spb/wp29_uqo

1{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}2{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:33:45.709Z","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","content":"Begin"}3{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:33:45.716Z","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}4{"parentUuid":null,"isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":"Begin"},"uuid":"749b364b-ab29-4b3f-950c-11c91bb581c0","timestamp":"2026-10-30T05:33:45.721Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}5{"type":"api-request-shape","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","timestamp":"2026-10-30T05:33:45.737Z","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/RT0013\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}}]}}6{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}7{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"da27c63d-abb9-4a0c-aee3-36f5baeb84b3","timestamp":"2026-10-30T05:33:45.737Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"847ce8110eff3a596f6b03990c49ed87ab6687c455ff4f2a412f0830e912190d"}8{"parentUuid":"749b364b-ab29-4b3f-950c-11c91bb581c0","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"877c5e31-2791-424d-a4a2-9c688a85efd9","timestamp":"2026-10-30T05:33:45.727Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}9{"parentUuid":"877c5e31-2791-424d-a4a2-9c688a85efd9","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"bdff0e22-48ea-41f6-9fae-20f3d43dae12","timestamp":"2026-10-30T05:33:45.727Z","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/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}10{"parentUuid":"bdff0e22-48ea-41f6-9fae-20f3d43dae12","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":"ae1f9fda-3d18-4bdb-9527-3b8ca39307ec","timestamp":"2026-10-30T05:33:45.728Z","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/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}11{"type":"tools-used","tools":["Bash"],"sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}12{"parentUuid":"ae1f9fda-3d18-4bdb-9527-3b8ca39307ec","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnu57oDkP7skFrLwKy","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":97,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":950,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsntsioqXXKpoAvbPAM","requestRef":"da27c63d-abb9-4a0c-aee3-36f5baeb84b3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8601d4c8-726a-486c-bd06-784c744096ef","timestamp":"2026-10-30T05:33:47.555Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}13{"parentUuid":"8601d4c8-726a-486c-bd06-784c744096ef","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsnu57oDkP7skFrLwKy","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WyNZviHip54cjvu8ozaybL","name":"Bash","input":{"command":"cat TASK.md; ls -laR data out 2>/dev/null | head -50"},"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":97,"output_tokens_details":{"thinking_tokens":23},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2209},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsntsioqXXKpoAvbPAM","requestRef":"da27c63d-abb9-4a0c-aee3-36f5baeb84b3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"24b736c5-51c5-4fb1-953b-07a085f345dd","timestamp":"2026-10-30T05:33:47.558Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}14{"parentUuid":"24b736c5-51c5-4fb1-953b-07a085f345dd","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WyNZviHip54cjvu8ozaybL","type":"tool_result","content":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n  - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n  - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n  - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ndata:\ntotal 80\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 .\ndrwxr-xr-x   6 simon-pierreboucher  staff    192 oct.  30 00:09 ..\n-rw-r--r--   1 simon-pierreboucher  staff   1384 oct.  30 00:05 first_release.csv\n-rw-r--r--   1 simon-pierreboucher  staff   9546 oct.  30 00:05 README.md\n-rw-r--r--   1 simon-pierreboucher  staff   7529 oct.  30 00:05 RSAFS_current.csv\n-rw-r--r--   1 simon-pierreboucher  staff  13438 oct.  30 00:05 UMCSENT.csv\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 vintages\n\ndata/vintages:\ntotal 560\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 .\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 ..\n-rw-r--r--   1 simon-pierreboucher  staff  18180 oct.  30 00:05 PAYEMS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18198 oct.  30 00:05 PAYEMS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18234 oct.  30 00:05 PAYEMS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18252 oct.  30 00:05 PAYEMS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18270 oct.  30 00:05 PAYEMS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18288 oct.  30 00:05 PAYEMS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18306 oct.  30 00:05 PAYEMS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18324 oct.  30 00:05 PAYEMS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18342 oct.  30 00:05 PAYEMS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18360 oct.  30 00:05 PAYEMS_vintage_2026-07-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7304 oct.  30 00:05 RSAFS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7322 oct.  30 00:05 RSAFS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7340 oct.  30 00:05 RSAFS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7358 oct.  30 00:05 RSAFS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7376 oct.  30 00:05 RSAFS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7394 oct.  30 00:05 RSAFS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7430 oct.  30 00:05 RSAFS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7448 oct.  30 00:05 RSAFS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7466 oct.  30 00:05 RSAFS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7484 oct.  30 00:05 RSAFS_vintage_2026-07-31.csv","is_error":false}]},"uuid":"120015d9-bb1c-4a22-856e-08a1a6b73dca","timestamp":"2026-10-30T05:33:47.673Z","toolUseResult":{"stdout":"# T1-forecast — Real-time forecasting of US retail-sales growth from data vintages: a complete mini-project\n\n## Scientific question\nHow well could the year-over-year growth of US retail and food services sales have been forecast *in real time* — using only the data actually published at each forecast origin — one and three months beyond the last published month, and does a model of your own design beat the no-change (naive) forecast once the forecast errors are measured against the first published value of each target month? This is an end-to-end forecasting project: question → data audit → real-time baselines → your model → rolling-origin evaluation → uncertainty → figure → short paper. The estimands are, for horizons h ∈ {1, 3} months and over the 10 forecast origins defined below: (a) the out-of-sample RMSE and MAE of three baselines (naive, seasonal naive, AR(1)) and of your model, all evaluated against the first-release value of the target; (b) the relative improvement of your model over the naive forecast, 1 − RMSE_model / RMSE_naive; (c) the Diebold–Mariano statistic of your model against the naive forecast under squared-error loss, with a long-run variance that is robust to the serial correlation of multi-step forecast errors; (d) the mean absolute revision between the first-release growth of the h = 1 target months and their currently published growth. Report what the data show, including a negative result if your model does not beat the naive forecast.\n\n## Inputs\nAll series are monthly, seasonally adjusted, dated by the first day of the month, and come from FRED/ALFRED (Federal Reserve Bank of St. Louis); full provenance, retrieval times (2026-10-30 UTC), SHA-256 and terms are in `data/README.md`.\n- `data/vintages/RSAFS_vintage_<YYYY-MM-DD>.csv` — 10 files, one per forecast origin (2025-10-31, 2025-11-30, 2025-12-31, 2026-01-31, 2026-02-28, 2026-03-31, 2026-04-30, 2026-05-31, 2026-06-30, 2026-07-31): the series RSAFS — Advance Retail Sales: Retail Trade and Food Services, total, millions of dollars, SA (US Census Bureau) — exactly as it was published on that date (ALFRED vintage; header `observation_date,RSAFS_<yyyymmdd>`; first observation 1992-01; the last row is the most recent month published at that date). The target variable is the year-over-year growth g_m = 100 · ln(L_m / L_{m−12}) in percent, where L is the level in the relevant vintage.\n- `data/vintages/PAYEMS_vintage_<YYYY-MM-DD>.csv` — 10 files, same dates: the series PAYEMS — All Employees, Total Nonfarm, thousands of persons, SA (US Bureau of Labor Statistics) — as published on that date (ALFRED vintage; first observation 1939-01). A candidate predictor.\n- `data/UMCSENT.csv` — the series UMCSENT — University of Michigan Index of Consumer Sentiment (1966Q1 = 100) — current vintage as served by FRED on 2026-10-30 (header `observation_date,UMCSENT`; 1952-11 to 2026-09; the field is empty for the months before 1978 in which the survey was not conducted). A candidate predictor; see the availability rule below.\n- `data/RSAFS_current.csv` — RSAFS as served by FRED on 2026-10-30 (header `observation_date,RSAFS`; 1992-01 to 2026-09), containing all revisions known today. **Provided only for the revision analysis (estimand (d)); it may not enter any forecast.**\n- `data/first_release.csv` — one row per target month from 2024-06 to 2026-09: `target_month`, `first_release_vintage` (the first month-end ALFRED vintage in the designer's grid 2024-06-30 … 2026-10-29 in which the month appears), `level_first_release` (the RSAFS level of the month in that vintage), `level_prev_year_same_vintage` (the level of the month twelve months earlier in the same vintage) and `yoy_first_release` = 100 · ln(level_first_release / level_prev_year_same_vintage), 6 decimals. This is the \"actual\" against which every forecast is evaluated.\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- Forecast origins are the 10 vintage dates listed above. A forecast made at origin V may use **only** the RSAFS vintage file dated V, the PAYEMS vintage file dated V, and the UMCSENT values of months on or before the month of V (the final sentiment reading of a month is published before the end of that month and is not revised afterwards; the current UMCSENT file is used with this rule). Estimation samples, model selection, transformations and the values plugged into a forecast must all respect this rule at every origin.\n- Let last(V) be the most recent month present in the RSAFS vintage dated V (it is not always the month before V: publication delays occurred). The target of origin V at horizon h is the month last(V) + h; the actual is `yoy_first_release` of that month in `data/first_release.csv`.\n- Baselines (all three required, computed from the RSAFS vintage dated V):\n  - **naive**: the forecast for both horizons is g_{last(V)}, the last available growth value in the vintage;\n  - **seasonal naive**: the forecast for target month T is g_{T−12} from the vintage;\n  - **AR(1)**: ordinary least squares of g_m on a constant and g_{m−1} over all consecutive pairs with 1993-02 ≤ m ≤ last(V) in the vintage, then iterated (plug-in) forecasts h steps beyond last(V).\n- Your model is free (it may use the vintage dynamics, PAYEMS and/or UMCSENT), but it must obey the availability rule and must be described in `model_description`.\n- Diebold–Mariano test (model vs naive, per horizon): loss differential d_t = e²_naive,t − e²_model,t over the 10 origins; `dm_stat_h` = d̄ / sqrt(σ̂²_LR / n) where σ̂²_LR is the Bartlett-kernel (Newey–West) long-run variance of d_t with truncation lag h − 1 (lag 0 only at h = 1; lags 1 and 2 with weights 2/3 and 1/3 at h = 3), without the Harvey–Leybourne–Newbold small-sample factor; `dm_pvalue_h` is the two-sided p-value from the standard normal. You may add other uncertainty measures (e.g. a bootstrap interval for the RMSE difference) in the report.\n- The series `RSAFS_current.csv` is used only for estimand (d): mean over the 10 h = 1 target months of |g^current_T − yoy_first_release_T|, where g^current is the growth computed from the current file.\n\n## Required outputs\n- `out/forecasts.csv` — exactly one row per (origin, horizon, model): 10 origins × 2 horizons × 4 models = 80 rows, columns `origin_date` (vintage date, YYYY-MM-DD), `target_date` (YYYY-MM-01), `horizon` (1 or 3), `forecast` (percent), `actual_first_release` (percent, from `first_release.csv`), `model` (one of `naive`, `snaive`, `ar1`, `model`), `vintage_used` (the vintage date of the RSAFS file used, YYYY-MM-DD).\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `task_id` | string | — | \"T1-forecast\" |\n| `model_name` | string | — | short name of your model |\n| `model_description` | string | — | specification, predictors, estimation window, alignment of predictors with the availability rule |\n| `n_origins` | integer | — | 10 |\n| `first_origin`, `last_origin` | string | — | first and last origin dates (YYYY-MM-DD) |\n| `rmse_naive_h1`, `mae_naive_h1`, `rmse_naive_h3`, `mae_naive_h3` | number | percent | naive baseline errors against first-release actuals |\n| `rmse_snaive_h1`, `mae_snaive_h1`, `rmse_snaive_h3`, `mae_snaive_h3` | number | percent | seasonal-naive baseline errors |\n| `rmse_ar1_h1`, `mae_ar1_h1`, `rmse_ar1_h3`, `mae_ar1_h3` | number | percent | AR(1) baseline errors |\n| `rmse_model_h1`, `mae_model_h1`, `rmse_model_h3`, `mae_model_h3` | number | percent | your model's errors |\n| `rel_improvement_rmse_h1`, `rel_improvement_rmse_h3` | number | — | 1 − RMSE_model / RMSE_naive |\n| `dm_stat_h1`, `dm_pvalue_h1`, `dm_stat_h3`, `dm_pvalue_h3` | number | — | Diebold–Mariano statistic and two-sided p-value, model vs naive, as defined above |\n| `conclusion_code_h1`, `conclusion_code_h3` | string | — | one of `model_better_significant`, `model_better_not_significant`, `naive_better_not_significant`, `naive_better_significant` (\"better\" = lower RMSE; \"significant\" = `dm_pvalue_h` < 0.05) |\n| `mean_abs_revision_h1_targets` | number | percent | estimand (d) |\n| `feasibility` | string | — | \"complete\", \"partial\" or \"infeasible\" |\n| `feasibility_reason` | string or null | — | explanation if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | — | every data problem detected (irregular publication timing, missing values, revisions that affect the design, …) and how it was handled; empty list if none |\n| `n_input_rows` | object | rows | {file name: number of data rows (lines after the header)} for every file under `data/` that you read |\n| `n_analysed` | integer or null | — | number of forecast–actual pairs evaluated for your model (both horizons) |\n| `random_seed` | integer or null | — | seed used, if any (e.g. bootstrap) |\n\n- `out/table1.csv` — the RMSE/MAE table: one row per (model, horizon) with columns `model`, `horizon`, `rmse`, `mae`, `n`.\n- `out/figure1.png` — first-release actuals and the forecasts of the naive baseline and of your model over the target months, one panel per horizon (or an equivalent single figure).\n- `out/report.md` — a short paper with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. The \"Data and exclusions\" section must document the real-time design (which vintage feeds which forecast, publication delays observed) and the \"Uncertainty\" section must interpret the Diebold–Mariano results given the small number of origins.\n- `out/analysis.py` — running `~/wp29/venv/bin/python out/analysis.py` from the workspace root must regenerate `out/results.json`, `out/forecasts.csv`, `out/table1.csv` and `out/figure1.png` from `data/` only, deterministically.\n- `out/claims.json` — a list of the central claims of the report: [{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}].\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Budget class: transfer mini-project — 12.00 USD cap, 60 minutes wall, 150 turns per session. The project is designed to be completed in well under 45 minutes of work.\ndata:\ntotal 80\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 .\ndrwxr-xr-x   6 simon-pierreboucher  staff    192 oct.  30 00:09 ..\n-rw-r--r--   1 simon-pierreboucher  staff   1384 oct.  30 00:05 first_release.csv\n-rw-r--r--   1 simon-pierreboucher  staff   9546 oct.  30 00:05 README.md\n-rw-r--r--   1 simon-pierreboucher  staff   7529 oct.  30 00:05 RSAFS_current.csv\n-rw-r--r--   1 simon-pierreboucher  staff  13438 oct.  30 00:05 UMCSENT.csv\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 vintages\n\ndata/vintages:\ntotal 560\ndrwxr-xr-x  22 simon-pierreboucher  staff    704 oct.  30 00:03 .\ndrwxr-xr-x   7 simon-pierreboucher  staff    224 oct.  30 00:05 ..\n-rw-r--r--   1 simon-pierreboucher  staff  18180 oct.  30 00:05 PAYEMS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18198 oct.  30 00:05 PAYEMS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18234 oct.  30 00:05 PAYEMS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18252 oct.  30 00:05 PAYEMS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18270 oct.  30 00:05 PAYEMS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18288 oct.  30 00:05 PAYEMS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18306 oct.  30 00:05 PAYEMS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18324 oct.  30 00:05 PAYEMS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18342 oct.  30 00:05 PAYEMS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff  18360 oct.  30 00:05 PAYEMS_vintage_2026-07-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7304 oct.  30 00:05 RSAFS_vintage_2025-10-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7322 oct.  30 00:05 RSAFS_vintage_2025-11-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7340 oct.  30 00:05 RSAFS_vintage_2025-12-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7358 oct.  30 00:05 RSAFS_vintage_2026-01-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7376 oct.  30 00:05 RSAFS_vintage_2026-02-28.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7394 oct.  30 00:05 RSAFS_vintage_2026-03-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7430 oct.  30 00:05 RSAFS_vintage_2026-04-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7448 oct.  30 00:05 RSAFS_vintage_2026-05-31.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7466 oct.  30 00:05 RSAFS_vintage_2026-06-30.csv\n-rw-r--r--   1 simon-pierreboucher  staff   7484 oct.  30 00:05 RSAFS_vintage_2026-07-31.csv","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"24b736c5-51c5-4fb1-953b-07a085f345dd","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}15{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"00f945c92fd66e8f64e94845197aa14f4af3fb2efa7c4979724c131734f8df40","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WyNZviHip54cjvu8ozaybL","name":"Bash","input":{"command":"cat TASK.md; ls -laR data out 2>/dev/null | head -50"}}]}}16{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"92acad8e-4c3a-44a3-9fae-537cb154518b","timestamp":"2026-10-30T05:33:47.679Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"da27c63d-abb9-4a0c-aee3-36f5baeb84b3","keep":2,"tail":["00f945c92fd66e8f64e94845197aa14f4af3fb2efa7c4979724c131734f8df40","ba18009135c305bf5c98f491fca4ec14392689ae014a7c659e67d67a36831ba4"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"7236f31943da51d697e0df8f7385d39c6657640aff7826bc9df93cc6e9d3fcbe"}17{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"120015d9-bb1c-4a22-856e-08a1a6b73dca","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}18{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}19{"parentUuid":"120015d9-bb1c-4a22-856e-08a1a6b73dca","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXso1w8EZp3hiStbek6b","type":"message","role":"assistant","content":[{"type":"text","text":"No `out/` yet — fresh start."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5684,"cache_read_input_tokens":3713,"output_tokens":226,"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":5684},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXso1gV8xi99RCNHxKn2","requestRef":"92acad8e-4c3a-44a3-9fae-537cb154518b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0be26414-b61c-486b-8c79-187d62161099","timestamp":"2026-10-30T05:33:48.687Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}20{"parentUuid":"0be26414-b61c-486b-8c79-187d62161099","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXso1w8EZp3hiStbek6b","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01McmmQ9bwzPbGFPr4RD8qQG","name":"Bash","input":{"command":"cat data/README.md; cat data/first_release.csv; cd data/vintages; for f in RSAFS*; do echo \"$f $(wc -l <$f) $(tail -1 $f) $(head -1 $f)\"; done; for f in PAYEMS*; do echo \"$f $(wc -l <$f) $(tail -1 $f)\"; done; cd ..; head -3 UMCSENT.csv; tail -3 UMCSENT.csv; tail -3 RSAFS_current.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":5684,"cache_read_input_tokens":3713,"output_tokens":226,"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":5684},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXso1gV8xi99RCNHxKn2","requestRef":"92acad8e-4c3a-44a3-9fae-537cb154518b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"051bfbe9-e2e6-490c-8612-b8a058f0437f","timestamp":"2026-10-30T05:33:49.968Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}21{"parentUuid":"051bfbe9-e2e6-490c-8612-b8a058f0437f","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01McmmQ9bwzPbGFPr4RD8qQG","type":"tool_result","content":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\ntarget_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\nRSAFS_vintage_2025-10-31.csv      405 2025-08-01,732010 observation_date,RSAFS_20251031\nRSAFS_vintage_2025-11-30.csv      406 2025-09-01,733258 observation_date,RSAFS_20251130\nRSAFS_vintage_2025-12-31.csv      407 2025-10-01,732633 observation_date,RSAFS_20251231\nRSAFS_vintage_2026-01-31.csv      408 2025-11-01,735904 observation_date,RSAFS_20260131\nRSAFS_vintage_2026-02-28.csv      409 2025-12-01,734967 observation_date,RSAFS_20260228\nRSAFS_vintage_2026-03-31.csv      410 2026-01-01,733537 observation_date,RSAFS_20260331\nRSAFS_vintage_2026-04-30.csv      412 2026-03-01,752063 observation_date,RSAFS_20260430\nRSAFS_vintage_2026-05-31.csv      413 2026-04-01,757085 observation_date,RSAFS_20260531\nRSAFS_vintage_2026-06-30.csv      414 2026-05-01,763705 observation_date,RSAFS_20260630\nRSAFS_vintage_2026-07-31.csv      415 2026-06-01,768553 observation_date,RSAFS_20260731\nPAYEMS_vintage_2025-10-31.csv     1041 2025-08-01,159540\nPAYEMS_vintage_2025-11-30.csv     1042 2025-09-01,159626\nPAYEMS_vintage_2025-12-31.csv     1044 2025-11-01,159552\nPAYEMS_vintage_2026-01-31.csv     1045 2025-12-01,159526\nPAYEMS_vintage_2026-02-28.csv     1046 2026-01-01,158627\nPAYEMS_vintage_2026-03-31.csv     1047 2026-02-01,158466\nPAYEMS_vintage_2026-04-30.csv     1048 2026-03-01,158637\nPAYEMS_vintage_2026-05-31.csv     1049 2026-04-01,158736\nPAYEMS_vintage_2026-06-30.csv     1050 2026-05-01,159001\nPAYEMS_vintage_2026-07-31.csv     1051 2026-06-01,158984\nobservation_date,UMCSENT\n1952-11-01,86.2\n1952-12-01,\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021","is_error":false}]},"uuid":"3de52ee3-972e-486f-91ce-80e61d5ba043","timestamp":"2026-10-30T05:33:50.151Z","toolUseResult":{"stdout":"# Data provenance — T1-forecast\n\nAll observed series were retrieved by the task designer on 2026-10-30 (between 04:00 and 04:01 UTC) from the Federal Reserve Bank of St. Louis FRED and ALFRED services, exactly as served (CSV, one header line, `observation_date` in YYYY-MM-DD, empty value field where the source reports no value). No value was altered. Row counts are data rows (lines after the header).\n\n| file | content | URL | retrieved (UTC) | data rows | SHA-256 |\n|---|---|---|---|---|---|\n| `vintages/PAYEMS_vintage_2025-10-31.csv` | PAYEMS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 1040 | d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60 |\n| `vintages/PAYEMS_vintage_2025-11-30.csv` | PAYEMS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 1041 | a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77 |\n| `vintages/PAYEMS_vintage_2025-12-31.csv` | PAYEMS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 1043 | 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031 |\n| `vintages/PAYEMS_vintage_2026-01-31.csv` | PAYEMS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 1044 | 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7 |\n| `vintages/PAYEMS_vintage_2026-02-28.csv` | PAYEMS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 1045 | 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3 |\n| `vintages/PAYEMS_vintage_2026-03-31.csv` | PAYEMS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 1046 | 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e |\n| `vintages/PAYEMS_vintage_2026-04-30.csv` | PAYEMS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 1047 | 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a |\n| `vintages/PAYEMS_vintage_2026-05-31.csv` | PAYEMS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 1048 | e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d |\n| `vintages/PAYEMS_vintage_2026-06-30.csv` | PAYEMS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 1049 | 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a |\n| `vintages/PAYEMS_vintage_2026-07-31.csv` | PAYEMS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=PAYEMS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 1050 | 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41 |\n| `vintages/RSAFS_vintage_2025-10-31.csv` | RSAFS as published on 2025-10-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-10-31` | 2026-10-30T04:00Z | 404 | 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36 |\n| `vintages/RSAFS_vintage_2025-11-30.csv` | RSAFS as published on 2025-11-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-11-30` | 2026-10-30T04:00Z | 405 | 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4 |\n| `vintages/RSAFS_vintage_2025-12-31.csv` | RSAFS as published on 2025-12-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2025-12-31` | 2026-10-30T04:00Z | 406 | 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd |\n| `vintages/RSAFS_vintage_2026-01-31.csv` | RSAFS as published on 2026-01-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-01-31` | 2026-10-30T04:00Z | 407 | b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e |\n| `vintages/RSAFS_vintage_2026-02-28.csv` | RSAFS as published on 2026-02-28 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-02-28` | 2026-10-30T04:00Z | 408 | 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77 |\n| `vintages/RSAFS_vintage_2026-03-31.csv` | RSAFS as published on 2026-03-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-03-31` | 2026-10-30T04:00Z | 409 | 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f |\n| `vintages/RSAFS_vintage_2026-04-30.csv` | RSAFS as published on 2026-04-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-04-30` | 2026-10-30T04:00Z | 411 | 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f |\n| `vintages/RSAFS_vintage_2026-05-31.csv` | RSAFS as published on 2026-05-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-05-31` | 2026-10-30T04:00Z | 412 | 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b |\n| `vintages/RSAFS_vintage_2026-06-30.csv` | RSAFS as published on 2026-06-30 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-06-30` | 2026-10-30T04:00Z | 413 | 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524 |\n| `vintages/RSAFS_vintage_2026-07-31.csv` | RSAFS as published on 2026-07-31 | `https://alfred.stlouisfed.org/graph/alfredgraph.csv?id=RSAFS&vintage_date=2026-07-31` | 2026-10-30T04:00Z | 414 | 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2 |\n| `RSAFS_current.csv` | RSAFS (current vintage, all revisions to date) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=RSAFS` | 2026-10-30T04:00Z | 417 | 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f |\n| `UMCSENT.csv` | UMCSENT (current vintage) | `https://fred.stlouisfed.org/graph/fredgraph.csv?id=UMCSENT` | 2026-10-30T04:00Z | 887 | 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46 |\n| `first_release.csv` | derived by the task designer from the month-end ALFRED vintages of RSAFS 2024-06-30 … 2026-10-29 (29 vintages; the 19 not shipped here were used only to date the first release of each month) | (derived) | 2026-10-30T04:00Z | 28 | 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4 |\n\n## Series\n- **RSAFS** — Advance Retail Sales: Retail Trade and Food Services, Total. Source: U.S. Census Bureau, Advance Monthly Sales for Retail and Food Services (via FRED). Units: millions of dollars, seasonally adjusted, monthly, 1992-01 onward. The advance estimate of a month is normally published in the middle of the following month and is revised in the two following monthly releases and in annual revisions; a month-end ALFRED vintage therefore normally contains the months up to the month before the vintage date. The vintage grid in this bundle shows departures from this pattern (e.g. the vintages of 2025-10-31 and 2026-03-31 end two months before their date; the vintage of 2026-04-30 adds two months at once), which reflect the actual publication calendar; the task rules refer to the last month present in each vintage, not to the calendar.