCRsJIYSQ9EGBRAghARVJXbt2TXcxCCGEkKyDIXaEEEIIIYQQ0ggFEiGEEEIIIYQ0QoFECCGEEEIIIY1QIBFCCCGEEEJIIxRIhBBCCCGEENIIBRIhhBBCCCGENEKBRAghhBBCCCHZIpAeeughycnJsVzWrVuX7uIRQgghhBBCAkTWTBR7/fXXS9++fZuta9u2bdrKQwghhBBCCAkeWSOQJk6cKKNGjUp3MQghhBBCCCEBJvQhdkYqKiqkrq4u3cUghBBCCCGEBJSsEUiHHXaYlJSUSFFRkUyZMkUWL16c7iIRQgghhBBCAkboQ+wgiM4555yoQPriiy/k9ttvl4MOOkjmzJkjvXr1ivn7DRs2yMaNG5ut+/77730uNSGEEEIIISQdZJRAqq+vl127djnatqCgQGWqO+WUU9SiOf744+WYY46RsWPHyo033ij3339/zP3cd999ct111yVddkIIIYQQQkjwySiB9N577ylPkBPmz58vgwcPtvzukEMOkTFjxsibb74Zdz8XXXSRnHzyybt5kCC0CCGEEEIIIeEiowQSBM+0adMcbdutW7eY3yO0buHChXH307lzZ7UQQgghhBBCwk9GCaSuXbuq8UResHTpUunUqVNCv62urlZ/ORaJEEIIIYSQ9KPtcm2nZ41ASgQkWDALoVdffVUla7j00ksT2ufKlSvVX4bZEUIIIYQQEhxgp++7775J7SMnEolEJMQMGDBARo4cqSaJLS0tVZnr/vOf/6gQvM8++0y6dOniep/btm2Td999V4XpIRlEOtDjoF588UXZc88901IGEgzYFgjbAuEzgfD9QLLdVqiurlbiaNy4cdK2bduk9hV6D9Kpp54qr7zyivzvf/+THTt2KGF03nnnyTXXXJOQOAKo9KlTp0oQQCMfNmxYuotBAgDbAmFbIHwmEL4fSDbbCvsm6TnKGoH0l7/8RS2EEEIIIYQQEo/cuFsQQgghhBBCSJZAgUQIIYQQQgghjVAgZSjIzIdxVImmKifhgW2BsC0QPhMI3w+EtoJ3hD6LHSGEEEIIIYQ4hR4kQgghhBBCCGmEAokQQgghhBBCGqFAIoQQQgghhJBGKJAIIYQQQgghpBEKJEIIIYQQQghphAIpw6iurpbf//730r17d2nVqpWMGTNG3njjjXQXi/hIZWWlSuk+YcIEad++veTk5MhDDz1kue38+fPVdq1bt1bbnnXWWbJx40ZenxDw2WefyS9/+UsZNmyYFBcXS+/eveWUU06RRYsW7bYt20G4+fbbb+Xkk0+Wfv36SVFRkXTs2FHGjh0rL7300m7bsi1kFzfeeKN6RwwfPny37z766CM55JBDVJvp2rWrXHrpper9QsLBO++8o6691TJ79uxm27ItxCffwTYkQJxzzjny7LPPyq9//WsZMGCAMpSPPfZYmTVrlnrwkfCxadMmuf7665VBvPfee6uHoBWrVq1SRlJpaan89a9/VS++W2+9Vb755hv59NNPpWXLlikvO/GOv//97/Lhhx8qw3ivvfaSdevWyT333CP77ruvevlpg4jtIPwsX75cKioq5Cc/+YnqLNuxY4c899xzMmXKFHnggQfk/PPPV9uxLWQXuN549qMDxczcuXPliCOOkCFDhsjtt9+utsX7YfHixfLaa6+lpbzEHyB8R48e3WzdnnvuGf0/24JDMA8SyQw++eQTzFkVueWWW6Lrdu7cGenfv3/kwAMPTGvZiH9UVVVF1q5dq/7/2WefqTYwbdq03ba78MILI61atYosX748uu6NN95Q2z/wwAO8RBnOhx9+GKmurm62btGiRZGCgoLIGWecEV3HdpCd1NbWRvbee+/IoEGDouvYFrKLU089NXL44YdHxo0bFxk2bFiz7yZOnBjp1q1bpKysLLruX//6l3o/zJw5Mw2lJV4za9YsdT2feeaZmNuxLTiDIXYZBDxHeXl50d5BUFhYKOeee658/PHHsnLlyrSWj/hDQUGBCoeIB3qQJ0+erDxNmiOPPFIGDhwoTz/9NC9PhnPQQQft5gWEFxkhdwij0rAdZCd4N/Tq1Uu2bdsWXce2kD289957yka48847d/uuvLxcheKfeeaZUlJSEl1/9tlnq3Bsvh/CBzzMtbW1u61nW3AOBVIG8eWXXypj1/iAA/vvv3/UbUqyk9WrV8uGDRtk1KhRu32H9oG2Q8JHJBKR9evXqzEogO0gu9i+fbsKwV2yZInccccdKlQKYVSAbSF7qKurk0suuUR+/vOfy4gRI3b7HmHWMJbN7wd0uOyzzz58P4SMn/70p8pORAf6YYcdJp9//nn0O7YF53AMUgaxdu1a6dat227r9bo1a9akoVQkKG0D2LWPLVu2qAQf8EaR8PDYY48pQxhj1ADbQXbxm9/8Ro05Arm5uXLiiSeqcWmAbSF7uP/++9W4tDfffNPy+3ht4f333/e9jMR/IHh/9KMfqXHp6DT77rvv1DizQw89VCVlGDlyJNuCCyiQMoidO3daGrjoJdDfk+xEX/t47YMCKTwsWLBALr74YjnwwAPVYH3AdpBdIFnPSSedpDrHECYFT8KuXbvUd2wL2cHmzZvl6quvlquuuko6depkuU28tkDbITxh2Fg0SNqC5wOS+vzhD3+Q119/nW3BBQyxyyCQ1hteADNVVVXR70l2oq8920d2gAx2kyZNUhkL9dhEwHaQXQwePFiNM8RYkpdfflllrjzuuONU6CXbQnbw5z//WU3pgBA7O+K1BdoO4QXZ66ZOnaoyHaMDhW3BOfQgZRBwhSOcxs59jnSvJDvRoRO6LRjBOrxA6T0KB2VlZTJx4kQ1GB+hMcb7nu0gu0Fv8QUXXKDmxmJbCD9I0f3ggw+qxAzGEHuInpqaGvnhhx/UWJR4bYG2Q7hB8hZ4ljFmkW3BOfQgZRAYTIkXH7KQGPnkk0+i35PspEePHiq8wjgYU4M5kNg2wgEMH3gI8ByAx2Do0KHNvmc7yG50qBRENNtC+EGHaX19vZr3pm/fvtEFNgGeEfg/xidijrT8/Pzd3g8wmpHcie+HcLN06VIVSomMhWwLzqFAyrDeQbhI0WOkgct82rRpMmbMGNVLQLIXDM6E0WxM9/7WW2+pFyUmFyWZDe79U089VaX0f+aZZ9TYIyvYDsIPMlaagcfg4YcfViE0WjizLYQbGLsvvPDCbgtS/2O6B/wf04AgFBehmI8++qhK/6x55JFHVFgm3w/hYOPGjbut++qrr2TGjBly9NFHq0QubAvOycFkSC62J2nmlFNOUQ+9yy67TMWW/ve//1UeAhjCY8eOTXfxiE8gMxVCqhBG8c9//lNlq0JGGoDYczz0IIywrm3btvKrX/1KvfhuueUW6dmzp3z22WcMsQvBgPy77rpLeZDwHDCDOU4A20H4OeGEE1QkAZ758BRhTBoyGiJxx2233SaXX3652o5tITsZP368Sv8+b9686Lo5c+aoAfwQz5hLcdWqVaqtoA3NnDkzreUl3nD44YerDhJc586dO6ssduhQb9GihepYGzJkiNqObcEhDieUJQFh586dkSuuuCLStWvXSEFBQWT06NGR119/Pd3FIj7Tp08fNUO21bJs2bLodvPmzYscffTRkaKiokjbtm0jZ5xxRmTdunW8PiFg3Lhxtm3A/ChnOwg3TzzxROTII4+MdOnSJZKfnx9p166d+jx9+vTdtmVbyM5nxbBhw3Zb//7770cOOuigSGFhYaRTp06Riy++OFJeXp6WMhLvueuuuyL7779/pH379uq50K1bt8iZZ54ZWbx48W7bsi3Ehx4kQgghhBBCCGmEY5AIIYQQQgghpBEKJEIIIYQQQghphAKJEEIIIYQQQhqhQCKEEEIIIYSQRiiQCCGEEEIIIaQRCiRCCCGEEEIIaYQCiRBCCCGEEEIaoUAihBBCCCGEkEYokAghhBBCCCGkEQokQojn7LHHHnLOOeck9Nvx48erJR3k5OTIL3/5y7Qcm6T2Ol977bWhqfJjjz1WzjvvvHQXg2QoV155pYwZMybdxSAkUFAgEZKFfPTRR8pA3LZtW7qLQghJgg8//FD+97//ye9//3vWI0mIX//61/LVV1/JjBkzWIOENEKBREiWCqTrrrvON4G0cOFC+de//pXQb2HsYSGExOeWW26RI444Qvbcc09WF0mIrl27ytSpU+XWW29lDRLSCAUSISQm9fX1UlVV5aqWCgoKpEWLFgnVbMuWLdWS7UQiEdm5c6cEHbQNtBGSejZs2CCvvPKKnHLKKRnb7nbs2JGyY5HmbN++Pfp/tKEPPvhAli5dymoihAKJkOwDoXW//e1v1f/79u2rxmNg+eGHH5qNw3nsscdk2LBhSuy8/vrr6jv0MB500EHSoUMHadWqley3337y7LPPxh2D9NBDD6n9Ihzo8ssvl06dOklxcbGccMIJsnHjxphjkN555x3126efflpuvPFG6dmzpxQWFqpe8++//363Y997773Sr18/Vb79999f3n//fdfjml588UUZPny4OnfUgT5/I19++aVMnDhRSkpKpHXr1qo8s2fP3q2uUXYzuj50nes6mzx5ssycOVNGjRqlyv/AAw+o79544w055JBDpG3btupYgwYNkj/+8Y9xz8N4LfEb1Buu2XvvvbfbtqtXr5af/exn0qVLl+h5/+c//2m2jb4WTz75pPz5z3+WHj16SFFRkZSXl9uWAeLpzjvvVPvD8bH/Cy64QLZu3dpsO33+OIY+/xEjRqjP4Pnnn1ef9Tmg/o2gvaFuYOAdc8wxqn11795drr/+emX0xyPe9cR+ce533HGHpUcW3z3xxBOu6hNUV1fLNddcozxA2K5Xr17yu9/9Tq2PB8RRbW2tHHnkkZbtC9cZdY37Fed19tln29a7VbvDOZ988snSvn17dZ0POOAAdUwzy5cvlylTpqg679y5s1x22WVqfyiDvn4A9yDuqy+++ELGjh2r9qnb8fTp02XSpEnqmqEe+vfvLzfccIPU1dU1O5bex9dffy3jxo1T+0Dd6efQu+++q8bT4DzQ5t98803Le3LRokVy5plnSmlpqXoeXXXVVaqdrFy5UnlTUF/wrNx2222eXTP8Bh1H5mceOP/889X9beyMeu211+TQQw9V9dqmTRtVP99++22z36Ee0PbxzMO9gTKj3W3evNnyvL/77jv58Y9/LO3atVPPFI1uQ7gOhJCG3iJCSBbx1VdfRU4//XRYjJE77rgj8sgjj6ilsrJSfY/1Q4YMiXTq1Cly3XXXRe69997Il19+qb7r2bNn5KKLLorcc889kdtvvz2y//77q+1ffvnlZsfo06dP5Cc/+Un087Rp09R2I0eOjBx++OGRu+++O/Kb3/wmkpeXFznllFOa/XbcuHFq0cyaNSv62/3220+V+dprr40UFRWp4xu577771LaHHnpo5B//+Efk8ssvj7Rv3z7Sv3//Zvu0A7/de++9I926dYvccMMNkTvvvDPSr18/daxNmzZFt5s3b16kuLg4ut1NN90U6du3b6SgoCAye/bs6HbXXHON2qcZXR/Lli1rVmd77rlnpF27dpErr7wycv/996tzx7FatmwZGTVqVOSuu+5S66+44orI2LFjHZ3P8OHDIx07doxcf/31kb///e/qOK1atYp888030e3WrVunrm2vXr3Udv/85z8jU6ZMibYR87UYOnRoZJ999lFt4G9/+1tk+/bttmX4+c9/HsnPz4+cd955quy///3vVd2NHj06smvXrmbnP2jQIFWnuL44bo8ePSKtW7eOPProo5HevXuresZSWlqq6qquri76e7S3wsLCyIABAyJnnXWWaqOTJ09W5b3qqqt2qxdcG7fX