{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T04:49:20.341Z","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","content":"Begin"}
{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T04:49:20.345Z","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":null,"isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":"Begin"},"uuid":"ec1a2701-76a4-4040-b936-64f29963cf4d","timestamp":"2026-10-30T04:49:20.348Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-shape","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","timestamp":"2026-10-30T04:49:20.357Z","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/RC0172\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"6e90ed53-bdea-45e3-990d-35b0017b15f6","timestamp":"2026-10-30T04:49:20.357Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","params":{"model":"claude-opus-5-5","betas":["claude-code-20250219","interleaved-thinking-2025-05-14","context-management-2025-06-27","prompt-caching-scope-2026-01-05","per-turn-control-2026-07-01","thinking-token-count-2026-05-13","mid-conversation-system-clear-at-2026-08-21","effort-2025-11-24","thinking-binding-controls-2026-08-01","thinking-display-updates-2026-08-18","cache-diagnosis-2026-04-07"],"max_tokens":128000,"thinking":{"type":"adaptive","display":"updates"},"context_management":{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]},"output_config":{"effort":"medium"}},"keep":0,"tail":["252097215a6af3e04abe3f3c5a1cce73f5f388825c554cef2907d381aaf4102e","d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",0,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b1a39da19495d1700bda785f1538721866d02ec56ce3230f46a33cd38901e871"}
{"parentUuid":"ec1a2701-76a4-4040-b936-64f29963cf4d","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"0bfe2f1b-2cc7-4407-a59a-aff8f75ea6a8","timestamp":"2026-10-30T04:49:20.352Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"0bfe2f1b-2cc7-4407-a59a-aff8f75ea6a8","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"ec806362-35b4-45ac-9372-b0733e0526fe","timestamp":"2026-10-30T04:49:20.352Z","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/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"ec806362-35b4-45ac-9372-b0733e0526fe","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":"58917877-fcd2-4bb6-b32b-f8f279313072","timestamp":"2026-10-30T04:49:20.352Z","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/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"tools-used","tools":["Bash"],"sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"58917877-fcd2-4bb6-b32b-f8f279313072","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQRtXbjGzZgU1HvEND","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":126,"output_tokens_details":{"thinking_tokens":20},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":293,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpQRcAbRoFzxk7CxNsJ","requestRef":"6e90ed53-bdea-45e3-990d-35b0017b15f6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"74be5171-4477-449e-bfad-4395d30b1e11","timestamp":"2026-10-30T04:49:22.329Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"74be5171-4477-449e-bfad-4395d30b1e11","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQRtXbjGzZgU1HvEND","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01YbGgxdcCbXPkSyLeRNvBnX","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":126,"output_tokens_details":{"thinking_tokens":20},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpQRcAbRoFzxk7CxNsJ","requestRef":"6e90ed53-bdea-45e3-990d-35b0017b15f6","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b45f1e83-7ccd-41ec-8827-88db9c0f9129","timestamp":"2026-10-30T04:49:22.924Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"b45f1e83-7ccd-41ec-8827-88db9c0f9129","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01YbGgxdcCbXPkSyLeRNvBnX","type":"tool_result","content":"# F6-conf-03 — Okun's law in the United States, 1960–2019: coefficient, uncertainty and stability\n\n## Scientific question\nHow strongly do quarterly changes in the US unemployment rate respond to real output growth, and has that response been stable? The estimand is the Okun coefficient β in the difference form Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, where Δu_t is the change in the quarterly-average civilian unemployment rate (percentage points) and g_t = 100·(ln GDPC1_t − ln GDPC1_{t−1}) is quarterly real GDP growth in percent (not annualised); uncertainty must be robust to heteroskedasticity and serial correlation. Stability is assessed by estimating β separately on 1960Q1–1983Q4 and 1984Q1–2019Q4 and by a classical Chow test of the joint equality of (α, β) across the two subperiods. 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/GDPC1.csv` — observed data, FRED GDPC1 (US real GDP, quarterly, billions of chained 2017 dollars, SAAR; BEA), full history, raw FRED CSV (`observation_date` = first day of the quarter, `GDPC1`). Provenance in `data/README.md`.\n- `data/UNRATE.csv` — observed data, FRED UNRATE (US civilian unemployment rate, monthly, percent, SA; BLS), full history, raw FRED CSV (`observation_date` = first day of the month, `UNRATE`). Provenance in `data/README.md`.\n- `data/README.md` — provenance, retrieval dates, SHA-256.\n\n## Information-availability rules\n- Quarterly unemployment u_t is the simple average of the three monthly UNRATE values of quarter t. Δu_t = u_t − u_{t−1}.\n- The regression sample is the 240 quarters 1960Q1–2019Q4 (the 1960Q1 differences use 1959Q4 levels). Quarters after 2019Q4 are outside the question and must not enter any estimate. Subperiod 1 = 1960Q1–1983Q4, subperiod 2 = 1984Q1–2019Q4.\n- Standard errors for the full-sample β must be HAC (Newey–West with Bartlett kernel); choose and report the lag length. The Chow test is the classical sum-of-squared-residuals F-test with 2 and n − 4 degrees of freedom.\n- Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `sample_start`, `sample_end` | string | ISO date | first day of the first and last quarter in the regression sample (`1960-01-01`, `2019-10-01`) |\n| `n_sub1`, `n_sub2` | integer | quarters | observations in each subperiod |\n| `baseline_metric` | number | percentage points | RMSE of the mean-only prediction of Δu over the full sample, sqrt(mean((Δu − mean Δu)²)) |\n| `model_metric` | number | percentage points | RMSE of the full-sample OLS residuals, sqrt(mean(e²)) |\n| `effect_estimate` | number | pp per percent growth | full-sample OLS Okun coefficient β |\n| `intercept` | number | percentage points | full-sample OLS intercept α |\n| `effect_se` | number | pp per percent growth | HAC (Newey–West) standard error of β |\n| `hac_lags` | integer | quarters | Newey–West lag length used |\n| `effect_ci_low`, `effect_ci_high` | number | pp per percent growth | 95% confidence interval for β based on `effect_se` |\n| `beta_sub1`, `beta_sub2` | number | pp per percent growth | OLS slope in subperiod 1 and 2 |\n| `chow_f_stat`, `chow_p_value` | number | — | Chow F statistic and p-value |\n| `stability_conclusion` | string | — | `stable` if the Chow test does not reject at 5%, else `unstable` |\n| `conclusion` | string | — | one of the codes below (sign of β from its 95% interval) |\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\n(`n_analysed` = quarters in the full-sample regression.)\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 Δu_t against g_t with the two subperiod fitted lines, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per sample (full, subperiod 1, subperiod 2) with columns `period`, `n`, `intercept`, `slope`, `slope_se` (header + three data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x    6 simon-pierreboucher  staff   192 oct.  29 23:42 .\ndrwxr-xr-x  102 simon-pierreboucher  staff  3264 oct.  30 00:49 ..\n-rw-r--r--    1 simon-pierreboucher  staff   600 oct.  29 23:42 bundle.json\ndrwxr-xr-x    5 simon-pierreboucher  staff   160 oct.  29 23:27 data\n-rw-r--r--    1 simon-pierreboucher  staff  2823 oct.  29 23:35 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6312 oct.  29 23:35 TASK.md\ndata:\nGDPC1.csv\nREADME.md\nUNRATE.csv","is_error":false}]},"uuid":"f9948d12-ad30-4917-ad70-433555e237ee","timestamp":"2026-10-30T04:49:22.969Z","toolUseResult":{"stdout":"# F6-conf-03 — Okun's law in the United States, 1960–2019: coefficient, uncertainty and stability\n\n## Scientific question\nHow strongly do quarterly changes in the US unemployment rate respond to real output growth, and has that response been stable? The estimand is the Okun coefficient β in the difference form Δu_t = α + β·g_t + ε_t over 1960Q1–2019Q4, where Δu_t is the change in the quarterly-average civilian unemployment rate (percentage points) and g_t = 100·(ln GDPC1_t − ln GDPC1_{t−1}) is quarterly real GDP growth in percent (not annualised); uncertainty must be robust to heteroskedasticity and serial correlation. Stability is assessed by estimating β separately on 1960Q1–1983Q4 and 1984Q1–2019Q4 and by a classical Chow test of the joint equality of (α, β) across the two subperiods. 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/GDPC1.csv` — observed data, FRED GDPC1 (US real GDP, quarterly, billions of chained 2017 dollars, SAAR; BEA), full history, raw FRED CSV (`observation_date` = first day of the quarter, `GDPC1`). Provenance in `data/README.md`.\n- `data/UNRATE.csv` — observed data, FRED UNRATE (US civilian unemployment rate, monthly, percent, SA; BLS), full history, raw FRED CSV (`observation_date` = first day of the month, `UNRATE`). Provenance in `data/README.md`.\n- `data/README.md` — provenance, retrieval dates, SHA-256.\n\n## Information-availability rules\n- Quarterly unemployment u_t is the simple average of the three monthly UNRATE values of quarter t. Δu_t = u_t − u_{t−1}.\n- The regression sample is the 240 quarters 1960Q1–2019Q4 (the 1960Q1 differences use 1959Q4 levels). Quarters after 2019Q4 are outside the question and must not enter any estimate. Subperiod 1 = 1960Q1–1983Q4, subperiod 2 = 1984Q1–2019Q4.\n- Standard errors for the full-sample β must be HAC (Newey–West with Bartlett kernel); choose and report the lag length. The Chow test is the classical sum-of-squared-residuals F-test with 2 and n − 4 degrees of freedom.\n- Use only the files listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `sample_start`, `sample_end` | string | ISO date | first day of the first and last quarter in the regression sample (`1960-01-01`, `2019-10-01`) |\n| `n_sub1`, `n_sub2` | integer | quarters | observations in each subperiod |\n| `baseline_metric` | number | percentage points | RMSE of the mean-only prediction of Δu over the full sample, sqrt(mean((Δu − mean Δu)²)) |\n| `model_metric` | number | percentage points | RMSE of the full-sample OLS residuals, sqrt(mean(e²)) |\n| `effect_estimate` | number | pp per percent growth | full-sample OLS Okun coefficient β |\n| `intercept` | number | percentage points | full-sample OLS intercept α |\n| `effect_se` | number | pp per percent growth | HAC (Newey–West) standard error of β |\n| `hac_lags` | integer | quarters | Newey–West lag length used |\n| `effect_ci_low`, `effect_ci_high` | number | pp per percent growth | 95% confidence interval for β based on `effect_se` |\n| `beta_sub1`, `beta_sub2` | number | pp per percent growth | OLS slope in subperiod 1 and 2 |\n| `chow_f_stat`, `chow_p_value` | number | — | Chow F statistic and p-value |\n| `stability_conclusion` | string | — | `stable` if the Chow test does not reject at 5%, else `unstable` |\n| `conclusion` | string | — | one of the codes below (sign of β from its 95% interval) |\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\n(`n_analysed` = quarters in the full-sample regression.)\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 Δu_t against g_t with the two subperiod fitted lines, produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per sample (full, subperiod 1, subperiod 2) with columns `period`, `n`, `intercept`, `slope`, `slope_se` (header + three data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ntotal 32\ndrwxr-xr-x    6 simon-pierreboucher  staff   192 oct.  29 23:42 .\ndrwxr-xr-x  102 simon-pierreboucher  staff  3264 oct.  30 00:49 ..\n-rw-r--r--    1 simon-pierreboucher  staff   600 oct.  29 23:42 bundle.json\ndrwxr-xr-x    5 simon-pierreboucher  staff   160 oct.  29 23:27 data\n-rw-r--r--    1 simon-pierreboucher  staff  2823 oct.  29 23:35 gate_spec.json\n-rw-r--r--    1 simon-pierreboucher  staff  6312 oct.  29 23:35 TASK.md\ndata:\nGDPC1.csv\nREADME.md\nUNRATE.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b45f1e83-7ccd-41ec-8827-88db9c0f9129","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"3891cc56358c73097a4c9de16c2283975c31241a95814a95ea85ec727c3eb4dd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSmgUKEAgTGAI4AUIIdGhpbmtpbmcSDOzKtbN0GjSgX9ms1RoMRJlPSRXp8ABF1bR/IjBchXdcj5l96CS0TE3hsNxYhGje5LuTl5vMhxWhpVsUyAVshW5oq/xunBGPi1dgUSwqtwS6FpFf3o2R6rj8I1Iy2hTxRqBRJtSbPhAAjP0seeF8wAkk/JmFqlqpamKVqLh23xlBLPkp02rBxqEczKhTwbWuLZ7ceTcNugNhhy/Yeb+FTEAgS7WQKYZVlg/O9Vrxn0e6FeJ5lMkeVBNMKu5HLwTNJH8HRbNh2nyf5p7CzGZRy6/GOthVNtqcIdqgsUvJp+DQerXQWT6xPJblKxL20iWTRiEM++uG9XK9KejSL9jVtE+p69JqO0OTs73pxR2KJl5TpLZY0Fv0hqNTYEtrkkiE0/OZguQ3rYN9Wv0B7UsyheivBsw5jH7KBElMD+q1Iea2ZiAt7F6ssaA0x4IM8DwCkeazbyyXcsE6f2VXdkdQpiWKCDMga+KoeLEhn6n7iOKO8FJOhhInpS6/d/iYULIvjP9Km2sjbTB2MLEkv9Fc0a4GdbDmZQCAsZLfFoX6Rvj4ufL6hB3uwMOj6VkTST9mEWdYMm/bszN+EpC8/7j9NdBwl8cernlprGlpnbl9Nw5umUhzkzAOn7WX9rGaxaH+MWwLUr4Zzy3kODmD6KeLPB02eY4JdjJPzTAyTFUqyxT4IgmSS/6Y8Qoj4/HDOKdiuoX6bqsDCsKZuL/oUs0/YcQwn/HZODlt1iHrk5MGkoQqgAVjuKxppIP2EA8eDeu6cmOJKCO6dA38dAACHSRu5tJDndKObnef8IpOLD0YGhkTkntLn1GQnhYISOM8PTL8matj60c0Fb74e2XFjR//gtcPWDvOtJIYAQ=="},{"type":"tool_use","id":"toolu_01YbGgxdcCbXPkSyLeRNvBnX","name":"Bash","input":{"command":"cat TASK.md; ls -la; ls -R data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"93b76faf-3ee5-47db-b6d5-664216ae53b5","timestamp":"2026-10-30T04:49:22.973Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"6e90ed53-bdea-45e3-990d-35b0017b15f6","keep":2,"tail":["3891cc56358c73097a4c9de16c2283975c31241a95814a95ea85ec727c3eb4dd","d1b9df16e43425aef7861fb31973146084e8008beb4d038ca13962b87b5651d6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0395b8ce32c125ee19df06c965a932d5547a25390e07082ce5a683d16a41d266"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f9948d12-ad30-4917-ad70-433555e237ee","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"f9948d12-ad30-4917-ad70-433555e237ee","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQb4wMZRdjLsF6nbhW","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019NcUt61HCKmiUHLmdH7se6","name":"Bash","input":{"command":"cat data/README.md; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*; grep -n -v '^[0-9-]*,[0-9.]*$' data/*.csv | head","description":"Inspect data files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2862,"cache_read_input_tokens":3713,"output_tokens":159,"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":2862},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpQaooTYU1yGg9iAzs1","requestRef":"93b76faf-3ee5-47db-b6d5-664216ae53b5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a02e96d9-1d1c-4919-8e2a-fbfc25e1bcdd","timestamp":"2026-10-30T04:49:25.126Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"a02e96d9-1d1c-4919-8e2a-fbfc25e1bcdd","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019NcUt61HCKmiUHLmdH7se6","type":"tool_result","content":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n     320 data/GDPC1.csv\n     946 data/UNRATE.csv\n    1266 total\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343  data/GDPC1.csv\n7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658  data/README.md\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c  data/UNRATE.csv\ndata/GDPC1.csv:1:observation_date,GDPC1\ndata/UNRATE.csv:1:observation_date,UNRATE","is_error":false}]},"uuid":"6ab4cc25-33cc-41fe-9223-e250db49ad6a","timestamp":"2026-10-30T04:49:25.202Z","toolUseResult":{"stdout":"# Data provenance — F6-conf-03\n\nBoth files are raw FRED CSV downloads (`observation_date`, value), retrieved 2026-10-30T03:23:28Z, unaltered. Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying series are produced by US government agencies and are in the public domain.\n\n## `GDPC1.csv` (319 rows)\n*Real Gross Domestic Product* (FRED `GDPC1`), quarterly, billions of chained 2017 dollars, seasonally adjusted annual rate. Source: U.S. Bureau of Economic Analysis. Observation dates are the first day of each quarter (e.g. `1947-01-01` = 1947Q1). Period 1947-01-01 to 2026-07-01 (current vintage as of retrieval).\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=GDPC1`\n- SHA-256: `1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343`\n\n## `UNRATE.csv` (945 rows)\n*Unemployment Rate* (FRED `UNRATE`), monthly, percent, seasonally adjusted, civilian labour force 16+. Source: U.S. Bureau of Labor Statistics. Observation dates are the first day of each month. Period 1948-01-01 to 2026-09-01.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UNRATE`\n- SHA-256: `621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c`\n==> data/GDPC1.csv <==\nobservation_date,GDPC1\n1947-01-01,2182.681\n1947-04-01,2176.892\n\n==> data/UNRATE.csv <==\nobservation_date,UNRATE\n1948-01-01,3.4\n1948-02-01,3.8\n==> data/GDPC1.csv <==\n2026-01-01,24274.383\n2026-04-01,24408.011\n2026-07-01,24611.077\n\n==> data/UNRATE.csv <==\n2026-07-01,4.1\n2026-08-01,4.1\n2026-09-01,4.2\n     320 data/GDPC1.csv\n     946 data/UNRATE.csv\n    1266 total\n1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343  data/GDPC1.csv\n7e61e05785988f6cf32be948415ecb9511994533c3a1ef76958fd13ffc4a8658  data/README.md\n621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c  data/UNRATE.csv\ndata/GDPC1.csv:1:observation_date,GDPC1\ndata/UNRATE.csv:1:observation_date,UNRATE","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a02e96d9-1d1c-4919-8e2a-fbfc25e1bcdd","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"16f09865343a8733646387df5c9e1045c09888b72972f514bc8813418c0a0bd0","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_019NcUt61HCKmiUHLmdH7se6","name":"Bash","input":{"command":"cat data/README.md; head -3 data/*.csv; tail -3 data/*.csv; wc -l data/*.csv; shasum -a 256 data/*; grep -n -v '^[0-9-]*,[0-9.]*$' data/*.csv | head","description":"Inspect data files"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"0d9316f4-d87e-4a33-b55d-e4984fd0e1c3","timestamp":"2026-10-30T04:49:25.205Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"93b76faf-3ee5-47db-b6d5-664216ae53b5","keep":4,"tail":["16f09865343a8733646387df5c9e1045c09888b72972f514bc8813418c0a0bd0","5e7dc1eb7f1224455f1be98b78b2bdeb8e5d14da20d92cdbde9b6b5f2c771da1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8410fdbdeda5ffb78c5c0afaa14d75584b522ed306a5f3ecaaf320ce96d4b65b"}
{"parentUuid":"6ab4cc25-33cc-41fe-9223-e250db49ad6a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQkcv7DNRycc7YxTgY","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":1183,"cache_read_input_tokens":6575,"output_tokens":457,"output_tokens_details":{"thinking_tokens":143},"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":1183},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1092,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpQkLneq88UWtsinpes","requestRef":"0d9316f4-d87e-4a33-b55d-e4984fd0e1c3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8d608dcb-096e-474c-a43f-99e40406e0f2","timestamp":"2026-10-30T04:49:27.731Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"8d608dcb-096e-474c-a43f-99e40406e0f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpQkcv7DNRycc7YxTgY","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019djfakvs4TDtarRwurNBvB","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f,fr in [('GDPC1','QS'),('UNRATE','MS')]:\n    d=pd.read_csv(f'data/{f}.csv',parse_dates=['observation_date'])\n    print(f,d.shape,d.isna().sum().to_dict(),d.observation_date.duplicated().sum(),d[f].min(),d[f].max())\n    full=pd.date_range(d.observation_date.min(),d.observation_date.max(),freq=fr)\n    print('missing dates',sorted(set(full)-set(d.observation_date)))\n\"; cat gate_spec.json bundle.json | head -5","description":"Audit gaps, NaNs, duplicates"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1183,"cache_read_input_tokens":6575,"output_tokens":457,"output_tokens_details":{"thinking_tokens":143},"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":1183},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpQkLneq88UWtsinpes","requestRef":"0d9316f4-d87e-4a33-b55d-e4984fd0e1c3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"56ce1df2-e8d9-477d-a0f1-87d13ec67365","timestamp":"2026-10-30T04:49:29.743Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"56ce1df2-e8d9-477d-a0f1-87d13ec67365","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019djfakvs4TDtarRwurNBvB","type":"tool_result","content":"GDPC1 (319, 2) {'observation_date': 0, 'GDPC1': 0} 0 2172.432 24611.077\nmissing dates []\nUNRATE (945, 2) {'observation_date': 0, 'UNRATE': 1} 0 2.5 14.8\nmissing dates []\n{\n  \"task_id\": \"F6-conf-03\",\n  \"required_files\": [\n    \"out/results.json\",\n    \"out/report.md\",","is_error":false}]},"uuid":"15ec6a6d-c80e-4942-9160-a66c6c7ba8e1","timestamp":"2026-10-30T04:49:29.947Z","toolUseResult":{"stdout":"GDPC1 (319, 2) {'observation_date': 0, 'GDPC1': 0} 0 2172.432 24611.077\nmissing dates []\nUNRATE (945, 2) {'observation_date': 0, 'UNRATE': 1} 0 2.5 14.8\nmissing dates []\n{\n  \"task_id\": \"F6-conf-03\",\n  \"required_files\": [\n    \"out/results.json\",\n    \"out/report.md\",","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"56ce1df2-e8d9-477d-a0f1-87d13ec67365","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"98a140cdd0351516407d62e020d460a295adfe01d79a4c3b5d483d951ae63396","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSswgKEAgTGAI4AUIIdGhpbmtpbmcSDGL54bzlOjpA+F6yChoM23w553qS1DjNb1GWIjBGUNQBC1uxd/o33AsB8/k35MMi3GdkGEjCSr8H60pHcgZdq5gr6GsrISW958O4dcoq0AcqxaSyoXSP/hEaSYoRDFb5Gb7+SK2O1jRYRiZvVuqrpqVYVjKEcjbk6uX6ORiX75IzJKK8+b6T6FRj/oZLyY3qURSpwdZ2wG9QvgBd5iDyb9SKw0ZtN8HPJLL9tfrUTRZSch8B7WEGTvnBLdn0+UM9HucdHqxhDJbi/Gr463n1PWw7QDDQVulNxZ0ba8aB44DmSv9pLv3Bs/07UstsqvjedBdw9dh59NMkyzjnrKAvXWqWzZhPYItjMedAwW/AK5tazRvGtQ+x6+EvS1wgdeFAAEC+YBRpCSIc/kTrXMYIHGBjkbCv+7ZuRIN8LFuasv+pguHXM4LhGn/Kf+3jQPOPCn1Sc3Usz1A5n6vtlxNr++qMFT4rP5QBky708b4eTKz+nAb9BXfg5Bhdho9IFeDpkhBML2IogRyCCh2p2jF2cpGG654+Li7xbIpKZ/a6zkHhKMsPGPsqw+cWjfOZUbLJLfe2v7EqBwMZwpI5eW2yuYB1Lqx94qYmvmU4Tabijp1mteWHwjAK2dEpTdA4tth/o/buMPlut+p/jrcJE7PI9cELfc7pA+Wg226WRg8LoHe/+9TSrL1jtYsdRA8Idekx1KlDhxbw34xEDimqVcfoXHdmjXZqHnLopZuXS6g6RBVB8g4tJt0v2O4pktR6zTwcOj63n0DOkc2Hz4VVfN6pv0WXUI4gpA/JOSfjQvgzX+/aloxnofxnMzaFKr+y8Si2xlz16SjXz5d40rsZnR/2ZQUBCEFIzDoxft9X8pZaOL3Z9hByjwK0x2eGeDuJ7H0g3CiKhxH4ZuB1elCGwaJCrhxCpH0L/l058NZQJ415+FWBawxQrtli7DYDgqMyBpnPij69QSjJeK9+OO4awzh5zZCObDHBoEVwV8NI6mkeo4q/pFA5bbwh8WXrFsnujpiwP6f15ZNq74WL2FPIatS4y4NwM8Fse8H4PahuAbdok3M3/cN34IaJ57YCW+GmLf5+4LE0LOK68pm9H71dEqnDNDtCmqXauiHanpDEG3doXwRqq53L+f/APNojXnz3FT3tOnarslc7jM/9J/OU0xecRMZyqsdleFBipHPJQWUyOozRU9DETu6afwdESqBOqm1kh72/vhx7GQfjoWWIL0ZCNPsfebYQTAbYM856PY8Jl+TvxIcW/4UUb+1YZqD9bbLoZt/tZB3g4q5V9q3scRlNZY8JHLqeKPlUwnHSYzEjiO/lS7wTZXCE5i6ToxcAQ4Viv4/b85IKqkbMQJSUwNlLwwrItcDwtWzismCuviXVZCv5slOxiopUwOptKoE4Cf+8GAE="},{"type":"tool_use","id":"toolu_019djfakvs4TDtarRwurNBvB","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nfor f,fr in [('GDPC1','QS'),('UNRATE','MS')]:\n    d=pd.read_csv(f'data/{f}.csv',parse_dates=['observation_date'])\n    print(f,d.shape,d.isna().sum().to_dict(),d.observation_date.duplicated().sum(),d[f].min(),d[f].max())\n    full=pd.date_range(d.observation_date.min(),d.observation_date.max(),freq=fr)\n    print('missing dates',sorted(set(full)-set(d.observation_date)))\n\"; cat gate_spec.json bundle.json | head -5","description":"Audit gaps, NaNs, duplicates"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"30dc64dd-dd47-4549-8967-4b27893639b5","timestamp":"2026-10-30T04:49:29.949Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"0d9316f4-d87e-4a33-b55d-e4984fd0e1c3","keep":6,"tail":["98a140cdd0351516407d62e020d460a295adfe01d79a4c3b5d483d951ae63396","516a8bc9ae6a815c98a9aec9ed03d5c0b79a09638f1f0d8279ade3090fcb4c1d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c5e6186a045f818568b5a00634bbc40888c03e35b7ca99cfa07376e39a43f9b3"}
{"parentUuid":"15ec6a6d-c80e-4942-9160-a66c6c7ba8e1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpR6sKSh5XLtV5tYWzv","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011L7sUNcaCz1ks76s7E5ukE","name":"Bash","input":{"command":"grep -n ',$\\|,\\.' data/UNRATE.csv; awk -F, 'NR>1 && $2==\"\"' data/UNRATE.csv","description":"Locate missing UNRATE value"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":606,"cache_read_input_tokens":7758,"output_tokens":129,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":606},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpR6chLvhxiQGrfeUpW","requestRef":"30dc64dd-dd47-4549-8967-4b27893639b5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"69087392-19c4-4ad5-bf05-cfbab7f593a8","timestamp":"2026-10-30T04:49:31.790Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"69087392-19c4-4ad5-bf05-cfbab7f593a8","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011L7sUNcaCz1ks76s7E5ukE","type":"tool_result","content":"2025-10-01,","is_error":false}]},"uuid":"26c2995f-d123-4844-b3bb-eaf0de036846","timestamp":"2026-10-30T04:49:31.838Z","toolUseResult":{"stdout":"2025-10-01,","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"69087392-19c4-4ad5-bf05-cfbab7f593a8","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"af427690d5e16116b33b6c1c732560b21e43224ec9d7fac291a7d569db5862bc","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_011L7sUNcaCz1ks76s7E5ukE","name":"Bash","input":{"command":"grep -n ',$\\|,\\.' data/UNRATE.csv; awk -F, 'NR>1 && $2==\"\"' data/UNRATE.csv","description":"Locate missing UNRATE value"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"80c15a70-176c-449b-974b-9f1a16e32a0a","timestamp":"2026-10-30T04:49:31.843Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"30dc64dd-dd47-4549-8967-4b27893639b5","keep":8,"tail":["af427690d5e16116b33b6c1c732560b21e43224ec9d7fac291a7d569db5862bc","beb57235b15f0621ce63aef65dfd0f5a9068059bd11f86a6e183b11f49d7a2f2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"37ef077ed55437e269f4d9dd3a0ecb8257ec06901871a97c64a33b9b0f17b1ff"}
{"parentUuid":"26c2995f-d123-4844-b3bb-eaf0de036846","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpRF7B45R8FgrdRs16V","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":141,"cache_read_input_tokens":8364,"output_tokens":1572,"output_tokens_details":{"thinking_tokens":29},"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":141},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":460,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpREoZRrvb4AFyB9dwR","requestRef":"80c15a70-176c-449b-974b-9f1a16e32a0a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"dddc0b55-f288-467d-886b-10b68392b082","timestamp":"2026-10-30T04:49:33.587Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"dddc0b55-f288-467d-886b-10b68392b082","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpRF7B45R8FgrdRs16V","type":"message","role":"assistant","content":[{"type":"text","text":"Only one missing value (Oct 2025, outside the sample window). Writing the P0/P1 state files now."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":141,"cache_read_input_tokens":8364,"output_tokens":1572,"output_tokens_details":{"thinking_tokens":29},"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":141},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpREoZRrvb4AFyB9dwR","requestRef":"80c15a70-176c-449b-974b-9f1a16e32a0a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"40a3a6dd-6ead-4170-824d-0e448f1512ca","timestamp":"2026-10-30T04:49:33.590Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"40a3a6dd-6ead-4170-824d-0e448f1512ca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpRF7B45R8FgrdRs16V","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_019WikG3Uaj94dWUac5obRDQ","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract — F6-conf-03\n**Question:** How much does the quarterly change in US unemployment (pp) respond to quarterly real GDP growth (%, not annualised), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?\n**Estimand:** β in Δu_t = α + β g_t + ε_t (OLS, 240 quarters). u_t = mean of 3 monthly UNRATE; g_t = 100·Δln GDPC1. Meaningful as a linear projection coefficient (descriptive association, not causal); HAC inference assumes weak stationarity / mixing of (g, ε).\n**Uncertainty:** Newey–West (Bartlett) HAC SE for full-sample β; lag length reported. 95% CI = β ± 1.96·SE (normal).\n**Stability:** subsample OLS slopes; classical Chow F (SSR-based), df (2, n−4)=(2,236).\n**Outputs:** out/results.json (keys per TASK.md table), out/figure1.png, out/table1.csv (period,n,intercept,slope,slope_se), out/report.md (6 sections), out/analysis.py, out/claims.json.\n**Information rules:** only data/GDPC1.csv, data/UNRATE.csv; no quarter after 2019Q4 in any estimate; 1959Q4 levels allowed for 1960Q1 differences.\n**Invalidity conditions:** missing months/quarters inside 1959Q4–2019Q4; incomplete quarters averaged; post-2019 data leaking; wrong growth definition (annualised).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n \"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols | range | missing | duplicates dates |\n|---|---|---|---|---|---|---|\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1 bn chained 2017 $ SAAR) | 1947-01-01..2026-07-01, no gaps in quarterly grid | 0 | 0 |\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE %) | 1948-01-01..2026-09-01, no gaps in monthly grid | 1 (2025-10-01 empty value) | 0 |\n\nAnomalies:\n- UNRATE 2025-10-01 is blank (outside sample; dropped by the sample window, no effect). \n- Values in range (GDPC1 2172–24611; UNRATE 2.5–14.8).\n- Data vintage is 2026 (GDPC1 in chained 2017 $): estimates reflect current revised data, not real-time data. Not a violation of the rules (task defines these files as inputs).\n- Observations after 2019Q4 violate the sample rule if used: handled by restricting to 1959Q4–2019Q4 levels before differencing/estimation.\nEOF\ncat > log.md <<'EOF'\n- 2026-10-30 P0 passed: contract written.\n- 2026-10-30 P1: data audited; hashes match README; only anomaly is blank UNRATE 2025-10 (out of sample). Decision: truncate to 1959Q4–2019Q4 levels; require 3 months per quarter.\nEOF","description":"Write contract, phases, audit, log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":141,"cache_read_input_tokens":8364,"output_tokens":1572,"output_tokens_details":{"thinking_tokens":29},"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":141},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpREoZRrvb4AFyB9dwR","requestRef":"80c15a70-176c-449b-974b-9f1a16e32a0a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"58c1d35c-24a1-4307-9bc9-bd5e586a8937","timestamp":"2026-10-30T04:49:46.084Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"58c1d35c-24a1-4307-9bc9-bd5e586a8937","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_019WikG3Uaj94dWUac5obRDQ","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"a1e84950-fa5b-4207-923e-5d0106273d7e","timestamp":"2026-10-30T04:49:46.138Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"58c1d35c-24a1-4307-9bc9-bd5e586a8937","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"04c7ccd1cb885e7db18fc72d3124a9862b30754d7de8b030d27d670024a19357","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Only one missing value (Oct 2025, outside the sample window). Writing the P0/P1 state files now."},{"type":"tool_use","id":"toolu_019WikG3Uaj94dWUac5obRDQ","name":"Bash","input":{"command":"mkdir -p out/state && cd out/state && cat > contract.md <<'EOF'\n# Contract — F6-conf-03\n**Question:** How much does the quarterly change in US unemployment (pp) respond to quarterly real GDP growth (%, not annualised), 1960Q1–2019Q4, and is the response stable across 1960Q1–1983Q4 vs 1984Q1–2019Q4?\n**Estimand:** β in Δu_t = α + β g_t + ε_t (OLS, 240 quarters). u_t = mean of 3 monthly UNRATE; g_t = 100·Δln GDPC1. Meaningful as a linear projection coefficient (descriptive association, not causal); HAC inference assumes weak stationarity / mixing of (g, ε).\n**Uncertainty:** Newey–West (Bartlett) HAC SE for full-sample β; lag length reported. 95% CI = β ± 1.96·SE (normal).\n**Stability:** subsample OLS slopes; classical Chow F (SSR-based), df (2, n−4)=(2,236).\n**Outputs:** out/results.json (keys per TASK.md table), out/figure1.png, out/table1.csv (period,n,intercept,slope,slope_se), out/report.md (6 sections), out/analysis.py, out/claims.json.\n**Information rules:** only data/GDPC1.csv, data/UNRATE.csv; no quarter after 2019Q4 in any estimate; 1959Q4 levels allowed for 1960Q1 differences.\n**Invalidity conditions:** missing months/quarters inside 1959Q4–2019Q4; incomplete quarters averaged; post-2019 data leaking; wrong growth definition (annualised).