\n- **PAYEMS** — All Employees, Total Nonfarm. Source: U.S. Bureau of Labor Statistics, Current Employment Statistics (via FRED). Units: thousands of persons, seasonally adjusted, monthly, 1939-01 onward. Published in the Employment Situation release on the first Friday (normally) of the following month and revised in the two following releases and in annual benchmark revisions; the ALFRED vintages dated as the RSAFS vintages give the data available at each origin.\n- **UMCSENT** — University of Michigan: Consumer Sentiment, index 1966Q1 = 100, monthly (quarterly before 1978; empty fields where no survey was conducted). Source: University of Michigan, Surveys of Consumers (via FRED). The preliminary reading of a month is published in the middle of the month and the final reading at the end of the month; the series is not revised afterwards. The current FRED vintage is provided; at a month-end origin the final reading of the origin month is available (verified on the ALFRED vintages of 2025-10-31, 2026-03-31 and 2026-07-31, which contain the origin month).\n- **first_release.csv** — the first month-end ALFRED vintage in which each target month appears, the level printed there, the level of the month twelve months earlier in the same vintage, and the year-over-year growth 100·ln(ratio) (6 decimals). \"First release\" is defined at month-end granularity: for RSAFS the advance estimate is the only release of a month that can appear in the month-end vintage of the following month, so the value equals the advance estimate except where the publication calendar was disrupted (then it is the first published value as of the first month-end on which it existed).\n\n## Terms\nFRED/ALFRED data are provided by the Federal Reserve Bank of St. Louis under its terms of use (https://fred.stlouisfed.org/legal/); the underlying series are U.S. government statistics (Census Bureau, BLS: public domain) and the University of Michigan Surveys of Consumers index (redistributed by FRED with permission; cite \"University of Michigan, University of Michigan: Consumer Sentiment [UMCSENT], retrieved from FRED\"). The data are reproduced here unchanged for research use.\ntarget_month,first_release_vintage,level_first_release,level_prev_year_same_vintage,yoy_first_release\r\n2024-06-01,2024-07-31,704324,688630,2.253436\r\n2024-07-01,2024-08-31,709668,691250,2.62957\r\n2024-08-01,2024-09-30,710773,695940,2.108966\r\n2024-09-01,2024-10-31,714358,702160,1.722294\r\n2024-10-01,2024-11-30,718867,698956,2.808857\r\n2024-11-01,2024-12-31,724609,698105,3.726268\r\n2024-12-01,2025-01-31,729191,701672,3.846964\r\n2025-01-01,2025-02-28,723853,694696,4.111399\r\n2025-02-01,2025-03-31,722708,700932,3.059439\r\n2025-03-01,2025-04-30,722025,688248,4.791053\r\n2025-04-01,2025-05-31,724131,688629,5.026965\r\n2025-05-01,2025-06-30,715417,692635,3.236242\r\n2025-06-01,2025-07-31,720106,692922,3.848098\r\n2025-07-01,2025-08-31,726283,698909,3.84192\r\n2025-08-01,2025-09-30,732010,697157,4.878354\r\n2025-09-01,2025-11-30,733258,703285,4.17354\r\n2025-10-01,2025-12-31,732633,708070,3.410194\r\n2025-11-01,2026-01-31,735904,712175,3.277601\r\n2025-12-01,2026-02-28,734967,717547,2.398715\r\n2026-01-01,2026-03-31,733537,711095,3.1072\r\n2026-02-01,2026-04-30,739772,711575,3.886121\r\n2026-03-01,2026-04-30,752063,723350,3.89269\r\n2026-04-01,2026-05-31,757085,721903,4.758475\r\n2026-05-01,2026-06-30,763705,714568,6.650342\r\n2026-06-01,2026-07-31,768553,720164,6.503056\r\n2026-07-01,2026-08-31,763602,727176,4.887817\r\n2026-08-01,2026-09-30,737763,700218,5.223092\r\n2026-09-01,2026-10-29,745021,700948,6.09787\r\nRSAFS_vintage_2025-10-31.csv      405 2025-08-01,732010 observation_date,RSAFS_20251031\nRSAFS_vintage_2025-11-30.csv      406 2025-09-01,733258 observation_date,RSAFS_20251130\nRSAFS_vintage_2025-12-31.csv      407 2025-10-01,732633 observation_date,RSAFS_20251231\nRSAFS_vintage_2026-01-31.csv      408 2025-11-01,735904 observation_date,RSAFS_20260131\nRSAFS_vintage_2026-02-28.csv      409 2025-12-01,734967 observation_date,RSAFS_20260228\nRSAFS_vintage_2026-03-31.csv      410 2026-01-01,733537 observation_date,RSAFS_20260331\nRSAFS_vintage_2026-04-30.csv      412 2026-03-01,752063 observation_date,RSAFS_20260430\nRSAFS_vintage_2026-05-31.csv      413 2026-04-01,757085 observation_date,RSAFS_20260531\nRSAFS_vintage_2026-06-30.csv      414 2026-05-01,763705 observation_date,RSAFS_20260630\nRSAFS_vintage_2026-07-31.csv      415 2026-06-01,768553 observation_date,RSAFS_20260731\nPAYEMS_vintage_2025-10-31.csv     1041 2025-08-01,159540\nPAYEMS_vintage_2025-11-30.csv     1042 2025-09-01,159626\nPAYEMS_vintage_2025-12-31.csv     1044 2025-11-01,159552\nPAYEMS_vintage_2026-01-31.csv     1045 2025-12-01,159526\nPAYEMS_vintage_2026-02-28.csv     1046 2026-01-01,158627\nPAYEMS_vintage_2026-03-31.csv     1047 2026-02-01,158466\nPAYEMS_vintage_2026-04-30.csv     1048 2026-03-01,158637\nPAYEMS_vintage_2026-05-31.csv     1049 2026-04-01,158736\nPAYEMS_vintage_2026-06-30.csv     1050 2026-05-01,159001\nPAYEMS_vintage_2026-07-31.csv     1051 2026-06-01,158984\nobservation_date,UMCSENT\n1952-11-01,86.2\n1952-12-01,\n2026-07-01,55.2\n2026-08-01,51.7\n2026-09-01,48.1\n2026-07-01,729915\n2026-08-01,739322\n2026-09-01,745021","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"051bfbe9-e2e6-490c-8612-b8a058f0437f","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}22{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"6ab6d937ceada7d5d4db916741b008da174b231444c786ba23ca7b7369349cd5","message":{"role":"assistant","content":[{"type":"text","text":"No `out/` yet — fresh start."},{"type":"tool_use","id":"toolu_01McmmQ9bwzPbGFPr4RD8qQG","name":"Bash","input":{"command":"cat data/README.md; cat data/first_release.csv; cd data/vintages; for f in RSAFS*; do echo \"$f $(wc -l <$f) $(tail -1 $f) $(head -1 $f)\"; done; for f in PAYEMS*; do echo \"$f $(wc -l <$f) $(tail -1 $f)\"; done; cd ..; head -3 UMCSENT.csv; tail -3 UMCSENT.csv; tail -3 RSAFS_current.csv"}}]}}23{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"ab60b633-a5b8-4dc4-84e8-1d40dc6e6b67","timestamp":"2026-10-30T05:33:50.156Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"92acad8e-4c3a-44a3-9fae-537cb154518b","keep":4,"tail":["6ab6d937ceada7d5d4db916741b008da174b231444c786ba23ca7b7369349cd5","2306df7e4a081694c9347b3d4d99a9d1b84ad84e127ba50e94eb64645894260e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2c0a4fd2899fbc19b0e741a914bcfa8fbe49047066e5b598b585c2b8b407020b"}24{"parentUuid":"3de52ee3-972e-486f-91ce-80e61d5ba043","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoCRQXGQAcKbTx33vE","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":6708,"cache_read_input_tokens":9397,"output_tokens":779,"output_tokens_details":{"thinking_tokens":448},"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":6708},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4363,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsoCEVKSvpm3VSEc8y7","requestRef":"ab60b633-a5b8-4dc4-84e8-1d40dc6e6b67","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"68c00c11-c045-46b5-85b8-6967696ce010","timestamp":"2026-10-30T05:33:55.534Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}25{"parentUuid":"68c00c11-c045-46b5-85b8-6967696ce010","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsoCRQXGQAcKbTx33vE","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01STTsSmjb7CxK6e7zPbYsrX","name":"Bash","input":{"command":"mkdir -p out/state && cd data && shasum -a 256 *.csv vintages/*.csv | awk '{print $2, $1}' && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('*.csv')+glob.glob('vintages/*.csv')):\n    d=pd.read_csv(f); c=d.columns[1]\n    print(f,d.shape,d.observation_date.iloc[0] if 'observation_date' in d else '',d.iloc[-1,0],'na',d[c].isna().sum(),'dup',d.iloc[:,0].duplicated().sum(), list(d.loc[d[c].isna(),d.columns[0]].tail(3)) if 'UMC' not in f else d.loc[d[c].isna(),'observation_date'].max())\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":6708,"cache_read_input_tokens":9397,"output_tokens":779,"output_tokens_details":{"thinking_tokens":448},"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":6708},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsoCEVKSvpm3VSEc8y7","requestRef":"ab60b633-a5b8-4dc4-84e8-1d40dc6e6b67","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8f266239-0292-4178-b486-b43ef191c4ce","timestamp":"2026-10-30T05:33:58.026Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}26{"parentUuid":"8f266239-0292-4178-b486-b43ef191c4ce","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"type":"tool_result","content":"Exit code 1\n(eval):cd:1: no such file or directory: data","is_error":true,"tool_use_id":"toolu_01STTsSmjb7CxK6e7zPbYsrX"}]},"uuid":"3d2a00e2-2e5e-4ef5-a770-d65eb0963db6","timestamp":"2026-10-30T05:33:58.084Z","toolUseResult":"Error: Exit code 1\n(eval):cd:1: no such file or directory: data","sandboxed":false,"sourceToolAssistantUUID":"8f266239-0292-4178-b486-b43ef191c4ce","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}27{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"c4260d655e7defef7137b492a0909162a2ed2a176edb61b0f534c10d8a9ded80","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01STTsSmjb7CxK6e7zPbYsrX","name":"Bash","input":{"command":"mkdir -p out/state && cd data && shasum -a 256 *.csv vintages/*.csv | awk '{print $2, $1}' && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('*.csv')+glob.glob('vintages/*.csv')):\n    d=pd.read_csv(f); c=d.columns[1]\n    print(f,d.shape,d.observation_date.iloc[0] if 'observation_date' in d else '',d.iloc[-1,0],'na',d[c].isna().sum(),'dup',d.iloc[:,0].duplicated().sum(), list(d.loc[d[c].isna(),d.columns[0]].tail(3)) if 'UMC' not in f else d.loc[d[c].isna(),'observation_date'].max())\n\""}}]}}28{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"76add7dd-88c7-442f-8caa-1e7d82ef9614","timestamp":"2026-10-30T05:33:58.087Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"ab60b633-a5b8-4dc4-84e8-1d40dc6e6b67","keep":6,"tail":["c4260d655e7defef7137b492a0909162a2ed2a176edb61b0f534c10d8a9ded80","a05f0e2153496e181d0e2f08f3036670c8e506945009e39b18ae6465e3ba36cc"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"74f51f556b122ec58a6a4de3e4d332a199c3abd11ad45481eb89a616e2aa0320"}29{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"3d2a00e2-2e5e-4ef5-a770-d65eb0963db6","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}30{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}31{"parentUuid":"3d2a00e2-2e5e-4ef5-a770-d65eb0963db6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsonRYZuXhbZW8TfPFT","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FqkNgrw7CWd59rdCHkpqH5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; mkdir -p out/state; cd data && shasum -a 256 *.csv vintages/*.csv | awk '{print $2, $1}' && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('*.csv')+glob.glob('vintages/*.csv')):\n    d=pd.read_csv(f); c=d.columns[1]\n    print(f,d.shape,d.iloc[0,0],d.iloc[-1,0],'na',d[c].isna().sum(),'dup',d.iloc[:,0].duplicated().sum(), list(d.loc[d[c].isna(),d.columns[0]].tail(3)) if 'UMC' not in f else d.loc[d[c].isna(),'observation_date'].max())\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":814,"cache_read_input_tokens":16105,"output_tokens":342,"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":814},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXson9gU63zTntcgAD5E","requestRef":"76add7dd-88c7-442f-8caa-1e7d82ef9614","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"029d94b4-588a-4cb7-8783-cedc2f744274","timestamp":"2026-10-30T05:34:00.787Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}32{"parentUuid":"029d94b4-588a-4cb7-8783-cedc2f744274","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FqkNgrw7CWd59rdCHkpqH5","type":"tool_result","content":"first_release.csv 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4\nRSAFS_current.csv 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f\nUMCSENT.csv 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46\nvintages/PAYEMS_vintage_2025-10-31.csv d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60\nvintages/PAYEMS_vintage_2025-11-30.csv a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77\nvintages/PAYEMS_vintage_2025-12-31.csv 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031\nvintages/PAYEMS_vintage_2026-01-31.csv 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7\nvintages/PAYEMS_vintage_2026-02-28.csv 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3\nvintages/PAYEMS_vintage_2026-03-31.csv 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e\nvintages/PAYEMS_vintage_2026-04-30.csv 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a\nvintages/PAYEMS_vintage_2026-05-31.csv e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d\nvintages/PAYEMS_vintage_2026-06-30.csv 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a\nvintages/PAYEMS_vintage_2026-07-31.csv 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41\nvintages/RSAFS_vintage_2025-10-31.csv 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36\nvintages/RSAFS_vintage_2025-11-30.csv 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4\nvintages/RSAFS_vintage_2025-12-31.csv 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd\nvintages/RSAFS_vintage_2026-01-31.csv b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e\nvintages/RSAFS_vintage_2026-02-28.csv 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77\nvintages/RSAFS_vintage_2026-03-31.csv 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f\nvintages/RSAFS_vintage_2026-04-30.csv 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f\nvintages/RSAFS_vintage_2026-05-31.csv 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b\nvintages/RSAFS_vintage_2026-06-30.csv 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524\nvintages/RSAFS_vintage_2026-07-31.csv 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2\nRSAFS_current.csv (417, 2) 1992-01-01 2026-09-01 na 0 dup 0 []\nUMCSENT.csv (887, 2) 1952-11-01 2026-09-01 na 210 dup 0 1977-12-01\nfirst_release.csv (28, 5) 2024-06-01 2026-09-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2025-10-31.csv (1040, 2) 1939-01-01 2025-08-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2025-11-30.csv (1041, 2) 1939-01-01 2025-09-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2025-12-31.csv (1043, 2) 1939-01-01 2025-11-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-01-31.csv (1044, 2) 1939-01-01 2025-12-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-02-28.csv (1045, 2) 1939-01-01 2026-01-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-03-31.csv (1046, 2) 1939-01-01 2026-02-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-04-30.csv (1047, 2) 1939-01-01 2026-03-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-05-31.csv (1048, 2) 1939-01-01 2026-04-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-06-30.csv (1049, 2) 1939-01-01 2026-05-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-07-31.csv (1050, 2) 1939-01-01 2026-06-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2025-10-31.csv (404, 2) 1992-01-01 2025-08-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2025-11-30.csv (405, 2) 1992-01-01 2025-09-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2025-12-31.csv (406, 2) 1992-01-01 2025-10-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-01-31.csv (407, 2) 1992-01-01 2025-11-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-02-28.csv (408, 2) 1992-01-01 2025-12-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-03-31.csv (409, 2) 1992-01-01 2026-01-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-04-30.csv (411, 2) 1992-01-01 2026-03-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-05-31.csv (412, 2) 1992-01-01 2026-04-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-06-30.csv (413, 2) 1992-01-01 2026-05-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-07-31.csv (414, 2) 1992-01-01 2026-06-01 na 0 dup 0 []","is_error":false}]},"uuid":"50510f48-f0cb-42df-8a36-e453106e64c0","timestamp":"2026-10-30T05:34:01.116Z","toolUseResult":{"stdout":"first_release.csv 1d1ae8b3cacf7799aaefc7e0a969b3886e7979c36fce02ccf77d7c79fb7343e4\nRSAFS_current.csv 627d8bb386ac80f4aede3a9496b63040df584875fb766d455b08ebd84311468f\nUMCSENT.csv 3076277f9f21f4bd3dc77fd68add84d417e5cce23f3adb96dc70313b3ad2dd46\nvintages/PAYEMS_vintage_2025-10-31.csv d4b4c909ed321fbf8021c385beb1512ac000009e22bb20bc27c791a248d33c60\nvintages/PAYEMS_vintage_2025-11-30.csv a05ef7fc50cfc339207788f9d4205a619717bc44a335488d7790ae823bdb7b77\nvintages/PAYEMS_vintage_2025-12-31.csv 829dae087af61916e87994220a3e5ebf5853fa43cc163b3798715603ec8bb031\nvintages/PAYEMS_vintage_2026-01-31.csv 8fd01c5d2740e869458721a66b81bb2e247085e1e60cb93f3cb06bedf01885d7\nvintages/PAYEMS_vintage_2026-02-28.csv 4a913e67ac5ffbb4d127f03f6f10ce0647998779629579617dabf1344d072db3\nvintages/PAYEMS_vintage_2026-03-31.csv 919de86b07be90466e19844b54482ef8a3f6c8da7f9fe2a3ef3af0d02923c92e\nvintages/PAYEMS_vintage_2026-04-30.csv 06a8d663d9aaa61c6d5bda15d2893b10fd127b1d64fa16d47335341f62431c7a\nvintages/PAYEMS_vintage_2026-05-31.csv e2a152e874139acdebfc1715ffff9c1e5320f639f1443fff976b389724a5932d\nvintages/PAYEMS_vintage_2026-06-30.csv 19fbc6cd3547ffad1e22f32ac76f91758859804654b77622a4f42eac2d4e286a\nvintages/PAYEMS_vintage_2026-07-31.csv 3a3a6603fcc31c6eb2ee3293143888ab3440bbe3a962565eb39711b92019df41\nvintages/RSAFS_vintage_2025-10-31.csv 3ecb0832a391e7261145af41a7a951f823df3a08d476162721022a0922d37e36\nvintages/RSAFS_vintage_2025-11-30.csv 4a683d85374690f1e73d66c4f890156d0d32cd8b27d5d67b72582b9a0dd825a4\nvintages/RSAFS_vintage_2025-12-31.csv 436df4b5509b1dfe61ea11b8f98dce27f012ff6b0255eb194eea564ad7e880dd\nvintages/RSAFS_vintage_2026-01-31.csv b92ab6a5c1dbdc5653e85c56fdb7dc0646f1fca7227ed6e64f1424e17446aa9e\nvintages/RSAFS_vintage_2026-02-28.csv 2af0a3aaeeba81efddb2613d326e3f96b5a1c88c41eb30ad384ab3cc4b289a77\nvintages/RSAFS_vintage_2026-03-31.csv 0316fdf238d55d9f109b0be85e8c2d2eb00aee57016c0328d39405b349a8815f\nvintages/RSAFS_vintage_2026-04-30.csv 02dcc697a1db34753194974b1481dbd6a3ffcfe333864850e5ddd0e3202d2b8f\nvintages/RSAFS_vintage_2026-05-31.csv 8c3fe3530213589635ad6bb086f78ed613c459bf435c4558a5c51c597e19d87b\nvintages/RSAFS_vintage_2026-06-30.csv 2f103157f4a9b7a3c90c63af2033b9570d5e334205878714bbd35c8b304d7524\nvintages/RSAFS_vintage_2026-07-31.csv 52c04a8fce2effa727f3ef267eaee04e13aef20f8aaabc982277d08fc5b8e5b2\nRSAFS_current.csv (417, 2) 1992-01-01 2026-09-01 na 0 dup 0 []\nUMCSENT.csv (887, 2) 1952-11-01 2026-09-01 na 210 dup 0 1977-12-01\nfirst_release.csv (28, 5) 2024-06-01 2026-09-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2025-10-31.csv (1040, 2) 1939-01-01 2025-08-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2025-11-30.csv (1041, 2) 1939-01-01 2025-09-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2025-12-31.csv (1043, 2) 1939-01-01 2025-11-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-01-31.csv (1044, 2) 1939-01-01 2025-12-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-02-28.csv (1045, 2) 1939-01-01 2026-01-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-03-31.csv (1046, 2) 1939-01-01 2026-02-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-04-30.csv (1047, 2) 1939-01-01 2026-03-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-05-31.csv (1048, 2) 1939-01-01 2026-04-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-06-30.csv (1049, 2) 1939-01-01 2026-05-01 na 0 dup 0 []\nvintages/PAYEMS_vintage_2026-07-31.csv (1050, 2) 1939-01-01 2026-06-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2025-10-31.csv (404, 2) 1992-01-01 2025-08-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2025-11-30.csv (405, 2) 1992-01-01 2025-09-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2025-12-31.csv (406, 2) 1992-01-01 2025-10-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-01-31.csv (407, 2) 1992-01-01 2025-11-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-02-28.csv (408, 2) 1992-01-01 2025-12-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-03-31.csv (409, 2) 1992-01-01 2026-01-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-04-30.csv (411, 2) 1992-01-01 2026-03-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-05-31.csv (412, 2) 1992-01-01 2026-04-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-06-30.csv (413, 2) 1992-01-01 2026-05-01 na 0 dup 0 []\nvintages/RSAFS_vintage_2026-07-31.csv (414, 2) 1992-01-01 2026-06-01 na 0 dup 0 []","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"029d94b4-588a-4cb7-8783-cedc2f744274","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}33{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"cf6c5cd61e7a4756bd830ccaa80433642af13ca5fd3a031ee2c5b6905b36c3e7","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01FqkNgrw7CWd59rdCHkpqH5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; mkdir -p out/state; cd data && shasum -a 256 *.csv vintages/*.csv | awk '{print $2, $1}' && ~/wp29/venv/bin/python -c \"\nimport pandas as pd,glob\nfor f in sorted(glob.glob('*.csv')+glob.glob('vintages/*.csv')):\n    d=pd.read_csv(f); c=d.columns[1]\n    print(f,d.shape,d.iloc[0,0],d.iloc[-1,0],'na',d[c].isna().sum(),'dup',d.iloc[:,0].duplicated().sum(), list(d.loc[d[c].isna(),d.columns[0]].tail(3)) if 'UMC' not in f else d.loc[d[c].isna(),'observation_date'].max())\n\""}}]}}34{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"a2c5bc87-fe2c-44ff-8ec5-9637778a949a","timestamp":"2026-10-30T05:34:01.121Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"76add7dd-88c7-442f-8caa-1e7d82ef9614","keep":8,"tail":["cf6c5cd61e7a4756bd830ccaa80433642af13ca5fd3a031ee2c5b6905b36c3e7","00e1991bdcfdba88647dc3c82c021b1e4fd8942f91fdf4c3d7052a7aa9cb7fd1"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"6f9e693ce77e2b3b8033691741265996a5af2287716ad77ec1bf620bc351ba36"}35{"parentUuid":"50510f48-f0cb-42df-8a36-e453106e64c0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsp1QenV4GjQjKAkBGo","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS/QkKEAgTGAI4AUIIdGhpbmtpbmcSDLfjN4Hv6Fqv2LGqNBoMDuppR+WXFVUNW8FqIjD6tGqcXuaRsLwJbqfJMbf5fY2DYBnbedG+haXojdC/mo4tyyo+R9T5mj/6CWSnXjMqmgnB56rI+rNuUek4KSIsyeaR4Lc+YTxZoqA/tW+A5oFRj4sY25E90/0MuCq+N9FqBLSl9wtYzQJQgvFsMYSwEiPtLjbaIMlZYjQswep5zKKTNnir/U0X5IPQCBDbgCv38DB9yrkCAZWzrmdnQ1trQsgj2O0eHN8DDZtmiOGYW5Dl8LHYpgL+xjJNtZu/SbNzJg7+nzUnsXpLmMT4z5Z8Zt/sqKV+fBSbO9qTDQs9KuLiXD3nVALlGNhgjaStHdMq4MEBvuXvMbnVnF9TSDgCY+PGmo0cOqSYtKvyQ3jKZIInDsZ8TUgTH7kRbxKUZoyASQ71Xt9M9PvUGaaX2ZNMIycoicYAXezsonzpJMlJsoMfsAHD+sZFmCosV3gcSmLb+yTcJi0YE5TJUXbqnX7C3T/T18omk+JxbjXVFxmR2TQodZkAe+Zn+f3xULDr1h10ZlJXhfvlvOxqZVPTyM52Ymu2LSe2s/auV8AtXN676E+ftmVO7Pt7tHEg9pThwUibc1uffg0afv6v575SREWiv9PENSAePX03lQCd9TegeSxNe6B8MpvmxopqWPT8BjGBqulLROTVkl+wrBv3eGWF/0EGiSGP35Yd3AIkyj81mQTdbujhy9UkJi8fy1Xws+zyr8OoE8KJ9QRE8jDlnQr4cExvcP6Hw4sqn/7BeJKk+HYwfuvf7SEi7anci6gdQQozJcqjITYkkXyI9yLSuwEs51VlLKxva357Frm4/sY+6l7ZimR/n7++qCFIpjzvXLCZtQ7vEfS6/cYNzP5z8Awzs8ZCC+BGrAlTydA07Cq8St2epCMguFf2WcsXnLH3RILETXZH02zCRms20nRrNUVIp6XJAGd2sp1DRimaumN6wLdgwOu+ROWjdo/3aVnO0A5Ub3fvtBixuXQay1BZz0jUNhDzZn1o95m+6H1om+82rcMOq4VIxbu2Wr00M5G/NfRKy+9jhG3GYzCErvu8j5asWeAe++nXcha0Qjyi2eIO6h3KYTnUyPtUyLnt/uvmwLonX0xzLSxhUd3u8e+Pi/I5ycYNJIX0uXzZeCVtRUav9YsEwUZBWq9bceJYOqkVpkJ35dX6NzZPwQ5Whojb21a8j7/0zQJimH57UyY3Q8zqt6YK+iKaI7KDOOXThwXQIN8uG9NfNiRkjYliKuyPdh0C9kS5CJOVurMTE6HbC05Q0ej0fnhiBU/Vqp36iB+QMxaCZ4DuUPmv75Fm9JHJS7m8V1SeEAxDHh9JuWloSFQrthj6TCCv5ezZnmT9UH11qx3NLFHpr+FT1Wjbx2J5jW1p+DhFkj12/q4zQd0hLQU+l1jUNKPTelt1ITzFk4rfzUPOQtX6vPI6zOYFn9Fo/y7MJHVHkyo+TIyaD8nqZlrhoO3RSJoyMg609nwpNkiPm8r+1HIKRTqfQZGS4vFaPt5G5ilu0L0sFqgtnU1hUlA2QjNysxwVOKvuEvUiQm47xAcfQmVnd1/vOa3t2OsTj2meE+txHZf11G1X9kMnfqJNqjqq5Q2zSkrMLh2lWWTHCnWJ2bO7+dPxuNuB2IFoVh+hccvlvpNWqy5S3VUHyxgB"}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3085,"cache_read_input_tokens":16919,"output_tokens":977,"output_tokens_details":{"thinking_tokens":222},"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":3085},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1687,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsp18HXurjs34KiCkW8","requestRef":"a2c5bc87-fe2c-44ff-8ec5-9637778a949a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"16d77307-8019-4ece-8341-dcacd1d59ab1","timestamp":"2026-10-30T05:34:03.917Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}36{"parentUuid":"16d77307-8019-4ece-8341-dcacd1d59ab1","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsp1QenV4GjQjKAkBGo","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DGLMNR2NPcvc9G7ESti36C","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np,glob\nfr=pd.read_csv('data/first_release.csv',parse_dates=['target_month']).set_index('target_month')\n# recompute yoy\nprint('fr yoy maxdiff',(100*np.log(fr.level_first_release/fr.level_prev_year_same_vintage)-fr.yoy_first_release).abs().max())\nfor f in sorted(glob.glob('data/vintages/*.csv')):\n    d=pd.read_csv(f,parse_dates=['observation_date']).set_index('observation_date').iloc[:,0]\n    full=pd.date_range(d.index[0],d.index[-1],freq='MS'); gaps=len(full)-len(d)\n    msg=''\n    if 'RSAFS' in f:\n        V=f[-14:-4]; L=d.index[-1]\n        if L in fr.index:\n            r=fr.loc[L]; msg=f'fr_vint={r.first_release_vintage} lvl_match={d.iloc[-1]==r.level_first_release} prev_match={d.loc[L-pd.DateOffset(years=1)]==r.level_prev_year_same_vintage}'\n    print(f[-30:],'gaps',gaps,'min',d.min(),msg)\nu=pd.read_csv('data/UMCSENT.csv',parse_dates=['observation_date']).set_index('observation_date').UMCSENT\nprint('umc na after 1978:',u['1978':].isna().sum(), u['2025-06':].values)\nc=pd.read_csv('data/RSAFS_current.csv',parse_dates=['observation_date']).set_index('observation_date').RSAFS\nprint(c['2025-06':].to_string())\nv=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',parse_dates=['observation_date']).set_index('observation_date').iloc[:,0]\nprint((v['2024-01':]).to_string())\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3085,"cache_read_input_tokens":16919,"output_tokens":977,"output_tokens_details":{"thinking_tokens":222},"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":3085},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsp18HXurjs34KiCkW8","requestRef":"a2c5bc87-fe2c-44ff-8ec5-9637778a949a","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c3338aab-5ceb-4b36-a9de-ea281f744c05","timestamp":"2026-10-30T05:34:09.761Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/data","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}37{"parentUuid":"c3338aab-5ceb-4b36-a9de-ea281f744c05","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01DGLMNR2NPcvc9G7ESti36C","type":"tool_result","content":"fr yoy maxdiff 4.656392009749766e-07\n/PAYEMS_vintage_2025-10-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2025-11-30.csv gaps 0 min 29923 \n/PAYEMS_vintage_2025-12-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-01-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-02-28.