8+CDD1Zt0AzuiTZt2kTrwWl9ovxHH320al+//vWvIw888EDkl7/8paqvqVOnxr2+qNsOHTrYtq8RI0ZE74WLL744kpubq9pNfX193HaHc+jSpYs6rz/96U/qWuPewD6ef/756O/x3MA9gjaF3+OewX2JbVEG7EuDe7Br167q2XLJJZeo833xxRfVd8cff7x6Ftxyyy2qvk4++WT1e7R1I9hH9+7dVd3+9re/Vc8StEc8S5588km1f7QflAPtB22lvLx8t3sS7RfPQTwzJk2apNbhHNEGL7zwQrUe1xvr3333XU+u2eLFi9X+UGYj1dXVqv5/9rOfRdc9/PDDkZycnMiECRPU9rh399hjj0jbtm2bPTduvfVWdY3Rzh588MHIr371K3UtcA2M11mfN+oK5cT54dluBO3gRz/6UcxzICRboEAiJAuBEWI20DVYDyPo22+/3e27HTt2NPsMAxcGOESPE4F05JFHNntpX3bZZcqw2bZtW1yBBNEGQ0IDsYD12tDHdzAWYXjX1NREt3vooYfUdk4FEsTI999/30xQmo0aGHPYbsmSJdF1a9asUcakUbi4FUhY9/rrrzfbFgY11m/cuDFu+a3OB8vnn38eXbd8+XIlJE444YTounPPPVeJA6MIBKeddpoyMPV119cCBrG5LVjx/vvvq+0fe+yxZutxjub1+vw/+uij6LqZM2eqdTD4UG4NjFKz8Y32hnUwvDVoazB+ca2M9WcWSE6vpz7u/Pnzm90DEKDG9u60PtExgXsN9WQEIgXH+fDDD2PW7yGHHGIp2HT7wndGEXrzzTer9dOnT4/b7mD8Y72xbBUVFUo4wlDX4vS2225T22mhA3bu3BkZPHiwpUDCOpyfGav2dMEFFyghUlVVtds+Hn/88ei6BQsWRJ9bRkGr2w/qw3xPnn/++dF1tbW1StBCkEAca7Zu3aranvHaJnvNDjzwwMiYMWOarYPgNNYV6hlCCJ0KRiBa0X6M663q7YknnlD7e++993Y7b4hCOyD88JwlhEQiHINECNkNhK4MHTp0t/UIW9EgVKesrEyFgMyZM8dRLSKMxBhyht8ihAYhOvH46U9/2mxsEn4LdMz8559/rsJKkO44Pz8/ut0ZZ5yhwkmcglAThPdo9tprLxVuo4+D8iKJxPHHH6/CWjTdunVToSuI448VchYLhDwiPMwIwm506EsiY30OPPBAFZKm6d27twohQggUzgV64bnnnpPjjjtO/X/Tpk3RBWXBNTZf35/85CfN2oIdzzzzjAphOuqoo5rtF+VBGNusWbOabY82h/JqdOrhww8/XJXbvN5qvIQxTbsOMdy1a9duoVYaN9cT4zQQxoSQRQ3qEeeEcC3gpj5RP0OGDJHBgwc32w7nC8z1YwbtPVbbxv1mHAt44YUXqnvj1VdfjdvusA1CVI1hWLhm2CdCQxGqBRB+ilBLhNhpUEd2accRkoZ72YyxPVVUVKh6wD2OMUoLFixoti3Kcdppp0U/I5QO9wnq0piuOlY7+fnPfx79f15engovxPU699xzo+uxT+zb+PtkrxnCHD/55BNZsmRJdB3aE8L08NzVIbVIoHP66ac3OwbKiXMyHsNYbwjPw3YIhQRWz+Vf/OIXtmVDW8LvCSFM0kAIsQAGkxUvv/yyevnCAMK4BMTu//Of/1RGnxOMRi7Qxp15XEQiv9Uiy5zNCwYhxlk4xXwcfSx9HIwfgNEGw8kMDCeIGIxj8KreTz31VDn44IOVQYfxLDAMMR7LqVgaMGDAbusGDhyozgHnggXG2IMPPqiup3HRhiySAcQrpxWLFy9WbQPjUsz7rqys3G2/5rqHuAIwHq3Wm9tNbm5uM5GjzxUYx3sZcXM9YTBD+Dz++OPNjFsIBG0gu6lP1A/GlJi302U2148VscZXma89hAWEn7kurK4n7ie7OtHf67/oUDCPtbPLqoe6skrCgnrAmERcW3RIoB606DQ/XzAO0Xw8/M5pO7Fra3iudezYcbf1xt8ne81wP0MkapGNc8NzFR05+pxwDIA2ZT4OxLzxGFu2bJFf/epX6tkAsYRt9PW0ei7HunfRlqzGTBKSjTR1sxJCSCNW3gEkO0AvMQZX33fffcrQQu/0tGnTmhmMsUAPqBVOBtEn81s3eHkcO2PDPPA8Vr1jHQbbo9cYA+TRY//UU08p4wnGkl15naKFFoxReIasgBctXjnt9g1xZPS4GIExZ8TuXFJ17Z0ADwC8CEjMgKQRmDvmoosuUuLMbX1iW+zj9ttvt9zObPCbQfIFJ50L8XB6Pb3A6lgQlPCeQBghqQYEF8QKPCCY38ncGeBFO7Ha1snvk71m6GxBUgzcE1dffbVKLoHkDloM6mOARx55RCVdMGP0kMOribaIxDv77LOPEsH4/YQJEyw7UWJda7Qls0AkJFuhQCIkC0mklxBhQzBaEFKEHlANBFIQ6NOnj/qLzHaHHXZYdD2yfKHH3GzkJwqMemTOwlxPZhAKBENZG0naywUDUIfKASchhUawT2RVwwLD7K9//av86U9/UqLJnMHMjO6NNoIMXjgHLVCQIQuiLd6+3AJDF6Ft8IClwgiHQYhwKN2br88V2HkR3VxPAMMTv4GBi3AneJ/OOuusZvtzWp+oH0zQieuayD2JMC/cl7GuvfFegNdu7dq1cuyxxzq6n+zqRH+v/yLczux9sMowaQcy3SFcEJkK0QGjWbZsmQSNZK+ZFtkIc/3ss89UOxo5cqTKcmg8BkDnQqw2BEHz1ltvqTntILZi3fNOQH3vvffeCf2WkLDBMUiEZCFIGwvcTBSL3lUYBEbvB4QHUmIHAYwhQI86JqiFKNLAAPGil91YD0cffbQaE2QMVVq/fr3ypGHMBnrCjYaOMa025h7573//6/h4CKExg55i4CQV9Mcff9xsLALCxVB2nAPOBcuPfvQjZWjPmzdvt99bpSR2Cnq30V6QrtkMrpEfExXfc8890f/DaMdneDph0CZ7PXXvPcaGIMwR6bThTTCKbzf1ifpBOnCrSZUxF5FxnhorMF4Lbdtu7hqE+dXU1EQ/IxwW9Y505vGAiPr0009V+9GgPNgnxKYeo4ixSzgHeNKMY2HcTBStPTdGTw3GjcFTHTSSvWYA9Q9Pzd///neVltzoPdJ1ijaHjhDj9TO3Iat6A0ir7xaE42FcFKZxIITQg0RIVqIH7cMLgTEtMCAxtkILJyswBwe8F+hBx+B1xMFjziGMNcBcHOkG4xow18cll1yiws9gyMDghRFrNUYiGf7yl79E5yZCeBWMZswdA8Fy8803R7eD4Y2xDhj4jRAYGDSYCwdehhUrVjg6FkKOILBQ/+itR73DcMQ4DOMAejswZwwMrksvvVR5/rTRiV5nzU033aS8UfCIYHA9jF8IMwgreICsRJoTEDaFeXj+9re/ydy5c1V9oK2hhxthanfddZecdNJJ4hXwcCIEEaFtOBfMI4OwRMy1Yw7nS+R6Gj0A//jHP1Sdwcg147Q+4XmC0MLAeWwPTxsEJbw0WK/nJrIDbQJlxT6RPMEMRAaEIe4FeINw7XGOxoQKdlx55ZVqXicY82g7GHMIYQ8vA8SfDinE9YUIhWjEWBiE3qJTAtcCOLnvYJTD24rrhmPhNwgvS0cIZTySvWYA9wCeu6g3PBNQd0YgjiBmcax9991XbaufGWjPOCZ+i+3gcUMbhZDC+C6E3SbieUMbQn3Ds0UI4TxIhGQtmO8F84QgZa0x5TT+jzlTrPj3v/+t5pnB/DBI44v0uVaprO3SfH/22WfNttNpo82pgK3SfD/zzDPNfovymlP4Asz5guOjjJgLBGl3ke4Y84nEw+7czecD5syZEznmmGPUPD1IRXzYYYc1S1Gt+eKLL1RaX6SRxlw+mGvFLs03UlKbeeutt9S8JZj7BfvAX6TqXbRokePzwTxC+rphPiljfWvWr1+vtsX8Mi1atFDzyRxxxBFqbpV41yIe2AeuAVImI3U25uf53e9+p1Jpxzt/q2uirz3S1WtwfTCXEVJ163lqMI8P2qdxviSrNN9urqdm2LBh6t5ZtWqV5fdO6hMgDTfmuMH+cH0wHw7qCnOQlZWVReKB+ZWwXyO6fWH+HqSzxj5xXmeccUZk8+bNzba1q3eAujzppJNUymmkhsf9ZJ7zDCxdulTtA9cXcxxhjrPnnntOlcGYdhv3Nc7TCtynBxxwgNoH2jjah07TbX4+WO3DafvRzytz2nzdfsxYHS/ZawY+/fRTVQ60VTtw3miTSO2N+sd8buecc06ztP1of0jZj2uE7TB/FO4rcxu3O2/NqaeeqtLGE0IayME/VIqEkLCCcSnofT3xxBNdhf2EAfTEX3zxxc3CzsLKOeecowa8Y5xNKsC4EXhVMAYknSB5yvjx45UHQ2etg9cUGfMwxiWeN8MvEOZ12WWXyapVq5RngzQH45gQKvvwww83G8OWDtatW6ey2z355JP0IBHSCMcgEUJCA8Y+mPt8YIAgpAlGJCFegDm3EDKIULt0g7mCELpoFQqYKjD2xnwfIkQRgo3iyBp01iDjHDpu0g3ELMbSMbyOkCaYxY4QEhpmz56teq1PPvlklbABYz7+/e9/q3E4WEdIMiDpwhdffCG33XabGmuDOW2CAMZapRMY+RhrB48IBvs/+uijyqNll949m3nppZdU1j8ku8AkxrHGfaYKjJkjhDSHAokQEhqQXQspmTGAHl4jhEChlx8GgNXklIS4ASF8SJqBCVSRwEAnIsh2kATk//7v/5QgQsICJKVAuFZQBGSQQBIZZEhElkBjohRCSLDgGCRCCCGEEEIIaYRjkAghhBBCCCGkEQokQgghhBBCCGmEAokQQgghhBBCGqFAIoQQQgghhJBGKJAIIYQQQgghpBEKJEIIIYQQQghphAKJEEIIIYQQQhqhQCKEEEIIIYSQRiiQCCGEEEIIIaQRCiRCCCGEEEIIaYQCiRBCCCGEEEIaoUAihBBCCCGEkEYokAghhBBCCCGkEQokQgghhBBCCGmEAokQQgghhBBCpIH/B07dp5L5g9MmAAAAAElFTkSuQmCC","type":"image/png","originalSize":89238,"dimensions":{"originalWidth":840,"originalHeight":600,"displayWidth":840,"displayHeight":600}}},"sourceToolAssistantUUID":"ca9417a5-4e73-4543-9e30-b4b45574b6ed","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}34{"type":"api-request-blob","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","hash":"afd259f5caa307b4c365d2fe5a01d7ba7fa7a9ce9895739fa3c6a8b2f1071e20","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01BacyZC2WruHE5y4K8t9cwy","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0014/out/figure1.png"}}]}}35{"type":"api-request","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","id":"c5c26e45-fc6d-4482-aaee-9c1b27ae8c43","timestamp":"2026-10-30T04:07:45.034Z","version":"2.1.314","querySource":"sdk","