{"type":"atis-latch","atis":"","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"type":"queue-operation","operation":"enqueue","timestamp":"2026-10-30T05:18:55.010Z","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","content":"Begin"}
{"type":"queue-operation","operation":"dequeue","timestamp":"2026-10-30T05:18:55.016Z","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":null,"isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":"Begin"},"uuid":"1c33829b-5581-4475-87db-117d81a958f7","timestamp":"2026-10-30T05:18:55.021Z","permissionMode":"default","promptSource":"sdk","turnOrigin":"sdk","turnPosition":{"promptIndex":0,"turnIndex":1},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-shape","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","timestamp":"2026-10-30T05:18:55.035Z","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/RC0269\nDate: 2026-10-30\n\nYou are a research assistant executing one bounded scientific task inside the current working directory, which is your workspace.\n\nEnvironment facts (identical for every task):\n- The task statement is the file `TASK.md` in the workspace. It is the complete and only authoritative description of what is required: the scientific question, the inputs under `data/`, the required output files and their exact keys, and the information-availability rules.\n- There is no network access. Use the Python interpreter `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib are installed). Standard shell tools are available. Do not try to install packages.\n- Write every deliverable under `./out/`. The required deliverables are listed in `TASK.md`; at minimum they always include `out/results.json`, `out/report.md`, and a replication entry point `out/analysis.py` that regenerates `out/results.json` from `data/` when run with `~/wp29/venv/bin/python out/analysis.py` from the workspace root.\n- You are working alone and unattended; nobody will answer questions. Make reasonable, documented decisions.\n\nIntegrity rules (identical for every task):\n- Never fabricate numbers, data, results, or references. Every number in `out/results.json` and `out/report.md` must be produced by code you ran on the provided inputs.\n- Respect the information-availability rules in `TASK.md` exactly (for example, never use information that would not have been available at the stated decision time).\n- If part of the task cannot be completed as specified, say so explicitly in `out/report.md`, explain why, and still write every required file (use `null` for values you could not legitimately produce). An honest statement of a limitation is always preferred to a fabricated or guessed value.\n- Do not modify anything under `data/`.\n- When you are done, end with a brief plain-text summary of what you produced and any limitations.\n\nComplete the task described in `TASK.md` by following this research protocol. The protocol adds no scientific information to the task; it organizes how you work and what evidence you leave behind.\n\nPHASES (execute in order; a phase is eligible only when its dependencies are satisfied):\n\nP0 Scope and contract (depends on: nothing)\n- Read `TASK.md` completely. In `out/state/contract.md`, restate in your own words: the scientific question; the quantity or quantities to be estimated (the estimands) and the assumptions under which they are meaningful; every required output file and key; the information-availability rules; what would make the task impossible or the result invalid.\n- Write the initial phase ledger `out/state/phases.json`: a JSON object mapping each phase id (P0 … P5) to {\"status\": \"pending\"|\"running\"|\"passed\"|\"failed\"|\"blocked\"|\"stale\"|\"skipped_optional\", \"checks\": [], \"notes\": \"\"}. Keep it current as you work. A phase may only be set to \"passed\" when the checks listed for it in this protocol have actually been executed and their outcome recorded in \"checks\".\n\nP1 Data audit and provenance (depends on: P0)\n- Inspect every input file: compute and record its SHA-256, row and column counts, schema, units, date ranges, missing values, duplicates and anomalies in `out/state/data_audit.md`.\n- Keep an exclusion ledger in `out/exclusions.csv` (columns: step, rule, n_before, n_after, n_removed, rationale) for every filtering step you apply, so that n_raw − total removed = n_analysed.\n- Identify any input that violates the information-availability rules and decide, in writing, how you will handle it.