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-03-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-04-30.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-05-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-06-30.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-07-31.csv gaps 0 min 29923 \ns/RSAFS_vintage_2025-10-31.csv gaps 0 min 158647 fr_vint=2025-09-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2025-11-30.csv gaps 0 min 158647 fr_vint=2025-11-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2025-12-31.csv gaps 0 min 158647 fr_vint=2025-12-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-01-31.csv gaps 0 min 158647 fr_vint=2026-01-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-02-28.csv gaps 0 min 158647 fr_vint=2026-02-28 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-03-31.csv gaps 0 min 158647 fr_vint=2026-03-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-04-30.csv gaps 0 min 158647 fr_vint=2026-04-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-05-31.csv gaps 0 min 158647 fr_vint=2026-05-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-06-30.csv gaps 0 min 158647 fr_vint=2026-06-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-07-31.csv gaps 0 min 158647 fr_vint=2026-07-31 lvl_match=True prev_match=True\numc na after 1978: 0 [60.7 61.7 58.2 55.1 53.6 51.  52.9 56.4 56.6 53.3 49.8 44.8 49.5 55.2\n 51.7 48.1]\nobservation_date\n2025-06-01    691883\n2025-07-01    698280\n2025-08-01    700407\n2025-09-01    700948\n2025-10-01    700790\n2025-11-01    705453\n2025-12-01    706264\n2026-01-01    701860\n2026-02-01    707959\n2026-03-01    719700\n2026-04-01    723921\n2026-05-01    731415\n2026-06-01    732898\n2026-07-01    729915\n2026-08-01    739322\n2026-09-01    745021\nobservation_date\n2024-01-01    680456\n2024-02-01    685280\n2024-03-01    687641\n2024-04-01    687602\n2024-05-01    692774\n2024-06-01    692449\n2024-07-01    698835\n2024-08-01    697039\n2024-09-01    703055\n2024-10-01    708290\n2024-11-01    711853\n2024-12-01    717265\n2025-01-01    711260\n2025-02-01    711575\n2025-03-01    723339\n2025-04-01    722442\n2025-05-01    714513\n2025-06-01    720164\n2025-07-01    727727\n2025-08-01    731700\n2025-09-01    732192\n2025-10-01    731051\n2025-11-01    734718\n2025-12-01    734717\n2026-01-01    734503\n2026-02-01    741278\n2026-03-01    754013\n2026-04-01    759097\n2026-05-01    766876\n2026-06-01    768553","is_error":false}]},"uuid":"eb99bc5d-d186-41e3-a76d-2b81e3d0e0b4","timestamp":"2026-10-30T05:34:10.130Z","toolUseResult":{"stdout":"fr yoy maxdiff 4.656392009749766e-07\n/PAYEMS_vintage_2025-10-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2025-11-30.csv gaps 0 min 29923 \n/PAYEMS_vintage_2025-12-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-01-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-02-28.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-03-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-04-30.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-05-31.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-06-30.csv gaps 0 min 29923 \n/PAYEMS_vintage_2026-07-31.csv gaps 0 min 29923 \ns/RSAFS_vintage_2025-10-31.csv gaps 0 min 158647 fr_vint=2025-09-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2025-11-30.csv gaps 0 min 158647 fr_vint=2025-11-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2025-12-31.csv gaps 0 min 158647 fr_vint=2025-12-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-01-31.csv gaps 0 min 158647 fr_vint=2026-01-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-02-28.csv gaps 0 min 158647 fr_vint=2026-02-28 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-03-31.csv gaps 0 min 158647 fr_vint=2026-03-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-04-30.csv gaps 0 min 158647 fr_vint=2026-04-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-05-31.csv gaps 0 min 158647 fr_vint=2026-05-31 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-06-30.csv gaps 0 min 158647 fr_vint=2026-06-30 lvl_match=True prev_match=True\ns/RSAFS_vintage_2026-07-31.csv gaps 0 min 158647 fr_vint=2026-07-31 lvl_match=True prev_match=True\numc na after 1978: 0 [60.7 61.7 58.2 55.1 53.6 51.  52.9 56.4 56.6 53.3 49.8 44.8 49.5 55.2\n 51.7 48.1]\nobservation_date\n2025-06-01    691883\n2025-07-01    698280\n2025-08-01    700407\n2025-09-01    700948\n2025-10-01    700790\n2025-11-01    705453\n2025-12-01    706264\n2026-01-01    701860\n2026-02-01    707959\n2026-03-01    719700\n2026-04-01    723921\n2026-05-01    731415\n2026-06-01    732898\n2026-07-01    729915\n2026-08-01    739322\n2026-09-01    745021\nobservation_date\n2024-01-01    680456\n2024-02-01    685280\n2024-03-01    687641\n2024-04-01    687602\n2024-05-01    692774\n2024-06-01    692449\n2024-07-01    698835\n2024-08-01    697039\n2024-09-01    703055\n2024-10-01    708290\n2024-11-01    711853\n2024-12-01    717265\n2025-01-01    711260\n2025-02-01    711575\n2025-03-01    723339\n2025-04-01    722442\n2025-05-01    714513\n2025-06-01    720164\n2025-07-01    727727\n2025-08-01    731700\n2025-09-01    732192\n2025-10-01    731051\n2025-11-01    734718\n2025-12-01    734717\n2026-01-01    734503\n2026-02-01    741278\n2026-03-01    754013\n2026-04-01    759097\n2026-05-01    766876\n2026-06-01    768553","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"c3338aab-5ceb-4b36-a9de-ea281f744c05","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}38{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"bbe62a645d0fc14ed3f98d1de330924de6394650b08c498b98a5d80a803f814c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01DGLMNR2NPcvc9G7ESti36C","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np,glob\nfr=pd.read_csv('data/first_release.csv',parse_dates=['target_month']).set_index('target_month')\n# recompute yoy\nprint('fr yoy maxdiff',(100*np.log(fr.level_first_release/fr.level_prev_year_same_vintage)-fr.yoy_first_release).abs().max())\nfor f in sorted(glob.glob('data/vintages/*.csv')):\n    d=pd.read_csv(f,parse_dates=['observation_date']).set_index('observation_date').iloc[:,0]\n    full=pd.date_range(d.index[0],d.index[-1],freq='MS'); gaps=len(full)-len(d)\n    msg=''\n    if 'RSAFS' in f:\n        V=f[-14:-4]; L=d.index[-1]\n        if L in fr.index:\n            r=fr.loc[L]; msg=f'fr_vint={r.first_release_vintage} lvl_match={d.iloc[-1]==r.level_first_release} prev_match={d.loc[L-pd.DateOffset(years=1)]==r.level_prev_year_same_vintage}'\n    print(f[-30:],'gaps',gaps,'min',d.min(),msg)\nu=pd.read_csv('data/UMCSENT.csv',parse_dates=['observation_date']).set_index('observation_date').UMCSENT\nprint('umc na after 1978:',u['1978':].isna().sum(), u['2025-06':].values)\nc=pd.read_csv('data/RSAFS_current.csv',parse_dates=['observation_date']).set_index('observation_date').RSAFS\nprint(c['2025-06':].to_string())\nv=pd.read_csv('data/vintages/RSAFS_vintage_2026-07-31.csv',parse_dates=['observation_date']).set_index('observation_date').iloc[:,0]\nprint((v['2024-01':]).to_string())\n\""}}]}}39{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"c43e9a25-96ba-4091-862c-82cdea92b8a8","timestamp":"2026-10-30T05:34:10.133Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"a2c5bc87-fe2c-44ff-8ec5-9637778a949a","keep":10,"tail":["bbe62a645d0fc14ed3f98d1de330924de6394650b08c498b98a5d80a803f814c","f5016a304197e5c70027fc984264a15190b9c194237d4c703e68a5c7c00f1b98"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"a2fbefd8e62e5a3936ed9378e34e4e2b5568bc18b538a721a067af14e4139833"}40{"parentUuid":"eb99bc5d-d186-41e3-a76d-2b81e3d0e0b4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspfvtodYJEGDRW9ZQP","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":2470,"cache_read_input_tokens":20004,"output_tokens":3327,"output_tokens_details":{"thinking_tokens":2047},"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":2470},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":22267,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXspfe2oXHnHBvWSjExT","requestRef":"c43e9a25-96ba-4091-862c-82cdea92b8a8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"731cec9e-bbc2-4bc4-a90d-2696bea88e75","timestamp":"2026-10-30T05:34:33.476Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}41{"parentUuid":"731cec9e-bbc2-4bc4-a90d-2696bea88e75","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXspfvtodYJEGDRW9ZQP","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01FRSFxuhghXv1NFkbNKYNbs","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out/state; cat > contract.md <<'EOF'\n# Contract — T1-forecast (restated)\n\n**Question.** Using only data published at each of 10 month-end forecast origins (2025-10-31 … 2026-07-31), how accurately can US retail & food services sales (RSAFS) year-over-year log growth g_m = 100·ln(L_m/L_{m-12}) be forecast h=1 and h=3 months beyond the last published month last(V), when judged against the first-release YoY value of the target month? Does a model of my own design beat the naive (no-change) forecast?\n\n**Estimands** (h ∈ {1,3}, n = 10 origins each):\n(a) RMSE and MAE vs first release for naive, seasonal naive, AR(1), and my model;\n(b) 1 − RMSE_model/RMSE_naive;\n(c) DM stat (model vs naive, squared loss, d_t = e²_naive − e²_model, Bartlett LRV with truncation lag h−1, no HLN correction, N(0,1) two-sided p);\n(d) mean |g^current_T − yoy_first_release_T| over the 10 h=1 target months.\nAssumptions: first release is the relevant \"truth\"; 10 origins is a tiny sample, so DM asymptotic normality is only a rough approximation; the loss differential must be covariance-stationary for DM to be meaningful.\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (keys listed in TASK.md: task_id, model_name, model_description, n_origins, first_origin, last_origin, rmse/mae × {naive,snaive,ar1,model} × {h1,h3}, rel_improvement_rmse_h1/h3, dm_stat/pvalue h1/h3, conclusion_code_h1/h3, mean_abs_revision_h1_targets, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/table1.csv, out/figure1.png, out/report.md, out/analysis.py, out/claims.json; plus protocol files in out/state, out/exclusions.csv.\n\n**Information rules.** At origin V: only RSAFS vintage V, PAYEMS vintage V, UMCSENT months ≤ month(V). Target = last(V)+h where last(V) = last month in RSAFS vintage V (not calendar). Actual = yoy_first_release. RSAFS_current only for (d), never in a forecast. Model selection must also respect the rule (no tuning on evaluation outcomes).\n\n**Invalidity / impossibility.** Missing target months in first_release.csv; vintage files not matching origins; any use of RSAFS_current or post-origin data in forecasts; choosing the model by its out-of-sample performance over these same 10 origins (would be look-ahead).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"pending\",\"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\necho \"- 2026-10-30 P0 passed: contract written. Fresh workspace (no prior out/).\" > log.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2470,"cache_read_input_tokens":20004,"output_tokens":3327,"output_tokens_details":{"thinking_tokens":2047},"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":2470},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXspfe2oXHnHBvWSjExT","requestRef":"c43e9a25-96ba-4091-862c-82cdea92b8a8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d15282a5-7e7b-43bc-9165-6ec8bf291955","timestamp":"2026-10-30T05:34:43.399Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}42{"parentUuid":"d15282a5-7e7b-43bc-9165-6ec8bf291955","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01FRSFxuhghXv1NFkbNKYNbs","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"f28da6c2-b2d1-4d81-a6e8-ae9023b6be70","timestamp":"2026-10-30T05:34:43.449Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d15282a5-7e7b-43bc-9165-6ec8bf291955","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out/state","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}43{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"ce8cfb31cff1938e1b2f7fcd7eb857c8bd0c39801ceeba4acae99cbf461be8aa","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01FRSFxuhghXv1NFkbNKYNbs","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out/state; cat > contract.md <<'EOF'\n# Contract — T1-forecast (restated)\n\n**Question.** Using only data published at each of 10 month-end forecast origins (2025-10-31 … 2026-07-31), how accurately can US retail & food services sales (RSAFS) year-over-year log growth g_m = 100·ln(L_m/L_{m-12}) be forecast h=1 and h=3 months beyond the last published month last(V), when judged against the first-release YoY value of the target month? Does a model of my own design beat the naive (no-change) forecast?\n\n**Estimands** (h ∈ {1,3}, n = 10 origins each):\n(a) RMSE and MAE vs first release for naive, seasonal naive, AR(1), and my model;\n(b) 1 − RMSE_model/RMSE_naive;\n(c) DM stat (model vs naive, squared loss, d_t = e²_naive − e²_model, Bartlett LRV with truncation lag h−1, no HLN correction, N(0,1) two-sided p);\n(d) mean |g^current_T − yoy_first_release_T| over the 10 h=1 target months.\nAssumptions: first release is the relevant \"truth\"; 10 origins is a tiny sample, so DM asymptotic normality is only a rough approximation; the loss differential must be covariance-stationary for DM to be meaningful.\n\n**Outputs.** out/forecasts.csv (80 rows; origin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used), out/results.json (keys listed in TASK.md: task_id, model_name, model_description, n_origins, first_origin, last_origin, rmse/mae × {naive,snaive,ar1,model} × {h1,h3}, rel_improvement_rmse_h1/h3, dm_stat/pvalue h1/h3, conclusion_code_h1/h3, mean_abs_revision_h1_targets, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/table1.csv, out/figure1.png, out/report.md, out/analysis.py, out/claims.json; plus protocol files in out/state, out/exclusions.csv.\n\n**Information rules.** At origin V: only RSAFS vintage V, PAYEMS vintage V, UMCSENT months ≤ month(V). Target = last(V)+h where last(V) = last month in RSAFS vintage V (not calendar). Actual = yoy_first_release. RSAFS_current only for (d), never in a forecast. Model selection must also respect the rule (no tuning on evaluation outcomes).\n\n**Invalidity / impossibility.** Missing target months in first_release.csv; vintage files not matching origins; any use of RSAFS_current or post-origin data in forecasts; choosing the model by its out-of-sample performance over these same 10 origins (would be look-ahead).\nEOF\ncat > phases.json <<'EOF'\n{\"P0\":{\"status\":\"passed\",\"checks\":[\"TASK.md read fully\",\"contract.md written\"],\"notes\":\"\"},\n \"P1\":{\"status\":\"pending\",\"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\necho \"- 2026-10-30 P0 passed: contract written. Fresh workspace (no prior out/).\" > log.md"}}]}}44{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"775a85a2-f035-48a0-84bc-97beeb22f2cc","timestamp":"2026-10-30T05:34:43.454Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"c43e9a25-96ba-4091-862c-82cdea92b8a8","keep":12,"tail":["ce8cfb31cff1938e1b2f7fcd7eb857c8bd0c39801ceeba4acae99cbf461be8aa","3301f5f2d8e9c4de0348d41f22fae8434f93c0014f137d4cc40e6aa9088a4be3"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"801500b7e21bba2bc2b8d8f8b3f1b8064e37800d132f6de98bc7446bbf5d0d60"}45{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"f28da6c2-b2d1-4d81-a6e8-ae9023b6be70","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}46{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}47{"parentUuid":"f28da6c2-b2d1-4d81-a6e8-ae9023b6be70","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXss8PvVd7CECP3R4owc","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":3342,"cache_read_input_tokens":22474,"output_tokens":503,"output_tokens_details":{"thinking_tokens":154},"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":3342},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1042,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXss87JqTipGcxn5Zxky","requestRef":"775a85a2-f035-48a0-84bc-97beeb22f2cc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9d9d798a-48d5-43f0-aec1-388b17a3bd71","timestamp":"2026-10-30T05:34:45.753Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out/state","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}48{"parentUuid":"9d9d798a-48d5-43f0-aec1-388b17a3bd71","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXss8PvVd7CECP3R4owc","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WAKACxMYPmZTag84hwCd3q","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nfr=pd.read_csv('data/first_release.csv',parse_dates=['target_month']).set_index('target_month')\nc=pd.read_csv('data/RSAFS_current.csv',parse_dates=['observation_date']).set_index('observation_date').RSAFS\nfr['cur_prev']=[c[t-pd.DateOffset(years=1)] for t in fr.index]; fr['cur_lvl']=[c[t] for t in fr.index]\nfr['gcur']=100*np.log(fr.cur_lvl/fr.cur_prev)\nprint(fr[['first_release_vintage','level_prev_year_same_vintage','cur_prev','yoy_first_release','gcur']].tail(14))\n\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3342,"cache_read_input_tokens":22474,"output_tokens":503,"output_tokens_details":{"thinking_tokens":154},"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":3342},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXss87JqTipGcxn5Zxky","requestRef":"775a85a2-f035-48a0-84bc-97beeb22f2cc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"43c1beb1-2290-4231-8320-82b0a686a35b","timestamp":"2026-10-30T05:34:47.981Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out/state","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}49{"parentUuid":"43c1beb1-2290-4231-8320-82b0a686a35b","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WAKACxMYPmZTag84hwCd3q","type":"tool_result","content":"             first_release_vintage  ...      gcur\ntarget_month                        ...          \n2025-08-01              2025-09-30  ...  4.338736\n2025-09-01              2025-11-30  ...  3.623323\n2025-10-01              2025-12-31  ...  2.746018\n2025-11-01              2026-01-31  ...  2.838681\n2025-12-01              2026-02-28  ...  2.070088\n2026-01-01              2026-03-31  ...  2.131524\n2026-02-01              2026-04-30  ...  3.476165\n2026-03-01              2026-04-30  ...  3.528239\n2026-04-01              2026-05-31  ...  4.010302\n2026-05-01              2026-06-30  ...  6.485002\n2026-06-01              2026-07-31  ...  5.758967\n2026-07-01              2026-08-31  ...  4.430792\n2026-08-01              2026-09-30  ...  5.407196\n2026-09-01              2026-10-29  ...  6.097870\n\n[14 rows x 5 columns]","is_error":false}]},"uuid":"90d0e43b-26b0-4fd6-b3da-fca670efd558","timestamp":"2026-10-30T05:34:48.314Z","toolUseResult":{"stdout":"             first_release_vintage  ...      gcur\ntarget_month                        ...          \n2025-08-01              2025-09-30  ...  4.338736\n2025-09-01              2025-11-30  ...  3.623323\n2025-10-01              2025-12-31  ...  2.746018\n2025-11-01              2026-01-31  ...  2.838681\n2025-12-01              2026-02-28  ...  2.070088\n2026-01-01              2026-03-31  ...  2.131524\n2026-02-01              2026-04-30  ...  3.476165\n2026-03-01              2026-04-30  ...  3.528239\n2026-04-01              2026-05-31  ...  4.010302\n2026-05-01              2026-06-30  ...  6.485002\n2026-06-01              2026-07-31  ...  5.758967\n2026-07-01              2026-08-31  ...  4.430792\n2026-08-01              2026-09-30  ...  5.407196\n2026-09-01              2026-10-29  ...  6.097870\n\n[14 rows x 5 columns]","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"43c1beb1-2290-4231-8320-82b0a686a35b","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}50{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"6374af682e5349e0d400f81348f0e55cfca08a603be5432c55868f69f6cbf6d1","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WAKACxMYPmZTag84hwCd3q","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python -c \"\nimport pandas as pd,numpy as np\nfr=pd.read_csv('data/first_release.csv',parse_dates=['target_month']).set_index('target_month')\nc=pd.read_csv('data/RSAFS_current.csv',parse_dates=['observation_date']).set_index('observation_date').RSAFS\nfr['cur_prev']=[c[t-pd.DateOffset(years=1)] for t in fr.index]; fr['cur_lvl']=[c[t] for t in fr.index]\nfr['gcur']=100*np.log(fr.cur_lvl/fr.cur_prev)\nprint(fr[['first_release_vintage','level_prev_year_same_vintage','cur_prev','yoy_first_release','gcur']].tail(14))\n\""}}]}}51{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"451bae74-fe3b-46b3-9506-25921d052547","timestamp":"2026-10-30T05:34:48.318Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"775a85a2-f035-48a0-84bc-97beeb22f2cc","keep":14,"tail":["6374af682e5349e0d400f81348f0e55cfca08a603be5432c55868f69f6cbf6d1","e79635d904476a488d4589da7014142cd9d8b02e7c1ae8a877bdcf2bc0d9f53b"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"44878f8456f011646449de2dad71357e67bb239d219d2bbf4499b9011fd2aa9d"}52{"parentUuid":"90d0e43b-26b0-4fd6-b3da-fca670efd558","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXssVCKvVHV8EF8nqiS7","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":853,"cache_read_input_tokens":25816,"output_tokens":1955,"output_tokens_details":{"thinking_tokens":38},"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":853},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":487,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXssUuwqd1DayxMa9S3n","requestRef":"451bae74-fe3b-46b3-9506-25921d052547","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"1c878ea3-f51e-4021-8957-74f708832878","timestamp":"2026-10-30T05:34:49.657Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}53{"parentUuid":"1c878ea3-f51e-4021-8957-74f708832878","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXssVCKvVHV8EF8nqiS7","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011AKdmZXkjmaVTMDtnVf935","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out/state; cat > data_audit.md <<'EOF'\n# Data audit (P1) — 2026-10-30\n\nAll SHA-256 values computed with `shasum -a 256` match those in data/README.md exactly (24 CSV files). Row counts (data rows after header) also match README.\n\n| file | rows×cols | first | last | missing | dup dates |\n|---|---|---|---|---|---|\n| RSAFS_vintage_2025-10-31 | 404×2 | 1992-01 | **2025-08** | 0 | 0 |\n| RSAFS_vintage_2025-11-30 | 405×2 | 1992-01 | 2025-09 | 0 | 0 |\n| RSAFS_vintage_2025-12-31 | 406×2 | 1992-01 | 2025-10 | 0 | 0 |\n| RSAFS_vintage_2026-01-31 | 407×2 | 1992-01 | 2025-11 | 0 | 0 |\n| RSAFS_vintage_2026-02-28 | 408×2 | 1992-01 | 2025-12 | 0 | 0 |\n| RSAFS_vintage_2026-03-31 | 409×2 | 1992-01 | **2026-01** | 0 | 0 |\n| RSAFS_vintage_2026-04-30 | 411×2 | 1992-01 | 2026-03 (adds 2 months) | 0 | 0 |\n| RSAFS_vintage_2026-05-31 | 412×2 | 1992-01 | 2026-04 | 0 | 0 |\n| RSAFS_vintage_2026-06-30 | 413×2 | 1992-01 | 2026-05 | 0 | 0 |\n| RSAFS_vintage_2026-07-31 | 414×2 | 1992-01 | 2026-06 | 0 | 0 |\n| PAYEMS vintages (10) | 1040…1050×2 | 1939-01 | 2025-08 … 2026-06; vintage 2025-12-31 ends 2025-11 (two months added at once) | 0 | 0 |\n| UMCSENT.csv | 887×2 | 1952-11 | 2026-09 | 210 (all before 1978-01, quarterly survey era); none after | 0 |\n| RSAFS_current.csv | 417×2 | 1992-01 | 2026-09 | 0 | 0 |\n| first_release.csv | 28×5 | 2024-06 | 2026-09 | 0 | 0 |\n\nUnits: RSAFS millions USD SA; PAYEMS thousands SA; UMCSENT index 1966Q1=100. All monthly, no internal gaps in any series (checked against a full monthly date range).\n\n## Anomalies / findings\n1. **Irregular publication timing**: last(V) is two months before V for 2025-10-31 (last 2025-08) and 2026-03-31 (last 2026-01); vintage 2026-04-30 adds 2026-02 and 2026-03 at once. Handled per task rule: targets are last(V)+h, not calendar-based. Consequence: 2026-02 is never an h=1 target; some target months are shared (e.g. h=3 targets).\n2. **first_release.csv consistency**: recomputed 100·ln(level/prev) matches `yoy_first_release` to < 5e-7 (rounding). For each origin, the last row of the vintage equals `level_first_release` and the 12-month-earlier level equals `level_prev_year_same_vintage` whenever the first-release vintage equals V (checked; all 10 match). For origin 2025-10-31 (last=2025-08) the first-release vintage of 2025-08 is 2025-09-30, but levels still match.\n3. **Annual/benchmark revision of RSAFS levels**: RSAFS_current levels are ~4% lower than the 2026-07-31 vintage for 2025 months, and `level_prev_year_same_vintage` jumps between the target months 2026-07 (727176) and 2026-08 (700218) — a level rebasing occurred between the 2026-08-31 and 2026-09-30 vintages. The YoY of current data is systematically lower than first release (~0.3–0.8 pp). This affects h=3 targets 2026-08 and 2026-09 (first-released after the rebasing) and estimand (d). Handled: no adjustment (the task defines the actual as first release); documented.