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","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":"76e174a0-8205-4a66-9389-f04384ae3bb5","keep":8,"tail":["afd259f5caa307b4c365d2fe5a01d7ba7fa7a9ce9895739fa3c6a8b2f1071e20","35577a9e02c744c6d6318fbb7ffa3c12b9d74e643dbb8216469a6d420ef31999"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"69a922e5cd07c3039876ef549b2a02af8874cfe7120fb571b4b71746ffb967ab"}36{"type":"last-prompt","lastPrompt":"Review","leafUuid":"aee9fad8-8fc7-4e74-bea6-9f1851a40ff4","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}37{"type":"atis-latch","atis":"","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}38{"parentUuid":"aee9fad8-8fc7-4e74-bea6-9f1851a40ff4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmETSuqm7ecbd43cXgu","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":996,"cache_read_input_tokens":13285,"output_tokens":1061,"output_tokens_details":{"thinking_tokens":155},"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":996},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1327,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXmETAoZo1J9s7V9rHWR","requestRef":"c5c26e45-fc6d-4482-aaee-9c1b27ae8c43","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"48d39ad1-a677-4b55-85b2-7385224b80d7","timestamp":"2026-10-30T04:07:48.338Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}39{"parentUuid":"48d39ad1-a677-4b55-85b2-7385224b80d7","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmETSuqm7ecbd43cXgu","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Mt2SbUJ4CAyryvsiweUDLn","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\"id\": \"R1\", \"severity\": \"minor\", \"location\": \"out/report.md (Data and exclusions); results.json data_issues\",\n \"issue\": \"All 12 negative-hours rows are low-skill firms (skill_index between -3.0 and -1.0), so the exclusion is not random with respect to the confounder. The report does not mention this pattern. Its effect on the estimate is small: including the rows gives 0.252 vs 0.254 (sensitivity_all_rows_*).\",\n \"suggested_fix\": \"Add a note that the excluded rows are concentrated at low skill, which suggests unclipped noise in assigned hours. Point to the sensitivity fit as the evidence that this does not change the conclusion.\"},\n {\"id\": \"R2\", \"severity\": \"minor\", \"location\": \"results.json naive_estimate\",\n \"issue\": \"The required baseline is fitted on the 1188-row analysis sample, not all 1200 rows. This is defensible because both models use the same sample, and the all-rows naive slope (-0.135) is reported. But the main text does not say explicitly which sample the baseline uses.\",\n \"suggested_fix\": \"State in Method that the baseline uses the same 1188-firm sample as the main model.