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"running\",\"checks\":[],\"notes\":\"\"},\n \"P2\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P3\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P4\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"},\n \"P5\":{\"status\":\"pending\",\"checks\":[],\"notes\":\"\"}}\nEOF\ncat > data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols | range | missing | duplicates dates |\n|---|---|---|---|---|---|---|\n| GDPC1.csv | 1c6c6e9f59e383e20c849dd299175c7a307526c09abdc18f18da9754fc5b3343 (matches README) | 319 | 2 (observation_date, GDPC1 bn chained 2017 $ SAAR) | 1947-01-01..2026-07-01, no gaps in quarterly grid | 0 | 0 |\n| UNRATE.csv | 621ff6fadf50910cb7a21ee20ba610c247cb043b29b4e05c4c1a72fadca2a06c (matches README) | 945 | 2 (observation_date, UNRATE %) | 1948-01-01..2026-09-01, no gaps in monthly grid | 1 (2025-10-01 empty value) | 0 |\n\nAnomalies:\n- UNRATE 2025-10-01 is blank (outside sample; dropped by the sample window, no effect). \n- Values in range (GDPC1 2172–24611; UNRATE 2.5–14.8).\n- Data vintage is 2026 (GDPC1 in chained 2017 $): estimates reflect current revised data, not real-time data. Not a violation of the rules (task defines these files as inputs).\n- Observations after 2019Q4 violate the sample rule if used: handled by restricting to 1959Q4–2019Q4 levels before differencing/estimation.\nEOF\ncat > log.md <<'EOF'\n- 2026-10-30 P0 passed: contract written.\n- 2026-10-30 P1: data audited; hashes match README; only anomaly is blank UNRATE 2025-10 (out of sample). Decision: truncate to 1959Q4–2019Q4 levels; require 3 months per quarter.\nEOF","description":"Write contract, phases, audit, log"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"ba76d1f5-5a52-48a8-af86-4186375c22e7","timestamp":"2026-10-30T04:49:46.141Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"80c15a70-176c-449b-974b-9f1a16e32a0a","keep":10,"tail":["04c7ccd1cb885e7db18fc72d3124a9862b30754d7de8b030d27d670024a19357","4a493e0b1e196251d5c1781aee8a2de88e630bb90c3ee8d129af2166c376a256"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"83839dd5c109193f4c6dffdab7df6c9be071e54e28e5dc0b5c58e5b2fd72624c"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a1e84950-fa5b-4207-923e-5d0106273d7e","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"a1e84950-fa5b-4207-923e-5d0106273d7e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSJ8Wok5PHdBncqGuU","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":1587,"cache_read_input_tokens":8505,"output_tokens":4269,"output_tokens_details":{"thinking_tokens":387},"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":1587},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3552,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpSHquBp5iNqCXsPdsJ","requestRef":"ba76d1f5-5a52-48a8-af86-4186375c22e7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a743e184-b97e-4ace-a4a5-d35fc0f3f588","timestamp":"2026-10-30T04:49:51.147Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"a743e184-b97e-4ace-a4a5-d35fc0f3f588","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpSJ8Wok5PHdBncqGuU","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01SmbnzcTQyXq7vhvpU1shFC","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n   ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\nimport json, os, math\nimport numpy as np, pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nSEED = None  # no randomness used\nLEVEL_START, END = pd.Timestamp(\"1959-10-01\"), pd.Timestamp(\"2019-10-01\")\nS1_END, S2_START = pd.Timestamp(\"1983-10-01\"), pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\nun = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\nexcl = []\ndef led(step, rule, nb, na, why):\n    excl.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\n# --- unemployment: monthly -> quarterly average (complete quarters only)\nnb = len(un); un_nonmiss = un.dropna(subset=[\"UNRATE\"])\nled(\"UNRATE_1\", \"drop months with blank UNRATE\", nb, len(un_nonmiss), \"2025-10 value blank in FRED file; outside sample\")\nnb = len(un_nonmiss)\nun_w = un_nonmiss[(un_nonmiss.observation_date >= LEVEL_START) & (un_nonmiss.observation_date < END + pd.DateOffset(months=3))]\nled(\"UNRATE_2\", \"keep months 1959-10..2019-12\", nb, len(un_w), \"levels needed for 1960Q1-2019Q4 differences; post-2019 excluded by rule\")\nq = un_w.observation_date.dt.to_period(\"Q\").dt.start_time\ngrp = un_w.groupby(q)[\"UNRATE\"]\ncnt = grp.count()\nassert (cnt == 3).all(), \"incomplete quarter in sample window\"\nu = grp.mean().rename(\"u\")\nled(\"UNRATE_3\", \"average 3 months -> quarters\", len(un_w), len(u), \"u_t = mean of 3 monthly values (rows are now quarters)\")\n\n# --- GDP\nnb = len(gdp)\ngdp_w = gdp[(gdp.observation_date >= LEVEL_START) & (gdp.observation_date <= END)].set_index(\"observation_date\")[\"GDPC1\"]\nled(\"GDPC1_1\", \"keep quarters 1959Q4..2019Q4\", nb, len(gdp_w), \"levels needed for 1960Q1-2019Q4 growth; post-2019 excluded by rule\")\nassert gdp_w.notna().all()\n\ndf = pd.concat([u, gdp_w], axis=1, join=\"inner\")\nassert len(df) == 241 and (df.index.to_series().diff().dropna().dt.days.between(89, 93)).all()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\nnb = len(df); df = df.dropna()\nled(\"MERGED_1\", \"first difference (drop 1959Q4)\", nb, len(df), \"1959Q4 only provides lagged levels\")\nassert df.index.min() == pd.Timestamp(\"1960-01-01\") and df.index.max() == END and len(df) == 240\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\ndef nw_lags(n):  # Newey-West (1994) plug-in rule of thumb\n    return int(math.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(d):\n    X = sm.add_constant(d[\"g\"]); y = d[\"du\"]\n    ols = sm.OLS(y, X).fit()\n    L = nw_lags(len(d))\n    hac = ols.get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\", use_correction=True)\n    return ols, hac, L\n\nfull, full_hac, L = fit(df)\nd1 = df[df.index <= S1_END]; d2 = df[df.index >= S2_START]\nf1, h1, L1 = fit(d1); f2, h2, L2 = fit(d2)\nassert len(d1) + len(d2) == len(df)\n\nbeta = float(full.params[\"g\"]); alpha = float(full.params[\"const\"])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test (classical, SSR-based)\nn, k = len(df), 2\nssr_p, ssr_1, ssr_2 = full.ssr, f1.ssr, f2.ssr\nF = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\np = float(stats.f.sf(F, k, n - 2 * k))\n\nbaseline = float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2)))\nmodel = float(np.sqrt(np.mean(full.resid ** 2)))\nconcl = \"negative_effect\" if hi < 0 else (\"positive_effect\" if lo > 0 else \"no_detectable_effect\")\n\nres = {\n    \"task_id\": \"F6-conf-03\",\n    \"sample_start\": df.index.min().strftime(\"%Y-%m-%d\"),\n    \"sample_end\": df.index.max().strftime(\"%Y-%m-%d\"),\n    \"n_sub1\": int(len(d1)), \"n_sub2\": int(len(d2)),\n    \"baseline_metric\": baseline, \"model_metric\": model,\n    \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n    \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n    \"beta_sub1\": float(f1.params[\"g\"]), \"beta_sub2\": float(f2.params[\"g\"]),\n    \"chow_f_stat\": float(F), \"chow_p_value\": p,\n    \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n    \"conclusion\": concl,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": \"UNRATE 2025-10-01 value is blank in the FRED file\", \"handling\": \"dropped; outside the 1959Q4-2019Q4 window, no effect on estimates\"},\n        {\"issue\": \"Files extend to 2026 (beyond question period)\", \"handling\": \"truncated to 1959Q4-2019Q4 levels before differencing; no post-2019Q4 data enters any estimate\"},\n        {\"issue\": \"Data are the 2026 vintage (revised, chained 2017 dollars), not real-time\", \"handling\": \"used as provided; noted as limitation\"},\n    ],\n    \"n_input_rows\": n_input, \"n_analysed\": int(full.nobs), \"random_seed\": SEED,\n    # supplementary\n    \"r_squared_full\": float(full.rsquared),\n    \"effect_se_ols_classical\": float(full.bse[\"g\"]),\n    \"chow_df\": [k, n - 2 * k],\n    \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n    \"slope_se_sub1_hac\": float(h1.bse[1]), \"slope_se_sub2_hac\": float(h2.bse[1]),\n    \"intercept_sub1\": float(f1.params[\"const\"]), \"intercept_sub2\": float(f2.params[\"const\"]),\n    \"effect_se_hac_lags8\": float(full.get_robustcov_results(cov_type=\"HAC\", maxlags=8, use_correction=True).bse[1]),\n    \"mean_du\": float(df.du.mean()), \"mean_g\": float(df.g.mean()),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\npd.DataFrame([\n    dict(period=\"full_1960Q1-2019Q4\", n=len(df), intercept=alpha, slope=beta, slope_se=se),\n    dict(period=\"sub1_1960Q1-1983Q4\", n=len(d1), intercept=f1.params[\"const\"], slope=f1.params[\"g\"], slope_se=h1.bse[1]),\n    dict(period=\"sub2_1984Q1-2019Q4\", n=len(d2), intercept=f2.params[\"const\"], slope=f2.params[\"g\"], slope_se=h2.bse[1]),\n]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d1.g, d1.du, s=14, alpha=0.6, label=f\"1960Q1-1983Q4 (n={len(d1)})\", color=\"tab:blue\")\nax.scatter(d2.g, d2.du, s=14, alpha=0.6, label=f\"1984Q1-2019Q4 (n={len(d2)})\", color=\"tab:orange\", marker=\"s\")\nfor d, f, c, nm in [(d1, f1, \"tab:blue\", \"sub1\"), (d2, f2, \"tab:orange\", \"sub2\")]:\n    xs = np.linspace(d.g.min(), d.g.max(), 50)\n    ax.plot(xs, f.params[\"const\"] + f.params[\"g\"] * xs, color=c, lw=2,\n            label=f\"{nm} fit: du = {f.params['const']:.3f} + ({f.params['g']:.3f}) g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1-2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n                                       \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\",\n                                       \"baseline_metric\", \"model_metric\", \"conclusion\", \"stability_conclusion\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1587,"cache_read_input_tokens":8505,"output_tokens":4269,"output_tokens_details":{"thinking_tokens":387},"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":1587},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpSHquBp5iNqCXsPdsJ","requestRef":"ba76d1f5-5a52-48a8-af86-4186375c22e7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"164d832c-6fef-4e97-8a11-441c0eea1d2d","timestamp":"2026-10-30T04:50:19.719Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"164d832c-6fef-4e97-8a11-441c0eea1d2d","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0172/out/state/out/analysis.py': [Errno 2] No such file or directory","is_error":true,"tool_use_id":"toolu_01SmbnzcTQyXq7vhvpU1shFC"}]},"uuid":"6070a54f-1248-4c57-996a-6c55b6948060","timestamp":"2026-10-30T04:50:19.786Z","toolUseResult":"Error: Exit code 2\n(eval):1: no such file or directory: out/analysis.py\n/opt/homebrew/Cellar/python@3.14/3.14.4/Frameworks/Python.framework/Versions/3.14/Resources/Python.app/Contents/MacOS/Python: can't open file '/Users/simon-pierreboucher/wp29/runs/RC0172/out/state/out/analysis.py': [Errno 2] No such file or directory","sandboxed":false,"sourceToolAssistantUUID":"164d832c-6fef-4e97-8a11-441c0eea1d2d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"e790094350e7574616e779704547ad0b51740f58813d971e161b0827b919c193","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01SmbnzcTQyXq7vhvpU1shFC","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n   ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\nimport json, os, math\nimport numpy as np, pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nSEED = None  # no randomness used\nLEVEL_START, END = pd.Timestamp(\"1959-10-01\"), pd.Timestamp(\"2019-10-01\")\nS1_END, S2_START = pd.Timestamp(\"1983-10-01\"), pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\nun = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\nexcl = []\ndef led(step, rule, nb, na, why):\n    excl.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\n# --- unemployment: monthly -> quarterly average (complete quarters only)\nnb = len(un); un_nonmiss = un.dropna(subset=[\"UNRATE\"])\nled(\"UNRATE_1\", \"drop months with blank UNRATE\", nb, len(un_nonmiss), \"2025-10 value blank in FRED file; outside sample\")\nnb = len(un_nonmiss)\nun_w = un_nonmiss[(un_nonmiss.observation_date >= LEVEL_START) & (un_nonmiss.observation_date < END + pd.DateOffset(months=3))]\nled(\"UNRATE_2\", \"keep months 1959-10..2019-12\", nb, len(un_w), \"levels needed for 1960Q1-2019Q4 differences; post-2019 excluded by rule\")\nq = un_w.observation_date.dt.to_period(\"Q\").dt.start_time\ngrp = un_w.groupby(q)[\"UNRATE\"]\ncnt = grp.count()\nassert (cnt == 3).all(), \"incomplete quarter in sample window\"\nu = grp.mean().rename(\"u\")\nled(\"UNRATE_3\", \"average 3 months -> quarters\", len(un_w), len(u), \"u_t = mean of 3 monthly values (rows are now quarters)\")\n\n# --- GDP\nnb = len(gdp)\ngdp_w = gdp[(gdp.observation_date >= LEVEL_START) & (gdp.observation_date <= END)].set_index(\"observation_date\")[\"GDPC1\"]\nled(\"GDPC1_1\", \"keep quarters 1959Q4..2019Q4\", nb, len(gdp_w), \"levels needed for 1960Q1-2019Q4 growth; post-2019 excluded by rule\")\nassert gdp_w.notna().all()\n\ndf = pd.concat([u, gdp_w], axis=1, join=\"inner\")\nassert len(df) == 241 and (df.index.to_series().diff().dropna().dt.days.between(89, 93)).all()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\nnb = len(df); df = df.dropna()\nled(\"MERGED_1\", \"first difference (drop 1959Q4)\", nb, len(df), \"1959Q4 only provides lagged levels\")\nassert df.index.min() == pd.Timestamp(\"1960-01-01\") and df.index.max() == END and len(df) == 240\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\ndef nw_lags(n):  # Newey-West (1994) plug-in rule of thumb\n    return int(math.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(d):\n    X = sm.add_constant(d[\"g\"]); y = d[\"du\"]\n    ols = sm.OLS(y, X).fit()\n    L = nw_lags(len(d))\n    hac = ols.get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\", use_correction=True)\n    return ols, hac, L\n\nfull, full_hac, L = fit(df)\nd1 = df[df.index <= S1_END]; d2 = df[df.index >= S2_START]\nf1, h1, L1 = fit(d1); f2, h2, L2 = fit(d2)\nassert len(d1) + len(d2) == len(df)\n\nbeta = float(full.params[\"g\"]); alpha = float(full.params[\"const\"])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test (classical, SSR-based)\nn, k = len(df), 2\nssr_p, ssr_1, ssr_2 = full.ssr, f1.ssr, f2.ssr\nF = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\np = float(stats.f.sf(F, k, n - 2 * k))\n\nbaseline = float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2)))\nmodel = float(np.sqrt(np.mean(full.resid ** 2)))\nconcl = \"negative_effect\" if hi < 0 else (\"positive_effect\" if lo > 0 else \"no_detectable_effect\")\n\nres = {\n    \"task_id\": \"F6-conf-03\",\n    \"sample_start\": df.index.min().strftime(\"%Y-%m-%d\"),\n    \"sample_end\": df.index.max().strftime(\"%Y-%m-%d\"),\n    \"n_sub1\": int(len(d1)), \"n_sub2\": int(len(d2)),\n    \"baseline_metric\": baseline, \"model_metric\": model,\n    \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n    \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n    \"beta_sub1\": float(f1.params[\"g\"]), \"beta_sub2\": float(f2.params[\"g\"]),\n    \"chow_f_stat\": float(F), \"chow_p_value\": p,\n    \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n    \"conclusion\": concl,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": \"UNRATE 2025-10-01 value is blank in the FRED file\", \"handling\": \"dropped; outside the 1959Q4-2019Q4 window, no effect on estimates\"},\n        {\"issue\": \"Files extend to 2026 (beyond question period)\", \"handling\": \"truncated to 1959Q4-2019Q4 levels before differencing; no post-2019Q4 data enters any estimate\"},\n        {\"issue\": \"Data are the 2026 vintage (revised, chained 2017 dollars), not real-time\", \"handling\": \"used as provided; noted as limitation\"},\n    ],\n    \"n_input_rows\": n_input, \"n_analysed\": int(full.nobs), \"random_seed\": SEED,\n    # supplementary\n    \"r_squared_full\": float(full.rsquared),\n    \"effect_se_ols_classical\": float(full.bse[\"g\"]),\n    \"chow_df\": [k, n - 2 * k],\n    \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n    \"slope_se_sub1_hac\": float(h1.bse[1]), \"slope_se_sub2_hac\": float(h2.bse[1]),\n    \"intercept_sub1\": float(f1.params[\"const\"]), \"intercept_sub2\": float(f2.params[\"const\"]),\n    \"effect_se_hac_lags8\": float(full.get_robustcov_results(cov_type=\"HAC\", maxlags=8, use_correction=True).bse[1]),\n    \"mean_du\": float(df.du.mean()), \"mean_g\": float(df.g.mean()),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\npd.DataFrame([\n    dict(period=\"full_1960Q1-2019Q4\", n=len(df), intercept=alpha, slope=beta, slope_se=se),\n    dict(period=\"sub1_1960Q1-1983Q4\", n=len(d1), intercept=f1.params[\"const\"], slope=f1.params[\"g\"], slope_se=h1.bse[1]),\n    dict(period=\"sub2_1984Q1-2019Q4\", n=len(d2), intercept=f2.params[\"const\"], slope=f2.params[\"g\"], slope_se=h2.bse[1]),\n]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d1.g, d1.du, s=14, alpha=0.6, label=f\"1960Q1-1983Q4 (n={len(d1)})\", color=\"tab:blue\")\nax.scatter(d2.g, d2.du, s=14, alpha=0.6, label=f\"1984Q1-2019Q4 (n={len(d2)})\", color=\"tab:orange\", marker=\"s\")\nfor d, f, c, nm in [(d1, f1, \"tab:blue\", \"sub1\"), (d2, f2, \"tab:orange\", \"sub2\")]:\n    xs = np.linspace(d.g.min(), d.g.max(), 50)\n    ax.plot(xs, f.params[\"const\"] + f.params[\"g\"] * xs, color=c, lw=2,\n            label=f\"{nm} fit: du = {f.params['const']:.3f} + ({f.params['g']:.3f}) g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1-2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n                                       \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\",\n                                       \"baseline_metric\", \"model_metric\", \"conclusion\", \"stability_conclusion\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"1dcd74ae-ad94-41c4-9c97-259c9cfd38c5","timestamp":"2026-10-30T04:50:19.789Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"ba76d1f5-5a52-48a8-af86-4186375c22e7","keep":12,"tail":["e790094350e7574616e779704547ad0b51740f58813d971e161b0827b919c193","c344223cc9535a0ff5069c445b74cd3df420355d5c8392b423cb40dca77ad176"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"65360c7e9bf02e2be4d97b63aff8a294feed9553a2804632b570548d107636fa"}
{"parentUuid":"6070a54f-1248-4c57-996a-6c55b6948060","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpUmytHZzDqShkMar1b","type":"message","role":"assistant","content":[{"type":"text","text":"The shell was still in out/state; rerunning from the workspace root."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4431,"cache_read_input_tokens":10092,"output_tokens":133,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4431},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpUmikFptPjCZKmurMM","requestRef":"1dcd74ae-ad94-41c4-9c97-259c9cfd38c5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bb8c2340-dd18-48fc-8d11-8a885ade1272","timestamp":"2026-10-30T04:50:21.136Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"bb8c2340-dd18-48fc-8d11-8a885ade1272","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpUmytHZzDqShkMar1b","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_012fx4XdZVot1a4KhUTg5dsq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0172 && ls out/state && pwd","description":"Return to workspace root"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4431,"cache_read_input_tokens":10092,"output_tokens":133,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":4431},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpUmikFptPjCZKmurMM","requestRef":"1dcd74ae-ad94-41c4-9c97-259c9cfd38c5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0be66af0-d23b-4ba3-8dc9-2eae5bf77749","timestamp":"2026-10-30T04:50:21.783Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"0be66af0-d23b-4ba3-8dc9-2eae5bf77749","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_012fx4XdZVot1a4KhUTg5dsq","type":"tool_result","content":"contract.md\ndata_audit.md\nlog.md\nphases.json\n/Users/simon-pierreboucher/wp29/runs/RC0172","is_error":false}]},"uuid":"fc2f841d-045a-4d64-8323-f1950975791c","timestamp":"2026-10-30T04:50:21.813Z","toolUseResult":{"stdout":"contract.md\ndata_audit.md\nlog.md\nphases.json\n/Users/simon-pierreboucher/wp29/runs/RC0172","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"0be66af0-d23b-4ba3-8dc9-2eae5bf77749","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"fef04918a0c15460046ee3c38a8f5a13ea1ca8ea3bd87e3f026433ad95d73319","message":{"role":"assistant","content":[{"type":"text","text":"The shell was still in out/state; rerunning from the workspace root."},{"type":"tool_use","id":"toolu_012fx4XdZVot1a4KhUTg5dsq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RC0172 && ls out/state && pwd","description":"Return to workspace root"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"57d525c8-df6d-44fe-ae13-daa297b274c1","timestamp":"2026-10-30T04:50:21.816Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"1dcd74ae-ad94-41c4-9c97-259c9cfd38c5","keep":14,"tail":["fef04918a0c15460046ee3c38a8f5a13ea1ca8ea3bd87e3f026433ad95d73319","223799289bf0de762cd28c05f87bb12d8a969de5c4cd78f62f100abdad2c2489"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7c7fd0a563de801ce307f838e6487957eff3c8e02aa5c9aabba29ce15b06d416"}
{"parentUuid":"fc2f841d-045a-4d64-8323-f1950975791c","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpUvfX7rZXvKq7iYQR9","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":184,"cache_read_input_tokens":14523,"output_tokens":3938,"output_tokens_details":{"thinking_tokens":27},"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":184},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":236,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpUvMQgqz7dwYozqwsf","requestRef":"57d525c8-df6d-44fe-ae13-daa297b274c1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7f5f44c3-127f-4f21-a010-3005d9828650","timestamp":"2026-10-30T04:50:23.577Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"7f5f44c3-127f-4f21-a010-3005d9828650","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpUvfX7rZXvKq7iYQR9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JFsmDiWRkGmF2kayXRE9C3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n   ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\nimport json, os, math\nimport numpy as np, pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nSEED = None  # no randomness used\nLEVEL_START, END = pd.Timestamp(\"1959-10-01\"), pd.Timestamp(\"2019-10-01\")\nS1_END, S2_START = pd.Timestamp(\"1983-10-01\"), pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\nun = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\nexcl = []\ndef led(step, rule, nb, na, why):\n    excl.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\n# --- unemployment: monthly -> quarterly average (complete quarters only)\nnb = len(un); un_nonmiss = un.dropna(subset=[\"UNRATE\"])\nled(\"UNRATE_1\", \"drop months with blank UNRATE\", nb, len(un_nonmiss), \"2025-10 value blank in FRED file; outside sample\")\nnb = len(un_nonmiss)\nun_w = un_nonmiss[(un_nonmiss.observation_date >= LEVEL_START) & (un_nonmiss.observation_date < END + pd.DateOffset(months=3))]\nled(\"UNRATE_2\", \"keep months 1959-10..2019-12\", nb, len(un_w), \"levels needed for 1960Q1-2019Q4 differences; post-2019 excluded by rule\")\nq = un_w.observation_date.dt.to_period(\"Q\").dt.start_time\ngrp = un_w.groupby(q)[\"UNRATE\"]\ncnt = grp.count()\nassert (cnt == 3).all(), \"incomplete quarter in sample window\"\nu = grp.mean().rename(\"u\")\nled(\"UNRATE_3\", \"average 3 months -> quarters\", len(un_w), len(u), \"u_t = mean of 3 monthly values (rows are now quarters)\")\n\n# --- GDP\nnb = len(gdp)\ngdp_w = gdp[(gdp.observation_date >= LEVEL_START) & (gdp.observation_date <= END)].set_index(\"observation_date\")[\"GDPC1\"]\nled(\"GDPC1_1\", \"keep quarters 1959Q4..2019Q4\", nb, len(gdp_w), \"levels needed for 1960Q1-2019Q4 growth; post-2019 excluded by rule\")\nassert gdp_w.notna().all()\n\ndf = pd.concat([u, gdp_w], axis=1, join=\"inner\")\nassert len(df) == 241 and (df.index.to_series().diff().dropna().dt.days.between(89, 93)).all()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\nnb = len(df); df = df.dropna()\nled(\"MERGED_1\", \"first difference (drop 1959Q4)\", nb, len(df), \"1959Q4 only provides lagged levels\")\nassert df.index.min() == pd.Timestamp(\"1960-01-01\") and df.index.max() == END and len(df) == 240\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\ndef nw_lags(n):  # Newey-West (1994) plug-in rule of thumb\n    return int(math.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(d):\n    X = sm.add_constant(d[\"g\"]); y = d[\"du\"]\n    ols = sm.OLS(y, X).fit()\n    L = nw_lags(len(d))\n    hac = ols.get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\", use_correction=True)\n    return ols, hac, L\n\nfull, full_hac, L = fit(df)\nd1 = df[df.index <= S1_END]; d2 = df[df.index >= S2_START]\nf1, h1, L1 = fit(d1); f2, h2, L2 = fit(d2)\nassert len(d1) + len(d2) == len(df)\n\nbeta = float(full.params[\"g\"]); alpha = float(full.params[\"const\"])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test (classical, SSR-based)\nn, k = len(df), 2\nssr_p, ssr_1, ssr_2 = full.ssr, f1.ssr, f2.ssr\nF = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\np = float(stats.f.sf(F, k, n - 2 * k))\n\nbaseline = float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2)))\nmodel = float(np.sqrt(np.mean(full.resid ** 2)))\nconcl = \"negative_effect\" if hi < 0 else (\"positive_effect\" if lo > 0 else \"no_detectable_effect\")\n\nres = {\n    \"task_id\": \"F6-conf-03\",\n    \"sample_start\": df.index.min().strftime(\"%Y-%m-%d\"),\n    \"sample_end\": df.index.max().strftime(\"%Y-%m-%d\"),\n    \"n_sub1\": int(len(d1)), \"n_sub2\": int(len(d2)),\n    \"baseline_metric\": baseline, \"model_metric\": model,\n    \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n    \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n    \"beta_sub1\": float(f1.params[\"g\"]), \"beta_sub2\": float(f2.params[\"g\"]),\n    \"chow_f_stat\": float(F), \"chow_p_value\": p,\n    \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n    \"conclusion\": concl,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": \"UNRATE 2025-10-01 value is blank in the FRED file\", \"handling\": \"dropped; outside the 1959Q4-2019Q4 window, no effect on estimates\"},\n        {\"issue\": \"Files extend to 2026 (beyond question period)\", \"handling\": \"truncated to 1959Q4-2019Q4 levels before differencing; no post-2019Q4 data enters any estimate\"},\n        {\"issue\": \"Data are the 2026 vintage (revised, chained 2017 dollars), not real-time\", \"handling\": \"used as provided; noted as limitation\"},\n    ],\n    \"n_input_rows\": n_input, \"n_analysed\": int(full.nobs), \"random_seed\": SEED,\n    # supplementary\n    \"r_squared_full\": float(full.rsquared),\n    \"effect_se_ols_classical\": float(full.bse[\"g\"]),\n    \"chow_df\": [k, n - 2 * k],\n    \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n    \"slope_se_sub1_hac\": float(h1.bse[1]), \"slope_se_sub2_hac\": float(h2.bse[1]),\n    \"intercept_sub1\": float(f1.params[\"const\"]), \"intercept_sub2\": float(f2.params[\"const\"]),\n    \"effect_se_hac_lags8\": float(full.get_robustcov_results(cov_type=\"HAC\", maxlags=8, use_correction=True).bse[1]),\n    \"mean_du\": float(df.du.mean()), \"mean_g\": float(df.g.mean()),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\npd.DataFrame([\n    dict(period=\"full_1960Q1-2019Q4\", n=len(df), intercept=alpha, slope=beta, slope_se=se),\n    dict(period=\"sub1_1960Q1-1983Q4\", n=len(d1), intercept=f1.params[\"const\"], slope=f1.params[\"g\"], slope_se=h1.bse[1]),\n    dict(period=\"sub2_1984Q1-2019Q4\", n=len(d2), intercept=f2.params[\"const\"], slope=f2.params[\"g\"], slope_se=h2.bse[1]),\n]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d1.g, d1.du, s=14, alpha=0.6, label=f\"1960Q1-1983Q4 (n={len(d1)})\", color=\"tab:blue\")\nax.scatter(d2.g, d2.du, s=14, alpha=0.6, label=f\"1984Q1-2019Q4 (n={len(d2)})\", color=\"tab:orange\", marker=\"s\")\nfor d, f, c, nm in [(d1, f1, \"tab:blue\", \"sub1\"), (d2, f2, \"tab:orange\", \"sub2\")]:\n    xs = np.linspace(d.g.min(), d.g.max(), 50)\n    ax.plot(xs, f.params[\"const\"] + f.params[\"g\"] * xs, color=c, lw=2,\n            label=f\"{nm} fit: du = {f.params['const']:.3f} + ({f.params['g']:.3f}) g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1-2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n                                       \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\",\n                                       \"baseline_metric\", \"model_metric\", \"conclusion\", \"stability_conclusion\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":184,"cache_read_input_tokens":14523,"output_tokens":3938,"output_tokens_details":{"thinking_tokens":27},"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":184},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpUvMQgqz7dwYozqwsf","requestRef":"57d525c8-df6d-44fe-ae13-daa297b274c1","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"3a1537af-563e-4dfd-a04f-b847235c404b","timestamp":"2026-10-30T04:50:47.808Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3a1537af-563e-4dfd-a04f-b847235c404b","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"3a1537af-563e-4dfd-a04f-b847235c404b","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JFsmDiWRkGmF2kayXRE9C3","type":"tool_result","content":"{\n \"effect_estimate\": -0.2557677277487258,\n \"effect_se\": 0.03598488399675878,\n \"hac_lags\": 4,\n \"effect_ci_low\": -0.3262968043702248,\n \"effect_ci_high\": -0.18523865112722682,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.090333006233798,\n \"chow_p_value\": 0.0026363238517333456,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253,\n \"conclusion\": \"negative_effect\",\n \"stability_conclusion\": \"unstable\"\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03598488399675878\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03921717107661775\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06879369233083425\nstep,rule,n_before,n_after,n_removed,rationale\nUNRATE_1,drop months with blank UNRATE,945,944,1,2025-10 value blank in FRED file; outside sample\nUNRATE_2,keep months 1959-10..2019-12,944,723,221,levels needed for 1960Q1-2019Q4 differences; post-2019 excluded by rule\nUNRATE_3,average 3 months -> quarters,723,241,482,u_t = mean of 3 monthly values (rows are now quarters)\nGDPC1_1,keep quarters 1959Q4..2019Q4,319,241,78,levels needed for 1960Q1-2019Q4 growth; post-2019 excluded by rule\nMERGED_1,first difference (drop 1959Q4),241,240,1,1959Q4 only provides lagged levels","is_error":false}]},"uuid":"f7858cf1-7c65-4ee9-a423-cd9103d95d94","timestamp":"2026-10-30T04:50:48.658Z","toolUseResult":{"stdout":"{\n \"effect_estimate\": -0.2557677277487258,\n \"effect_se\": 0.03598488399675878,\n \"hac_lags\": 4,\n \"effect_ci_low\": -0.3262968043702248,\n \"effect_ci_high\": -0.18523865112722682,\n \"beta_sub1\": -0.25902105345680587,\n \"beta_sub2\": -0.27339263306757905,\n \"chow_f_stat\": 6.090333006233798,\n \"chow_p_value\": 0.0026363238517333456,\n \"baseline_metric\": 0.32465793964999184,\n \"model_metric\": 0.2497438816636253,\n \"conclusion\": \"negative_effect\",\n \"stability_conclusion\": \"unstable\"\n}\nperiod,n,intercept,slope,slope_se\nfull_1960Q1-2019Q4,240,0.18438835418210714,-0.2557677277487258,0.03598488399675878\nsub1_1960Q1-1983Q4,96,0.2542326539884382,-0.25902105345680587,0.03921717107661775\nsub2_1984Q1-2019Q4,144,0.15168581347724602,-0.27339263306757905,0.06879369233083425\nstep,rule,n_before,n_after,n_removed,rationale\nUNRATE_1,drop months with blank UNRATE,945,944,1,2025-10 value blank in FRED file; outside sample\nUNRATE_2,keep months 1959-10..2019-12,944,723,221,levels needed for 1960Q1-2019Q4 differences; post-2019 excluded by rule\nUNRATE_3,average 3 months -> quarters,723,241,482,u_t = mean of 3 monthly values (rows are now quarters)\nGDPC1_1,keep quarters 1959Q4..2019Q4,319,241,78,levels needed for 1960Q1-2019Q4 growth; post-2019 excluded by rule\nMERGED_1,first difference (drop 1959Q4),241,240,1,1959Q4 only provides lagged levels","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"3a1537af-563e-4dfd-a04f-b847235c404b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"9fffd4ded82b75468888e0816116fee2e3c380636dca1134f5ad3ea124429755","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01JFsmDiWRkGmF2kayXRE9C3","name":"Bash","input":{"command":"cat > out/analysis.py <<'EOF'\n\"\"\"Okun's law (difference form), US 1960Q1-2019Q4. Run from workspace root:\n   ~/wp29/venv/bin/python out/analysis.py\nReads only data/; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\"\"\"\nimport json, os, math\nimport numpy as np, pandas as pd\nimport statsmodels.api as sm\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nSEED = None  # no randomness used\nLEVEL_START, END = pd.Timestamp(\"1959-10-01\"), pd.Timestamp(\"2019-10-01\")\nS1_END, S2_START = pd.Timestamp(\"1983-10-01\"), pd.Timestamp(\"1984-01-01\")\n\ngdp = pd.read_csv(\"data/GDPC1.csv\", parse_dates=[\"observation_date\"])\nun = pd.read_csv(\"data/UNRATE.csv\", parse_dates=[\"observation_date\"])\nn_input = {\"GDPC1.csv\": int(len(gdp)), \"UNRATE.csv\": int(len(un))}\nexcl = []\ndef led(step, rule, nb, na, why):\n    excl.append(dict(step=step, rule=rule, n_before=nb, n_after=na, n_removed=nb - na, rationale=why))\n\n# --- unemployment: monthly -> quarterly average (complete quarters only)\nnb = len(un); un_nonmiss = un.dropna(subset=[\"UNRATE\"])\nled(\"UNRATE_1\", \"drop months with blank UNRATE\", nb, len(un_nonmiss), \"2025-10 value blank in FRED file; outside sample\")\nnb = len(un_nonmiss)\nun_w = un_nonmiss[(un_nonmiss.observation_date >= LEVEL_START) & (un_nonmiss.observation_date < END + pd.DateOffset(months=3))]\nled(\"UNRATE_2\", \"keep months 1959-10..2019-12\", nb, len(un_w), \"levels needed for 1960Q1-2019Q4 differences; post-2019 excluded by rule\")\nq = un_w.observation_date.dt.to_period(\"Q\").dt.start_time\ngrp = un_w.groupby(q)[\"UNRATE\"]\ncnt = grp.count()\nassert (cnt == 3).all(), \"incomplete quarter in sample window\"\nu = grp.mean().rename(\"u\")\nled(\"UNRATE_3\", \"average 3 months -> quarters\", len(un_w), len(u), \"u_t = mean of 3 monthly values (rows are now quarters)\")\n\n# --- GDP\nnb = len(gdp)\ngdp_w = gdp[(gdp.observation_date >= LEVEL_START) & (gdp.observation_date <= END)].set_index(\"observation_date\")[\"GDPC1\"]\nled(\"GDPC1_1\", \"keep quarters 1959Q4..2019Q4\", nb, len(gdp_w), \"levels needed for 1960Q1-2019Q4 growth; post-2019 excluded by rule\")\nassert gdp_w.notna().all()\n\ndf = pd.concat([u, gdp_w], axis=1, join=\"inner\")\nassert len(df) == 241 and (df.index.to_series().diff().dropna().dt.days.between(89, 93)).all()\ndf[\"du\"] = df[\"u\"].diff()\ndf[\"g\"] = 100 * np.log(df[\"GDPC1\"]).diff()\nnb = len(df); df = df.dropna()\nled(\"MERGED_1\", \"first difference (drop 1959Q4)\", nb, len(df), \"1959Q4 only provides lagged levels\")\nassert df.index.min() == pd.Timestamp(\"1960-01-01\") and df.index.max() == END and len(df) == 240\npd.DataFrame(excl).