\n4. **PAYEMS** may extend beyond last(V) of RSAFS (e.g. V=2025-12-31: PAYEMS ends 2025-11, RSAFS 2025-10). Not used by my model (see decisions).\n5. **UMCSENT** is a current vintage; per README and TASK it is unrevised and the origin-month value is available at month-end. Not used by my model.\n\n## Availability-rule violations / handling\n- RSAFS_current.csv would violate the rule if used in forecasts → used only in the revision computation (estimand d), in a separate code block.\n- first_release.csv contains post-origin information → used only as evaluation actuals.\n- No other file violates the rules provided vintage V is used only at origin V (enforced in code by loading files by origin date).\nEOF\ncd ..; cat > exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_analysed_note_placeholder\nEOF\necho \"- 2026-10-30 P1: audit written; hashes match README; issues: publication delays, benchmark revision between 2026-08 and 2026-09 vintages.\" >> state/log.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":853,"cache_read_input_tokens":25816,"output_tokens":1955,"output_tokens_details":{"thinking_tokens":38},"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":853},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXssUuwqd1DayxMa9S3n","requestRef":"451bae74-fe3b-46b3-9506-25921d052547","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"b6f901bb-20ea-443c-ad9d-5bb215717d3c","timestamp":"2026-10-30T05:35:05.673Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}54{"parentUuid":"b6f901bb-20ea-443c-ad9d-5bb215717d3c","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011AKdmZXkjmaVTMDtnVf935","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"5a5d5ae5-8a07-45ca-92dd-8652620d897b","timestamp":"2026-10-30T05:35:05.731Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"b6f901bb-20ea-443c-ad9d-5bb215717d3c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}55{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"2670117a1546bb8db9355d2fc067bcb2334d12c298b4780b97483a10e92378ee","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS2AYKEAgTGAI4AUIIdGhpbmtpbmcSDPlRYlmxx6QHQZBeSBoMdMCOSAGe6w40nZjwIjDlvNC2mGf59UJ6VhLTEA62FbKgRwHq8/+Qw75MeM7vvtIwINsIQ3oTfSQb6E6A4V4q9QUJyXwYRLrQBH2Y4hT2d46F/aD0LrJFBIktjMmWqv0sib3bv36hfcw8AX7rAMKr8OYbLuGWgn2cj+Z0VfByXH8fpoAGPTiN+uM833k4wpUASW2lCg86ns1TgkPFHRoME3DxV0nW4pTmfwg/gQ1ecgYizFx7xfOXng30//cntzCEORT4JghZy/fK/lqihBAaZFO2+GDf1kLSwKg9Ntchm//v2uP+FP6GyYwd36Chg5XnnXR1TNK/coMyJCXoR095DBDzdR6720J+zh2MV478BGLMkVMQVwpmFZBnADVlQr4C5JwSuO+NVSda5InI/jbFT+Xa+2UQ5cN/LUM+AcRGdL0bcfaYcanhBaYOUiBNg3Xw738c8RIPnfgvmzLcBPA8ofy6ROgChXgX0t6gNNpv8ORd8paDOHxyIvCjCzOj/n5Zi44qh3dSLpJG5B8HFMIIDsCaE2/KKxtDKieczU7EfhviNswVmCXFM8QczdZvI7vu9qVqzJlRh9eXAksgpRx8Y34qPVwKAIsVKGx09jVK9I4eskYqa7fc3PCCTqzpv7cgVHlIiFbgtuqv8DqkjWgWYu823Aiu0F8jB54D62Lbr9WvlTuUUnUxXfqk+z2QtcAtp96833q70JtHHwPmDzdrGfeZ4uMJtxXb2fy7sxuLYlQTKRVnEvaUt2wJeCl0bQ6HCtk/QjxK4d6LXOD9Ii6q8elWhWw2lwcQ9b/lNLRtmB44x0Cb/TttGjMwNZkTQuhHj8lLxxqPKX06Tx1RJ0XyrNBwhE/U0pW8ntCi6jhHMOcpXmwtWbaY0oMoNtR/C18gTxkcbCFFbA1SFTN1QAksW60vX2BpjOcrVZIayfWuNkOwF7L7d/Wc8dByQ4sRr0o4w8fTbBClJGj/7J3mva14xIXTNqUOXap5MVGsFMjbYPGJvCvd751gdwHRmbKIOohhgBf5gHW75HW0DTND4j7LYLG4QKUs7BzlFVgf3idOa1Q2h+8+l6VpIPpIAnIyXG8+88Cb6l0zGAE="},{"type":"tool_use","id":"toolu_011AKdmZXkjmaVTMDtnVf935","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out/state; cat > data_audit.md <<'EOF'\n# Data audit (P1) — 2026-10-30\n\nAll SHA-256 values computed with `shasum -a 256` match those in data/README.md exactly (24 CSV files). Row counts (data rows after header) also match README.\n\n| file | rows×cols | first | last | missing | dup dates |\n|---|---|---|---|---|---|\n| RSAFS_vintage_2025-10-31 | 404×2 | 1992-01 | **2025-08** | 0 | 0 |\n| RSAFS_vintage_2025-11-30 | 405×2 | 1992-01 | 2025-09 | 0 | 0 |\n| RSAFS_vintage_2025-12-31 | 406×2 | 1992-01 | 2025-10 | 0 | 0 |\n| RSAFS_vintage_2026-01-31 | 407×2 | 1992-01 | 2025-11 | 0 | 0 |\n| RSAFS_vintage_2026-02-28 | 408×2 | 1992-01 | 2025-12 | 0 | 0 |\n| RSAFS_vintage_2026-03-31 | 409×2 | 1992-01 | **2026-01** | 0 | 0 |\n| RSAFS_vintage_2026-04-30 | 411×2 | 1992-01 | 2026-03 (adds 2 months) | 0 | 0 |\n| RSAFS_vintage_2026-05-31 | 412×2 | 1992-01 | 2026-04 | 0 | 0 |\n| RSAFS_vintage_2026-06-30 | 413×2 | 1992-01 | 2026-05 | 0 | 0 |\n| RSAFS_vintage_2026-07-31 | 414×2 | 1992-01 | 2026-06 | 0 | 0 |\n| PAYEMS vintages (10) | 1040…1050×2 | 1939-01 | 2025-08 … 2026-06; vintage 2025-12-31 ends 2025-11 (two months added at once) | 0 | 0 |\n| UMCSENT.csv | 887×2 | 1952-11 | 2026-09 | 210 (all before 1978-01, quarterly survey era); none after | 0 |\n| RSAFS_current.csv | 417×2 | 1992-01 | 2026-09 | 0 | 0 |\n| first_release.csv | 28×5 | 2024-06 | 2026-09 | 0 | 0 |\n\nUnits: RSAFS millions USD SA; PAYEMS thousands SA; UMCSENT index 1966Q1=100. All monthly, no internal gaps in any series (checked against a full monthly date range).\n\n## Anomalies / findings\n1. **Irregular publication timing**: last(V) is two months before V for 2025-10-31 (last 2025-08) and 2026-03-31 (last 2026-01); vintage 2026-04-30 adds 2026-02 and 2026-03 at once. Handled per task rule: targets are last(V)+h, not calendar-based. Consequence: 2026-02 is never an h=1 target; some target months are shared (e.g. h=3 targets).\n2. **first_release.csv consistency**: recomputed 100·ln(level/prev) matches `yoy_first_release` to < 5e-7 (rounding). For each origin, the last row of the vintage equals `level_first_release` and the 12-month-earlier level equals `level_prev_year_same_vintage` whenever the first-release vintage equals V (checked; all 10 match). For origin 2025-10-31 (last=2025-08) the first-release vintage of 2025-08 is 2025-09-30, but levels still match.\n3. **Annual/benchmark revision of RSAFS levels**: RSAFS_current levels are ~4% lower than the 2026-07-31 vintage for 2025 months, and `level_prev_year_same_vintage` jumps between the target months 2026-07 (727176) and 2026-08 (700218) — a level rebasing occurred between the 2026-08-31 and 2026-09-30 vintages. The YoY of current data is systematically lower than first release (~0.3–0.8 pp). This affects h=3 targets 2026-08 and 2026-09 (first-released after the rebasing) and estimand (d). Handled: no adjustment (the task defines the actual as first release); documented.\n4. **PAYEMS** may extend beyond last(V) of RSAFS (e.g. V=2025-12-31: PAYEMS ends 2025-11, RSAFS 2025-10). Not used by my model (see decisions).\n5. **UMCSENT** is a current vintage; per README and TASK it is unrevised and the origin-month value is available at month-end. Not used by my model.\n\n## Availability-rule violations / handling\n- RSAFS_current.csv would violate the rule if used in forecasts → used only in the revision computation (estimand d), in a separate code block.\n- first_release.csv contains post-origin information → used only as evaluation actuals.\n- No other file violates the rules provided vintage V is used only at origin V (enforced in code by loading files by origin date).\nEOF\ncd ..; cat > exclusions.csv <<'EOF'\nstep,rule,n_before,n_after,n_analysed_note_placeholder\nEOF\necho \"- 2026-10-30 P1: audit written; hashes match README; issues: publication delays, benchmark revision between 2026-08 and 2026-09 vintages.\" >> state/log.md"}}]}}56{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"6cdd643a-b8b0-4765-8996-8b961516dd55","timestamp":"2026-10-30T05:35:05.734Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"451bae74-fe3b-46b3-9506-25921d052547","keep":16,"tail":["2670117a1546bb8db9355d2fc067bcb2334d12c298b4780b97483a10e92378ee","588692fa067bea1443899bf1308a88b68c50f874eef8a516143ba5d8dd745cbb"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"8352ea3f2f69fa6b75b6c50c14405acbdc1b93a45b2eb3a977198aac98a0683f"}57{"parentUuid":"5a5d5ae5-8a07-45ca-92dd-8652620d897b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstmeJxZA1epmSfHtuS","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":1970,"cache_read_input_tokens":26669,"output_tokens":849,"output_tokens_details":{"thinking_tokens":424},"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":1970},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4428,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXstmNwDGf7jYxYMJvMS","requestRef":"6cdd643a-b8b0-4765-8996-8b961516dd55","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"28ecbb98-5f88-4be8-a361-ba417e99bc1b","timestamp":"2026-10-30T05:35:11.215Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}58{"parentUuid":"28ecbb98-5f88-4be8-a361-ba417e99bc1b","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXstmeJxZA1epmSfHtuS","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01QYfdgGYCD2EX8VA8AzYGxJ","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat >> state/log.md <<'EOF'\n- 2026-10-30 DECISION (pre-registered before computing any out-of-sample error): own model = \"base-effect drift\" (BED). At origin V: ln L̂_{last+h} = ln L_last + h·μ̂ with μ̂ = mean monthly log growth over the last 12 months of vintage V (= g_last/12); forecast g_T = 100·ln(L_last/L_{T−12}) + h·g_last/12, using L_{T−12} from vintage V. Rationale: YoY growth is a sum of 12 monthly growths, 12−h of which are already published at the origin; the naive forecast replaces the h unknown months by the h oldest months of the last window (base-effect noise), BED replaces them by their 12-month average. PAYEMS/UMCSENT not used (no pre-sample model selection budget; avoiding snooping over 10 origins). Single specification, no tuning. Supplementary: moving-block bootstrap of RMSE difference, seed 20261030.\nEOF"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1970,"cache_read_input_tokens":26669,"output_tokens":849,"output_tokens_details":{"thinking_tokens":424},"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":1970},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXstmNwDGf7jYxYMJvMS","requestRef":"6cdd643a-b8b0-4765-8996-8b961516dd55","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"4bd9bc6b-242a-49ae-9684-fb66a9f80412","timestamp":"2026-10-30T05:35:14.759Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}59{"parentUuid":"4bd9bc6b-242a-49ae-9684-fb66a9f80412","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01QYfdgGYCD2EX8VA8AzYGxJ","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"2bb925d9-4afa-4b4d-a7f8-c328459b615f","timestamp":"2026-10-30T05:35:14.806Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"4bd9bc6b-242a-49ae-9684-fb66a9f80412","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}60{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"4aa8351b87ee2285f4b887bdbfb1d23bcb8f090d680fc4752cdbf5abb1a8b618","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01QYfdgGYCD2EX8VA8AzYGxJ","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat >> state/log.md <<'EOF'\n- 2026-10-30 DECISION (pre-registered before computing any out-of-sample error): own model = \"base-effect drift\" (BED). At origin V: ln L̂_{last+h} = ln L_last + h·μ̂ with μ̂ = mean monthly log growth over the last 12 months of vintage V (= g_last/12); forecast g_T = 100·ln(L_last/L_{T−12}) + h·g_last/12, using L_{T−12} from vintage V. Rationale: YoY growth is a sum of 12 monthly growths, 12−h of which are already published at the origin; the naive forecast replaces the h unknown months by the h oldest months of the last window (base-effect noise), BED replaces them by their 12-month average. PAYEMS/UMCSENT not used (no pre-sample model selection budget; avoiding snooping over 10 origins). Single specification, no tuning. Supplementary: moving-block bootstrap of RMSE difference, seed 20261030.\nEOF"}}]}}61{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"9f42e3bb-7f16-46fe-b28d-409bec0ae02c","timestamp":"2026-10-30T05:35:14.810Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"6cdd643a-b8b0-4765-8996-8b961516dd55","keep":18,"tail":["4aa8351b87ee2285f4b887bdbfb1d23bcb8f090d680fc4752cdbf5abb1a8b618","f6659f78901f27b36b49071177a2fc86404c5e967c9383a930fcbeb3410224de"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"ff057993e29e17a1b69a2aba1a0670d57aa479b21acae00357d98a6b31a51f2d"}62{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"2bb925d9-4afa-4b4d-a7f8-c328459b615f","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}63{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}64{"parentUuid":"2bb925d9-4afa-4b4d-a7f8-c328459b615f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsuSUuhCzxJvVJpsSCk","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":864,"cache_read_input_tokens":28639,"output_tokens":6083,"output_tokens_details":{"thinking_tokens":155},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":864},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1395,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsuSBoonzhoz7ZX7BCU","requestRef":"9f42e3bb-7f16-46fe-b28d-409bec0ae02c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"93b9c2bb-df9e-4255-a68a-9845cdeeefba","timestamp":"2026-10-30T05:35:17.402Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}65{"parentUuid":"93b9c2bb-df9e-4255-a68a-9845cdeeefba","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsuSUuhCzxJvVJpsSCk","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01K2fjv1UDNJPQTh9kYHCPnw","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat > analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/forecasts.csv, out/table1.csv,\nout/figure1.png, out/exclusions.csv. Deterministic (bootstrap seed fixed).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import norm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nSEED = 20261030\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\nn_input_rows = {}\n\n\ndef read_series(rel):\n    d = pd.read_csv(os.path.join(DATA, rel), parse_dates=[\"observation_date\"])\n    n_input_rows[rel] = int(len(d))\n    return d.set_index(\"observation_date\").iloc[:, 0].astype(float)\n\n\ndef yoy(level):\n    \"\"\"g_m = 100 ln(L_m / L_{m-12}) on a gap-free monthly series.\"\"\"\n    s = level.asfreq(\"MS\")\n    assert not s.isna().any(), \"gap in level series\"\n    return (100 * np.log(s / s.shift(12))).dropna()\n\n\ndef mshift(t, k):\n    return t + pd.DateOffset(months=k)\n\n\n# ---------------------------------------------------------------- inputs\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\nn_input_rows[\"first_release.csv\"] = int(len(fr))\nfr = fr.set_index(\"target_month\")\n\n# PAYEMS vintages and UMCSENT are candidate predictors; they are read for the\n# audit row counts only and do NOT enter the chosen model.\nfor V in ORIGINS:\n    read_series(f\"vintages/PAYEMS_vintage_{V}.csv\")\nread_series(\"UMCSENT.csv\")\n\n# ---------------------------------------------------------------- forecasts\nrows, origin_info = [], []\nfor V in ORIGINS:\n    L = read_series(f\"vintages/RSAFS_vintage_{V}.csv\")      # only vintage V\n    g = yoy(L)\n    last = L.index[-1]\n    assert last < pd.Timestamp(V), \"vintage contains month at/after origin\"\n    origin_info.append({\"origin\": V, \"last\": last.strftime(\"%Y-%m\"),\n                        \"lag_months\": (pd.Timestamp(V).year - last.year) * 12 + pd.Timestamp(V).month - last.month})\n    g_last = g[last]\n    # AR(1): g_m on const + g_{m-1}, 1993-02 <= m <= last\n    gs = g[g.index >= \"1993-01-01\"]\n    y = gs[gs.index >= \"1993-02-01\"].values\n    x = gs.shift(1)[gs.index >= \"1993-02-01\"].values\n    X = np.column_stack([np.ones_like(x), x])\n    (c, phi), *_ = np.linalg.lstsq(X, y, rcond=None)\n    for h in HORIZONS:\n        T = mshift(last, h)\n        actual = float(fr.loc[T, \"yoy_first_release\"])\n        # naive\n        f_naive = g_last\n        # seasonal naive\n        f_snaive = g[mshift(T, -12)]\n        # AR(1) iterated\n        f = g_last\n        for _ in range(h):\n            f = c + phi * f\n        f_ar1 = f\n        # own model: base-effect drift\n        f_model = 100 * np.log(L[last] / L[mshift(T, -12)]) + h * g_last / 12.0\n        for m, fc in zip(MODELS, [f_naive, f_snaive, f_ar1, f_model]):\n            rows.append({\"origin_date\": V, \"target_date\": T.strftime(\"%Y-%m-%d\"), \"horizon\": h,\n                         \"forecast\": round(float(fc), 6), \"actual_first_release\": actual,\n                         \"model\": m, \"vintage_used\": V})\n\nfc = pd.DataFrame(rows)\nassert len(fc) == 80\nfc.to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False)\nfc[\"err\"] = fc[\"actual_first_release\"] - fc[\"forecast\"]\n\n# ---------------------------------------------------------------- evaluation\nres = {}\ntab = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)][\"err\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        tab.append({\"model\": m, \"horizon\": h, \"rmse\": rmse, \"mae\": mae, \"n\": len(e)})\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n\ndef dm_test(e_naive, e_model, h):\n    d = e_naive ** 2 - e_model ** 2\n    n = len(d)\n    dbar = d.mean()\n    dc = d - dbar\n    lrv = np.sum(dc * dc) / n\n    for k in range(1, h):                      # Bartlett, truncation lag h-1\n        w = 1 - k / h\n        lrv += 2 * w * np.sum(dc[k:] * dc[:-k]) / n\n    stat = dbar / np.sqrt(lrv / n)\n    return float(stat), float(2 * (1 - norm.cdf(abs(stat)))), float(lrv)\n\n\nboot = {}\nrng = np.random.default_rng(SEED)\nfor h in HORIZONS:\n    sub = fc[fc.horizon == h]\n    en = sub[sub.model == \"naive\"].sort_values(\"origin_date\")[\"err\"].values\n    em = sub[sub.model == \"model\"].sort_values(\"origin_date\")[\"err\"].values\n    stat, p, lrv = dm_test(en, em, h)\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = stat, p\n    res[f\"rel_improvement_rmse_h{h}\"] = 1 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    better = res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"]\n    sig = p < 0.05\n    res[f\"conclusion_code_h{h}\"] = (\"model_better\" if better else \"naive_better\") + \\\n        (\"_significant\" if sig else \"_not_significant\")\n    # supplementary: moving-block bootstrap of RMSE_model - RMSE_naive (block length max(h,2))\n    n, b = len(en), max(h, 2)\n    starts = np.arange(n - b + 1)\n    draws = []\n    for _ in range(9999):\n        idx = np.concatenate([np.arange(s, s + b) for s in rng.choice(starts, size=int(np.ceil(n / b)))])[:n]\n        draws.append(np.sqrt(np.mean(em[idx] ** 2)) - np.sqrt(np.mean(en[idx] ** 2)))\n    draws = np.array(draws)\n    boot[f\"h{h}\"] = {\"rmse_diff_model_minus_naive\": float(np.sqrt(np.mean(em ** 2)) - np.sqrt(np.mean(en ** 2))),\n                     \"ci95\": [float(np.percentile(draws, 2.5)), float(np.percentile(draws, 97.5))],\n                     \"share_draws_model_better\": float(np.mean(draws < 0)),\n                     \"block_length\": b, \"n_boot\": 9999, \"dm_lrv\": lrv,\n                     \"n_origins_model_smaller_sq_error\": int(np.sum(em ** 2 < en ** 2))}\n\n# ---------------------------------------------------------------- revision (estimand d)\n# RSAFS_current is used ONLY here; it never enters a forecast.\ncur = read_series(\"RSAFS_current.csv\")\ngcur = yoy(cur)\nt1 = fc[(fc.horizon == 1) & (fc.model == \"naive\")]\ntargets = pd.to_datetime(t1[\"target_date\"]).tolist()\nrevs = [float(gcur[T] - fr.loc[T, \"yoy_first_release\"]) for T in targets]\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(np.abs(revs)))\n\n# ---------------------------------------------------------------- exclusions ledger\nexcl = pd.DataFrame([\n    {\"step\": 1, \"rule\": \"first_release.csv: keep only rows that are targets last(V)+h of some origin\",\n     \"n_before\": len(fr), \"n_after\": int(fc.target_date.nunique()),\n     \"n_removed\": len(fr) - int(fc.target_date.nunique()),\n     \"rationale\": \"rows outside the evaluation design are not needed as actuals (not an error-driven exclusion)\"},\n    {\"step\": 2, \"rule\": \"forecast-actual pairs for own model: drop pairs with missing forecast or actual\",\n     \"n_before\": 20, \"n_after\": int(fc[fc.model == \"model\"].dropna(subset=[\"forecast\", \"actual_first_release\"]).shape[0]),\n     \"n_removed\": 20 - int(fc[fc.model == \"model\"].dropna(subset=[\"forecast\", \"actual_first_release\"]).shape[0]),\n     \"rationale\": \"no pair is missing; nothing removed\"},\n])\nexcl.to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\n# ---------------------------------------------------------------- figure\nfig, axes = plt.subplots(2, 1, figsize=(9, 7), sharex=True)\nfrp = fr.loc[\"2025-06-01\":\"2026-09-01\", \"yoy_first_release\"]\nfor ax, h in zip(axes, HORIZONS):\n    ax.plot(frp.index, frp.values, \"k-o\", ms=4, label=\"first-release actual\")\n    for m, sty, lab in [(\"naive\", \"s--\", \"naive\"), (\"model\", \"^-\", \"BED model\"), (\"ar1\", \"x:\", \"AR(1)\")]:\n        s = fc[(fc.horizon == h) & (fc.model == m)]\n        ax.plot(pd.to_datetime(s.target_date), s.forecast, sty, ms=5, label=lab)\n    ax.set_title(f\"h = {h}: forecasts by target month (10 origins)\")\n    ax.set_ylabel(\"YoY growth, % (100·log)\")\n    ax.grid(alpha=.3)\n    ax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n\n# ---------------------------------------------------------------- results.json\nlag_issue = [o for o in origin_info if o[\"lag_months\"] != 1]\nresults = {\n    \"task_id\": \"T1-forecast\",\n    \"model_name\": \"BED (base-effect drift)\",\n    \"model_description\": (\n        \"Base-effect drift model on the RSAFS vintage dated V only. Log level forecast \"\n        \"ln L_{last+h} = ln L_last + h*mu, with mu = mean monthly log growth over the last 12 published months \"\n        \"= g_last/12 (percent). Hence forecast g_T = 100*ln(L_last / L_{T-12}) + h*g_last/12 for T = last(V)+h, \"\n        \"where L_last and L_{T-12} are read from vintage V (T-12 <= last(V) always). It exploits that 12-h of the \"\n        \"12 monthly growth terms in the target YoY are already published at the origin (known base effects), \"\n        \"replacing only the h unknown months by their trailing 12-month average. No parameters are estimated; \"\n        \"estimation window = last 13 levels of the vintage. PAYEMS and UMCSENT were not used. The specification \"\n        \"was fixed before any out-of-sample error was computed; no tuning on the evaluation origins.\"),\n    \"n_origins\": len(ORIGINS),\n    \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1],\n}\nfor k in [\"rmse_naive_h1\", \"mae_naive_h1\", \"rmse_naive_h3\", \"mae_naive_h3\",\n          \"rmse_snaive_h1\", \"mae_snaive_h1\", \"rmse_snaive_h3\", \"mae_snaive_h3\",\n          \"rmse_ar1_h1\", \"mae_ar1_h1\", \"rmse_ar1_h3\", \"mae_ar1_h3\",\n          \"rmse_model_h1\", \"mae_model_h1\", \"rmse_model_h3\", \"mae_model_h3\",\n          \"rel_improvement_rmse_h1\", \"rel_improvement_rmse_h3\",\n          \"dm_stat_h1\", \"dm_pvalue_h1\", \"dm_stat_h3\", \"dm_pvalue_h3\",\n          \"conclusion_code_h1\", \"conclusion_code_h3\", \"mean_abs_revision_h1_targets\"]:\n    results[k] = res[k]\nresults.update({\n    \"feasibility\": \"complete\",\n    \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": \"Irregular publication timing: last(V) is two months before the origin for \"\n                  + \", \".join(f\"{o['origin']} (last {o['last']})\" for o in lag_issue)\n                  + \"; vintage 2026-04-30 adds 2026-02 and 2026-03 at once, so 2026-02 is never an h=1 target.\",\n         \"handling\": \"Targets defined as last(V)+h from the vintage content, per the task rule, not from the calendar.\"},\n        {\"issue\": \"Benchmark/annual revision of RSAFS levels: the current vintage is ~4% lower in level and its YoY growth is \"\n                  \"systematically lower than first release; the base level used in first_release jumps between targets 2026-07 and 2026-08 \"\n                  \"(rebasing between the 2026-08-31 and 2026-09-30 vintages), affecting h=3 targets 2026-08 and 2026-09.\",\n         \"handling\": \"No adjustment: actuals are first-release values by definition; the revision is quantified in mean_abs_revision_h1_targets and discussed.\"},\n        {\"issue\": \"UMCSENT has 210 empty values (all before 1978, quarterly survey era) and is a current (not real-time) vintage.\",\n         \"handling\": \"Not used by the model; would have been usable under the stated no-revision rule.\"},\n        {\"issue\": \"PAYEMS vintages sometimes extend beyond last(V) of RSAFS (e.g. 2025-12-31 vintage ends 2025-11 while RSAFS ends 2025-10).\",\n         \"handling\": \"Not used by the model.\"},\n        {\"issue\": \"For origin 2025-10-31 the target month's predecessor 2025-08 had first-release vintage 2025-09-30 (not shipped); levels in vintage 2025-10-31 still match first_release.csv.\",\n         \"handling\": \"None needed; checked for consistency.