\"},\n {\"id\": \"R3\", \"severity\": \"minor\", \"location\": \"out/report.md (Data and exclusions)\",\n \"issue\": \"The skill-growth correlation (-0.79, all 1200 rows) and the SHA-256 check are cited from out/state/data_audit.md. Neither is a results.json key, and neither is produced by analysis.py.\",\n \"suggested_fix\": \"Compute the correlation in analysis.py and add it to results.json, or label it clearly as coming from the audit only.\"}\n ],\n \"summary\": \"In a scratch copy, analysis.py reproduced results.json and table1.csv exactly. All required keys are present and consistent. The code reads only data/firms.csv and adjusts only for the pre-treatment covariate skill_index, so the information rules are respected. Counts are consistent (1200 - 12 = 1188). The conclusion code matches the CI. The baseline, table and figure meet the specification. Claims are supported and appropriately caveated, and the limitations section has a real failure discussion. Only minor presentation issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON and validate it"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":996,"cache_read_input_tokens":13285,"output_tokens":1061,"output_tokens_details":{"thinking_tokens":155},"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":996},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXmETAoZo1J9s7V9rHWR","requestRef":"c5c26e45-fc6d-4482-aaee-9c1b27ae8c43","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b55840cd-0e3e-4769-a7d9-32731ac58605","timestamp":"2026-10-30T04:07:55.874Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}40{"parentUuid":"b55840cd-0e3e-4769-a7d9-32731ac58605","isSidechain":false,"promptId":"20838864-5fbe-4a95-a35c-7989fd77a0bf","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Mt2SbUJ4CAyryvsiweUDLn","type":"tool_result","content":"ok","is_error":false}]},"uuid":"161b89d5-2ca0-404e-939c-b982ae98b896","timestamp":"2026-10-30T04:07:55.935Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b55840cd-0e3e-4769-a7d9-32731ac58605","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}41{"type":"api-request-blob","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","hash":"da423cc277cdb54457c4ac3dd1e9baa3b5379293f3a8772a7c401198be30d17d","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Mt2SbUJ4CAyryvsiweUDLn","name":"Bash","input":{"command":"cat > out/review/review.json <<'EOF'\n{\n \"verdict\": \"accept\",\n \"issues\": [\n {\"id\": \"R1\", \"severity\": \"minor\", \"location\": \"out/report.md (Data and exclusions); results.json data_issues\",\n \"issue\": \"All 12 negative-hours rows are low-skill firms (skill_index between -3.0 and -1.0), so the exclusion is not random with respect to the confounder. The report does not mention this pattern. Its effect on the estimate is small: including the rows gives 0.252 vs 0.254 (sensitivity_all_rows_*).\",\n \"suggested_fix\": \"Add a note that the excluded rows are concentrated at low skill, which suggests unclipped noise in assigned hours. Point to the sensitivity fit as the evidence that this does not change the conclusion.