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\ndef nw_lags(n):  # Newey-West (1994) plug-in rule of thumb\n    return int(math.floor(4 * (n / 100) ** (2 / 9)))\n\ndef fit(d):\n    X = sm.add_constant(d[\"g\"]); y = d[\"du\"]\n    ols = sm.OLS(y, X).fit()\n    L = nw_lags(len(d))\n    hac = ols.get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\", use_correction=True)\n    return ols, hac, L\n\nfull, full_hac, L = fit(df)\nd1 = df[df.index <= S1_END]; d2 = df[df.index >= S2_START]\nf1, h1, L1 = fit(d1); f2, h2, L2 = fit(d2)\nassert len(d1) + len(d2) == len(df)\n\nbeta = float(full.params[\"g\"]); alpha = float(full.params[\"const\"])\nse = float(full_hac.bse[1])\nz = stats.norm.ppf(0.975)\nlo, hi = beta - z * se, beta + z * se\n\n# Chow test (classical, SSR-based)\nn, k = len(df), 2\nssr_p, ssr_1, ssr_2 = full.ssr, f1.ssr, f2.ssr\nF = ((ssr_p - (ssr_1 + ssr_2)) / k) / ((ssr_1 + ssr_2) / (n - 2 * k))\np = float(stats.f.sf(F, k, n - 2 * k))\n\nbaseline = float(np.sqrt(np.mean((df.du - df.du.mean()) ** 2)))\nmodel = float(np.sqrt(np.mean(full.resid ** 2)))\nconcl = \"negative_effect\" if hi < 0 else (\"positive_effect\" if lo > 0 else \"no_detectable_effect\")\n\nres = {\n    \"task_id\": \"F6-conf-03\",\n    \"sample_start\": df.index.min().strftime(\"%Y-%m-%d\"),\n    \"sample_end\": df.index.max().strftime(\"%Y-%m-%d\"),\n    \"n_sub1\": int(len(d1)), \"n_sub2\": int(len(d2)),\n    \"baseline_metric\": baseline, \"model_metric\": model,\n    \"effect_estimate\": beta, \"intercept\": alpha, \"effect_se\": se, \"hac_lags\": L,\n    \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n    \"beta_sub1\": float(f1.params[\"g\"]), \"beta_sub2\": float(f2.params[\"g\"]),\n    \"chow_f_stat\": float(F), \"chow_p_value\": p,\n    \"stability_conclusion\": \"stable\" if p >= 0.05 else \"unstable\",\n    \"conclusion\": concl,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": \"UNRATE 2025-10-01 value is blank in the FRED file\", \"handling\": \"dropped; outside the 1959Q4-2019Q4 window, no effect on estimates\"},\n        {\"issue\": \"Files extend to 2026 (beyond question period)\", \"handling\": \"truncated to 1959Q4-2019Q4 levels before differencing; no post-2019Q4 data enters any estimate\"},\n        {\"issue\": \"Data are the 2026 vintage (revised, chained 2017 dollars), not real-time\", \"handling\": \"used as provided; noted as limitation\"},\n    ],\n    \"n_input_rows\": n_input, \"n_analysed\": int(full.nobs), \"random_seed\": SEED,\n    # supplementary\n    \"r_squared_full\": float(full.rsquared),\n    \"effect_se_ols_classical\": float(full.bse[\"g\"]),\n    \"chow_df\": [k, n - 2 * k],\n    \"hac_lags_sub1\": L1, \"hac_lags_sub2\": L2,\n    \"slope_se_sub1_hac\": float(h1.bse[1]), \"slope_se_sub2_hac\": float(h2.bse[1]),\n    \"intercept_sub1\": float(f1.params[\"const\"]), \"intercept_sub2\": float(f2.params[\"const\"]),\n    \"effect_se_hac_lags8\": float(full.get_robustcov_results(cov_type=\"HAC\", maxlags=8, use_correction=True).bse[1]),\n    \"mean_du\": float(df.du.mean()), \"mean_g\": float(df.g.mean()),\n}\nwith open(f\"{OUT}/results.json\", \"w\") as fh:\n    json.dump(res, fh, indent=2)\n\npd.DataFrame([\n    dict(period=\"full_1960Q1-2019Q4\", n=len(df), intercept=alpha, slope=beta, slope_se=se),\n    dict(period=\"sub1_1960Q1-1983Q4\", n=len(d1), intercept=f1.params[\"const\"], slope=f1.params[\"g\"], slope_se=h1.bse[1]),\n    dict(period=\"sub2_1984Q1-2019Q4\", n=len(d2), intercept=f2.params[\"const\"], slope=f2.params[\"g\"], slope_se=h2.bse[1]),\n]).to_csv(f\"{OUT}/table1.csv\", index=False)\n\nfig, ax = plt.subplots(figsize=(7, 5))\nax.scatter(d1.g, d1.du, s=14, alpha=0.6, label=f\"1960Q1-1983Q4 (n={len(d1)})\", color=\"tab:blue\")\nax.scatter(d2.g, d2.du, s=14, alpha=0.6, label=f\"1984Q1-2019Q4 (n={len(d2)})\", color=\"tab:orange\", marker=\"s\")\nfor d, f, c, nm in [(d1, f1, \"tab:blue\", \"sub1\"), (d2, f2, \"tab:orange\", \"sub2\")]:\n    xs = np.linspace(d.g.min(), d.g.max(), 50)\n    ax.plot(xs, f.params[\"const\"] + f.params[\"g\"] * xs, color=c, lw=2,\n            label=f\"{nm} fit: du = {f.params['const']:.3f} + ({f.params['g']:.3f}) g\")\nax.axhline(0, color=\"grey\", lw=0.5); ax.axvline(0, color=\"grey\", lw=0.5)\nax.set_xlabel(\"Real GDP growth g_t (% q/q, not annualised)\")\nax.set_ylabel(\"Change in unemployment rate du_t (pp)\")\nax.set_title(f\"Okun's law, US 1960Q1-2019Q4 (Chow F={F:.2f}, p={p:.3f})\")\nax.legend(fontsize=8); fig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150)\n\nprint(json.dumps({k: res[k] for k in [\"effect_estimate\", \"effect_se\", \"hac_lags\", \"effect_ci_low\", \"effect_ci_high\",\n                                       \"beta_sub1\", \"beta_sub2\", \"chow_f_stat\", \"chow_p_value\",\n                                       \"baseline_metric\", \"model_metric\", \"conclusion\", \"stability_conclusion\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv out/exclusions.csv","description":"Write and run analysis script"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"663624f8-5406-4208-b3dc-f9f12d49ea6a","timestamp":"2026-10-30T04:50:48.661Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"57d525c8-df6d-44fe-ae13-daa297b274c1","keep":16,"tail":["9fffd4ded82b75468888e0816116fee2e3c380636dca1134f5ad3ea124429755","3e78d5a248fc75d29233244ddfc3f216b25223ddcbf7e9ea6e1e294f8dee9331"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"5e6d2271d8a1356cbde1a359588858652c23f38605a971102d56c5eca794c5e6"}
{"parentUuid":"f7858cf1-7c65-4ee9-a423-cd9103d95d94","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWuV8W377ovSdqXR55","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":4594,"cache_read_input_tokens":14707,"output_tokens":957,"output_tokens_details":{"thinking_tokens":244},"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":4594},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":3074,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpWuDFstGc6qJ4dvtpe","requestRef":"663624f8-5406-4208-b3dc-f9f12d49ea6a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"53e2b8fc-af41-4385-8a83-4ffa5031f265","timestamp":"2026-10-30T04:50:54.456Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"53e2b8fc-af41-4385-8a83-4ffa5031f265","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWuV8W377ovSdqXR55","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"Slopes look nearly identical across the subperiods, so the Chow rejection likely stems from the intercepts. Next I'll run a HAC Wald test on both the slope and intercept differences, plus residual variance by subperiod.\n\n","signature":"CAQSgAgKEQgTGAI4AUIJbmFycmF0aW9uEgwWaDCnqJMF440EbrQaDEVsLysq71n1qMy1SiIwc5lYW9sDBSYMkggfr2lD3f6jPkNzWsLMQV78O795wc4NDh+rTLFHjWt5jF4QJ5SeKpwHx7Bn6xVsR1BiRvIsPDVo+0ZCCHsM8FNQOwIoH8Yzp6N7qygSnd+8JTp2bwSUx6AIv6YacghK17H3LaQlRSBjObE+onjUN3pUg/WYr+EaVpqwNhKVzzn9qW10kTQBZ5aBrNvGrfeAbQqANjlpX3/xKdhAIioW06+BBC9vN8x7/stznExapSk7bZzst4y2d6WImISZfIPXq0Ot33TQydFIMejgjuBwoDaC9N8VhwOXeT0AIAT4WSA7w9IFdGbKudBadAS507Ea9HZnSeWwHmIT05TYHLwTuNH4hSSvOURZAJRauEpgX8jFrnClQ74ZQA4TtYMIqrYhoyBfKYyYYFUMUaOPwHYusJXOCfW0+gClNjafOeZEy5ZrWo8VIpxS9IjIO0XrgqXxzOrLKgnqEsHFV1UAG2wb7w+5QmggMKaiQJp4ZQyUiwvAmJKY0wSd+1q2zJQsdrDLV/cHy8x0SWo0wT6bmYcZpTm1hFXqSXUC5nM0TFnjCaiiXxqvB6+zMeHe4Fkl8Jx/ybaceVWxKeDs2uIUdf/he/zomBqfu6AsW7HKwJdfrdvdb00YHTSsYou5ieeoBVMaXdtu8ewr8kVaMPqN7fTNI68HXy7a5GMFOEGivDXCIVj18L495frb7oq6IbAFVSMv3dtHKCGxasDkSRIllK6tZv3Sh+Q+ZY/S6OLR1DQQxvT9tds+LsecxB/R9tFPKtJQhp3Aw3Vees1ti0t14vR/83L9nFI/nu9YYk6/0AZoJFVpSavNxFMe5SZpkvXjuRrUs8kkPCC5igzHCHLfeRv7XVvJx8KUU7a0ivVLba2WZREy/n27q6dBOpyKGKZn4Pb+5rkQt8oifutVnIPu0is93OrD8DeBZM7Iaqzx02lag4dhN34MR6ESw97HrehrHEGSlwhail9V+NivuBAFlcoTRpqRuZFSFqr36VkOd94WSoVJkfcn+X/ccmEdlnOe62SJFEU0ud+9nv0iCXfg3cQV+4o5mDhAnFpetLyp5LnqkYXhUX1v0wwF5CN2YO3YkgzUcwyMz/i6QWnbaP+jw50IwYi3PKv1V/xyfxZ9ny1aXFTMofrVzlvyeJ8XNkbOF7/00ns0X0HaVi8ymLgGuJAfVGeK3/9Jed955gWyTQuPYPfBestKJsz9hqOLnpk+qlhTNuEU+dE4/Verjt6MhNK+yxIqMa1ZwPKQr8RKqZr8P/VpXCihQyjciBbeITWe/DtfOJPcufobGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4594,"cache_read_input_tokens":14707,"output_tokens":957,"output_tokens_details":{"thinking_tokens":244},"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":4594},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2,"thinkingDisplay":"updates","apiBlockIndex":1,"requestId":"req_011CgXpWuDFstGc6qJ4dvtpe","requestRef":"663624f8-5406-4208-b3dc-f9f12d49ea6a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f7f1901e-afbe-428c-a8ba-57d6b71e66c1","timestamp":"2026-10-30T04:50:54.461Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"f7f1901e-afbe-428c-a8ba-57d6b71e66c1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpWuV8W377ovSdqXR55","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01JAW68c6rZrsiqXFhFvhhYQ","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\nadd='''\n# Supplementary: dummy-interaction model with HAC SEs (robust to the heteroskedasticity the classical Chow ignores)\nD = (df.index >= S2_START).astype(float)\nXi = pd.DataFrame({\"const\": 1.0, \"g\": df.g, \"D\": D, \"Dg\": D * df.g}, index=df.index)\ninter = sm.OLS(df.du, Xi).fit().get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\", use_correction=True)\nwald_slope_p = float(inter.pvalues[3]); wald_int_p = float(inter.pvalues[2])\nwald_joint = inter.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), scalar=True, use_f=True)\nwald_joint_p = float(wald_joint.pvalue)\nresvar1 = float(f1.ssr / (len(d1) - 2)); resvar2 = float(f2.ssr / (len(d2) - 2))\n'''\ns=s.replace(\"baseline = float(\", add+\"\\nbaseline = float(\",1)\ns=s.replace('    \"mean_du\": float(df.du.mean()),','''    \"hac_wald_slope_diff_p\": wald_slope_p, \"hac_wald_intercept_diff_p\": wald_int_p,\n    \"hac_wald_joint_p\": wald_joint_p, \"resid_var_sub1\": resvar1, \"resid_var_sub2\": resvar2,\n    \"mean_du\": float(df.du.mean()),''')\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cat out/results.json | tail -22","description":"Add HAC interaction test and rerun"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4594,"cache_read_input_tokens":14707,"output_tokens":957,"output_tokens_details":{"thinking_tokens":244},"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":4594},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpWuDFstGc6qJ4dvtpe","requestRef":"663624f8-5406-4208-b3dc-f9f12d49ea6a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f7c2e01b-0a8f-49f6-a29f-3073749576e9","timestamp":"2026-10-30T04:50:58.748Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"f7c2e01b-0a8f-49f6-a29f-3073749576e9","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01JAW68c6rZrsiqXFhFvhhYQ","type":"tool_result","content":"  \"random_seed\": null,\n  \"r_squared_full\": 0.4082508284562034,\n  \"effect_se_ols_classical\": 0.01996009291490984,\n  \"chow_df\": [\n    2,\n    236\n  ],\n  \"hac_lags_sub1\": 3,\n  \"hac_lags_sub2\": 4,\n  \"slope_se_sub1_hac\": 0.03921717107661775,\n  \"slope_se_sub2_hac\": 0.06879369233083425,\n  \"intercept_sub1\": 0.2542326539884382,\n  \"intercept_sub2\": 0.15168581347724602,\n  \"effect_se_hac_lags8\": 0.03729120927832668,\n  \"hac_wald_slope_diff_p\": 0.8549842111206841,\n  \"hac_wald_intercept_diff_p\": 0.25511124393301005,\n  \"hac_wald_joint_p\": 0.005229923279613946,\n  \"resid_var_sub1\": 0.07850312611325812,\n  \"resid_var_sub2\": 0.04827674526450526,\n  \"mean_du\": -0.008333333333333335,\n  \"mean_g\": 0.753502755065237\n}","is_error":false}]},"uuid":"5851ff07-0d93-4c69-8356-c972a60447fe","timestamp":"2026-10-30T04:50:59.611Z","toolUseResult":{"stdout":"  \"random_seed\": null,\n  \"r_squared_full\": 0.4082508284562034,\n  \"effect_se_ols_classical\": 0.01996009291490984,\n  \"chow_df\": [\n    2,\n    236\n  ],\n  \"hac_lags_sub1\": 3,\n  \"hac_lags_sub2\": 4,\n  \"slope_se_sub1_hac\": 0.03921717107661775,\n  \"slope_se_sub2_hac\": 0.06879369233083425,\n  \"intercept_sub1\": 0.2542326539884382,\n  \"intercept_sub2\": 0.15168581347724602,\n  \"effect_se_hac_lags8\": 0.03729120927832668,\n  \"hac_wald_slope_diff_p\": 0.8549842111206841,\n  \"hac_wald_intercept_diff_p\": 0.25511124393301005,\n  \"hac_wald_joint_p\": 0.005229923279613946,\n  \"resid_var_sub1\": 0.07850312611325812,\n  \"resid_var_sub2\": 0.04827674526450526,\n  \"mean_du\": -0.008333333333333335,\n  \"mean_g\": 0.753502755065237\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"f7c2e01b-0a8f-49f6-a29f-3073749576e9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"7b135026d2fbfb66effd9305c93d69b7c643c264a85603024228026597e4a427","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"thinking","thinking":"Slopes look nearly identical across the subperiods, so the Chow rejection likely stems from the intercepts. Next I'll run a HAC Wald test on both the slope and intercept differences, plus residual variance by subperiod.\n\n","signature":"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"},{"type":"tool_use","id":"toolu_01JAW68c6rZrsiqXFhFvhhYQ","name":"Bash","input":{"command":"~/wp29/venv/bin/python - <<'EOF'\nimport re\ns=open('out/analysis.py').read()\nadd='''\n# Supplementary: dummy-interaction model with HAC SEs (robust to the heteroskedasticity the classical Chow ignores)\nD = (df.index >= S2_START).astype(float)\nXi = pd.DataFrame({\"const\": 1.0, \"g\": df.g, \"D\": D, \"Dg\": D * df.g}, index=df.index)\ninter = sm.OLS(df.du, Xi).fit().get_robustcov_results(cov_type=\"HAC\", maxlags=L, kernel=\"bartlett\", use_correction=True)\nwald_slope_p = float(inter.pvalues[3]); wald_int_p = float(inter.pvalues[2])\nwald_joint = inter.wald_test(np.array([[0, 0, 1, 0], [0, 0, 0, 1]]), scalar=True, use_f=True)\nwald_joint_p = float(wald_joint.pvalue)\nresvar1 = float(f1.ssr / (len(d1) - 2)); resvar2 = float(f2.ssr / (len(d2) - 2))\n'''\ns=s.replace(\"baseline = float(\", add+\"\\nbaseline = float(\",1)\ns=s.replace('    \"mean_du\": float(df.du.mean()),','''    \"hac_wald_slope_diff_p\": wald_slope_p, \"hac_wald_intercept_diff_p\": wald_int_p,\n    \"hac_wald_joint_p\": wald_joint_p, \"resid_var_sub1\": resvar1, \"resid_var_sub2\": resvar2,\n    \"mean_du\": float(df.du.mean()),''')\nopen('out/analysis.py','w').write(s)\nEOF\n~/wp29/venv/bin/python out/analysis.py >/dev/null && cat out/results.json | tail -22","description":"Add HAC interaction test and rerun"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"68bcc637-de6c-4b9d-8dc6-5873355675c5","timestamp":"2026-10-30T04:50:59.613Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"663624f8-5406-4208-b3dc-f9f12d49ea6a","keep":18,"tail":["7b135026d2fbfb66effd9305c93d69b7c643c264a85603024228026597e4a427","186d03cafcb8d51038fea7e9423bde248b7c6f298cde9a27dd5faf7c9888d852"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"b472b362eb7d4d9b82ebce5e2da4e2a3287aed92f585a70e061f879e7d53017c"}
{"parentUuid":"5851ff07-0d93-4c69-8356-c972a60447fe","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpXiGTwBLWuifbexTci","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":1343,"cache_read_input_tokens":19301,"output_tokens":1505,"output_tokens_details":{"thinking_tokens":74},"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":1343},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":644,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpXhy7Tn6ncswp5VZH3","requestRef":"68bcc637-de6c-4b9d-8dc6-5873355675c5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"be243fa7-8bc4-48bf-b1a1-10b05057141a","timestamp":"2026-10-30T04:51:01.880Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"be243fa7-8bc4-48bf-b1a1-10b05057141a","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpXiGTwBLWuifbexTci","type":"message","role":"assistant","content":[{"type":"text","text":"Now P4: rerun from a clean state and run the consistency checks."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1343,"cache_read_input_tokens":19301,"output_tokens":1505,"output_tokens_details":{"thinking_tokens":74},"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":1343},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpXhy7Tn6ncswp5VZH3","requestRef":"68bcc637-de6c-4b9d-8dc6-5873355675c5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"60b0282b-cc19-455b-a7cc-9c2886b4fb06","timestamp":"2026-10-30T04:51:01.882Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"60b0282b-cc19-455b-a7cc-9c2886b4fb06","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpXiGTwBLWuifbexTci","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FmgWgHPjFGv1vB5om6AyJ4","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; md5 -q out/table1.csv > /tmp/t1; rm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp /tmp/r1.json out/results.json && echo IDENTICAL_JSON; [ \"$(md5 -q out/table1.csv)\" = \"$(cat /tmp/t1)\" ] && echo IDENTICAL_TABLE; ls out\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); e=pd.read_csv('out/exclusions.csv'); t=pd.read_csv('out/table1.csv')\nreq=\"sample_start sample_end n_sub1 n_sub2 baseline_metric model_metric effect_estimate intercept effect_se hac_lags effect_ci_low effect_ci_high beta_sub1 beta_sub2 chow_f_stat chow_p_value stability_conclusion conclusion task_id feasibility feasibility_reason data_issues n_input_rows n_analysed random_seed\".split()\nc={}\nc['all required keys present']=all(k in r for k in req)\nc['n_sub1+n_sub2==n_analysed==240']=r['n_sub1']+r['n_sub2']==r['n_analysed']==240\nc['n_sub1==96,n_sub2==144']=(r['n_sub1'],r['n_sub2'])==(96,144)\nc['dates']=(r['sample_start'],r['sample_end'])==('1960-01-01','2019-10-01')\nc['SE>0']=r['effect_se']>0\nc['CI contains estimate']=r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high']\nc['CI symmetric 1.96*SE']=abs((r['effect_ci_high']-r['effect_ci_low'])/2-1.959964*r['effect_se'])<1e-5\nc['model_metric<baseline_metric']=r['model_metric']<r['baseline_metric']\nc['R2 identity 1-(model/base)^2']=abs(1-(r['model_metric']/r['baseline_metric'])**2-r['r_squared_full'])<1e-10\nc['conclusion consistent with CI']=(r['conclusion']=='negative_effect')==(r['effect_ci_high']<0)\nc['stability consistent with p']=(r['stability_conclusion']=='unstable')==(r['chow_p_value']<0.05)\nc['chow df (2,236)']=r['chow_df']==[2,236]\nc['F>=0, 0<=p<=1']=r['chow_f_stat']>=0 and 0<=r['chow_p_value']<=1\nc['UNRATE ledger: 945-sum removed->241 quarters chain']=e.iloc[0].n_before==945 and all(e.n_before-e.n_removed==e.n_after)\nc['final n after ledger =240']=e.iloc[-1].n_after==240\nc['n_input_rows matches wc']=r['n_input_rows']=={'GDPC1.csv':319,'UNRATE.csv':945}\nc['table1 3 rows, full slope matches']=len(t)==3 and abs(t.slope[0]-r['effect_estimate'])<1e-12 and list(t.columns)==['period','n','intercept','slope','slope_se']\nc['magnitude plausible (|beta| 0.1-0.6, classic ~-0.3 with q/q growth)']=-0.6<r['effect_estimate']<-0.1\nc['HAC SE >= classical SE (positive autocorr)']=r['effect_se']>r['effect_se_ols_classical']\nfor k,v in c.items(): print(('PASS' if v else 'FAIL'),k)\nEOF","description":"Clean rerun, determinism and consistency checks"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1343,"cache_read_input_tokens":19301,"output_tokens":1505,"output_tokens_details":{"thinking_tokens":74},"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":1343},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpXhy7Tn6ncswp5VZH3","requestRef":"68bcc637-de6c-4b9d-8dc6-5873355675c5","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1a2d85e3-5391-4526-b18c-4e9468423ca9","timestamp":"2026-10-30T04:51:12.543Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"1a2d85e3-5391-4526-b18c-4e9468423ca9","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"1a2d85e3-5391-4526-b18c-4e9468423ca9","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FmgWgHPjFGv1vB5om6AyJ4","type":"tool_result","content":"IDENTICAL_JSON\nIDENTICAL_TABLE\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv\nPASS all required keys present\nPASS n_sub1+n_sub2==n_analysed==240\nPASS n_sub1==96,n_sub2==144\nPASS dates\nPASS SE>0\nPASS CI contains estimate\nPASS CI symmetric 1.96*SE\nPASS model_metric<baseline_metric\nPASS R2 identity 1-(model/base)^2\nPASS conclusion consistent with CI\nPASS stability consistent with p\nPASS chow df (2,236)\nPASS F>=0, 0<=p<=1\nPASS UNRATE ledger: 945-sum removed->241 quarters chain\nPASS final n after ledger =240\nPASS n_input_rows matches wc\nPASS table1 3 rows, full slope matches\nPASS magnitude plausible (|beta| 0.1-0.6, classic ~-0.3 with q/q growth)\nPASS HAC SE >= classical SE (positive autocorr)","is_error":false}]},"uuid":"d3311d44-8d4e-49d4-9ead-023df4004d94","timestamp":"2026-10-30T04:51:13.569Z","toolUseResult":{"stdout":"IDENTICAL_JSON\nIDENTICAL_TABLE\nanalysis.py\nexclusions.csv\nfigure1.png\nresults.json\nstate\ntable1.csv\nPASS all required keys present\nPASS n_sub1+n_sub2==n_analysed==240\nPASS n_sub1==96,n_sub2==144\nPASS dates\nPASS SE>0\nPASS CI contains estimate\nPASS CI symmetric 1.96*SE\nPASS model_metric<baseline_metric\nPASS R2 identity 1-(model/base)^2\nPASS conclusion consistent with CI\nPASS stability consistent with p\nPASS chow df (2,236)\nPASS F>=0, 0<=p<=1\nPASS UNRATE ledger: 945-sum removed->241 quarters chain\nPASS final n after ledger =240\nPASS n_input_rows matches wc\nPASS table1 3 rows, full slope matches\nPASS magnitude plausible (|beta| 0.1-0.6, classic ~-0.3 with q/q growth)\nPASS HAC SE >= classical SE (positive autocorr)","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"1a2d85e3-5391-4526-b18c-4e9468423ca9","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"beaee2e6abcb04820eb712879c4c8fe64cda35a2fc304c25286f1da99ccf05f7","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Now P4: rerun from a clean state and run the consistency checks."},{"type":"tool_use","id":"toolu_01FmgWgHPjFGv1vB5om6AyJ4","name":"Bash","input":{"command":"cp out/results.json /tmp/r1.json; md5 -q out/table1.csv > /tmp/t1; rm -f out/results.json out/table1.csv out/figure1.png out/exclusions.csv\n~/wp29/venv/bin/python out/analysis.py >/dev/null; cmp /tmp/r1.json out/results.json && echo IDENTICAL_JSON; [ \"$(md5 -q out/table1.csv)\" = \"$(cat /tmp/t1)\" ] && echo IDENTICAL_TABLE; ls out\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); e=pd.read_csv('out/exclusions.csv'); t=pd.read_csv('out/table1.csv')\nreq=\"sample_start sample_end n_sub1 n_sub2 baseline_metric model_metric effect_estimate intercept effect_se hac_lags effect_ci_low effect_ci_high beta_sub1 beta_sub2 chow_f_stat chow_p_value stability_conclusion conclusion task_id feasibility feasibility_reason data_issues n_input_rows n_analysed random_seed\".split()\nc={}\nc['all required keys present']=all(k in r for k in req)\nc['n_sub1+n_sub2==n_analysed==240']=r['n_sub1']+r['n_sub2']==r['n_analysed']==240\nc['n_sub1==96,n_sub2==144']=(r['n_sub1'],r['n_sub2'])==(96,144)\nc['dates']=(r['sample_start'],r['sample_end'])==('1960-01-01','2019-10-01')\nc['SE>0']=r['effect_se']>0\nc['CI contains estimate']=r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high']\nc['CI symmetric 1.96*SE']=abs((r['effect_ci_high']-r['effect_ci_low'])/2-1.959964*r['effect_se'])<1e-5\nc['model_metric<baseline_metric']=r['model_metric']<r['baseline_metric']\nc['R2 identity 1-(model/base)^2']=abs(1-(r['model_metric']/r['baseline_metric'])**2-r['r_squared_full'])<1e-10\nc['conclusion consistent with CI']=(r['conclusion']=='negative_effect')==(r['effect_ci_high']<0)\nc['stability consistent with p']=(r['stability_conclusion']=='unstable')==(r['chow_p_value']<0.05)\nc['chow df (2,236)']=r['chow_df']==[2,236]\nc['F>=0, 0<=p<=1']=r['chow_f_stat']>=0 and 0<=r['chow_p_value']<=1\nc['UNRATE ledger: 945-sum removed->241 quarters chain']=e.iloc[0].n_before==945 and all(e.n_before-e.n_removed==e.n_after)\nc['final n after ledger =240']=e.iloc[-1].n_after==240\nc['n_input_rows matches wc']=r['n_input_rows']=={'GDPC1.csv':319,'UNRATE.csv':945}\nc['table1 3 rows, full slope matches']=len(t)==3 and abs(t.slope[0]-r['effect_estimate'])<1e-12 and list(t.columns)==['period','n','intercept','slope','slope_se']\nc['magnitude plausible (|beta| 0.1-0.6, classic ~-0.3 with q/q growth)']=-0.6<r['effect_estimate']<-0.1\nc['HAC SE >= classical SE (positive autocorr)']=r['effect_se']>r['effect_se_ols_classical']\nfor k,v in c.items(): print(('PASS' if v else 'FAIL'),k)\nEOF","description":"Clean rerun, determinism and consistency checks"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"8ab1cd05-aab3-44ae-925f-19af813e691a","timestamp":"2026-10-30T04:51:13.571Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"68bcc637-de6c-4b9d-8dc6-5873355675c5","keep":20,"tail":["beaee2e6abcb04820eb712879c4c8fe64cda35a2fc304c25286f1da99ccf05f7","6894cf479113c0fa36d233e981af57de79bdd5d1f8fe1a3b7a617acda4b78c34"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9f0a8d24feffdd010972c9a038f8d52b3330337c05f633911bd7e080c0aab1ec"}
{"type":"tools-used","tools":["Bash","Read"],"sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"d3311d44-8d4e-49d4-9ead-023df4004d94","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYjxh7KxiVjUg78Dm6","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UbqLPmUk8ugwAtAYPr6Z8x","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0172/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":1882,"cache_read_input_tokens":20644,"output_tokens":80,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1882},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpYjfbPJji2YtnLdTht","requestRef":"8ab1cd05-aab3-44ae-925f-19af813e691a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f239d990-c9f4-40ca-80a6-8f307f0b9c73","timestamp":"2026-10-30T04:51:15.291Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"f239d990-c9f4-40ca-80a6-8f307f0b9c73","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UbqLPmUk8ugwAtAYPr6Z8x","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"f675de9c-b17c-4bbc-85a1-83b8f6c7e7bc","timestamp":"2026-10-30T04:51:15.323Z","toolUseResult":{"type":"image","file":{"base64":"iVBORw0KGgoAAAANSUhEUgAABBoAAALuCAYAAAAAD3VqAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAXEgAAFxIBZ5/SUgABAABJREFUeJzs3Qd4U9X7B/C3u7SUDWW27FWWIEtkg6AIioIgUxEnCrgXIiiigjhwoCLiAAcuZKnIEmQP2XuWWXaBQvf9P9/T/8nvNk3StCRp0n4/z3MpTW6Tm5ubm3ve8573+BmGYQgRERERERERkQv4u+JBiIiIiIiIiIgYaCAiIiIiIiIil2JGAxERERERERG5DAMNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DAMNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DAMNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DAMNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DAMNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DAMNRF7u8OHD4ufnpxb8n2wbM2aM2kft2rXjLiKiAuPs2bNSvHhxKV26tFy5csXlj8/vICJyhdjYWAkJCZHq1atLcnIyd2oBwEADkZslJibKZ599JrfffrtERUVJoUKFpGjRolKnTh156KGHZOnSpfm64X/ffffl9abkOzrwhH3s7PuAxZ6FCxdKv3791Jd/eHi4OkYrV64sLVq0kMcee0y+//57OXPmTI638+rVq/LHH3/IuHHj5K677pLo6Ogcbbs2Z84c6d69u5QtW1aCg4OlXLlycscdd6jHdtb+/fvl6aeflnr16qnPH15n1apV5c4775RPPvnE4d8eOHBAHn74YalSpYqEhoaqBl2XLl3kl19+ydHzv/jii9K0aVP193gdeD0333yzvP7663Lq1KlsH2PFihXywQcfyODBg9XrCAwMdGlwLSkpSebOnSuPP/643HjjjVKsWDEJCgpS29u+fXv58MMP1XuaHcMwZNq0adK6dWspUaKEOp5q1qwpTz31lMTFxdn9u9TUVFm8eLFMnDhR+vbtq/7G398/x+cR7Kc+ffpIxYoV1UVtmTJlpHPnzuo4dlZ8fLxMmjRJOnXqJBUqVFCPg9fSoEEDefLJJ2Xz5s2SGxcuXJDy5cvn6nNgz9ixY+XixYvy3HPPSeHChR2uu3LlShk+fLg0atRIva94fxGkaNiwoTrGFy1apN6/gmzZsmWW9ye7Bet60n///SePPvqo1KpVS73XRYoUUZ8TfF5ycnzbsmnTJhkwYIDlc4PzbM+ePWXJkiXZ/u2lS5fkjTfeUOcNnF/DwsLUdo0YMUKOHTsmBREa0u+++64652Of4P2qX7++vPrqq3L58uXrfnw8Bs4feEw8Np4Dz4XzljONeJyL8Z2IYwnnaJzfcM7+4osvHJ4D8B3xzDPPqO+EatWqqWMQ32c4r916660yffp0dS63BdfA999/v/pO/fjjj6/r9ZOPMIjIbRYuXGhUrFgRZ2zLUqRIESMkJCTTbbfeeqtx9uxZm49x6NAhy3r4v6949dVX1TYPHjzYo8/Xtm1bI7/TxwNes7P7xdbpPjEx0ejdu3emY9Hf398oUaKEERQUlOl2Z57L2tKlSzM9Rk4fLzU11ejfv7/lb/z8/IzixYsbAQEBltueeOKJbB/nvffey/SZCwsLMwoXLmz5vWjRonb/dv78+Wp98+cX+0j/fv/99xvp6ekOX8MzzzxjBAYGWv4G24/XYX6c8PBw4/3333f4OuztS1cd8506dcr0uNhm7BvzbdWrVzf27dtn9zFwTHXp0iXTY5j3dcmSJY0NGzZke66zXpw9jzz//POZ/q5YsWKZjuWePXsaKSkpDh9jxowZ6jPg6HFwLA4ZMsS4du2akRN4Hdf7uTLbs2eP2selS5c2EhIS7K538uRJ45ZbbsnyWcdxaP1Zv+GGGzK9x776HZRb5vMW9k9kZKTdZeXKlR7ZJpxjnn322UznjIiICKNQoUKW3xs2bJjrx586dWqmcxQ+9zjGnTlOd+3aZVSuXNmyLs61+LyYz5lLliwxCpLz58+rz5F5n5i/R6Kjo43Dhw/n+vHxt+Z9jsc2f8fhubEN9uAcjHOxXh/naPP7j3N4UlKSzb+NiYnJdL7AcRgaGprptsaNGxunTp2y+fdHjhxR5xycYy9cuJDrfUC+gYEGIjf54YcfLCfuChUqGF988UWmEz++nEeOHGlZBxfwcXFxWR7HVy/yGGjw/kADGun6PjSaNm/ebGmEpaWlGbt37zY+/PBD4+abbzbGjBmTqwt2XKh37NhRXSR///33RtmyZZ3e9hdeeMGyfSNGjLAE465cuWK88847ls/OBx98YPcxJk2aZGnwvvjii8bBgwct9+Hz+OeffxpPP/20zb/FuggA4O9btWqlGnVw+fJlY/To0ZZte/vtt23+PfbhHXfcYVmva9euxj///KOCD4ALOTz/TTfdZFkH+8keNCqaNWtmPPLII6phoBv0rgo04HFwAYz3etOmTWr79X7Ca9QXyjhX2WtgP/roo2odXEh+9NFHlovV9evXG7Vr11b34RiIj4/P8rc4v+GiFccb3u+vv/7aaNSokdOBhk8//dSyH/v27WscPXrUEvz46quvLO/lk08+afcxcFzpx8D2zpo1Sx1vurG3ceNGtS26Eda6dWv1+M7Ae42/Mb/f1xtoePjhh9XjIJhlD45jfAfp9wXv0dq1ay3HIV7XgQMH1OeoSpUqar3ffvvN57+DXBFowP+9gT5Xo0E4YcIEFTjSzpw5Y/zyyy/G2LFjc/XYq1atsgRv77zzTsvnBudbfXxh+fHHH7P87dWrV42qVatagojYDv0dgmAVOlF0sEE/bkFgft3Yb/pcis6ncuXKqfvq169v+QzmBPYv/haPgcf6+++/1e14Dlx34hyK+2677Tabf3/x4kXL9zDOcTg3A87VOGfrwCPOE7bgnPX5558bO3bsUO+/dvz4cXUM6mAYvp/s0d+LEydOzPHrJ9/CQAORG+zcudNyUY4vhNOnTzvsMQ0ODlbrokFmzVcv8hho8O5Aw6VLlyw9ILiYzI75gsJZti6i0JB1Zttx8ay3Dxe/jnqv0Xtmq+G6detWy0XTzz//nOPtHzBggKVhbKvn5aGHHrJcTNrqPcJFl973CJrYgwvEQYMGWdb96aefnNqfunfcVYGGFStWOOztR6BIb+O3336b5X4EYnSD5c0338xyPxqzugd21KhRNveDdXYIXpszgQZsN3qYdW+avrA3mzJliiXohG2xhl5XfZHcoUMHhxkCCPTofTFs2DAjO/i8RUVFqXM9LtBdEWjAY+psEQQJbUEQRAdr0ABZtmxZtvsR2zRnzhyf/w7KL4GGP/74wxIkWr16tcsfH4E9fa2SnJyc5X4d0EQPuvU5CIFova9mz56d5W8RkNTnfASzC4JFixZZ9gnOmbYCO/p+dEDlFP5G/z0ey9p3331nuR/bYg3nXtyHc7E58K6NHz9e3Y9zuQ6u5wQC+vr57QWX8B2H+2vUqOEwI5B8HwMNRG5w1113qZMoGkroFc7Oa6+9Zjkxz5s3L9N92V3koQGoo8PoUdAXIs4MJTBfUFmz/nt8YSFCXqpUKfW6EAlHz6e9ns3sAg2IvKOHt0yZMpYUbfSUdu/eXUXVc5qS7Oj1osGAL9+BAweq9FK8BlzwozcA+27BggUOezebNGli8/6aNWtavpDRS2CvIYoGq7cFGtatW2e53d7rdwdnAw04PvT22UtPPnfunGUd9H5bQ6+2o0CFI+jF1o1iez2F5s/ml19+mek+ZCfpv2/fvn22F1NoENapU0etj32UXXq/OwIN2UHjXfeWDR8+PMv9r7zyiqXXVWcBWLvvvvssr9EZzgYa1qxZY3kvZs6caXMdNJJ0Sret9xSfc9yHYQgIdGUHDSesj+BEdhfkOtMDmTDgikADehXxGHXr1rW7zieffGJ5rm+++cbpxzYHaqy/g5ASjfcfDU98F+Ac3qdPH5Wl5wjOkdjvSOvW6dY45yNDx1bgB++BzhzZtm2b3QYRFjR47TXocK7PSaDU2wINLVq0UNuCDEhXw353dA4FBKf0OtZDIPAdrhuM2WWVIaMoNwFrR6ZPn57pfIKMAWwTvuNxfOGz8frrr+f4euJ64DoD24RMD3vn/Xbt2ql12rRpk+PHRxaV/l6xBc+pM5MQwLaGgKce9mcLMvZ0AFOfr3Li999/txwvOC/b+77T3yUFbVhNQcNikEQudvLkSZk9e7b6/7333qsK7WQHxcUiIiLU/3NSIOf8+fOqWNnvv/+uiuz8+++/qoCfq6E4G4qpofgeivyg0NDu3btVIaLbbrtN0tLScvR4Q4YMUcWr/vzzTzl9+rQqsJeSkqIK5ulidM4Ux3PWrFmzVLHDb7/9VrZu3aqeC4X08F5h3+E1oLiRNRQ70gW4UGzN7Pjx47J37171f7z+f/75J8vf6yJaHTp0EG/mjcW6jhw5Yvl/3bp1ba6D4lUo9KcLWpolJCRYijUOHDgwx8+Pz9K1a9fU/1HgyhYUzERRV1vPj4JY+u9R/MtRMU5A8bUXXnjB8trnzZsn3gaFGVE8EGx95v/++2/1s02bNqrYpi16X+I17tmzx6PHS0BAgCpQZ+v9Wrt2rWzcuFH9f9iwYVKqVKlsn/OVV15R+yQ9Pd1hQVGcGz799FOpXbu2vPTSS+IqOH8CCrjZ89FHH6mfNWrUUIX+nIXXZcuOHTtUQczJkyerczfg548//ijNmzeXLVu22P07FDDFZwHnU5yDcSzhnI99g/fMurgq3gP8DdgqSGi+zdH9+E5EsTtftG/fPlmzZk2uz2PZ0Z9Z6Nq1q811ULBWX59Yf270587eZw70ORLnZBQjdRd8BlGkF58LXKdg2blzp/qc3nTTTaoQqyfofYr9ae+8r8+D5u8ZZ6AYr96H9r6X8Jz6vbR+v3DOxcwPjv4ehSX1OcX6750txqu3AwWX7X3fNWvWLNN5jPInBhqIXAxVqHHhCXfffbdTf4MT+y233GI5Sdur2Gt29OhRdQGwatUqVXV49erV6kLW1XDhiAYQFlxQ4ssaje7Ro0er+zFrxtdff+304+GLFY0wXMi+/fbbcu7cOVU9GRchmKbtr7/+UlX1UcXYVVBVHYEEPDemf8P24/lOnDihKrbjgheVmjG7gRkqs+Nv8X5aVxfXs4Wg4rKtC1003nERbQ5YeBNcwKMyOGAfrF+/XryVo0CWvm/btm2Zbl+3bp1qzECTJk3Ue4+ZKlBpH4EtzCCB6tfbt2+3+bjm23VjxxZ9HxpSZvp4KFmypLRt29aJVylqBgx9YepMpXdPwz5GcBNwzrGm94Ez+8u8fl4cL9bvu3l/O3veRqDphhtuyPL3ZmhEDB06VP3/888/VxfYrqIv6PUFuzUEa9HQAhz72QW7nIHGLoIWOF/gHIrzKRpWmKEAMw888cQTWf4G53fMGoNzImbwmD9/vvpbrI/ZOxAIwIwn/fv3zxKo0OdO6/2LYDcaXAgg4PyNYI7+3rU+R3vj+ddZOG8BXiMCPAjEo3MB30t6Nhfs89xOfa0/BwjY6qCtrQCdvraw95l15jNn6zztKpgVaeTIkdKrVy/VkMZ1Co6vKVOmqM8cglsPPPCAuBuuZ3QniTPnQRyzu3btcvrxsa4+zp15fGyLPmfn5ntNnz+yg/MAHhsz3+BaSp8r8H1rDwKTYKuThvIPBhqIXMz8RawvQp2BRq0+YZt752zBCR0RenzpoPcQF5yYWsgd0ChHj8D48eMtvXxoXKNxiikLwda0Wsh2QIbwV199lel2BEYAF0v4UkKvtIZGGQIu+BtXvh5cZCMro1WrVpbGNeDiGAETvDZAL50ZgiG6kWh9oat/x8WNo/vRGMHibXCR+vLLL1uyM9BYQc8TGkXoYUTvrjMBL3cx7zN7wQBcROHCDhA0MtPZJjqjBZ8TBJIw3Swu2nFhjuOscePGKvBlTT+evqC3Bw0nW8+vzwM5OQfgc6V7gJB5422ef/559RPTXvbu3TtLY1JP2ab3iS3m+6z3mbuPFzRO0UOsp69EY9f6/UKA01HvrL3zNv7euqELo0aNUgHHBx980GHmQU4dPHjQMuUspqZ05XeRI5GRkSqwgGkMAZlhOJdjCmfAd5F1hhR6mg8dOqQ+d+i9RAaZzpjAtqPXFO8fgg36nKTpbDDrQAJ6+RHEwfcgpvRDY8o85SgeS3/XXE+gAd9xmIbW1jJ16tQs62MaVmenxrS1WNPnMZyHkA3To0cPNQUs9gXWx/GMrBUE/nLTM6w/g44+s+b7rT+z+nOHY83elIjmz6MrP/PWPf04Fn744QepVKmSug3n7UceecSSJfrbb79lCajje+B63i/r6WnNr88d58Hrffyc/j2CNbgmtQWfQb0fkPGCYxDXWfhsI2sV1xGO6HMSrjWcmY6TfBMDDUQuphs+uuHsLHOqrvkxrOFCDhesuJjDRRAu0jB/srugN8DWsALdgM9powiNFMBFck6HXLhLt27d1E9khVhvk70eNd1bhrnnMe84Lqb0hb+v9KbhwhXBFR3swXCYadOmqXna0ZDAMYnAAxo1noYGhu79xfzstphvxwWRmTlNFtk4aNAgPV43iHGRhB5CZD089NBDKgPCTDeazYEpW/T91vOi689wTs4B5vOAo3NAXpgwYYIaOgXIRDIHCK1fv6N9Zr7PFXPJawgYoRGst89WkOzDDz/MdJyY/6/3Nxp09oYNOHq/0PCzTs3G8fb++++rgCa2yZXMDQZ7vYbmY8j6/cqtp59+2mbgDWnYOgvNutcawyoAvc22elHRSEHQGXCMIQikIdCL9wMB702bNmU5v+I8oYMR5nO0DkQge+l6hhPiPY2Li7O5mANVGr6LcRzmdrH1/IBsPzTi8FrRy4x9hAYgvv8xbBL/v+eee7LtpLB2vec5BI0AgaTvvvsuy99hu8wBfOvztCshqGfrs4vMNXxHAwIR1tka1/N+IRvVk+fB6318V24fPu96P5gzUHFNhCFS2Q1X0udOnKvN106UvzDQQORDEJFHjz8uutAY/Omnn1yaimtLTExMli9TTWcdmFPzstOxY0d18YdURgRM0LDFRYq74cIQX34tW7ZUjT/0xOlovO7BRK+IdWNBX8Six0aPScb2oicE9TewDxBMQG+Ovvj1lUADIO0WQauff/5ZjU1H76C+QMDFLN4f9FR4umYALkKGDx+u/o8eVIwvRyAEgQGkxiJ4gJ4qXTPA+gLT3PuJ4w3p2uYUc6Rt4jXhteJCx14wI6+gR9ZbICPkxRdfVP8fNGiQCsx4G3ye9XAuZHrdfvvtqmGKnjJkvqCRhtegjxfISUAhp+8Znhe9ejgOEeDQAVZXMV+YuyqI4Ayd7mxr/+uAh/n7APtBB6KR+WAPagAB9pc5oID9Zmt4irn+ja1gsP4/ermv5zsS5/H/L5yeZdHZbGYffPCBOt5yu1jT5zH8xHcNhk7omgc4frHfcO7G9xgahO+++654EhrxGIamG5joxUaAS2eU4HoFtZBwfOhtdgc8vr2MITxnu3bt1P83bNiQ6T5kP1zP+2WvE6YgQHBX7wcE9ZBdg2sIHAO4brQeimrNfN5ioCH/YqCByMXMPZg56ZVEj4WtxzB76qmnVOo3euCRjuquL20zXQTKFn3xkJMU+2rVqskXX3yhghfIIECPOdLFMT60T58+qjijvRTM3NL1K1577TXV04ULYTQw8ZyIxpuzSax7qfCFqceu6otXc2+a+ae+HxkAumfJ2wMNgH2BcelIwUXPPnqdMP4ZtTJ0AAbFO11ZoNMZGNKC54WZM2eqC2z0nERHR6seYjR69Lhb9ETbO25RCNTWUBxcZOI+QDqyOZtF/z1euyP6fuvPif4M5zQzQZ8HrF/P9RgxYoTd9G9ngpsYO4+GDo4RBJ5sMb9+R/vMfJ+jc0tuPPbYY5YLf9R6QW0ONDKRUYAec6R5655z632s3y8EGm0NgXDmvG0OJuBcg55nZH05W/MhJ/A9oNlrSJu/R3ISDL7e7wNdG0U/r/5cOUrV1j3OoAO6mnUgAY0anMexLci8QjABwURzfSNfCfTmZH/j+LbVC43gsP4Oymnxvus9z6HoKwK2OCfjuxMdIPg+xfuBoYp4n5ANpT8brjyvmeE5HQWU9LFnfWy5mrvPg9f7+O7aPlyLVq9eXV1DIKiLTBZ8byDIZI8548F8PqP8hYEGIhczj+8198xkBz38gAY4vrRt0VXDFyxYkO34N2+GLyA0xPEaEFxAgw8RbfScoiAe0mVdlWKJC0/M/oEsEIynxr7DY6P3B1kOaDzrqt5gHeRAT5HuDdEXutazSVgHGvRPfPGaL6BdBRdx4Ey1an3BoP/GGWgw4OIdNQx0LzEuIq3TTt0N24H6H8hGwHGCYBE+G+i5Qjru8uXLLa9PzyagmRs1ugfQ0ecVr88cFNCBCTQ8He1n1Lcwr2/9uPpz7Qwcl3qYijOz1TgLmSn20r8dwew52O/4DPXs2VO9/7oxaQ0Xo/qCVO8TW8z3uaOuDC5yUUAPY+URJMS5BZks48aNU+8FUqUBx5E53Ve/X+iBz0mRSv3+4nl0IxA1GRAIQyMMP3HRbb1oeD7r25xhDiLYq6Zv/i7KyXHobfT5Fe8rghgIgmK/oe4Kjkec25Cphn2IQCnOCRi2kh8CDTk9j+V06IT+DDr6zJrvt/WZxXNjuAw+e/iuRIYDCoZiKAdqayDQqWdtsj5P5zfm/eOO8+D1Pn5O/x51g+xltNqDgBiCPvg82qrfZSv4mdMhhuQ7GGggcjFc2OhMA+vpuuzRlbsBjSh7F/Ovv/66KsyIxjBO5o6mwtSP4ShSbB4L62lIm0OqJRovSIXHxTnS4dGwR8+UdZGl68lmwMUXGhjoecFYYusIfXY99dY9augtw3bq2zFGFlkZSB3EMAR3T2upMzCyuzg0r+Oo+rMjeI80V05HmBMYB4zjBCnxGLKCAAOGfCANXqfCIjBihvoLzjAHlszF2Mxjye0VFzTfh0at9RAhQPDCesYSR9kDent0cMsVEDCyl/7taFvQUEDDDsE/jLO3d17S9D5wZn+Z13c19KSiwCeeC+cWNDpRZBANf3vHi36/cnLexhAq3YA3v184ByA4g+AVgmM6CGNetDfffNNym/UUuo6YP8/2shWQyaEboO7IFHP2PK+DO46m0TXfZz37gf5OxP7Ee2nr/Go+RyMggUAE3m97M3K4i6PsIWcWazk9j+V0ZhF9nkNPv730dWSkYNiao88sjl9kE+G7EcFSFLHEOQPvHWYS0Zkm1p87V0FmkaOCgvp70PrYwuxd1/N+vfPOO5keDw1m/T46cx7EtaKjAJI1rKuvL515fGyLeYhCTr/XclIYV0PgTz+nnnnLFvN5K7fXJ+T9GGggcjFc3OkiiWgcOdM4e++99ywFdxBAcAQpuXpGh8cff1yNCbVFpyjii9Qe3evjDTCkAhfdOpXdPL/39dCvH19k9lJ3Fy1a5PAx9EXsgQMH1HahEBsuAM1ReHNWg25Yuqs3DSnhkN2c5DhG9Dr6b3LK3Jvh7nogOYVGnp5+C7UDzJBNomdwcDR9mP579NyY309MHatTO+1Vc0cASz+2np7WPHZZZ5HgM5tdIw9jmnXBQFy06xld8sKvv/6qMhl0kAGZRubaBtmNs0eg0F5art6XyChwZdaGM5DBoT/r1scLhuFgzDEggGseEmEPsiT0+6qHGXkKeox14MdRsVaMmQYEQWfMmOH04+dk+IgjyBrRjWUMT7JHvy9oROn3wXwO0rNc4PxqPXTN/H/z/fgMO3PcupKj7CFnFltBMwRMnD2P6XoJztKfWUfnOXyH6OsT6/OcM/Rxh8+YuzIaEMjQ071aw2dUT6GojyNzEOV63i9bmUh6n2L4lr3zvt7X5u8ZZyBrCseE+TFsvV48t633C/sfHSOO/h4BPb0vc/N+41jRQStHwy50bS5cM7u6hg15EYOIXG779u1GoUKF8A1j1K9f3zhz5ozddRcsWGAEBwerddu3b2+kp6dnuv/QoUPqPiz4vzZu3DjL7ZMmTcryuCtWrLDcv2bNmiz3x8XFGaVKlbKsY+3VV19Vt7dt29buti9dutTu39uTmJjo8P6hQ4eqx2vQoIHTj+loe+fNm6du9/PzM06dOpXl744ePWqUKFHC5j42K1++vLq/efPm6ueTTz6Z6f6ZM2dmuh/LyZMnDXf47rvvLM+B/+dmPRyTGzZsyPa5Jk+ebHmMr7/++rq3PTo6Wj0W3q/rkZCQYNnXvXr1srnOa6+9pu4PCwszjh8/nuX+2NhYy+e0b9++We4fMGCAuq9cuXLGxYsXs9z/6KOPqvsjIiKM8+fP2z0msbz44ot2X0taWpoxePBgy7rYbmfov3H0Gc2pX3/91QgKClKP27NnTyM5Odnpv929e7cREBCg/vbtt9/Ocj8+W3p/jxo1yqnHxGvD+nit1yM1NdW488471WM1a9Ysy3kWFi1aZPj7+6t1OnToYFy9etXu433xxReW9wvr5pT+2+v5HOB1ZPcYON/iO0gfp//880+2+2ns2LHGnDlzsv0OsvfZnj59eqbbcSzgdhxX27Zty/J3ly9fNqpUqaLWuf32220+9ksvvaTub9KkiREYGGiULFky03uI4zQ8PNwIDQ01GjZsqNZ96623jNwwf6/h/3ltyJAhalvwHYTznrV169ap7zes88ILL+T48W+++Wb1t9hvtj7vt956q7of7y+Oj5xYvXq15Xwyd+5cw9VwrOn3CtdPOJc6Wmft2rWGu+E8op/vxx9/zHI/rsf0/TiP5JQ+9+A9t3Vth+fUj49tsYZzr/5etPV51p9XnMv37NmT6b6UlJRst++VV16xPD+ub+0ZNGiQWqdPnz7ZPib5LgYaiNwEDU990V2xYkVj2rRpxoULFyz34wSOxioumrBO1apVbTZMHV3k4UJK32d9YY8vXH3hV6tWLWP9+vXqwgy34+KpTp06mRrYngo0IJDQu3dv4+eff1bBDvPF5pQpUyxBF0cNM1vsbS8aiLgAxX1t2rSxfHHigunPP/80qlWrpi5as7uQ7t+/v2UdWxdNJ06cyHQ/9q8z+836otwZ+LLXjWxcWL/zzjvG6dOnLfdjv+K2kJAQS/DD+gIRF/x6n2C/o5GoL9yxLn4fOXKk5RjGsXTlypUcbysa4Ahq6KVSpUrq8Z599tlMt+P9t4aLqDfeeMPYsWOHkZSUpG7Dzz/++MO44YYb1OPg8czHkRm2V38GGjVqlOkiE/9HMAv3ofG7c+fOLH9/8OBBy7HTunVrY+/evZbHRWNMX9zbalQDPmtoOOn3Ghfsy5cvt7wXuKj/66+/jFatWlnW6dSpk92LOewj8z5DcAR/c9NNN2W63VbQwxmzZ8+2NAruvvtupy4q7QVf8Dn+5JNPLO8bglp169ZV95UtW9aIj4+3+ff4vJpfC16bDgSZb7cV+Dlw4IBqkG7cuNG4du2a5T34999/VTAAj1OsWDGb77X1RTaW2rVrG7NmzcrUuNu0aZNx3333Wd57nNsRrMyLQMNzzz2nHqNr164O19u/f78KlunG/mOPPaYap+ZzAs57H3/8sVG9enW13m+//eayQMOlS5csgQTsLzQ+dINw69atlvcY56vNmzfbfOy///470/kVx6e1Ll26ZFont41Kbws0HDt2zChatKjano4dO1qOX+xD7JeoqCh1X5kyZTJ9D1gH6/D+2LJy5UrLef6uu+5Szwfnzp2zfJ7tNZrh/fffV9c75kC+/g4qXLiw+tuHHnrI7uvLbvsc0UEENJpxbKPRqj+POAd89tln6jsS69xxxx2Gp+jgDN43nEP08Y6Gv+60QADQVuDGHBixdfzhvKyDhxUqVLAEE/AceK4iRYpYvm9swbkT52Csg3Oy7nDAuRrnbH0Nhvfe2ldffWV0797d+OWXXzJ97+K5t2zZYjz44IOWbcf3mq2ArobrUqyH56T8i4EGIjdCg0h/qegFXzz6i08vt9xyi80LBGcu8vBlru9Ho8wMDWndcNBfxvq5a9SoYXz//fceDzSYe26x4EIEF//m29DDktNGraPtRUPa+jn1fkBWB3rvsruQRqBIr4OLMlsNJTRM9Dq4mHdXoEEHNszZE1hwgaEvMvSCdWwFsHbt2mVpLOkFQS8En/RFp14QBENjPzd04yO7xVaPNRo7+n5sq/W21atXz2HDR79OXIyZ33t98at/d9TTNn/+fPW5MX9+zdtw//33O7yYwkWhOWCjjx+8Ft17rpd7773XZo+lvc+OvSU3F+ygG4P6cxEZGWl3QbaDvR50c4MP5x/0pOvfEdRzlEmjGx3ZLbY+5//991+mdYoXL57p/IcGGYIQ2cHFtPmchGMPj6UvwPXSuHFjFdzIDVcEGvTrRaDMXuBGQ0YPGqnm7cfxh+PQ+nXhnGF+XdcbaNCBTfPnEOdf87kKQYaffvrJ7mMju8S8nQiKWDMH3vHYOe1999ZAAyBAaT4mcR7S2UE6yGAvsOJMQ37q1KmWTg8seC7z94Oj4xQNeHvvKx7jiSeesJlpkJPts0c3yvG3H330kWWbrT/7yNY4e/as4SkI9upguN4v5u8RbO/hw4cdviZHxx8+h5UrV7Z5bYcFz+0o4IxzsLmDBedo8/7CNamt7FPztmFBIB7fFdbnEAR2EaiyBx0+WA9/Z+/al/IHBhqI3AwXSIjY3nbbbepCCxdUOKnXrFnTeOCBB2ymtpk5c5GHHgW9DnparXuF0auKL148NwIMSK9EL5OjQIG7Ag3oXUM6PhoqaJjjggYXOLhQ6ty5s/Hll1/m6gIxu+1Fg7Fdu3aWIAMyGXABhAtwZ/YxerfNF+K2ILig13F00TxjxgzLhT6G2eQWGrEYEoELPfQU4nVhwf9xG+5z1CuNniv0+GCIAHr3dSMaFy24iOnRo4dK08xuuIu7Ag0Y2oDMB+xvNG5xIYTjBL3+n3/+udM97ujBGT16tHqNeP9xgY7elOHDh9u92LM+ZtFTg32CzxAurHCsIivHWbiwQg80Gqe4wDMHGfB/ZBNkx92BBmffq+zOCwi8oOGCgCE+3zgmcd5BBpet4UuuCjQgYwzvM7J0EODFRSz2NXrWMLzMURDHGi7SJ0yYoNKx0ftnboRhef7553OV8eHKQIN5+ISzAUs0WIcNG6Y+Cwgy4HXhc4+G2COPPGIsW7Ysy9+4ItCgP4djxoxR2UX4HOKzhPMwnhefsezgfdXbgQCiNWRp6Pu7detm5JY3Bhp0cPmpp55S5y6co7GgZxtZPI4aa8425BGE69evn7pOwWcH51wMN1q8eLHDv0OGysCBA9V2IciAzzuC0wjCYuhEdnQWTW5S6M2BBli4cKHK8MHnHscXrjEwFM3RMCh3QYYAOoIw3AfXfGiUIziOc5SjwKAzgQbANRweC4+Jx8Zz4LnwnDqTzBGci3FOxrkZ7xnO1Thn49xtLzCE4wz3I8MzJiZGfRfimgGfZ+xrHAe41soOtju37zn5Fj/8k9d1IoiICpKhQ4fKtGnT1HSl3377bV5vDuURVHJHYS9U3+7UqZOaFcXbCm5S5iJpKPC6fv16NW0tZjewNxWxp3zzzTeqECW2S8/GQOQrMNsIpobFzCQoaJnTYpGYUQeFd/E5xIxE5P3Q7EQxWxTXRpFOTFNL+RdnnSAi8jA0CFANfezYsdz3BRimPpw7d66qOo6q+5hOUk8DR94H1f/nz5+vZjRBAwlTYp48eTJPt6l///5qCjrMtLBu3bo83RainNLBMQTL3DUjBXkXzGKEIEOXLl0YZCgAGGggIvIgTImIaZ0eeOABy/SLVHBhXnlMg4sevTlz5sjAgQNdNrUguR6mycXUcZGRkepiGZkozkyF6S44biZMmKD+j2mPiXwJAmTI4nr11VfzelPIA/DdhumeMY3txIkTuc8LAA6dICIiIvJh77//vsTHx8vTTz8thQsXzuvNIfIIDp3wLcgE++KLL6RKlSoqi4XyPwYaiIiIiIjIpzDQQOTdGGggIiIiIiIiIpdhjQYiIiIiIiIichkGGoiIiIiIiIjIZRhoICIiIiIiIiKXYaCBiIiIiIiIiFyGgQYiIiIiIiIichkGGoiIiIiIiIjIZQJd91DkDcqWLSsJCQkSFRWV15tCREREREREXio2NlbCw8Pl1KlTLn9sZjTkMwgypKSk5PVmEBHla2fOnMnrTSAiIiK6Lmg3ov3oDsxoyGd0JsOOHTvyelOIiPKltLQ0GTdunIwaNUoCAgLyenOIiIiIciUmJkbchRkNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DItBEhEREZHPMQxDLURE9D9+fn5qyWsMNBARERGRz8z6cu7cObl8+bIkJyfn9eYQEXml8PBwKVWqlISFheXZNjDQQEREREQ+EWSIjY2VxMTEvN4UIiKvlpCQoM6V1apVy7OpuBloICIiIiKvh0wGXDjjojkyMlL12Pn7s9wYEZFZSkqKHD9+XJKSkuTMmTNStmxZyQsMNBARERGR18NwCUCQoWjRonm9OUREXikkJETKlCkjR48eVefNvAo0MAxMRERERF4NRR91TQZkMhARkeNgA6SmpuZZ0VwGGoiIiIjIq5kvlDlcgojIMXNdBgYaiIiIiIiIiMjnMaOBiIiIiIiIiFyGgQYiIiIiIiIflp6eLvXq1ZM33nhDfH12GdRhWbBgQV5vCl0nBhqIiIiIiPLYlStX5NVXX5WuXbtKiRIlxM/PT7766iu763/00UdSp04dVfStQoUK8tRTT0lCQoLNdQ8cOCD9+vVTlegLFSokNWrUkJdffjnLert27VLPX7hwYbUNAwcOVNPj2RIbGyuPPPKIVK5c2VLlvmfPnrJq1Sqb66MB3KNHDzVrCF7bmDFjJCfWrVsnjz32mDRp0kSCgoLUY9gTFxcn999/v+X1Nm7cWH766Seb6y5atEjat28vpUqVkmLFikmzZs3k22+/zbTOtWvX5IEHHlANecx4gv3TsGFD+eCDD9RUgrasXLlS7Q+8Xuwf7CfsL8wEkJ0HH3xQvb7bb79dnPX999+rx3788cfF08ftyJEjpWLFiup14picMmWK3fWxvzt06KD2Y0REhHo/f/zxR8v9JUuWlKFDh8orr7zioVdA7sLpLYmIiIiI8tjZs2fltddek6ioKNWIXbZsmd11n3/+eZkwYYL06tVLRowYITt37pQPP/xQduzYIX/99VemdTdv3izt2rVTwYinn35aNeQQJLBu8B47dkzatGmjGoDjx49XDch33nlHtm3bphr5wcHBmRrRt912m/o/GoV169aVU6dOqcDIzTffLB9//LE8+uijmR5/1KhRapq9G264Ics2OgM93F988YU0aNBAqlatKnv37rW53qVLl9Q2INiAfYPnnDVrltxzzz0yc+ZMFXDR5syZI3feeae0bNlSBT7QuMe6gwYNUu/Hk08+aQk0YN/iNSNggIKkCKjg/rVr18p3332XaRvwXuC5sZ1PPPGElCtXTgVxsP1oVP/xxx/SokULm9u/YcMGtR9DQ0NztH8mTpwoffv29ejUr2lpadKlSxe1zcOGDVMBLLy3CAhduHBBXnrppUzrT58+XQVsOnfurI4xFCzcs2dPlmMRAZnJkyfLkiVLVFCCfJRB+UrdunXVQkRE7pGammqMGTNG/SQiz0hLSzN27typFvw/P0pMTDROnjyp/r9+/XpMs2FMnz49y3onTpwwAgMDjYEDB2a6/cMPP1R/M2fOHMtt2Ff16tUzmjdvbly9etXh8z/66KNGoUKFjCNHjlhu+/vvv9VjfvbZZ5bbzp8/b5QtW9aIjIw09u/fn+kx8BytW7c2AgICjNWrV2e679ChQ+rnmTNn1GO++uqrRk6cOnXK8hqGDRumHsOWCRMmqPsWL16caT80bdpUbXdSUpLl9s6dOxvly5dX+15LSUkxqlWrZjRo0CDbbXr88cfVc+n3Df7991/D399f7YeEhIRM62N/Yb/hOS9cuJDl8dLT042WLVsaQ4YMMaKjo41u3boZzti0aZPajkWLFhmeNGvWLPW806ZNy3T73XffbYSGhhpxcXGZ3n8cX8OHD3fqsXHcWh/j5Ppzpjvbjhw6QURERESUx5B2jt737KxevVpSU1NV77WZ/v2HH36w3LZw4ULZvn27GpKBIQRXr15VvdC2/PLLLypVHxkVWqdOnaRmzZqql1/77LPPVPYCetCrVauW6THwHF9//bX6P7IzzJAJcD0wBAGPn50VK1ZI6dKlM/WEIwMBGQ3Y7n/++SdT9kPx4sXVvtcCAwPVMApnnku/posXL1pue/3111VmBPZDWFhYpvWxv5CJcuLECfn888+zPB6GbOD9ymmdhdmzZ6uME2SkmOksjf3798t9992nhoYg4wHDSnAsXC/sa7B1LCYmJsrvv/9uue3TTz9Vx54+LpAx42jaRWQ9zJ07N8+mZqTrx0ADERERERVoyanpsu1YvKw6cFb9xO/eKikpSf20bgjrRu3GjRszjYcHNKRvvPFGVWQP66EheP78ect6x48fl9OnT6t1rKFmwX///Wf5HY0/pPWj4W5LlSpV1NAFPDcam3mxf2wFCWztHwwpwZAI1ANAYxy1LBAowFCA5557LstjJCcnqyEVSPX/7bff1NCS6OhoqV69urofjffFixdL69at1X6wpU+fPur9wH40u3z5shoSg+EGzgSczDCMA/UjULvCFrxXePw333xT/R9DM8aOHZtpnfj4ePXaslsQIDDvawx/MA+rcXQs1q5dWw2BQT0H1GfAMB7sexSytIbaDQjg4P0h38QaDURERERUYK05eE4W7oiT05cTJSklTUKCAqRMRKjcEhMpLaqWFG9Tq1YtS50EFDG07l1G0EDbt2+f+onGJYo8vvjii7JlyxbV4ERj+d9//1U93idPnlTroZaANdyGoAQalWggox4EtsGcBWANNSaQOYDnr1+/vngStg2N2iNHjqgggKP9g0buoUOHVAbBuHHjLI1kZHfccccdWR77119/lXvvvdfyOwIzX375pcqCALxeZJvg9duD/YZtxH40Q08/AiS6LkRO7N69W5o3b273ftTFmDZtWqaZHfD722+/bbkNr9ec7WHP4MGDLUVK8TqQpbBmzRoVXMruWERQAtkUCOJgH2F/Yr9jn+GYNEN9C8B+QhCFfA8DDURERERUYIMMP204KnvjrkhauiHhIYGScDFRYs9dlfhryWodbws2YAYFNCrRSESBRwQbUGgQxRfRo43ChZrufW7atKnMmDFD/f/uu+9WjWkEHdD7juER+m9sBQ90UUKsg/vRM47eaEf0/VjX01CcEmn6CK689957asgFhn4gAwHM+wevB0NDUFTzrrvuUo1mDGkYMGCA/P3331kKNmJf43b0tGPfIWhjnulDv15n9o9536CwJWawwMwRjgI49iBwgCEg9qC4ohkyLrA/MHSkSJEi6rZJkyapAo7ZKV++vOX/KKyJAMmQIUNUAVAUg8RwnU8++UTdb30sInPhrbfeUpkb+lhEEAuvHZkc5v2mXw+yKMg3MdBARF4Dqap7Tl2Wy0kpEhESJLXKRkhwIEd4ERGRe75zkMmAIEOxsCCpUKyQ6t3HmPDjF6/Jvrgr6v4m0cUlKMC7vovQ444UfDTwAD3FmN4SPdKo4q/pIQTmXnjdQESgASn3CDTo9fSwDDM9/EGvY91ItkXfj+klcwKNUXNqPl4X6i3kBGalwCwQaFy3atVK3YahCO+//74KxmBqSg1TQaI3ftOmTaqOAyBAERMTo2aNwIwSZghaYAEEJzBzAmoJoLcez+FsgAX3m/cNnuumm25SDe/cclTLwFx3w9yIR2BBBxowVCGn8JoxcwemQb3lllvUbXg8zLqBzAfzvsbxg6CM9bGI3//88081PMdcY0K/HkfTmJJ3Y6CBiLyCr6WuEhGRb0NgG985yGTQQQbAT/x+7kqyuh/r1avguSkDnYFMBgx7QAMXBQ7Rk4xGH3qb0UNv3fusG8eabuTqHmw9ZEIPoTDDbSVKlLD0tGMqSzTM9VAKW7Zu3arG7WM7cwI1D8y1AzD04fDhw5JTCAL06NFDZRwgSwFZIHq6UL1/UG8BwweQxq+DDICskFtvvVU++ugjtY51/QHr53n55ZdV0cOHH35YvQ8YRoHXbw/2G4JBqH0BmMIRDW0MIzC/VgwnQEYAbsP+1wEBW1DrwFE2AgI22QUnkFmA15sdBAzMU2giOHDw4EE1DSoCCRgSgWKXYH0s4njN7ljU9O8ozEm+iYEGIspzvpi6SkREvg3Zcwhs4zvHutcUv4eHBEhSappcSkwRb4WGLRY9lh1BAcwuoKGXeurUqZnGyoNuCOpsAQQE8H8UQbS2bt06adSokeX37t27q0yIn376SQ0xsIaGMcboY8y/MzM3mA0aNCjTWP+c/r0ZAgQYMmJdGBMZHHq4ARrztmbhSElJUWn+9mbo0PTQABRSBAxJ6dixo80aERqGcSDY0Lt3b/V7bGys+omhG9bwvqGoJIaAjBw50u52oMgiak1cDzx/Tms0mAMZ5mPEel/rYxGBBrwmXX/B1rGo6ddTp06dXL8mylsMNBBRnvLl1FUiIvJdGKKH7DkEtvGdYw424PeEpDSJLBIqRUJtV/L3JmgUo2ceDV3zeHw09pGWP336dBWA0D33X3zxhfqJtH8NafuYkhFFIitVqqRuQx0C1A8wFyhEzz3G1D/77LMq3d/caMQwCxT7w760NWtDdvBY5sdzFTRwUbcB03fqXnb0pGO6R9QqQJ0BnbmAoRuYEQKNdx3oQJ0AZA1YB6T0fjTP1jFq1ChVxwH7GzMsmIMlaDxjv2D/YrgBYBpOXT/C7KGHHlKBCmRMZFdQs2XLlqr2gaMsk+zkpkaDLWfOnFH1QzCExRxowFAfTL2KLBI9fSeOWxybyNiwHrqBGSuQOYFhLOSbGGggojzly6mrRETku1AHCEP0kD2HwLZ1oDvQ30/dj/U8Ben6KDSoe3nR4D127Jj6/xNPPGFJWUfwAI169CKj9x01CZB5gECBeTw+hlOgoTp69Gg168Sdd96phhMgywFj4809/ijGhywFFDzE46PBPXHiRNXIRfDAPL7/559/lttuu00NSUDxRQynwBAO9HQjjR6vw3oWhG+//Vb18mMKSFi+fLllpgc0um31/pvhb/EYoDMv9N/jb3XDHbA9yBjAvkDjfsqUKaoxi2CDuRf+mWeeUYEBFH1ENgUyGNAQxj7XxTMB/8ffYv8hEIIaC3/99ZcKKCDDA8ECDRkZOgMBjW0EHDA0BTNDYL8j2DN79mwV5ABso3UNBcDfY5gBnjM7CChhWk5kJOhaCTmVmxoN0LZtWxXowBSfOAZQTBPHzrx58zINScE2ItsDs0sgcIMhFtgPGAL02WefZQmQ6H3LGg0+zKB8pW7dumoh8hUr958xhn61zug1ZZXxwi9bsyy9pqw0hn69Tq1H5A1SU1ONMWPGqJ9E5BlpaWnGzp071YL/u8rqA2eNp378z+g+eYVx6/vL1XcOfuJ33I77PSk6OhqD5m0uhw4dsqw3ffp0o2HDhkZ4eLgRERFhdOzY0ViyZInNx0xPTzc+/PBDo2bNmkZQUJBRqVIlY9SoUUZycnKWdbdv327ccsstRlhYmFGsWDGjf//+xqlTp2w+7uHDh42HHnrIiIqKMgIDAy3buWjRIpvrt23b1u5rW7p0abb7BuvY+3s8tlnfvn3V6wwODjbKly9vPPLII0ZcXJzNx505c6bRrFkz9XoLFSpkNG/e3Pj5558zrbN+/Xqjd+/e6rWGhISo/d64cWPj3XffNVJSUmw+7ooVK4w77rjDKFWqlOHn56e2s0yZMsbJkycNZ4+Fbt26Gc5q0KCB8cADD2S67dVXX1XPe+ZM5msoHD/Wx1RuPfnkk0bVqlXVfildurTRr18/48CBAzbXvXz5sjFixAijbNmy6r2pX7++MWPGjCzr7dq1y+GxRK47Z7qz7eiHf/I62EGuo9OLduzYwd1KPmHbsXj5bPkBOXgmQRpULJoldXXrsXipWjpcHmlbjRkN5BXQ44VeNPSC2SuwRUSuhRRrPZtCrVq1MvWUurQYcWqahASyGHFuYJgFshzQo//HH384LKJYECHjAJklyDDRmRiuhGyPYcOGqZoPOlvCVyGbAxkvGD7BjAb3njPd2Xbk0AkiylPemLpKREQFB4oNow4Qhuih8CNqMuA7h3WBcgZp8Ri6gakzMdQCww3YSPyfV155RQ2JQX0CDJVADQZX6t+/v6qN8PHHH6tghq9CkU7UvkDRTB4/vo2BBiLKU8GB/moKS8wugcKPqMmASt8owoUgQ43Iwup+XvAREZG74DuGdYCuX9++fdVCtqFWBBZ3QI/19u3bfX7Xo+gmajyQ72OggYjynJ660py6ikrfyGRAkIFTWxIRERER+Q4GGojIKzB1lYiIiIgof2CggYi8BlNXiYiIiIh8n+tK9hIRERERERFRgcdAAxERERERERG5DAMNREREREREROQyDDQQERERERERkcsw0EBERERERERELsNAAxERERERERG5DAMNREREREREPiw9PV3q1asnb7zxhhQUn376qURFRUlSUlJebwrZwEADEREREVEeu3Llirz66qvStWtXKVGihPj5+clXX31ld/2PPvpI6tSpIyEhIVKhQgV56qmnJCEhIct6J0+elIceekiqVKkihQoVkmrVqql1z507Z/exU1JSpG7dumob3nnnHZvrxMbGyiOPPCKVK1dW21CmTBnp2bOnrFq1yub6aAD36NFDIiMj1eOOGTNGctKIxr7A31eqVEnCw8NVo3rcuHGSmJho82+mTZum9k9oaKjUqFFDPvzwwyzr7NmzR5588km56aab1HrYrsOHD9t9f0aOHCkVK1ZUrxePPWXKFLvbvHLlSrU/8HqxPvYT9tfRo0ezfb0PPvig2pbbb79dnPX999+rx3788cfFk3788UcZMGCA2sfY5nbt2jn1dzgesD7eR0cuXryoji2s+/PPP2e677777pPk5GT57LPPrus1kHsw0EBERERElMfOnj0rr732muzatUsaNmzocN3nn39ennjiCdVI++CDD+Tuu+9WDem77rorS+O4ZcuW8ttvv8mgQYPUOrfddpsKUnTq1Ek14G3BeggkOGpE169fXzVu8dyffPKJjBgxQrZv3y4333yzzQb4qFGjZP369XLDDTdITl29elXuv/9+OXPmjGqsv//++9KsWTMVmLn11lvFMIxM66PhOXToUImJiVGvBftg+PDh8vbbb2dab/Xq1TJ58mS5fPmyChzYk5aWJl26dFGv65577lHPX6tWLXnsscdk/PjxWdbHc7Zu3Vq2bdum3ifsn169eskPP/wgDRo0kDVr1th9rg0bNqigCgIfOTFx4kTp27evFC1aVDwJ++T3339XAaDixYs79TfHjh1T+w0Bo+yMHj1avf+2YB8NHjxY3n333SzHAHkBg/KVunXrqoWIiNwjNTXVGDNmjPpJRJ6RlpZm7Ny5Uy34f36UmJhonDx5Uv1//fr1aDUZ06dPz7LeiRMnjMDAQGPgwIGZbv/www/V38yZM8dy28yZM9Vt8+bNy7Tu6NGj1e2bNm3K8vhxcXFG0aJFjddee02tM3HixEz3nz9/3ihbtqwRGRlp7N+/P9N9V69eNVq3bm0EBAQYq1evznTfoUOH1M8zZ86ox3311Ved3jdJSUnGypUrs9w+duxY9Vh///13pm0oWbKk0a1bt0zr9u/f3wgPD1fbr507d864dOmS+j9eJx5Lb6fZrFmz1H3Tpk3LdPvdd99thIaGqn2m/fvvv4a/v7/aDwkJCZnWx/7Cfitfvrxx4cKFLM+Tnp5utGzZ0hgyZIgRHR2d5TXYg/cR27do0SLD02JjYy2fyZiYGKNt27bZ/k2fPn2MDh06qHXxN/Zs27ZNHev6WPzpp5+yrLNhwwZ13+LFi6/zlRTMc2ZdN7YdmdFARERERAUPekBTkxwvHuwlRXp92bJls10PvfCpqamq99pM/45ec+3SpUvqJ9L3zcqVK6d+YiiFtRdeeEH11iMd3hZkC5w6dUr1oGMYhhke7+uvv1b/R3aGGYYO5FZwcLAa3mANQxMAWSDa0qVL1bAQZBuYDRs2TA0tmT9/vuU2DFGJiIjI9vlXrFihftra5xi6gR597fXXX1dp/tgPYWFhmdbH/powYYKcOHFCPv/88yzP8+2336qskJzWWZg9e7baR23atMl0O4anYFv279+vhhkUK1ZMZTwgO8RelkBOIZPB39/5JuXy5cvVEAhkhWQHWTJ4j5EdYk+TJk3U+2h+D8g7BOb1BhAREREReRQCCCs/ELlwyPF6xauItBoh4ucn3kIXvrMOEuhG7caNGy23oeGJRiAabJMmTVL1BbZu3aoasnfeeafUrl0702OsW7dONZD//fdf1UC1Ze7cuSplHUMIbEEtCAyfWLRokWqE53QIQE4g4AGlSpWy3Pbff/+pnzfeeGOWBin2Be63F0RxtM8DAgJUY97ePkddBTTeFy9erBrG2A+29OnTR9XMwH587rnnLLdj+AaGxLz00ktOBZzMUBcDw2iCgoJs3o/3Ctvz5ptvyqZNm+SLL75QdQ/MQ0ni4+NVbY7s4P0sXLiw5AaGoGAoCYa1YOiNIz/99JN6XQgi2auboTVu3FgN5yHvwkADERERERUsackZQYYjq5xbNzBEvAWyDQANq/bt22fpdT9+/LjlNhR0RM/5M888o+oUaBjXjsamGca4oxGIhjDWtde427lzp9oGZGDYgxoT//zzj+zbty/bBuX1QHZAkSJFVJ0Gc/FLBAXQkDZDkKBkyZIqmyCn8HrRSEZtBQRR7O1zvF5kmziqsYH9hsfDfjRDBgiCRyhOmVO7d++W5s2b270fdTFQHFNDxgd+Nwca7rjjDvWeZQfHjqMipdnNEnHkyBEVhHLk2rVr6pjFvkAmTHaBhqpVq6psEPIuDDQQERERUcFVsamIn1Xqt5Eucmy9eCP03qJRiUYiZptAsAG9vo8++qjq0UYjzQzroHAiikBGR0erxjEKICILwDyjBBqPKF5oXdnfGnresxtuoO/Huu6CYoJosKLQIoYEaHj91pkH5t546/3jjH79+qlAwJAhQ+Tjjz9WMywsXLhQPbd+TvPrdWb/mPfN3r17VVFPFNd0FMCxB4EDR4UYUUDTDBkXKBCKoTUI1AAyXi5cuJDtc5UvXz7H26e3EYUdX3nlFSldurTDdd966y2VXYHsDmfgteM9QEaJ9XAVyjsMNBARERFRwYUgg39A5ttsT8bgNX755ReVeYCGL6AHH1NWokcaUzZqyHrAFInoiddDCTBkAo3LsWPHqr9H1gManC+++KI8++yzasx9ThrJtuj7rbMKsoNZMrBoeF22GqWYUhGzWDzwwAMqwGKGrABMeWgLhnLYqkuRHQxlmDNnjgwcOFBuueUWdRv2IWaXQA+/HkrgbIAF95v3DYa2oAYFZvDILUezLkRFRWX6XQclEFjQgQYMLXEnvF+opYCsGUeQvYD6HwjoODtEQ792e8N9KG8w0EBERERE5EOQpYA6CkjVR50C9LCjMYze5po1a2Yq3IhCkNb1Cnr06KEKBWIMPAINyGxA4xzBC52mjikIdWMUt+GxkSmA9THOH3UL7PW+ow4E1sV25gS2AwEQDRkY1mnzf//9t5qqs1u3bioV3xoKXWKYw+nTpzM15vH60Kue2x551Ls4ePCgyvpAUUkMj9DDMPQ+x/sQGBioXr892G8IBiHLBJYsWSJ//vmn/Prrr5leK4ZgoJcet6GBrgMCtmBIiKNsBARssgtOnD9/3m6AxgyBmpxOoYnjFEN4UADSPHQFgR9kLuA14vXhdSLrAcdNu3btLPtD1+LA9Ka4DYETcwFKvHZkMuQmiETuw0ADEREREZEPQsMWC2DMP+oTYHYBLS4uTjW6remif2jMQmxsrGqsxcTE2ByigAVFFBs1aiTdu3dXAQoU67NVVBENQQzPwJj/nDb8EEAw10Cw/vu1a9eqWQgQOJk1a5Zq1FvDNsKGDRvUcBENv6enp1vuzw002M1/r2sNdOrUSf1EY7djx47qdtQiQKDEGrYbwYbevXtb9j3cddddWdZF7QcUcXzvvfdk5MiRdrcLRT0PHcqmsGk28PzuqtGA14F9P3z4cLVYw2tEVgcCEdgfmCUDdRes6ZlEcKyah8vgtdepUydH20Tux0ADEREREZEPQyMOMxigoWsej4+edtQSWLZsmeoh1lALQBcJBDT+MKTCDBkBDz/8sApcIGigZ1HAbagngGEWSPc3NwjRQ42pE5HCbp5RwVl4LFsNTEAdCmQxoDjgvHnz7AYxOnTooHrGp0yZkinQgN+xf/AYroDeddTJaNCggSXQoIcIIOsC+23BggWZthMNYuwXDE/BMAy9vaiXYA0zUyBQ8fLLL2dbUBPFO1HXwFGWSXbcWaMBM2LYeo3YVxhGguNJT5U6btw4OXv2bKb1MOUnajtg3+G1hoeHZ7ofGTb9+/fP8XaRezHQQEREREQFFwo/ptu4LQ989NFHcvHiRUt6OaZA1EMYMLZdp6yj9xeNevSuIzvhu+++s0xNaR6P//jjj8v06dNVFgL+Hg1X9Foj0NC5c2fLTAUoMInFTKetI8vBHITA+H4UjEQjHn+DqQoxnALp7ejpxvACvA7rWRAwKwB6+VGwD5YvX64alYBGt63efw2N0S5duqiGMAIc8+fPz3Q/Gql6Vg007F9//XUZNmyYyhrA3yHDYsaMGWpaTwQhzFM6os4C6OkRse3oLceC/ae1bdtWPUf16tXVa8VQANSTQNDDnMaPjAydgYAgBAIOGM6BmSGmTp2q1p09e7alRx7vl3UNBcDfY9iLdQDIFgSC8Jrx3uoaEjmV2xoNeB+x6OALhpXo9xXDTbCg8Kit14EMBjDfZ85o0fS+atq0aZbHwdSiGPaBfUDehYEGIiIiIiq4vGh2CdQoQGNcw7h9LIBhCjrQgEwENNJmzpypGq4Y77948eJM010CplFEQww9x2hoo4GMHmlMHWiuhZBTrVq1UnUIMKQCQygQGNHDMDBsAMMHrGE6RXNq/tKlS9WiG5eOAg2orXD06FH1/xdeeMFmOr95+k6k2GMGDvTSo4gjMgjQ+EeAxgyBC/SUm+FvANtjDjSgIY7XimEAqCeAQA0a97YyMJAhgiAM3k+8T9h+1ENAzYgtW7aoehquhG1DUAPDMnIbaMgt1JiwPpb0Pn311VdVoMGd8J4gUIPMEPIufoajEqXkc/TYuh07duT1phAR5UsY74zeGly42yuwRUSuHxqgZ1NA49ncg5wruPxd+YHIhWzGtRevItJqBMrZX9/zFQAIdCDLAUGDP/74w+4UkwUVghIodIihELrH35WQMYIsDtQ4MNcvyM8wVARDaRB8sg4iFXTpTp4z3dl2ZEaDA4gAY4wVUtGwIIIJuYnN4ENgjlDbGneGQi5ERERE5GYIHCCAkJZNlf2AYAYZnIQsBgzd6Nevn6rTgAwKTjeYuZcfmR8YvoEeeNRgcCXUKEDNCEwLiWBGQYBhQchcMdclIe/BQEM2kcfff//dpTscqV225HSaGCIiIiK6zmBDYO4K55Ftffv2VQvZhoKUWNwBPdYomliQIMDAIIP3YqDBAYz1wngnFB7BgqwEpOhcj5xOB0NERERERETkSxhocOD555/33DtBRERERERElA9cZyUdIiIiIiIiIqL/YUaDh02cOFEOHDggISEhqspnz549pXTp0jwmiYiIiIiIKF9goMHDnnvuuUy/P/nkk/Lhhx/KkCFDPL0pRERERERERC7HQIOH9OjRQ9q3by9NmjRRGQwHDx6UL7/8Uj744AMZOnSolCxZUu644w6nH0/PeWoN2RLVqlVz4ZYTEREREREROY+BBg+ZPHlylkDBpEmTpHbt2moeXRSezEmggYiIiIiIiMgbMdCQxx544AEZNWqU7NmzRw4fPqym0HTGjh07cpTpQEREREREROQJnHUij/n7+1uGOpw8eTKvN4eIiIiIiIjoujDQ4AUuXLigfoaHh+f1phARERERERFdFwYa8hiGQGDYRFhYmKrXQERERER0PZYtWyZ+fn7y888/e2RHYvr2qlWrSkBAgDRq1EjdhuHA9913n0eePy+ej1zvtttukwcffDBf79pz586pzuUFCxZIfsdAgwt99NFHKljw4osvZrodB9KSJUuyrL9161bp3bu3GIahZp4IDg525eYQERERETmEDi9Mt37TTTdJaGioClCgbpizFi5cqKZvb9WqlUyfPl3Gjx9vc72dO3fKmDFjcvTY+UlSUpIq/l6+fHkpVKiQNG/eXP7++2+n/vbXX3+VPn36qGAOOidr1aolTz/9tFy8eNFmwAXvofXyyCOPOHwONPCx3u233y55YeXKlepYwj7y1f2J57/55pvVYxYvXlx69eqV5XjHTINo973yyiuS37EYpAPz58+X119/3fJ7cnKy+tmiRQvLbThIunXrpv5/9uxZdbK2rrWwbt06GTt2rERHR0vDhg3VwYfpLTdt2iSpqanSrl07eeutt1z93hIRERERObR69Wo1O1rdunWlTp06snnz5hztMXSmoebYtGnTMnWa4ZoYt5sDDbgexnWvs8XP8xNkWyDDZOTIkVKjRg356quvVA/+0qVLVePUEcxQhwb1gAEDJCoqSrZt26Y6ONGZifYEGtpmyCpBw9msZs2adh9/w4YNansQaMoryIrp2LGjVK9e3Sf357x589QMgo0bN1btukuXLskHH3ygtuW///6T0qVLW9ZFkAKfOXx2OnToIPkVAw0OnDlzRtauXZvldvNtWCc7Xbp0kaNHj8r69etVtC4+Pl6KFCmiDrz+/fvL/fffr1LNiIiIiIg8qUePHqonNyIiQt55550cBxpOnz6tGmbWmbkhISEu3lLfhU7HH374QTWmn3nmGXXboEGDpF69eiobZNWqVQ7/Hg1qBGjMmjRpIoMHD5aZM2eqHnKzChUqqEa0M5BZPXz4cLU9ixcvltxCz32VKlVUQ996W505htDB++mnn/rs/kR2BTIk0NbTn4Xu3btbAg+TJk2yrIuAHrYVwZH8HGjg0IlsImX48DlazGPBkA6G23DQmLVs2VJFeTFUAlkPKSkpanwOPog4kBlkICIiIirYLl++rHpn0duPRnqZMmWkc+fOqoc1uzoEaDTZatylpaXJSy+9JGXLllXjwhFUQOeXWYkSJVSQITeQQo7hEgkJCZaUcn0dbN5W3IbhwtC+fXvLuqglAeiE2717t/qZHVxrjxs3TipWrKiyhPF4tqZ9x3U5nsMatiWnw0OuFxq2uN5HT7qG7AFMc4+MEuv3xJqt97Znz57q565du2z+DTKx8b5k59tvv5Xt27fLG2+8IXkFQQZkeXfq1Mkn9+f58+dVxg4ewxxwa9iwoQoqIChiDZ/tuXPnquM5O2hDtm3bVgX0cNzj+MfnztPHcU4xo4GIiIiIfFJ6uiEXrmYMbfUmxcOCxd8/ayPXEaRTowH1+OOPq2EM6JT6999/VcMHvaK5gcYjGiPobUWv8fvvv68ac8hasE4Pzw00Uj///HPVw/zFF1+o21DrwVqbNm1UrznSxRH4QOML9M/ffvtNZfii8ZRdQcfRo0erhhbS5LEgEHPLLbdYhji7CmoAIPjjjFKlSjm8H6nzSLVHRrNZs2bN1E+8H5UqVcrR9p06dcrucyMlH0EYBJowdBs1OEaMGJFlPbw+HBs6GJVXkIGA2gXYVmd42/7EsQK2PlNhYWEqEIbHN+9jZFC899576j5kN9hz/PhxS3AOdQARMMRnzRcyhhhoICIiIiKfhCBDk3GLxNtsHNVJShYOyXGvLgrymVOskQZ+PdDTikCFzlhAwOKee+6RqVOnqob/9UI6+aJFi1Rj31FqOVLKW7durQIN6MnNaWq9ecjyhAkTVH009AbrjIWXX37ZbhHK3Pr+++9V8MMZ2fVKo35buXLlstyubztx4kSOt+/tt99WvfooOGjWoEEDNTwbBQ4RrEIGBzJl8Bz4G7PXXntNNY7RcM5LyGbJSd0Ob9ufkZGRUqxYMTVswuzcuXMq00EHDMyBBnwmAPc7CjTgOS5cuKA+Y3pGFxyXqEvh7RhoICIiIiLKY2iooA4YGjAoVOcKGLduHhaBRhQaYyh654pAg6sgi8GZqSkR1EDmwhNPPJFpWAQafq4ONKDGmrOzGGTn2rVrNnugdfFF3J8T3333nRqWjUCUdYNzzpw5mX5Ho/TWW2+Vd999V+03pN7D3r17VbFCBFRy0zt+5coVSUxMtPyOxjBg+AuGimtBQUFStGhRh4+FBjnqIPjq/kTR04cfflgFBZB1MGTIEFUMEo+nM22stwmzUoB5X9ny559/qmH4Osighzuhzt+HH34o3oyBBiIiIiKiPIaeehSjQ8o30qoxLACBAt3zmRvWjSY0zlHV35vHdTty5MgRm68LFf11w81VEJCx1WueG8ga0On1ZrqhnpNhLCtWrFC1CBAIcaauAt5zZCz89ddfqiaGzjxB6j+Gudx9992SGxji8/XXX2e5/c4778z0O2oL6FocOckKwTAF66L7aGCjBoI37k9khyBogM+xnk3wlltuUY+NIpeFCxe2+Xpt1RGxPuYRaLDm7OwceYmBBiIiIiKiPIYhDRhegHoFCxcuVBX10UP666+/qh5UR40SNMpYXDwzR/vKGeiBdqY4JWRX3wABC6TO2xoCAM5msGzZskUV9ESqPep5BAY615TT9QowlEbXHEBPOY4tc9AJBRnxunEbGvXWNRDM0FtvHi4TFxenfsfMJSiCqDkTAEJ9Bp0RoaGgI2axMNMzWnjb/gQEQFA7AcEKZItERkaqOhL9+vVTGQ/WgQH9erOr7+HLGGggIiIiIp+Eoouoh+CN25UbaEA99thjakHxRtRUQMNFBxrQaMNUlLZ6PW1lPuzbty9LL+r+/fvVuHNPy67n1hm6WCBel/n1oufbuqGqG7jYXxiWYp0VkZ0ff/zRZTUakPaORjLS6c2NdwyV0fdn58CBA9K1a1c1GwmGvlj3kDty8OBBS+YHxMbGqp933XVXlnXRgEcDH4UKMSTFHhQsxaLpgAWycXJag6N27dryyy+/ZAneWA9d0QEMb9ufZggwYNFBLWQ9NG/ePMvjHzp0KFNBVEfHPD6z1mzd5m0YaCAiIiIin4SZHXJadNEboUGCMe/msexoAKFn1pwiXq1aNZXqjXHfehq9efPmqd5fW4GGb775Ro0Z13Ua0GuLXl/MNOBpqJYPtgIlyBzQBf4cjefHjBkY84+x6UhL18ELzKZhDfsKli9frnqtAdMT2kr3d3eNBtTGQE8/Zuh45pln1G14XzHLBhqh5hkSEAS4evWqanxrmLEArxc940jZt9XA1T3s2H/m7JaUlBSVyo/jBbMXQIcOHVTmjDVMF4mGLYpr1q9fXzwFQwOQDYAGvD6OUW/B3nSX3rY/7XnnnXfUcW2rlsLGjRvVY8fExGR7HH788cdqJg0dQMF2zZw5U7wdAw1E5FvQa5CWzRRWAcHoOvHUFhEREV0XTDOIonJoQKHXFr2fKHy4fv36TLNQDB06VAUL0BOLoRbolZ0xY4alUW0N6e+omI+eeaS2o0GOFG7MbmFu5OuGkK6a/9FHH6ksACwYi+8KaCShwYbhIHhOFPNDgxcBFWent0SDEA3LN998U26//XZVxwJTHf7xxx9ZUtDRkIyKilJj5J999ln13F9++aV6DN2j76kaDWj89u7dWwV9kKmC9wABD2QBoAihGepy/PPPP5myJPB+oxGO4QqY8hSLht5zzOShCxdi6k8cR8hKQIMUhQ63b9+uimXqIR7YL1isIYMBj2ddZ8HdMIsIhi3gmEeww9f2J+BziKwMTOWqP7+zZs1Sn1lbdTAQxOrevXu2mT7YRjw2tgnFJ/X0lnj/sD2uyBRyG4Pylbp166qFKF9KTzeMFe8Zxpzhjhesg3WJ3CA1NdUYM2aM+klEnpGWlmbs3LlTLfh/fpOUlGQ8++yzRsOGDY2IiAgjPDxc/f+TTz7Jsu6kSZOMChUqGCEhIUarVq2MDRs2GG3btlWLtnTpUrSqjO+//9548cUXjTJlyhiFChUyunXrZhw5ciTT4x06dEita2uJjo7OdtsHDx6sttca/hb3mU2dOtWoWrWqERAQoB4f2wnTp09Xv+NndvD+jx071ihXrpx6Te3atTO2b99u8/k2btxoNG/e3AgODjaioqKMd9991/JceN2edO3aNeOZZ54xypYtq967pk2bGn/++WeW9fA+WjfR7L0/WMzvO46F7t27q+MDr7lw4cLGzTffbMyaNcupbcQ+xDGSG/o40u9pTvXo0cPo2LGjz+7PtWvXGm3atDGKFy9uhIaGqs/vp59+aqTbuB7dtWuXeq5FixY59Vr/++8/o3Xr1up1VqxY0XjzzTeNyZMnq8c4derUdZ0z3dl29MM/eR3sINfR6Tc7duzgbqX8JzVJ5I/nRI6scrxe9E0it04QCfT9dFryzhRn9HCMGjWKxdeIPCQ9PV327Nmj/o/57JHyTET5B4YEobbD7t27s8wqkt+MHDlSDenB8IncZiTgMT777DM15MpWIVhnz5nubDty6AQR+aaKTUX8rE6aRrrIsfV5tUVERERElAuYcQXDXTA95NSpU/PtPjx37pwa+oBhFc4GGTATiHnKTjzGt99+q4ZFefNsMww0EJFvQpDB3+rkmp5XG0NERERE1wO1NvK7kiVLqiyEnBbLRLYHZqhArRXUocCMG6+88op4MwYaiIiIiIiIiLzQbbfdporAYpYNZEFg2lsEG1B40psx0EBERERERETkhcaPH68WX8NKOkRERERERETkMsxoICLfhMKP6TZuIyIiIiKiPMVAAxH5Js4uQURERETklRhoICLfERAsUrxK9uthHaxLREREREQex0ADEfkOzDfcaoRIWrLj9RBkcHJuYiIiIiIici0GGojItyCAEBiS11tBRERERER2cNYJIiIiIiIiInIZBhqIiIiIiPKRZcuWiZ+fn/z8888eeb6JEydK1apVJSAgQBo1aqRuq1y5stx3330eef68eD5yvccee0w6d+6c73dtixYt5LnnnpP8Lk8CDampqXL27Fn1k4iIiIiI8savv/4qffr0UYGCsLAwqVWrljz99NNy8eJFp/5+4cKFqtHUqlUrmT59uowfP97mejt37pQxY8bI4cOHpSBKSkqS559/XsqXLy+FChWS5s2by99//+3U3+7Zs0eefPJJuemmmyQ0NFQFkeztRwRccL/18sgjj2Rab/HixTJkyBCpWbOmet/x/g8dOlROnjwpeeHQoUPyxRdfyEsvveTU+unp6TJhwgSpUqWK2icNGjSQ77//3qm/dfa1Yx/b2pd6efDBBy3r7tixQ3r37m35HJUqVUratGkjc+fOzfL8OA4+/vhjOXXqlORnHqnRsH79epk/f778888/snnzZrl06ZLlviJFiqjIZ9u2baVbt27StGlTT2wSEREREVGB99BDD6nG74ABAyQqKkq2bdsmH330kSxYsEA2bdqkGsWOLFmyRPz9/WXatGkSHBycqXGM282BhrFjx0q7du1UY7igQbYFMkxGjhwpNWrUkK+++kpuu+02Wbp0qdx8880O/3b16tUyefJkqVu3rtSpU0e1pxxB2wrBIjM0qq0bu+fPn1eNY2zPwYMH1fs+b9489fhly5YVT/rggw9U0KB9+/ZOrf/yyy/LW2+9pRr7aD/+/vvv0q9fPxUA6Nu3r8O/dfa1ly5dWr799tssf//nn3/KzJkz5ZZbbrHcduTIEbl8+bIMHjxYfZ6uXr0qv/zyi/To0UM+++wz9TnT7rjjDtUG/uSTT+S1116TfMtwk9TUVOPTTz81GjVqZPj7+xt+fn6WpUiRIkbFihWNiIiITLdjvRtuuMH47LPPjJSUFHdtWr5Wt25dtRARkfu+38aMGaN+EpFnpKWlGTt37lQL/k+OLV261MBl/k8//eTUuta+/vpr9fdTp07N9u/vv/9+Izw8PNv1sC14TFvP5wrR0dHG4MGDDW+0du1a9donTpxoue3atWtGtWrVjJYtW2b79+fOnTMuXbqk/o/HwGMdOnTI7n7o1q1bto/5zz//ZPks4TY89ssvv2zkBv52+vTpOf675ORko1SpUsaoUaOcWv/YsWNGUFCQMWzYMMtt6enpRuvWrVUbM7vv5+t97R07dlTtWbyHjqSmphoNGzY0atWqleW+xx9/XL1X2O68PGe6s+3olqETiNYh2vboo4+qCBEipIhyIkKakpIi8fHxcvToUZXZkJycLFu3blWpMohC7d+/X6X2IGKHKBARERERUX6H3lD0dqO3PyQkRMqUKaPGqyOrILs6BMgSwGItLS1NpaKjhzY8PFz1ruIa3PpvrfXs2VP93LVrl8NtRu8xhkskJCRY0snRU2+9rbgNvceAHmu9LmpJANoGu3fvVj+zg/bsuHHjpGLFiipFHY+HtHVrGKaB57CGbXE09MBdbSPUrzD3aiPd/4EHHlDZCtbvibUSJUpIREREjp4TbSy8L/Ygrd+ccaJvw3Nl97672r///quG1Xfq1Mmp9ZG9gDYlajpoeE/R9jx27Jjap45cz2vH8Apkodx1113qPXQkICBAKlWqZHMYEj7byILILjsFzp07JwMHDlRZEMWKFVNZE1u2bMn0eSswQyfuueceadiwoRong9QQR29CYGCg1KtXTy0YK5OYmCi//fabvP322+pxcIIkIiIiIsoiPV3k2nnv2zGFSohYNWSyg442NEgff/xx1eGGxgUaYGj4NG7cOFeb8cYbb6jGCFLFT58+Le+//75qzKFx42hIhB47jnHmjiCt/PPPP5d169apTkNAHQFraMQNHz5cpf8j8IEOSdA/ce1///33q6BFdgUdR48erQINGHaABYEYpLCjYe3qmgoI/jgju/3033//qaELaCiaNWvWTP3E+4EGqatgOAuCMGhHRUdHq/oOI0aMyPbvrly5opbsXo+rrVq1Sh2nN9xwg1PrY38icKaPH+v9ifuzG46S29f+ww8/qPoQ/fv3t3k/gjvXrl1TQbM5c+bIH3/8oWqgWGvSpIn6uXLlSoevG8/VvXt39RlDIKV27doq0IJgg7dzS6ABJwsEGHIDQYl7771XLdiJREREREQ2IcgwsZr37ZxnD4iE56yxhnpmGG8+adIky23XW5ke49ARqNC94QhYoCNv6tSpquFvDzr80Bvbq1cvh4+PrOVFixapxj7+bw8K5LVu3VoFGtCTayuLwhlnzpxRBQBR1w1F9nTGAsbr2ytCmVvoMEXwwxkZowYc94KXK1cuy+36thMnToiroCgiGtko6olgFXq8kSmD58D76ggCUQjY2GoYuxOyWZBNYB2IcbQ/IyMjs2SsXM/+dPa1ozYDnqdDhw4270dtDNRkAGRNIPMB9R+sVahQQdU0Qe0SR2bPnq0yNLB9OliEgIMvzM7hlkBDboMM7nocIiIiIiJvhpTotWvXqkYSism5wqBBgzKl3CNwgEYSCj3aCzR89913asgzghwolOcJyGJwZmpKBDXQGHziiScyNTLRkHZ1oKFLly5OzwqRHfRwYziMNZ31jftdBb3oZgiW3HrrrfLuu++q/YYhJ7YsX75cFetEIMpeI9oMxQ6xWENWAIZBaAhYFS9e3OFjISCS3Tru3J/Ovva9e/fKxo0bVYaI9dAL87GIz9mJEydk1qxZKqvEXrYNXrN5X9mCwpNBQUGZZrjAcw8bNkxlrkhBn3WCiIiIiIjsQ0890qGRQo+0agwLQKAA2QC5ZR0oQOO8evXqdusTrFixQtUNQCMbwy68Dca023pdmB0gJw1VZyAgYysLITcwTAVDMaxhyLi+313wnqNh/Ndff6maGLYyT5BRgLocGMquh8A4c7yicW4NwQwsGoZuOFMPw1ZWiPX0j0WLFlX7ypX7MyevHdkMYG/YBGBoAxbA5xfDejD0AUFE6wwMvGZbdUSsj3kchxgKY4bPsbfzeKABY3BwEtMpLYjYIr0Hc+8SERERERVE6E3F8AIMQV64cKFMnDhRpbr/+uuvqkca7DVK0GuKnuPrgeJyKBaJBhdqRaCOmi9ztK+cocfZOyO7qSDRUDx+/LjNIQDgqgwWe3T9BwylsYZClGgMoxGPTBdni06iEW1dBwHp/M8++2ymaR+dafSXLFlSLly4kOV260CPruGB21GQ0bqhntP9mdPXjmwfDEnR9RWc0atXL3n44YdVNgT+1gxFIj1dD8OTPHYGwYwTODB0ZU0dtdIHB4pHYgwRxhURERERETlVdBH1ELxxu3IBDShU0seC4o2oqYDMAh1oQK+9rQr26PW0lfmwb9++TL/j+hszvFlfbx84cEC6du2qZrpAg6tw4cLiatn13DoDveP6dZlfL2o3WDdUdYYD9heGpVhnRWTnxx9/dFmNhkaNGqmGMWbcM9chQC+3vt+dMAugzvywHrKAhjayAxYvXpyjDA7sf1vHHAqZOjt7hIYMAGQLILCDRr9mPXQlJibGsr+QfYD6I3i+3OzPnL52PDY+O6+99lqOXtu1/x/GYR20QuAJQyqsC1raOuZx7GCYijmrAdvi7TwSaNizZ4+0bdtWfdAxLgiRHUx5oz/smMYSAQgUhkHGg043ISIiIiKyC+Okc1h00Ruhlx1j282NLDT60TNrThGvVq2aygxGAwWF5GDevHmqZ9ZWo++bb76RF1980dJTi0wF9PpiFgpzejoaXBj3jfR668aoq2CWALAVKEEjTBdMNO8Da2jAYrz6hx9+qLZZBy9QKM8a9pUef49MDT0jwNdff+3xGg1o+7zzzjtqho5nnnlG3Yb3FT30zZs3zzTjRGxsrGpU5qY9hIwF7D9zdgumgXzrrbfU8YKpQDXsCwzPQYMXDVlP1eOwpWXLlipYg/oH5hoJ9gIWqOOH4SCffPKJpdAi/v7TTz9VRRbNM5/guMLxheMBx05uXzuyGaBfv34270dgEJ9Zs5SUFPUZRFaHOSACeK32ZmmxPg5RvBWLLgaJmSg+/vhj8XYeCTRgGhucVF544QUVBbJOxcIYH0xV8+abb6qqsQg8EBEREREVBJhGUXfGIcsXGQUofLh+/fpMs1AMHTpUBQuQfYChFshEmDFjhqVRbQ2V/JHejp75uLg41SDH2G5zYTk8Fnq8UfwR02li0VDZ31XV7dHLjAYwhoOg4YdifmhUonHm7PSWCIKgoY42w+23364ai5jKEFMIWqegIxARFRWlak4gnR/P/eWXX6rHQGPekzUaEEzo3bu3CvqgQYr3AAEP1C5A4U3rIQn//PNPpiwJ7C8EV/R0iIAGNjI1sGBKVF0IElN/4jiqUqWKCjyggbx9+3ZVLNM8xAN1BjBl4pAhQ1RmABYNx9+dd94pnoJjFMMncMw7U4gSnxUUXcTwIjTmmzZtqmZnQBAOmRHmQAv2Ofb1oUOHLB3dOX3tCAQiw6VFixZ2P2sYHoGMFUzlimDHqVOn1LagBgQ+w9ZZQghi4fjMbkpPbAum7cRsFshiQAAK77MeBuOKTCG3MTygePHiRr169bJdD+tgXcq9unXrqoWIiNwjNTXVGDNmjPpJRJ6RlpZm7Ny5Uy34f36TlJRkPPvss0bDhg2NiIgIIzw8XP3/k08+ybLupEmTjAoVKhghISFGq1atjA0bNhht27ZVi7Z06VK0Uo3vv//eePHFF40yZcoYhQoVMrp162YcOXIk0+NhPXuL+THtGTx4sNpea9HR0eo+s6lTpxpVq1Y1AgIC1ONjO2H69Onqd/zMDt7/sWPHGuXKlVOvqV27dsb27dttPt/GjRuN5s2bG8HBwUZUVJTx7rvvWp7r0KFDhiddu3bNeOaZZ4yyZcuq965p06bGn3/+mWU97HPrJhq21d57hNet4Vjo3r27Oj7wmgsXLmzcfPPNxqxZs7I8D/7OmcfMCWffQ1uGDx9uVK9e3en1cRyMHz9ebStea0xMjDFjxows6+GYsH6/c/ra8T7hvsmTJ9vdHnzWOnXqZERGRhqBgYGqTYvff//9d5vbjuN31KhRTr3WM2fOGP369VPnhqJFixr33XefsXLlSrVNP/zww3WdM93ZdvTDP+4OZiBdCylLulKnPYguIUKDqC7ljh67tGPHDu5CIiI3QM8GeoxGjRp13cXXiMg5SBXGUFxAQTV7U8sRkW9CVg1665Gd0rFjR8nPZs+erYZgICMpt1kzeAzMloEMJFuTKjh7znRn29EjZ2mkgGFHZgfrYF0iIiIiIiIqGFBjBMNcUE8iv3v77bfVcBdngwy6oKS5wwNDaVBYFAVjC3SNBtRdwDgqjIvCWBhbMCYL49Dmzp3riU0iIiIiIiIiLzFlyhQpCFavXp2j9Z944gkVbEDRTBQRxZS3mEABdTecmT40XwcaUGX20UcfVYVnMIVlnz59LNPTYNaJWbNmqbQPrINCGagOa4aiGkREREREREQFSYcOHVRBScwwk5iYqIqJIqNBFwEt0IEGTFuJipgoB4GAgq6WqukyEYhi2YpkIT2EiIiIiIiIqCDp16+f3Wk1paAHGjBNi1dPvUFEREREREREvhNowHAJIiIiIiIiIsr/ODcQEREREXk1c2Yspm0jIiL7zKUH8mpkgUcyGsySk5Plv//+kxMnTqjfy5cvL40aNZKQkBBPbwoRERER+QBcKAcHB6vryISEBClatGhebxIRkddKSkpSPwMDA/N/oOHKlSsyevRomTZtmvq/GWaawLSXr732mkRERHhqk4iIiIjIR+Aa8dy5cxIXF2eZ1czfn8m5RERmKSkpcvr0afX/vGxbeyTQEB8fr2ae2Lp1q/q9YcOGUrlyZcv0lps3b5bJkyfLkiVL1NSWjFITERERkVnJkiVVNgOmd9OZsUREZFtAQICULl1a8opHwsDIZNiyZYu0b99etm/fLps2bZJff/1VLRs3bpQdO3ao+UFxH9YlIiIiIrK+aI6KilIBBwyjICIi25DxVbFiRXXezCt+hmEY7n4SvEgU7tm/f7+EhYXZXOfatWtSrVo1lQJ37Ngxd29SvhUTE6N+InhDRETuKbA0btw4GTVqVJ5+gRMVdLiE9cBlLBGRT/Hz83O6LoM7244eGTqB8XR33nmn3SADFCpUSNq0aSNz5szxxCYRERERUQG5mCYionw4dKJq1apy4cIFp2o5VKlSxRObRERERERERES+Gmh46KGHZNmyZarooz24D8Ughw4d6olNIiIiIiIiIiI38MjQiREjRqj6DCgG+cQTT0ifPn0kOjraMuvErFmz5MMPP5SHH35YnnzySU9sEhERERERERH5ajFIXSwLT2VvLJ29+3Bbamqquzcx32AxSCIi92IxSCIiIsoPYny9GGSlSpVYrIeIiIiIiIioAPBIoOHw4cOeeBoiIiIiIiIiKgjFIImIiIiIiIioYGCggYiIiIiIiIi8O9Dwxx9/uORxFixY4JLHISIiIiIiIiIfDjR069ZNWrZsKXPmzFHVuXMCM0z89ttv0rx5c+nevbs7No+IiIiIiIiIfCnQ8NVXX8mJEyekZ8+eUrZsWXn00Uflhx9+kAMHDthcf//+/fL999/Lww8/rNbv1auXxMXFqcchIiIiIiIiogI+68SgQYOkT58+8sknn8iUKVPks88+k88//1zd5+/vL8WKFZOIiAi5fPmyXLx4UdLT09V9hmFIzZo1ZfTo0SroEBIS4o7NIyIiIiIiIiJfm94SQYInn3xSLcuXL5d58+bJihUrZOvWrXLu3Dm1QKFChaRhw4bSunVrNeSiTZs27tokIiIiIiIiIvLVQIMZggfmAEJCQoLEx8dL0aJFJTw83BObQERERERERET5JdBgDcEFBhiIiIiIiIiI8h+3FIMkIiIiIiIiooKJgQYiIiIiIiIiYqCBiIiIiIiIiLwPMxqIiIiIiIiIyGUYaCAiIiIiIiIil2GggYiIiIiIiIhchoEGIiIiIiIiIvKtQENAQIA88MAD2a734IMPSmBgoCc2iYiIiIiIiIh8NdBgGIZanF2XiIiIiIiIiHyTVw2diI+Pl5CQkLzeDCIiIiIiIiLKJbeNU4iNjc30+5UrV7LcpqWmpsqePXtk4cKFUq1aNXdtEhERERERERH5aqChcuXK4ufnZ/n9l19+UUt2wyZQp4GIiIiIiIiIfJPbAg1t2rSxBBr++ecfKVOmjNSuXdvmusHBwVK+fHnp0aOH9OzZ012bRERERERERES+GmhYtmyZ5f/+/v5y6623ypdffumupyMiIiIiIiIiL+CRuSQPHTokhQsXztXf/v7777JlyxYZPXq0y7eLiIiIiIiIiHxw1ono6GgpWbJkrv529uzZMnbsWJdvExERERERERHl8+ktiYiIiIiIiMi3MdBARERERERERC7DQAMRERERERERuQwDDURERERERETkMgw0EBEREREREZHLMNBARERERERERC7DQAMRERERERERuQwDDURERERERETkMoGueygiIqI8YBgiacmO1wkIFvHz89QWERERERVoXh9oGDp0qLRr1y6vN4O8THJquuw5dVkuJ6VIREiQ1CobIcGBTNAhKpBBhpUfiFw45Hi94lVEWo1gsIGIiIjIA7w+0NCqVSu1EGlrDp6ThTvi5PTlRElKSZOQoAApExEqt8RESouqJbmjiAoSZDIgyHBklXPrBoZ4YquIiIiICjSPBBoCAgKcXtfPz09SU1Pduj3k20GGnzYclb1xVyQt3ZDwkEBJuJgoseeuSvy1jNRpBhuICqiKTUX8rDKbjHSRY+vzaouIiIiICiSPBBoqVaqkAgjW0tPT5dSpU5KSkqJ+j46O9sTmkA8Pl0AmA4IMxcKCpEKxQuq4MgxDjl+8Jvvirqj7m0QXl6AADqMgKnAQZPC3Cmyn59XGEBERERVcHgk0HD582O59CDYsWbJERowYIfXr15fvv//eE5tEPgg1GTBcApkMOsgA+Infz11JVvdjvXoViub15hIRERERERVIed7t6+/vL506dZJ58+bJ/Pnz5e233xZvsXHjRnnrrbfkrrvukooVK6oGra3MDGdduHBBBVSQuRESEqJ+jhw5Ui5evOjS7c6vUPgRNRkwXML6fcDv4SEBkpSaJpcSMzJkiIiIiIiIqAAGGrQqVapIixYt5MsvvxRv8frrr8uLL74ov/32mxw/fvy6Huvs2bPSrFkzmTx5sgQGBsqdd94pERER8sEHH0jz5s3l/PnzLtvu/AqzS6DwY0JSqhouYYbfE5LSJCQwQIqEBuXZNhIRERERERV0XhNogLCwMDl69Kh4i5YtW8orr7wic+bMkZMnT6oshNxC5sL+/ftVdsSePXvkxx9/lO3bt8sTTzwhe/fulaeeesql254fYQpLzC4R6O+najLoYIOu0YDbcT/WI6ICCIUf09MyL7iNiIiIiArm9JZHjhyR5cuXS2RkpHiL559/3iWPgyAFak8EBwfLJ598ojIatIkTJ8oPP/wgM2bMkAkTJkiZMmVc8pz5UXCgv5rCErNLoPAjajJguAQyGRBkqBFZWN3PQpBEBRRnlyAiIiIqOIGGb775xu59V65cUT36aGhfunRJHnvsMclv/vzzT1X0snXr1lkCKciS6N69uxoysmDBArnvvvvybDt9gZ66ErNLoPAjajJEFglVmQwIMnBqS6ICJiBYpHiV7NfDOliXiIiIiPJHoAGNZ0dFFHUK/KBBg2Ts2LGS32zZskX9bNy4sc37cTsCDVu3bvXwlvkmBBMwhSVml0DhR9RkwHAJZjIQFUD4bmk1QiQt2fF6CDJcRzFfIiIiIvKyQMPo0aPtBhownKBcuXLSpk0bqVq1quRHsbGx6idmrrBF347hI+QcBBU4hSURKfh+Ccx9DR0iIiIi8sFAw5gxY6Qgw/AQXezSlvDwcPXz8uXLTj9mTEyMzdsPHDgg1apVy9V2EhEREREREeWrWSeIiIiIiIiIyLd5zawT+VnhwoXVz6tXr9q8PyEhQf2MiHB+WsYdO3bkKNOBiIiIiIiIyGcDDddTawG1HJD+n59ERUWpn8eOHbN5v749Ojrao9tFROROyanpqmjr5aQUiQjJKNqKaWqJiIiIKH9zS6Dh8OHDuQow6Nkn8puGDRuqn5s2bbJ5v769QYMGHt0uIiJ3WXPw3P+moU1Jk5CgAE5DS0RERFRAuKVrKT09Pcvy+OOPqyEEzz//vGzevFkuXryoFkz9+MILL6j7sA7WzW+6du0q/v7+smLFCjl9+nSm+5KSkmTu3LkSEBAgt912W55tIxGRK4MMP204KusPn5eDZxLk4rVU9XPD4fPqdtxPRERERPmXR3JYJ0+eLJ999pksWbJE3nzzTdVzX6RIEbXUr19fxo8fL4sXL5ZPP/1U3n//ffFVH330kdSuXVtefPHFTLdj+s57771XkpOT5bHHHpPU1FTLfc8995ycOXNGBgwYIGXKlMmDrSYicu1wCWQy7I27IsXCgqRBxaJSvUxh9bNoWJDsi7ui7k9Jy39BZSIiIiLyYKABQYZ27drJjTfeaHcd3NehQweZOnWqeIv58+dLixYtLAsCBWC+DetoZ8+elT179sjJkyezPBYCKJh28pdfflHBiL59+6ogC4IwNWrUkHfffdejr42IyB1QkwHDJdLSDalQrJAaFgf4id9T0w11P9YjIiIiovzJI4GGgwcPSokSJbJdr3jx4nLo0CHxFsg0WLt2rWXRNSTMt2EdZ5QqVUrWrVsnTzzxhApY/PbbbxIfHy/Dhw9Xtzuzf4iIvB0KP6ImQ3hIoCXIoOH38JAASUpNk0uJKXm2jURERETkXn6GByowVqhQQf3EbBKhoaE210lMTFQ9/nD8+HF3b1K+pae3tDf9JRGRO207Fi+fLT+gajJguIQ52ICvm63H4qVq6XB5pG01qVehqE++GWlpaTJu3DgZNWqUqq9DRERE5Iti3Nh29EhGQ8+ePdVwgl69etmckQK39e7dW06dOqXWJSIi34QpLMtEhEqgv58cv3jNkgmGn/gdt+N+rEdERERE+ZNbpre09vrrr6tCkAsWLFD1CFCPITo6Wt135MgR2bhxoyqQiNoFWJeIiHxTcKC/3BITKfHXklXhx3NXktVwiYSkNBVkqBFZWN0fFOCRODcRERER5ddAA2ovrFq1Ss3G8M0331jqG2iFChWSIUOGqBkpsC4REfmuFlVLqp+YXQKFH1GTIbJIqMpkQJBB309ERERE+ZNHAg1QrFgxmTJlikyaNEllMJw4ccIy9WOTJk0kPDzcU5tCRERuhmBCk+jianYJFH4sEhqkhkswk4GIiIgo//NYoEELCwuT1q1be/ppiYjIwxBU8NWCj0RERESUexwkS0REREREREQuw0ADEREREREREbkMAw1ERERERERE5DIMNBARERERERGRyzDQQEREREREREQuw0ADEREREREREbkMAw1ERERERERE5DKB4kHnzp2TGTNmyLp16+Ts2bPSsWNHee6559R9O3bskAMHDkinTp0kLCzMk5tFRERERERERL4WaPjpp59k6NChcuXKFTEMQ/z8/KRChQqW+48fPy49e/aUr7/+WgYMGOCpzSIiIiIiIiIiXxs6sXr1aunXr58EBgbKpEmTVEYDgg1myG4oWrSo/Prrr57YJPIkvNepSY4Xq+OBiIiIiIiIfJNHMhrGjx8v/v7+8vfff0vjxo1trhMQEKDu2759uyc2iTwFAYSVH4hcOOR4veJVRFqNEPHz89SWERERERERka8GGlatWiUtW7a0G2TQypYtK2vXrvXEJpGnpCVnBBmOrHJu3cAQT2wVERERERER+XKg4erVq1K6dOls17tw4YInNofySsWmIn5Wo3WMdJFj6/Nqi4iIiIiIiMgXAw0o+ohZJRxBzQYMm6hSpYonNonyAoIM/gGZb0vnW0FERERERJSfeKQYZNeuXWXPnj3yww8/2F3niy++kKNHj0q3bt08sUlERERERERE5KsZDS+88IJ89913MmjQIPnvv//UNJaQkJCgfv/tt99kwoQJanjFk08+6YlNIiIiIiIiIiJfzWioWLGizJ8/X0qVKiUTJ06UVq1aiZ+fn/z8889y4403yrhx46RYsWIyZ84cKVOmjCc2iYiIiIiIiIh8NaMBMOsEhk9MmzZNTXN5+PBhSU9PV0GIzp07y8MPPyxFixb11OZQXkDhx3QbtxG5WHJquuw5dVkuJ6VIREiQ1CobIcGBHomrEhEREREVeB4LNEBERISMHDlSLVQAcXYJ8oA1B8/Jwh1xcvpyoiSlpElIUICUiQiVW2IipUXVknwPiIiIiIjyQ6Dhtddek0aNGkmPHj0crjd37lxVs2H06NGe2CzyhIBgkeJOzCSCdbAu0XUGGX7acFT2xl2RtHRDwkMCJeFiosSeuyrx15LVOgw2EBERERHlg0DDmDFj5L777ss20IAaDV9++SUDDfmJn59IqxEiaRmNPLsQZMC6RNcxXAKZDAgyFAsLkgrFCqlaMJg69/jFa7Iv7oq6v0l0cQkK4DAKIiIiIiJ38aqr7bS0NPH396pNIldAACEwxPHCIANdJ9RkwHAJZDLoIEPG4eenfk9NN9T9WI+IiIiIiNzHq1r1O3bskOLFi+f1ZhCRD0LhR9RkwHAJHWTQ8Ht4SIAkpabJpcSUPNtGIiIiIqKCwG1DJ4YMGZLp93///TfLbVpqaqqakWLDhg1y5513umuTiCgfw+wSKPyImgwYLmEONuD3hKQ0iSwSKkVCg/J0O4mIiIiI8ju3BRq++uory/9xwb9//361ONKgQQOZOHGiuzaJiPIxTGGJ2SVQ+BE1GaxrNAT6+6n7sR4REREREflgoGHp0qXqJy7yO3ToIF27dpXnn3/e5rrBwcFSvnx5iY6OdtfmEFE+Fxzor6awxOwSKPx47kqyGi6BTAYEGWpEFlb3sxAkEREREZGPBhratm1r+f/gwYOldevWmW4jInI1PXUlZpdA4UfUZMBwCWQyIMjAqS2JiIiIiPLJ9JbTp0/3xNMQEalgAqawxOwSKPyImgwYLsFMBiIiIiKifBRoIHKHaf8eklvqRkqlEmHcwZQJggr1KhTlXiEiIiIiys/TW169elXGjRsnTZs2lWLFiklAQIDNJTCQsQ/K3n+xF+T1eTulzcSl8sBX62XZntOSnm5w1xEREREREeUxj7Tq4+PjVY2GHTt2qGACij+iSGS5cuXk1KlT6v/AYpDkrG/XHFE/cegs3n1aLVElwmRAiyjp3aSSFA8P5s4kIiIiIiLKrxkNb731lmzfvl0eeughuXTpkvTq1UtNO3f8+HFJSEhQU2GWLVtWmjdvLgcPHvTEJpEPO5+QLPO2nsxye+z5qzJ+wW5p/uZieXrWFtl89KIliEVERERERET5KNAwe/ZsNX3l5MmTJTQ0VAUZNPw+aNAgWbRokfz2228yadIkT2wS+bC0dEP6NYuSiBDbCTnJqenyy6ZjcufHK6XHRytl1vqjci05zePbSUQFB847247Fy6oDZ9VP/E5ERERUUHlk6MSRI0ekU6dOEhQUpH7398+Ib6SkpFhuq1u3rpr+EtkNzzzzjCc2i3xU6YgQGdMjRp7tUkt+33xCvll9WHafumxz3W3H4+W5X7bKuPk7pfeNlaR/8yipWrqwx7eZiPKvNQfP/W9K1ZQ0CQkK4JSqREREVKB5JNCArAUsWpEiRdRP1GeoVKmS5fYSJUrIypUrPbFJlA+EhwRKv+ZRcm+zSrIp9oJ8u/qILNh2SpLTsvYkXkpMVbNUYGldo5QMaBEtHWuXkcAAj9VDJaJ8GmT4acNR2Rt3RWVb4byUcDFRYs9dlfhryZYpV4mIiIgKEo8EGhBMOHr0qOX32rVrq5///POPDBgwQP0/NTVV1q9fLyVL8oKMcgZDcZpEl1DLqNuTZNaGozJzTawcv3jN5vor9p1VS7mioWoIRp9mlVTvIxFRTmB4BDIZEGQoFhYkFYoVUucj1IbB+Wdf3BV1f5Po4mrKVSIiIqKCwiNXPphxYuvWrXL5ckZ6e/fu3dU0lsOHD5dPP/1U5s6dqwpEHj58WA2foHwMxRk3fyeSdMUtD1+qcIg81q66LH+uvUwbfKO0q1VaTCVBMjkZnyiT/t4rrd5aIk98/5+sO3SexSOJyGl74y6r4RLIZNBBBsBP/J6abqj799gZ2kVERESUX3kko6Fv376yceNGWbVqlXTp0kUVhnzzzTdVLYZhw4apddADhJkn3n77bU9sEuWVg0tFZj8q8scLIo0HijR7SKR4tMufJsDfTzrWiVTLkXMJMnNtrMp0uHg1Jcu6KWmGzN1yQi21IiNkQMto6XlDBSlsp9gkERFcTkpRNRkwXMJc5Bjwe3hIgCSlpsmlxKznHSIiIqL8zM/Iw/n/1q5dq2aauHDhgtSsWVPuv/9+VaeBci8mJkb93LFjh3fuxpn3iOz763+/+/mL1L5dpMVjIlEtcHXutqdOTElT02J+u+aIbDl60eG64cEBclfjiqqWQ62yEW7bJiLyPWlpaTJu3Di58/4nZOq/h+XgmQRpULFopmADvlq3HouXqqXD5ZG21aRehaJ5us1EREREnmw7eqTL9tKlS+oCLCIic4OtefPmaqEC4uz+zEEGMNJFds3JWMo1ygg4xPQUCQx2+dOHBgVIryYV1bL12EWZseaImrUiycY0dAnJaSoggaVZlRIysEW0dIkpK8GBHGd9PePZkUKOXuCIkCAVwOH+JF9WMzJC1XdB4UfUZLCu0RDo76fuZ7CSiIiIChqPBBqKFSumAgqrV6/2xNORtzLSMrIXds/HL1nvP7lZ5LeHRP5+RaTpUJEm94sULu2WTWlQsZhM6FVMXrqtjvy88ZgKOhw+d9XmuqjdgAX1HzDDxb3NoqR8sUJu2a78itP/UX6EQNktMZFqdgkUfjx3JVkNl0hISlNBhhqRhdX9LARJREREBY1HAg1FixaVqlWreuKpyJuVriXSd6bI+YMi66aKbPpWJNlGkbQrcSJL3xBZ/o5Ig94izR8VKVvPLZtULCxYhrauKkNaVZGVB86qKTIX7YqTdBtxkLNXkuTDJfvl46X7pVOdSBnUsrLcVK2k+Pu7b7hHfsDp/yg/01NXYnYJFH5ETYbIIqEqkwFBBk5tSURERAWRRwINN9xwgxw4cMATT0W+oERVka5virR7UWTzTJG1n4pcOJx1vbQkkf9mZCxV2mQMq6jRRcTf9cMXECxoXaO0Wk5cvCbfr4uV79cdVcEFawhCLNwZp5YqpcKlf/Mo6d2kkhQNC3L5dvk6Tv9HBQGCCZjCEkODUPixSGjG0CBmMhAREVFB5ZEB588//7ysX79efv75Z088HfmK0CIiLR4VeWKTSN/vRCq3tr/uoeUi3/cV+aiJyNrPRJLcN10chkU8fUstWfVCB/nw3htUjQa7m3U2QcbN3yXN31wkz/+8VbYfj3fbdvkiNLw4/R8VBAgqoODjTdVKqZ8MMhAREVFB5pGMhkKFCsnQoUOlT58+cvvtt0v37t0lKipKQkNDba7fpk0bT2wWeQv/AJHa3TKWk1szMhy2/SSSlpx1XQy7+OM5kSXjRBoPEmn2oEjxym4bf929YXm1oMGMOg6/bjqmCkVaS0xJlx83HFVLo0rFVPHIbg3KqQKUBRmn/yMiIiIiKng8Mr2lv7+/pRK3etJspjDE1GGUT6e3dNaV0yIbvhRZ/4VIwhn766npMbv9//SYLd06PSZcTkyR2f8dV7NR7I274nDd4mFBcs+NlaR/82iJKhkmBdG2Y/Hy2fIDnP6P8uX0lqNGjZKAgIIdTCQiIiLfFePr01sOGjQo2+ACUSaFy4i0e0Hk5idFtv8isuYTkVPbsu4kNT3m3IylXMOMwpH17hIJDHHLDo0IDZKBLSvLgBbRaiYKBBz+3H5KUm1Uj7xwNUU+W35QPl9xUNrWLK2yHNrVKiMBBah4JMapc/o/IiIiIqKCxSOBhq+++soTT0P5EQIGjfqJNLxX5MhKkTVTHEyPuUVk9iMif4/OmB7zxiFumx4TgbPmVUuqBTUIflx3VL5bFysn4xOzrItEnmV7zqilQrFC0r9FlPS5sZKULOyeYIg34fR/REREREQFj0eGTpDn5JuhE46cPySy7nP702NqASEi9XuLtHhEpGx9t29Walq6LN59WtVyWLHvrMN1gwP85bb6ZWVgy2hpHFU832f8YIpL8/R/IYEBnP6PfBaHThAREVF+EOPGtiMDDflMgQg0aImXHE+PaYYZLVDHoSamx3T/mOqDZ67IzLWx8tOGo3IpMdXhunXKFVHDKu5oVF7CQzySZJQnUtLSOf0f5QsMNBAREVF+EMNAA3nDweK10tNE9v6VUcfh8ArH6xavItL8EZEb+ouERLh9064lp8ncLSfkmzWHZfvxSw7XjQgJlLubVFT1H6qXKez2bSOi3GGggYiIiPKDGAYayBsOFp+AgpFrMD3mLNvTY2ohRURuGCjS/CG3TY9phhFKm49eVMUj5209Kcmp6Q7Xv6laSZXl0KlupAQF+Lt9+4jIeQw0EBERUX4Qw0ADecPB4nvTY07//+kxTzueHrPWbRnDKqJvcvv0mHA+IVkNqcDQitjzVx2uG1kkRO5tFqWWyCKhbt82IsoeAw1ERESUH8Qw0EDecLD4pNQkke2/iqz52Pb0mGZlG2QEHNw4PaZZerohy/edkW9XH5Ele06r2SnswZSYXWIi1bCKllVL5vvikeRhOPgcZQBBQLBHAnG+wGsCDXzfiIiIyEvbjvm38hyRZXrMe0Ua9hU5siqjjoO96TFPbfXY9Jjg7+8n7WqVUcvR81fV9Jg/rj+qMh6spaUbsmDbKbVUKx2uhlXc1aSiFAkN4vucDQxT2XPqslxOSpGIkCCpVTZCTbtJpsbqyg9ELhzKvr5JqxEMNngLvm9ERETkxTwSaPjmm2+kevXqctNNNzlcb82aNbJ3714ZNGiQJzaLChL0xFZulbGo6TGnimz6xvb0mBhqsWy8yIp3ROrf45HpMSuVCJPnu9aWkZ1qyB/bTqlaDhuPXLC57oEzCTJm7k55+889cucNFVTQoW75Im7dvnwxrWZKmoQEcVrNLJDJgCADAnHOrOuBbB9yAt83IiIiKuiBhvvuu08t2QUapk2bJl9++SUDDeReJaqIdB0v0u4Fkc3f/f/0mIdsX8hvnpGxqOkxHxWp2dWt02OGBAao4AGWHSfiZcaaWJn933G5lpKWZV3c9v26WLU0iS6uAg631i+rHoMyggyohbE37orKCMHUoQkXEyX23FWJv5aRNdKiaknuKrOKTTPqlpgZ6SLH1nM/eTO+b0RERORlvGroRHp6Oseek+eEFsnIVmj2YPbTY+J2LJihAtNjNuqf8fduFFO+qLx5V3158bba8uvGYyrLAdkMtiD7Acvr84LlnqaVpF+zKJUlUZCHSyCTAUGGYmFBUqFYIXVuwewfxy9ek31xV9T9CNBwVg8TBBmsA2mOJ0ghb8D3jYiIiLyMVw1UPnjwoBQpwhRw8jA0rGrfJnLfPJFHVorcMEAkwE56+IXDIn++IPJuXZE/XhA5f9Dtm4c6DPe1qiKLnmor3z3YXG6rX1YVh7TlXEKyTFl2QNpMXCoPfLVelu05rYpOFjSoyYDhEshk0EEGwE/8nppuqPuxHhERERER+UhGw2uvvZbp982bN2e5TUtNTZU9e/bI8uXLpXPnzu7aJKLsla0ncsfHIh3HiGycnlHLwdb0mKjtsHZKxrALNT3moyKVb3ZroTw0km+qVkotp+ITLcMmTl9OslknbvHu02qJKhEmA1pESe8mlaR4eLAUBCj8iJoMGC5hPUMHfg8PCZCk1DS5lJiSZ9tIRERERJRfuS3QMGbMGEuqMn4i0IDFkTJlysj48ePdtUlEzsNsE22fy6iyv+M3kdWYHnOrjRUNkT3zM5bI+hkBh3p3iwSFunVvly0aKk92rimPd6guf++MU1Nkrj54zua6seevyvgFu+WdhXule4PyMrBltDSsWDRfD1PC7BIo/IiaDPocpOH3hKQ0iSwSylk7iIiIiIh8KdAwffp0y0X9kCFD5Oabb5YHHnjA5rrBwcFSvnx5adGihYSEsKI5eRFU2MfUmA36iMSu/t/0mCiQZy1um8jvj4kselXkxgdEmj4gUriMWzcP9QVuq19OLftPX1bFI3/ZeEwuJ6XarFvwy6ZjaqlfoagqHtm9YXkpFJz/ikdiCssyEaGq8CNqMljXaAj091P3Yz0ywXFtfWjbOtbJu/B9IyIiooISaBg8eLDl/19//bXceuutmW4j8inoEY++KWNBnQY9PWbSpazrJpwR+ectkX/fFanXKyPLoVwDt29i9TIRMqZHjDzbpZb8vvmEfLP6sOy2U4Ng2/F4ee6XrTJu/k7pfWMlGdAiWqqUCpf8IjjQX26JiVSzS6Dw47kryWq4BDIZEGSoEVlY3c9CkFY4u4Rv4vtGREREBXHWiaVLl3riaYg8AzNPdHnjf9Njrplif3rMLd9lLNE3ZwQcat3q1ukxAXUJ+jWPknubVZJNsRfUsIoF205JclrWnulLiaky7d9Damldo5TKcuhQu4wEBnhVndhc0VNXYnYJFH5ETQYMl0AmA4IMnNry/wUEixSvkv0OxTpYl7wD3zciIiLyYn4Gcokp34iJiVE/d+zYkdebUnCkp4nsW5gxrOLQcsfrFovOmB4TM1u4eXpMs7NXkmTWhqMyc02sGjrgSPmioSpQ0adplJSO8P2hTClp6Wp2CRR+xAweGC7BTAYr+BpAYCy7hm0+ruuRE2lpaTJu3DgZNWqUBATk4dAjvm9ERETkpW1HjwUadu7cKRMmTFAzS5w8eVKSk21f1GIcNWahoNxhoCGPndqeMRvF1p9E0rLOBmERHJERbGj+kEiJqh7bPEz3uHT3afl2zRH5Z+8Zh+sGBfhJ13rlVJZD08rF83XxSCKfDDQQEREReWnb0SNDJ1avXi2dOnWSa9cyelJLlCghZcuW9cRTE3mWF0+PCQH+ftKpbqRajpxLkJlrY1Wmw8WrWad5TEkzZO6WE2qpFRkhA1pGS88bKkjhEI+cNoiIiIiIyEd5JKOhXbt2KpNh5MiRqgcIgQZyD2Y0eJnUpGymxzTx4PSYZokpaSqYMGNtrGw5etHhuuHBAXJX44qqeCRnbKCCihkNRERElB/E+PrQicKFC0vNmjVl06ZN7n6qAo+BBi+Fj1l202NqYaUypsbEFJkRkZ7cStl67KLMWHNEzVqRlOp4WsNmVUqoYRVdYsqqWR6ICgoGGoiIiCg/iPH1oRPBwcFSu3ZtTzwVke9Pj3n1rMg/b4useFekvp4es2GOni45NaMA4uWkFIkIySiA6EwwoEHFYjKhVzF56bY68vPGYyrocPjcVZvrrjt0Xi2lCoeoGS7ubRYl5YsVytF2Erlbbj8LnuLt2+fN2+pt20NEREQezmjo0aOHxMbGyubNm939VAUeMxp8SNJlkc3fZ9RqOH/Q8brRrf5/eszbsp0ec83Bc/+b0jElTUKCAnI9pWN6uiH/7j+rikcu3hUn6Q7OFv5+Ip3qRMrAltHSqlop8ccNRHnIlZ8Fd2Q0uGv73MHbttXbtoeIiMgXxfh6RsP48eOlRYsW8vHHH8uwYcM88ZRE3i8kImPWiaZDRfb9JbJmisihf2yve2RlxqKmx3z4/6fHLGrz4vunDUdlb9wVNcNEeEigJFxMlNhzVyX+WsZMLzm5CEewoE3N0mrBtJjfr42VH9bHytkrWWeNQRBi4c44tVQpFS79m0dJ7yaVpGhYUE72CpFLuPqzUNC2z5u31du2h4iIiPIo0IDaDPfff78MHz5cZs2aJZ07d5aKFSuKv7/tFMdBgwZ5YrOIvAM+B7VuzVjidmQEHLbOsj095sUjIn+9JLJ0fEawodlDIiWrWdKI0cOHi+9iYUFSoVghNSUlkpYQJNgXd0Xd3yS6uAQF5Dy9GI/3TJdaMrxjDflzxymZsfqIrDt83ua6h84myLj5u+SdhXvkjoYVVJZDvQpZAyNE7uDuz0J+3z5v3lZv2x4iIiLKw0DDfffdZ7kQWLFihVrwuzXcj9sZaKACKzJG5I6PRDqNEdkwXWT9VJErcVnXS76SMTXm2s8yAhQtHpU9gQ1UGjF6+PTFN+Anfj93JVndjzHN19PoxxjoHg3Lq2X3qUuqjsNvm45LQnJalnUTU9Llxw1H1dKoUjFVPLJbg3ISGpT7dHOi7OAY98RnIb9unzdvq7dtDxEREeVhoGH06NE2AwtEZEd4KZG2z4q0GpExPeaaj0VObrGxoiGyZ4FaqhavLU0CbpfzwW2yfN7we3hIgCSlpsmlxBSX7fbaZYvIuDvry/Nda8vs/47LN6uPyL7TV2yuu/noRbWMm79T7rmxkvRvHi1RJcNcti1EGooDYtw+Uuo99VnIT9vnzdvqbdtDREREeRhoGDNmjCeehij/CQwWadhHpME9IrFr/n96zHk2p8cMv7Bb7pfd0tNvqmwwesrakj3lSlBJS7ZQQlKaRBYJlSKhrq+ZEBEaJANbVpYBLaLVTBTfrDkif20/Jak2qkdeuJoiny0/KJ+vOChta5aWQS2jpW3NMhLA4pHkquMxJEgVB8S4fZ0pp7n7s5Afts+bt9XbtoeIiIjyMNBARK6YHrNlxnLhSMaQio2YHjM+y6rFjHjpdPoraXdmhmwt1kn+LdlL1idFSaC/n6rKjing3AUX/c2rllTL6UuJ8sP6o/Ld2lg5dSkxy7qY72bZnjNqqVi8kMpwuOfGilKycIjbto8KBhzjONZRHBDj9q3H8Xvis+DL2+fN2+pt20NEREReEmjYsmWLrFu3Ts6ePaum08DUl5CUlKSWIkWKeHqTiHxL8WiRW8aJtH1BZMv3GcUjzx/IslqgkSqNL/yplu2B9WR92T5Sp05fjxVIK1MkVBWOfKxdNVm067Sq5YCpMm05duGavP3nbnnv772qhgMyIxpHFeOQK8p1HRFMc4gZCFAcEOP2kVKP3m40RGtEFlb351WxQG/fPm/eVm/bHiIiIrLNz0A3gAfs2bNHzTyxdu1ay22DBw+WL7/8Uv1/+vTpMnToUJk/f7507drVE5uUL7lzLlTyUunpIvv/zhhWcXCZ43WzmR7T3Q6cuSIz18TKTxuPyuXEVIfr1i1XRM1WcUej8hIWzOQryt00iJiBAMUBMW4/JDBA9XajIXo90x+mpaXJuHHjZNSoURIQEOB12+cO3rat3rY9REREvijGjW1HjwQajh49KjfeeKOcOXNGZTC0bt1ann32WTUbhQ40JCQkSKlSpWTAgAEydepUd29SvsVAQwGH6THXfirGlh/Fz9b0mFpw4SzTY3rS1eRUmbvlhCoeuePEJYfrRoQGyt2NK6osh+plCntsGyl/SElLVzMQoDggxu0jpf56e7tdFWhw1/a5i7dtq7dtDxERka+J8fVAw4MPPqgCCgggDBkyRN3m7++fKdAALVu2VAGHrVu3unuT8i0GGkhJOCuycbrIui9ErpxysFP8RGp2VdNjSpU2GbUgPAinH8xE8e2aIzJv60lJTs1a5NLspmol1RSZnetGSiAbFJRHXBloICIiIsqPbUeP5CP/+eef0qBBA0uQwZ7KlSvLwoULPbFJRPl/esw2z4rcNEJk5+yMYRUn/rOxoiGy94+MpUxMRsChfm+RoFCPbCaKuN0QVVwto7rVlZ82HJUZa4/I0fPXbK6/6sA5tUQWCZF+zaKlb7NKqsI8ERERERF5D4/kGJ4+fVpq1aqV7XopKSly9epVT2wSUcGZHhNTYz64VGTIXyJ17xDxs/OxP71DZM7jIu/FiCx5Q+Syo0wI1ysRHiwPt60m/zzTXqbf31Q61i5jN8Ei7lKSvLdor7R6a4kMm7lJVh84p7IjiIiIiIgo73kko6FkyZISGxub7Xp79+6VcuXKeWKTiAoWtNijWmQsF2NF1n1ud3pMuXpWZPkEkX/fE6l3d0aWQ/lGHttUf38/aV+rjFqOnr8q362LlR/XH5XzCclZ1k1NN2T+tpNqQf2GAc2j5K4mFdV4bSLKHzCkCrUYLielSERIRi0GzD5BREREBTzQ0KpVK5k9e7Zs3rxZGjWy3WD5559/ZPv27apuAxG5UbGozNNjrv1U5Nz+rOulp4hs/SFjibopI+BQu5uIv+fGpFcqESbPd60tIzvVkD+2nZJvVh+WTbEXba67//QVGTN3p0z4a4/ceUMFGdA8WuqW53S5RL4s0+wSKWkSEsTZJYiIiHyBR7oEnnnmGZXWfMcdd8gff/yhCmmZLVmyRAYOHCiBgYEycuRIT2wSEYUUFmn2oMiw9SL9fhKp2t7+PoldJTJroMjkRiKrPhJJtJEJ4UaYug7Bg18fayXznrhZ7m1WSQoF2Q54XE1Ok+/Wxsptk1dIrymr5PfNx9X0d0Tke0EG1G1Zf/i8HDyTIBevpaqfGw6fV7fjfiIiIvJOHpl1Aj755BMZMWKEpKenS1hYmKrFULhwYTX7xKVLl1RROKzz0EMPeWJz8i3OOkHXJW5nRobD1h9FUhMdT4/ZqL9I84fzZHpMiL+WIr9uOqZmrEDjw5GS4cHSp2kl6dc8SioWD/PYNlL+xFknPDNc4q0/dqsgQ7GwIKlQrJC6TsAly/GL1yT+aorcWLmEvHhbbU5pSURE5IVtR48NcnzsscdkxYoV0r17d8vFwuXLlyUpKUm6dOmihk4wyECUxyLrivSYLPLkTpEOr4gULmt7veQrIus+E/mwich3fUUOLsNclR7d1KKFguT+VlVk8VNt5buhzaVrTFkJ8LddPfJcQrJ8suyAtJmwVIZ+vV6W7Tkt6eksHknkrVCTAcMl0tINS5AB8BO/oz4L7sd6REREVEBrNGgtWrRQtRoQZDh79qzKbihVqpTXz0N+7do1efPNN+WHH35QRS1LlCghXbt2lddff10qVKjg9ONg+s4jR47YvX/Xrl1Su3ZtF2010XUILynS5hmRm4aL7PxdZM3HTk6P+cj/T49ZyGO7Hw2Pm6qXUsup+ET5fl2sWk5fTsqyLmILi3adVkt0yTDp3zxKejepJMXDgz22vUSUPRR+RE2G8JBAS5BBw+/hIQFqSNSlxBTuTiIiooIeaDBfJJQuXVp8QWJionTo0EHWrFmjZsRAnYnDhw/L9OnTZd68eer2qlWr5ugxBw8ebPP2okWLumiriVw5PWZvkfq9RI6uE1nziciuOSJGup3pMZ8QWTRG5MYhIk2HikTYyYhwk7JFQ+XJzjXl8Q7V5e+dcfLt6iOy2s447iPnrsr4Bbtl0sK90r1heRnYIloaVirm0e0lItswuwQKPyZcTFSdE+ZgA35PSEqTyCKhnGGGiIjIS+VJoMGXjBs3TgUTWrZsKQsXLlR1JeDdd9+Vp59+WoYMGSLLli3L0WN+9dVXbtpaIndOj9k8Y1HTY04V2fS17aKQV8+JLJ8o8u/7IvXu+v/pMW/w6FsTFOAvt9Uvp5Z9cZdlxpoj8sum43IlKTXLukmp6fLzxmNqaVCxqAxoES09GpaXUDvFJonI/TCFZZmIUIk9d1XVZLCu0RDo76fux3pERERUgItBosDEO++8o2oxnDx5UpKTk21vkJ+fpKZmbQzkBWxjmTJlJD4+XjZt2iQ33JC5sdSwYUPZunWrbNiwQZo0aeL00Al37nIWgySPSbrieHpMs6iWGQGHWt1EAvImvpmQlCqzNx9XWQ67sxnXjfoPvZtUlP4toqVKqXCPbSP5BhaD9OysE/virqiaDBgugUwGBBlqRBaW3jdWkhZVS3poa4iIiPKfGDcWg/TIFT+CC7feeqsahoBAAmoc6MwAb7Zy5UoVZKhWrVqWIAP06tVLBRrmzp3rVKCBKF9Oj3njAyL7/xZZM0Xk4FLb68auzliKRok0f0jkhoEihTw7TAFjvfs3j5Z+zaJk45ELaraKBdtOSkqaYXNGiy/+PaSW1jVKqWEVHWqXkcAAj9XPJSrwdBBh4Y44VfgRNRkwXAKZDLfERDLIQERE5MU8Emh47rnnVJBh1KhR8swzz0iRIkXEF2zZskX9bNy4sc379e0INuTExIkT5cCBAxISEqKiSD179vSZmhVEWfj7i9TskrGc3pURcLA3PWZ8rMjCUSJL3xS5AdNjPuLx6TER7MS0eFhGdasrszYcle/Wxqp0bFtW7DurlvJFQ9X0mH2aRknpiBCPbjNRQQ42NIkurmaXQOHHIqFBargEhkcRERFRAQ80oCGOGSdee+018SWYYQIqVqxo8359u6OZJOwFXsyefPJJ+fDDD1W9ByKfVqZOxvSYHV8V2fRVRi2HyyezrpeSILLu84z7EaDAsIoqbTNqQXgQAgbD2leXR9pWk6W7T8s3a47I8r1nbK57Ij5R3lm4Vz5YvE9urVdOBraMlhuji2epiE9EroWgQr0KLJZMRETkSzwSaChZsqSqT+Brrly5on6GhYXZvD88PGPs9uXLzs3j3aNHD2nfvr0aZoEMhoMHD8qXX34pH3zwgQwdOlTtJ8xqkZPxNNaQKYGhHkR5Pj1m66f/Nz3makyPucnO9Jh/Zixl6mYEHDw8PSYE+PtJp7qRajl8NkFmrj0iszYcU0MorGGoxZwtJ9RSu2yEKh555w0VpHAIa+sSEREREYFHcg+7deumZm5AAa2CbPLkyWqYRFRUlBQqVEgFCyZNmiRTpkxRBSKff/75vN5EItcKCMqYGvPBJSIP/C0S01PEz85sDqd3ZkyP+V6MyJJxIpdsZEJ4QOVS4fJyt7qy9qWOMrFXA2lY0X5PKopKjpq9XVqMXyyjf98ue+OcCzoSEREREeVn/p6aIhLpxQ888IAqrugrdMHKq1ev2rw/ISFB/YyIuL7ptbBfMLvFnj175PDhw079DSqD2lqYzUBeCcMLKjUT6f2VyIgtIq1GioTaKQapp8d8v77ILw+KHLeVCeF+mN4SVe1/f/xm+X1YKzULRUig7VMmps38ZvURueW95dLns9Uyb+sJSU5Nl3wDM+WkJjlePDOBERERERH5AI/k+mKYwLp166Rt27ZqCMWNN94oFSpUEH8UkbOCgMS0adPEGyDzAI4dO2bzfn17dHT0dT0P9gMCBKdPn1ZTf/riMBMipxWrJNJ5rEjb5zKmx1yD6TH3ZV0vPUVk26yMpVKLjGEVtW/Pk+kxG1YqppaXu9WRnzcekxlrjsjhc7YDkGsPnVcL6j/c27SS3Ns8SsoV9exQEJdCAGHlByIXDjler3gVkVYjstTZQMAFhfwuJ6VIREhGIb9gOwEbIiIiIsofPHLFfunSJendu7fs2rVLDRFYvHix3XW9KdDQsGFD9XPTJts9qvr2Bg0aXPdzXbhwIVPdB6J8LzhcpOlQkSZDRA4sFlnziciBJbbXPbomYylaSaTZQyKNB3l8ekwoFhYsQ1tXlSGtqsi/+8+qKTIX74qTdBud+WcuJ8nkJfvl42UHpFOdMjKwRWVpVb2k7xWPTEvOCDIcWeXcuoH/m5FjzcFz/5uaMCVNQoICODUhERERUQHgkUADprRctmyZ1KtXTx588EGpWrWqZViCN2vVqpUULVpUFVjcvHmzNGrUKNP9P//8s/rZvXv363oeDHnAsAkUnaxdu/Z1PRaRz0FmU43OGcvp3SJrPxXZ8oNIqo3pJuOPivz9isiyt0Qa9cuYHrNU9TzYZD9pU7O0WjAt5vdrY+WH9bFy9kpylnXT0g35a0ecWqqWCpf+LaKlV5OKUrRQkPicik1F/KyyEYx0kWPrs6yKIMNPG47K3rgrah+EhwRKwsVEiT13VeKvJVumLiQiIiKi/McjgYbff/9dKlWqJKtXr/apHvvg4GB5/PHH5Y033pBhw4bJwoULLdv/7rvvqmk7MRwEs0hoH330kVpQ9PHNN9+03L5gwQIJDQ2VDh06ZHoOPEbfvn1VpgdmnsBzEhVYZWqLdH9fpONokY16eswTtqfHXD81Y6nx/9NjVm3n8ekxoUKxQvJMl1oyvGMN+WP7SZm5JlbWHT5vc92DZxPk9Xk7ZeJfu+XORhXUjBU+NW0fggz+VsU8bZSiwHAJZDIgyFAsLEjtI2Ry4DyHwMy+uCvq/ibRxdXUhURERESUv3gk0HDt2jVp166dTwUZtFGjRsmiRYtk1apVUqNGDWndurUcOXJE1q5dq2pPYHpKs7Nnz6rsBNRaMEONirFjx6p6DhiSgewFTG+J4Repqalq/7z11lsefnVEXiqshEjrp0RueiJjekwMqzi+0fa6+/7KWErXyQg4NLjH49NjAuoO3NGoglp2n7ok364+Ir/9d1yuJmedbScxJV1+WH9ULTdEFZMBzaOlW4NyqgBlfoCaDBgugUwGHWQA/MTv564kq/uxnk8FWoiIiIjIKR7pSsKQg1OnTokvQhbC0qVL5ZVXXlHBgdmzZ6tAw3333aeCBBgG4owuXbrIkCFDpEiRIrJy5Uo17GL//v1y8803y9SpU1UwA1NeEpG96TEXicTcZX96zDO7ROYOF3m3rsji1/NsekyoXbaIvNGzvpoi87U7YqRGGftDxf6LvShP/7RFWr65WN5csEsNLfB1KPyImgwYLmFdkwK/h4cESFJqmlxKTMmzbSQiIiIi9/EzkMvqZmhE33rrrTJ37lzp2rWru5+uQIuJibHUfSDKl+KPZQypwNCKxIv21/MPzAhMIMuhQmPJSzjNYiYKFI/8a/spSbVVPfL/oV3etmZpGdgiWtrVKiMB/nlcPBJTV/7xXEYxyErNbQydSBM5ulYk+iaRWyeoYpDbjsXLZ8sPyMEzCdKgYtFMwQbsi63H4qVq6XB5pG01n8xoSEtLU9M2I+MtICB/ZKEQERFRwRPjxrajR4ZOoO4AahygaGL//v2lc+fOdqe3hDZt2nhis4jIFxWtaJoe8weRNVPsTI+Z6vrpMRGXxcwKjgQEZ6kVgYY2Ch9iOX0pUQ2Z+G5trJy6lGjzKZbtOaOWisULSf/m0XLPjRWlZOH/zeaQZ1D4Md3GbeqnkRGUEJFapYKlXLi/nDibKnEX4qV80YzhE6kSKMfjEyXQ30/NPoGpLomIiIgo//FIRgMCCroQmHrSbAq2obeIcocZDVTgpKdnTIuppse0P3WuYpkec6BIoeJOPwWKG+45eUki/vtYIq4ek2KFguxnGhSvItJqRLaFKVPT0mXRrjiV5bBy/zmH6wYH+KsaDige2TiqmGenyDRnNNiDc3toEZEydS0ZD3GXkuTgmSsSfy1FTf8ZFOAnRyVSZhfqJTXKRkjvGyv57KwTzGggIiKi/CDG1zMaBg0a5HtzxxORD02P2SljccP0mJimETMknI+/JD3jdkjNpG1y3t9PwoMDJSzYTto8sh4CHWcgBAb4S9d65dSy//QVmbn2iPy88ZhcTkzNsm5yWroqLImlbrkiMrBltNzRqLyEBXvgFI4MDQRPHMHwidM7M4ZQ/L9IEYlIT5MEv1RJNQwxUkUKhQVI8+gI6Vjfd4MMREREROQlGQ3kOcxoIBKRq+cdT49pVuOW/58es32WLAQEGX7acFRN0+iXlixPJH0utZK2yZ7A2hJRKFiqlCoskUVC/jeE4Nj6TLUKcupqcqr8vvmEmrFi58lLDteNCA2UuxtXVFkO1R0Um3SJ7IaMIOth4SsisatEKjbNmAbz/6UZhsQnJElo3CZJLN9cInq+K0Ehvl34lhkNRERElB/E+HpGAxFR3k6POUXk+Abb6+5bmLGo6TEfEWnQR02PieESyGRAkKFYWJBEFQmVIieDJCQ9QAIDAuRiYroci0+SUkULSQACFOku2OzgQLm3WZT0bVpJ/jt6UWasPiLztp5UGQ3WkPnw1arDarmpWkkZ1DJaOtWJVJkSLofXl13gRMdoEGQwFYzE/0oU9hO5ECBh4cEi7tg+IiIiIvIqHrniu//++2XNmjWeeCoiIhvTYy52cnrMEf8/PeZrcuDAPjl9OVHS0g2pUCyjmKGGaRtRd+BaSprEX3X9FI14rsZRxeXdPo1k9Ysd5IVba6vCkPasOnBOHpmxSW5+e6l8sGifKjhJRERERJSvAw1ff/21tGrVSurXry+TJ0+WCxcueOJpiYj+p1JTkd7TRUZuFWk1UiS0mO29c+28yIpJUuuHm2Tg8delgf8BmzVmUNwQQQhb2QauhNkmMA3kP8+2l+n3NZUOtcvYrTOJWSzeW7RXbnpriQybuUlWHzhnKcJLRERERJSvAg0zZsxQU1Zi7MeTTz6pprYcOHCgLF++3BNPT0SUdXrMp3aKdHtXpFRNm3vH30iV5glL5K1zI+Th/Y9ITPyy/03lKCIpaYaaeQIzQngCnqt97TLy5X1NZfmz7VXwoXhYkM11U9MNmb/tpNw7dY10fm+5fL3qsFxKdH3mBRERERGRLR65Qu7Xr58sXbpU9u3bJ88++6wULVpUZs6cKe3bt5c6derIpEmT5OzZs57YFCKiDMHhIk0fEHlsrciAX0Sqd7K7Zypf3S73Hn1NGsUvlrDUeElJvCoBki5hgSJFQ/0zZl0wBSHcrVKJMDWcYvWLHeW9Pg3VlJf2YEaLV+fskBbjF8tLv22TXdkUmbxu2A/YH+bFg/uGyF1Qt2XbsXhZdeCs+onfiYiIyItmnUhNTZU5c+bIF198IQsXLpT09HQJDg6WO++8Ux588EHp2LGjpzcp3+CsE0TX4cyejOkxN39ve3rM/5cufpLoHy5+hYpLoUJWtROuY9aJ67H9eLyaInP2fydU7QhHmlYurmar6FqvrIQE2qlZkROYdeKP50SOrHK8Xh7tG1fjrBMFj57mFnVbklLSJCQoQMpEhMotMZGcqpWIiHxWjBtnncjz6S2PHj0qEyZMkI8//tgyDrpKlSoybNgwefjhhyUsLCwvN8/nMNBA5KLpMTd9nTE95qXjjtctUlEkso5IRPmM2RmKVxFpNSLLVJmeEn8tRX7ZeExmrD0iB88kOFy3VOFg6dO0kvRrHq0KXuYavkZWfiBy4ZDj9fJ437gKAw0Fi3maW9RlQTHYhKRUCfT3kxqRhaX3jZUYbCAiIp8Uk18DDUuWLJGpU6fK7NmzJSkpSQUVGjduLKtXr1ZZDpUqVZJ58+ZJvXr18moTfQ4DDUQulJYismuOpK+eIv7H1ztet1QtkWYPijTqlzEsI4/h1I7ZKL5dfUT+3hWnGkj2+PuJdKgdKQNbRkvr6qXEHzfk/AlF0pIdrxMQ7PNBBmCgoeDA8Ii3/tgt6w+fV9Pc6hlo8Pk6fvGamnXmxsol5MXbaksQp24lIiIfE+PGQIPHJzSPi4uTt956S2rUqCGdO3eWH3/8UapXr65mozhx4oQqEHno0CF55JFHJDY2VoYPH+7pTSQi+t/0mPXuFv8HF4kMXaz+L/6BtvfO2T0iC54ReS9GZNFYkUsn8nQvojHUqnop+XRgE/n3+fYyvGMNKR1he8gCYhCLdsXJ4C/XSftJy2Tq8oNy8WpyTp8wY0iEoyUfBBmoYNlz6rLNaW7xE7+j8Crux3pERET0P3aumF0Lkf8///xTZS/Mnz9fUlJSJCQkRO69914VULj55pszrV+xYkU1lGLPnj2yZs0aT2wiEZFjFW8U6fWlSPxxkfVfiGycLnLNxlS9uO3fd0VWTRape6dIi8dEKjbJ071brmgheapzTXmiQ3U1zvzbNYdlzcHzNtc9cu6qvLFgl7yzcI90b1heBraIloaV7BebJMrPLielqJoMGC5hPc0tfg8PCZCk1DTO6kJERJQXgYbKlSvLsWPHVMAB2QsPPfSQ3H///VKyZMls/w6zVRAReY2iFUQ6vSrS5lmRrT+KrJmSkc1gLT1VZPvPGUvFZiItHhWp00MkwCOnXZuQ2t2tQTm17I27LDPXHJFfNh2XK0mpWdZNSk2XnzceU0vDikVV8UgEHkKDXFA8Mr8qQMNHCoqIkCBV+DHhYqK6hjEHG/B7QlKaRBYJlSKhtqeaJSIiKqg8UqMhKChI7rjjDpW90KmT/SnkrO3du1dOnjwpbdu2dev25Ses0UDkYTiFHliSEXDY/3f2hSNRx6HJYJFCxcUbIMjw++bjqpbD7mzSv4sWCpJ7bqwo/ZtHS+VSeV+HwqtqNBSwgpgFrUbDhsPnpShrNBARUT4T48YaDYGemlmibNmyOf67mjVrqoWIyGuhwVi9Y8ZyZq+c+vt9KbnvZwkykrKue+mYyKJXRf55W6ThvSLNHxEpnbfnuMIhgSpw0K9ZlGw4ckEFHP7YflJS0gybM1pMXXFILW1qllbDKjrULiMBuSkemd8gkwFBhuym+NTr+vgUnwVFcKC/msIy/lqy7Iu7IueuJKvhEshk0LNO4H4WgiQiIsqDQENuggxERL5mzeWS8lPgQ3KiWHfpnPin9EiaJ6XSz2ZdMeWqyIZpGUv1ThnDKqp1zNNebqSEN61cQi1nLteVWRuOqqEVJ+ITba6/fO8ZtaAgXr/mUXLPjZXsFpsscCo2FfGzqrVspIscy2bmEvJKLapmDPNEfRMUfkRNBgyXKBMRqoIM+n4iIiL6H48OFt66dasq8rhixQo5fjxjbvoKFSpImzZt5LHHHpMGDRp4cnOIiFyaYo2GyN64K1KscAnZW/EBeU/uk7oX/5FmcT9KjeSdtv9w/6KMpXTtjAyHBn1EgsPy9J1BwGBY++rySNtqsmT3afl2zREVVPg/9s4DvK3yeuOvpm15720nzt4he0AgC8IMeyZAKZSWMgptoGwKYRQKLdDSUlb/kLDDDiRkEBKSOM7ee3jEjrflpS39n/Ndy5alK2/Jsn1+PB+KdNd3v3tl+zv3nPeVgyz+Xlp5GP9YfQQXjkwWFpkTMqM9hPP6FBRkULppWdi7qzNMV0DBhPGZ0cJdotpoEZoMQ5LCOZOBYRiGYbo70PDqq69i0aJForbVVRbi0KFDor377rt46aWXcN999/mrSwzDMD61wbNDjX3Rs7E3ahZMp3JwE5ZjfO16KBye4osoPQR89wdgzV+A8bcCE++QhCe7ESqJmDs8UbRTZXVYuiUXn24rECUU7lCpxTe7C0UbmhQuAg6Xj00Vav0M0xug8oiRqZHd3Q2GYRiG6RG45Xb6hlWrVuH++++HVqsVrzt37kRlZSWqqqqwa9cu/PGPfxR2lw888ADWrFnjjy4xDMP41QavIHQ43ox/BNuvWAec/YB3MUhhj/l34B+jgM9vAwq2BcSVIvHHRy8eji2PzMZLV4/G6DTvEy4SlXz0y32Y/NwaPPn1PhwtbllkkmEYhmEYhuld+CXQ8Morr0CtVuPHH3/E3/72N4wZMwaRkZGIiIgQ5RKUyUDLlEolXn75ZX90iWEYxjc2eCZrs6wtVxu8ILUKwbEZkj3m/QeAS/4BxA2R36HDBuxbBrw9G3h7jvRvm2cmgb8he8trJqTjm7vPxte/n46rx6chSK306mjxf5tzMffv63H9fzdj+R4SmeQaAoZhGIZhmN6OX3Jac3JyhEXltGnTvK4zdepUnHfeediyZYs/usQwDNOlUL02icPlldcL3QJn+QQFGeg9KdTTclpPQDoME34llUkIe8w3JK0GOUhE8POtQESqZI857hZAF9PtV3BMepRoj140DJ9vL8CSLbnILa+XXTf7RIVopP9ww4QU3DAhFcmRwfI7Vml7tv0jCT/aZT7rTij4RW4XLeHrcQ+EPjAMwzAM03sCDfX19YiPj291PVqH1mUYhukzNnhu9pjY8h9g90eSM4U71aeB1U8B6/4KjHXaY3rJiPAj0aFa3DEjC78+uz82HCsTFplrDxXD7umQidIaE1776ST+9dNxzI0txcKkfEyLrGg+t4zuD0y/zycTThLtJD0NKnWhLBQK/NC161ICyF1CnG9RNcJ3/gvh9QWICtF4tyP14biLIMPGVyUL0JbwZR8YhmEYhuldgYb09HRs3rwZVqtVlFDIQctoHVqXYRimT9rgxQ8GLnkFmPUYsON9IOe/UnDBHasB2Pau1ALEHpNQKhU4d3C8aAWV9fgoJw8f5+SjvM7zKbYNSqwoTxQtS12GBaFbcVXobkQqG+w06cm3umvtMrNPlDddG4tNlLp0mUUhPYmnSXJr0Dq0rh9wnm+FvhpXFO/HYNNeVCgVCNWqodO6uWI48cG4N+6Xggy5m9q2ri/6wDAMwzBM7wo0zJ8/X2gv3HbbbXjttdcQFRXVbHl1dbVwm8jLyxPCkAzDMH3aBo/KIs7+AzD198DBb4HsfwMFOS3bY5LWwxSyx7y+2+0xibRoHRZdMBT3zh6EFfvOYEl2LraeqpRd94Q1Dk/rL8SLNefj8pBdWBBrxkgfTLo/25Yv7EfJGYREO+uqjKLUhbJQiE4FGyjIQ0/iA6Q0wPV8FTazyGywWO3Ypx6KcIUW/SPDkBgR1FTW4c8sjLSJkgWoK/7uA8MwDMMwPT/Q8PDDD+OLL77A0qVL8fXXX2PevHno16+fWJabm4sVK1aIYENWVpZYl2EYpifTZTZ4Kg0w8kqpkfsEBRwOfAXYZewxyw4D390PrP6LpP0QAPaYBAlgzh+bKtrBgjIs+fxzfFmciHqH51N9o12Fj+vG4+PdwFkVW7Fwaj9cNCpZCFB2Bppk05N9mnRH6TQe+hlU6kLLKUDUroCQOxRACIAn8e7nmxERjIgiDYLsKqhVKlQZ7SjQmxAXGQIV9dnf8hEUZFC6XVPWCGUYhmGYXoVfAg0xMTHYsGED7rzzTixfvhyfffaZxzoXX3wx3nzzTURHe7F8YxiG6cukTQCufgeofgbY+rZUNkFWmO4YqyR7zI2vASMuB6bcJW0bAAxLCsezAw7iz8ol+DLoMnxwJhNHDWGy6+7M12Nn/m48890BXDsxHQsmZyI9pmOZGpRdQuUSlMngDDIQ9ErvSU+DltN6XRIg6mY8ztfR5FZCmRyGOhsMFhv09RbEhPqnjINhGIZhmL6FXwINREpKCr799lucPHkSv/zyCwoLCxs/P/vss9G/fxtqWxmGYfo6ESnA7CeAc/4E7P1UynIoPeTdHpMapaqTcOTw+VKWRDcTrjTh5qQ8LEw+jezqaCwpSsfKigRYHZ7ZBJX1Frz58wn8d/0JnDc4HgunZuLcwQneBQ1lIOFH0mSgSbYzyOCE3pNoJ+lpUKlLb8DjfN1EOTUqhQhCmNlqlGEYhmGYnh5ocEIBBQ4qMAzDdBLSYSBrTLK6PPGTFHA4+qP8ulT7Tu3HxyV7TNouAOwxaQ48NbJStGJTED4+k4IPCxNRbI+QNS346XCpaGnRIbhpciaunZCG2LDWSxXIXYKEH0mTgcolXIMN9J6cQUi0k/Q0egPu5+uOxeZAiFYBbWfKRJjOwVafDMMwTC/H74EGhmEYpguhSfOAWVIrOyrZY+76UN4es6YQWPMX4OcXu98ek8T/XOryEzX1uC/tCO5yfIQ14ZfhffNMbDohLx5ZUGnAX1ccwt9XHcElo5OxYGomzkqP8shWcEJinOQuQcKPpMngrtFA9qO0nNbrDbifb0ZEkx6CwWQBvdOpgchgJWC3SdfCn3ahbte+8bO+Alt9MgzDMH0AnwQa3n///U5tf/PNN3dZXxiGYfoMcYOAi19ussfcQvaYBS3bY5ItJuk4UKBC6ccn3F4cBjQKYF5sCeZdOB7HKixYuiUXn28vQI3RUwCTUv+/2HlatBEpEVg4JROXjU2BTtv8VxtNfMnCktwlSPiRNBmoXIIyGSjIMCgxTCzvlBBkAOF+vntr6nBeQzlFluWAWB5u0UBVoOoeu9C+7i7BVp8MwzBMH8AngYZbb73V65OllnCmtHKggWEYphOEREtWi1N+DxxqsMfM3yK/7vE1UosbLGU4jCF7zFDfDD9ZO0a3QY+H1lFpMTAhCE9eOgKLLhiCb3YV4v3NuThQVC27yf7Cavz5i7149vuDuHp8GhZMycSA+CahSefEt3FibJXKJdo0Me6BNDvfagP05WnI06oQolEJ61Gd09pSZtx9YhfazmvfZ2CrT4ZhGKaX4pNAwxNPPNGhQAPDMAzThajUwIgrpFawHdjyb2D/l17sMY8Ayx8A1jwtaTiQlkNkWtdeDvq9QAEQeqLbYr+10roNUIbC9ZMycN3EdOzMr8KSzbn4bk+RrJghZT68t/GUaNMHxooshznDEqFWKcXElywsKdWfhB9Jk4FS/XtLJoM7zc7X8BAitQ4MTmzhfN3GvUvtQjt47Xs9bPXJMAzD9FJ8Emh46qmnfLFbhmEYpqOkjQfS3gbmPt1gj/keYKiQt8fc+A9g0+uSSwWVVaRP7Lpxp0mkOqiDmyowLiNatEcvHobPthdgSXau0GyQY+OxctGSIoJxw6QM3DApHQkRwb3CwrKt0ES/q8+3w3ahnbj2DMMwDMP0LHrnYxyGYRimZXvMBw4Al74GxA+TX4/sMfd/AbwzB3hrNrD3c8AWOPaP5Dbx23MH4OdFM/HurRMwc0i81wfhZ6qN+PvqI5j2wlr8fukOkfYv58bAtI2+ZhfKMAzDMEwPcJ0wm83YuXMnCgsLxfuUlBSMHTsWQUH8lINhGMZvaEKA8bcA424GTqxrsMdcKb/u6W3Asl8HnD0moVIqMGtoomikD7A0Jxefbs1HZb3nJNdqd2D53iLRBiWEYeHUTFxxVirCe4mtpb/otXahPcVysqf0k2EYhunT+C3QUFtbK7Qb3nnnHfFvV8LCwnDbbbfh6aefRnh477AXYxiG6Tn2mDOlJuwx3wR2LW3dHpNEI0k8MmEoAoWMWB0evnAY7p8zGN/vLRLikbvyq2TXPVpSiye+3o8Xfjgkgg0kHjksOcLvfe6J9Eq70O6ynGyv1SdbYzIMwzA9BL8EGvR6Pc477zzs2bNHvB8zZgz69esn/p2bm4tdu3bhtddew9q1a7F+/XpERvad+lmGYZjAssf8GzDrUWDHB0DOfwF9vrw95vb3pCbsMX8nvfrTHrMFgjUqXDkuTbR9p/VCx+GrXadhtHhO4OrNNizdkifaxH7RIuAwb2QSgtSds37szfRKu9Duspxsr9UnW2MyDMMwPQS/BBook2H37t2YNWsWXn/9dQwb1rwm+NChQ7jnnntEoIHWffXVV/3RLYZhGMarPea9khDkoe8a7DGzW7bHjB0ETCF7zBt8Z4/ZAUiM8IWrRuPhi4ZhWYN45ImyOtl1t56qFC0uTCscLkhAkqwgGU96tV2ory0nu8rqk60xGYZhmABG4fCDIlZaWhrsdjuOHTsGnU7+jzaDwYABAwZAqVSioKDA113qtYwYMUK87t+/v7u7wjBMb+L0diD7P5JApJw9ppPgSEnDYeIdQFQ6Ag36lbfpeDne33wKqw4Uw97Cb0ClAkL7gbQczhkYByV9QA+VbTYsXrwYjz32GFSqvp35YLHZe4ddqNUE/PCglNGQPhlQul1Xuw3I3wJkTgMufLHzGQ0d1Vnwdz8ZhmGYXs0IH84d/ZLRUF5ejssvv9xrkIEICQnBjBkz8M033/ijSwzDMEx7SB0PXPWWiz3mu17sMfVSrfumfwLDL5OyIsST18AQpiMtgekD40Qr0hvw0ZY8fLQ1H6U1Jo91KQix+mCxaJmxOiyYnIlrJqQhPKhvBxd8bZ/ZJ2CrT4ZhGKaX45fHDllZWaisrGyTlkP//m1IJ2QYhmG6h4hkYPbjkj3mZa8DCcNbsMf8EnhnLvB24NljEsmRIXjg/CHY+NAs/PPGszC5v3cnjdzyejz7/UFMfm4NHlom6Q0xDMMwDMMw3Rho+M1vfoN169YJ0Udv0DLSaLj99tv90SWGYRims/aYZI35u03Awq+AwfNaLrsge8x/jAI2vAzUy2RCdLO44SWjU/DJnVPx4/0zcPPUTIQFySf8max2LNshlfdd8cZGfLotH0aLzc89ZhiGYRiGCWz8Ujpx3333CX2GmTNnCtHH6667DpmZmY2uE59++qkQibzzzjtx//33+6NLDMMwTJfbYx4Dct4EdpI9pozgYk0RsOZpF3vM3wWUPSYxODEcT88fiQfnDcWXO09jyeZcHC6ukV1372k9Hvx8D55dfhDXjE8TjhX94gJHCLPTegA9ka441/ZaTvbmfjIMwzBMIItBOsWy6FBUHyuHt2X0mdXagvAY0wwWg2QYptsxVAE7PwC2kD1mXsvrDpglBRwGzgkYe0z3303bcivxweZc/LCvCBabAwrYcWvIDvzPMA4Ot8TAGYPjsXBKJmYNTYCqQTyyW6Ff8aSZQdaNrTkcTL+vZwcbOnOuriKLLdEVIosy/bTZHagyWIS4JuleRIVooIrN6t5+MgzDML2eET1dDDI9Pd1rgIFhGIbpZYREAdPukQIIh5dL9ph5m+XXPb5WarEDgcm/BcbeGFD2mPS7a2K/GNFKa4aLUokPN58EvMhNrD9SKlpqVAhunJyBayekIz68Gyd79NScJrStTUyd6/bkiWlnzrWrLCc70M96sw11ZiusdoeIQZgVQIVSAXu6GYlTurGfDMMwDBPogYZTp0754zAMwzBMIKFSA8PnS+30DmDLf4B9ZI8pM0svPwZ8/ydg7TMBa49JAYPfzxyI26dn4oXnN+GcQfFYf7Rcdt3TVQa8tPIw/rH6CC4cmSwsMidkRndv0F24fyg9U+0LtqLX0d5zpetC2QN+LjEpiRyNE2X10NutIsigVpF9qh3DzYdQUFqLUyfLMXlQSrf3k2EYhmECMtDAMAzD9HFSxwFX/heY8xdg2zuSPWZ9eY+zxyTUKmkC+96tE5FXacSHW3Lx6bYC6A2eARQqtfhmd6FoQ5PChY7D5WelehWb9Ck08Va6WXP21pL+jpyrny0nyT61oMqIKqMdWo0aoQ33hMJhg7JGIe6n7QdKMC4rSZRTdFc/GYZhGKYjBF5BLMMwDNO77TFnPQbcvx+47J9AglQb2KI95luzgD2fAdZWnuJ2A/3jQvHoxcOx5ZHZeOnq0RidFul13UNnavDYV/sw5bk1eOLrfTjiRWSS6RuYbXYYLDYRcHAGGVyDWfR5aY0Rh8/wfcIwDMP0PPz6SIVKKNavX4+ioiKYTCbZdSit9PHHH/dntxiGYZhuscdcCJy1ADi5XtJxOLKCIgye6xbuAL64HVj1ODDxdmD8r4DQ2IC6ZsEaFa6ZkC7a7vwqfJCdi293Fwo7THdqTVa8vzlXtClZMVg4pR/OH5HY/Kk10+ux2x1CBFKjks/Woc9NNhuqjV4EQRiGYRimrwcajEYj7rjjDnz44YfifUtGFxxoYBiG6QF0lWUiLc86V2rlx4EtZI+5xLs9Jmk4rH8JGH0dMIXsMYch0BiTHiXaoxcNw+fbC7BkSy5yy+tl180+USFaQngQrp+UgRsmpSM5MqTrrge5FNhtkj6B702mAh8aAxoPGpdu1jdQKhVQQQGLWf66UNlNkEqFiGCNz/vCMAzDMD0y0PDQQw9h6dKlSEhIwE033YSsrCyEhYX549AMwzBMT7FMjB0AXPQiMPMRKdhAQQc5e0yrEdjxf1LLminpOASgPWZ0qBZ3zMjCr8/ujw3HyoRF5tpDxSIl3p2SGhNeW3MU//rpGOYOSxTikdMGxLZNPLKl60GT6vwtQF0pULwPSBzZ/HpQAKI3QudllxkLQ6U0Hisf8dRw8LPVp1alhE6pQC1sqDeamjQa4IDVZhfdiw8PxpCkcJ/2ozdhttpFqUmNyYLwII0YO606sH4uMAzD9BX8Emj45JNPEBcXh127diEpKckfh2QYhmF6qmWisMe8W7K7PPx9gz2ml2Od+ElqTnvMMTcAQYEVyKYn1+cOjhetoLIeH+Xk4eOcfJTXeWYgUCr9iv1nRMuKD8WCyZm4anwaIkM0HbseFISoKwEsBmkdc62nG0NvRM5dQgQfLEBtMZCX3XIgwQ9Wn0oFMMRyGCmwwGy0w2GkzxSwOxwiRhIZpsGc4QlcUtNGsk+U48f9xSipMcJksSFIo0JCeLAoS5qSFVilVgzDMH0BvwQaamtrMW/ePA4yMAzD9DZ8aZko7DEvk1rhTiCb7DGXtW6POe5mYNJvgKgMBBpp0TosumAo7p09CCv2ncGS7FxsPVUpu+6J0jo8/d0BYZM5f2yKcKwYmRrZvutB2RPFe6UgQ1gikD5Z/kk+PcWnkoGeDPWfzsMbzuyO+gogbZJnBoy/rD5d+qmjiqBqE0oq64UwJAWaVEoFQjQqpGQMRebAZN/3p5cEGT7blo8jxbViDCk7pK7KiLzyeugNUkCPgw0MwzC9MNAwcuRIVFdX++NQDMMwTG+0TEw5C7jyTWDuX4CtZI/5jnd7zE2vA5vfAIZdIpVV0OQ6gOwxiSC1CvPHpop2sKhaBBy+3Hka9Wabx7o0Af14a75oZ2VE4eapmbhwZLIQoGzT9UgcBZjrpHG44Dn5J/V+0iXwKdR/Knnwph1CugxUMkHBBmU3Wn269TMRQIzNLlxISPiRNBkGJ4ZDow3u+dfET+USlMlAQYYonQapUSGi5Ij0wE5XGXC0uFYsH58ZzdkhDMMwfsQv+ZN//OMfsW7dOuzcudMfh2MYhmF6K+FJwKxHgfsPtG6PeeBr4N0LgLdmAns+DUh7TGJYcgSevWKUsMh8ev4IDErwXvqxM68K93+yG9NeWIsXfjiE/Ap5kclm0FyVJqw0saYgg1zrLRNaOg9v50jNmy5DN/dTExSCERkJmDo4VbzS+15zTXwMaTJQuQRlMjiDDAS90nur3SGWs00owzBML8xouOaaa1BQUIC5c+fi7rvvFq+pqalQehHuysgIvHRXhmEYJoDQBLfDHnMn8MUdwI+PA5PIHvO2gLPHJMKDNbh5aj8snJKJLScrhEXmyn1nxETJnYo6M/7z83G8uf44Zg6Ow0JlHGY4yMWAYfoWJPxImgxULuEunkrvQ4NUMFnZJpRhGKZXBhqI0aNHIyYmBs8884xo3qBfClar1V/dYhiGYXoycvaYu5ZKoofu1J4B1i4G1v8NGH0tMPl3QOJwBBr0e5DqyamVVBtFycSHW/Jwptooq/W49nAZ1mIc0lX9cZOqGNcmFSFGI6Nj0V14s950/dxb6UZvKOlgfAq5S5DwI2kyULmEa7CB3teZbEiMCGabUIZhmN4YaPjuu+9w5ZVXigACuU9kZmayvSXDMExvtRHsLstEpz0mlVYIe8z/AFXe7DHfl1rWeQ32mHMDzh6TSIgIFsKRd503AKsPFossh43HZLQpAOTbovFCXjReyR+ES+KKsDAxD2PD9FD4TXzAE7PFhvIfX4Ki6qSoj48K0Qixw0aRSlONtGJQuKf1ZjusJtttaxhI9y3TKehak7sECT+SJoO7RoNaqRDL2SaUYRimFwYannzySfED/7333sPNN9/cNl9whmEYJvDxh0p/ewmOBKb+vrk9Zu5G+XVPrJNazABgyu8C0h6TUKuUmDcyWbRjJbVYuiUXn28vQI3RMwPQ7FDhi9I00UZqCrEwbCsuC9EgpBucANbszce5J/Yiq34PzAqgQqlAqFYNnUbZZLtJaEIkIU85681WrCY7ZGsYiPct0yEooETXmtwlSPixvNYsyiUok4GCDIMSw8RyCnQxDMMwvSzQcPDgQcyYMQO33HKLPw7HMAzDdKeNYKBYJpLw37BLpVa4S8pw2Pu5vD1mxXHJHnPNM8D4wLXHJAYmhOHJS0dg0QVD8M2uQry/ORcHiuSdnfZZUvBQ5Xw8W30Rrg6qxYIKM7ISvE/au9pu8MSZSpxlsMJud2C/cghgVyJSoUb/qBAkYjdQWyJtEJogWXM6xRrbaDXZLlvDnnLfMu3GeY0bA05WqVyi1YATwzAM07MDDVQuQY1hGIbpBbRmIxiI9fUpY4Er/gPM+YtkjUkWmfVlnuuZnPaY/5ICFAFqj0notGpcPykD101Mx47cSizZfBLL9xXDbPMUj6y2afDuyWi8+8p6nD0wDgumZGLOsASRKeFLu8E4nRqx0EJTp0S0Lgi1ZgeqjHacrjIjXqFssr5yumI4Aw12H9ga9sT7lmkzFEyga00lNE6bUCqX4EwGhmGYXhxouPrqq/HRRx/BaDQiODjYH4dkGIZh/GHP19MITwRmPgKc/QCw73OprKJ4n+d69ESd7DGppZwlBRyGXw6oA+9JN02ux/eLEe2xWhM+3VaAJdm5YrItxy/HykRLigjGjZMzcP3EdKEF4Qu7wZTIEMDFgZMyDowWM4wWG8xKO4J9aGtIKfROW8ORqZE9+75l2gQFFRqvNcMwDNOt+KVgbfHixejXrx8uu+wyHD9+3B+HZBiGYZiW7THJGvO3vwC3fAsMuYhmofLrOu0x/zEKWP8SUCeTCREgxIYF4XfnDcD6B2fi3VsnYOaQeK8P58nF4pVVRzDthbX4/Yc7RBkCZQP40m6Q0KgUsDkcopzCV8dhW0OGYRiG6QMZDZdccglUKhXWrFmDoUOHiqBDamoqlDIK3/THAa3HMAzDMD6HJqj9Z0iN7DFz/is5VrRkj/nzKwB+CxQfBFJGBuRFImeHWUMTRSO9gqU5ufh0az4q6z31Kax2B5bvKRJtUEIYFk7NxBVnpSI8WNMFdoOe+7DYHAjVKKEk94lOwLaGDMMwDNPHAw3r1q1r/LfNZhNZDd4yG9iRgmEYhuk2e8wL/yqVVrRkj2kzSskP/z0H6H+OVFYx6PyW7TEpU6Ct2gDtWbcNZMTq8PCFw3D/nMEimEAWmbvyq2TXPVpSiye+3o+//nBIBBsWTEzB0KSwdvXD1W6wUN9UvqGAA3VGE1RwIESthJY8Lu12aXubDTAbmotB2m1S85JlwbaGLdDF9xDDMAzDBGSg4eTJk/44DMMwDMN0sT3mDw32mL/Ir3vyZ6mRPSatP/ZGT3tMmvRtfBWoPNm628G0e4FNr7VtXRI2bMdEMVijwlXj00Tbd1ovdBy+2nUaRoun8mKd2YYlW/JEmxRRiQVJ+ZgXWwyt0tFqP1ztBk+eqRRaCak2OxL1e5DUsDy6rhZKSw1gJ3tOB2CpA/R5zfbjUChhOrEJxctfRPX4ezEkOUJs21lbQxKRJN0GKr2grAgKWLjut63rBCztud/aeQ8xDMMwTEAFGjIzM/1xGIZhGIbpYnvMS6RWtFsKOAh7TJu8PeYPi6TSinELJXvM6IbfffRkmSZ9uZtaPyaVbLR1XdpvB4UNSTDvhatGi0yHZTsk8cgTZXWy6+ZUR4sWp6zFdaE7cGPodqSq9S32o9FucJ8G5rwMHDepRDlHiEaFtKggaKt2AZV1TRkcotkaZTJIvsGuUMJSU4ZTxw7hy9pDiImM8LAqbK+tIelQNK5rsYkSD/d127JOQNOe+60T9xDDMAzDdHuggWEYhmF6NMljmuwxc94BfvHUOmi0x9z8TyD7DWDoJVJZBblWOEmbCCjcnoxTmUDBVs99tWfdDhKp0+C2s/vjV9P7YdPxcry/+RRWHSgWE313yuxh+FfNDPy75hzMji7GQtUqnO3wrirdaDdY9Chq6uuE3eDgxHBoHBZg5SNNZRH1pYCOLLClPRksVjjqylCBSDiggNlmx4myepyotIrsBee+22trSAGEz7blCztMcqogEUnSkaASD+d+idbW6RHBBj/eQwzDMAzT7YGGAwcO4K233kJOTg7Kysowf/58vPjii2LZpk2bsG3bNixYsAAxMTH+7BbDMAzDtN0e87yHgF8WA5e+DuS0YI958BupUZAiKEKaVNOkz6lD4MSzckGiPet2EtJHmj4wTrQivQEfbT6JjzYeQqnF82m3HQqsqkzCKixEv9o6LIjMxdUT+yFKp5W3G0yLAkCtAWvDeVE2A52j8zwVShHgqLVYEEJDpVJCq1IiIkSDUckRyKu2iRIJyjagwIJrIKE1W0MqhaDtKIAQpdM02mGSywbZgNJ+V+w7I6o4WlpH7tgBjR/vIYZhGIbplkDDK6+8gj//+c+wWq2Nf9RQsMGV+++/H0FBQbjzzjv91S2GYRiG6RhjbwDG3QSc+kUqqzj8vaQ34A6VXRAKFaDVAfHDJHvNACU5MgQPzBmAu03/xY+Hq/CBdRa2VMs/xT9lDMXiH47ipVXHcdmYFOFYMVoEFjoGZS9QJgGNotplMk9/M9DEn3QYqKSBshdaCiy4Q+vTdrRvZwDBfb/HSySnkZbW6cixGYZhGKYv4peQ/PLly/GnP/0J6enp+OKLL1BSUuLh1T1t2jTEx8fj66+/9keXGIZhGKaL7DHPAW74ELh3BzD5d4DWi0sDaRBQ0GHvp8CpjUB9RUBfARJ+vES3H5+MyMGPZ23EzUl5CFNJDwvcMVnt+Gx7AS7750bM/+cvovzAaJHRsmgFOwUZHA5ZfUKa8JPYI+kwUIlEeyBRR9JboFIId3cr537rLVbUm60trtORYzMMwzBMX0Tpr2yG0NBQrFq1Cpdffjni4qgW05OxY8fi8OHD/ugSwzAMw3QtMVnAhS8ADxwALngeiPIihExlFeVHpbKKIysBfb5XC8dAYbCuDk8POITsCT9jcdYBDNVVe113d4Eeiz7fg8nPrcGzyw/glBeRSTmUSkVDuYLnMgpAkKNEkFoldBjaAzlHkKhjncnq8aDDuV+dRg2dVt3iOh05NsMwDMP0RfxSOrF9+3ZMmTIFWVlZLa5HAYgNGzb4o0sMwzBMb7HzC0h7zLuAyXdK9pib/wXkeXEAqCmSmlID6GIAk5S+3xiQcK+np8+aXTO976+ZSz/ClDYsSMzFTfEnse1EMT5wXIgfKlNgsXlGBvQGC97acFK0GYPjsXBKJmYNTUBzxQBHM9cJrQJQK0gC0gGbzQa1Slpb6CToDcK2khwg6Fzbcx/TK21Hoo6kt+Cuv0D7HZAQJrqjN1R6XaelYwckrdxDDNMX4d93DNOLAg1msxnh4a3/YqaSCrWajTAYhmH8SY+38wt0e8xBc4FlvwZO/AyYauR1HOwWIH8L8MYkIDIDsFladAYorjbh7ZWHUVRn9/01k+kHFRZMDAImZu5FydnX4tOdxfhwSx4K9UbZXaw/UioaTd5vnJCCa81axNOCulLAapSyOhrSLKMdDtjhQIStCpWOaFQbLNh7uhpQaTEoMUyco5wYY2v3Mb2ScwSJOpLeApVCUJYCBRBov/NGJon9UJDC2zrejh2wsLsEwzSDf98xjP/wy6y+f//+2L27QQyrhWDEnj17MHjwYH90iWEYhmmj5R8HGzqJSgukTgB0sYDFAJQeBkoPSRNsdygQUbJfmspHZQAJw4GwBEkLwiXIsFUfgezyGlAigU+uGfU5un/r60X3R0JUOO6eFYHfnjsAaw+V4IPsXGw42lzs2QllBry0+jj+oTgXF8UOxkLdzxivONxMk4FyGExmG6qsQchVZ0GvTkZGbCQSIkK8BlLacx83BiOsNiRGBMsGaNqyTsDSjmsn1mWYPgL/vmOYXhhouOyyy4SNJWk1PPDAA7Lr0PLS0lLcd999/ugSwzBMn6ctln89zs4vEKFZ9PT7AJs04RVYTcD+L4GcN4FiCiy44wCqcqWWNBqYdAcw/HKYoRGZDBRkiArV+u6ayfVZDpqoNkQJyCXi/BFJop0sq8PS7Fx8ui0f1UZPAUmLQ4Gvy1LwNW7A0MRQLJyYjMtHJYgMAkJHlpVQQ19SC6VZgd+GaEXJgtw5tec+pkABvVJ5BYk6kt6C+37bsk5A04FrxzC9Hf59xzC9NNDw4IMPYunSpVi0aBG2bNmCK664QnxeXFyML7/8UjRaTpkPd999tz+6xDAM0+dpi+Uf2/l1ETS26qCm9/Tv8bcA424GcjdK9piHlsuXVZzZA3xzD7DmGVQOWYAa/dmwObS+v2bufW4H/eNC8dglw/HH84fg2z2F+GBzLvae1suue6i4Do9+dwzPrzqFq8alYsGUTAxKDAdJLo7IoJBD197HFDBobWzask5A04lrxzC9Ef59xzC9NNAQHR2N1atX4+qrr8Znn32Gzz//XHy+YsUK0eipw/Dhw/HVV1+1ScuBYRiG6TxtsfxjOz8fQ+Pe72ypVZwEcv4L7PgAMJOWgxt1JUjc8QqeUbyODcEzsdd4A86EDAroaxaiVeHaCemi7c6vEmUV3+wuFE8X3ak1WfF/m3NFm5IVg4VT+rVJE4HvY4ZhWoN/TjCM//Gb8iJpL+zatQvffvstfvzxR5w6dQp2ux1paWmYO3currrqKqga1KUZhmEY39No+VdlFAFf12CD086