\"},\n    ],\n    \"n_input_rows\": n_input_rows,\n    \"n_analysed\": int(fc[fc.model == \"model\"].dropna(subset=[\"forecast\", \"actual_first_release\"]).shape[0]),\n    \"random_seed\": SEED,\n    \"supplementary\": {\"bootstrap_rmse_diff\": boot, \"origins\": origin_info,\n                      \"revisions_h1_targets\": {T.strftime(\"%Y-%m\"): r for T, r in zip(targets, revs)},\n                      \"ar1_note\": \"AR(1) re-estimated by OLS at each origin on the vintage, 1993-02..last(V)\"},\n})\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n    json.dump(results, f, indent=2)\n\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.3f} \"\n          f\"p={res[f'dm_pvalue_h{h}']:.4f} -> {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets =\", round(res[\"mean_abs_revision_h1_targets\"], 4))\nEOF\ncd ..; ~/wp29/venv/bin/python out/analysis.py && cat out/forecasts.csv | head -45 && python3 -c \"import json;print(json.dumps(json.load(open('out/results.json'))['supplementary'],indent=1))\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":864,"cache_read_input_tokens":28639,"output_tokens":6083,"output_tokens_details":{"thinking_tokens":155},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":864},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsuSBoonzhoz7ZX7BCU","requestRef":"9f42e3bb-7f16-46fe-b28d-409bec0ae02c","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"891f64be-bcb0-4ca6-86ad-2e5b81b6585e","timestamp":"2026-10-30T05:36:02.103Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}66{"parentUuid":"891f64be-bcb0-4ca6-86ad-2e5b81b6585e","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01K2fjv1UDNJPQTh9kYHCPnw","type":"tool_result","content":" model  horizon     rmse      mae  n\n naive        1 0.996874 0.848722 10\n naive        3 1.420040 1.200449 10\nsnaive        1 1.674543 1.306670 10\nsnaive        3 1.316079 1.065869 10\n   ar1        1 0.940524 0.797651 10\n   ar1        3 1.187118 0.952689 10\n model        1 0.550298 0.486332 10\n model        3 1.142220 0.933977 10\nh=1: rel_impr=0.4480 DM=2.429 p=0.0151 -> model_better_significant\nh=3: rel_impr=0.1956 DM=1.547 p=0.1220 -> model_better_not_significant\nmean_abs_revision_h1_targets = 0.5482\norigin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used\n2025-10-31,2025-09-01,1,4.878354,4.17354,naive,2025-10-31\n2025-10-31,2025-09-01,1,1.964326,4.17354,snaive,2025-10-31\n2025-10-31,2025-09-01,1,4.821776,4.17354,ar1,2025-10-31\n2025-10-31,2025-09-01,1,4.439021,4.17354,model,2025-10-31\n2025-10-31,2025-11-01,3,4.878354,3.277601,naive,2025-10-31\n2025-10-31,2025-11-01,3,3.838399,3.277601,snaive,2025-10-31\n2025-10-31,2025-11-01,3,4.734345,3.277601,ar1,2025-10-31\n2025-10-31,2025-11-01,3,3.970852,3.277601,model,2025-10-31\n2025-11-30,2025-10-01,1,4.17354,3.410194,naive,2025-11-30\n2025-11-30,2025-10-01,1,3.080399,3.410194,snaive,2025-11-30\n2025-11-30,2025-10-01,1,4.228201,3.410194,ar1,2025-11-30\n2025-11-30,2025-10-01,1,3.907823,3.410194,model,2025-11-30\n2025-11-30,2025-12-01,3,4.17354,2.398715,naive,2025-11-30\n2025-11-30,2025-12-01,3,4.471737,2.398715,snaive,2025-11-30\n2025-11-30,2025-12-01,3,4.312665,2.398715,ar1,2025-11-30\n2025-11-30,2025-12-01,3,3.193276,2.398715,model,2025-11-30\n2025-12-31,2025-11-01,1,3.410194,3.277601,naive,2025-12-31\n2025-12-31,2025-11-01,1,3.838399,3.277601,snaive,2025-12-31\n2025-12-31,2025-11-01,1,3.584932,3.277601,ar1,2025-12-31\n2025-12-31,2025-11-01,1,3.120518,3.277601,model,2025-12-31\n2025-12-31,2026-01-01,3,3.410194,3.1072,naive,2025-12-31\n2025-12-31,2026-01-01,3,4.455744,3.1072,snaive,2025-12-31\n2025-12-31,2026-01-01,3,3.854961,3.1072,ar1,2025-12-31\n2025-12-31,2026-01-01,3,3.784978,3.1072,model,2025-12-31\n2026-01-31,2025-12-01,1,3.277601,2.398715,naive,2026-01-31\n2026-01-31,2025-12-01,1,4.471737,2.398715,snaive,2026-01-31\n2026-01-31,2025-12-01,1,3.472669,2.398715,ar1,2026-01-31\n2026-01-31,2025-12-01,1,2.78323,2.398715,model,2026-01-31\n2026-01-31,2026-02-01,3,3.277601,3.886121,naive,2026-01-31\n2026-01-31,2026-02-01,3,3.790905,3.886121,snaive,2026-01-31\n2026-01-31,2026-02-01,3,3.774129,3.886121,ar1,2026-01-31\n2026-01-31,2026-02-01,3,4.155712,3.886121,model,2026-01-31\n2026-02-28,2026-01-01,1,2.398715,3.1072,naive,2026-02-28\n2026-02-28,2026-01-01,1,4.455744,3.1072,snaive,2026-02-28\n2026-02-28,2026-01-01,1,2.731303,3.1072,ar1,2026-02-28\n2026-02-28,2026-01-01,1,3.450393,3.1072,model,2026-02-28\n2026-02-28,2026-03-01,3,2.398715,3.89269,naive,2026-02-28\n2026-02-28,2026-03-01,3,4.955017,3.89269,snaive,2026-02-28\n2026-02-28,2026-03-01,3,3.245443,3.89269,ar1,2026-02-28\n2026-02-28,2026-03-01,3,2.300532,3.89269,model,2026-02-28\n2026-03-31,2026-02-01,1,3.1072,3.886121,naive,2026-03-31\n2026-03-31,2026-02-01,1,3.790905,3.886121,snaive,2026-03-31\n2026-03-31,2026-02-01,1,3.327514,3.886121,ar1,2026-03-31\n2026-03-31,2026-02-01,1,3.273081,3.886121,model,2026-03-31\n{\n \"bootstrap_rmse_diff\": {\n  \"h1\": {\n   \"rmse_diff_model_minus_naive\": -0.44657672212259436,\n   \"ci95\": [\n    -0.6982530105268047,\n    -0.2612591327392867\n   ],\n   \"share_draws_model_better\": 1.0,\n   \"block_length\": 2,\n   \"n_boot\": 9999,\n   \"dm_lrv\": 0.8091373211601599,\n   \"n_origins_model_smaller_sq_error\": 8\n  },\n  \"h3\": {\n   \"rmse_diff_model_minus_naive\": -0.2778206411547539,\n   \"ci95\": [\n    -0.6376736715848398,\n    0.14490466807245417\n   ],\n   \"share_draws_model_better\": 0.8764876487648765,\n   \"block_length\": 3,\n   \"n_boot\": 9999,\n   \"dm_lrv\": 2.1185178340561874,\n   \"n_origins_model_smaller_sq_error\": 6\n  }\n },\n \"origins\": [\n  {\n   \"origin\": \"2025-10-31\",\n   \"last\": \"2025-08\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2025-11-30\",\n   \"last\": \"2025-09\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2025-12-31\",\n   \"last\": \"2025-10\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-01-31\",\n   \"last\": \"2025-11\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-02-28\",\n   \"last\": \"2025-12\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-03-31\",\n   \"last\": \"2026-01\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-04-30\",\n   \"last\": \"2026-03\",\n   \"lag_months\": 1\n  },\n  {\n   \"origin\": \"2026-05-31\",\n   \"last\": \"2026-04\",\n   \"lag_months\": 1\n  },\n  {\n   \"origin\": \"2026-06-30\",\n   \"last\": \"2026-05\",\n   \"lag_months\": 1\n  },\n  {\n   \"origin\": \"2026-07-31\",\n   \"last\": \"2026-06\",\n   \"lag_months\": 1\n  }\n ],\n \"revisions_h1_targets\": {\n  \"2025-09\": -0.5502167925401702,\n  \"2025-10\": -0.6641763167214578,\n  \"2025-11\": -0.4389199822781502,\n  \"2025-12\": -0.3286268165544084,\n  \"2026-01\": -0.9756759757612237,\n  \"2026-02\": -0.40995563089387543,\n  \"2026-04\": -0.7481728291014038,\n  \"2026-05\": -0.16533992600871716,\n  \"2026-06\": -0.7440888135516674,\n  \"2026-07\": -0.45702494497780943\n },\n \"ar1_note\": \"AR(1) re-estimated by OLS at each origin on the vintage, 1993-02..last(V)\"\n}","is_error":false}]},"uuid":"a3ae6002-b66b-4637-97f7-eaccd31b75a2","timestamp":"2026-10-30T05:36:03.591Z","toolUseResult":{"stdout":" model  horizon     rmse      mae  n\n naive        1 0.996874 0.848722 10\n naive        3 1.420040 1.200449 10\nsnaive        1 1.674543 1.306670 10\nsnaive        3 1.316079 1.065869 10\n   ar1        1 0.940524 0.797651 10\n   ar1        3 1.187118 0.952689 10\n model        1 0.550298 0.486332 10\n model        3 1.142220 0.933977 10\nh=1: rel_impr=0.4480 DM=2.429 p=0.0151 -> model_better_significant\nh=3: rel_impr=0.1956 DM=1.547 p=0.1220 -> model_better_not_significant\nmean_abs_revision_h1_targets = 0.5482\norigin_date,target_date,horizon,forecast,actual_first_release,model,vintage_used\n2025-10-31,2025-09-01,1,4.878354,4.17354,naive,2025-10-31\n2025-10-31,2025-09-01,1,1.964326,4.17354,snaive,2025-10-31\n2025-10-31,2025-09-01,1,4.821776,4.17354,ar1,2025-10-31\n2025-10-31,2025-09-01,1,4.439021,4.17354,model,2025-10-31\n2025-10-31,2025-11-01,3,4.878354,3.277601,naive,2025-10-31\n2025-10-31,2025-11-01,3,3.838399,3.277601,snaive,2025-10-31\n2025-10-31,2025-11-01,3,4.734345,3.277601,ar1,2025-10-31\n2025-10-31,2025-11-01,3,3.970852,3.277601,model,2025-10-31\n2025-11-30,2025-10-01,1,4.17354,3.410194,naive,2025-11-30\n2025-11-30,2025-10-01,1,3.080399,3.410194,snaive,2025-11-30\n2025-11-30,2025-10-01,1,4.228201,3.410194,ar1,2025-11-30\n2025-11-30,2025-10-01,1,3.907823,3.410194,model,2025-11-30\n2025-11-30,2025-12-01,3,4.17354,2.398715,naive,2025-11-30\n2025-11-30,2025-12-01,3,4.471737,2.398715,snaive,2025-11-30\n2025-11-30,2025-12-01,3,4.312665,2.398715,ar1,2025-11-30\n2025-11-30,2025-12-01,3,3.193276,2.398715,model,2025-11-30\n2025-12-31,2025-11-01,1,3.410194,3.277601,naive,2025-12-31\n2025-12-31,2025-11-01,1,3.838399,3.277601,snaive,2025-12-31\n2025-12-31,2025-11-01,1,3.584932,3.277601,ar1,2025-12-31\n2025-12-31,2025-11-01,1,3.120518,3.277601,model,2025-12-31\n2025-12-31,2026-01-01,3,3.410194,3.1072,naive,2025-12-31\n2025-12-31,2026-01-01,3,4.455744,3.1072,snaive,2025-12-31\n2025-12-31,2026-01-01,3,3.854961,3.1072,ar1,2025-12-31\n2025-12-31,2026-01-01,3,3.784978,3.1072,model,2025-12-31\n2026-01-31,2025-12-01,1,3.277601,2.398715,naive,2026-01-31\n2026-01-31,2025-12-01,1,4.471737,2.398715,snaive,2026-01-31\n2026-01-31,2025-12-01,1,3.472669,2.398715,ar1,2026-01-31\n2026-01-31,2025-12-01,1,2.78323,2.398715,model,2026-01-31\n2026-01-31,2026-02-01,3,3.277601,3.886121,naive,2026-01-31\n2026-01-31,2026-02-01,3,3.790905,3.886121,snaive,2026-01-31\n2026-01-31,2026-02-01,3,3.774129,3.886121,ar1,2026-01-31\n2026-01-31,2026-02-01,3,4.155712,3.886121,model,2026-01-31\n2026-02-28,2026-01-01,1,2.398715,3.1072,naive,2026-02-28\n2026-02-28,2026-01-01,1,4.455744,3.1072,snaive,2026-02-28\n2026-02-28,2026-01-01,1,2.731303,3.1072,ar1,2026-02-28\n2026-02-28,2026-01-01,1,3.450393,3.1072,model,2026-02-28\n2026-02-28,2026-03-01,3,2.398715,3.89269,naive,2026-02-28\n2026-02-28,2026-03-01,3,4.955017,3.89269,snaive,2026-02-28\n2026-02-28,2026-03-01,3,3.245443,3.89269,ar1,2026-02-28\n2026-02-28,2026-03-01,3,2.300532,3.89269,model,2026-02-28\n2026-03-31,2026-02-01,1,3.1072,3.886121,naive,2026-03-31\n2026-03-31,2026-02-01,1,3.790905,3.886121,snaive,2026-03-31\n2026-03-31,2026-02-01,1,3.327514,3.886121,ar1,2026-03-31\n2026-03-31,2026-02-01,1,3.273081,3.886121,model,2026-03-31\n{\n \"bootstrap_rmse_diff\": {\n  \"h1\": {\n   \"rmse_diff_model_minus_naive\": -0.44657672212259436,\n   \"ci95\": [\n    -0.6982530105268047,\n    -0.2612591327392867\n   ],\n   \"share_draws_model_better\": 1.0,\n   \"block_length\": 2,\n   \"n_boot\": 9999,\n   \"dm_lrv\": 0.8091373211601599,\n   \"n_origins_model_smaller_sq_error\": 8\n  },\n  \"h3\": {\n   \"rmse_diff_model_minus_naive\": -0.2778206411547539,\n   \"ci95\": [\n    -0.6376736715848398,\n    0.14490466807245417\n   ],\n   \"share_draws_model_better\": 0.8764876487648765,\n   \"block_length\": 3,\n   \"n_boot\": 9999,\n   \"dm_lrv\": 2.1185178340561874,\n   \"n_origins_model_smaller_sq_error\": 6\n  }\n },\n \"origins\": [\n  {\n   \"origin\": \"2025-10-31\",\n   \"last\": \"2025-08\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2025-11-30\",\n   \"last\": \"2025-09\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2025-12-31\",\n   \"last\": \"2025-10\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-01-31\",\n   \"last\": \"2025-11\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-02-28\",\n   \"last\": \"2025-12\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-03-31\",\n   \"last\": \"2026-01\",\n   \"lag_months\": 2\n  },\n  {\n   \"origin\": \"2026-04-30\",\n   \"last\": \"2026-03\",\n   \"lag_months\": 1\n  },\n  {\n   \"origin\": \"2026-05-31\",\n   \"last\": \"2026-04\",\n   \"lag_months\": 1\n  },\n  {\n   \"origin\": \"2026-06-30\",\n   \"last\": \"2026-05\",\n   \"lag_months\": 1\n  },\n  {\n   \"origin\": \"2026-07-31\",\n   \"last\": \"2026-06\",\n   \"lag_months\": 1\n  }\n ],\n \"revisions_h1_targets\": {\n  \"2025-09\": -0.5502167925401702,\n  \"2025-10\": -0.6641763167214578,\n  \"2025-11\": -0.4389199822781502,\n  \"2025-12\": -0.3286268165544084,\n  \"2026-01\": -0.9756759757612237,\n  \"2026-02\": -0.40995563089387543,\n  \"2026-04\": -0.7481728291014038,\n  \"2026-05\": -0.16533992600871716,\n  \"2026-06\": -0.7440888135516674,\n  \"2026-07\": -0.45702494497780943\n },\n \"ar1_note\": \"AR(1) re-estimated by OLS at each origin on the vintage, 1993-02..last(V)\"\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"891f64be-bcb0-4ca6-86ad-2e5b81b6585e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}67{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"ac117cad50682aac31ed81a545af78a5a0a07479409bcd6bc574d7eab815f8e0","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01K2fjv1UDNJPQTh9kYHCPnw","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat > analysis.py <<'EOF'\n\"\"\"T1-forecast: real-time forecasting of US retail-sales YoY growth from ALFRED vintages.\nRun from workspace root:  ~/wp29/venv/bin/python out/analysis.py\nReads only data/, writes out/results.json, out/forecasts.csv, out/table1.csv,\nout/figure1.png, out/exclusions.csv. Deterministic (bootstrap seed fixed).\"\"\"\nimport json, os\nimport numpy as np\nimport pandas as pd\nfrom scipy.stats import norm\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nDATA, OUT = \"data\", \"out\"\nSEED = 20261030\nORIGINS = [\"2025-10-31\", \"2025-11-30\", \"2025-12-31\", \"2026-01-31\", \"2026-02-28\",\n           \"2026-03-31\", \"2026-04-30\", \"2026-05-31\", \"2026-06-30\", \"2026-07-31\"]\nHORIZONS = [1, 3]\nMODELS = [\"naive\", \"snaive\", \"ar1\", \"model\"]\nn_input_rows = {}\n\n\ndef read_series(rel):\n    d = pd.read_csv(os.path.join(DATA, rel), parse_dates=[\"observation_date\"])\n    n_input_rows[rel] = int(len(d))\n    return d.set_index(\"observation_date\").iloc[:, 0].astype(float)\n\n\ndef yoy(level):\n    \"\"\"g_m = 100 ln(L_m / L_{m-12}) on a gap-free monthly series.\"\"\"\n    s = level.asfreq(\"MS\")\n    assert not s.isna().any(), \"gap in level series\"\n    return (100 * np.log(s / s.shift(12))).dropna()\n\n\ndef mshift(t, k):\n    return t + pd.DateOffset(months=k)\n\n\n# ---------------------------------------------------------------- inputs\nfr = pd.read_csv(os.path.join(DATA, \"first_release.csv\"), parse_dates=[\"target_month\"])\nn_input_rows[\"first_release.csv\"] = int(len(fr))\nfr = fr.set_index(\"target_month\")\n\n# PAYEMS vintages and UMCSENT are candidate predictors; they are read for the\n# audit row counts only and do NOT enter the chosen model.\nfor V in ORIGINS:\n    read_series(f\"vintages/PAYEMS_vintage_{V}.csv\")\nread_series(\"UMCSENT.csv\")\n\n# ---------------------------------------------------------------- forecasts\nrows, origin_info = [], []\nfor V in ORIGINS:\n    L = read_series(f\"vintages/RSAFS_vintage_{V}.csv\")      # only vintage V\n    g = yoy(L)\n    last = L.index[-1]\n    assert last < pd.Timestamp(V), \"vintage contains month at/after origin\"\n    origin_info.append({\"origin\": V, \"last\": last.strftime(\"%Y-%m\"),\n                        \"lag_months\": (pd.Timestamp(V).year - last.year) * 12 + pd.Timestamp(V).month - last.month})\n    g_last = g[last]\n    # AR(1): g_m on const + g_{m-1}, 1993-02 <= m <= last\n    gs = g[g.index >= \"1993-01-01\"]\n    y = gs[gs.index >= \"1993-02-01\"].values\n    x = gs.shift(1)[gs.index >= \"1993-02-01\"].values\n    X = np.column_stack([np.ones_like(x), x])\n    (c, phi), *_ = np.linalg.lstsq(X, y, rcond=None)\n    for h in HORIZONS:\n        T = mshift(last, h)\n        actual = float(fr.loc[T, \"yoy_first_release\"])\n        # naive\n        f_naive = g_last\n        # seasonal naive\n        f_snaive = g[mshift(T, -12)]\n        # AR(1) iterated\n        f = g_last\n        for _ in range(h):\n            f = c + phi * f\n        f_ar1 = f\n        # own model: base-effect drift\n        f_model = 100 * np.log(L[last] / L[mshift(T, -12)]) + h * g_last / 12.0\n        for m, fc in zip(MODELS, [f_naive, f_snaive, f_ar1, f_model]):\n            rows.append({\"origin_date\": V, \"target_date\": T.strftime(\"%Y-%m-%d\"), \"horizon\": h,\n                         \"forecast\": round(float(fc), 6), \"actual_first_release\": actual,\n                         \"model\": m, \"vintage_used\": V})\n\nfc = pd.DataFrame(rows)\nassert len(fc) == 80\nfc.to_csv(os.path.join(OUT, \"forecasts.csv\"), index=False)\nfc[\"err\"] = fc[\"actual_first_release\"] - fc[\"forecast\"]\n\n# ---------------------------------------------------------------- evaluation\nres = {}\ntab = []\nfor m in MODELS:\n    for h in HORIZONS:\n        e = fc[(fc.model == m) & (fc.horizon == h)][\"err\"].values\n        rmse, mae = float(np.sqrt(np.mean(e ** 2))), float(np.mean(np.abs(e)))\n        res[f\"rmse_{m}_h{h}\"], res[f\"mae_{m}_h{h}\"] = rmse, mae\n        tab.append({\"model\": m, \"horizon\": h, \"rmse\": rmse, \"mae\": mae, \"n\": len(e)})\npd.DataFrame(tab).to_csv(os.path.join(OUT, \"table1.csv\"), index=False)\n\n\ndef dm_test(e_naive, e_model, h):\n    d = e_naive ** 2 - e_model ** 2\n    n = len(d)\n    dbar = d.mean()\n    dc = d - dbar\n    lrv = np.sum(dc * dc) / n\n    for k in range(1, h):                      # Bartlett, truncation lag h-1\n        w = 1 - k / h\n        lrv += 2 * w * np.sum(dc[k:] * dc[:-k]) / n\n    stat = dbar / np.sqrt(lrv / n)\n    return float(stat), float(2 * (1 - norm.cdf(abs(stat)))), float(lrv)\n\n\nboot = {}\nrng = np.random.default_rng(SEED)\nfor h in HORIZONS:\n    sub = fc[fc.horizon == h]\n    en = sub[sub.model == \"naive\"].sort_values(\"origin_date\")[\"err\"].values\n    em = sub[sub.model == \"model\"].sort_values(\"origin_date\")[\"err\"].values\n    stat, p, lrv = dm_test(en, em, h)\n    res[f\"dm_stat_h{h}\"], res[f\"dm_pvalue_h{h}\"] = stat, p\n    res[f\"rel_improvement_rmse_h{h}\"] = 1 - res[f\"rmse_model_h{h}\"] / res[f\"rmse_naive_h{h}\"]\n    better = res[f\"rmse_model_h{h}\"] < res[f\"rmse_naive_h{h}\"]\n    sig = p < 0.05\n    res[f\"conclusion_code_h{h}\"] = (\"model_better\" if better else \"naive_better\") + \\\n        (\"_significant\" if sig else \"_not_significant\")\n    # supplementary: moving-block bootstrap of RMSE_model - RMSE_naive (block length max(h,2))\n    n, b = len(en), max(h, 2)\n    starts = np.arange(n - b + 1)\n    draws = []\n    for _ in range(9999):\n        idx = np.concatenate([np.arange(s, s + b) for s in rng.choice(starts, size=int(np.ceil(n / b)))])[:n]\n        draws.append(np.sqrt(np.mean(em[idx] ** 2)) - np.sqrt(np.mean(en[idx] ** 2)))\n    draws = np.array(draws)\n    boot[f\"h{h}\"] = {\"rmse_diff_model_minus_naive\": float(np.sqrt(np.mean(em ** 2)) - np.sqrt(np.mean(en ** 2))),\n                     \"ci95\": [float(np.percentile(draws, 2.5)), float(np.percentile(draws, 97.5))],\n                     \"share_draws_model_better\": float(np.mean(draws < 0)),\n                     \"block_length\": b, \"n_boot\": 9999, \"dm_lrv\": lrv,\n                     \"n_origins_model_smaller_sq_error\": int(np.sum(em ** 2 < en ** 2))}\n\n# ---------------------------------------------------------------- revision (estimand d)\n# RSAFS_current is used ONLY here; it never enters a forecast.\ncur = read_series(\"RSAFS_current.csv\")\ngcur = yoy(cur)\nt1 = fc[(fc.horizon == 1) & (fc.model == \"naive\")]\ntargets = pd.to_datetime(t1[\"target_date\"]).tolist()\nrevs = [float(gcur[T] - fr.loc[T, \"yoy_first_release\"]) for T in targets]\nres[\"mean_abs_revision_h1_targets\"] = float(np.mean(np.abs(revs)))\n\n# ---------------------------------------------------------------- exclusions ledger\nexcl = pd.DataFrame([\n    {\"step\": 1, \"rule\": \"first_release.csv: keep only rows that are targets last(V)+h of some origin\",\n     \"n_before\": len(fr), \"n_after\": int(fc.target_date.nunique()),\n     \"n_removed\": len(fr) - int(fc.target_date.nunique()),\n     \"rationale\": \"rows outside the evaluation design are not needed as actuals (not an error-driven exclusion)\"},\n    {\"step\": 2, \"rule\": \"forecast-actual pairs for own model: drop pairs with missing forecast or actual\",\n     \"n_before\": 20, \"n_after\": int(fc[fc.model == \"model\"].dropna(subset=[\"forecast\", \"actual_first_release\"]).shape[0]),\n     \"n_removed\": 20 - int(fc[fc.model == \"model\"].dropna(subset=[\"forecast\", \"actual_first_release\"]).shape[0]),\n     \"rationale\": \"no pair is missing; nothing removed\"},\n])\nexcl.to_csv(os.path.join(OUT, \"exclusions.csv\"), index=False)\n\n# ---------------------------------------------------------------- figure\nfig, axes = plt.subplots(2, 1, figsize=(9, 7), sharex=True)\nfrp = fr.loc[\"2025-06-01\":\"2026-09-01\", \"yoy_first_release\"]\nfor ax, h in zip(axes, HORIZONS):\n    ax.plot(frp.index, frp.values, \"k-o\", ms=4, label=\"first-release actual\")\n    for m, sty, lab in [(\"naive\", \"s--\", \"naive\"), (\"model\", \"^-\", \"BED model\"), (\"ar1\", \"x:\", \"AR(1)\")]:\n        s = fc[(fc.horizon == h) & (fc.model == m)]\n        ax.plot(pd.to_datetime(s.target_date), s.forecast, sty, ms=5, label=lab)\n    ax.set_title(f\"h = {h}: forecasts by target month (10 origins)\")\n    ax.set_ylabel(\"YoY growth, % (100·log)\")\n    ax.grid(alpha=.3)\n    ax.legend(fontsize=8)\nfig.tight_layout()\nfig.savefig(os.path.join(OUT, \"figure1.png\"), dpi=130)\n\n# ---------------------------------------------------------------- results.json\nlag_issue = [o for o in origin_info if o[\"lag_months\"] != 1]\nresults = {\n    \"task_id\": \"T1-forecast\",\n    \"model_name\": \"BED (base-effect drift)\",\n    \"model_description\": (\n        \"Base-effect drift model on the RSAFS vintage dated V only. Log level forecast \"\n        \"ln L_{last+h} = ln L_last + h*mu, with mu = mean monthly log growth over the last 12 published months \"\n        \"= g_last/12 (percent). Hence forecast g_T = 100*ln(L_last / L_{T-12}) + h*g_last/12 for T = last(V)+h, \"\n        \"where L_last and L_{T-12} are read from vintage V (T-12 <= last(V) always). It exploits that 12-h of the \"\n        \"12 monthly growth terms in the target YoY are already published at the origin (known base effects), \"\n        \"replacing only the h unknown months by their trailing 12-month average. No parameters are estimated; \"\n        \"estimation window = last 13 levels of the vintage. PAYEMS and UMCSENT were not used. The specification \"\n        \"was fixed before any out-of-sample error was computed; no tuning on the evaluation origins.\"),\n    \"n_origins\": len(ORIGINS),\n    \"first_origin\": ORIGINS[0], \"last_origin\": ORIGINS[-1],\n}\nfor k in [\"rmse_naive_h1\", \"mae_naive_h1\", \"rmse_naive_h3\", \"mae_naive_h3\",\n          \"rmse_snaive_h1\", \"mae_snaive_h1\", \"rmse_snaive_h3\", \"mae_snaive_h3\",\n          \"rmse_ar1_h1\", \"mae_ar1_h1\", \"rmse_ar1_h3\", \"mae_ar1_h3\",\n          \"rmse_model_h1\", \"mae_model_h1\", \"rmse_model_h3\", \"mae_model_h3\",\n          \"rel_improvement_rmse_h1\", \"rel_improvement_rmse_h3\",\n          \"dm_stat_h1\", \"dm_pvalue_h1\", \"dm_stat_h3\", \"dm_pvalue_h3\",\n          \"conclusion_code_h1\", \"conclusion_code_h3\", \"mean_abs_revision_h1_targets\"]:\n    results[k] = res[k]\nresults.update({\n    \"feasibility\": \"complete\",\n    \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": \"Irregular publication timing: last(V) is two months before the origin for \"\n                  + \", \".join(f\"{o['origin']} (last {o['last']})\" for o in lag_issue)\n                  + \"; vintage 2026-04-30 adds 2026-02 and 2026-03 at once, so 2026-02 is never an h=1 target.\",\n         \"handling\": \"Targets defined as last(V)+h from the vintage content, per the task rule, not from the calendar.\"},\n        {\"issue\": \"Benchmark/annual revision of RSAFS levels: the current vintage is ~4% lower in level and its YoY growth is \"\n                  \"systematically lower than first release; the base level used in first_release jumps between targets 2026-07 and 2026-08 \"\n                  \"(rebasing between the 2026-08-31 and 2026-09-30 vintages), affecting h=3 targets 2026-08 and 2026-09.\",\n         \"handling\": \"No adjustment: actuals are first-release values by definition; the revision is quantified in mean_abs_revision_h1_targets and discussed.\"},\n        {\"issue\": \"UMCSENT has 210 empty values (all before 1978, quarterly survey era) and is a current (not real-time) vintage.\",\n         \"handling\": \"Not used by the model; would have been usable under the stated no-revision rule.\"},\n        {\"issue\": \"PAYEMS vintages sometimes extend beyond last(V) of RSAFS (e.g. 2025-12-31 vintage ends 2025-11 while RSAFS ends 2025-10).\",\n         \"handling\": \"Not used by the model.\"},\n        {\"issue\": \"For origin 2025-10-31 the target month's predecessor 2025-08 had first-release vintage 2025-09-30 (not shipped); levels in vintage 2025-10-31 still match first_release.csv.\",\n         \"handling\": \"None needed; checked for consistency.\"},\n    ],\n    \"n_input_rows\": n_input_rows,\n    \"n_analysed\": int(fc[fc.model == \"model\"].dropna(subset=[\"forecast\", \"actual_first_release\"]).shape[0]),\n    \"random_seed\": SEED,\n    \"supplementary\": {\"bootstrap_rmse_diff\": boot, \"origins\": origin_info,\n                      \"revisions_h1_targets\": {T.strftime(\"%Y-%m\"): r for T, r in zip(targets, revs)},\n                      \"ar1_note\": \"AR(1) re-estimated by OLS at each origin on the vintage, 1993-02..last(V)\"},\n})\nwith open(os.path.join(OUT, \"results.json\"), \"w\") as f:\n    json.dump(results, f, indent=2)\n\nprint(pd.DataFrame(tab).to_string(index=False))\nfor h in HORIZONS:\n    print(f\"h={h}: rel_impr={res[f'rel_improvement_rmse_h{h}']:.4f} DM={res[f'dm_stat_h{h}']:.3f} \"\n          f\"p={res[f'dm_pvalue_h{h}']:.4f} -> {res[f'conclusion_code_h{h}']}\")\nprint(\"mean_abs_revision_h1_targets =\", round(res[\"mean_abs_revision_h1_targets\"], 4))\nEOF\ncd ..; ~/wp29/venv/bin/python out/analysis.py && cat out/forecasts.csv | head -45 && python3 -c \"import json;print(json.dumps(json.load(open('out/results.json'))['supplementary'],indent=1))\""}}]}}68{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"29ff49e6-6c86-4855-97f9-09ab47a162c8","timestamp":"2026-10-30T05:36:03.597Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"9f42e3bb-7f16-46fe-b28d-409bec0ae02c","keep":20,"tail":["ac117cad50682aac31ed81a545af78a5a0a07479409bcd6bc574d7eab815f8e0","23bfb8284575859cc01a29bf48b1c108735e9a5259cb234d4a57b262018fda6a"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",21,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0d1fa2cdc57a9bf2b115d5faecac026c7d41749a154d92720b9ced23bb719f20"}69{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"a3ae6002-b66b-4637-97f7-eaccd31b75a2","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}70{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}71{"parentUuid":"a3ae6002-b66b-4637-97f7-eaccd31b75a2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsy33sCm5NhATvhtHxv","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":8969,"cache_read_input_tokens":29503,"output_tokens":1228,"output_tokens_details":{"thinking_tokens":519},"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":8969},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":4946,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsy2nFY1LhaR8xTjz4J","requestRef":"29ff49e6-6c86-4855-97f9-09ab47a162c8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"793065f9-15eb-439d-950c-837902eba4f6","timestamp":"2026-10-30T05:36:09.660Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}72{"parentUuid":"793065f9-15eb-439d-950c-837902eba4f6","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsy33sCm5NhATvhtHxv","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MnDwE56DvAKNQagX4PZrCy","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace(\"so 2026-02 is never an h=1 target.\",\"so 2026-03 is never an h=1 target (it is the h=1 target of no origin) and 2026-02 is reached from the 2026-03-31 vintage.\")\ns=s.replace(\"For origin 2025-10-31 the target month's predecessor 2025-08 had first-release vintage 2025-09-30 (not shipped); levels in vintage 2025-10-31 still match first_release.csv.\",\n \"first_release.csv dates the first release of 2025-08 (last month of the 2025-10-31 vintage) to the unshipped 2025-09-30 vintage; its level in the 2025-10-31 vintage still equals level_first_release.\")\nopen(p,'w').write(s)\np='out/state/data_audit.md'; s=open(p).read()\ns=s.replace(\"1. **Irregular publication timing**: last(V) is two months before V for 2025-10-31 (last 2025-08) and 2026-03-31 (last 2026-01); vintage 2026-04-30 adds 2026-02 and 2026-03 at once.\",\n\"1. **Irregular publication timing**: last(V) is two calendar months before the origin month for the six origins 2025-10-31 … 2026-03-31 (last = 2025-08 … 2026-01; month-end vintages normally end one month before), and one month for 2026-04-30 … 2026-07-31; vintage 2026-04-30 adds 2026-02 and 2026-03 at once, so 2026-03 is never an h=1 target.\")\nopen(p,'w').write(s)\nEOF\ngrep -n \"Irregular\" out/state/data_audit.md; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cat out/exclusions.