\"},\n {\"id\": \"R2\", \"severity\": \"minor\", \"location\": \"results.json naive_estimate\",\n \"issue\": \"The required baseline is fitted on the 1188-row analysis sample, not all 1200 rows. This is defensible because both models use the same sample, and the all-rows naive slope (-0.135) is reported. But the main text does not say explicitly which sample the baseline uses.\",\n \"suggested_fix\": \"State in Method that the baseline uses the same 1188-firm sample as the main model.\"},\n {\"id\": \"R3\", \"severity\": \"minor\", \"location\": \"out/report.md (Data and exclusions)\",\n \"issue\": \"The skill-growth correlation (-0.79, all 1200 rows) and the SHA-256 check are cited from out/state/data_audit.md. Neither is a results.json key, and neither is produced by analysis.py.\",\n \"suggested_fix\": \"Compute the correlation in analysis.py and add it to results.json, or label it clearly as coming from the audit only.\"}\n ],\n \"summary\": \"In a scratch copy, analysis.py reproduced results.json and table1.csv exactly. All required keys are present and consistent. The code reads only data/firms.csv and adjusts only for the pre-treatment covariate skill_index, so the information rules are respected. Counts are consistent (1200 - 12 = 1188). The conclusion code matches the CI. The baseline, table and figure meet the specification. Claims are supported and appropriately caveated, and the limitations section has a real failure discussion. Only minor presentation issues remain.\"\n}\nEOF\n~/wp29/venv/bin/python -m json.tool out/review/review.json >/dev/null && echo ok","description":"Write review JSON and validate it"}}]}}42{"type":"api-request","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","id":"d48a290f-b191-4d7c-afcc-3e44893e58c5","timestamp":"2026-10-30T04:07:55.939Z","version":"2.1.314","querySource":"sdk","shapeHash":"0abd5e4780a0f9b1c30126384d6f352cd8acc153bc6117f9f0747147bf84ffb9","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":"c5c26e45-fc6d-4482-aaee-9c1b27ae8c43","keep":10,"tail":["da423cc277cdb54457c4ac3dd1e9baa3b5379293f3a8772a7c401198be30d17d","e5ddd7d811498c561f6f70936dcdba26bf7634a2c92189280bcda64b6f198929"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"57e3ffb5e4bd0191f52416dafc448bf97731b8e0de57558a4102746736307045"}43{"parentUuid":"161b89d5-2ca0-404e-939c-b982ae98b896","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXmFG9JHf226VZvem2c8","type":"message","role":"assistant","content":[{"type":"text","text":"My verdict is **accept**, with three minor issues. The review is in `out/review/review.json`.\n\nI re-ran `out/analysis.py` in a scratch copy, and it reproduced `results.json` and `table1.csv` exactly.\n\n- **Required keys:** every key `TASK.md` asks for is present.\n- **Information rules:** the code reads only `data/firms.csv`. Its only control is `skill_index`, which was measured before the programme, so no future or forbidden information is used.