P6tPZzq+DkJOCXPq66+eu6esRKcCcp4Bz/gjs+VQqq6g85bG5xmHBLMOPmHX0RxwPHYeNcdfiUMRU2B0KmIxGhIYpEamxS+UZAZQuPyY9SrRHLxqGz7bnY0l2HvIq6mXXzT5RIVpCeBCun5SBGydlICky2Hf3sbdr1dmx89V+GYZpF/z7jmH8j18tHpRKJebPny8awzAM0720xfKvx9n5BQo0wdz4KlB50vPz4n0N7hMAgsKBxFGSjYO7UN/d24GjK6WyilPy1s8D6naIVqZNRa4yHRX2MMRUhWLorihgt8zklfZL9fvdOLGNDtXiNzMG4Pazs7D+aCmWZOdizaESMTTulNSY8Nqao/jn2qOYOzwRt0zth6kDYpsFEzp9H3u7Vp0dO1/tl2GYdsO/7xjG/7CXJMMwTB9Fq1a2avnX4+z8AgV6ik0TzNxNzT932CVLR3KfIDQhgLFafpLpsAFDL5Za0R5gy39g3/MZlHbPJ+Rx5tOIw2nYoYCtOgKqkzGASuO9bwFQv69UKnDekATR8ivq8VFOHj7Zmo/yOs/zszuAlfuLRRsQHyp0HK4cl4bIEE3n72Nv16qzY+er/TIM02749x3D9PJAQ319PbZt24aioiKYTDIpnQ3cfPPN/uwWwzBMn6U9ln9MB0mbCCgaJrl2G1CwFagtlt6HxkvLlaqmQAQtdyd5NLJHP4Mf6q/G4PzPcaHhO8TAU1xRCQeUZj1grgYi04CEYUBogiQyKbffACE9RocH5w3FfXMG4fW1x/DRljzZgANxvLQOf/n2AF5ccRiXn5Uigg5ddh+7Xisn3q5Je/DVfhmGaTP8+45hemmg4YknnsDf//53EWzwhrO2kgMNDMMw/qPH2/kFOjTBdAYSxHuF5zLnck+NxGbWbDvKtTgRdwsORNyG0VVrMLX0U2SYj8ls4QD0+VILiQHih0oT2wBHAQXqTTakRIUgI1aHaoMFueX1sFJKgxsGiw0f5eSLNi4jCjdP7YcHzh+EU2X1Hb+P3a8V0RXD5qv9MgzTLvj3HcP0skDDiy++iMWLFwuxx4svvlgIQ7K7BMMwTODQ4+38+pg1m12hwK7Yi7Ar5kL0q92J0QVLMcWyxUPqQWCoAPI2AQoVoA0DakuAqHQE+nmOSIkQDx/GpkfjVFkdjpZQIMwqu92OvCrsyNuFmFAtrpuYLsQjKUuCYRjGHf59xzC9KNDw1ltvISQkBBs2bMC4ceP8cUiGYRiG6f3WbAoFToWPw7qYTChr/4Fxlh3QWOsBu0Ve86FoF/D6OGDUtcCU3wJJoxDo50m11YOTwoXWws68SlQZLCirMcMmox5ZUWfGv9cdx39+Po5ZQxKwYGomzh0UL/QgGIZhGIbpZYGG/Px8zJo1i4MMDMMwDOMTazY7LOpQ2DTx0GSMl0QIiw8C5gZ3C3fhwV1LpNbvHGDKXcDgCzxT+wPsPAmVUomJ/WJwzfg07MrX48OcXBRXe2o+UQyCnCyoZcTocNPkDFwzIV1kPDAMwzAM00sCDUlJSQgNDfXHoRiGYRgmsCBtBGc9PolBuj6JF8tszd930JotRKmCFqQFoAZiBwPRWUB1IVB2uEl80h2yzaQW3Q+YeAcw7mYgOKKN5+WQghbu/3ZFpW3SpHD9t5dthsRpkRyqRGGpBeUVZUiIDIdCqRTnWag3IFhhFcun9QvHuYPjcdfMAVhzsBgfbM7FxuPlst3Mq6jH8z8cwsurjuCS0clYOCUTY9OjPIIYHtfK9bO2joMrVlPT9bbL7KMHaGYwDMMwTEAHGq6//nq88847qKur44ADwzAM07dwdRZw2ltajdJ7+jctl5v0tsOabWhCKNJsOigrKY0wB3ZDJexWs5jj0q5VmjAorAapfEKOylPAj48Ca54GJv4amHynFHzwBu1446tS5gT9u3gfYJLJnggKBxJHkcojEN0fmH6f1CHX7V3PE8DttUYsMOyGUl+DujM65GuyYLEDVP1AdpZZtWHQ/Bgk9ueYfA9SI0PwbOIalGkq8W1VFr4oTUGNTSMrqPnFjtOijUyNEAGHy8akIsRVK7K9LhBezoM0JqrqjAg5sw1aYylUR1dCoYuBP6DzJK0LKkOhDBEKUtH9w/gfvhYMw/Rl/BJoeOqpp7Bp0yZcdtllePPNNzFw4EB/HJZhGIZhugd6ek8Ta3fcJ+WuE3FXaFvaR1ut2YYnILFoKBARhOKqeijrtkDnDGYI20tAq1BCJSIPLTxNt5mA7DeALf8BhlwETPkdkDndMxBCT/Bpcp27qSl4YjF47k8TAhirm7an7dRBzbd3I9HhgMVWDIWjHiYEI8JqgEKpgFqhQKhdDV2lCqiEKJl4u3wvSmuMuKJ4Pwab9uJupQL3xIRglWUs3q+bhIOWJNnT3He6Gg8t24tnlx/E1ePTsEAzGFmZ8kPS0jWRO496sw11ZiusNjs0tho4YEe9MhT2qLFIjNS1bb8dJPtEedP9YbGJMhS2qu0e+FowDNPX8Uug4aKLLoLdbse6deswbNgwZGZmIi0tDUqlZ4SdUhnXrFnjj24xDMMwjG+giTU9vZdLqXdNtXcvJ3Di5fMWrdmy7sOWY0X4ausJnOeownAcwDHtEJhtCqhgxygcQYyyCpqIBKC2FNDqpH4YKmX6aAcOfSc1EowkHYeRV0lBAndSJwCnt0vlGaHxTZ9T8IHep44HCnd4H6u0iZL9oxO7DZr8HDj0eVCFJkAZNxZatQaROg1UIhvCjvoT2ThRWott5ZUie4CeHFusduxTD0W4UotZqXZcH74TO2qjsORMOpaXJcEs8ycPuVi8u/EU3kU/nD1gHBZOTsPsIXFQy1liertWLudRXGPBybJa6O1WMhiFVmPHQPNBHLQPwTrlLbh8aBYm949t337bMbH9bFs+jhTXijEhQU3SuqByG8qEcQ1WMb6FrwXDMIyfAg0UYHBis9lw4sQJ0eSQrZlkGIZhmJ4G/T6Tm5gTmuAut2Yz2xxYeagKh8osmKtWQwsVQkOCoVOoYDCZYTYAViqjgEIK9AdHAmmTgPoyoHg/oM+XP+CZvcBXvwNWPSmVVUy4Tdq28TyV0rk2NqUUTHH+2zWIIActdxeipE0BBGtUSIoMbbbcZnWIjAG9w4KoeDVSIkMQUaRBkF0FtUqFKqMdBXoT4iJDMD6yBuPD9+IxzYf4RHs5lupH43RVU6aHK78crxAtOTIYN0zKwPUT05EQ0fbrZHMoxHHp+FqNWnLOcNgQBDU0ajUOl1nE9RmXlSQFhroQCrRQJgMFGaJ0Gg8NDyq3oeUUpOrqYzN8LRiGYeTwy2+bkydPtrl5C0B0JwaDAU888QQGDx6M4OBgpKSk4LbbbsPp06fbva/Kykrcd999IqsjKChIvP7hD39AVVWVT/rOMAzD9A0oy4FS5p1Ps13RaVXiCbvdIU1KG6FgQHgSkHWepMmQMFwq55CjrgRY9zzw9xHAN/cC9fLii76G7C2tdoc4FwoyuD6goPOmzw0WG/T1TRafsap63JV2CusfmI53b52AmUPivSYRFOmNeGXVEUx7YS1+/+EO8XSaJuxt6Rcdl47vPv70nvpM14euky+vvTPIQNArvfflsRm+FgzDMN2W0UCT6Z6K0WgU1pzZ2dlITk7G/PnzcerUKbz33nv47rvvxOdZWVlt2ldZWRmmTp2KY8eOiW0uv/xy7N+/H6+++ip++OEHbN68GTEx/hGLYhiGYXoXJP5HdfkkEommObZAQVkMouxACjbIQin86ZOAW74D9n4m6TS4iRwKqNxiz8dNGgxhSc2dNHyMxWYXh9OoFbJZkBqVQiqnsHnqUKiUCswamigalRQszcnFp1vzUekSlHBCk/Ple4pEG5QQhoVTM3HFWakID9Z47Rcdl44vR2iQUuhqUMmL76692mNM6D3dE746NsPXgmEYRg7On2uFxYsXi2ACBQiOHDmCTz75BFu2bMHLL7+M0tJSkdnQVihzgYIMV155JQ4fPiz2tW/fPtxzzz1i3w888ECb98UwDMP0YGimTPaHLbV2Tt7JYYDE/8iJwuNwJEnYsD9yb2iRoDBgym+Be7YDN3wM9J/hfV0SgDy1XnKtsBib7BxJ48Fp62izSK9WsyQMadBLGhH03tGwXKxja9i+IUDg3I/z84amUTiggAM2qxVKqxEqu1mUKND69Gqz2qBW2KFVOLyPocOBjEgVHp6bhc2LzsbLVw3H2DTvtp5HS2rxxNf7MeW5NXj0i104lF8mnQs16rtDOh71TfSroU+u/TIZTQhV2hCpaRibLqTp2ls9si/oPd0TQWqV0PTo8fjgu9OV9KlrwTAM0wIKR1vyATtJXl5eu9bPyMhAIGA2m5GQkAC9Xo8dO3bgrLPOarZ8zJgx2LNnD7Zt24bx48e3uK+ioiIhgKlWq8V4JCYmNi4zmUxIT09HRUUFCgsLxTE7yogRI8QrZUowDMN0BWzR1hzSGqIg9GOPPQaVStX+8fJiieiBqx1kG6/TCz8cwq6Txbjb9F+MsO5Hnm4EaFpuMFmQZdiPOEUVgiIToSRdhrBESYiR9A9oQk/WjpnTgAtf9NSWOLMP2PJvYM9nkjNFSygbJlB2K6BUA+pgwFJPHptARCpg1EtZEdTouLTcuZ0uWhqf+grAVA1oQ4HQhGZjQAETk/4MTHYVytWJKA8diEzDfoRbylGljAIlMgRrlIgN00IZFAHEDwVOb2s6N8rc8DL+e2vDsaQoHV+XJcNo97y2rkzS5mJB6BbMs6+H1loLhzYMZdZQaCx6aBQ22JVqGFQRCLNWolIZjf2qYYgND8HYjCioYrKaXduOfsec21XWm/H59gIhkBkdqvXQaKAykgn9YvDwRUMDUqOhzefvo+9OV+L8Hm47VSEETHvatWAYpm8xwodzR7+UTvTr16/NIo+0ntVqRSCwceNGEWQYMGCAR5CBuPrqq0Wg4dtvv2010LBixQrhvHHOOec0CzIQpNVw6aWX4t1338X333+PW2+9tcvPhWEYpiOwRZsPxqsFa0cPnHaQbYAmZnSc2rpamE/axfGTq/eKiTn9Bo5V6KGFGcrqgibNhYKc1sUaiaSRwPx/AbOfAra/B+T8V3KVkMNuaf5vc8N7qw2oOEWPOJrbazodOKgfFFxwnVSaa6WsCZe/IYRVp8MBNTVLAbT6OoSiCmqHCfH2M9I6FgWUVQqptIP26XqOLYz/KAB/1QKPJAXj86DLsaR6HE6W18ueZo45U7Q4XIDrVWtxg3UdkpRFdAB6igOHTYFgW53Qxoi0V2CM8hDCzRqo8lTS+TRc245+x9y3qzVZYbTacLrSgPJasyiXoKfnaqUCgxLDxP4CcWLbrvP30XenK3F+D8npg0Q4e9K1YBiG6XGBhhkzZsgGGmjinZ+fL57w07+pPEGr7Rov6a5g9+7d4nXcuHGyy52fU7ChK/ZFgYa27IthGMYfsEWbH8bL3dqRcGYXdACxf4cDtTUDkFerFv0gXYIQjQpROAUVDE0rk+hj4sjmT33pSTA98fdGWDxw7oPAtHslJ4oT6wBDRcudcrpQEJHpgJGyFWqkDAdVsGQvQcEECgqQHSYFMCi7gYIUNFmMSJPWcUFF+6sqgApKnNaNgMV8CiEOg5jIhWrV0GmUQH2plLWRPlnK2nCem6vlqJfxjyzYil+n5OFXv/o9Np2owAffrMCqinjYZSpOyxCJf9quwBu2+ZgddBg3KlfiHPs2mJQhqFZFi/G1qUOhSRkFXbi22bXt6HdMdjuTVVSokBZHZIgaYcFqJEYEtylo0SN/xnTxd6crcfa5MYBitQX8tWAYhunx9pZykD7B7bffLtLKSBQxUHCWfFDJgxzOz3Nzc/26L4ZhGF/Ddnk+HK/WrB09NQzbxZQBcbBkPoMjheVC/I9qwQcnhkND4gyuk2yadLs/BJD7zJs959XvSvXwpzYA393v3R7TNXvBpJfe0zFUQVLggqDgQlgCkDIeKNwOpE4UyhI4vb2pvMMVmwWq+jJQ0cXgpAiYMQ5alQORIVoILUbSc6AJJwUZLnhOerItd26tjL9SqcDZA2Nx9rDdKDy+Dx+rLsOHJekos3g+KacgxCrTMKzCMPRTnMF1oTswO9WKuGAHInXBIuAj+tXJ71hr21EZBdlyXjU+FTG6IFGGEIhPzzv9M8YH352uhIIJ1HcqCXF+DwP1WjAMw/TYQENrkG3kF198gSFDhuDJJ5/EX//6VwQCtbW14lWn08kuDw0NFa81NTV+3ZdrPY07x48fF6UeVEPMMAzTUQ4W6lFSXQ+7zYbUyDAhvidE7QCkRgahosYolh8srMKIlMg+NdDOn6+uP2fbNV4JwWIODYfkAiGaK67L6BiK9v88pznt0NTmT01trvoJ3qBH4u06kAbImA4MmA2cWC/pLZQfBxxe3A1In6HxWPQ/50SRJl9UUkDvVZK2g/NzhfNzt7OhMaIkCZ0WUGubn6fCdVu11JznRmPanvFv+CxRVYP70o/id6nHsPpoDT6oHo2ttkGyp5nrSMCLtfPw6hE7Lo07gwXJ+RgZVtNs34eKqjr0HWvLvUb3ZlSwGsOSwkTnA/Fvgg79jGnvtevAd6crobtaugZOAvNaMAzD9FgxyLZy0UUXCSGKQHmq/5vf/AZvvfUWHn30USH85Q45SAwaNEg0yspoifPPPx+rVq0S+6PsDXdWr16NuXPnivbjjz92KtAQERGB3//+963ug2EYhmEYhmEYhumb/Otf/0J8fHzPFYNsKxTzKC4uRqAQFiZFoevr5YWg6urqxGt4eLhf90V4uxmcAQhSQ2cYhuko+07r8daGEzhZWodRaZHNdHboZ/XeAj36x4fiNzOy+mRGw/PPP4+HH3640XWiXeNFGQ0rHwZyNwPpk2TSv21Afg6QORW44PmuE7Sj5wqupRNytLV0whUqn3A9H4L6X3NGco0gO0ubizaEHHTMkFig/7nAmT3N9+McI/G0uuFpMFlKHm4otRw4tymjgdLphdCitaF0YhJw/rNSqYdzDEgfYs1fmu/bfZyEA0fD+BNy51dbLDliwIHa2mp8jdlYajkHRwwt/x6PUhpwdWIJJpx7Cb7dX9a2eyY5ovHa7S/U491fTuJEWT1GpUY0bmdTaMQQtfm76av7wZc/Y+heW0HXYhOQNkH+u1PQ4DAyrwu/OwzDML2UTz/91Gf7DphAw86dO/Hzzz8jMzMTgYLTZrOgoEGh2w3n523pc1fuqy3IWa4xDNNz6G5LyWEpUUiI0CGvwojTelPz+mm9UfyMoeW0nqqP1hzTGDh/1rZrvKisgOZU5L5A9QNueYU2uw0Wmw1VNUaUnanF4NTgDl1713soWKVE3J7/wFRyXCyjmviYUK2kG9BZW0CHyu18pFeHwgGTUgtHSByCaguggL1B01EmkZI+qi8BDn4JaMMAc40kVuncJ1U9lOyTggSNk2SDNLE8trKpvyQwGRQFmKrgMNbAVlcCw+l9MMeNFOeson0YqyXHDZq0Fjg8BQUpOEIHpF06f5e6nZ/dYYPdbkOdwSgWh9rrsECzEgt1W7BVGYkPjNPxg20SrI2lIU1U2kPxVlF/vPXxfnGfkHZGQZURadG6xnumoNIIkx2wORRStcCm16HWnxLbj7A7sFBfhVKjCdpcpRBQJMq1KfhIfUXbvpsBYBPZoZ8xdiVQsheoL25wTJG7j0qldZTKpuvHMAzD+B2/BBqefvrpFrULqOyARCDJ1vLOO+9EoDBmzBjxumPHDtnlzs9Hjx7t130xDNO7CQRLSbZo8+F4uTo4uynk15ttqDNbYbU7cORMDb7ccAIxkWXtvvau91CR3oiSymrca96O8Tgo5mb1ZCWtViIyRAOdVtV1toB0Pg47LNUlUFjroTJJWXyOBpU+EkxUiX97qdq0WwFjFXDgKyAyTVqNsgcICg6QO4XYoaNBWNEuBSWcUNDAoIfdQUENOxRmC5QVx2GprkSFUoEoexU0FKBwZkZU5XlOop3uF17Or95shaO2BBq7ESEN/bHDAYfVCKVRj0mwY5JmB0o00fjUNhNLrTNR5JC/diR6KF71BiGKmBIVjMp6i3CQCFarUFJtxP/9cgQLq3ZimHmfuFZ0tYaZbUhzWGA22OEwSE4T5Soz6sIMGJQU3bp9YgDYRHboZwz1hYJNNO56SWRbFlqH1nVmsjAMwzC9M9Dw1FNPNUapvUEiiZSG+sADDyBQmD59OiIjI4Xuwa5duzB27Nhmyz///HPxeumll7a6r3nz5kGpVGLDhg0oKSlBQgKlW0qYTCZ8++23InpPOhUMw/RdAslSki3afDRelI5OT4rdKK424URpLfQOi5iKlzuScKTMDHVlRbuuves9RGr35EJgNhphUdlhVzqwC4PgoAm/Q4FojQbD4yORGK7puC2g2/kU640w1u2G0lYjdPloEhxqrxYBDpM6AtHKOmgp2kLuE1QCYTPJ71ffkAEYEg3ED5WCE+ROIYIACslW01QrBRwoOGA1itd6dQxgKIXGbhI5FJWKaOzHECgdwGgcRozSAQ3MkusF7csZaHA+DXdaYrpafTacH10jKl2Ityuhc7iWQjoQpahDsMMKjTYIWoUNCSol7g7Zi9869mONcRCWVI/FButw2VO12BwoqTGhtMaEYI0KGpUCOo1K/N1AJRKlBpMILNTGn4WEiBCQrHRNtQmlVfUwWazINBxARIhauBzMHpXevp8R3WgT2e6fMXQ9KNOlMRgkk9JA9wit05JNK8MwDNM7Ag3vvfee12VarRbJycmYOHFio/NCoEB9u/vuu/Hss88KcUUSaXT28ZVXXsGePXtw7rnnYvz48Y3b/POf/xTtiiuuEDW8Tugcb7jhBixduhR33XUXPv74Y6jV0vA/+OCDKC0txS233NIsAMEwTN8iEC0l2aLNB+NFE1tKR3epj6dr//bKw9hWXomoeDVSIkNgV2pBOW7tufau91BksAZGsxUmix0qhUJM+Akl1bUrVbDaHKg02JGvNyEuXCuT5N9GXM6n8TxCKhAXCyRHBEv3sN2Oomoj9AYbxqVH4o+z+0GjbXjaTBPabe8AR1Y0t8J0YqgE8jZLT9U1OiBxFBAU1qRlQZkOungRJLCHJeKIPQuxBitiFJViGqrRqBCtCxLZImaDA1bYodYEQUEBBVfrTHdLTFG60TCRnX4fzCYj3vzhEL43FMHksCFa44BOqxarmAwG/Mb2AcYrDqMydAzGpEdDRftVSH9oXWC34YKCj3EifjaWBt+Iz3YVo9romtrSFOswWGwwWKQATWIkMDQpDNp8pcheKK0yIjYyVFzPxCgd4iJDoK81IviMBsOTIzB53hBogkLaef261yayXT9jaLATR0ruJWle9E2opILW8ZG2BMMwDBNAgQaaQPdUSFSRHCE2bdok3CXOOecc4YqxZcsWodD57rvvNlu/rKwMhw8fRlFRkce+/vGPfyA7OxvLli3D0KFDMWHCBCHquG/fPrFvCl4wDNN3oT+06akeZTI4gwwEvdJ7Si2m5bTeyFT/CTDSH/z+PF5Pp03jRdfWJR398Bk9iursMDnUSIyOhN157cnqrx3X3vUe0gWpUGOywe5wQE2ZBTRvo4oDB6BRKGBXOGBzOFBtsEBfb0FMZ0664XwazwMaxMZEwuIy2YuNDcfpAj0KjBocrg1uOo9Bc6RWmQvk/BfY8T5gqvY8BmkqUDv4tZRhED9EOik6htBQUMBsc6De5hDnonTJpFRAIcoOqMyAzp/OW03bNQRdmp0Hvadr4zpRVShwuMyMI+Vm1Nsp00ANBGthaFhHo9MAtVQUooDeZIfeDMSEuk2CFUpkhZrw+IXD8KeLRuHb3YV4P/sU9p2WOVeq6jBYsPVUBXapFKgOnoQb7WegstikaxUqPa2ngIP4t1YFHb32UL2Udv2MEde7ITjiHmgQyxvuCYZhGKZb6Zm/kfxIcHAwfvrpJzz++OOivOOrr74SgYZbb71V6CpkZWW1eV9xcXHIycnBPffcA7PZjC+//BJ6vR733nuv+DwmplN/5jEM08Mh0T7SZKByCVcFdoLeU/0ypRbTUz+md9FV1951P6TzYLXZxCSbJt20H2nXDvGf+Izm73YHzDZ7959HdCZwwbPAAweAC18CYrz8fqWsh4rjwOHvgap8qfyiIaBgtztAp+LM3mh2/IZxELtwdOzcDGar2AdNjJufn6Jd4xmiVeHaien49u6z8dXvp+OqcWmiXMJbWcWKusG42fgnLK6cgxUVibDYeSLNMAzDBDYB4zoRyISEhAhBy5ZELV31KKh5g4IJr732mmgMwzCukLsECT+SJgM9iXW3eyORNKpfptRipnfRVdfedT/ROg3UKhVEsYDDIfYjJthiQqwQgon0loT3tF30JLxLzoNKFib/Bph4O3D0RyD7X8DJ9fLrWhvEIUkYUKmGMsguHurT+bpDwRXn5x154E3nFqJVi31YbHa385P23d7xpO3HpkeJduVZqVj8/QEcK6kVwQU5DlqS8UheMv5RZMQNSadxQ2IBkjTyttkMwzAM051wRgPDMEyAQHXJJIJGExWqy3emfTs1GuhzWk7rMT6Gxt6Zqi/XnOt05bUPC0KwworiSj2UNhNUdrN4pff0eXKoEkMSw9p8D9WbbAgPUjWUENDTfmkdtcIOB9WyO+zQwIHIYHKfULV/DKi5jYHsPexweJ5HnLbF/QioLGLIPOCWb4HfrANiB8mI/7m4VViNCNKfwiDzIWgcUnCl8TwcVhhMFiioLwqp5KDRucLZ5PQh3M5tQHyYCCJY7XZYjPUIsdVBZ6uFqq4caodZOGrEam2IVJoBswGwmAGrucEho+XxnZgeirP7RWBkQjBGJ+uQGuldzLDEEoxX8wdg+rZz8LvDY7HJ2L/jtyOdt+s4tGEsAoKe2m+GYZg+Amc0MAzDBAhsKRkg0Ixt46uS/Z/scvpfDLDpdeCcP3RJPbhWpcAt+Bpz7QegL7XAXkJ16wrxZJsmxmRDmVUbBk32UEl40csx3e8hs92BILUCZlPD03wFMNJxBAr6p0KBILUS0RYtVKdV7RsDJ6SV4NIfj3u4xoQbrF8i1lzY/Dx+DGpxPx4kDAf6TZdsKUkIkCwwZSbvCjgQb8oTl8gBBahwJNRchiTrPrE8VqGHFmY4LIC1uhi2U1ugUatEhgKVXSiVCmjsDllhTDq3C0cl4WRpDcYVvI+Z5i0Is9QhCrVQw4YQBQUabFBUFUOpl3oDlUbSe1BqJPeMFsaXwgq315owy1ELvcEitCSORWfhA9O5MBpqUePwFHm0QYkfKpLxA27BgLpaLIzOw5UT+7Uv68kP7hI+oaf2OwAhEVfSd6HyIMrcoaAa3e+Bsj+GYXomHGhgGIYJINhSMgAgNwiaAOZukl9Ono24GKg6Ja3rIurYmWNmKooRbz+AOoUVVkrDtzZoLAp7SDV0lSogIqjVY7rfQ0V6I05XqlFsTsYusrVUKqBWKoWzyeDEcOhon06clo6tjYFb313743r8Cn01MoqLMRgHmp9HZev7aYa7JSgFGSpPAae3AxbP0gGhDSlMPB2wK2wwamNQE5qBIMsp1JlrhI6CATqcMPeDxQBo1JLuAll+GkvCEJZbgykDPPtC56awmWD5pgJZNUUIglFkMdCxnCES+rcUjKJ+KqWggi6muWWml/FNpBINu63xHghVq3AiJRIXGDag1BKMr6v6Y3uNS8DCheOGMDy1/Aj++uNxXH5WKhZMycCIFC8Ci14sVj1wtfgMBHpqvwMYssNttBe12ETpk1d70W7YH8MwPRcONDAMwwQYbCkZQJD9IanYu0I1CBW+ORw5IwT1nyxsIElQkNL0I3UakNJCe57gut9DOo0KVutYHD1TCTJVzEoOx/CUSE8LQZqcuWcVyI0Bpai30B/n8Y+cLkPshnBElWqhyZwkWT62Yz8tWYI2Xou8TcBWssf8QTZ1PshhwiDjHpgdBVgfdiE+UZyLckTB4lAJy03nOCdFhkhikQYNBm0vEMeUmxhN7h8L24BYOA6oYLMFw0rikHYToApqKuywGqXXyHSpBETOMtPL+Oqoz3YbLLk5GBIfjjvOGYDBKU9DAytuBnCgqAZLcgrw1e4zwrLTHbLH/CgnTzS6BgunZIpMjCC1qvXxdEfufuhOemq/AxQKCny2LV/Y4ZJTDYm4kr5KXnm9yEoi2hMc6Or9MQzTs+FAA8MwTADClpIBgtNGz5Wuk2aQhSbjMeFuT2Plavw7cA9NyIrrmjGwt+344ol6RDBQ6cWOsD0l9W6WoI0MnC21qjzJHnM72WOK2oVmaE0VmGNaivPwCXZHzsa79nkoUKSRhiTIxMECDcakRorgA5V90FNZmqh7BGMabCWpFkRNUldC76HBP9Sp/SAsGBsavFhmtjC+9E6lViIpIhhJNIYiSCCtMzw9CM+lx+HPF1vw5Y7T+CA7VwhIyrE9t1K0p7/T4rqJ6bhxUgbSY3Qtj2eg01P7HWBQeQPd4xQUoOwmp6WyUxOote+Ar/fHMEzPh7/pDMMwDMP0fKIygPMXS/aYF/0NiBkgu5oaVozXr8S/au/H244nMD9omwjkUCaA3mgVEyQqraDUb8oICVRIh+GWaf2w6v4Z+PCOybhoVJIoi5Gjos6Mf687jhkv/YRf/28rfjpcIjQpmL4L3dt0j1PmgTMoQNBrR74DXb0/hmF6Pn7NaDh58iQ2bNiAoqIimEwNqt1u0A+kxx9/3J/dYhiGYRimtxAUBky6A5jwa+DYKiD7DeDEOtlVx+MgxhsP4jdIwDLzRThsuRwKRRxCg1QwWW2i7CTQob+bpg2IE6242thYNlFc7fl3FiVbrDlUIlpGjA43Tc7ANRPSERPKegZ9DRJqJA0FKm9wtaEl6H17vwNdvT+GYXo+fgk0mM1m3H777Vi6dKl477Rsk4MDDQzDMAzTAk5bxK6qUaf9ude80/6FXWCDBaRCJSksCjsHW/NlTntK5z5cj924H7IidKuTENtYpOUWE1Bb2lzDwPm3gvO93Dm5f+Z+LlnniXZ0bw7KfvonxlevgRaeE51UlOBe6/9gzP8E2+suwnuW8xEUMbh97g0BQGJEMP4wZzB+P3MgVh8oFmUVm46Xy66bV1GP5384hJdXHcElo5OFlsPY9CiPSWKXIHePueO8lu1Ztzv610sgNwgSaiQNBfq73PW60/s6k03cT239DnT1/hiG6fn4JdDwxBNPYMmSJYiKisKCBQswePBghIezDzzDMAwT4IgJssxn3XVMijFsfB36MyeEJSPVOkeFaDxT5luzi2zNxpIm/xsndXsAAIB7SURBVPlbgLoSID8HCA4HEkYAJfsBU40UcKgvldZZ8TBQelD6nKBgQeIoKTDh3E9tCXBiLaAJbZpMGiulQAPZPlSfBg4vlyZz5NBA1DcobpItJG0j9juy+Tm5nmcLlpxZdgeqtUHYoD0H8Qo9+tlOIcLqOQEPdhgwvXwZpuILHFVMxwDDIpgt5+BwcW2TVV+cVlhReoyjsznfd+M9RvfFhaOSRTtWUoMl2XlYtr0ANSaSAvWsrf9ix2nRRqZGiIDDZWNSEaKVM/nsAO2xSp12L7DptXbbqvqtf111zACwjaRtyQ2ChBpJQ8FdU0GtVIjltF537I9hmJ6PXwINH374oQgy7Ny5E5mZmf44JMMwDMN0HjlHBKe9pa9owYWhuLoep3N3Iblmj5gfmRVAhVKBUK1aOFY0oy3Wm95sLGmiW1cqBQH0eUB9iBRIcH7mpLYYyNsM1Jc1fa4JAYzVTZN/ClbQMnJicJQ1fU6ZEc4Jtd0iLSdhRGODkCMtJ+g9bSP2S/9Wyp9nC5acNDLDzDbUwIKdGI6nQh/CJPMWXGr4EiNwwmN9ssUcov8FWPILikMGYHfEldgYPBOqoBAkhypxe7VJWFFK59RwHmb3TAmlNF5hYk3vtMNNpCMMTAjHU5eNwKILhuCb3YV4f3MuDhZVy66773Q1Hlq2F88uP4irx6cLi8ys+LDOdaA9Vqnm2g7bqvqlf111zA7Q1baRFKCgbckNgoQay2vNoryBMg8oKDAoMUwsb6twY1fvj2GYno9fAg0lJSW44IILOMjAMAzDBD70VJ2eXnqDHlbTw/aoftK6/jimCDKYsK0qFKoaPeKsdhzTDoPZpoDCDkQq1OgfGYbEcE3HJ66uNosUCCg5AJiqmybLtJz2TcGF0HjJTYGyDOKGAKe3SZ8TtIzWJScFGqvivUDFiaYAQ2iCNIjOoIU6uKHEwiJlPDiX6/Ol/UWmAfXl0ueN+23FFlPGklNH25zIRrw2CBlRkThuvxCLDXOQWrsXV1u+wSTjJihlbDASDcexwPASLlX+F8u1F2Jl8EXYqonCuaH9EB5aDxgqpb67o9QA0ZlSdgddW9d7pQ3XW+C+XSeg2vkbJmXg+onp2JFXiQ825+L7vWeEvac71UYr3t14UrRzBsVhwZRMzB6aAHVnJ4ntsUrtgK1qp+mOY3ajbaRzm8YAhlUqb+hoAKOr98cwTM/GL4EGzmJgGIZhegw0IaYUaW812zYbsPMlYNo9XZdG3coxKWX67ZWHsa2sAvdo3kKQQoWwEC0cCnpiaEWV0Y4CvQlx4doGE8SO9MHNZjFplFTaUJADpE8GZj8JrPmLlMGQNklal7ahiZjrODj349wXTbTpSTUFJmjd9EnS565BCwo6mK3SfpTu+3SxinTu194xS07K+hibEYXgsVnQW5SiXjwrfhJOlF6PnWWnkHF8KeIOfwQFBVjciLTrcaPxY1xr/Bzrtefg03534eb586ChshW560YBAqelpXt9f2v3mOs+ujhVn9LZx2fGiPbYJSZ8ui0fS7PzRHq7HBuOlomWHBks7DGvm5QuJo4dO3g7rFI7aKvaKbrjmN1sG0mTf9qWSjJIqJG+E1Te0NHMg67eH8MwPRe/BBpuu+02PPfccygtLUV8PD0FYRiGYZgAhiZ33lKkFQ0p/V1dq93CMQ+f0aOozg4bJQQEqQGXUnt6b7SYJXvGegtiurI/zmACvVLfXN87J2StyRGIYWoIFNCrcztn8MDPqBQKjEiJbDbWI1MjgdQxwJgxgOkJnP75Xai3/heJloasCjd7zFnmn4AjP6Hug0nQnHsvMOQizwlqZ+4xPxEXFoS7zhuIO2cMwLrDJUI88ucjpbISE0V6oxCOfHXNUcwbmSS0HCb1j/GNeCTTZttIKlFw2kaK+7gDUBCgo9v6Y38Mw/RM/BJoWLRokdBnmDlzJl5//XWcd955/IuJYRiGYdpIk3WcCjKmCdCoFGIiIpcGz7SToDDkDrgR/yucjH76bFxj+RaDauVT50PP5ACfLACiMoBJdwJnLQBConrckJOY6OxhiaLlltfhwy15+GRbPqrqPW82q92B7/YUiTY4MUwEHC4/KxXh7CbgE9g2kmGYnopfAg0DBw4Ur7m5uZgzZw40Gg2SkpKgpPRINyhCe/z4cX90i2EYhmF6BE7ruGKTTWgMumOxORCiVUDr7/RkevLttLoU70nk0S6VBFDiB1laChvMhhQMWs3ckKJvs3q6NXRJnxpsN5u9d/bJKh3foAc0wfJlDg3jrdVq8AvGobr/TCQZT2B62acYW7UKGodMuUNVHvDjo8BPzwFjbwQm/hqIyWpbSURnrBXdt5Xbl/u2rRw7M1KNh8/Pwv0zM7F8XzE+yCnErvwq2W5ROv/jX+/HCz8cwhXjUrFwSj92Fehi2DaSYZieil8CDadOnWr23mw2Iy8vzx+HZhiGYbrJPo3pOpzWcYVlCqHJQCho1u6wifcqOKBTA5EhHVNosDuAylojLHY0t8z0ZrMoggmk9rxPcpgQGgu10sS1wgBU5jUEFyiA4BZEqC5o2AcFKJyTXZO0T2dQQJybczuXYIQzgOC1Xw5JnJF0JeBio0l9E0EPm3T842uabDQJErUceilw9h/EJLyZVV9lPWZYN8OuUGFP5ExE1Z1EqiUXwTB5Ht9SB2x9S2okYpkwHAhP9gwSOK0SiY5aK7rbMjqFN502o67n5moL2sKxKSumymBptE69PESDq8ZkYe/8W0VZxde7CmGyeo59ndkmLDSpUTkFiUfOG5Hk+bOjPVaegWYt202wbSTDMD0VvwQa7OKPBoZhGCaQ6Wr7NKbrcFrH1dbVwnzSLq5PcvVe2B0OIYFAy8MtGqhOtz/QQG4WyjoTrDVbWrfMdEJCjk7rSnN9QwCg4Xe9gzIVWjigu0ODuab5RJ3sNMV+GoIK+gJpkkzHogCCuyuAx0TRImUYiPfO4ITL3yH0BL++osk2kyDrzIrjjfaFrlZ9J89UArWnkGrbL8abdlmsiEOYwoBwRy20chkOzn5TowyCkGhpwu/ad2cmQUetFd1tGV2tRF2RswWVOXa92YY6s1WURrjeB/Z0M0ZNCcGLV4/BoxcNx2fb87F0Sx5OltXJdjPnZIVopP9ADhc3jE9CqnNhe9wbusPpoZvdJeRg20iGYXoqfgk0MAzDMIGNr+zTmK5DjL/DgdqaAcirVYvrRFkHIRoV0qJ10EUEtdsWMTu3BmX6CKgdw8RUXKNWiDIMpQOIVGqQFR2GRNov7U8b1tySkSbw+VuAmjOAUi09SafPVOqGCb6MmAShoOV0NHKWUDeJTlJ/qTkzDSgYQNAkndZxfzLvfp7CMrKfZMVJbha6+CYbTRO5XjgARYM1prbBRpN2Rcu9jTeANXuBiBNqKOsVOKoeCoNFOj0ae7XSgXBrJUbZ9iMEBkn30h2a1FN/jFVA7CDAUt/11oq0LXWKAjG1JQ32ow3n5rQFpXHzsq+SyNE4UVYPvd0qdqNWkbmKHcPNh1BQWotTJ8sxeVAKInUa3H5OFm6b3h8bj5cJi8zVB4tFRow7ZbUm/POnY3hj3THMTpiGhbGxODuqHJQoI4vcPeYH28/usBptL2wbyTBMT4QDDQzDMH0cX9unMV3HlAFxsGQ+gyOF5Y3WcYMTZazj2mCLKK77gRJstV6KuHggJbLpuhfqDdDXWzE+LBoPnj8EGm2wpyWj1QSsfESyu0weBxRulya5NMGvb7CrFKkNzn44AKUGUAcDViN1EohIh5h5kn3mzEcbnvq76AcQzvdy5+T6Gb1OvRuoPAXkZUuTa4Im3/SUn/an0QE2o2ShKXSiHK1b9aXqUPNlBIIK1QhSaGC02xGsVkruH3RYhxaVNcXIUWYhODIRkyu+gkJOc4HGq3hf0/ui3UDymK6xVqRtFc5XcvNoODdXW1AvUJCgoMooLFK1GrXLedmgrFFAb7Bg+4ESjMtKarzPlEoFzhkUL1phlQEf5eTho5x8EVyQ2/+q4jCsKh6PfrEhWDApDVeflSJ+1sheS3/bfnaj1Wh7YNtIhmF6Gj4JNDj1F1JTU6FSqdqtx5CRkeGLbjEMwzDdZJ/GdB0atQojMhK67ro7gMToSNhdJlGJ0VoU10mWmofLzBiZGiJvyei0u6QsBmF5SZNlFyvLZoEGNztLMQFumBSrtUBYfOftHhstOV0n1y7H7cA8kSbXMaFaGJVKOBrKCpyTcSdqlRL1jhB8G7EQg6MdiDn9sxRMMVXL77TiBPDOXCnAQqUNXSmG2U7IqcRgt4mAgNx50eelLXz/U6JC8Mfzh+CeWYOwcv8ZoeVApRNynCo3YPEPR/HSquOYPzZFiEeOSovsftvPALAabQtsG8kwDPp6oKFfv37CUeLAgQMYPHiweN9Wn2Vaz2p1MQhnGIZhfArbp/VN+Lq3D7vdIYJxZCUqB31Ok3YzBTjI4jJtElBbBBQfBGoK5XdKpScElZ4ERQDxg/0+4W3LeZlsNpFB05qWwKVjUkSjoMSS7Fx8saNACEW6Q4KSn24rEG1MepSwyLxkdDKCNR0TM2UYhmH6SKBhxowZImCg0+mavWcYhmECD7ZP65vwdW8fVC6gggIWs3z2AWlbkL1oo8Uo/d0TmS41csIoOQiUH28SuXSFHDqo9OTMbiB2oORWERyBQDmvIJVKlOm0xynhmctH4sF5Q/DVztMiy4FKs+TYnV8l2uLlB3DthHTcNDkDmbGhHT4fhmEYphcHGtatW9fie4ZhGCZwYPs0PyPsHP1cDy5zzCFxWiSHKlFYZkVxpR6JURFQUHlAgzaHWqkQriN0f7S+f3uTPaWzNS1seiUXKqecBP2b8vKV9GqTNAzaMw7u50TvSZDSapb2ZyEdCGWDjabTHtPevCnasF/ql90GrRIIhQ31disM9VaEBjdoGcABq9UGlcqOJJ0SkWq1p1UiZStQmUTSKODEOkkzQk4UkgIOpYekFpECxA6WzsV1fOTGpHHsXV6d5+J03vAyjhQY0SkVqKVzMxgRFqT0PK9QpbhfRB/acW+GB2uwcGo/YXdJ5RQUcFix74xwtnCnqt6C/64/Idq5g+NFlsPMoQkNNqtt/M4QAa61wDAM01dgMUiGYZg+Dtun+QcSXzxcVI3wnf9CeH0BokI00iTKm8I9CdR1xYSIJmkbX5WsDF2gadnttSbMstdCX2pBYXkSfoi4FnVmuwgyDEoMExaPbRIAPb1dcjggXQJ9vpulpMukkqwvLU47SwVQnS9pFFAJAQlLuosWehsHl3OitP+qejO0ZQegsdYgyFgOhdUg9YOO4bS8JCy1zW00Xe0tvY1Vg7uGsq4Eoyz5sJOegVUBs1HTIJ4pxSvGqg7hrPp3oTKeanCA8OIWoYuVgg6Z04AtbwJFu+TXqy6UGmlYmGulIASVVTjHRNZu1OUaOGnFFpRuwSGWw0hxmBFkrIbK0Lx8dYzqEMbWvQXNj7oO35s0TpOzYkUjXZCPc/KFgGSRnoJBnvx8pFQ00oi5cXI6rrOvQFz9Mdl1xfU3WFATkoYglRIJtiLv36t29F98X8/UiBIjyv6hgBv9rPQV/j4ewzCMr+FAA8MwDMP2aX6wDyXnjgp9Na4o3o/Bpr2oUCoQqlVDp/VSl05PZruiXp/2QxPn3E0eixLpqbPdhjqFFWFaNbbqgMTIUJHJQEGGFi1NXW0BKZZQvFfKKKAJr6ECMNc1BBxoJu4sJyDhx6DmT6hpwkdWlk69graMQ8M51R/dgDqzFVabHcG2SqjsRthhFxN/MdckO0vhxEBjTNkTasn1wtVGkyC3i5gB0r/lxqrBalOlcEBB+1cooWwQmXRqWkYra6HV75X2lTGlRacHMW5jbgBGXw98/yfg+BqgMlfeBYMCJWSPuedTIDgSGDhHOn93W0bXa+CKuy2oq01jw/YUQqipqochLxthlnI4GvqhgAI6azXUJduBKlWX3Jt0b907exDuOm8A1hwqEVoOG46Wya5LmTUvrTyCfyj64aLgWiwM24rx2vzGU6k326Trb3cgXztCaJGqzQda/l61of/O7ysFRUwWG4I0qrZ9JzqIv4/HMAzjDzjQwDAMwwjYPs030CTis235okadbA/pyaXFasc+9VCEK7ToHxmGxIigpkmltyfhXQFZPro92dY57Agu2IrhcRG4eVw/hIeGiaeprWYyuNsCugYP6N+UZk/vydLSmVHgTFunZT89K51r6nhpHdcHzG0Yh+JqE2C0YA8GiwqMEYpDiEIlqhQRohwgGnpoIhKB1AnS/gp3SOc/6/HmNprOftHE0zXt3nWsaN5N51CwFcqqPCAqA6bo0bBAAY1SicgQLVS0v9NbgcRRwPnPtDwRd44DtYtflo5bfgJY9mug9GBT6YMrVAJCAZy9n0n/JitPd1tGuRID91IB1/cu2+ceK4Kt7GGkVu/GfsUgKMlJRASJVIhUqJEVqUOCfg+6CnK0uGBEkmgnSmuxdEue+J5UGz0FwS0OJb42jBZtmK4aC5PyMFV7UpT81NjNGGI9BJPKDqvJAaPNhhNBw9EvMrzpe9WO75br95WyJciJo67KiLzyeugN0lh15eTf38djGIbxFxxoYBiGYRph+7SuhYIK9KSSJhFROg0yIoIRUaRBkF0FtUqFKqMdBXoT4iJDpImqzPyyS6GJs/uT9gbZBLJwnJoV174n1e62gJrgtm1HgQaytKTtVRrZPrU2rgWV9Uiw2qEOVonJmaZeBaWDMgxUMNkBK+1aqYKSjkPQMah/bbXRdB8rkSEhBQeUCiViIsKaLxfZGw3r0f7bOo7OMYzNAtInAjYTEBIj6TTI2mM6gH3LpJY+BZjyO2DoJZLFaHuugcuxaTxXHa7CeKMdGSolYsND4RBZIECdySrdp1VGxFH2BrqerPgwPH7JcPzp/CH4ZvdpvL85F/sL5a1BD9ZH4JETI6FTDMZkzXHMCTmM0RoVIoM1IhNDWaNAlcHW/HtF2Nv/fXXa/Tp1S44W14rl4zOj21ZSFGDHYxiG8Sf8U4thGIZhfATVXFM6ND2pdE4inNDkmJ7EGyw26Otbtg5kmnOkuEaMm6NhHN2flBM0tjSR63FQgCN+CDDiCqlMgkQhvZGfDXx2C/DaWGDja4ChqsP3aWmNUYyZc/zk7lNfj2eIVoXrJmbgu3vOxpd3TcOV41K96hTUO7T4yTwMj+ovx121t2OzIR1Wh0L039HB75W37yu90nsq0aDltF5X4O/jMQzD+BPOaGAYhmEYH0HCblRzTZM1MYlwK8HXqBRikmG29cAJcTePK42b0ougn/hYmEzIWzb2CIQ9ZprUyB6z+ABQToKIMudE4o+rHgfWvQCMvRGY/FsgbmD77lOrTdyPck/+nfepXe7YPoC+K2dlRIv22AUD8NmHb2NJQTzybdGy62+3DcD2qgGIVtbjKk0ChgRVIMRuaff3yuP76tan0CCVGKdqY9cEBv19PIZhGH/CgQaGYRiG8RGkHk/CblRzTenQ7lhsDoRoFUJTIOAtMt21F1o6LjWnLkMLlpGN1otwCje2fVyrlArYZcbUeThC2ZL7ANlbkpuDK+LcLFI9P70KIUmZfdBystF0L50QNpRmyVqzK8c/JFoSmKTjkiBkTSFQc8ZzPXLT2PqW1AZdIJVVZJ3Xaj/EfapWiftR7hrQ5zqNouXx9BFU0nNn2incYf0IP4dfhCXF/bC2Mg4ky+lOpV2Ht01zoDTZMT6oAL+OOI0LwmvafBncv6+uk396X2eyIZHKn4I1XXJu/j4ewzCMP+FAA8MwDMP4CBJVJPV4EnajmuuMiKaJqcFkAb3TqYHIYGXDxNveYbtKD+RsEIXVo/v+2vjU13ncg994Ohu4og2THB0i0qRJq5wbAh2T0vwpGJFP1osN7ggJ5I7Qep8GJ4Zjr0YlVqVx1GmVUNBEjQwFbFYoyGBC4YAwHqBxdZ9pUpDhw2uBqlzPsSCLSIsBqC2RzmXALGl7cX1oWyugL5CWu++XrCXryyR9heHzO25R6u06UWAjeTRwy7fAkRXA5n9JIpdyHF0ptfhhwJTfAqOva7LxlLlP48ODhXsGOXgo6ERJcLJBo0EFB3RqNbRk69BN1o50PWdGlWBmdBlyDcF49VgCfqwbgFqHpyaFHUpsNWVg6/EMDCisxcLEPFwZl4+Idn5f3TUTyPaVltN6XYG/j8cwDNOrAw27d+9GTk4OysrKMGLECFx22WXic5PJJFpERGu/BhiGYRimZ0CTJbKoI/V4EnbbW1OH8xrSpbMsB8TycIsGqoIWrPjaYVcpu64rnXG0EM4Ix6RGE3FvkH2kKVGyaxTlIg6grqT5NvSZc5klT/qMJsGm2jZNzGnc0qJ1QLUSWcYDcBgc0KEKKocJ8TCKdaisQklBAzpn931SJgMFGSpPNf/c0TDBFhkNZilwQDoIlNngPA8KNpBgIzU5KBDhHKeO2kC2dp1IQHPU1cDIq6R1s98ADnzTGBxoBrlYfHsfsPovwIRfARNv99B9oPGcMzwB9pMa2KsdSNTvEeNHGSM0cuI+tWqgbMky0h/Wjg3jkglgsc6Gexw2rDKPxFfWaTjg6Ce7/+OGMDx1ajj+mjsQl+tisSDWghFt/L6W15pF+QJlFtCkf1BimFjeVcKM/j4ewzBMrww0HD58GL/61a+wZUuTT/Ytt9zSGGj48MMPcfvtt2P58uWYN2+ev7rFMAzDMD7FOVkSk6lqA/TlacjTqhCiUYnJss7Vgs81G4FS7ztgV+lh40f7of21RluP6QwmhMZ7fk4Te/f+0QS9IEfKAHBuQ/8mN4jgaCmDgbYLSwTSJzcvR/DWJ5UWiZlDUQygpLIeBrMVVuNxhKBeTNBCtWroaFJMWRJkN6lw2x+VSDghDQTnCtRXY0OmhblOCn5Qn2hiTwGGM3ukAAIto23kMgQouNCRLIaOXCc6TvokqVGWRc5bwPb/SefgDlljbnhZykohoUkqqyBr0QYmD0xGbtZwlOQphZAiaTKolArP+7Q990lXWDv2j5Edl5pqE04W6hFnN+FXqrXYaR+IPbZMHLGlwAzPUgODQ4uP6ibgo93A+KrtWDglExeOShIlI16/rxT8sErlC16DH53E38djGIbpVYGG/Px8zJgxA6WlpSKwcM4552DRokXN1rn22mtx1113YdmyZRxoYBiGYXoVNFkgizpKD682PIRIrUOk/3t9UtnW+n4vdpXN11FIKfxdrengrl8gV+4g1nFZVwRFqK5BKVk4UiCCoEAETegveK55BoC3PjWcU+IUM2JsduFCUWwwi3EdlOAyru7by+5P0XwMdbFSmQTpLFBgZM5fgOCGbEv67PtFwOHvpf3QctdADwUqain80QE6e50oYDL3L8C5DwK7PwKy/wOUH5XPuNj7mdRozIU95qXCHjPz0oeRYjaK8SQBQtIG8LhPu0h7ol3Wjm7jQtu+vfIwtgVVIjJKjVCtCga7GqlKBSINBuRWGFFjdkBvtMoee3tupWhPf6fFdRPTceOkDKTH6OS/rw3jQOULvsos8PfxGIZhek2g4emnnxalEm+//TZuu+028Zl7oCE0NBRjx45tlvHAMAzDML0FmjSMTI3snoPTxLAjKfy+7pNzgu8MmFAf29rPhnPSqIERGSFd26/GpvTsE2ViUKDEWf7hPunuzCS8K66TNlQqjxh/G3B8DZD9b+lVjvwtUiM9jcm/AcbdDE1IdNeOZwetHamMwGntKL43LuNy+IweRXV2mBxqJMVEim2chbfRYUGoNOkxJlOHaQPi8MuxMvx4oFgcx52KOjP+ve44/vPzccwakoAFUzNx7qB4IXrp7+9rt/58YBiG6amBhhUrVmD06NGNQQZv9OvXDz/++KM/usQwDMMwDNN7oWDIoLlSKzkEbPk3sPsTwCqjr1FdAKx6ws0ec5BPu9cZa8e2bEvWlv3jQ3HTlEyc0RvxUU6eaCU1ntoaFDNac6hEtIwYHW6anIFrJ6QjOrRrSkQYhmH6In7JySopKcGQIUNaXc9isaC+vt4fXWIYhmEYhukbJAwFLn0VeOAAMPtJILy5GGQjlnpg69vAPycAS64Gjq1p8grtYhqtHU1WD+tXp7Uj6SfIWTu2d9ukyGDcP3cwNv55Ft64aRymtqB7kFdRj+d/OITJz6/BHz/djV35VbLWtAzDMEwAZDTExsYiL69BVboFjhw5guTkZH90iWEYhmH8A01SvNXdO5e1VPfe0rLO2FV2FjqOoy3rOJq/is/p3w5568muGFdvY+fchsQgXftkczkR+if5YzqXGaubltF2NmvT5JtsMmndngLZjp59PzDpN8Ch74Cc/wKnt8uve2yV1OKGAJPukDIdqCyji+iwtaPDgSFxWiSHKlFYZkVxpR4pkU3bFuoNUCsguy2VJ1w0Klm0o8U1WLolD8u2F6DG5KnlQDoQy3YUiDYqNVKIR146JgUhPnDeYBiG6Y34JdAwffp0fPXVV9i1a5fQYZDj559/xr59+3Drrbf6o0sMwzAM0yFoAkJsPlGGyBBpMkM2dbLQhJRU/smO0mMZgOK9gKmmwR1hpPykmxT3SQxPblln7Co7A9k+6vO9O1K49k/YQpZ6bkNWkSQC6e6a0RZaGldvY+e6jc0i9YnsIMnm0nW/jSgkJ4f3L2vSkqDl9RWSVSdtSzaZtJ67MKacG0U33q+kc0DlBuFaNYadfA9qfYOtZ9Ioye0jbzNgqJTfQdlh4Ps/AaseByb/Tgo6uNlj+s3aseEaaitP4vZaE2bZa6EvtcBeQkEEBSw2B5QKwBqZibjhD7YopjgoMRxPXTYCiy4Ygq93FeL/Np8S4yTH3tN6PLhsDxYvP4BrJqSL0oqs+DDv4xykafnngp9oT5980f9AHBOGYXpZoOFPf/oTvvzyS8yfPx//+c9/cP755zdbvnbtWhFgUKvV+MMf/uCPLjEMwzBMh+z4Vu4rEv/+v42nEKTVtGxDR0/PaWKbu8lzmZiAl0iTVpqYGvXeJ920H6cYni/sKtsC7St2oNQoOOINbZj05JwEBhVuARVX3IMr7elvS+Pqbezct6Fgg1LtFmSwSf9WqJocGipzJb2DRtwCC3TtQhOaBxro3GicunL8O3i/NtomkqaByoaFVTsxzLxPsv8kRGaHHVCShafNe0YM3ae/vAJseg0Yfjkw5S4grcke0y/Wji7XMJFKKOw21CmssDoccFgbtDQVCtgjo5GY6ZYJ4QXSeciKD8W0rFjEhmpxorRW6DjIaEei2mjFO7+cFO2cQXFYMCUTs4cmYFtuZbNxprKO7randL/2LfWpPev64vgMw/RO/BJomDx5Ml577TXcd999uOSSS6DT6USKG1lZUgCiurpavH/jjTeEaCTDMAzDBBr0h/Nn2/Jx9Ew1aHpVZbCiTm8Wqd/0VJZo8Q9osnJ0DSRQ2UB+DqDPk2wS0yY1t1mkCZ9cxoKv7Cpbw3lcEgps6dh0XGp2S8tlDm2ynmwD7uPa0ti5bkPjTYEEJxR4oFIBYsAcaZ9FO6XMB7o+BP07LAFIGS8do3CHZBE592lPW05635Xj38H7lewjyXGBJtTFRgNKDSakOSyojT8LCREh0n0oMk+KgdA4oLYU0ARLZSIml7IRJzRm+z6XGo0h2WMOu0zYY/rV2jFtInQKJYIcDujrLUL8UasEoip3QxkR1OFxSo8JFX2gvlBgod7cEHxyY8PRMtFiQrVIiggSgQmlEKJUo67K2PafC3669t761J51fXF8hmF6L34JNBB33XUXxo0bhxdeeEFkMFAdXU1NDYKDg3HBBRfg0UcfFSUWDMMwDBNoUAowPZ2jP5yjdBqgEhiYEAYHFKKenFK/aTlNmLxOkJwWjs0+c/kHLXNdbg9Au0o6Lk1CqbWG0q1/bdmmQ32SGVd7G7dxnRw3y1IIbroejRaWrpaXDZkKwpJTCwRHBJR9qPv96tQ/UNo00J5Swmywo7TKiNjIUIjb1fUcKXsjJFoKItQVA2f2AzWF8gei0pfPc6TsFSqpGH+LtK0/rB0briFd+ZjwhutIQRMvFSDtGSenTkRVnRmJkSEwW21Yf7RMdh9kkUmNRi89RofkqGBkxelQqDe27edCF9PaObn2ieJ/bV23rf1vz/H9NSYMw3QPfv2GT5kyRWg16PV6FBcXo6ioSAQbvv/+ew4yMAzDMAELPW2lFGB6Okd/ODuhP6DpvdXuEMu91XgzTHfer04LSMn6US2qWQwWm8gE8AptE5EKDJwNRGVKopBqL9oTZI+5+kngleHAdw8ApUfQ08eJ3pNGaLBGiQfnDcW6P52H38zIkgKNMjgaHCvWHCzBiv3FIhPCZLX7/edCa+fk+rOqPev64vgMw/RuuiWUSD9s4uPjkZiYCJWK1XsZhmGYwIbEzESNe5C68Q9nJ9LkTSXqyyndmmEC+X4lKMWfJoJUbtAmKFsjcypw3y5gzlNSAMKbPea2d4B/TfS5Paa/v9f94kLxyEXDkP3wbPztmjEYk+Y9A0NvsGB7biWOltQIe8z9hXoE4jn54uca/6xkGMYJ5ywxDMMwvocmG1Tz3VIL4AkJKaaTmFmdySpSgF2h96SUH6RWidruXksPv4ayOBrS7ak12l06XD5z9Mgxa+l+JewOB1RKBbTtTV2nsgiyx7xvN3D1u5LWhTdI72LJlcAbU4Bt7wHmevSG73WwRoWrx6fh67vPxivXjEF6dEhTBZQbpNtQUGnAQ8v24to3N+Pb3YWNrjWBcE6++LnGPysZhvGrRkNWVlab1tNqtYiNjcVZZ52Fm266CVOnTvV53xiGYRgf0xErwgCDxOlIMZ3EzKjOeGDD5866Y7Ljo+W0nldoIus6xxAT2caF0nv39QOFQL6G7uPq/Ky1bWi4S/Y1uWGIoIBR+nfBNkk/g8Qfbc5gQEMQQhzP1vo5tmPMzJPvweHi2nbZALZkHeh+v7rWydOkknquUysQGaxsCqjInaO3sVRpgJFXSY3GKvsN4MDXzcU1nZQeAr77A7DmL8D4W4GJdwCRXjIifH3d3WhpnNy/13LjfcmYFOwrrEb2iTIYLVQmYUKtSWYMAOScrBAtLiwIN0xKxw2TMpDiUobVVbTnnOhSy61rs9lxtKQWRotNZL/0jwv1yfEZhund+CXQcOpUg19zG9m8eTP+/e9/45577sE//vEPn/WLYRiG8QMdsSIMMGgCR7ZspJhOrhPEsZIa1Jkd4g/nQYlhYnmL4mbuLgj0V359qfRvmtCSsJ43e8vuJpCvYUvuEi1t42ovSogJdsPkmpxAxGcN76vymgIL4lptbT3Q0MYxK6424e3yvSiqs7fZBrA168Bm92txLcprzVIavNGIc6x2sXyI9TBUBSppck7nREEWfUH7zpFImyBlN+hPA1vfBra/BxhkFBnps1/+Dmx8DRjhtMecAL9edze8jRM9yXf9XlMZhLfxdt0+SK2EzeFAUZURNV4CDmW1Jry+9hj+9dMxzBmWiIVTMzF9QByUyq4JzrX1nJw/q9zXpZKa0hoTbA47dBo1SmuMePnHI222pWzv8RmG6b34JdBgt9tx//3343//+x/uvvtuXHfddcjIyBDL8vPz8cknn+Cf//wnFi5ciEWLFuGXX34Rr6+//roQkLz++uv90U2GYRjG13TEijBAcP6RvXJfkVC2J1G4xEhNy5NCsjmkp/xy0APk4r3SE/WgcCBxpPzEjran/QQKgXANWxpXb2Pnvo2wF90C1BY32VcaqqQLE0zOCQ6g+rQUNAlNaLo24lqNanIMacv18TJm9SeycaK0FtvKK2FyqNtkA9hW60Dndo0TZKsNQeFBUNcPAHTR0DktICnAUuyS2SF3jm05T8pSmPMkMGMRsOcTIPvfQNlhz/UoeLNvmdRoXBrtMTW+ue6tIDdOiRHBjd9roqXxvmZCumiu2w9ODIdOq4bFZseGo6UoqzXLllX8eKBYtKy4UNw0JRNXj0tDpBexyfbQ2jm53lOu6x4s0uNUeb0IMqiUSkToNNAbrNh2qqJdtpTtOT7DML0XhUOueK+LeeONN/DAAw8gOzsbY8eOlV1n9+7dmDRpEl5++WURjNi1axcmTJiA8847D6tXr/Z1F3sNI0aMEK/79+/v7q4wDMNIUB36Dw9KT3bTJ8tYETZM+DKnARe+GJAZDa4YzRb89fnnMPvG3yJKJ6UAt/h0jn7N0tPtlpbRpMjb0+OWlvXla9jSuHobO9dt6JxWPgLkbZasHOmcnH8S0TbOc6Lznft00zm579Pb9WllzGxWKyoOb8B2xzB8En83EqMjm6WYkyPEhH4xePiioY33F6Xvv/DDIWw9VSFrHSi3DU12KeWfBP2o1n5IYhg0sLY8lnLn1N77kPZ5fK0UcCC9hpYgcUmyxxx3C6CL6frr3gY8xqmhtKCt4024b0/XgK7Ziv1nsGRzLnJOVbTYB3K4mD8mVWQ5tNvus43n5O1nFZXUPPzFXuw9rUdUiAaDEsKgUilbvLe68vgMw/S+uaNfMhqoDIICBt6CDMSYMWMwa9Ys/Oc//xGBBlp3/Pjx2Llzpz+6yDAMwzBtwvmH8tSsuLY5J9GEp6WJtyaYR74jtDaubdmGJv+UaUCv7sET53K1FgiO6PLgSZXBIqz+SFUgJTIEdjcbQEo5d9oAOiedrVkHym1D96vnpFXl+/uQ+kbWmNTI7nLLf4BdHwLWhlIVVyhzZPVTwLq/AmNvACb/Fogf4n2/PghkyY3T3gJ9u8ZbLjhApQSXjUkR7dCZaizJzsWXO06jzmzzDGJa7PhkW75oY9OjsHBKJi4enSwEKLvqnLxxorROiISGaFQiINCWe6srj88wTO/DL2HF48ePIzqa0hBbJioqCidOnGh8379/f9TW1vq4dwzDMAzDMP6FnvbSE3ONStFma8Eeax0YPxi45BXggQPAnL94t8ekIMS2d4F/TQKWXAUcW92tTiZdPd5DkyKw+PJRyH5kNp6ZPwKDE8O8rku2mH/8bDemPr8Gz39/UJRq+JIee28xDNO3Aw0UZCDdBbPZe6obLaN1XAMS1dXVIvjAMAzDMAzTZThtJ502llazZ7NZm9wXfDDZpae9NJ+z2BzerQVVSkRq7I1WmBFqO0JVNpiMBihtJqjs5sa+9QibVSqLOPsPDfaY70klK96gIAMFG/41WQo+dIM9pq+sGsODNVg4tR9W/mEGPvnNFFwyOlkIJcpRWW/Bm+tP4Ny//YRb38vBmoPFIsOiq2FbSoZhemTpxGWXXYY333xTiDqSi4RTCNJJQUEB7rvvPhQWFuLOO+9s/PzgwYNttsZkGIZhegBdYEnHdDM9/Ro6bSfLjwF52VLaPrksuEPihDaLpNOw+Z/AOX/suFaGzJhFBatQoVRA6QAK9QYkRmub2wAqgMvrl2Horlpgt3TcYXYHFlZVodRggvaUUjx9rtCm4ue4G3Bab+yQdWBLNpk+Q9hjXik1YY/5b+DAV/L2mCQo+d39wOq/ABN+1XX2mAFg1Uj7mpwVKxqVJXySk48Pc/JQpG+wWXW7bdcdLhWN+nHTlAxcNyEdsWFBXXKd2ZaSYZgeGWhYvHgx1qxZg6+++grfffcdJk6ciPT09EbXiW3btsFisWDgwIF45plnxOc7duzAmTNncNttt/mjiwzDMIw/6AHuEkwvv4ZO20kKMpDjBL0na0d3SLtBoZLWqTzVOdtOmTGjqvtQrRqRSg309VYU1+mb2QAOTQjCKFsFVHnbm20zzGxDmsMCs8EOhwGoDrLggLFcCCC21zqwNZtMvyDsMd8B9E+3bI9prGpujzn5d0D6RJ92zZ9WjTTu98wehN+dNwBrDpUILYcNR8tk16Ugx4srDuMfq47iolFJQjxyXEa0R8lDe64z21IyDNMjAw2xsbHYvHkzHnroIXz44Yfi39ScBAcH4+abb8YLL7wg1iXGjRsHg0FGMIhhGIbpWfjAko7xM73xGtKkLLqfFESwGAC1ixgiBR40IZLtpVEvBRx8MGY6EoJ0JGIsElBSa2pmA3jB0CgkHgoSVqqu9pi0TU21CWWVtUiq3ScmiFlxOsRERrQrQNBWm0y/0RF7zNQJkj3m8Plts8fsAP62alSrlLhgRJJoZH26dEueuE7VRs9sD7PNjq92FYo2PDlCBBzmj00R1poduc5sS8kwTI+zt3Slrq4O27dvR1FRkXifnJws3CVCQ0P92Y1eC9tbMgwTkPjIkq47sNlsIlPvsccea5vrRG+ht1xDV9vJlAnA6a1S1gIFFWgyT+dZVwKEJQKp44HCHR237WzjmFnsDk8bQIelZXtMmxWWU9moip+A8nOeweDUuDY/We+ITabfobE78ROw+Y3W7THDUyR7zPG3tm6P2UG606rRYLbhm92n8f7mXOwvrG5x3fAgNa4an4YFUzKREaPr0HVmW0qG6TuM6On2lq5QQGHGjBn+PizDMAzTnfjIko7xI73xGioazsu1ic+d75V+GTNynvCwAZSRK3BFpVBApVYiKSIYSSmRQDsmvR2xyfQ71KcBs6TmtMfc/RFgkRGFrCkE1vwF+PlFYMz1UpaDN3vMDtKdVo0hWhWum5iBayekCzeKD7Jz8d2eIhEwcqfGZMX/Np0SbXRapLi3rDZ7u64z21IyDNMjAw0MwzAMwzBM99HjrAyd9pizHgN2vA/kvAVUF8jbY5LGA7UBs4Epd0mBCmU3ZWV0MXRtzsqIFu2xi4eLkoglW3KRXyFfarynQC9eKdigUikxID60sawiIK8zwzC9Cr8FGkwmEz766COsX79elE3QeznoBx8JRzIMwzAMwzDwnZVhlVGk0bsGG5y2jaRDEHA2mU57zKl3A4e+lXQcyBVEjuNrpBY3GJj8WynTQdt7ynRjQrW489wBuOOcLPx8tBRLNudi7eESWSdWslDdd1qP/af1SIsOwaDEcMSHaQP3OjMM0yvwS6Dh9OnTmD17No4ePerhQ+yON8VchmEYhmG6mN6iu9BRyHaSxqCx2Ro+dzQss3ffmPvQUrTHWxmq1MCIK6RWsB3Y8m9g/5de7DGPAMsfANY8LWk4kJZDZBp6C0qlAjOHJIiWX1Ev7DE/2ZqPijrPe4z+As+vNIhG5RjRIRpEhUQH7nVmGKZH45dAw6JFi3DkyBFMmzYNDzzwAAYPHozwcP6hxjAMwzC+hGq4qf6aUuXpKTZNKMiloHHCu/FVyeqxJcg5Yfp9vTPYcHobUFcquUzo85svo89Pb+/a827PmNNTeB9ZivYqK8O08UDa28DcBnvMbe96t8fc+A9g0+uSSwWVVfjYHtPfpMfo8NC8ofjDnEH4Ye8ZoeWwPbfSq8Aktc+258PmcGDhlEwMT4nwe58Zps/97u1D+CXQsHLlSmRkZGD16tXCypJhGIZhGN9CtnaNlnwWm0iVb2bJR0/VacJLrgatQev2FiFIV9tJmvgX7wNMNZ7rBYUDiaMkwciusu1sz5gTPrQU7XVWhhEpwOwngHP+BOz9VCqrKD3kuR5lrez/Qmp+sMfsDoLUKlx+Vqpo+wv1eOXHI/j5SCmsds+sYpPVjo9y8kSbkBktLDLnjUwS+2AYxge/e/sQfgk0kB7DnDlzOMjAMAzDMH76Q4eE4o4U1wpnARL9o3p8SpWnp9jElIywpg3SJno6LFBqfhc/SQ8IKEOBMjSc5QveShlcS0Z8UT7S2pi799Mbnegb/dE7PjO622wbfYJWJ5VIjLtFssekgMPRH71ntCz7NfDj48Ck24Hxv/KZPWZ3MSIlEu/cOhEVdSa8+fMJfLunEIVVRtl1t+VWihYbqsV1E9Nx4+QMpEXr/N5nhunVv3uz+k6wwS+BhlGjRqGsrMwfh2IYhmEY9PWUTXqaQn/oROk0HvX3lCpPy8en6tD4DJcmvEq3J5g+kCcIGNxtJzXdkG3ZljH3g6Vor7UydLXHLDsq2WPu+rAFe8yngZ9fAsZcB0z+HZAwFL2JmNAgPHzRMPz5wqHYfKIcS7JzsXJ/sZgMuVNeZ8Yb647j3z8fx+yhCVgwJRMzBsULPQiGYTr5uzczumcHc9uBX87yoYceEm4TOTk5/jgcwzAMw/RZ6Ok0pWzSBML5hw5Br/Se0qdp+ZFimXIBhumNxA0CLn4ZeOCApOUQ4UUMUthj/g94YzLwwRXA0VWAvXdF3OjnwLQBcXjjpvHY+NAs3Dd7EBLC5YNZlOyz+mAJbn1vK8772zr8d/1xVMqITDIM0/bfvYfP9J3fvX7JaBg3bpwQgSTnCXqdO3cu0tLSoPTia0x6DgzDMAzDtB8Sn6K6UErZdHdyovck+kf1+JQqzzB9ipBoqRxlyu/bYI+5Vmqxg4ApZI95Q6+yxySSIoNx/9zBuHvWQKw6UIwPNueKbAc58irq8dz3h/C3H4/g0tEpQsthbHqU3/vMMIEK/+7tpkBDv379GlNHFi9eLJo3aD2rVcaeiGEYhmGYViGFaxKforpQ+r3rGmyg9+QsQKJ/VI/fJ60xA7Xf1C+7TdJpsFkBY7Vn2YQvdSMCdVy62x6z/Ciw/I9N9pgT7wCi0tGboDTui0Yli3aspAZLsvOwbHsBakxW2fTwZTsKRBudFinKKijwQHaZDNOX8dvv3h6EXwINM2bM8HiqwjAMwzBM10NifqRwTeJTVBfqXidK9oW0fHCii800TW7dM8TpM2/0VGvMQOq365hTv0oOAKZqoLYEOLJCetLufnzhhDFS+rwr+xhI49Lt9pjvAYYKz/WMemmMNv0TGH6ZZI8pBD0VvcrabmBCOJ66bAQWXTAEX+8qxPubT+GQl1TvPQV6PPj5Hjy7/CCuGZ+Gm6Zkon9c78r6YJiu/t07JMnld28vxy+BhnXr1vnjMAzDMAzT56EJDdlokcI1iU+V15pFuQQ9TaE/dAYlhonlzcSo2usu0VOtMQOp365jTkGHulLAYpAm/VajNLF1n8RqQho+V3ZtHwNpXLrbHnPGImCP0x7zoBd7zC+lljpeCji42GP2Fms7Kr0i14kbJqVjR16lKKv4fu8ZmG2eAUi9wYK3fzkp2jmD4rBwSiZmDU2Auo8I3jFMh3/39nL8EmhgGIZhGMZ/OCc0jRMeq5Sy2WzCQxNaekLdGrQOpcx7o6daY3ZHv2kc5cacSiYog6G2GNDFAYYqwG4BQuOb1qFARGiCNLkt3OG7PvbU69lVUDBn/C3AuJuBE+sa7DFXyq97enuDPeZjwKQ7sC12Pj7bV9urrO3oiez4zBjRHrvEhE+35WNpdp54QivHhqNloqVEBotAxXUTMxDvRWySYfrk794+BAcaGIZhGKYXQn/QkI0WpXCT8CPVhVLKZuPTFHpaTmnwna3L76nWmN3Rb29jbjUBKx8B8rKbAgkUdKA+0jY00adX0Xz8NKynXk+f2GPOlJqwx3wT2LXUiz1mkdBwGKN4AWXaWdBEXwnED+t11nZxYUG467yBuHPGAPx0qAQfZOfi5yOlsusW6o1COPLVNUcxb2SyyHKY2C+aS6mZXk+rv3v7EH4NNNTX1+Onn37C0aNHUVNTI374ukM/lB9//HF/dothGIZheiX0h83I1MiWJ1O9MQ0+kPE25jS590cggemgPebfgFmPAjs+AHL+C+jzPVbTOMyYZ1qBeWdW4GjtRGyMuxZHwieLWm1Ko3Za27X4newBqJQKzBmeKFpueR2WbskTmQ5V9Z5ONhabA9/uLhRtSGI4FkzNxBVnpSIsiJ91Mn34d28fwW/f8v/973+4//77UV1d3fiZnCInBxoYhmEYhmGYwLTHvFfSZTj0XYM9ZrbsqoNqt4pWqk3HprhrcFpzNkzW4F5nK5sZG4pHLhqGB+YOxnd7ikSWw+78Ktl1DxfX4PGv9uGF7w/iynFpwrGiLwnjMUxfwy9h89WrV+PXv/61CCI88sgjmDp1qvj8zTffxKJFizBw4EARZLj77rvx7rvv+qNLDMMwDMMwDNNBe8zLgV+vBO5YC4y6Fg6F/LO7eHM+5he+gifLFyFIreq11nbBGhWuHp+Gr38/Hd/cPR3XTkhDkBenjTqzTQQkLvjHelz75mZ8t6dQOHUwDNO78Eug4eWXXxZBBiqbeOaZZzBo0CDx+R133IEXXngB+/fvxx/+8AcRZBg/frw/usQwDMMwTJfZNNqat5asMQOFQO039UE0R1Mfxb+dzd43x6Ud0KR1b4Eem46XiVefTmJJU+Oqt2C5dw82JN2KakWE7Go/B83sM9Z2o9Oi8OLVY7Dlkdl47OJh6Ber87puzskK3P3hTkz/61q88uNhFOnlRSYZhul5+KV0YuvWrZgyZQrGjBkj3wm1Gn/729/w1Vdf4cknn8SyZcv80S2GYRiGYTpLT3UjCNR+k5MBOUyQxaW7DkBdCXB6m291HAJ1XNpId9lLaqNToTn/CTybcyPS8r/DpYav0c+eK5bVIwQn0q/ApX3M2i5Kp8Xt52Thtun98cuxMpHFsOZgMeyeEm0orTHhtbXH8K91xzFnWAIWTumHaQNioVS2IETLMExA45dAQ21tLTIyMhrfBwVJIkgkCBkeLkV2lUolJk+ejDVr1vijSwzDMAzDdLVNY3utMf1NoPbbtV80