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":8969,"cache_read_input_tokens":29503,"output_tokens":1228,"output_tokens_details":{"thinking_tokens":519},"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":8969},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsy2nFY1LhaR8xTjz4J","requestRef":"29ff49e6-6c86-4855-97f9-09ab47a162c8","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2ccc6d1a-d7b1-4d1e-9bd4-a609e5ea3c7e","timestamp":"2026-10-30T05:36:14.567Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}73{"parentUuid":"2ccc6d1a-d7b1-4d1e-9bd4-a609e5ea3c7e","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MnDwE56DvAKNQagX4PZrCy","type":"tool_result","content":"25:1. **Irregular publication timing**: last(V) is two calendar months before the origin month for the six origins 2025-10-31 … 2026-03-31 (last = 2025-08 … 2026-01; month-end vintages normally end one month before), and one month for 2026-04-30 … 2026-07-31; vintage 2026-04-30 adds 2026-02 and 2026-03 at once, so 2026-03 is never an h=1 target. Handled per task rule: targets are last(V)+h, not calendar-based. Consequence: 2026-02 is never an h=1 target; some target months are shared (e.g. h=3 targets).\nstep,rule,n_before,n_after,n_removed,rationale\n1,first_release.csv: keep only rows that are targets last(V)+h of some origin,28,13,15,rows outside the evaluation design are not needed as actuals (not an error-driven exclusion)\n2,forecast-actual pairs for own model: drop pairs with missing forecast or actual,20,20,0,no pair is missing; nothing removed","is_error":false}]},"uuid":"5a6ca225-93e8-4430-b215-dda3d038da2d","timestamp":"2026-10-30T05:36:16.057Z","toolUseResult":{"stdout":"25:1. **Irregular publication timing**: last(V) is two calendar months before the origin month for the six origins 2025-10-31 … 2026-03-31 (last = 2025-08 … 2026-01; month-end vintages normally end one month before), and one month for 2026-04-30 … 2026-07-31; vintage 2026-04-30 adds 2026-02 and 2026-03 at once, so 2026-03 is never an h=1 target. Handled per task rule: targets are last(V)+h, not calendar-based. Consequence: 2026-02 is never an h=1 target; some target months are shared (e.g. h=3 targets).\nstep,rule,n_before,n_after,n_removed,rationale\n1,first_release.csv: keep only rows that are targets last(V)+h of some origin,28,13,15,rows outside the evaluation design are not needed as actuals (not an error-driven exclusion)\n2,forecast-actual pairs for own model: drop pairs with missing forecast or actual,20,20,0,no pair is missing; nothing removed","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"2ccc6d1a-d7b1-4d1e-9bd4-a609e5ea3c7e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}74{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"b7d519680f12bf0f1cb417f1c3a6160e07402add29a5a758c949b25a12aa5b1c","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01MnDwE56DvAKNQagX4PZrCy","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python - <<'EOF'\np='out/analysis.py'; s=open(p).read()\ns=s.replace(\"so 2026-02 is never an h=1 target.\",\"so 2026-03 is never an h=1 target (it is the h=1 target of no origin) and 2026-02 is reached from the 2026-03-31 vintage.\")\ns=s.replace(\"For origin 2025-10-31 the target month's predecessor 2025-08 had first-release vintage 2025-09-30 (not shipped); levels in vintage 2025-10-31 still match first_release.csv.\",\n \"first_release.csv dates the first release of 2025-08 (last month of the 2025-10-31 vintage) to the unshipped 2025-09-30 vintage; its level in the 2025-10-31 vintage still equals level_first_release.\")\nopen(p,'w').write(s)\np='out/state/data_audit.md'; s=open(p).read()\ns=s.replace(\"1. **Irregular publication timing**: last(V) is two months before V for 2025-10-31 (last 2025-08) and 2026-03-31 (last 2026-01); vintage 2026-04-30 adds 2026-02 and 2026-03 at once.\",\n\"1. **Irregular publication timing**: last(V) is two calendar months before the origin month for the six origins 2025-10-31 … 2026-03-31 (last = 2025-08 … 2026-01; month-end vintages normally end one month before), and one month for 2026-04-30 … 2026-07-31; vintage 2026-04-30 adds 2026-02 and 2026-03 at once, so 2026-03 is never an h=1 target.\")\nopen(p,'w').write(s)\nEOF\ngrep -n \"Irregular\" out/state/data_audit.md; ~/wp29/venv/bin/python out/analysis.py >/dev/null; cat out/exclusions.csv"}}]}}75{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"785365e1-5f89-4ded-b3b8-3405f34d093b","timestamp":"2026-10-30T05:36:16.060Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"29ff49e6-6c86-4855-97f9-09ab47a162c8","keep":22,"tail":["b7d519680f12bf0f1cb417f1c3a6160e07402add29a5a758c949b25a12aa5b1c","cad63ff5ce27d216c4d9aa44396463778a0ddbf698adf28d17094ac632881480"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",23,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"cac6ae0fe7672e818ee56ce7d261cc7342d0b42d895b254d9c3db9f6494716af"}76{"parentUuid":"5a6ca225-93e8-4430-b215-dda3d038da2d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsyxMspTjJbeRB2fyQk","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":1580,"cache_read_input_tokens":38472,"output_tokens":2105,"output_tokens_details":{"thinking_tokens":232},"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":1580},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":2269,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXsyx3m79dBnXWtiS5kf","requestRef":"785365e1-5f89-4ded-b3b8-3405f34d093b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"ef11ef3a-a10a-4cad-8cd9-349f9f54a951","timestamp":"2026-10-30T05:36:19.462Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}77{"parentUuid":"ef11ef3a-a10a-4cad-8cd9-349f9f54a951","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXsyxMspTjJbeRB2fyQk","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01KX9MGP6Y2Cm4YVfGvLEgkm","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; sed -i '' 's/ Consequence: 2026-02 is never an h=1 target; some target months are shared (e.g. h=3 targets)./ Consequence: some target months are shared between h=1 and h=3 (13 distinct target months)./' out/state/data_audit.md\nshasum -a 256 out/results.json out/forecasts.csv out/table1.csv > /tmp/h1.txt; rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py > /dev/null; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv | diff - /tmp/h1.txt && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); f=pd.read_csv('out/forecasts.csv'); fr=pd.read_csv('data/first_release.csv')\nok=lambda n,c: print(('PASS' if c else 'FAIL'),n)\nok('80 rows, 10x2x4 unique',len(f)==80 and f.groupby(['origin_date','horizon','model']).size().eq(1).all() and f.origin_date.nunique()==10)\nok('vintage_used==origin',(f.vintage_used==f.origin_date).all())\nok('target > origin-month-? (target after last month; target month first-released after origin)',all(pd.to_datetime(fr.set_index('target_month').loc[t,'first_release_vintage'])>pd.to_datetime(o) for t,o in zip(f.target_date,f.origin_date)))\n# naive equals first release of last(V) where first-release vintage == V\nfri=fr.set_index('target_month')\nn=f[(f.model=='naive')&(f.horizon==1)]\nchk=[]\nfor _,row in n.iterrows():\n    last=(pd.Timestamp(row.target_date)-pd.DateOffset(months=1)).strftime('%Y-%m-%d')\n    chk.append(abs(fri.loc[last,'yoy_first_release']-row.forecast)<1e-5)\nok('naive forecast == first-release yoy of last(V) (all 10)',all(chk))\n# recompute RMSE/MAE\nf['e']=f.actual_first_release-f.forecast\nfor m in ['naive','snaive','ar1','model']:\n  for h in [1,3]:\n    e=f[(f.model==m)&(f.horizon==h)].e\n    ok(f'rmse/mae {m} h{h}',abs(np.sqrt((e**2).mean())-r[f'rmse_{m}_h{h}'])<1e-9 and abs(e.abs().mean()-r[f'mae_{m}_h{h}'])<1e-9 and r[f'rmse_{m}_h{h}']>=r[f'mae_{m}_h{h}']>0)\n# DM independent via statsmodels HAC on constant regression\nimport statsmodels.api as sm\nfor h in [1,3]:\n    s=f[f.horizon==h].sort_values('origin_date')\n    d=s[s.model=='naive'].e.values**2-s[s.model=='model'].e.values**2\n    res=sm.OLS(d,np.ones(10)).fit(cov_type='HAC',cov_kwds={'maxlags':h-1,'use_correction':False}) if h>1 else sm.OLS(d,np.ones(10)).fit(cov_type='HC0')\n    ok(f'DM h{h} matches statsmodels HAC ({res.tvalues[0]:.4f})',abs(res.tvalues[0]-r[f'dm_stat_h{h}'])<1e-6)\n    ok(f'rel impr h{h}',abs(1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']-r[f'rel_improvement_rmse_h{h}'])<1e-12)\n    b=r['supplementary']['bootstrap_rmse_diff'][f'h{h}']; ok(f'boot CI contains point h{h}',b['ci95'][0]<=b['rmse_diff_model_minus_naive']<=b['ci95'][1])\n    ok(f'conclusion code h{h}',r[f'conclusion_code_h{h}']==('model_better' if r[f'rmse_model_h{h}']<r[f'rmse_naive_h{h}'] else 'naive_better')+('_significant' if r[f'dm_pvalue_h{h}']<0.05 else '_not_significant'))\nok('n_analysed=20',r['n_analysed']==20)\nok('all 24 csv in n_input_rows',len(r['n_input_rows'])==24)\nok('revision mean recompute',abs(np.mean(np.abs(list(r['supplementary']['revisions_h1_targets'].values())))-r['mean_abs_revision_h1_targets'])<1e-12)\nok('magnitudes: model rmse within 0.3x-2x naive',all(0.3<r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']<2 for h in [1,3]))\nEOF\ngrep -n \"current\" out/analysis.py | head"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1580,"cache_read_input_tokens":38472,"output_tokens":2105,"output_tokens_details":{"thinking_tokens":232},"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":1580},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXsyx3m79dBnXWtiS5kf","requestRef":"785365e1-5f89-4ded-b3b8-3405f34d093b","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d20f6082-829f-4469-846a-ba2548d9c898","timestamp":"2026-10-30T05:36:33.496Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}78{"parentUuid":"d20f6082-829f-4469-846a-ba2548d9c898","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01KX9MGP6Y2Cm4YVfGvLEgkm","type":"tool_result","content":"IDENTICAL\nPASS 80 rows, 10x2x4 unique\nPASS vintage_used==origin\nPASS target > origin-month-? (target after last month; target month first-released after origin)\nPASS naive forecast == first-release yoy of last(V) (all 10)\nPASS rmse/mae naive h1\nPASS rmse/mae naive h3\nPASS rmse/mae snaive h1\nPASS rmse/mae snaive h3\nPASS rmse/mae ar1 h1\nPASS rmse/mae ar1 h3\nPASS rmse/mae model h1\nPASS rmse/mae model h3\nPASS DM h1 matches statsmodels HAC (2.4290)\nPASS rel impr h1\nPASS boot CI contains point h1\nPASS conclusion code h1\nPASS DM h3 matches statsmodels HAC (1.5466)\nPASS rel impr h3\nPASS boot CI contains point h3\nPASS conclusion code h3\nPASS n_analysed=20\nFAIL all 24 csv in n_input_rows\nPASS revision mean recompute\nPASS magnitudes: model rmse within 0.3x-2x naive\n143:# RSAFS_current is used ONLY here; it never enters a forecast.\n144:cur = read_series(\"RSAFS_current.csv\")\n212:        {\"issue\": \"Benchmark/annual revision of RSAFS levels: the current vintage is ~4% lower in level and its YoY growth is \"\n216:        {\"issue\": \"UMCSENT has 210 empty values (all before 1978, quarterly survey era) and is a current (not real-time) vintage.\",","is_error":false}]},"uuid":"386ff3d8-dedc-408a-907d-fb45f0ce451d","timestamp":"2026-10-30T05:36:35.688Z","toolUseResult":{"stdout":"IDENTICAL\nPASS 80 rows, 10x2x4 unique\nPASS vintage_used==origin\nPASS target > origin-month-? (target after last month; target month first-released after origin)\nPASS naive forecast == first-release yoy of last(V) (all 10)\nPASS rmse/mae naive h1\nPASS rmse/mae naive h3\nPASS rmse/mae snaive h1\nPASS rmse/mae snaive h3\nPASS rmse/mae ar1 h1\nPASS rmse/mae ar1 h3\nPASS rmse/mae model h1\nPASS rmse/mae model h3\nPASS DM h1 matches statsmodels HAC (2.4290)\nPASS rel impr h1\nPASS boot CI contains point h1\nPASS conclusion code h1\nPASS DM h3 matches statsmodels HAC (1.5466)\nPASS rel impr h3\nPASS boot CI contains point h3\nPASS conclusion code h3\nPASS n_analysed=20\nFAIL all 24 csv in n_input_rows\nPASS revision mean recompute\nPASS magnitudes: model rmse within 0.3x-2x naive\n143:# RSAFS_current is used ONLY here; it never enters a forecast.\n144:cur = read_series(\"RSAFS_current.csv\")\n212:        {\"issue\": \"Benchmark/annual revision of RSAFS levels: the current vintage is ~4% lower in level and its YoY growth is \"\n216:        {\"issue\": \"UMCSENT has 210 empty values (all before 1978, quarterly survey era) and is a current (not real-time) vintage.\",","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"d20f6082-829f-4469-846a-ba2548d9c898","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}79{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"f584960eb4d29cb4dd3840a23e9b718cb9f5344c45f3053078d17b5968673013","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01KX9MGP6Y2Cm4YVfGvLEgkm","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; sed -i '' 's/ Consequence: 2026-02 is never an h=1 target; some target months are shared (e.g. h=3 targets)./ Consequence: some target months are shared between h=1 and h=3 (13 distinct target months)./' out/state/data_audit.md\nshasum -a 256 out/results.json out/forecasts.csv out/table1.csv > /tmp/h1.txt; rm out/results.json out/forecasts.csv out/table1.csv out/figure1.png out/exclusions.csv; ~/wp29/venv/bin/python out/analysis.py > /dev/null; shasum -a 256 out/results.json out/forecasts.csv out/table1.csv | diff - /tmp/h1.txt && echo IDENTICAL\n~/wp29/venv/bin/python - <<'EOF'\nimport json,pandas as pd,numpy as np\nr=json.load(open('out/results.json')); f=pd.read_csv('out/forecasts.csv'); fr=pd.read_csv('data/first_release.csv')\nok=lambda n,c: print(('PASS' if c else 'FAIL'),n)\nok('80 rows, 10x2x4 unique',len(f)==80 and f.groupby(['origin_date','horizon','model']).size().eq(1).all() and f.origin_date.nunique()==10)\nok('vintage_used==origin',(f.vintage_used==f.origin_date).all())\nok('target > origin-month-? (target after last month; target month first-released after origin)',all(pd.to_datetime(fr.set_index('target_month').loc[t,'first_release_vintage'])>pd.to_datetime(o) for t,o in zip(f.target_date,f.origin_date)))\n# naive equals first release of last(V) where first-release vintage == V\nfri=fr.set_index('target_month')\nn=f[(f.model=='naive')&(f.horizon==1)]\nchk=[]\nfor _,row in n.iterrows():\n    last=(pd.Timestamp(row.target_date)-pd.DateOffset(months=1)).strftime('%Y-%m-%d')\n    chk.append(abs(fri.loc[last,'yoy_first_release']-row.forecast)<1e-5)\nok('naive forecast == first-release yoy of last(V) (all 10)',all(chk))\n# recompute RMSE/MAE\nf['e']=f.actual_first_release-f.forecast\nfor m in ['naive','snaive','ar1','model']:\n  for h in [1,3]:\n    e=f[(f.model==m)&(f.horizon==h)].e\n    ok(f'rmse/mae {m} h{h}',abs(np.sqrt((e**2).mean())-r[f'rmse_{m}_h{h}'])<1e-9 and abs(e.abs().mean()-r[f'mae_{m}_h{h}'])<1e-9 and r[f'rmse_{m}_h{h}']>=r[f'mae_{m}_h{h}']>0)\n# DM independent via statsmodels HAC on constant regression\nimport statsmodels.api as sm\nfor h in [1,3]:\n    s=f[f.horizon==h].sort_values('origin_date')\n    d=s[s.model=='naive'].e.values**2-s[s.model=='model'].e.values**2\n    res=sm.OLS(d,np.ones(10)).fit(cov_type='HAC',cov_kwds={'maxlags':h-1,'use_correction':False}) if h>1 else sm.OLS(d,np.ones(10)).fit(cov_type='HC0')\n    ok(f'DM h{h} matches statsmodels HAC ({res.tvalues[0]:.4f})',abs(res.tvalues[0]-r[f'dm_stat_h{h}'])<1e-6)\n    ok(f'rel impr h{h}',abs(1-r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']-r[f'rel_improvement_rmse_h{h}'])<1e-12)\n    b=r['supplementary']['bootstrap_rmse_diff'][f'h{h}']; ok(f'boot CI contains point h{h}',b['ci95'][0]<=b['rmse_diff_model_minus_naive']<=b['ci95'][1])\n    ok(f'conclusion code h{h}',r[f'conclusion_code_h{h}']==('model_better' if r[f'rmse_model_h{h}']<r[f'rmse_naive_h{h}'] else 'naive_better')+('_significant' if r[f'dm_pvalue_h{h}']<0.05 else '_not_significant'))\nok('n_analysed=20',r['n_analysed']==20)\nok('all 24 csv in n_input_rows',len(r['n_input_rows'])==24)\nok('revision mean recompute',abs(np.mean(np.abs(list(r['supplementary']['revisions_h1_targets'].values())))-r['mean_abs_revision_h1_targets'])<1e-12)\nok('magnitudes: model rmse within 0.3x-2x naive',all(0.3<r[f'rmse_model_h{h}']/r[f'rmse_naive_h{h}']<2 for h in [1,3]))\nEOF\ngrep -n \"current\" out/analysis.py | head"}}]}}80{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"1116c015-a95a-4bb3-89e1-214082d8eb33","timestamp":"2026-10-30T05:36:35.691Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"785365e1-5f89-4ded-b3b8-3405f34d093b","keep":24,"tail":["f584960eb4d29cb4dd3840a23e9b718cb9f5344c45f3053078d17b5968673013","3a6d1a8e6206c614fd60d60cf96db56ce1d6f4ad02a92743ab464a89c1e3f289"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",25,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"312b55ea1dd4513dd789f48562a4c525778464bbc0470e5a202b8814797a5eb5"}81{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"386ff3d8-dedc-408a-907d-fb45f0ce451d","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}82{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}83{"type":"tools-used","tools":["Bash","Read"],"sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}84{"parentUuid":"386ff3d8-dedc-408a-907d-fb45f0ce451d","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1QFe1RPCE331yDyV9","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":2654,"cache_read_input_tokens":40052,"output_tokens":332,"output_tokens_details":{"thinking_tokens":146},"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":2654},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1250,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt1Pz23msNJj5LMCfpP","requestRef":"1116c015-a95a-4bb3-89e1-214082d8eb33","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"fcdb92d0-768a-40d4-9d9e-8bce53f37136","timestamp":"2026-10-30T05:36:38.027Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}85{"parentUuid":"fcdb92d0-768a-40d4-9d9e-8bce53f37136","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1QFe1RPCE331yDyV9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01G3wEPEFY1hHPiPq2Yfhsyq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; python3 -c \"import json;print(json.load(open('out/results.json'))['n_input_rows'])\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2654,"cache_read_input_tokens":40052,"output_tokens":332,"output_tokens_details":{"thinking_tokens":146},"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":2654},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt1Pz23msNJj5LMCfpP","requestRef":"1116c015-a95a-4bb3-89e1-214082d8eb33","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"68eca133-c1c0-4408-b1fd-589273861e1a","timestamp":"2026-10-30T05:36:38.779Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}86{"parentUuid":"68eca133-c1c0-4408-b1fd-589273861e1a","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01G3wEPEFY1hHPiPq2Yfhsyq","type":"tool_result","content":"{'first_release.csv': 28, 'vintages/PAYEMS_vintage_2025-10-31.csv': 1040, 'vintages/PAYEMS_vintage_2025-11-30.csv': 1041, 'vintages/PAYEMS_vintage_2025-12-31.csv': 1043, 'vintages/PAYEMS_vintage_2026-01-31.csv': 1044, 'vintages/PAYEMS_vintage_2026-02-28.csv': 1045, 'vintages/PAYEMS_vintage_2026-03-31.csv': 1046, 'vintages/PAYEMS_vintage_2026-04-30.csv': 1047, 'vintages/PAYEMS_vintage_2026-05-31.csv': 1048, 'vintages/PAYEMS_vintage_2026-06-30.csv': 1049, 'vintages/PAYEMS_vintage_2026-07-31.csv': 1050, 'UMCSENT.csv': 887, 'vintages/RSAFS_vintage_2025-10-31.csv': 404, 'vintages/RSAFS_vintage_2025-11-30.csv': 405, 'vintages/RSAFS_vintage_2025-12-31.csv': 406, 'vintages/RSAFS_vintage_2026-01-31.csv': 407, 'vintages/RSAFS_vintage_2026-02-28.csv': 408, 'vintages/RSAFS_vintage_2026-03-31.csv': 409, 'vintages/RSAFS_vintage_2026-04-30.csv': 411, 'vintages/RSAFS_vintage_2026-05-31.csv': 412, 'vintages/RSAFS_vintage_2026-06-30.csv': 413, 'vintages/RSAFS_vintage_2026-07-31.csv': 414, 'RSAFS_current.csv': 417}","is_error":false}]},"uuid":"0e6f3551-dc4c-418d-ac30-e5549f4d8b55","timestamp":"2026-10-30T05:36:38.840Z","toolUseResult":{"stdout":"{'first_release.csv': 28, 'vintages/PAYEMS_vintage_2025-10-31.csv': 1040, 'vintages/PAYEMS_vintage_2025-11-30.csv': 1041, 'vintages/PAYEMS_vintage_2025-12-31.csv': 1043, 'vintages/PAYEMS_vintage_2026-01-31.csv': 1044, 'vintages/PAYEMS_vintage_2026-02-28.csv': 1045, 'vintages/PAYEMS_vintage_2026-03-31.csv': 1046, 'vintages/PAYEMS_vintage_2026-04-30.csv': 1047, 'vintages/PAYEMS_vintage_2026-05-31.csv': 1048, 'vintages/PAYEMS_vintage_2026-06-30.csv': 1049, 'vintages/PAYEMS_vintage_2026-07-31.csv': 1050, 'UMCSENT.csv': 887, 'vintages/RSAFS_vintage_2025-10-31.csv': 404, 'vintages/RSAFS_vintage_2025-11-30.csv': 405, 'vintages/RSAFS_vintage_2025-12-31.csv': 406, 'vintages/RSAFS_vintage_2026-01-31.csv': 407, 'vintages/RSAFS_vintage_2026-02-28.csv': 408, 'vintages/RSAFS_vintage_2026-03-31.csv': 409, 'vintages/RSAFS_vintage_2026-04-30.csv': 411, 'vintages/RSAFS_vintage_2026-05-31.csv': 412, 'vintages/RSAFS_vintage_2026-06-30.csv': 413, 'vintages/RSAFS_vintage_2026-07-31.csv': 414, 'RSAFS_current.csv': 417}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"68eca133-c1c0-4408-b1fd-589273861e1a","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}87{"parentUuid":"0e6f3551-dc4c-418d-ac30-e5549f4d8b55","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1QFe1RPCE331yDyV9","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01AjU6pUiLbQd2Bg7uAvghvw","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0013/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":2654,"cache_read_input_tokens":40052,"output_tokens":332,"output_tokens_details":{"thinking_tokens":146},"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":2654},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":2,"requestId":"req_011CgXt1Pz23msNJj5LMCfpP","requestRef":"1116c015-a95a-4bb3-89e1-214082d8eb33","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"720a995d-4fba-49db-a90e-d973a383af79","timestamp":"2026-10-30T05:36:39.188Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}88{"parentUuid":"720a995d-4fba-49db-a90e-d973a383af79","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01AjU6pUiLbQd2Bg7uAvghvw","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"97a7ea24-fb67-4c9b-8080-f525931be789","timestamp":"2026-10-30T05:36:39.195Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":147406,"dimensions":{"originalWidth":1170,"originalHeight":910,"displayWidth":1170,"displayHeight":910}}},"sourceToolAssistantUUID":"720a995d-4fba-49db-a90e-d973a383af79","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}89{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"ae8d90b3d51cddacd3ef55a7455722814fe5ecf9f34b4d084db8b64f84effec4","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01G3wEPEFY1hHPiPq2Yfhsyq","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; python3 -c \"import json;print(json.load(open('out/results.json'))['n_input_rows'])\""}},{"type":"tool_use","id":"toolu_01AjU6pUiLbQd2Bg7uAvghvw","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RT0013/out/figure1.png"}}]}}90{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"c8b9bdd0dbc9e7c7333676ceca33dc207d313d87d6a4db30e91a0ec65bf2be06","message":{"role":"user","content":[{"tool_use_id":"toolu_01G3wEPEFY1hHPiPq2Yfhsyq","type":"tool_result","content":"{'first_release.csv': 28, 'vintages/PAYEMS_vintage_2025-10-31.csv': 1040, 'vintages/PAYEMS_vintage_2025-11-30.csv': 1041, 'vintages/PAYEMS_vintage_2025-12-31.csv': 1043, 'vintages/PAYEMS_vintage_2026-01-31.csv': 1044, 'vintages/PAYEMS_vintage_2026-02-28.csv': 1045, 'vintages/PAYEMS_vintage_2026-03-31.csv': 1046, 'vintages/PAYEMS_vintage_2026-04-30.csv': 1047, 'vintages/PAYEMS_vintage_2026-05-31.csv': 1048, 'vintages/PAYEMS_vintage_2026-06-30.csv': 1049, 'vintages/PAYEMS_vintage_2026-07-31.csv': 1050, 'UMCSENT.csv': 887, 'vintages/RSAFS_vintage_2025-10-31.csv': 404, 'vintages/RSAFS_vintage_2025-11-30.csv': 405, 'vintages/RSAFS_vintage_2025-12-31.csv': 406, 'vintages/RSAFS_vintage_2026-01-31.csv': 407, 'vintages/RSAFS_vintage_2026-02-28.csv': 408, 'vintages/RSAFS_vintage_2026-03-31.csv': 409, 'vintages/RSAFS_vintage_2026-04-30.csv': 411, 'vintages/RSAFS_vintage_2026-05-31.csv': 412, 'vintages/RSAFS_vintage_2026-06-30.csv': 413, 'vintages/RSAFS_vintage_2026-07-31.csv': 414, 'RSAFS_current.csv': 417}","is_error":false},{"tool_use_id":"toolu_01AjU6pUiLbQd2Bg7uAvghvw","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]}}91{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"38a28824-0ec7-48fa-a782-23476db0227f","timestamp":"2026-10-30T05:36:39.199Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"1116c015-a95a-4bb3-89e1-214082d8eb33","keep":26,"tail":["ae8d90b3d51cddacd3ef55a7455722814fe5ecf9f34b4d084db8b64f84effec4","c8b9bdd0dbc9e7c7333676ceca33dc207d313d87d6a4db30e91a0ec65bf2be06"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",27,"content",1],"value":{"type":"ephemeral"}}],"requestDigest":"e52cbe532398e9dc59092bade2dfb8d8c7e9795d38cca6dbe92f7a61d73dcee3"}92{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"97a7ea24-fb67-4c9b-8080-f525931be789","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}93{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}94{"parentUuid":"97a7ea24-fb67-4c9b-8080-f525931be789","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1fCJgBefNDvxaNJ4i","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSwggKEAgTGAI4AUIIdGhpbmtpbmcSDGtArd8Kyi/536y0zBoMwMpe+LOsIvqO9yIWIjAOoggDWCljp6cF1LkvtYQplK+COKCuaSjSrtxGVaIhIE9gUUkEXwDpkPsF1N0lid0q3wdiPXzFvqQNTinLa+/RQ3O83A1f5rSDNLdoHwDSKfivQwqESwZsm4fRTTkNyPfOZIFNJCd20KogmMbnFBIGg8uP92c0oyN3t18RSVnt3C/mTUYZ53f4fTa9CMiCTHU0vjeYKZeG/ydsnyfeiQ4UdhcEBhjTrxqsSOZ1+XSpAA6U4a5JM9N5GTlz48P2LwKd1TRaTvrmPYLAiFjXx/PFzg5x+rTJh0HA7bU3jemYXlNVd5E1G5fdCej9j2cV3JBEmwyEQXE0Ig+7KT7nVQTo5CUwk0UeeLm9MW0bySDyMGBoKSBNgYWzV8VVrBfT10+CgudzBQNGjEGBqMMQTwUVkjyooeAKIW5Z1hq23IJLdMByyc+ytB698u4rsDXZ07c0mJ1+E08/71AEdlSbRdM6Htg6M9QnN605szELo+yZFkeYyaVTEqRohzr2o4v0aqBQcpRaOEU4FFibBAhc2KofFqJL+tPl5Z6yVJMdCzEi+TT/bjdRjHtJ6RSBLZ8U9hhPPGVyB6wV50HRXJ3AWTdf7LAIY2slIcRHiKYIcs45AqHpEV0Y4gjOeOo71k/p+dg4o/0MJmhZyK22un5VwR28EWkbXgBrFuSna6qRUInRIn6C/ewZqDZUG9Bpgon8L8p3KhKPH5k1cFn6mB0rXfHwgXMowujhvIWRI6/YrM+hDRzZvTfW5/IZsfT2yjOCuyw2wnijgfqXugKOs5tn/qgeUNaw+OnprYGAxzo+OYD2F3XK2SkGEuSWTjZ9YYbdpyqTSOW+uo9p2zLsVvOXfucBoov15UFOXpEcZgnvDkuun8SNrdt4HjdA7+pnlx/EVe88ohDW9DOiOozZhtzLzyDqspFpnKBhBwCFJkMgmOYzwB7u9EbTGfKueVOf9sGD9FmhROKar6RRFVaDYenvQJ5HBjRzZEdaip++VGB5o2Is5TySon0TGTj+w18hfgRFZ9X6cUtof8i3SCBW7tieyazCzqMgIlDreCnMQrsnmtyEIxp7jgGy98WW6OktF6qpmTPwxZpIHBEwrBR6uGVfhCqoWZjXXIFZQXx8rFn9TkOFpg4+Haou8v0/gGpEHQ6tiaObKBrtSnUfnCY+CWhNcV7XjQcO8veu6f8wdnk+h4qsYr1URVIqYMrhp3hC2DtuYjZMkDTOv+auYhuHs3S1ikAg/N1TEwLeZjGrX+hfD1Ns3Xyqc3AbXnGKPW1mV+TpxhVG9Eay4HeUeJwa5oPV7xmeFKJ6w0kmU3MQjtgJ/+2uG4Y6AQuEc4Sj9dibBw0pkI8MAj5iGKswT1/dddbkWiXQgweuFJxnr/YorrRcCOXzNYuJGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2422,"cache_read_input_tokens":42706,"output_tokens":315,"output_tokens_details":{"thinking_tokens":159},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2422},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1007,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt1f19QfNQ2jpBV42WY","requestRef":"38a28824-0ec7-48fa-a782-23476db0227f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f6a7ce34-d217-45ae-b688-e254fa66a016","timestamp":"2026-10-30T05:36:41.459Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}95{"parentUuid":"f6a7ce34-d217-45ae-b688-e254fa66a016","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1fCJgBefNDvxaNJ4i","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_0132tgM6XVFfUpx7s4mUPHjB","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; python3 -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n  if k not in('data_issues','n_input_rows','supplementary','model_description'):print(k,v)\"; cat out/table1.csv"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2422,"cache_read_input_tokens":42706,"output_tokens":315,"output_tokens_details":{"thinking_tokens":159},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":2422},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt1f19QfNQ2jpBV42WY","requestRef":"38a28824-0ec7-48fa-a782-23476db0227f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8330f5f5-ebc0-4ae2-8f8a-a4fde91d71f2","timestamp":"2026-10-30T05:36:42.313Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}96{"parentUuid":"8330f5f5-ebc0-4ae2-8f8a-a4fde91d71f2","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_0132tgM6XVFfUpx7s4mUPHjB","type":"tool_result","content":"task_id T1-forecast\nmodel_name BED (base-effect drift)\nn_origins 10\nfirst_origin 2025-10-31\nlast_origin 2026-07-31\nrmse_naive_h1 0.996874361153601\nmae_naive_h1 0.8487221999999999\nrmse_naive_h3 1.4200403019751233\nmae_naive_h3 1.2004486\nrmse_snaive_h1 1.674542814799132\nmae_snaive_h1 1.3066698\nrmse_snaive_h3 1.3160788608225193\nmae_snaive_h3 1.0658687\nrmse_ar1_h1 0.940524354787796\nmae_ar1_h1 0.7976509999999999\nrmse_ar1_h3 1.1871176370926342\nmae_ar1_h3 0.9526893999999999\nrmse_model_h1 0.5502976390310066\nmae_model_h1 0.48633190000000004\nrmse_model_h3 1.1422196608203694\nmae_model_h3 0.9339774000000001\nrel_improvement_rmse_h1 0.4479769362367869\nrel_improvement_rmse_h3 0.19564278617186803\ndm_stat_h1 2.4289778933188826\ndm_pvalue_h1 0.015141455540092164\ndm_stat_h3 1.546577321548468\ndm_pvalue_h3 0.12196520179653336\nconclusion_code_h1 model_better_significant\nconclusion_code_h3 model_better_not_significant\nmean_abs_revision_h1_targets 0.5482198028388884\nfeasibility complete\nfeasibility_reason None\nn_analysed 20\nrandom_seed 20261030\nmodel,horizon,rmse,mae,n\nnaive,1,0.996874361153601,0.8487221999999999,10\nnaive,3,1.4200403019751233,1.2004486,10\nsnaive,1,1.674542814799132,1.3066698,10\nsnaive,3,1.3160788608225193,1.0658687,10\nar1,1,0.940524354787796,0.7976509999999999,10\nar1,3,1.1871176370926342,0.9526893999999999,10\nmodel,1,0.5502976390310066,0.48633190000000004,10\nmodel,3,1.1422196608203694,0.9339774000000001,10","is_error":false}]},"uuid":"0b59628e-32dc-4294-a718-6c3f4502ab19","timestamp":"2026-10-30T05:36:42.374Z","toolUseResult":{"stdout":"task_id T1-forecast\nmodel_name BED (base-effect drift)\nn_origins 10\nfirst_origin 2025-10-31\nlast_origin 2026-07-31\nrmse_naive_h1 0.996874361153601\nmae_naive_h1 0.8487221999999999\nrmse_naive_h3 1.4200403019751233\nmae_naive_h3 1.2004486\nrmse_snaive_h1 1.674542814799132\nmae_snaive_h1 1.3066698\nrmse_snaive_h3 1.3160788608225193\nmae_snaive_h3 1.0658687\nrmse_ar1_h1 0.940524354787796\nmae_ar1_h1 0.7976509999999999\nrmse_ar1_h3 1.1871176370926342\nmae_ar1_h3 0.9526893999999999\nrmse_model_h1 0.5502976390310066\nmae_model_h1 0.48633190000000004\nrmse_model_h3 1.1422196608203694\nmae_model_h3 0.9339774000000001\nrel_improvement_rmse_h1 0.4479769362367869\nrel_improvement_rmse_h3 0.19564278617186803\ndm_stat_h1 2.4289778933188826\ndm_pvalue_h1 0.015141455540092164\ndm_stat_h3 1.546577321548468\ndm_pvalue_h3 0.12196520179653336\nconclusion_code_h1 model_better_significant\nconclusion_code_h3 model_better_not_significant\nmean_abs_revision_h1_targets 0.5482198028388884\nfeasibility complete\nfeasibility_reason None\nn_analysed 20\nrandom_seed 20261030\nmodel,horizon,rmse,mae,n\nnaive,1,0.996874361153601,0.8487221999999999,10\nnaive,3,1.4200403019751233,1.2004486,10\nsnaive,1,1.674542814799132,1.3066698,10\nsnaive,3,1.3160788608225193,1.0658687,10\nar1,1,0.940524354787796,0.7976509999999999,10\nar1,3,1.1871176370926342,0.9526893999999999,10\nmodel,1,0.5502976390310066,0.48633190000000004,10\nmodel,3,1.1422196608203694,0.9339774000000001,10","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8330f5f5-ebc0-4ae2-8f8a-a4fde91d71f2","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}97{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"471f083c1c9d82938baa81ba83e1f2b5b156afb5d855c96429bf3424a8d2dd4a","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_0132tgM6XVFfUpx7s4mUPHjB","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; python3 -c \"\nimport json;r=json.load(open('out/results.json'))\nfor k,v in r.items():\n  if k not in('data_issues','n_input_rows','supplementary','model_description'):print(k,v)\"; cat out/table1.csv"}}]}}98{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"4a8423f1-b424-498c-a9dc-0c1060851294","timestamp":"2026-10-30T05:36:42.378Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"38a28824-0ec7-48fa-a782-23476db0227f","keep":28,"tail":["471f083c1c9d82938baa81ba83e1f2b5b156afb5d855c96429bf3424a8d2dd4a","fda6b454e4a5722e74f07a2676e1a05895981beb5b8a3553fa8dd839b5bd8bf6"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",29,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"78b4b0c4576c217bf3f3d95d60794f0a5679fe61ad6d88c7b4601e94726bf4bc"}99{"parentUuid":"0b59628e-32dc-4294-a718-6c3f4502ab19","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1traYo8mv2jYXzSgd","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":1081,"cache_read_input_tokens":45128,"output_tokens":1649,"output_tokens_details":{"thinking_tokens":45},"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":1081},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":484,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt1taDRJQKZHxwXUbwP","requestRef":"4a8423f1-b424-498c-a9dc-0c1060851294","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"62abfca4-e408-4b70-bf58-a2fdbe61c1c0","timestamp":"2026-10-30T05:36:43.798Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}100{"parentUuid":"62abfca4-e408-4b70-bf58-a2fdbe61c1c0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt1traYo8mv2jYXzSgd","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01T45myYAzt6Un57MYwUzyVE","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat > state/checks.md <<'EOF'\n# Verification checks (P4) — 2026-10-30\n\n| # | check | outcome |\n|---|---|---|\n| 1 | Delete results.json, forecasts.csv, table1.csv, figure1.png, exclusions.csv; re-run analysis.py; SHA-256 of results.json/forecasts.csv/table1.csv identical to previous run | PASS (IDENTICAL) |\n| 2 | forecasts.csv: 80 rows, exactly one per (origin, horizon, model), 10 origins | PASS |\n| 3 | vintage_used == origin_date for every row (only vintage V used at origin V) | PASS |\n| 4 | Every target month's first-release vintage is strictly after the origin (actual not observable at the origin) | PASS |\n| 5 | Naive h=1 forecast equals the first-release YoY of last(V) for all 10 origins (independent cross-check vintage vs first_release.csv) | PASS |\n| 6 | RMSE/MAE recomputed from forecasts.csv match results.json (1e-9), RMSE ≥ MAE > 0 for all 8 cells | PASS |\n| 7 | DM statistic reproduced independently with statsmodels OLS-on-constant HAC (Bartlett, maxlags=h−1, no small-sample correction; HC0 at h=1): 2.4290 (h1), 1.5466 (h3) | PASS |\n| 8 | Long-run variances positive (0.809 at h1, 2.119 at h3) | PASS |\n| 9 | rel_improvement = 1 − RMSE_model/RMSE_naive identity | PASS |\n| 10 | conclusion codes consistent with RMSE ordering and p<0.05 | PASS |\n| 11 | Bootstrap 95% intervals contain their point estimates (h1, h3) | PASS |\n| 12 | n_analysed = 20 = 10 origins × 2 horizons; exclusions ledger: 20 − 0 = 20 | PASS |\n| 13 | n_input_rows has 23 entries (10 RSAFS + 10 PAYEMS vintages + UMCSENT + RSAFS_current + first_release) matching README row counts | PASS (initial assertion \"24\" in my check script was my own miscount; 23 is the correct number of CSVs) |\n| 14 | mean_abs_revision recomputed from per-target revisions | PASS |\n| 15 | Magnitude: model RMSE between 0.3× and 2× naive; all errors in percent units, comparable to YoY range 2.4–6.7% | PASS |\n| 16 | Code inspection: RSAFS_current.csv read only after all forecasts are written, used only for estimand (d); PAYEMS/UMCSENT not used in forecasts | PASS |\n| 17 | Model specification fixed (log.md entry) before any out-of-sample error was computed; single run, no tuning | PASS (documented) |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of 23 CSVs match README\",\"row/col counts, date ranges, gaps, missing, duplicates checked\",\"first_release consistency with vintages checked\",\"availability violations identified (RSAFS_current, first_release) and handling written\"],\"notes\":\"see data_audit.md\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) computed for both horizons with first-release evaluation; values in results.json rmse_/mae_ keys\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes all required outputs\",\"seed 20261030 fixed and recorded\"],\"notes\":\"BED model pre-registered in log.md\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run hash identical\",\"17 consistency checks in checks.md all pass\"],\"notes\":\"\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ncat >> state/log.md <<'EOF'\n- 2026-10-30 P1 passed (audit). P2 passed: baselines naive/snaive/AR(1) computed. P3 passed: analysis.py complete, deterministic.\n- 2026-10-30 P4 passed: clean re-run identical; all checks in checks.md pass. Starting P5.\nEOF"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1081,"cache_read_input_tokens":45128,"output_tokens":1649,"output_tokens_details":{"thinking_tokens":45},"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":1081},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt1taDRJQKZHxwXUbwP","requestRef":"4a8423f1-b424-498c-a9dc-0c1060851294","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9d6726ef-04e6-491f-8ee7-d0f24b66948d","timestamp":"2026-10-30T05:36:56.364Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}101{"parentUuid":"9d6726ef-04e6-491f-8ee7-d0f24b66948d","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01T45myYAzt6Un57MYwUzyVE","type":"tool_result","content":"Traceback (most recent call last):\n  File \"<stdin>\", line 2, in <module>\nFileNotFoundError: [Errno 2] No such file or directory: 'out/state/phases.json'","is_error":false}]},"uuid":"d082e500-95e1-4718-86e4-c94d932720bc","timestamp":"2026-10-30T05:36:56.451Z","toolUseResult":{"stdout":"Traceback (most recent call last):\n  File \"<stdin>\", line 2, in <module>\nFileNotFoundError: [Errno 2] No such file or directory: 'out/state/phases.json'","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"9d6726ef-04e6-491f-8ee7-d0f24b66948d","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}102{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"9c8ae3c3430b6c17dc6bb44073e8f406a82611032ddf61a5245b1131d860a407","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01T45myYAzt6Un57MYwUzyVE","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat > state/checks.md <<'EOF'\n# Verification checks (P4) — 2026-10-30\n\n| # | check | outcome |\n|---|---|---|\n| 1 | Delete results.json, forecasts.csv, table1.csv, figure1.png, exclusions.csv; re-run analysis.py; SHA-256 of results.json/forecasts.csv/table1.csv identical to previous run | PASS (IDENTICAL) |\n| 2 | forecasts.csv: 80 rows, exactly one per (origin, horizon, model), 10 origins | PASS |\n| 3 | vintage_used == origin_date for every row (only vintage V used at origin V) | PASS |\n| 4 | Every target month's first-release vintage is strictly after the origin (actual not observable at the origin) | PASS |\n| 5 | Naive h=1 forecast equals the first-release YoY of last(V) for all 10 origins (independent cross-check vintage vs first_release.csv) | PASS |\n| 6 | RMSE/MAE recomputed from forecasts.csv match results.json (1e-9), RMSE ≥ MAE > 0 for all 8 cells | PASS |\n| 7 | DM statistic reproduced independently with statsmodels OLS-on-constant HAC (Bartlett, maxlags=h−1, no small-sample correction; HC0 at h=1): 2.4290 (h1), 1.5466 (h3) | PASS |\n| 8 | Long-run variances positive (0.809 at h1, 2.119 at h3) | PASS |\n| 9 | rel_improvement = 1 − RMSE_model/RMSE_naive identity | PASS |\n| 10 | conclusion codes consistent with RMSE ordering and p<0.05 | PASS |\n| 11 | Bootstrap 95% intervals contain their point estimates (h1, h3) | PASS |\n| 12 | n_analysed = 20 = 10 origins × 2 horizons; exclusions ledger: 20 − 0 = 20 | PASS |\n| 13 | n_input_rows has 23 entries (10 RSAFS + 10 PAYEMS vintages + UMCSENT + RSAFS_current + first_release) matching README row counts | PASS (initial assertion \"24\" in my check script was my own miscount; 23 is the correct number of CSVs) |\n| 14 | mean_abs_revision recomputed from per-target revisions | PASS |\n| 15 | Magnitude: model RMSE between 0.3× and 2× naive; all errors in percent units, comparable to YoY range 2.4–6.7% | PASS |\n| 16 | Code inspection: RSAFS_current.csv read only after all forecasts are written, used only for estimand (d); PAYEMS/UMCSENT not used in forecasts | PASS |\n| 17 | Model specification fixed (log.md entry) before any out-of-sample error was computed; single run, no tuning | PASS (documented) |\nEOF\n~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of 23 CSVs match README\",\"row/col counts, date ranges, gaps, missing, duplicates checked\",\"first_release consistency with vintages checked\",\"availability violations identified (RSAFS_current, first_release) and handling written\"],\"notes\":\"see data_audit.md\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) computed for both horizons with first-release evaluation; values in results.json rmse_/mae_ keys\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes all required outputs\",\"seed 20261030 fixed and recorded\"],\"notes\":\"BED model pre-registered in log.md\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run hash identical\",\"17 consistency checks in checks.md all pass\"],\"notes\":\"\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ncat >> state/log.md <<'EOF'\n- 2026-10-30 P1 passed (audit). P2 passed: baselines naive/snaive/AR(1) computed. P3 passed: analysis.py complete, deterministic.\n- 2026-10-30 P4 passed: clean re-run identical; all checks in checks.md pass. Starting P5.\nEOF"}}]}}103{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"b6c372ed-8778-4eab-a1b8-bdbebdf18f83","timestamp":"2026-10-30T05:36:56.454Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"4a8423f1-b424-498c-a9dc-0c1060851294","keep":30,"tail":["9c8ae3c3430b6c17dc6bb44073e8f406a82611032ddf61a5245b1131d860a407","457c1d3869a414134342e98f9cd14f8356a21ac4bff5bab22018b999c4b5539d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",31,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"81cfcd997d2fce6b68296d1ca3dd6daefb1954575dffdbdcab03654f2d2f603f"}104{"parentUuid":"d082e500-95e1-4718-86e4-c94d932720bc","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt2w5KFWWf6SnXzKC8d","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MMBNKWPjVvUsm4F35Bxe8i","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of 23 CSVs match README\",\"row/col counts, date ranges, gaps, missing, duplicates checked\",\"first_release consistency with vintages checked\",\"availability violations identified (RSAFS_current, first_release) and handling written\"],\"notes\":\"see data_audit.md\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) computed for both horizons with first-release evaluation; values in results.json rmse_/mae_ keys\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes all required outputs\",\"seed 20261030 fixed and recorded\"],\"notes\":\"BED model pre-registered in log.md\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run hash identical\",\"17 consistency checks in checks.md all pass\"],\"notes\":\"\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ntail -3 out/state/log.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1718,"cache_read_input_tokens":46209,"output_tokens":491,"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":1718},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt2vnCK2PAx3d7UzZH5","requestRef":"b6c372ed-8778-4eab-a1b8-bdbebdf18f83","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"27e4684d-13b3-41e2-b61a-fb2941d21425","timestamp":"2026-10-30T05:37:00.144Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013/out","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}105{"parentUuid":"27e4684d-13b3-41e2-b61a-fb2941d21425","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MMBNKWPjVvUsm4F35Bxe8i","type":"tool_result","content":"- 2026-10-30 DECISION (pre-registered before computing any out-of-sample error): own model = \"base-effect drift\" (BED). At origin V: ln L̂_{last+h} = ln L_last + h·μ̂ with μ̂ = mean monthly log growth over the last 12 months of vintage V (= g_last/12); forecast g_T = 100·ln(L_last/L_{T−12}) + h·g_last/12, using L_{T−12} from vintage V. Rationale: YoY growth is a sum of 12 monthly growths, 12−h of which are already published at the origin; the naive forecast replaces the h unknown months by the h oldest months of the last window (base-effect noise), BED replaces them by their 12-month average. PAYEMS/UMCSENT not used (no pre-sample model selection budget; avoiding snooping over 10 origins). Single specification, no tuning. Supplementary: moving-block bootstrap of RMSE difference, seed 20261030.\n- 2026-10-30 P1 passed (audit). P2 passed: baselines naive/snaive/AR(1) computed. P3 passed: analysis.py complete, deterministic.\n- 2026-10-30 P4 passed: clean re-run identical; all checks in checks.md pass. Starting P5.","is_error":false}]},"uuid":"b804faa1-991e-451d-be2d-15be84de5ba9","timestamp":"2026-10-30T05:37:00.207Z","toolUseResult":{"stdout":"- 2026-10-30 DECISION (pre-registered before computing any out-of-sample error): own model = \"base-effect drift\" (BED). At origin V: ln L̂_{last+h} = ln L_last + h·μ̂ with μ̂ = mean monthly log growth over the last 12 months of vintage V (= g_last/12); forecast g_T = 100·ln(L_last/L_{T−12}) + h·g_last/12, using L_{T−12} from vintage V. Rationale: YoY growth is a sum of 12 monthly growths, 12−h of which are already published at the origin; the naive forecast replaces the h unknown months by the h oldest months of the last window (base-effect noise), BED replaces them by their 12-month average. PAYEMS/UMCSENT not used (no pre-sample model selection budget; avoiding snooping over 10 origins). Single specification, no tuning. Supplementary: moving-block bootstrap of RMSE difference, seed 20261030.\n- 2026-10-30 P1 passed (audit). P2 passed: baselines naive/snaive/AR(1) computed. P3 passed: analysis.py complete, deterministic.\n- 2026-10-30 P4 passed: clean re-run identical; all checks in checks.md pass. Starting P5.","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"27e4684d-13b3-41e2-b61a-fb2941d21425","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}106{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"b51e26a716e63b8aac3f9ae3718f9cf55aad763a013e92d3af98c2c66c7251ff","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MMBNKWPjVvUsm4F35Bxe8i","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P1']={\"status\":\"passed\",\"checks\":[\"SHA-256 of 23 CSVs match README\",\"row/col counts, date ranges, gaps, missing, duplicates checked\",\"first_release consistency with vintages checked\",\"availability violations identified (RSAFS_current, first_release) and handling written\"],\"notes\":\"see data_audit.md\"}\np['P2']={\"status\":\"passed\",\"checks\":[\"naive, snaive, AR(1) computed for both horizons with first-release evaluation; values in results.json rmse_/mae_ keys\"],\"notes\":\"\"}\np['P3']={\"status\":\"passed\",\"checks\":[\"analysis.py reads only data/, writes all required outputs\",\"seed 20261030 fixed and recorded\"],\"notes\":\"BED model pre-registered in log.md\"}\np['P4']={\"status\":\"passed\",\"checks\":[\"clean re-run hash identical\",\"17 consistency checks in checks.md all pass\"],\"notes\":\"\"}\np['P5']={\"status\":\"running\",\"checks\":[],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\ntail -3 out/state/log.md"}}]}}107{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"7c30aefc-2e33-4888-8af5-74bd67973581","timestamp":"2026-10-30T05:37:00.210Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"b6c372ed-8778-4eab-a1b8-bdbebdf18f83","keep":32,"tail":["b51e26a716e63b8aac3f9ae3718f9cf55aad763a013e92d3af98c2c66c7251ff","16de385be320e9f071ddaed55b6a2a55127d469c68f52a454fa0a7b45b2b11af"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",33,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"93e5e8039c85c92683e4c59bfd13e3ffee7bf5c00fab32784cc5d1dc44f3c7a8"}108{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"b804faa1-991e-451d-be2d-15be84de5ba9","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}109{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}110{"parentUuid":"b804faa1-991e-451d-be2d-15be84de5ba9","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt3D7iU76V93DSYo35o","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":926,"cache_read_input_tokens":47927,"output_tokens":4696,"output_tokens_details":{"thinking_tokens":26},"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":926},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":378,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt3Cqb6BFo9zQvrmKUB","requestRef":"7c30aefc-2e33-4888-8af5-74bd67973581","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bb3ffc7c-a0c4-40bc-8a7d-5aa5619e77e4","timestamp":"2026-10-30T05:37:01.612Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}111{"parentUuid":"bb3ffc7c-a0c4-40bc-8a7d-5aa5619e77e4","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt3D7iU76V93DSYo35o","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UPR5iBAhTrtcetnkiA8fmE","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat > report.md <<'EOF'\n# Real-time forecasts of US retail-sales YoY growth: does a base-effect model beat no-change?\n\n## Question\nUsing only the data published at each of 10 month-end forecast origins (2025-10-31 … 2026-07-31; `first_origin`, `last_origin`, `n_origins`), how well can the year-over-year log growth g = 100·ln(L_m/L_{m−12}) of US Retail Trade and Food Services sales (RSAFS) be forecast 1 and 3 months beyond the last published month, judged against the first-release value of each target month? Does a model of my own design beat the naive (no-change) forecast?\n\n## Data and exclusions\n- **Inputs** (FRED/ALFRED, retrieved 2026-10-30; all SHA-256 hashes match `data/README.md`, see `out/state/data_audit.md`; row counts in `n_input_rows`): 10 RSAFS vintages and 10 PAYEMS vintages dated at the origins, UMCSENT (current), RSAFS current vintage, and `first_release.csv` (actuals).\n- **Real-time design.** The forecast at origin V uses only `RSAFS_vintage_V.csv` (column `vintage_used` in `forecasts.csv` equals `origin_date` on every row). Targets are last(V)+h, where last(V) is the last month in that vintage. **Publication delays observed:** for the six origins 2025-10-31 … 2026-03-31 the last published month is two calendar months before the origin (last = 2025-08, 2025-09, 2025-10, 2025-11, 2025-12, 2026-01) instead of the usual one; the 2026-04-30 vintage adds 2026-02 and 2026-03 at once, and the four origins 2026-04-30 … 2026-07-31 end one month before (last = 2026-03 … 2026-06). Consequently the h=1 targets are 2025-09 … 2026-02 and 2026-04 … 2026-07 (2026-03 is never an h=1 target), and the h=3 targets are 2025-11 … 2026-04 and 2026-06 … 2026-09 (13 distinct target months overall). Origin information is in `results.json → supplementary.origins`.\n- **Actuals**: `yoy_first_release` from `first_release.csv`; each target's first-release vintage is strictly after its origin (check 4 in `out/state/checks.md`).\n- **Not used in forecasts**: `RSAFS_current.csv` (used only for the revision estimand), PAYEMS and UMCSENT (read for auditing only; the chosen model does not use them).\n- **Exclusions** (`out/exclusions.csv`): no forecast–actual pair was dropped; 20 model pairs evaluated (`n_analysed`). Only the 15 rows of `first_release.csv` that are not targets of any origin are unused.\n- **Data issues** (full list in `data_issues`): irregular publication timing (above); an annual/benchmark revision of RSAFS between the 2026-08-31 and 2026-09-30 vintages lowered levels by ≈4% and current YoY growth sits below first release for every h=1 target; it changes the base of the first-release actuals for h=3 targets 2026-08 and 2026-09. No adjustment was made, since the task defines the actual as the first release.\n\n## Method\n- **Baselines** (from vintage V only): naive g_{last(V)}; seasonal naive g_{T−12}; AR(1) estimated by OLS of g_m on a constant and g_{m−1} over 1993-02 … last(V), re-estimated at each origin, with iterated forecasts.\n- **Own model, “BED (base-effect drift)”** (`model_name`, `model_description`). YoY growth of month T is the sum of the 12 monthly log growths T−11 … T, and 12−h of them are already published at the origin. BED keeps those known terms and replaces only the h unknown months with the trailing 12-month average monthly growth: ĝ_T = 100·ln(L_last/L_{T−12}) + h·g_last/12, with both levels taken from vintage V. Nothing is estimated and there is nothing to tune. In comparison, the naive forecast implicitly fills the unknown months with the h oldest months of the last 12-month window, which brings in last year's month-specific noise (the \"base effect\"). I fixed this specification in `out/state/log.md` before computing any out-of-sample error and evaluated no other specification. I did not try PAYEMS or UMCSENT variants, because searching over models on 10 origins would mean selecting on the evaluation sample.\n- **Evaluation**: RMSE and MAE against the first release; relative improvement 1 − RMSE_model/RMSE_naive; Diebold–Mariano test on d_t = e²_naive − e²_model with a Bartlett long-run variance at truncation lag h−1 (no HLN factor) and a two-sided N(0,1) p-value. As a supplement, a moving-block bootstrap of RMSE_model − RMSE_naive (block length 2 at h=1, 3 at h=3, 9 999 draws, seed `random_seed` = 20261030).\n- **Revision estimand**: mean over the 10 h=1 targets of |g^current_T − yoy_first_release_T|.\n- Everything is produced by `out/analysis.py`.\n\n## Results\nTable 1 (`out/table1.csv`), percentage points of YoY growth, n = 10 per cell:\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 (`rmse_naive_h1`) | 0.849 (`mae_naive_h1`) | 1.420 (`rmse_naive_h3`) | 1.200 (`mae_naive_h3`) |\n| seasonal naive | 1.675 (`rmse_snaive_h1`) | 1.307 (`mae_snaive_h1`) | 1.316 (`rmse_snaive_h3`) | 1.066 (`mae_snaive_h3`) |\n| AR(1) | 0.941 (`rmse_ar1_h1`) | 0.798 (`mae_ar1_h1`) | 1.187 (`rmse_ar1_h3`) | 0.953 (`mae_ar1_h3`) |\n| BED model | 0.550 (`rmse_model_h1`) | 0.486 (`mae_model_h1`) | 1.142 (`rmse_model_h3`) | 0.934 (`mae_model_h3`) |\n\n- At h=1, BED reduces RMSE relative to naive by 44.8% (`rel_improvement_rmse_h1` = 0.448). DM = 2.43, p = 0.015 (`dm_stat_h1`, `dm_pvalue_h1`), so `conclusion_code_h1` = `model_better_significant`. BED has a smaller squared error than naive at 8 of 10 origins (`supplementary.bootstrap_rmse_diff.h1.n_origins_model_smaller_sq_error`).