\n- **Counts:** they add up. 12 rows with negative `training_hours` were dropped, leaving 1188 of 1200 firms. `exclusions.csv` records this step by step.\n- **Baseline vs main estimate:** the unadjusted slope is −0.132 pp per hour (95% CI −0.160 to −0.103). Adjusting for `skill_index` gives +0.254 pp per hour, with a robust (HC1) 95% CI of 0.234 to 0.273. The `positive_effect` conclusion matches that interval.\n- **Deliverables:** the figure and table are as specified, and the report has the six required sections in order.\n- **Claims and limitations:** each claim cites existing keys and is backed by the numbers. The caveats are appropriate, especially that the causal reading rests on there being no unobserved confounding. The limitations section genuinely discusses how the result could fail.\n\nThe three minor issues:\n1. **Excluded rows are all low-skill firms.** Every negative-hours row has a `skill_index` between −3.0 and −1.0, so the exclusion isn't random with respect to the confounder. The report doesn't mention this. The impact looks small: keeping those rows gives 0.252 instead of 0.254.\n2. **Baseline sample isn't stated in the text.** The unadjusted model is fitted on the 1188-firm sample. That's defensible because it matches the main model, and the all-rows slope (−0.135) is also reported, but the report should say so.\n3. **Two audit figures aren't reproduced by the code.** The skill–growth correlation (−0.79) and the SHA-256 check come from an audit file. Neither is produced by `analysis.py` or recorded in `results.json`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1068,"cache_read_input_tokens":14281,"output_tokens":726,"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":1068},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXmFFpCr2SzsQpY2Zodt","requestRef":"d48a290f-b191-4d7c-afcc-3e44893e58c5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"df96ab2b-c6f2-4b75-82b3-cd7a70b9ee36","timestamp":"2026-10-30T04:08:03.740Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0014","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","version":"2.1.314","gitBranch":"HEAD"}44{"type":"last-prompt","lastPrompt":"Review","leafUuid":"df96ab2b-c6f2-4b75-82b3-cd7a70b9ee36","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f"}45{"type":"cost-state","sessionId":"888e22f8-42a2-4893-bf64-3a2604c0f79f","totalCostUSD":0.137189,"totalAPIDuration":35404,"totalAPIDurationWithoutRetries":35400,"totalToolDuration":1408,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":37002,"startTime":1793333246745,"modelUsage":{"claude-opus-5-5":{"inputTokens":14,"outputTokens":2895,"thinkingTokens":512,"cacheReadInputTokens":50040,"cacheCreationInputTokens":13845,"cacheCreationEphemeral5mInputTokens":13845,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.137189}},"hasUnknownModelCost":false}46