CSveC5hqPNcLCgcSR0qikV3Zx0Adlw4EGT7blt9t9pKN1nahN+Bv1Zejf+02nF/9JepD03Hp5GF9ztrOCQULZgyOF40cOD7akoePt+ahrNbT8Yau28r9xaJlxYXipimZuHpcGiJ1vbPkhGF6M34JNCQlJaGioqLxfXJysng9cuRIs1IJWsdg4JQphmEYhglousoa098Ear/d+0UlEnJ9dO1XV/YxUMelHVB5BGUyUJAhSqcRTg/dYS/Z3NouE4rg6zEuMRQaNbssEHRd/nTBENw7exBW7D+DJZtzkXOqaY7gyomyOjzz3QG8tPIQ5o9JxcKpmazkzzA9CL/81Bs6dKiwtHQybdo08YP/xRdfxMcffyx+EWzatAlr1671Wl7BMAzDMEwA0VOtMQO13+790gR37/F7GDSxp3IJeiLuDDIQ9Opve0m2tmsdrVqJy8akiHboTDWWZOfiyx2nhVCkO0aLHZ9syxdtbHoUFk7JxMWjk4UAJcMwgYtfCsUuvvhinDx5Ejk5OeL97NmzMXr0aHz++edITU0VWQ0zZ86E3W4XopAMwzAMwzAM01ZqTBahyUDlEq7W6QS9Dw1SwWS19Tp7yd7A0KQILL58FLIfmY1n5o/AoIQwr+vuyq/CHz/bjanPr8Hz3x8UZTEMw/ThQMPNN9+MH374AYmJidJBlUosX74cc+fORUlJCXbu3AmdTofFixdjwYIF/ugSwzAMwzAM00sID9II4cc6k1VkzbpC7+tMtl5tL9kbCA/WYOHUfvjx/hn45DdTRNaC2osYZGW9BW+uP4Fz//YTbn0vB2sPFYtsFoZh+ljpRGRkJC644IJmn1Emw4oVK1BfXw+9Xo+EhASoVJwCxTAMwzAMw7QPso0kdwl6wn26sh4ZkVJmAwUZCvUGBCusSA5VYkicFrCaAlpvoq9D121yVqxoJdVGfLw1Hx9uycOZaqPHuhRTWne4VLS06BDcNDkT105IQ2xYzy0DYpjeQrcr01AmAzWGYRiGYRiG6WjNP1lY6utNGJX7f0goKYJGpYDF5gA9FI8M0SCrNgyaH4OaHDRIAJODDX4X7SSdDCp1oSwUChDRtfNGQkSwEI6867wBWH2wRGg5kFWmHAWVBvx1xSH8fdURkQ2xYEomxmVEeZTSMAzTRwINDMMwDMMwDNMVjg8Kmwnq0gqkVB+Aw9qgcUkaDXY1dJUqoNJlA3LZ6MECmD0Nsh8l5w8S5SQ9DSp1oSwUChC1Zv2pVikxb2SSaMdLa7E0Ow+fbc9HjdHqsa7ZZseXO0+LNjw5QrhVzB+bAp2Wpz0M40/89o0jLYY33ngD69evR1FREUwmk+x6FHU8fvy4v7rFMAzDMAzD9BIm94+FLSMKlhNa6GPHQKNSI1Kngcr5VNthBwq2dnc3+2SQ4bNt+cJ+lLQUSLSzrsooSl30BslWtbVgg5MB8WF44tLh+NMFg/Ht7kK8vzkX+wurZdc9UFSNh7/Yi+e+P4irxqVhwZQMDEwI79JzYximGwMNBw8exLnnnovy8nIPgR6GYRiGYRiG6SooqKBSKxEcoQOUbvpfdh7n7iiXoEwGCjJE6TSN9qM0JzhdZcDR4lqxfHxmtLAGbSuUoXDdxAxcOyEdO/OrRFnFd3uKxPHcocyH/206JdrUrFjcPDUTc4Yntut4DMO0D798uxYtWoSysjJceeWV2LZtG6qrq4WVpbfGMAzDMAzDMEzPhzQZqFyCMhmcQQaCXum91e4Qy2m9jkD7GZcRjVeuHYvsh2fjzxcORXpMiNf1N58ox++W7sDZf12LV1cfRbGMyCTDMD0ko2HDhg0YMmQIPv30UxZkYRiGYRiGYZg+Agk/kiYDlUu4CzPS+9AgFUxWG6qNlk4fKyZUi9+eOwB3nJOF9UdK8UF2Ln46XCLcKdwprjbh76uP4PW1R3HBiCQhHjklK4bnKgzTkwINlBo1duxY/uIyDMMwHfklIom2tQRb1TEMf4eYgITcJUj4kTQZaE7gGmyg93UmGxIjghERrOmyY6qUCswcmiBafkU9lm7Jwydb81BZ7xnMoIyK5XuLRBuYEIaFUzJxxbjULu0Pw/RF/BJomDBhAnJzc/1xKIZhGKa3BRk2vgpUnmx5PbaqYxj+Dnn8/LB7ajLQZ0y7bSY7A+2b3CVI+JE0Gdw1GtRKhVhO6/mC9BidKKf4w5xB+GFfET7YnIsdeVWy6x4rqcWT3+wXNpmXn5WKBZMzMTwlwif9Ypjejl8CDU899RRmz56Nb7/9Fpdeeqk/DskwDMP0BiiTgYIMuZvati5b1TEMf4ecsLtEl9tMdgQKYNC+yV2ChB/La82iXIIyGSjIMCgxTCz3tTBjsEaFK85KE23faT2WbsnFVzsLYbDYPNatN9vw4ZY80SZkRguLTLLWDFK7iYsyDOPfQANZWLpz3333CTHIG2+8EXPnzkVaWhqUSvkfKDNmzPBFtxiGYZieTNpEQOH2e4Ot6hiGv0PuZVSU4dQatA6t28foSpvJ9uDcZ2OAwyqVS/gywNESI1Mj8fyVo/HnC4fhix0FQsvhRGmd7LrbcitFiw3V4rqJ6bhxcgbSonV+7S/D9ER8Emg477zzZPUYKEXqgw8+wJIlS1rc3mbzjCwyDMMwfRwKMrBVHcPwd6jFnxMKYPp9rOviR5vJtkLBBNo3lWyQ8CNpIFC5RHdaTEaGaPCr6f1x67R+2HS8XJRVrDpYLIIw7pTXmfHGuuP4z8/HMWtoghCPnDEoHkql55yHYRgfBRpuvvnmXiP8uHHjRjz77LPIzs6G2WzG8OHDcffdd4tzbA//+9//8Ktf/crr8uuuuw4ff/xxF/SYYRiGYRimD0N/g3IZVbttJqmkwWkzSU/8fQEFFXy1785AYzB9YJxoRXoDPsrJx0c5eSitMXmsSzGI1QdLRMuM1eGmyRm4Znw6okP7XoYMw/g90ECT6t7AsmXLRADAbreLco64uDisWbMGt9xyC/bs2YO//e1v7d7nmDFjhAOHO5MnT+6iXjMMwzAMwzBM99lM9mSSI0PwwNzBuGfWQJHh8UH2KWSfqJBdN7e8Hs99fwgv/3gEl45JEY4VY9Kj/N5nhumzYpA9kYqKCtx2222ijIMCDqQvQRQXF+Pss8/Gyy+/jEsuuUSUibSHyy+/XIhjMgzDMAzDMExvtpnsyVD2xcWjk0U7WlyDJdm5WLbjNGpNVo91TVY7Pt9eINrotEhRVnHp6BSEaFk8kum7+Kwoau3atXj//fdx4MCBVteldWjdn376CYHC22+/jerqasyfP78xyEAkJibixRdfFP+mYAPDMAzjT6s6W/PGVnUMw98hpl02k+T0QJoMFFwQP1r9ZDPZkxmUGI6/zB+JLY/MxrNXjMTQFsZoT4EeD36+B1OeX4PF3x3AyTJ5kUmG6e34JKMhPz8fF198MdLT07F9+/ZW16f1rrjiChQUFODo0aNISUlBd7N8+XLxevXVV3sso3MLDg7G6tWrYTQaxb8ZhmEYH8NWdQzD3yGmx9tM9mSo7OSmyZm4cVIGtudWCreK7/cWwWLzFI/UGyx4+5eTop0zKE6UVZCIpJrHl+kjqH2VDUDCifTkPzy89agorfPSSy+JsoJ33nkHjz/+OLqb3bt3i9dx48Z5LNNqtRg5ciS2bduGI0eOYPTo0W3eLwVeFi1aJLIlkpKSMGvWLJx77rld2neGYZheA1vVMQx/h5heazPZU6Gykwn9YkR77OLh+HRbPj7ckicyQ+TYcLRMtJTIYGGPed3EDMSHB/m93wzjTxQOZ95UFzJt2jScOHECZ86cadd2ycnJ6N+/PzZt2oTuhIIAkZGSIq5er0dERITHOpSB8dVXX+Gbb77BpZde2inXCQo0fPLJJ6Iso7OMGDFCvO7fv7/T+2IYhgkI6NeUTfJ3bzEg4Se3I9LuWbx4MR577DGoVFx/y/QAAuw7xHQ/Fps9oGwmewPk5rH2UInIclh/pLTFdTUqBeaNTBZZDhP7Rfcatz6m5zHCh3NHn2Q0HDp0CNOnT2/3dhMmTOj2IANRW1vb+G+dTie7TmhoqHitqalpcxCFRCBJ8yErKwsGgwE5OTl48MEH8fPPPwthSbLQbOsfrc6bwp3jx49jwIABbdoHwzBMj4Ct6hiGv0NMn7CZ7MmolArMHZ4o2qmyOizdkotPtxWIEgp3qNTi292FopHeA4lHXn5WKsKCWKef6T345G6uq6trzAhoD7SN6yS/M1DGwcGDB9u1DQlSTpo0Cb7gggsuEM0JZUlQJsTMmTMxfvx4UYbx6aef4oYbbvDJ8RmGYRiGYRiG8T394kLx6MXD8cfzh4hgAjlW7C7Qy6576EwNHvtqH1744RCuHJcqgg6DE1mQk+n5+CTQEB0dLWwg2wttQ9t2BSdPnsThw4fbtU19fb14DQsLa/aZXOkEBVOItmhQtAQd695778Xdd9+NlStXtjnQ4C29xVumA8MwDMMwDMMw/iNYo8I1E9JF251fJQIO3+wuFHaY7pBt5vubc0Wb3D8GC6dm4vzhSULEk2F6Ij4JNAwfPlyUAVB5QEhISJu2oQn95s2buyyjYNeuXR3elgILlF1B+gzkhEHn4w59TmRmZqKzDBo0SLwWFRV1el8MwzAMwzAMwwQWY9KjRHv04mH4fHuBCDqcKpcecrqz5WSFaCQYecPEdNwwOQPJkW2bUzFMoOCTEBnpDdATfxLLaiu0LgUm2iKs6A/GjBkjXnfs2OGxzGKxYN++fcLWcvDgwZ0+VmVlZTPdB4ZhGIZhGIZheh9ROi1uPycLa/94Ht6/bZLQdFB60YIsrTHhtbXHcPZff8KdH2zDL0fL4AMdf4bpOYGG3/72t8JB4YUXXhABBLvdMz3ICS175plnxLq0zZ133olA4OKLLxavn3/+ucey7777DkajEXPmzBHBhs6ybNkyr1aaDMMwDMMwDMP0LpRKBWYMjsdbN0/Ahodm4e6ZAxEXpvXqaLFyfzEWvLMFs1/+Ge/8clJWZJJher29JUHuETQRN5lMSEtLwzXXXCMm0vHx8WJ5aWmpyBb47LPPRBlCUFAQ1qxZg6lTpyIQqKioEFabZHVJgYArr7xSfF5SUiIcNY4dO4affvoJ5513XrPthg4dKl7pXFJTUxs/f/7553HHHXcgLi6uWWbEc889J9woqMTk6NGjzbbpCGxvyTAM41vY3pJhGIbxBSarDSv2nRFlFVtPSRnP3gjWKHH5WEk8kh1EmECcO/os0ODUSVi4cKHouJw/rPPQdIJLlixpLFcIFCjAcO2114p+UkAhNjYWq1evRlVVFR544AG8/PLLHts4z5PEKPv169fscwqmkIVnenq6CGDQ+BQWFoqsiKVLlzYGMzoDBxoYhmF8CwcaGIZhGF9zsKhaBBy+3Hka9WZbi+uelRGFhVMycdGoZCFAyTC9PtDgZMWKFVi+fLmYWJeXl4vPaNI+duxYUaIwb948BCobN24U5R8kbmk2m4UwJDlE3HLLLbLrews0PPnkk0LskpwwKJuDhp0yPWbPno37778fQ4YM6ZL+cqCBYRjGt3CggWEYhvEXNUaLCDZ8sDkXR0tqW1w3WqfBtRPTsWByJtJjdH7rI9NzGdHTAw2M/+BAA8MwjG/hQAPDMAzjb2jKRk4UH2TnYuW+M7DavU/h6LnneYPjhUXmuYMToPKmNsn0eUb4MNDgE3tLhmEYhmEYhmEYpmugrOkpWbGilVQb8fHWfHy4JQ9nqo0e69Jj5J8Ol4qWFh2CmyZn4toJaYgNC+LLwfgNDjQwDMMwDMMwfQ6z1Y7DZ2pQY7IgPEiDIUnh0KqVPWb/vbVvTOskRATj3tmDcNd5A7D6YLHIcth4TCpPd6eg0oC/rjiEv686gktGJ2PB1EyclR4lq5/HMF0JBxoYhmEYhmGYPkX2iXL8uL8YJTVGmCw2BGlUSAgPxvkjEsUT40Dff2/tG9M+1Col5o1MFu1YSa0Qj1y2owA1RqvHumabHV/sPC3aiJQIIR552dgU6LQ8HWR8A99ZDMMwDMMwTJ+BJtqfbcvHkeJa2OwOhAapUVdlRF55PfQGs1inMxNuX++/MwRy35jOMTAhDE9dNgIPzhuCb3YV4v3NuThQVC277v7Cavz5i7149vuDuHp8mrDIHBAfxpeA6VI40MAwDMMwDMP0CahkgJ7m00Q7SqdBalSISCEnob3TVQYcLa4Vy8dnRkOjUgbc/jtDIPeN6TooQ+H6SRm4bmI6duZXYcnmXHy3p0hkNLhDmQ/vbTwl2vSBsSLLYc6wRJEpwTCdhe8ihmEYhmEYpk9AugRUMkBP850TbYJe6T0p+dNyWi8Q998ZArlvTNdD13VcRjReuW4sNj88C3++cKgQhvQGaTz8dskOnP3Xn/Dq6qNCcJJhOgMHGhiGYRiGYZg+AYkfki4BlQy4i+HR+9AgFUxWG6qNloDcf2cI5L4xvoXcJn577gD8vGgm3rt1ImYNTRAWmHKQi8XfVx/BtBfW4vdLd2Dz8XKR9cIw7YVLJxiGYRiGYZg+ATkskPgh6RLQ5Ml1wk3v60w2JEYEIyJYE5D77wyB3DfGP6iUCswcmiBafkU9lm7Jwydb81BZ7xlcogyX5XuLRCP9ByqruGJcKt8fTJvhjAaGYRiGYRimT0A2juSwoFYqhC6B80mtU6eAPqfltF4g7r8zBHLfGP+THqMT5RSbH56Nv183BuMyoryuS44WT36zH1OeW4NHvtyLg15EJhnGFc5oYBiGYRiGYfoEWrVS2DiSwwKJH5bXmkXJAD3Np4n2oMQwsbyjYoi+3n9nCOS+Md1HsEaFK85KE23faT2WbsnFVzsLYbDYPNatN9vw4ZY80SZkRmPh1EzMG5mEILWqW/rOBDYcaGAYhmEYhmH6DE77RnJYIPFD0iWgkgF6mk8T7c7aO/p6/721b0z3MzI1Es9fORp/vnAYlm0vwJLsXJwoq5Ndd1tupWhxYVrhcHHDpAykRev83mcmcFE4WN2jVzFixAjxun///u7uCsMwTK/EZrNh8eLFeOyxx6BS8VMchumpWGx24bBA4oekS0AlA135NN/X+++tfWMCB5ombjpejg8252LVwWLhWOINpQKYNTRRZDmcMzAOSvqA6dNzR85oYBiGYRiGYfocNLGmJ7g9df+9tW9M4ECCodMHxolWpDfgo5x8fJSTh9Iak8e6FINYfbBYtMxYHRZMzsTV49MQHartlr4z3Q+HLhmGYRiGYRiGYRivJEeG4IG5g7Hpz7PwrxvHYUpWjNd1c8vr8ez3BzHl+TX402e7sTu/ike2D8IZDQzDMAzDMAzDMEybsmEuHp0s2pHiGizNzsWyHadRa7J6rGuy2vH59gLRRqdFYsGUTFw2JkUIUDK9H85oYBiGYRiGYRiGYdrF4MRw/GX+SGQ/MhvPXjESQ1uwRt1ToMeDn+/B5OfWYPF3B3DKi8gk03vgjAaGYRiGYRiGYRimQ4QFqXHT5EzcOClDOFGQeOQP+4pgsXmKR+oNFrz9y0nRZgyOx8IpmZg1NAEqFo/sdXCggWEYhmEYhmEYhum0eOTEfjGildYMx6fb8kVpRaHeKLv++iOloqVGheDGyRm4dkI64sOD+Cr0Erh0gmEYhmEYhmEYhukyKGDw+5kDsf7BmXjr5gkie8Ebp6sMeGnlYUx7YQ3u/Wgntp6qENaaTM+GMxoYhmEYhmEYhmGYrp9sqpSYOzxRtJNldfhwSy4+3VYgSijcoVKLb3YXikZ6DyQeeflZqaI0g+l5cEYDwzAMwzAMwzAM41P6x4Xi0YuHY8sjs/HS1aOFE4U3Dp2pwWNf7cOU59bgia/3CYcLpmfB4SGGYRiGYRiGYRjGL5C95TUT0kXbnV+FD7Jz8e3uQmGH6Q7ZZr6/OVe0KVkxWDilH84fkShsNpnAhgMNDMMwDMMwDNNZqKbcZm55HZWWFPN4rBmmgTHpUaI9etEwfL69AEu25CK3vF52fLJPVIhG+g83TMrADZPSkRwZwmMZoHCggWEYhmEYhmE6G2TY+CpQebLl9aL7A9Pv42ADw7h/NUK1uGNGFn59dn9sOFYmLDLXHiqGXUYTsrTGhNfWHMW/fjqGucMSsXBqJqYNiBWuF0zgwIEGhmEYhmEYhukMlMlAQYbcTW1bV80Wfgwjh1KpwLmD40UrqKzHRzl5+DgnH+V1ntlCNrsDK/afEe3/27sP+Ciq9f/jJ5DQqzQhVBEQAWnSRUFQ4EoTEUQRAcVesHdQsSAqwlWuvcsVkAuIDUThoiIgUgUp0jtSpZME9v/6nt+d/W82synLJLtkP+/Xa0mY2TI7LXOeOed5zilT2PRtVsVc1biiKV4wgZUbBQg0AAAAAF6p2MSYuKDx475TxmxdwDoGsnIolSxkHuxwnrm7XQ0zbflO8+m8TWbBxv2uz12/+4h55qs/zIjpq0z3Bom2YkXdxNDJJpH9CDQAAAAAXlGQIU/e1NPS5rgDkEn54/Oabg0S7WPljoM24DB58TZzNOlkmuceTz5lxi3YYh8NK5cw1zevYv5Rr7xNQImcRbpOAAAAAEDUq12+mHnuynq2ROYz3eqYGmWLhHzu4s0HzH0TlpqWw2ea4d+uMlv2uSeZRPagRwMAAAAA4IxRtECC6deiqu2xMH/DPlsic/rynSbFJXvkviNJ5s3Z68xbP64zbWuVta+5uGYZkzcPySOzE4EGAAAAAMAZR5Ummp9Tyj7+OnjcDpn49/zNZufB467FYWau+ss+Kp1V0FzXrIrpdWElc1bhfBFZ9tyOoRMAAACAV5T48dTJ1A9NA5CtyhYrYBNH/vxwW/Nm30am1bmlQj53y75jdjhF8xd+MPeNX2IWbd5vfIpEwDP0aAAAAAC8QnUJIKLi8+YxHeuWt4+1fx02Y+dvMhMXbjWHjqekeW5SyikzafE2+6hToZgdVtG1QQVTKB/N5NPFGgQAAABOR958xpSslvHz9Bw9F0COOLdsETO0Sx3zYIdaZuqS7ebjuZvMHzsOuj53xfaD5pFJv5vnvllpejauaEtkVi8TOtkk0kegAQAAADgdcXHGtLrHmJNJ6T9PQQY9F0COUg+Fa5pWNr2bVDKLtxwwn87dZL5atsMknUw7rEk9Hz6Ys9E+NPxCvRza1y5ne0og8wg0AAAAAKdLAYT4/KxHIMqTRzaqXNI+Hr+itvl84Vbz6bxNZuv+Y67Pn7N2r32cXayAubZZZXNNk0o2FwQyRlgGAAAAABBTShXJb269pLqZ/WBb837/C03bWmVCdjhSFYuRM9aYlsNnmjv+vcjMW7+X5JEZoEcDAAAAACAm5c0TZy49r5x9bN571CaPnPDbFrP/aHKa56ac8pmvl+2wjxpli5jrW1QxVzZMNEULJERk2aMZPRoAAAAAADGvcqlC5tF/1DZzH21nRvaqbxpWLhFynfz512Ez5IsVptnzP5jHJ/9uVu10TzIZq+jRAAAAAADA/xRIyGt6NKpoH8u3/W3zOExZss0cT06bPPJo0kkzdv5m+2hStaStVtGpbnmTLz627+kTaAAAAAAAwEXdxOJm+FUX2J4O//lf8sj1e464rqsFG/fbx7Aif9gKF9c2q2ISSxSMyfUa22EWAAAAAAAyULxgghl4UTXzw/2XmLE3NTMd6pQzeUIkj9xzOMmMmbXOtH5xpnn+m5UxuW7p0QAAAAAAQCZLZLY6t7R97Pj7mPls/mbz2YItZvehE2mee8pnTLXShWNyvdKjAQAAAACALCpfvKC57/JaZs7Dl5rXr21omlU7K9X8ogXiTbcGFWJyvdKjAQAAAACAMCnxY+cLKtjHml2HbB6HSYu2mZ6NK5pC+WKzyR2b3xoAAAAAAI/VLFfUPNOtrnmo43kmKSVtlYpYQaABAAAAyAFqdKzeecgcOpFsiuZPMLXOLhrzJfCA3KpI/nhj8puYRaABAAAAyGbz1u81363YZf46dNycSD5p8ifkNWWLFjCX1ylnmp9TivUPIFch0AAAAABkc5Dh89+2mDW7DpuTp3ymcP54c+TAcbN571Hz97Ek+xyCDQByEwINAAAAQDYOl1BPBgUZShRKMIklCtryeD6fz2w7cMz8ueuwnd+4SkmTkJeCcAByB85mAAAAQDZRTgYNl1BPBifIIPqp/6ec8tn5eh4A5BYEGgAAAIBsosSPysmg4RJOkMGh/xfOn9ecSDlpDh5PZhsAyDUINAAAAADZRNUllPjxyIkUO1wikP5/5MRJkz8+rylWIIFtACDXINAAAAAAZBOVsFR1ifg8cTYngxNscHI0aLrm63kAkFuQDBIAAADIJvni89gSlqouocSPew8n2eES6smgIEONckXsfBJBAshNCDQAAAAA2cgpXanqEkr8qJwM5YoVsD0ZFGSgtCWA3IZAAwAAAJDNFExQCUtVl1DiR+Vk0HAJejIAyI0INAAAAAA5QEGFuonFWdcAcj2SQQIAAAAAAM8QaAAAAAAAAJ4h0AAAAAAAADxDjgYAAAAgCiWlnLLJIw+dSDZF8/9f8kiVywSAaEegAQAAAIgy89bv/f/lMJNPmvwJeSmHCeCMQaABAAAAiLIgw+e/bTFrdh02J0/5TOH88ebIgeNm896j5u9jSf5ymQAQrQg0AAAAAFE0XEI9GRRkKFEowSSWKGji4uKMz+cz2w4cM3/uOmznN65S0pbLBIBoxNkJAAAAiBLKyaDhEurJ4AQZRD/1/5RTPjtfzwOAaEWgAQAAAIgSSvyonAwaLuEEGRz6f+H8ec2JlJPm4PHkiC0jAGSEQAMAAAAQJVRdQokfj5xIscMlAun/R06cNPnj85piBRIitowAkBECDQAAAECUUAnLskULmPg8cTYngxNscHI0aLrm63kAEK1IBgkAAABEiXzxeczldcrZ6hJK/Lj3cJIdLqGeDAoy1ChXxM4nESSAaEagAQAAAIgiTulKVZdQ4kflZChXrIDtyaAgA6UtAUQ7Ag0AAABAlFEwQSUsVV1CiR+Vk0HDJejJAOBMQKABAAAAiEIKKtRNLB7pxQCALCMZJAAAAAAA8AyBBgAAAAAA4BkCDQAAAAAAwDMEGgAAAAAAgGcINAAAAAAAAM8QaAAAAAAAAJ4h0AAAAAAAADxDoAEAAAAAAHiGQAMAAAAAAPAMgQYAAAAAAOAZAg0AAAAAAMAzBBoAAAAAAIBnCDQAAAAAAADPEGgAAAAAAACeIdAAAAAAAAA8Q6ABAAAAAAB4hkADAAAAAADwDIEGAAAAAADgGQINAAAAAADAM3E+n8/n3dsh0ooWLWqSk5NN9erVI70oAJBr7d6925QpUybSiwEAABC2devWmYSEBHPo0CHjNXo05DKFCxe2OwvcDyQ9gPSwnyAz+8jBgwdZUeBcgtPG3xywnyCS5xO1G9V+zA70aEDMqFOnjv25YsWKSC8Kohj7CdhHwLkE/M1BNOHaBGfifkKPBgAAAAAA4BkCDQAAAAAAwDMEGgAAAAAAgGcINAAAAAAAAM8QaAAAAAAAAJ6h6gQAAAAAAPAMPRoAAAAAAIBnCDQAAAAAAADPEGgAAAAAAACeIdAAAAAAAAA8Q6ABAAAAAAB4hkADAAAAAADwDIEGAAAAAADgGQINiEmrVq0yL774omnbtq0pXbq0SUhIMGeffbbp0aOH+emnnyK9eIgSR44cMZ988om56667TLNmzUz+/PlNXFyceeqppyK9aIiAY8eOmSFDhpiaNWuaAgUKmAoVKpiBAweabdu2sT1gLVy40AwfPtz+LalYsaI9X+gBOI4ePWqmTJlibrzxRlOrVi17LilcuLCpX7++eeaZZ8zhw4dZWbBGjhxpzyU1atQwxYsXt9cgVapUMf369TO///47awlp7N2715QtW9b+3Tn33HNNpMX5fD5fpBcCyGm6AFTjoEiRIqZ58+bmrLPOMn/88YdZvny5PTh1ch88eDAbJsYtWbLENGzYMM30oUOHEmyIMcePH7eByXnz5pny5cub1q1bm40bN5pff/3VlClTxk4/55xzIr2YiLDu3bubL774Is10LrXgePfdd82gQYPs77Vr1zZ169Y1Bw8eNL/88os5dOiQOe+888zs2bNtYwGxTTfCdMPjggsuMImJiXbaihUrzJo1a+wNskmTJpnOnTtHejERRfr3728+/vhj+zenevXqZu3atRFdHno0ICbpD7kOxN27d5sZM2aY8ePH2+jwm2++aQ/OBx54wAYeENuKFi1q7zppv9CdSt1tQmx69tlnbTChRYsW9iJP54z58+ebV155xZ5H1LMB0P7x5JNPmqlTp5odO3bYO5BAIDUQb775ZnuNoceECRPMtGnTzOrVq21gWz0uudEBUdBy//799m+Nggp6aD8ZM2aMSU5ONjfddJNJSUlhZcH64YcfzEcffeQPZEYDejQAQTp06GC+++47e8dad64Bh7pEP/roo/RoiDFJSUn27uLff/9tFi1alKaXi7o8L1u2zPz222+mcePGEVtORB91iz9x4gQ9GpApc+fONS1btrQBKvVyyJcvH2sOrtQtft26dWbp0qW2xwNi27Fjx0y9evXsuUNDszTEkx4NQBRSo0G2b98e6UUBEAXmzJljgwz6o+02lKZnz57255dffhmBpQOQ264/FJzSWGsgvZ4xQjAK8vTTT5v169fbHrjOvhENGDoBBNGBKkoOCQC6YySNGjVyXRnOdPVqAIDTvf5QQ0G5owA3SlKtIRRKEqkHYtuyZcvsMM4BAwbY/FHRJD7SCwBEE3VD++qrr+zvXbt2jfTiAIgCmzdv9ieRdeNM37RpU44uF4DcZfTo0fZnx44dye8Bv5deeskmgVRiyJUrV9rfVfXos88+M3nz5mVNxbBTp07ZXB0lSpQwI0aMMNGGQAPwP0qoo2yt6rLYu3dvxloDsJxyc4UKFXJdIypNJ8oYDwDh+Oabb8x7771nezMMGzaMlQi/6dOn20R/DpW4VEJzcgLhtddeMwsWLDAffPCBKVWqVNStEAINOCNdeeWVNqqbFTopN23aNOT8u+++2/z888+2RN2//vUvD5YSuXE/AQDAS6o00bdvX5s0VHevnVwNgHz//ff254EDB2yFNFXAuuSSS2w1pMcff5yVFMO9LZ944gm7L+hGaTQi0IAz0oYNG+z4tKw4evRoyHnPPfeceeONN0y5cuVs5JixkbmD1/sJYlORIkXS3TfUndUphwoAWbFt2zY7VEJlDO+77z5zzz33sALhSt3jNQZfvV+cUrqXX365adKkCWssBt1xxx22KpYSQEYrAg04Iy1ZssSz99IBqohg8eLFbS1rlQxC7uDlfoLYVblyZftz69atrvOd6erOCgCZtW/fPttQVH4XJXJ7+eWXWXnIkIbXaIjvwoULbbUjAg2x6auvvrLBp1tvvTXV9OPHj/uDmG3atLG/jxs3LiJJ7gk0IKbpwFNEUGOvv/76a9OgQYNILxKAKON0Y160aJHrfGc6tcwBZCX3S6dOncwff/xhevToYd555x0TFxfHCkSmlC5d2v7cvXs3ayyGHThwwMyePdt1ngIOzjwn+JDTKG+JmKWuZ/369TPx8fFm8uTJplWrVpFeJABRSOcG9XhSVRq3XjITJ060P7t06RKBpQNwplHS6W7duplff/3VdOjQgeoByDKnAVm9enXWXozy+XyuDw0bdvYNZ1rVqlUjsowEGhCT5syZY3r27GkPvvHjx9uuiwDgJl++fObOO++0v6sHlJOTQUaOHGlrWCsZExnAAWTk5MmTpk+fPmbmzJl2vP2kSZPsOQYIvk7VcF6VLwyUnJxsKw188sknpmDBgnYIBRCt4nxqaQExpmTJkra7UbVq1czFF1/s+pyLLrrI1qZFbFPlih07dtjft2/fbrZs2WISExNNxYoV7bTy5cvbHjHI3dTtUGMd58+fb7e5GggaV63/lylTxsybN89WrEFs0xC8wNKEumOty6xmzZr5pymB2xVXXBGhJUSkjR492gwePNj/96VYsWKuz1O+Bqd7PGLPhx9+aPN2aB9QEFulC/fs2WOrTuiapECBAuajjz4yvXr1ivSiIsps3LjRtm/Uo2Ht2rURXRZyNCAmKcgg6l7kdDFyQ6ABixcvtg3KQEqwo4eQADA26KJu1qxZ5oUXXjD//ve/zZQpU2x1GpWUUsPSCTwhtmm8tIJPwQKnMaY6tqm6hCO9IPVTTz1FoCGGqZfcY489ZodIqNecggzq+aIu8OqRq5LsJC9HtKNHAwAAAAAA8Aw5GgAAAAAAgGcINAAAAAAAAM8QaAAAAAAAAJ4h0AAAAAAAADxDoAEAAAAAAHiGQAMAAAAAAPAMgQYAAAAAAOAZAg0AAAAAAIBAAwAAAAAAiD70aAAAAAAAAJ4h0AAAAAAAADxDoAEAPBYXF5fqkSdPHlO8eHHTvHlzM2rUKJOcnByxdV61alW7TOFYvXq1uffee039+vVNyZIlTUJCgildurS56KKLzBNPPGH++OOPNK/573//m2Z9FCxY0Jx99tmmRYsW5p577jHz5s0L+Zlur4+Pj7ev79atm5k1a1ZY3yUWnM62PhMdOHDAlCpVylx99dWppp86dcoMGTLEVKhQwe57bdq0McuWLXN9j5SUFFOvXj3TsmVL4/P5TE4bNGiQ3WYbNmzI8c9G9NO+q/1j48aNUX+suy3rjh077DF4++23R3TZAOQMAg0AkE1uuOEG+7juuuvMBRdcYBYsWGAb6p06dbINmjOFGlxPPvmkqVOnjg2U7N6927Rq1cr06tXLNGnSxKxZs8Y899xzpm7duubFF190fY9y5cr518dVV11lGjVqZDZv3mz++c9/2oBDhw4dzM6dO0MuQ+Dre/bsaUqUKGGmTp1q2rVrZ9544w0Ti3QRrwZGbvDhhx/a7/PUU0+F/R7aB/fv32+GDh2aarr2yWHDhtlg32WXXWbmzp1r2rdvbw4dOpTmPV577TUbMBszZkyON9x0nH399df2OKpWrZrJjbR9tV61vRF7ypcvb26++Wbzzjvv2L8bAHK3+EgvAADkVsEX0/Pnz7d3eX744Qczbtw407dvX3MmePjhh81LL71kG/tvv/226dq1a5oG0syZM20j4s8//3R9j/POO8+1cfHTTz+Zu+++23z33Xembdu2dh0VK1Ysw9frM5955hn7mffff78NXpQtW9aT74szj+6UKkjQpUsX21B3qPfQiBEjbC8c7Vv58+c3Y8eOtcfeW2+9ZR544AH/c3ft2mX3p1tuucU0bNgwx7+DApH6Hv3798/xz8aZTX9TItlTLiseeugh8/rrr9vg9fjx4yO9OACyET0aACCHNGvWzN+ImD59+hmx3nX39+WXXzaFCxc2s2fPThNkEN2hVM+CH3/80dxxxx1Zev/WrVubOXPm2O7qq1atyvQdbX2mLlSrV69ujh07ZgMViF3vv/++OXHihOnXr1+q6eq2rSEV11xzjQ0ySJ8+fUyBAgXMkiVL0jSANBzo2WefNZHw5Zdf2p9uxxiQHp0HFYw9EyQmJtqg8uTJk21wD0DuRaABAHKQhh/IX3/9lWae7tJ/9tln5tJLL7U5ENQYql27tm18Hz16NM3z165da+dp6IFyFuTLl89UrFjRNra86pb6yiuv2OVSLoVatWpl2PgP505woUKFzKuvvmp/V4+J48ePZ+p1yn2hO9WyZcuWTL1G30Wfodc5uSJuvPFGuz0UBNJ3UF4ItyEKSUlJtheFLujVaO3evbv/Ofp83QmvUqWKnafeFT169LB3qQPpu2m7ug150Pvps5TzItiFF15ov6+GrTjDDGTTpk2p8leox4ybd9991w7fcb6zllUN8KyaNGmSzTWibab8HMqH4OyH4XaJ1zIPGDDA/v7000+n+j6ZeT9t0/fee88ULVrUXHHFFanmaSiF6HhyODlTnHnyyy+/mE8++cS88MIL5qyzzjKnQ0N6dExqHSlnhHrb6HjMaB3pddpvmjZtmmr6ihUr7L6h76DvqODctGnT/PlLvOgBETh0RUOarr32WlOmTBm7v2jfc4Igbr755hs7JMU5Z+k88cgjj6TZv7TPa/uKtnfgdg4+5tyEc75zjt2TJ0/aITQ1a9a0x2elSpVsTy0Fp4IF5jvI7HGTXo6EUNtJvVfU2+aSSy6xjW99H32G23kjI6E+f/ny5bb3zjnnnGO3jbZpgwYNzODBg+3nB1u5cqVdTq0frSf1YlOQTvugG61XBaJ1TtT763X6W3Hw4MF0l1f7l3pgMIQGyOV8AABP6dQa6vT6/PPP23l9+/ZNNf3kyZO+Pn362HlFihTxtWnTxnfllVf6KlWqZKc1bdrUd/To0VSvefjhh31xcXG+evXq+Tp37uy76qqrfLVr17bPL1asmG/p0qVpPr9KlSohly1YSkqKfR89//fff/eFY9asWfb1l1xySYbPLVOmjH3ujz/+mOnXX3bZZXb+K6+8kqnlGTx4sH1+vnz5fB06dPD16tXLd/bZZ/uqVq3q69q1q52nzwykadoOnTp18hUuXNj3j3/8w3f11Vf7br31Vjt/2bJlvtKlS9vn1apVy3fNNdf4WrZsaf8fHx/vmzBhQqr3u/jii+28DRs2pNr+JUuW9C/bkSNH/PMOHDjgy5Mnj69OnTr2/z/99JPvhhtusM/V8uh35/HCCy+k2dYPPvigfc/LL7/c7lNly5a101u3bu07deqUL7NGjRplX6dl0f6p71mtWjW73P369bPzPvjgA19WaZlbtWplX1+/fv1U30ffNSPLly+3r9W+EGzHjh123n333eeftm/fPvsdnO2ndd+wYUPfhRdeaH8/HW+88Yb9PB2X2s69e/e226F48eL2mA+1jjZt2mTnDRw4MNX0BQsW2POB5tWtW9eu88aNG9v3v/322+10rafTpWVy3kv7R/Xq1e2yt2jRwr/Np0+fHvJ8pv28Xbt29jUVK1a002rWrOnbuXOn/7n333+/3b6ap+0duJ1XrlyZ4TKGc77TPK1/Hedaj3qdHtoemnfdddeleU04x01651XnHBa8nZx9ReeMjh072mXUfqhpCQkJrutb58Hgc0eoz//tt998BQoUsNMvuOAC+/767ueff77reW7y5Mm+/Pnz23kNGjTw9ezZ09esWTO7zgsVKuSbPXt2muXR/qjna36XLl3setK61T7avHlz12WVdevW+dclgNyLQAMA5GCgwWlkfvrpp6mmjxgxwk5XA06NI8eJEyd8N954o52nC+1Ac+fO9a1fvz7NZ7z//vv2+W3btj2tQMOff/5pn6uLz3AbYFkJNLRv394+96233srU63ft2uUPhMyYMSPD91ejVc8966yzUgVO1KhX0MHZbm6BBj3OPfdc39atW1PNU4NDDR/Nf+ihh1I1QCZOnGgbaGrgbN++3T99yJAhaRqcixYtstMUTAj+PlOnTrXT7rjjjjTLpe0ZirOtFUhZtWqVf/ru3bvtd9G8H374wZcZahio0aXHzJkz/dOTk5N9AwYM8K+jcAINgQ3doUOHZvm1ToPtsccec53fqFEjGwzR9leQoX///vb5X375pZ0/ZswY25iaP3++73Rs3LjRNuzUSJw2bZp/elJSkm3QpreOXnvtNTtPjT2H9iWnUah9JpCW2Xk/LwMNeiggEHi8v/rqq66Nwl9//dW/f8+bN88//fjx4zYQp9coGBBI2zfc/SSc853znRSQCDyv6n1KlChh561du/a0j5twAg0KUCpIFkz7jo4zBXuCAxpZCTQ4wb+XX345zWcosBN4TtL7KWipbRl8Lv3222/tPq1gq/4eOcaNG2ffv3LlyqmWR+dlBcWcde8WaBAFZ/W35dixY67zAZz5CDQAQDYHGnTRrotZ3UHV9G7dutkGmkO/66JLF3qBdwAd6smgi141ljLb4NcdQzWedDc83ECDGg/OBbebX375JdVdSecRbqDBuTs2fPjwdF+vC1Mtm+62OXcE1fsiI05jb9iwYWnmrV692jaa0gs0fP7552lep0a3c7GtBmWwHj162PnPPvtsmtcErquRI0faaePHj7c/H3/8cf883Y3XtOCeEZkNNLzzzjtp5qnxkZWGvZZHz1fQK9j+/fv9d90jEWi47bbb7Gs/+ugj1/nanmq4OdtRD/VKkT179tjAU/D30j6W1eCaE0BSAy+YPkd3fUOtI901V5AisCeLs5+cc845rvu3s/97GWhQD5XAxqRzftK5R43NwHlOQ/bRRx9N835qbBYsWNAeU5s3b/Yk0BDO+c7Z3m6ByDvvvNN1WcI5bsIJNGTmXKVgRLiBBvXA0rQlS5Zk+Hn33HOPfa4CXm7uvvtuO3/SpElpguYK9ARTcCKjQIPTi0lBVgC5E1UnACCbuI2ZHTRokM12Hzhv0aJFZs+ePXacs8bEBtP44MaNG9vSd6rqEJgr4fDhw3b8tBLb7du3z595XONvdZ29bt06W0oyO+i9P/roozTTwx13+3/tAvf1pkSUbtPPPfdcM2XKFJM3b94M319JJ0V5BYJp7LbGLmtbuNFnq6KBW9UMUalPJRIMdv3119u8Bs7zRDkONP45cFy6ftf4e43nV56H4HkSKv9CRi6//HLX7ytu47Szuu5UalSfoe8ZCU6+k8A8DIG03rRdlYNB4+uVlFXbRR599FG73w0fPtyfvV9VUFTiUsednjd69Gg7/jwjzjbWmPZgytWgdaR9NZjKbGobq+Sm8joEv5/Kubrt30pqqUoaXtK6Uq6AQPHx8bbcptbh3r17bYnCwOVT+d5gyjWh7/vFF1/YfcdtnYQjnPOdjkslH8zqMeDFcZMR5YhQvo1ff/3V5l9RHhj5/fff7U+d75UoNxz6m/Htt9/aBL1KcKrcL9qWbpxkusoP4UZ5QVSKWMt55ZVX2vU+b948O693795pnt+xY0d7PAbmQQnm5ELR9waQOxFoAIBscsMNN/gTAC5dutRWVVD98JYtW6ZKDKbM+DJjxoyQCcUcCkg4gQaVlNQFfHoXamrEhEuNI9HF4qlTp2wSvUBKMhZYolONMbfkapml7yZuyfgUgNHFq+hiWcumBnvnzp1dG/hunMaBEpa5qVy5cshAgxpOTtWCQNu3b7c/3ZI7Bk7ftm2bf5oasEr4p4aatr0+V7/rYl4NSjX2lBRUCUB1Qa9G1fnnn28TuYVDCfOCKaghmd1emVl3kfL333+n+k6hkrA6wQTHb7/9ZpNIqgGlxJbaRk55zP/85z822KDkg6q4MnLkyAyXw9kXFChyE2ofUQUaNTCDq02E+36nw21fCbW/hLPvn45wz3dKsOgWqMnoGPDiuEmPggna5s753+vz94MPPmh+/vlnG8RSoKVIkSI2kaYSpurvjxKiOpxlUFLKzJyjFXDSPqtzUmBwLJD22/QCDU4Z43CS0gI4MxBoAIBsEnxn/6WXXrIl9HSHSRd+TgNCjXjn7nyrVq0y1fjXnT3dRdddvSFDhtgLcL2fGrEKViirtxqrTi+BcOgupi6sdbGrRpcaYNlFy6lgjKhRHUxZzSOZoTwzd7TdhAocKZig4IIaAaqAoQtyp8eCfqqniCohqHSn9g9lpg9XcIAot3EaTFlplGl/03GoigK33nqrnTZmzBgbFJwwYYJtJOvuriodaLruCIdqUJ0uVZvQfqKgWaR5ua9kFDTNitM534X7nbxaF875PZCWU99HDXztf3qoMoSCAfo+jz32mK2AcjrnbzXkFZxRjxL1AtG5Rv9XQFvvrfNPjRo1Ui2jExwPRb2BvA4QqkcUgNyJQAMA5BDdYfr+++9tN1WVeXv//fdT3TnLSmNaF4m6q6Ru1U7JuEDr168/7eXVXUB1H9bd3XHjxtnGVnZRl3XdLVNgQ11+s4O6fOvCXqUo3Up1ZrZEZqAKFSr4y0y6CXWnUIGDYcOG2Yt/565fYKBBNE+BhsBpkaJ1t3r1aruO3AJB4aw7r6i3iagRmlk69lRCUMeRc7dbPY7UsyHwDr16nijoo4CDghKZWUfaF9zWkds+ovKAKg+p7v7B+4gzRCHUvhVqek7Rvr9hw4aQ3zezd8mj5Xx3OpzhJgqIKFiQ0bGhfU0PlQ594403su37OOVynZK5Gmak0pYKyjz++OM2qOb8DdKwE5UzdoLZ6dFz9J3Vu0TnKAV8gqlManqc8164PbUARL/cfZsDAKKM031b48WdhkKTJk3sXVnlIchsY8m5SHPr3qtGUaghAFl1//3325+jRo2yjajsoCEC9913n/1dd/bchih4wektosCJ2zpbvHhxlt9Twx3k888/t43GYJ9++mmq5zk0fEYX6gom6KG7j87YcjV0nTwNTn4Gtx4NGjKSkpJickJ66053Jp0x3qfbUAvn+6hHiGR2/1RXbeVmUP6F4B5ETmDHceTIkUzf3Xa2sdN4C6Tj2m0dqdeKGtBu+T+c99M6d7srruBfJDnLp0ZrMDVANSREDd3AdRzuds6p8124nKDQmjVr0sxTD4KsfB/Nc3uNV0E5DQeS5cuX+6crP5BMnjw5U++jc4/Tu8Ftf9e+ntHfMgVadK6vXbt2lr4DgDMHgQYAyEENGzY03bt3txfaI0aMsNN0saUhFer6re7abnezNM5ZwYngpGRKwBc4ZlmNqBtvvNGfJO10aUzvAw88YBtcauwquZsbJQlza2hnRGOI1RDReGWNo3/yySdNdrnlllvsT42311CQwMalEgC6NeYyop4GStamu7fq0h3Y1VkX7do+usM5cODAVK9z8jQo2KSLcic/Q+D7ap0qP4N6urglCdUd5V27duXIGOcBAwbYRuLHH39sfvzxR/90bXMFo05nLHlgz5BwgllOg1c9FDLjiSeesGPsnePPof1Pd6SdfVzHkAJIOj6rV6+eqXWk544dO9b2XHLofe69915/0CKQurRLcH4GZx/Qtted5uDeREooO3fu3JDLoga+HumN/z9dGnqiAIxyXCjfhUNj9++66y57XOl8FpjXI9ztnFPnu3A5gUANSQg8DyoI4xaI0TA5rTsNZVDCR4eG7ijYmpXeOaG8+eabtsdJMPWgkcDtomNY5ySd692Suup4mThxotm6dat/2m233WZ/Dh06NFXvBfVMU++99GifVoBN58Bwh6UBOANEuuwFAOT28pbBVG5MpdhUzs6p7a5Setdff719nUrxqXSdyj2qPGKdOnXs8+vXr5/qfS677DL7fNWD7969u33od9V6VwlNt1KNWSlv6VAtd5U3dMo/qtxl586dfddee60ty6d675quZdQ0t9Ju5cqV85e/VOk2lRdMTEz0r6uOHTu6lvbMSnnMzBg8eLB9P9Vv12f26tXLV758ebteunTpYufNmTMnS2UkVYKuVKlS9nm1a9f29enTx1+6LT4+3pasTK9kpB4vvfSSa7lBPVQW1c1dd93lL0modaoSjSNGjMi2knujRo2yr9F+0LZtW7t/qvSi9rm+ffvaeWPHjvWFQ+Uky5Yt69/WAwYMsN8neFuE2j+1DooWLWrfJz069vLmzet79dVX08zTsagyndo3unbt6jv//PPt8jzyyCOZ/h6vv/66fx21adPGrqOqVav6ihcv7i9ZGFhOUaVZK1asGPL9VMZVZW/1unr16tl9q0mTJvZYu/322123oc4lzr6zdetWT8qLhiqr+Nxzz/n38/bt29vvW6lSJTutRo0aaY7pbdu22fOetoGOv4EDB9rtvGrVqgyXMZzzXXrHbqjvHM5xo+9ZpkwZO69mzZq+nj172vO1vue9997r+ppBgwbZ6SoDesUVV9jX6DypUsf9+/d3Lb2ZlfKW+nxN03581VVX+Xr37u2fpm3w888/p3r+lClT/CVYtU51PtT2bN26tX8fXLx4carXXH311Xa65uuY0d8rbZNGjRr5mjdvHrK85bvvvpumlDGA3IdAAwDkcKBBdEGm5zz44IOppn/xxRf2olONLtWt18/GjRv7HnroId/ChQtTPffo0aO2saoLejWOdIGvRumePXvsRa1XgQbHypUrbb11NXjUcFLjQg3sFi1a2OVbsWJFyAvzwIeWVd9LF6Kqzz537tyQn+l1oEGN0jfffNN+B2c5tK7UyFRDSZ8V3OjJKNAgmzZtsg0HbQNtNzUW1BCaP39+yNfMmDHDv04WLFiQap4uzp1548aNc3394cOHfXfeeaf9TG2L4PXkdaBBJk6c6GvatKltHJUsWdLux6tXr/bddNNN9v2mTZvmC5fWgRqT2rfUkHZraIXiNHgnTJiQ7vPUaKpbt64vOTnZdb4CG9qfFezTvvHAAw/4kpKSsvQ9Jk+ebAOFzjpSI1jHjhq0gd9pzZo19v+33XZbuu+nQJYafVovatBp+b766quQ23DRokV2+qWXXprpZQ430CBalnbt2tnl03pTI1Xng3379rm+1/Tp020gTkEdZx8PPk+5Ced8l1OBBtE2VgBWAS9tp4svvtg3c+bMkK9JSUnxvfLKKzYQoIa/ggwKRm3cuDHNvhJOoGHq1Kk2kKNAtRr/CiIoCKJjNVRgZ+3atTaApXWsZdJ3UTBMAQcdWydOnEj1fB1HL774on1fbfsKFSrY1x84cCDdfUb7ps6TbsFlALlHnP6JdK8KAAAiSV3mVWVDXZfVHdutHB7cqau4EiWuXLnSljxUOcGctnPnTrv92rdv7x+OEG00Nl6JDD/44ANbXlCJ99RVXV3ZO3XqlOX3c8oWqlJAYBJZDQ1SV3hnWBIQTTT8QjlolNhz/PjxkV4cANmIHA0AgJihxrCSTwY6ePCgufnmm+3YYpXNI8gQelx1cD4Ijd1WfhHlvGjXrl1Eggyiz1VegK+//trm+zgTaIy8gg+XXnqpp+87a9YsWy2GIAOikco8Kz/FM888E+lFAZDNKG8JAIgZo0ePtpUgVEJTmeIVXFC1CSVfUx37559/PtKLGLWUGFGJ37Tu1EhWgGbp0qVmx44dtizk66+/HtHle+yxx8x7771new0ocV2069WrV7a8b7T26AB0rnj77bfNoEGDXEsMA8hdCDQAAGKGsuCrm/3ChQttVQdRl/ubbrrJ3pnPTA35WKUeCwoszJs3zyxbtsxWTklMTLTZ51UuMjCLvYYGZIYCFC+//LIny1eiRAmbyR5AdFJwN7iELIDcixwNAADA24uLuLhMPU9jtbOzBCMAAIgMejQAAABPkWcaAIDYRjJIAAAAAADgGQINAAAAAADAMwQaAAAAAACAZwg0AAAAAAAAzxBoAAAAAAAAniHQAAAAAAAAPEOgAQAAAAAAeIZAAwAAAAAA8AyBBgAAAAAA4BkCDQAAAAAAwDMEGgAAAAAAgGcINAAAAAAAAM8QaAAAAAAAAJ4h0AAAAAAAAAg0AAAAAACA6EOPBgAAAAAA4BkCDQAAAAAAwDMEGgAAAAAAgGcINAAAAAAAAM8QaAAAAAAAAJ4h0AAAAAAAADxDoAEAAAAAAHiGQAMAAAAAADBe+X/qNUzU8j264QAAAABJRU5ErkJggg==","type":"image/png","originalSize":98587,"dimensions":{"originalWidth":1050,"originalHeight":750,"displayWidth":1050,"displayHeight":750}}},"sourceToolAssistantUUID":"f239d990-c9f4-40ca-80a6-8f307f0b9c73","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"9dcf305b51a9c74be3b0ac2eb70fe8111902dec2632c56931a2fbeb9dcf7c0d5","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01UbqLPmUk8ugwAtAYPr6Z8x","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0172/out/figure1.png"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"0cd601d6-76cf-4e1d-8b7d-3ffc116b019a","timestamp":"2026-10-30T04:51:15.330Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"8ab1cd05-aab3-44ae-925f-19af813e691a","keep":22,"tail":["9dcf305b51a9c74be3b0ac2eb70fe8111902dec2632c56931a2fbeb9dcf7c0d5","b74097e2784950e76af6c4cdf3c2ad866138b0d481df54b02fcc83ce11d9a612"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"9b3dea8d8a3c41263bcf7988baa4c2f52eb870ff0fa8c7a1745aaf4c07d73a14"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f675de9c-b17c-4bbc-85a1-83b8f6c7e7bc","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"f675de9c-b17c-4bbc-85a1-83b8f6c7e7bc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYsSQ7NENhxYk1VpA1","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":1125,"cache_read_input_tokens":22526,"output_tokens":1893,"output_tokens_details":{"thinking_tokens":164},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1868,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpYsAmzXfvVW9hdhEwR","requestRef":"0cd601d6-76cf-4e1d-8b7d-3ffc116b019a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"de4d639d-2c3f-4f47-a40c-fc3b0967a526","timestamp":"2026-10-30T04:51:19.179Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"de4d639d-2c3f-4f47-a40c-fc3b0967a526","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYsSQ7NENhxYk1VpA1","type":"message","role":"assistant","content":[{"type":"text","text":"Figure looks right. Now the checks file, report, claims and final ledger."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1125,"cache_read_input_tokens":22526,"output_tokens":1893,"output_tokens_details":{"thinking_tokens":164},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpYsAmzXfvVW9hdhEwR","requestRef":"0cd601d6-76cf-4e1d-8b7d-3ffc116b019a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"327da642-8c11-451f-8977-0883d50e0abb","timestamp":"2026-10-30T04:51:19.180Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"327da642-8c11-451f-8977-0883d50e0abb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpYsSQ7NENhxYk1VpA1","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Y6KbHZtGLhv8CJEcXWkPRq","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# P4 verification checks (2026-10-30)\nDeterminism: deleted results.json/table1.csv/figure1.png/exclusions.csv, re-ran `out/analysis.py`; results.json byte-identical (cmp), table1.csv identical md5. PASS.\nAssertions inside analysis.py (all passed at runtime): every quarter 1959Q4–2019Q4 has exactly 3 monthly UNRATE values; 241 merged quarters with regular spacing; 240 regression quarters from 1960-01-01 to 2019-10-01; n_sub1+n_sub2=n.\nPost-hoc checks (all PASS):\n- all required results.json keys present\n- n_sub1+n_sub2 = n_analysed = 240; n_sub1=96, n_sub2=144; sample dates 1960-01-01/2019-10-01\n- effect_se > 0; CI contains estimate; CI half-width = 1.96·SE\n- model_metric < baseline_metric; 1−(model/baseline)² equals R² (identity)\n- conclusion code consistent with CI (upper bound < 0 → negative_effect)\n- stability_conclusion consistent with chow_p_value < 0.05\n- Chow df = (2, 236); F ≥ 0, p in [0,1]\n- exclusion ledger: n_before − n_removed = n_after for every step; final n = 240\n- n_input_rows = 319 / 945 match `wc -l` minus header\n- table1 has header + 3 rows with required columns; full-sample slope = effect_estimate\n- magnitude: β ≈ −0.26 is in the conventional range for q/q (non-annualised) growth\n- HAC SE (0.036) > classical SE (0.020), consistent with positive residual autocorrelation\n- No date after 2019-10-01 enters any estimate (window filter + assertion on max date)\nFigure inspected visually: two subperiod clouds, two fitted lines, labels correct.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4, a 1 percentage point higher quarterly real GDP growth rate is associated with a 0.26 pp lower change in the unemployment rate (OLS Okun coefficient about -0.256).\",\"results_keys\":[\"effect_estimate\",\"n_analysed\",\"sample_start\",\"sample_end\"],\"status\":\"supported\",\"caveat\":\"Descriptive linear association, not a causal effect; current-vintage revised data.\"},\n {\"id\":\"C2\",\"text\":\"The Okun coefficient is significantly negative: the Newey-West (Bartlett, 4 lags) 95% CI is about [-0.326, -0.185].\",\"results_keys\":[\"effect_se\",\"hac_lags\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Normal-approximation CI; SE barely changes with 8 lags (effect_se_hac_lags8).\"},\n {\"id\":\"C3\",\"text\":\"Real GDP growth explains a substantial part of quarterly unemployment changes: residual RMSE 0.250 pp vs 0.325 pp for the mean-only baseline (R^2 about 0.41).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"r_squared_full\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C4\",\"text\":\"The classical Chow test rejects joint equality of (alpha, beta) across 1960Q1-1983Q4 and 1984Q1-2019Q4 at 5% (F about 6.09, p about 0.003), so the relationship is classified as unstable.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\"],\"status\":\"supported\",\"caveat\":\"Classical Chow assumes homoskedastic, serially uncorrelated errors with equal variance across regimes; residual variance falls from 0.079 to 0.048. A HAC-robust joint Wald test also rejects (p about 0.005).\"},\n {\"id\":\"C5\",\"text\":\"The instability is not a change in the slope: subperiod slopes are nearly identical (-0.259 vs -0.273; HAC test of slope difference p about 0.85). The point estimates instead show a lower intercept after 1984 (0.254 vs 0.152).\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"hac_wald_slope_diff_p\",\"intercept_sub1\",\"intercept_sub2\",\"hac_wald_intercept_diff_p\"],\"status\":\"supported\",\"caveat\":\"The intercept difference alone is not significant under HAC (p about 0.26); only the joint test rejects, because intercept and slope estimates are correlated. Attributing the break to the intercept is an interpretation of point estimates.\"}\n]\nEOF\necho ok","description":"Write checks.md and claims.json"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1125,"cache_read_input_tokens":22526,"output_tokens":1893,"output_tokens_details":{"thinking_tokens":164},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":1125},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpYsAmzXfvVW9hdhEwR","requestRef":"0cd601d6-76cf-4e1d-8b7d-3ffc116b019a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"cd135b2b-bd76-45b6-a4ad-7cb91a6f4efe","timestamp":"2026-10-30T04:51:32.822Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"cd135b2b-bd76-45b6-a4ad-7cb91a6f4efe","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Y6KbHZtGLhv8CJEcXWkPRq","type":"tool_result","content":"ok","is_error":false}]},"uuid":"2ddef376-bcc6-49d7-a581-b8e0731fead1","timestamp":"2026-10-30T04:51:32.867Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"cd135b2b-bd76-45b6-a4ad-7cb91a6f4efe","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"c8240eeb6fada0b60ee8c1152f09cebcb5529efa6a50d83355e9f3ffd33f9cdd","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"text","text":"Figure looks right. Now the checks file, report, claims and final ledger."},{"type":"tool_use","id":"toolu_01Y6KbHZtGLhv8CJEcXWkPRq","name":"Bash","input":{"command":"cat > out/state/checks.md <<'EOF'\n# P4 verification checks (2026-10-30)\nDeterminism: deleted results.json/table1.csv/figure1.png/exclusions.csv, re-ran `out/analysis.py`; results.json byte-identical (cmp), table1.csv identical md5. PASS.\nAssertions inside analysis.py (all passed at runtime): every quarter 1959Q4–2019Q4 has exactly 3 monthly UNRATE values; 241 merged quarters with regular spacing; 240 regression quarters from 1960-01-01 to 2019-10-01; n_sub1+n_sub2=n.\nPost-hoc checks (all PASS):\n- all required results.json keys present\n- n_sub1+n_sub2 = n_analysed = 240; n_sub1=96, n_sub2=144; sample dates 1960-01-01/2019-10-01\n- effect_se > 0; CI contains estimate; CI half-width = 1.96·SE\n- model_metric < baseline_metric; 1−(model/baseline)² equals R² (identity)\n- conclusion code consistent with CI (upper bound < 0 → negative_effect)\n- stability_conclusion consistent with chow_p_value < 0.05\n- Chow df = (2, 236); F ≥ 0, p in [0,1]\n- exclusion ledger: n_before − n_removed = n_after for every step; final n = 240\n- n_input_rows = 319 / 945 match `wc -l` minus header\n- table1 has header + 3 rows with required columns; full-sample slope = effect_estimate\n- magnitude: β ≈ −0.26 is in the conventional range for q/q (non-annualised) growth\n- HAC SE (0.036) > classical SE (0.020), consistent with positive residual autocorrelation\n- No date after 2019-10-01 enters any estimate (window filter + assertion on max date)\nFigure inspected visually: two subperiod clouds, two fitted lines, labels correct.\nEOF\ncat > out/claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"Over 1960Q1-2019Q4, a 1 percentage point higher quarterly real GDP growth rate is associated with a 0.26 pp lower change in the unemployment rate (OLS Okun coefficient about -0.256).\",\"results_keys\":[\"effect_estimate\",\"n_analysed\",\"sample_start\",\"sample_end\"],\"status\":\"supported\",\"caveat\":\"Descriptive linear association, not a causal effect; current-vintage revised data.\"},\n {\"id\":\"C2\",\"text\":\"The Okun coefficient is significantly negative: the Newey-West (Bartlett, 4 lags) 95% CI is about [-0.326, -0.185].\",\"results_keys\":[\"effect_se\",\"hac_lags\",\"effect_ci_low\",\"effect_ci_high\",\"conclusion\"],\"status\":\"supported\",\"caveat\":\"Normal-approximation CI; SE barely changes with 8 lags (effect_se_hac_lags8).\"},\n {\"id\":\"C3\",\"text\":\"Real GDP growth explains a substantial part of quarterly unemployment changes: residual RMSE 0.250 pp vs 0.325 pp for the mean-only baseline (R^2 about 0.41).\",\"results_keys\":[\"model_metric\",\"baseline_metric\",\"r_squared_full\"],\"status\":\"supported\",\"caveat\":\"In-sample fit only; no out-of-sample evaluation.\"},\n {\"id\":\"C4\",\"text\":\"The classical Chow test rejects joint equality of (alpha, beta) across 1960Q1-1983Q4 and 1984Q1-2019Q4 at 5% (F about 6.09, p about 0.003), so the relationship is classified as unstable.\",\"results_keys\":[\"chow_f_stat\",\"chow_p_value\",\"stability_conclusion\"],\"status\":\"supported\",\"caveat\":\"Classical Chow assumes homoskedastic, serially uncorrelated errors with equal variance across regimes; residual variance falls from 0.079 to 0.048. A HAC-robust joint Wald test also rejects (p about 0.005).\"},\n {\"id\":\"C5\",\"text\":\"The instability is not a change in the slope: subperiod slopes are nearly identical (-0.259 vs -0.273; HAC test of slope difference p about 0.85). The point estimates instead show a lower intercept after 1984 (0.254 vs 0.152).\",\"results_keys\":[\"beta_sub1\",\"beta_sub2\",\"hac_wald_slope_diff_p\",\"intercept_sub1\",\"intercept_sub2\",\"hac_wald_intercept_diff_p\"],\"status\":\"supported\",\"caveat\":\"The intercept difference alone is not significant under HAC (p about 0.26); only the joint test rejects, because intercept and slope estimates are correlated. Attributing the break to the intercept is an interpretation of point estimates.\"}\n]\nEOF\necho ok","description":"Write checks.md and claims.json"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"85f7ea46-dbc9-495a-a992-90c80f5ac1b9","timestamp":"2026-10-30T04:51:32.872Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"0cd601d6-76cf-4e1d-8b7d-3ffc116b019a","keep":24,"tail":["c8240eeb6fada0b60ee8c1152f09cebcb5529efa6a50d83355e9f3ffd33f9cdd","8ac1ad964fb785453a3036de2843e4283f85439332bb2b0088e5765d3f45ad38"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"cf349bace12de872cf4c5c5a806d8559100bb2c652a95034eb5579a5f37b1e99"}