\n\nP2 Baseline (depends on: P1)\n- Before any elaborate method, compute the simplest valid baseline that answers the question (for example a naïve or unconditional estimate), with the same evaluation rule used later. Record it in `out/results.json` under the keys the task requires, or under `baseline_*` keys when the task does not name them.\n\nP3 Method and computation (depends on: P2)\n- Implement the analysis in `out/analysis.py` so that it reads only `data/`, writes `out/results.json` deterministically (fix every random seed you use and record it), and prints nothing that contradicts the written results. Any figure or table must be generated by this script.\n\nP4 Verification (depends on: P3)\n- Re-run `out/analysis.py` from a clean state and confirm it regenerates `out/results.json` with identical values. Record the check in `out/state/phases.json` under P4.\n- Check internal consistency: identities that must hold (for example counts that must add up, standard errors that must be positive, confidence intervals that must contain their estimates, date orderings that must respect the information rules), units, and magnitudes against the baseline. Record every check and its outcome in `out/state/checks.md`. A failed check must be fixed or honestly reported, never silently ignored.\n\nP5 Reporting (depends on: P4)\n- Write `out/report.md` with the sections: Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues. Every quantitative statement must cite the key of `out/results.json` it comes from.\n- Write `out/claims.json`: a list of the central claims of your report, each as {\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}. Do not state a claim in the report that is not in this ledger.\n- Set the final statuses in `out/state/phases.json`.\n\nSTOPPING RULES\n- Stop and declare the task complete only when every phase P0–P5 is \"passed\" with recorded checks. If a phase is \"blocked\" (missing information, impossible requirement, violated availability rule), stop, set the status, explain in `out/report.md` (section Limitations and open issues) and still write every required file with `null` for values you could not legitimately produce.\n- Do not spend effort on extensions that the task does not require.\n\nRECOVERY RULES\n- Append a short dated entry to `out/state/log.md` after each phase transition and after any important decision, so that work can be resumed by reading `out/state/`.\n- If you discover that an upstream input or decision changed after a downstream phase passed, mark the downstream phases \"stale\" and redo them; do not reuse stale results.\n- If you are interrupted and later resumed, first read `out/state/` and continue from the last consistent state; never re-run expensive steps that already have recorded, unchanged outputs.\n"}],"tools":[{"name":"Bash","description":"execute shell commands","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"command":{"description":"The command to execute","type":"string"},"timeout":{"description":"Optional timeout in milliseconds (max 600000 for a foreground command)","type":"number"},"description":{"description":"Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nSay what the command does in plain words: do not echo the command's text, its flags, or file paths - the user reads this description, often without seeing the command.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\"","type":"string"},"dangerouslyDisableSandbox":{"description":"Set this to true to dangerously override sandbox mode and run commands without sandboxing.","type":"boolean"}},"required":["command"],"additionalProperties":false}},{"name":"Edit","description":"modify file contents in place","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to modify","type":"string"},"old_string":{"description":"The text to replace","type":"string"},"new_string":{"description":"The text to replace it with (must be different from old_string)","type":"string"},"replace_all":{"description":"Replace all occurrences of old_string (default false)","default":false,"type":"boolean"}},"required":["file_path","old_string","new_string"],"additionalProperties":false}},{"name":"Read","description":"read files, images, PDFs, notebooks","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"file_path":{"description":"The absolute path to the file to read","type":"string"},"offset":{"description":"The line number to start reading from. Only provide if the file is too large to read at once","type":"integer","minimum":0,"maximum":9007199254740991},"limit":{"description":"The number of lines to read. Only provide if the file is too large to read at once.","type":"integer","exclusiveMinimum":0,"maximum":9007199254740991},"pages":{"description":"Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request.","type":"string"},"allow_large":{"description":"Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.","type":"boolean"}},"required":["file_path"],"additionalProperties":false}}]}}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"d43ab0e0b8ec9db790a6459cb2f4bc4ffce02825ca05063162023be60912ced9","message":{"role":"system","content":[],"output_config":{"effort":"medium"}}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"2a491407-f006-4da3-b87f-46d7d42068fc","timestamp":"2026-10-30T05:18:55.035Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"3e4d2609b50ddabb67e5cc98961f4e24683b711f5d7ff17f03cd6b84585530c7"}