\n- At h=3, BED reduces RMSE relative to naive by 19.6% (`rel_improvement_rmse_h3` = 0.196). DM = 1.55, p = 0.122 (`dm_stat_h3`, `dm_pvalue_h3`), so `conclusion_code_h3` = `model_better_not_significant`. BED wins at 6 of 10 origins. At this horizon its RMSE is only slightly below AR(1)'s (1.142 vs 1.187), and I did not test that difference.\n- At h=1, AR(1) is only marginally better than naive, and seasonal naive is the worst baseline. At h=3, all three alternatives (seasonal naive, AR(1), BED) have lower RMSE than naive.\n- Figure 1 (`out/figure1.png`) shows the misses common to all methods: the jump to ≈6.6% YoY in 2026-05 and the drop to 4.9% in 2026-07.\n- **Revisions**: the mean absolute revision between first-release and current YoY growth of the h=1 targets is 0.548 pp (`mean_abs_revision_h1_targets`). Every revision is negative (−0.17 to −0.98 pp; `supplementary.revisions_h1_targets`), which reflects the benchmark revision. The revision is about as large as BED's h=1 RMSE, so the ranking could differ if the forecasts were scored against current data.\n\n## Uncertainty\n- There are only 10 origins per horizon. The DM statistic relies on asymptotic normality, which is a rough approximation at n = 10, and without the Harvey–Leybourne–Newbold correction the test tends to over-reject in small samples. The h=1 p-value of 0.015 (`dm_pvalue_h1`) should therefore be read as suggestive evidence rather than a precise significance level. A Student-t reference distribution or the HLN factor would give a larger p-value; I did not compute this.\n- At h=1 the evidence holds up under a second check: the moving-block bootstrap 95% interval for RMSE_model − RMSE_naive is [−0.70, −0.26] pp and lies entirely below zero (`supplementary.bootstrap_rmse_diff.h1`). This bootstrap is itself crude with n = 10.\n- At h=3 the long-run variance uses only two lags on overlapping 3-step errors. The DM test cannot reject equal accuracy (`dm_pvalue_h3` = 0.12), and the bootstrap interval [−0.64, +0.14] pp contains zero (`supplementary.bootstrap_rmse_diff.h3`).\n- The 10 origins span a single 9-month period with unusual publication delays and a sharp acceleration in mid-2026, so the results may not carry over to other periods.\n\n## Limitations and open issues\n- The sample is small and covers a single episode. The h=1 result is significant at 5% under the prescribed DM test but has not been confirmed on other periods.\n- The actual is the first release, which here sometimes comes from a vintage that already includes a large level rebasing (2026-08 and 2026-09 targets). With a different definition of \"truth\" (current vintage) the errors would change by about 0.5 pp on average (`mean_abs_revision_h1_targets`).\n- PAYEMS and UMCSENT were deliberately left out (see Method), so the task's question about the value of these predictors is not addressed (claim C5: not evaluated).\n- `n_input_rows` lists the 23 CSV files read by the script. `data/README.md` was read for provenance only and has no data rows.\n- Feasibility: complete (`feasibility`). No required value is null.\nEOF\ncat > claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the BED model reduces RMSE relative to the naive forecast by about 45% and the DM test (Bartlett LRV, lag 0) rejects equal accuracy at 5% (DM=2.43, p=0.015).\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"Only 10 origins in one episode; asymptotic DM without HLN correction likely over-rejects; bootstrap interval also excludes zero but is crude.\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the BED model has about 20% lower RMSE than naive, but the difference is not statistically significant (DM=1.55, p=0.12).\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\"],\"status\":\"supported\",\"caveat\":\"Bootstrap interval for the RMSE difference includes zero; BED only marginally below AR(1) at h=3 (untested).\"},\n {\"id\":\"C3\",\"text\":\"Among baselines, AR(1) is slightly better than naive at both horizons and seasonal naive is worst at h=1 but beats naive at h=3.\",\"results_keys\":[\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_snaive_h1\",\"rmse_snaive_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\"],\"status\":\"supported\",\"caveat\":\"Point estimates only; no tests among baselines.\"},\n {\"id\":\"C4\",\"text\":\"First-release YoY growth of the h=1 targets differs from currently published growth by 0.55 pp on average, all revisions being downward, driven by a benchmark revision.\",\"results_keys\":[\"mean_abs_revision_h1_targets\"],\"status\":\"supported\",\"caveat\":\"Sign pattern from supplementary.revisions_h1_targets; attribution to the benchmark revision is inferred from the level shift between vintages.\"},\n {\"id\":\"C5\",\"text\":\"PAYEMS or UMCSENT add predictive value for real-time retail-sales growth.\",\"results_keys\":[],\"status\":\"not_evaluated\",\"caveat\":\"Deliberately not tested to avoid model search on 10 evaluation origins.\"},\n {\"id\":\"C6\",\"text\":\"Six of ten origins (2025-10-31 to 2026-03-31) had last(V) two months before the origin; targets were defined from vintage content, not the calendar.\",\"results_keys\":[\"data_issues\"],\"status\":\"supported\",\"caveat\":\"Details in supplementary.origins.\"}\n]\nEOF\ncd ..; ~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'));print('ok')\""},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":926,"cache_read_input_tokens":47927,"output_tokens":4696,"output_tokens_details":{"thinking_tokens":26},"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":926},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt3Cqb6BFo9zQvrmKUB","requestRef":"7c30aefc-2e33-4888-8af5-74bd67973581","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"f6faf623-7289-49df-8743-4606785804db","timestamp":"2026-10-30T05:37:40.293Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}112{"parentUuid":"f6faf623-7289-49df-8743-4606785804db","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01UPR5iBAhTrtcetnkiA8fmE","type":"tool_result","content":"ok","is_error":false}]},"uuid":"8e65f67e-4163-48b2-947e-de996f6af196","timestamp":"2026-10-30T05:37:40.358Z","toolUseResult":{"stdout":"ok","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":true},"sandboxed":false,"sourceToolAssistantUUID":"f6faf623-7289-49df-8743-4606785804db","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}113{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"d4235ee381396af92238125999def30c5e6fe92eaf4de59f96290f278c5a7590","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01UPR5iBAhTrtcetnkiA8fmE","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013/out; cat > report.md <<'EOF'\n# Real-time forecasts of US retail-sales YoY growth: does a base-effect model beat no-change?\n\n## Question\nUsing only the data published at each of 10 month-end forecast origins (2025-10-31 … 2026-07-31; `first_origin`, `last_origin`, `n_origins`), how well can the year-over-year log growth g = 100·ln(L_m/L_{m−12}) of US Retail Trade and Food Services sales (RSAFS) be forecast 1 and 3 months beyond the last published month, judged against the first-release value of each target month? Does a model of my own design beat the naive (no-change) forecast?\n\n## Data and exclusions\n- **Inputs** (FRED/ALFRED, retrieved 2026-10-30; all SHA-256 hashes match `data/README.md`, see `out/state/data_audit.md`; row counts in `n_input_rows`): 10 RSAFS vintages and 10 PAYEMS vintages dated at the origins, UMCSENT (current), RSAFS current vintage, and `first_release.csv` (actuals).\n- **Real-time design.** The forecast at origin V uses only `RSAFS_vintage_V.csv` (column `vintage_used` in `forecasts.csv` equals `origin_date` on every row). Targets are last(V)+h, where last(V) is the last month in that vintage. **Publication delays observed:** for the six origins 2025-10-31 … 2026-03-31 the last published month is two calendar months before the origin (last = 2025-08, 2025-09, 2025-10, 2025-11, 2025-12, 2026-01) instead of the usual one; the 2026-04-30 vintage adds 2026-02 and 2026-03 at once, and the four origins 2026-04-30 … 2026-07-31 end one month before (last = 2026-03 … 2026-06). Consequently the h=1 targets are 2025-09 … 2026-02 and 2026-04 … 2026-07 (2026-03 is never an h=1 target), and the h=3 targets are 2025-11 … 2026-04 and 2026-06 … 2026-09 (13 distinct target months overall). Origin information is in `results.json → supplementary.origins`.\n- **Actuals**: `yoy_first_release` from `first_release.csv`; each target's first-release vintage is strictly after its origin (check 4 in `out/state/checks.md`).\n- **Not used in forecasts**: `RSAFS_current.csv` (used only for the revision estimand), PAYEMS and UMCSENT (read for auditing only; the chosen model does not use them).\n- **Exclusions** (`out/exclusions.csv`): no forecast–actual pair was dropped; 20 model pairs evaluated (`n_analysed`). Only the 15 rows of `first_release.csv` that are not targets of any origin are unused.\n- **Data issues** (full list in `data_issues`): irregular publication timing (above); an annual/benchmark revision of RSAFS between the 2026-08-31 and 2026-09-30 vintages lowered levels by ≈4% and current YoY growth sits below first release for every h=1 target; it changes the base of the first-release actuals for h=3 targets 2026-08 and 2026-09. No adjustment was made, since the task defines the actual as the first release.\n\n## Method\n- **Baselines** (from vintage V only): naive g_{last(V)}; seasonal naive g_{T−12}; AR(1) estimated by OLS of g_m on a constant and g_{m−1} over 1993-02 … last(V), re-estimated at each origin, with iterated forecasts.\n- **Own model, “BED (base-effect drift)”** (`model_name`, `model_description`). YoY growth of month T is the sum of the 12 monthly log growths T−11 … T, and 12−h of them are already published at the origin. BED keeps those known terms and replaces only the h unknown months with the trailing 12-month average monthly growth: ĝ_T = 100·ln(L_last/L_{T−12}) + h·g_last/12, with both levels taken from vintage V. Nothing is estimated and there is nothing to tune. In comparison, the naive forecast implicitly fills the unknown months with the h oldest months of the last 12-month window, which brings in last year's month-specific noise (the \"base effect\"). I fixed this specification in `out/state/log.md` before computing any out-of-sample error and evaluated no other specification. I did not try PAYEMS or UMCSENT variants, because searching over models on 10 origins would mean selecting on the evaluation sample.\n- **Evaluation**: RMSE and MAE against the first release; relative improvement 1 − RMSE_model/RMSE_naive; Diebold–Mariano test on d_t = e²_naive − e²_model with a Bartlett long-run variance at truncation lag h−1 (no HLN factor) and a two-sided N(0,1) p-value. As a supplement, a moving-block bootstrap of RMSE_model − RMSE_naive (block length 2 at h=1, 3 at h=3, 9 999 draws, seed `random_seed` = 20261030).\n- **Revision estimand**: mean over the 10 h=1 targets of |g^current_T − yoy_first_release_T|.\n- Everything is produced by `out/analysis.py`.\n\n## Results\nTable 1 (`out/table1.csv`), percentage points of YoY growth, n = 10 per cell:\n\n| model | RMSE h=1 | MAE h=1 | RMSE h=3 | MAE h=3 |\n|---|---|---|---|---|\n| naive | 0.997 (`rmse_naive_h1`) | 0.849 (`mae_naive_h1`) | 1.420 (`rmse_naive_h3`) | 1.200 (`mae_naive_h3`) |\n| seasonal naive | 1.675 (`rmse_snaive_h1`) | 1.307 (`mae_snaive_h1`) | 1.316 (`rmse_snaive_h3`) | 1.066 (`mae_snaive_h3`) |\n| AR(1) | 0.941 (`rmse_ar1_h1`) | 0.798 (`mae_ar1_h1`) | 1.187 (`rmse_ar1_h3`) | 0.953 (`mae_ar1_h3`) |\n| BED model | 0.550 (`rmse_model_h1`) | 0.486 (`mae_model_h1`) | 1.142 (`rmse_model_h3`) | 0.934 (`mae_model_h3`) |\n\n- At h=1, BED reduces RMSE relative to naive by 44.8% (`rel_improvement_rmse_h1` = 0.448). DM = 2.43, p = 0.015 (`dm_stat_h1`, `dm_pvalue_h1`), so `conclusion_code_h1` = `model_better_significant`. BED has a smaller squared error than naive at 8 of 10 origins (`supplementary.bootstrap_rmse_diff.h1.n_origins_model_smaller_sq_error`).\n- At h=3, BED reduces RMSE relative to naive by 19.6% (`rel_improvement_rmse_h3` = 0.196). DM = 1.55, p = 0.122 (`dm_stat_h3`, `dm_pvalue_h3`), so `conclusion_code_h3` = `model_better_not_significant`. BED wins at 6 of 10 origins. At this horizon its RMSE is only slightly below AR(1)'s (1.142 vs 1.187), and I did not test that difference.\n- At h=1, AR(1) is only marginally better than naive, and seasonal naive is the worst baseline. At h=3, all three alternatives (seasonal naive, AR(1), BED) have lower RMSE than naive.\n- Figure 1 (`out/figure1.png`) shows the misses common to all methods: the jump to ≈6.6% YoY in 2026-05 and the drop to 4.9% in 2026-07.\n- **Revisions**: the mean absolute revision between first-release and current YoY growth of the h=1 targets is 0.548 pp (`mean_abs_revision_h1_targets`). Every revision is negative (−0.17 to −0.98 pp; `supplementary.revisions_h1_targets`), which reflects the benchmark revision. The revision is about as large as BED's h=1 RMSE, so the ranking could differ if the forecasts were scored against current data.\n\n## Uncertainty\n- There are only 10 origins per horizon. The DM statistic relies on asymptotic normality, which is a rough approximation at n = 10, and without the Harvey–Leybourne–Newbold correction the test tends to over-reject in small samples. The h=1 p-value of 0.015 (`dm_pvalue_h1`) should therefore be read as suggestive evidence rather than a precise significance level. A Student-t reference distribution or the HLN factor would give a larger p-value; I did not compute this.\n- At h=1 the evidence holds up under a second check: the moving-block bootstrap 95% interval for RMSE_model − RMSE_naive is [−0.70, −0.26] pp and lies entirely below zero (`supplementary.bootstrap_rmse_diff.h1`). This bootstrap is itself crude with n = 10.\n- At h=3 the long-run variance uses only two lags on overlapping 3-step errors. The DM test cannot reject equal accuracy (`dm_pvalue_h3` = 0.12), and the bootstrap interval [−0.64, +0.14] pp contains zero (`supplementary.bootstrap_rmse_diff.h3`).\n- The 10 origins span a single 9-month period with unusual publication delays and a sharp acceleration in mid-2026, so the results may not carry over to other periods.\n\n## Limitations and open issues\n- The sample is small and covers a single episode. The h=1 result is significant at 5% under the prescribed DM test but has not been confirmed on other periods.\n- The actual is the first release, which here sometimes comes from a vintage that already includes a large level rebasing (2026-08 and 2026-09 targets). With a different definition of \"truth\" (current vintage) the errors would change by about 0.5 pp on average (`mean_abs_revision_h1_targets`).\n- PAYEMS and UMCSENT were deliberately left out (see Method), so the task's question about the value of these predictors is not addressed (claim C5: not evaluated).\n- `n_input_rows` lists the 23 CSV files read by the script. `data/README.md` was read for provenance only and has no data rows.\n- Feasibility: complete (`feasibility`). No required value is null.\nEOF\ncat > claims.json <<'EOF'\n[\n {\"id\":\"C1\",\"text\":\"At h=1 the BED model reduces RMSE relative to the naive forecast by about 45% and the DM test (Bartlett LRV, lag 0) rejects equal accuracy at 5% (DM=2.43, p=0.015).\",\"results_keys\":[\"rmse_model_h1\",\"rmse_naive_h1\",\"rel_improvement_rmse_h1\",\"dm_stat_h1\",\"dm_pvalue_h1\",\"conclusion_code_h1\"],\"status\":\"supported\",\"caveat\":\"Only 10 origins in one episode; asymptotic DM without HLN correction likely over-rejects; bootstrap interval also excludes zero but is crude.\"},\n {\"id\":\"C2\",\"text\":\"At h=3 the BED model has about 20% lower RMSE than naive, but the difference is not statistically significant (DM=1.55, p=0.12).\",\"results_keys\":[\"rmse_model_h3\",\"rmse_naive_h3\",\"rel_improvement_rmse_h3\",\"dm_stat_h3\",\"dm_pvalue_h3\",\"conclusion_code_h3\"],\"status\":\"supported\",\"caveat\":\"Bootstrap interval for the RMSE difference includes zero; BED only marginally below AR(1) at h=3 (untested).\"},\n {\"id\":\"C3\",\"text\":\"Among baselines, AR(1) is slightly better than naive at both horizons and seasonal naive is worst at h=1 but beats naive at h=3.\",\"results_keys\":[\"rmse_ar1_h1\",\"rmse_ar1_h3\",\"rmse_snaive_h1\",\"rmse_snaive_h3\",\"rmse_naive_h1\",\"rmse_naive_h3\"],\"status\":\"supported\",\"caveat\":\"Point estimates only; no tests among baselines.\"},\n {\"id\":\"C4\",\"text\":\"First-release YoY growth of the h=1 targets differs from currently published growth by 0.55 pp on average, all revisions being downward, driven by a benchmark revision.\",\"results_keys\":[\"mean_abs_revision_h1_targets\"],\"status\":\"supported\",\"caveat\":\"Sign pattern from supplementary.revisions_h1_targets; attribution to the benchmark revision is inferred from the level shift between vintages.\"},\n {\"id\":\"C5\",\"text\":\"PAYEMS or UMCSENT add predictive value for real-time retail-sales growth.\",\"results_keys\":[],\"status\":\"not_evaluated\",\"caveat\":\"Deliberately not tested to avoid model search on 10 evaluation origins.\"},\n {\"id\":\"C6\",\"text\":\"Six of ten origins (2025-10-31 to 2026-03-31) had last(V) two months before the origin; targets were defined from vintage content, not the calendar.\",\"results_keys\":[\"data_issues\"],\"status\":\"supported\",\"caveat\":\"Details in supplementary.origins.\"}\n]\nEOF\ncd ..; ~/wp29/venv/bin/python -c \"import json;json.load(open('out/claims.json'));print('ok')\""}}]}}114{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"6099519b-4f53-41f5-9487-42839438af19","timestamp":"2026-10-30T05:37:40.367Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"7c30aefc-2e33-4888-8af5-74bd67973581","keep":34,"tail":["d4235ee381396af92238125999def30c5e6fe92eaf4de59f96290f278c5a7590","c22a8e789f70c251a51c41671884032de409a55cf1817f925ce569eb26a1e466"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",35,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"0553419173a10913c1e758ab7dfe7de7ecffb25980a0ab3b31086597c326db8c"}115{"parentUuid":"8e65f67e-4163-48b2-947e-de996f6af196","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6AntpTG8GtdHC4bqn","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":4703,"cache_read_input_tokens":48853,"output_tokens":386,"output_tokens_details":{"thinking_tokens":96},"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":4703},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":646,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXt6AXGsNstwBM4UsYyH","requestRef":"6099519b-4f53-41f5-9487-42839438af19","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"2dba85de-eebc-4723-8883-657bc34b42e0","timestamp":"2026-10-30T05:37:42.259Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}116{"parentUuid":"2dba85de-eebc-4723-8883-657bc34b42e0","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6AntpTG8GtdHC4bqn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01D7vrU2ZYun7cn5UkzUkQr5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md has the 6 required sections, numbers cite results.json keys\",\"claims.json valid JSON, 6 claims, every report claim listed\",\"all required files present\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P5 passed: report.md and claims.json written. Task complete.\" >> out/state/log.md; ls out out/state; grep -c \"^## \" out/report.md"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":4703,"cache_read_input_tokens":48853,"output_tokens":386,"output_tokens_details":{"thinking_tokens":96},"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":4703},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXt6AXGsNstwBM4UsYyH","requestRef":"6099519b-4f53-41f5-9487-42839438af19","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"6ab1f0f0-4177-45cd-a74d-2d9d4d0b8cda","timestamp":"2026-10-30T05:37:44.281Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}117{"parentUuid":"6ab1f0f0-4177-45cd-a74d-2d9d4d0b8cda","isSidechain":false,"promptId":"509655a8-2b8b-4cd2-88f1-250c485dfa98","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01D7vrU2ZYun7cn5UkzUkQr5","type":"tool_result","content":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\nstate\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json\n6","is_error":false}]},"uuid":"cff6c8f2-5e43-4c19-be5e-9f54ddbb0488","timestamp":"2026-10-30T05:37:44.343Z","toolUseResult":{"stdout":"out:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nforecasts.csv\nreport.md\nresults.json\nstate\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json\n6","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"6ab1f0f0-4177-45cd-a74d-2d9d4d0b8cda","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}118{"type":"api-request-blob","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","hash":"d561c943d07cc5b71a392e2b003673b9da7c5e5d88a3e6673aa74a91fbcf567e","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01D7vrU2ZYun7cn5UkzUkQr5","name":"Bash","input":{"command":"cd /Users/simon-pierreboucher/wp29/runs/RT0013; ~/wp29/venv/bin/python - <<'EOF'\nimport json\np=json.load(open('out/state/phases.json'))\np['P5']={\"status\":\"passed\",\"checks\":[\"report.md has the 6 required sections, numbers cite results.json keys\",\"claims.json valid JSON, 6 claims, every report claim listed\",\"all required files present\"],\"notes\":\"\"}\njson.dump(p,open('out/state/phases.json','w'),indent=1)\nEOF\necho \"- 2026-10-30 P5 passed: report.md and claims.json written. Task complete.\" >> out/state/log.md; ls out out/state; grep -c \"^## \" out/report.md"}}]}}119{"type":"api-request","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","id":"d26245ca-4aba-464a-a191-c568e1a95ae3","timestamp":"2026-10-30T05:37:44.347Z","version":"2.1.314","querySource":"sdk","shapeHash":"adf629f7aef0d96c79cd6c37c6ceaa9a840d806026c2ab4328309c0e4202e539","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":"6099519b-4f53-41f5-9487-42839438af19","keep":36,"tail":["d561c943d07cc5b71a392e2b003673b9da7c5e5d88a3e6673aa74a91fbcf567e","e6456a140f2b8e04de205461d6e0bc7d5a4a47c582e97e92c55f7c2964aef19e"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",37,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"d80d40c37c6c2069283ca0d940f44439580bb1909965c828ca4cf13efd58bb8b"}120{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"cff6c8f2-5e43-4c19-be5e-9f54ddbb0488","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}121{"type":"atis-latch","atis":"","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}122{"parentUuid":"cff6c8f2-5e43-4c19-be5e-9f54ddbb0488","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXt6Tv3cXSqxt6j2N8Xp","type":"message","role":"assistant","content":[{"type":"text","text":"My model beats the no-change (naive) forecast one month ahead, and the difference is significant at 5% under the prescribed Diebold–Mariano test. Three months ahead it also does better, but not significantly. All protocol phases (P0–P5) passed, and every required output is in `out/`.\n\n**My model (\"base-effect drift\").** Year-over-year growth is the sum of 12 monthly growth rates, and 12 − h of them are already published at each forecast origin. The model keeps those published months and fills in only the h missing ones with the average monthly growth of the past year. It has no estimated parameters. I fixed it in the log before computing any forecast errors and tried no other version.\n\n**Results (10 origins, errors in percentage points against the first-release value):**\n\n| | naive | seasonal naive | AR(1) | my model |\n|---|---|---|---|---|\n| RMSE, 1 month ahead | 0.997 | 1.675 | 0.941 | **0.550** |\n| RMSE, 3 months ahead | 1.420 | 1.316 | 1.187 | **1.142** |\n\n- **1 month ahead:** RMSE is 44.8% lower than naive. DM = 2.43, p = 0.015, so the code is `model_better_significant`. My model had the smaller error at 8 of 10 origins.\n- **3 months ahead:** RMSE is 19.6% lower than naive. DM = 1.55, p = 0.12, so the code is `model_better_not_significant`. The model is only slightly better than AR(1) at this horizon, and I did not test that difference.\n- **Revisions:** first-release and current growth for the 1-month-ahead target months differ by 0.548 points on average, and every revision is downward. An annual revision lowered sales levels by about 4% between the August and September 2026 data releases.\n\n**Data issues:** at six of the ten origins (2025-10-31 to 2026-03-31) the latest published month was two months old instead of one. The 2026-04-30 data added two months at once. As the task requires, targets are counted from the last published month, not the calendar.\n\n**Limitations:**\n- With only 10 origins in a single 9-month period, the 1-month result is suggestive. The DM test without the small-sample correction tends to reject too often. A supplementary bootstrap 95% interval for the RMSE difference excludes zero at 1 month ahead ([−0.70, −0.26]) but includes it at 3 months ahead.\n- I did not use payroll employment or consumer sentiment, to avoid choosing a model on the same 10 origins used to evaluate it. So whether they help is not evaluated.\n\nA clean re-run of `analysis.py` reproduced identical outputs, and all 17 consistency checks in `out/state/checks.md` pass.\n\nFiles are in `out/`:\n- results.json\n- forecasts.csv\n- table1.csv\n- figure1.png\n- report.md\n- claims.json\n- analysis.py\n- exclusions.csv\n- state/ (contract, data audit, checks, log, phase ledger)"}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":475,"cache_read_input_tokens":53556,"output_tokens":994,"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":475},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXt6TWjEUg5e5MCquk8T","requestRef":"d26245ca-4aba-464a-a191-c568e1a95ae3","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"d451ab1e-8fb7-4c86-b47e-9a629d0c963d","timestamp":"2026-10-30T05:37:53.904Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RT0013","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","version":"2.1.314","gitBranch":"HEAD"}123{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d451ab1e-8fb7-4c86-b47e-9a629d0c963d","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4"}124{"type":"cost-state","sessionId":"9fa7fba7-8a62-49eb-b4ea-2f590df456a4","totalCostUSD":0.9222041999999998,"totalAPIDuration":241198,"totalAPIDurationWithoutRetries":241184,"totalToolDuration":6985,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":248354,"startTime":1793338425557,"modelUsage":{"claude-opus-5-5":{"inputTokens":40,"outputTokens":27334,"thinkingTokens":4734,"cacheReadInputTokens":563646,"cacheCreationInputTokens":52527,"cacheCreationEphemeral5mInputTokens":52527,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.9222041999999998}},"hasUnknownModelCost":false}125