{"parentUuid":"2ddef376-bcc6-49d7-a581-b8e0731fead1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpaATsehKbnpWP457x2","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Nnr3MNsQ22By917PZQw3bL","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960–2019 (task F6-conf-03)\n\n## Question\nHow strongly does the quarterly change in the US unemployment rate respond to real GDP growth, and has the response been stable? We estimate β in Δu_t = α + β·g_t + ε_t for 1960Q1–2019Q4. Here u_t is the quarterly average of monthly UNRATE (percent) and g_t = 100·Δln GDPC1 (quarterly percent, not annualised). We check stability with separate fits for 1960Q1–1983Q4 and 1984Q1–2019Q4 and with a classical Chow test.\n\n## Data and exclusions\nInputs are the raw FRED files `data/GDPC1.csv` (319 rows) and `data/UNRATE.csv` (945 rows) (`n_input_rows`). Their SHA-256 hashes match `data/README.md` (details in `out/state/data_audit.md`). Neither file has gaps in its date grid or duplicate dates. The one missing value is UNRATE for 2025-10, which is outside the sample. The full exclusion ledger is in `out/exclusions.csv`:\n- drop 1 blank month;\n- keep months 1959-10 to 2019-12 (723 months), which become 241 complete quarters;\n- keep GDP quarters 1959Q4–2019Q4 (241);\n- take first differences, which drops 1959Q4.\n\nThat leaves 240 regression quarters (`n_analysed`), from `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01. Subperiods have `n_sub1` = 96 and `n_sub2` = 144 quarters. No data after 2019Q4 enter any estimate. Data issues and how each was handled are listed under `data_issues`.\n\n## Method\n- **Baseline:** the mean-only prediction of Δu, scored by RMSE (`baseline_metric`).\n- **Main model:** OLS of Δu_t on a constant and g_t over the full sample.\n- **Inference:** Newey–West HAC standard errors with a Bartlett kernel. The lag length is the Newey–West (1994) rule floor(4·(T/100)^{2/9}), which gives 4 for T = 240 (`hac_lags`). statsmodels' small-sample correction n/(n−k) is applied. The 95% CI is β ± 1.96·SE.\n- **Subperiods:** the same regression is fitted on each subperiod. Table 1 reports HAC standard errors using the same lag rule: 3 lags for subperiod 1 and 4 for subperiod 2 (`hac_lags_sub1`, `hac_lags_sub2`).\n- **Chow test:** F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n−4)], compared with F(2, 236) (`chow_df`).\n- **Supplementary check (not required by the task):** a dummy-interaction regression with HAC errors. It tests the slope difference, the intercept difference, and both jointly without assuming equal error variances.\n\nNo randomness is used (`random_seed` = null). Everything is produced by `out/analysis.py`, including `out/table1.csv` and `out/figure1.png`.\n\n## Results\n- **Okun coefficient (full sample):** β = −0.256 (`effect_estimate`), with intercept α = 0.184 pp (`intercept`). Each extra 1% of quarterly real growth goes with a quarter-on-quarter change in unemployment about 0.26 pp lower. On these point estimates, unemployment is flat at roughly 0.7% quarterly growth (0.184/0.256, computed from `intercept` and `effect_estimate`).\n- **Fit:** the residual RMSE is 0.250 pp (`model_metric`), against 0.325 pp for the mean-only baseline (`baseline_metric`). R² is 0.41 (`r_squared_full`).\n- **Subperiod slopes:** −0.259 for 1960–83 (`beta_sub1`) and −0.273 for 1984–2019 (`beta_sub2`). The intercepts are 0.254 (`intercept_sub1`) and 0.152 (`intercept_sub2`).\n- **Chow test:** F = 6.09 (`chow_f_stat`), p = 0.0026 (`chow_p_value`). Equality of (α, β) is rejected at 5%, so `stability_conclusion` = `unstable`.\n- **What drives the rejection:** it is not a change in the slope. A HAC test of the slope difference gives p = 0.85 (`hac_wald_slope_diff_p`). Figure 1 shows two nearly parallel fitted lines, with the post-1984 line shifted down. The intercept difference alone is not significant under HAC (p = 0.26, `hac_wald_intercept_diff_p`), but the HAC joint test rejects (p = 0.005, `hac_wald_joint_p`). The two coefficients are estimated with correlated errors, so the break appears in (α, β) jointly. Saying it is an intercept shift is our reading of the point estimates, not something we tested.\n- **Conclusion code:** `conclusion` = `negative_effect`.\n\nTable 1 (`out/table1.csv`):\n\n| period | n | intercept | slope | slope_se (HAC) |\n|---|---|---|---|---|\n| full 1960Q1–2019Q4 | 240 | 0.184 | −0.256 | 0.036 |\n| 1960Q1–1983Q4 | 96 | 0.254 | −0.259 | 0.039 |\n| 1984Q1–2019Q4 | 144 | 0.152 | −0.273 | 0.069 |\n\n## Uncertainty\n- **HAC standard error and CI:** the HAC SE of β is 0.036 (`effect_se`), giving a 95% CI of [−0.326, −0.185] (`effect_ci_low`, `effect_ci_high`). The interval is well below zero.\n- **Comparison with classical OLS:** the classical OLS SE is 0.020 (`effect_se_ols_classical`). Correcting for heteroskedasticity and autocorrelation therefore widens the interval by about 80%.\n- **Lag sensitivity:** with 8 lags the SE is 0.037 (`effect_se_hac_lags8`), so the result does not depend much on the lag choice.\n- **Subperiods:** the post-1984 slope is estimated less precisely (Table 1).\n- **Chow p-value:** its validity rests on the classical assumptions discussed below.\n\n## Limitations and open issues\n- **The classical Chow test's assumptions are violated.** It assumes homoskedastic, serially uncorrelated errors with the same variance in both regimes. The residual variance falls from 0.079 to 0.048 between subperiods (`resid_var_sub1`, `resid_var_sub2`; this is the Great Moderation), and the gap between the HAC and classical SEs points to serial correlation. The nominal p-value may therefore be miscalibrated. The HAC joint Wald test reaches the same answer (`hac_wald_joint_p`), which is reassuring. However, it is a single asymptotic test with a rule-of-thumb lag length.\n- **The break date is fixed in advance (1984Q1), not estimated.** We did not run unknown-break tests (Quandt–Andrews/sup-F) or rolling regressions. Rejecting equality at 1984 does not show that the break happened then, or only once.\n- **\"Unstable\" is mostly about the intercept, not Okun's coefficient.** The slope itself looks stable (`hac_wald_slope_diff_p`). A lower intercept is consistent with slower trend growth or labour-force changes after 1984, but we did not test either explanation. Reading `unstable` as \"Okun's coefficient changed\" would be wrong.\n- **Specification and causality.** The static difference form leaves out lagged growth: unemployment responds to output with a lag, and jobless recoveries matter here. It also ignores possible asymmetry between recessions and expansions and simultaneity between output and unemployment. β is a reduced-form association, not a structural effect, and OLS would be biased for any structural parameter. We did not run residual diagnostics beyond the SE comparison: no formal autocorrelation or normality tests, and no check of influential observations. The large 1980 and 2008–09 quarters visible in Figure 1 could be influential.\n- **Data vintage.** The data are the 2026 vintage: revised, in chained 2017 dollars, with seasonal factors as of retrieval. Estimates could differ with real-time data or earlier vintages. Averaging monthly UNRATE into quarters is as the task specifies.\n- **What would invalidate the result.** The result would be wrong if either input file did not match its README description, if quarters had been misaligned, or if growth had been annualised. Code assertions and the checks in `out/state/checks.md` guard against these failures.\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\nr=json.load(open('out/results.json'))\nprint(r['intercept']/-r['effect_estimate']*-1, -r['intercept']/r['effect_estimate'], r['effect_se']/r['effect_se_ols_classical'])\nfor c in json.load(open('out/claims.json')):\n    assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok')\nEOF","description":"Write report and verify derived numbers and claim keys"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1900,"cache_read_input_tokens":23651,"output_tokens":3278,"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":1900},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpaABWCtCaXbUpgi7Hw","requestRef":"85f7ea46-dbc9-495a-a992-90c80f5ac1b9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bd166c1e-7116-4c8c-b0cc-5098fe425e4f","timestamp":"2026-10-30T04:52:02.553Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"bd166c1e-7116-4c8c-b0cc-5098fe425e4f","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Nnr3MNsQ22By917PZQw3bL","type":"tool_result","content":"-0.7209211099660549 0.7209211099660549 1.8028415073097532\nclaims keys ok","is_error":false}]},"uuid":"ad0ccc70-c546-4480-8829-d70bb284e25d","timestamp":"2026-10-30T04:52:02.629Z","toolUseResult":{"stdout":"-0.7209211099660549 0.7209211099660549 1.8028415073097532\nclaims keys ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"bd166c1e-7116-4c8c-b0cc-5098fe425e4f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"022fb2259896193028be832737e7f2fded26b075c749607a1538f2e1cdfc7b60","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01Nnr3MNsQ22By917PZQw3bL","name":"Bash","input":{"command":"cat > out/report.md <<'EOF'\n# Okun's law in the United States, 1960–2019 (task F6-conf-03)\n\n## Question\nHow strongly does the quarterly change in the US unemployment rate respond to real GDP growth, and has the response been stable? We estimate β in Δu_t = α + β·g_t + ε_t for 1960Q1–2019Q4. Here u_t is the quarterly average of monthly UNRATE (percent) and g_t = 100·Δln GDPC1 (quarterly percent, not annualised). We check stability with separate fits for 1960Q1–1983Q4 and 1984Q1–2019Q4 and with a classical Chow test.\n\n## Data and exclusions\nInputs are the raw FRED files `data/GDPC1.csv` (319 rows) and `data/UNRATE.csv` (945 rows) (`n_input_rows`). Their SHA-256 hashes match `data/README.md` (details in `out/state/data_audit.md`). Neither file has gaps in its date grid or duplicate dates. The one missing value is UNRATE for 2025-10, which is outside the sample. The full exclusion ledger is in `out/exclusions.csv`:\n- drop 1 blank month;\n- keep months 1959-10 to 2019-12 (723 months), which become 241 complete quarters;\n- keep GDP quarters 1959Q4–2019Q4 (241);\n- take first differences, which drops 1959Q4.\n\nThat leaves 240 regression quarters (`n_analysed`), from `sample_start` = 1960-01-01 to `sample_end` = 2019-10-01. Subperiods have `n_sub1` = 96 and `n_sub2` = 144 quarters. No data after 2019Q4 enter any estimate. Data issues and how each was handled are listed under `data_issues`.\n\n## Method\n- **Baseline:** the mean-only prediction of Δu, scored by RMSE (`baseline_metric`).\n- **Main model:** OLS of Δu_t on a constant and g_t over the full sample.\n- **Inference:** Newey–West HAC standard errors with a Bartlett kernel. The lag length is the Newey–West (1994) rule floor(4·(T/100)^{2/9}), which gives 4 for T = 240 (`hac_lags`). statsmodels' small-sample correction n/(n−k) is applied. The 95% CI is β ± 1.96·SE.\n- **Subperiods:** the same regression is fitted on each subperiod. Table 1 reports HAC standard errors using the same lag rule: 3 lags for subperiod 1 and 4 for subperiod 2 (`hac_lags_sub1`, `hac_lags_sub2`).\n- **Chow test:** F = [(SSR_pooled − SSR_1 − SSR_2)/2] / [(SSR_1 + SSR_2)/(n−4)], compared with F(2, 236) (`chow_df`).\n- **Supplementary check (not required by the task):** a dummy-interaction regression with HAC errors. It tests the slope difference, the intercept difference, and both jointly without assuming equal error variances.\n\nNo randomness is used (`random_seed` = null). Everything is produced by `out/analysis.py`, including `out/table1.csv` and `out/figure1.png`.\n\n## Results\n- **Okun coefficient (full sample):** β = −0.256 (`effect_estimate`), with intercept α = 0.184 pp (`intercept`). Each extra 1% of quarterly real growth goes with a quarter-on-quarter change in unemployment about 0.26 pp lower. On these point estimates, unemployment is flat at roughly 0.7% quarterly growth (0.184/0.256, computed from `intercept` and `effect_estimate`).\n- **Fit:** the residual RMSE is 0.250 pp (`model_metric`), against 0.325 pp for the mean-only baseline (`baseline_metric`). R² is 0.41 (`r_squared_full`).\n- **Subperiod slopes:** −0.259 for 1960–83 (`beta_sub1`) and −0.273 for 1984–2019 (`beta_sub2`). The intercepts are 0.254 (`intercept_sub1`) and 0.152 (`intercept_sub2`).\n- **Chow test:** F = 6.09 (`chow_f_stat`), p = 0.0026 (`chow_p_value`). Equality of (α, β) is rejected at 5%, so `stability_conclusion` = `unstable`.\n- **What drives the rejection:** it is not a change in the slope. A HAC test of the slope difference gives p = 0.85 (`hac_wald_slope_diff_p`). Figure 1 shows two nearly parallel fitted lines, with the post-1984 line shifted down. The intercept difference alone is not significant under HAC (p = 0.26, `hac_wald_intercept_diff_p`), but the HAC joint test rejects (p = 0.005, `hac_wald_joint_p`). The two coefficients are estimated with correlated errors, so the break appears in (α, β) jointly. Saying it is an intercept shift is our reading of the point estimates, not something we tested.\n- **Conclusion code:** `conclusion` = `negative_effect`.\n\nTable 1 (`out/table1.csv`):\n\n| period | n | intercept | slope | slope_se (HAC) |\n|---|---|---|---|---|\n| full 1960Q1–2019Q4 | 240 | 0.184 | −0.256 | 0.036 |\n| 1960Q1–1983Q4 | 96 | 0.254 | −0.259 | 0.039 |\n| 1984Q1–2019Q4 | 144 | 0.152 | −0.273 | 0.069 |\n\n## Uncertainty\n- **HAC standard error and CI:** the HAC SE of β is 0.036 (`effect_se`), giving a 95% CI of [−0.326, −0.185] (`effect_ci_low`, `effect_ci_high`). The interval is well below zero.\n- **Comparison with classical OLS:** the classical OLS SE is 0.020 (`effect_se_ols_classical`). Correcting for heteroskedasticity and autocorrelation therefore widens the interval by about 80%.\n- **Lag sensitivity:** with 8 lags the SE is 0.037 (`effect_se_hac_lags8`), so the result does not depend much on the lag choice.\n- **Subperiods:** the post-1984 slope is estimated less precisely (Table 1).\n- **Chow p-value:** its validity rests on the classical assumptions discussed below.\n\n## Limitations and open issues\n- **The classical Chow test's assumptions are violated.** It assumes homoskedastic, serially uncorrelated errors with the same variance in both regimes. The residual variance falls from 0.079 to 0.048 between subperiods (`resid_var_sub1`, `resid_var_sub2`; this is the Great Moderation), and the gap between the HAC and classical SEs points to serial correlation. The nominal p-value may therefore be miscalibrated. The HAC joint Wald test reaches the same answer (`hac_wald_joint_p`), which is reassuring. However, it is a single asymptotic test with a rule-of-thumb lag length.\n- **The break date is fixed in advance (1984Q1), not estimated.** We did not run unknown-break tests (Quandt–Andrews/sup-F) or rolling regressions. Rejecting equality at 1984 does not show that the break happened then, or only once.\n- **\"Unstable\" is mostly about the intercept, not Okun's coefficient.** The slope itself looks stable (`hac_wald_slope_diff_p`). A lower intercept is consistent with slower trend growth or labour-force changes after 1984, but we did not test either explanation. Reading `unstable` as \"Okun's coefficient changed\" would be wrong.\n- **Specification and causality.** The static difference form leaves out lagged growth: unemployment responds to output with a lag, and jobless recoveries matter here. It also ignores possible asymmetry between recessions and expansions and simultaneity between output and unemployment. β is a reduced-form association, not a structural effect, and OLS would be biased for any structural parameter. We did not run residual diagnostics beyond the SE comparison: no formal autocorrelation or normality tests, and no check of influential observations. The large 1980 and 2008–09 quarters visible in Figure 1 could be influential.\n- **Data vintage.** The data are the 2026 vintage: revised, in chained 2017 dollars, with seasonal factors as of retrieval. Estimates could differ with real-time data or earlier vintages. Averaging monthly UNRATE into quarters is as the task specifies.\n- **What would invalidate the result.** The result would be wrong if either input file did not match its README description, if quarters had been misaligned, or if growth had been annualised. Code assertions and the checks in `out/state/checks.md` guard against these failures.\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\nr=json.load(open('out/results.json'))\nprint(r['intercept']/-r['effect_estimate']*-1, -r['intercept']/r['effect_estimate'], r['effect_se']/r['effect_se_ols_classical'])\nfor c in json.load(open('out/claims.json')):\n    assert all(k in r for k in c['results_keys']),c['id']\nprint('claims keys ok')\nEOF","description":"Write report and verify derived numbers and claim keys"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"d0b20e79-db5a-4202-8d89-ca0156acf809","timestamp":"2026-10-30T04:52:02.632Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"85f7ea46-dbc9-495a-a992-90c80f5ac1b9","keep":26,"tail":["022fb2259896193028be832737e7f2fded26b075c749607a1538f2e1cdfc7b60","af1f630b4e6f340cd4a0387b9dbf8e7733902da2012001b4b760f2da99fe7367"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"76ffd7e9a7dcbe4adbd2ebb3c5df205d7c34963b6505c476ad4ff0dc4f15a8be"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"ad0ccc70-c546-4480-8829-d70bb284e25d","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"atis-latch","atis":"","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"parentUuid":"ad0ccc70-c546-4480-8829-d70bb284e25d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpcMkKxJ1cB2ofYLC7F","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS4gYKEAgTGAI4AUIIdGhpbmtpbmcSDDVZp0kknYaIC2n8XhoMqPXVMwrHClOEL70lIjBgMt9KPeBORoLnLXUhb+Tc/IOwbjMW78XH3zOD3Y8lwA3kbYkhImLQp7X0Xk/RrlQq/wXh0bJD46YdvJ1fonVXYgTIgRcZYY9+bVJCuLEGSVSNzgI1pq8Jlav93ZoZs6oJV1wAmuddzh5jm2oLZHumDaz/Wcz3jMkkua27w2+AhKXw3HAuSLAQ/dlEFJH7nOSi9flQafELw+gf8BaWPKkLf1F9zg1gF0sI6dWFWnmfnDDj1nW5/t4JcwY7rx/pnjOORhsCiZtm40Uw6jhoL6S0KQrscoLk40NBw6pXTJBFN1TQ7CZCd4S1xjN9Eg3X8F+SGDHPgMm62bX5yVInTXHouEGJC06Y6ljQSzBrY2sLoaIBNG4hMPDIpfMYiZmzFWDWYMAY3C+oluPDfDKylPQ22ytrRF+/LAKQt3gOlTApmCfxKP4EtXntkT928WOUB0L+GzNyfYr5SBJFJTA2WRd5vhG+6ZqjSZtxTBDQhavyhEoh+VaA9AMxHqcbDMMOpHgRULgHeUG2DRVUyQ9MRBZIe9SWVaBkGQHmwCCHP4dRJ2lGvHatQ33OAQzXDBuXMCfglhFKZ9Iav5+h3Wlc8vRW0JZ0ySvyymDqUIz2qsiXe/dwhp05NnpgJS1mVr0gZm1hlLSycBdIEwdTfApqEe5TxOR+fCtTka+vwpjV/JDkCq9uw3ejxzXLyoi8dftM0bRj5vjd4l4Gjle5BZVu2KRJOdfnY8QLhvJ09Czh/PuQ7eNfPTmOj8pBbgJnJxdqfGZAMJtuZ0UrPSG/B1RAnZAez+BW2SmoYskIYK5eVaKe736i6BZQcP+myur/DNFW3+HnoYHycdnXnoq+owHLwleTigqrbLjDBu77klNQBa9m1yzlp78IyfUKCNRNSUrtWGx3SP34NqlIUaBqdUuYn2nDt7pNihdblUoFzfBUYKrmoYEcL9Dw/dY3nFS9C3bhaluBBlSK+USyoR+gm4+CwBUb6qMazjdAVkHI4KKpv2BaI2ud2KHy9uSMoMdEIntJD8dIEHWso/6Z5qYYIPVA2d1ZYwh8DXIQGFsXpLQuOeIX+PLktMWiFg1FS79D+7oIlQxcXhgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3317,"cache_read_input_tokens":25551,"output_tokens":933,"output_tokens_details":{"thinking_tokens":43},"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":3317},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":536,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXpcMQkAY77vBMh9FhzY","requestRef":"d0b20e79-db5a-4202-8d89-ca0156acf809","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1cccd89b-67f0-424c-887a-d29bfc781d4e","timestamp":"2026-10-30T04:52:06.086Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"1cccd89b-67f0-424c-887a-d29bfc781d4e","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpcMkKxJ1cB2ofYLC7F","type":"message","role":"assistant","content":[{"type":"text","text":"Derived figures in the report (0.72% break-even growth, HAC SE about 80% larger than the classical SE) check out. Finalising the ledger."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3317,"cache_read_input_tokens":25551,"output_tokens":933,"output_tokens_details":{"thinking_tokens":43},"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":3317},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXpcMQkAY77vBMh9FhzY","requestRef":"d0b20e79-db5a-4202-8d89-ca0156acf809","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7cb0fd07-885e-48e4-ae12-ba4dd2a5ceae","timestamp":"2026-10-30T04:52:06.090Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"7cb0fd07-885e-48e4-ae12-ba4dd2a5ceae","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpcMkKxJ1cB2ofYLC7F","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01BLenGpT6CpbctWmQu7SchX","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimand, outputs, info rules, invalidity conditions\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs match README\",\"row counts 319/945 recorded\",\"date grids complete, no duplicate dates\",\"1 blank UNRATE (2025-10) out of sample\",\"exclusions.csv ledger consistent: final n=240\"],\"notes\":\"post-2019 data excluded by window filter\"},\n \"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE)=0.3247 computed on same 240-quarter sample\"],\"notes\":\"\"},\n \"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png, exclusions.csv\",\"no randomness (random_seed null)\",\"runtime assertions passed\"],\"notes\":\"HAC lags=4 via NW(1994) rule; supplementary HAC interaction Wald tests added\"},\n \"P4\":{\"status\":\"passed\",\"checks\":[\"clean rerun: results.json byte-identical, table1.csv identical\",\"19 consistency checks PASS (see checks.md)\",\"figure visually inspected\"],\"notes\":\"\"},\n \"P5\":{\"status\":\"passed\",\"checks\":[\"report.md has 6 required sections in order\",\"all claims.json results_keys exist in results.json\",\"derived numbers in report (0.72 break-even, 1.8x SE ratio) verified by code\"],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed. P2/P3: analysis.py written; beta=-0.256, HAC SE 0.036 (4 lags); Chow F=6.09 p=0.0026 -> unstable. Decision: add HAC dummy-interaction Wald tests as supplementary since slopes nearly equal (rejection driven jointly/intercept).\n- 2026-10-30 P4 passed: deterministic rerun identical; all checks pass.\n- 2026-10-30 P5 passed: report, claims written. Task complete.\nEOF\ngrep -n '^## ' out/report.md; ls out","description":"Finalize phases ledger and log"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3317,"cache_read_input_tokens":25551,"output_tokens":933,"output_tokens_details":{"thinking_tokens":43},"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":3317},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXpcMQkAY77vBMh9FhzY","requestRef":"d0b20e79-db5a-4202-8d89-ca0156acf809","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"a45fc2c9-bcf8-43f8-bd1a-0dd279c323da","timestamp":"2026-10-30T04:52:12.643Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"a45fc2c9-bcf8-43f8-bd1a-0dd279c323da","isSidechain":false,"promptId":"194fb98d-63bb-428d-9140-926a846661b5","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01BLenGpT6CpbctWmQu7SchX","type":"tool_result","content":"3:## Question\n6:## Data and exclusions\n15:## Method\n25:## Results\n41:## Uncertainty\n48:## Limitations and open issues\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\ntable1.csv","is_error":false}]},"uuid":"e7de14dc-9efd-4e8d-8c02-e96eb2e65146","timestamp":"2026-10-30T04:52:12.689Z","toolUseResult":{"stdout":"3:## Question\n6:## Data and exclusions\n15:## Method\n25:## Results\n41:## Uncertainty\n48:## Limitations and open issues\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\ntable1.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"a45fc2c9-bcf8-43f8-bd1a-0dd279c323da","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","hash":"cfc0260860b660a6145c65de336b33455e25d289fd42580c5d78e8100b5ad7fc","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS4gYKEAgTGAI4AUIIdGhpbmtpbmcSDDVZp0kknYaIC2n8XhoMqPXVMwrHClOEL70lIjBgMt9KPeBORoLnLXUhb+Tc/IOwbjMW78XH3zOD3Y8lwA3kbYkhImLQp7X0Xk/RrlQq/wXh0bJD46YdvJ1fonVXYgTIgRcZYY9+bVJCuLEGSVSNzgI1pq8Jlav93ZoZs6oJV1wAmuddzh5jm2oLZHumDaz/Wcz3jMkkua27w2+AhKXw3HAuSLAQ/dlEFJH7nOSi9flQafELw+gf8BaWPKkLf1F9zg1gF0sI6dWFWnmfnDDj1nW5/t4JcwY7rx/pnjOORhsCiZtm40Uw6jhoL6S0KQrscoLk40NBw6pXTJBFN1TQ7CZCd4S1xjN9Eg3X8F+SGDHPgMm62bX5yVInTXHouEGJC06Y6ljQSzBrY2sLoaIBNG4hMPDIpfMYiZmzFWDWYMAY3C+oluPDfDKylPQ22ytrRF+/LAKQt3gOlTApmCfxKP4EtXntkT928WOUB0L+GzNyfYr5SBJFJTA2WRd5vhG+6ZqjSZtxTBDQhavyhEoh+VaA9AMxHqcbDMMOpHgRULgHeUG2DRVUyQ9MRBZIe9SWVaBkGQHmwCCHP4dRJ2lGvHatQ33OAQzXDBuXMCfglhFKZ9Iav5+h3Wlc8vRW0JZ0ySvyymDqUIz2qsiXe/dwhp05NnpgJS1mVr0gZm1hlLSycBdIEwdTfApqEe5TxOR+fCtTka+vwpjV/JDkCq9uw3ejxzXLyoi8dftM0bRj5vjd4l4Gjle5BZVu2KRJOdfnY8QLhvJ09Czh/PuQ7eNfPTmOj8pBbgJnJxdqfGZAMJtuZ0UrPSG/B1RAnZAez+BW2SmoYskIYK5eVaKe736i6BZQcP+myur/DNFW3+HnoYHycdnXnoq+owHLwleTigqrbLjDBu77klNQBa9m1yzlp78IyfUKCNRNSUrtWGx3SP34NqlIUaBqdUuYn2nDt7pNihdblUoFzfBUYKrmoYEcL9Dw/dY3nFS9C3bhaluBBlSK+USyoR+gm4+CwBUb6qMazjdAVkHI4KKpv2BaI2ud2KHy9uSMoMdEIntJD8dIEHWso/6Z5qYYIPVA2d1ZYwh8DXIQGFsXpLQuOeIX+PLktMWiFg1FS79D+7oIlQxcXhgB"},{"type":"text","text":"Derived figures in the report (0.72% break-even growth, HAC SE about 80% larger than the classical SE) check out. Finalising the ledger."},{"type":"tool_use","id":"toolu_01BLenGpT6CpbctWmQu7SchX","name":"Bash","input":{"command":"cat > out/state/phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written with estimand, outputs, info rules, invalidity conditions\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"passed\",\"checks\":[\"SHA-256 of both inputs match README\",\"row counts 319/945 recorded\",\"date grids complete, no duplicate dates\",\"1 blank UNRATE (2025-10) out of sample\",\"exclusions.csv ledger consistent: final n=240\"],\"notes\":\"post-2019 data excluded by window filter\"},\n \"P2\":{\"status\":\"passed\",\"checks\":[\"baseline_metric (mean-only RMSE)=0.3247 computed on same 240-quarter sample\"],\"notes\":\"\"},\n \"P3\":{\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png, exclusions.csv\",\"no randomness (random_seed null)\",\"runtime assertions passed\"],\"notes\":\"HAC lags=4 via NW(1994) rule; supplementary HAC interaction Wald tests added\"},\n \"P4\":{\"status\":\"passed\",\"checks\":[\"clean rerun: results.json byte-identical, table1.csv identical\",\"19 consistency checks PASS (see checks.md)\",\"figure visually inspected\"],\"notes\":\"\"},\n \"P5\":{\"status\":\"passed\",\"checks\":[\"report.md has 6 required sections in order\",\"all claims.json results_keys exist in results.json\",\"derived numbers in report (0.72 break-even, 1.8x SE ratio) verified by code\"],\"notes\":\"\"}}\nEOF\ncat >> out/state/log.md <<'EOF'\n- 2026-10-30 P1 passed. P2/P3: analysis.py written; beta=-0.256, HAC SE 0.036 (4 lags); Chow F=6.09 p=0.0026 -> unstable. Decision: add HAC dummy-interaction Wald tests as supplementary since slopes nearly equal (rejection driven jointly/intercept).\n- 2026-10-30 P4 passed: deterministic rerun identical; all checks pass.\n- 2026-10-30 P5 passed: report, claims written. Task complete.\nEOF\ngrep -n '^## ' out/report.md; ls out","description":"Finalize phases ledger and log"}}]}}
{"type":"api-request","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","id":"cda63288-4398-46cd-b3ce-70198b4c80e7","timestamp":"2026-10-30T04:52:12.693Z","version":"2.1.314","querySource":"sdk","shapeHash":"6d833aaeaca61b36a8ba0e7ad1b2dd8236c3b5ee7b4b31203e68e051b293247a","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":"d0b20e79-db5a-4202-8d89-ca0156acf809","keep":28,"tail":["cfc0260860b660a6145c65de336b33455e25d289fd42580c5d78e8100b5ad7fc","efce965a8972af853fe417bb0ff6d3ff23af6ae5013a92215660bf1db01f35cf"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a0d690e0708e3e4d44123d37aaa45ec9799edc431f78a6fe61093ee85ff1fbad"}
{"parentUuid":"e7de14dc-9efd-4e8d-8c02-e96eb2e65146","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXpd6iEMvupUWKy2FkAL","type":"message","role":"assistant","content":[{"type":"text","text":"I've completed the task: the full 1960–2019 relationship is clearly negative, and the Chow test rejects stability. But that rejection does not come from a change in the Okun coefficient itself — the two subperiod slopes are almost the same. Rerunning `out/analysis.py` from scratch reproduces identical results, and all consistency checks passed.\n\n**Results** (240 quarters, 1960Q1–2019Q4):\n- **Okun coefficient:** β = −0.256 per 1% of quarterly growth, with intercept α = 0.184 pp. Each extra 1% of quarterly real growth goes with a change in unemployment about 0.26 pp lower.\n- **Uncertainty:** the Newey–West standard error (Bartlett kernel, 4 lags) is 0.036, giving a 95% interval of [−0.326, −0.185]. The conclusion code is `negative_effect`. Using 8 lags barely changes the SE (0.037).\n- **Fit:** the residual RMSE is 0.250 pp, against 0.325 pp for predicting the mean every quarter (R² = 0.41).\n- **Subperiods:** the slope is −0.259 for 1960–83 (96 quarters) and −0.273 for 1984–2019 (144 quarters).\n- **Chow test:** F(2, 236) = 6.09, p = 0.0026, so `stability_conclusion` is `unstable`.\n\n**What the \"unstable\" verdict means:** I added a check the task didn't ask for, a regression with subperiod dummies and robust errors:\n- The slopes do not differ (p = 0.85).\n- The post-1984 line sits lower (intercept 0.152 vs 0.254), though that difference alone isn't significant (p = 0.26).\n- Intercept and slope together still differ (p = 0.005).\n\nSo the instability is a joint shift in intercept and slope, not a change in Okun's coefficient. Calling it an intercept shift is my reading of the estimates, not a tested result.\n\n**Limitations** (discussed in the report):\n- The classical Chow test assumes equal, uncorrelated errors in both periods. Here the residual variance falls from 0.079 to 0.048 after 1984 and the errors show serial correlation, so its p-value may be off. The robust joint test agrees with it, though.\n- The 1984 break date is imposed, not estimated; I didn't test for breaks at unknown dates.\n- The model is a simple one-equation form: it leaves out lagged growth, ignores possible recession/expansion differences, and measures an association, not a causal effect.\n- The data are the 2026 revised vintage, not the figures available in real time.\n- The only data problem was a blank October 2025 unemployment value, which falls outside the sample. No data after 2019Q4 enter any estimate.\n\nEverything is in `out/`; open `report.md` first.\n- `report.md`\n- `results.json`\n- `table1.csv`\n- `figure1.png`\n- `analysis.py`\n- `claims.json`\n- `exclusions.csv`\n- `state/` (contract, data audit, checks, phase ledger, log)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1029,"cache_read_input_tokens":28868,"output_tokens":1027,"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":1029},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXpd6SMoEymYkXZ3H5HS","requestRef":"cda63288-4398-46cd-b3ce-70198b4c80e7","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"da09f164-7c36-4469-9136-055603abdc26","timestamp":"2026-10-30T04:52:22.824Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0172","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"da09f164-7c36-4469-9136-055603abdc26","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6"}
{"type":"cost-state","sessionId":"df8c09f0-8046-49f1-86e8-7b64bf68e0f6","totalCostUSD":0.5944694000000001,"totalAPIDuration":179241,"totalAPIDurationWithoutRetries":179236,"totalToolDuration":3217,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":182605,"startTime":1793335760246,"modelUsage":{"claude-opus-5-5":{"inputTokens":32,"outputTokens":20456,"thinkingTokens":1131,"cacheReadInputTokens":216282,"cacheCreationInputTokens":28393,"cacheCreationEphemeral5mInputTokens":28393,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.5944694000000001}},"hasUnknownModelCost":false}