{"parentUuid":"1c33829b-5581-4475-87db-117d81a958f7","isSidechain":false,"attachment":{"type":"session_context","context":{}},"type":"attachment","uuid":"4ea50503-78e6-49b9-8893-bdd7639d409b","timestamp":"2026-10-30T05:18:55.027Z","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"4ea50503-78e6-49b9-8893-bdd7639d409b","isSidechain":false,"attachment":{"type":"date","date":"2026-10-30"},"type":"attachment","uuid":"f28268f9-cf60-4571-b797-ebae90cd6a99","timestamp":"2026-10-30T05:18:55.027Z","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/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"f28268f9-cf60-4571-b797-ebae90cd6a99","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":"9c2894e4-e998-4276-b4ce-1dfcca589309","timestamp":"2026-10-30T05:18:55.028Z","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/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"tools-used","tools":["Bash"],"sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":"9c2894e4-e998-4276-b4ce-1dfcca589309","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrfDaXEQYPJSFX6eeWf","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSpAUKEAgTGAI4AUIIdGhpbmtpbmcSDHfhB3pDCwsHQ6wW2hoMtHPFsojieR+f00znIjBdmBu7yhh8gdZxt7LncOCK/4DdkuChfgs4ncQfjwoHPl4x1NqXlVJEX7LHJdTq/ooqwQTm7QNut+3OSpxf0CX5fRTPbj01NmZ2JF3NuUETjcF1bU/snlGjrqNzKGNYZNh4yx+oayFDAq3rqTbK6aEUV+p0UH1VHajgENLS+vsH0U/PfwhBzaAsCSz4wLEgs4DBImwe/F7hQEIz2Bg7hZjzLrC3lOVQL2+7S+FzcQrxaUIQrpyCtF3Yl+DvA8+Z+4TiYsKqYTJ5dvg3kRuKqzgN74TICgVIzHocqFXKpqQh8lAvgjvQlTegqmx+khvUyougfuTkTmYUTQ8as065xIuF7yMSzhSz8jauhwO0JrJMdoDlTlETbD4BeV3w8zaF1IhXealFWGUBeLku/Iw9fRnMSVtAk9oemTQJphtJVY9K80VWXOU3AIGw5q0gdKWqosJBQ4ibarJVGvSw0sKsLtOsSuPQaz0kBtwdiGvePAwVNC0e+wukDsdG/NSnbSIctM1CR1Rw/7EFB87mPyeI4+mTI4rY1QNC4QzZY4FjRevVs7J3qqt0xE/0N4sIKM1HMFOXv4m12FdQD7DwRmZKcfGLYZt9BEgqn6Hu7CDx3Eb7Wdtf02O2ecmx59Hn0k2cCGmH1O0WQXhIbfyLQWl2q0A6Bx6+XH1Ty37IWMygxixF2zZFB8J4tY7Cen/XOtc/3Z/2URjG2XcTRqux1dTCOhCD9VEMsgWNZoRu35CO19YNIlsys4KPCNxvIMECSMN+TYr6BCUKVfbnoPY8PeZOCFjCAnJpc9rimLYhSP5E+8+kpbtyK6kL27wKylmkC2tKvOWzH1egGAE="}],"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":125,"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":456,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXrfDHfE4EGSrVWz3X3q","requestRef":"2a491407-f006-4da3-b87f-46d7d42068fc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"0963291b-224b-4e84-bd3e-cfb905699e29","timestamp":"2026-10-30T05:18:56.403Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"0963291b-224b-4e84-bd3e-cfb905699e29","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrfDaXEQYPJSFX6eeWf","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01P81NRvPNCbKr2PAnhrzgX3","name":"Bash","input":{"command":"cat TASK.md; ls -laR data out 2>/dev/null | head -50","description":"Read task and list workspace"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":2209,"cache_read_input_tokens":1504,"output_tokens":125,"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_011CgXrfDHfE4EGSrVWz3X3q","requestRef":"2a491407-f006-4da3-b87f-46d7d42068fc","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e87ab8aa-3eb4-40a7-98ac-55fd0c46afca","timestamp":"2026-10-30T05:18:56.995Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"e87ab8aa-3eb4-40a7-98ac-55fd0c46afca","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01P81NRvPNCbKr2PAnhrzgX3","type":"tool_result","content":"# F6-conf-01 — Does the day of the week carry predictive content for daily changes in the 10-year Treasury yield?\n\n## Scientific question\nFinancial folklore attributes systematic \"Monday\" or \"Friday\" patterns to daily asset-price changes. Using twenty years of daily data (2000–2019) on the 10-year US Treasury constant-maturity yield, determine whether the day of the week has any predictive content for the one-day change in the yield. The estimands are: (i) the differences in the conditional mean of the one-day change Δy_t (basis points) across the five weekdays, tested jointly; (ii) the \"Monday contrast\", the mean change on Mondays minus the mean change on the other four weekdays, with a 95% interval; (iii) the out-of-sample predictive value of weekday-specific means relative to a zero-change (random-walk) baseline. This is a complete, bounded mini-project: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report. Report what the data show, whatever that is.\n\n## Inputs\n- `data/DGS10.csv` — observed data, FRED series DGS10 (Board of Governors, H.15), daily, percent; raw FRED CSV restricted to 2000-01-01 … 2019-12-31 (provenance, URL, retrieval date, terms and SHA-256 in `data/README.md`). Columns: `observation_date` (YYYY-MM-DD, every weekday is listed) and `DGS10` (percent; the field is empty on days when no yield was published, i.e. US market holidays).\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- First drop the rows with an empty `DGS10` field; then define the one-day change as Δy_t = 100·(y_t − y_{t−1}) in basis points between consecutive *available* observations. The change is dated t and attributed to the weekday of t (Monday … Friday). The first available observation has no change.\n- The estimation period is the set of changes dated on or before 2009-12-31; the evaluation period is the set of changes dated on or after 2010-01-01. Any weekday-specific quantity used to forecast an evaluation-period change must be estimated from the estimation period only.\n- The joint test is the classical one-way (equal-variance) analysis-of-variance F-test of equal weekday means over all changes (both periods together). The Monday contrast and its interval may use any valid two-sample method (Welch, pooled, or a regression on a Monday indicator with heteroskedasticity-robust SE); state the choice.\n- Use only the file listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `n_missing_rows` | integer | rows | rows of `DGS10.csv` with an empty `DGS10` field |\n| `n_train`, `n_test` | integer | changes | number of daily changes in the estimation and evaluation periods |\n| `anova_f_stat` | number | — | one-way ANOVA F statistic for equal weekday means (all changes) |\n| `anova_p_value` | number | — | its p-value (F(4, n−5)) |\n| `effect_estimate` | number | basis points | Monday contrast: mean Monday change minus mean change on the other weekdays (all changes) |\n| `effect_ci_low`, `effect_ci_high` | number | basis points | 95% confidence interval for the Monday contrast |\n| `baseline_metric` | number | basis points | RMSE of the zero-change forecast over the evaluation period |\n| `model_metric` | number | basis points | RMSE over the evaluation period of the forecast that predicts each change by the estimation-period mean change of its weekday |\n| `conclusion` | string | — | one of the codes below (decided by the ANOVA at the 5% level; if it rejects, the sign is given by the Monday-contrast interval) |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\n(`n_analysed` = number of daily changes used in the ANOVA.)\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — mean change by weekday with 95% confidence bars (all changes), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per weekday with columns `weekday`, `n`, `mean_bp`, `se_bp` (header + five data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ndata:\ntotal 176\ndrwxr-xr-x  4 simon-pierreboucher  staff    128 oct.  29 23:27 .\ndrwxr-xr-x  6 simon-pierreboucher  staff    192 oct.  29 23:42 ..\n-rw-r--r--  1 simon-pierreboucher  staff  82635 oct.  29 23:27 DGS10.csv\n-rw-r--r--  1 simon-pierreboucher  staff   1162 oct.  29 23:27 README.md","is_error":false}]},"uuid":"43c56bda-5318-4c88-ab2e-c7733b45c7f2","timestamp":"2026-10-30T05:18:57.098Z","toolUseResult":{"stdout":"# F6-conf-01 — Does the day of the week carry predictive content for daily changes in the 10-year Treasury yield?\n\n## Scientific question\nFinancial folklore attributes systematic \"Monday\" or \"Friday\" patterns to daily asset-price changes. Using twenty years of daily data (2000–2019) on the 10-year US Treasury constant-maturity yield, determine whether the day of the week has any predictive content for the one-day change in the yield. The estimands are: (i) the differences in the conditional mean of the one-day change Δy_t (basis points) across the five weekdays, tested jointly; (ii) the \"Monday contrast\", the mean change on Mondays minus the mean change on the other four weekdays, with a 95% interval; (iii) the out-of-sample predictive value of weekday-specific means relative to a zero-change (random-walk) baseline. This is a complete, bounded mini-project: question → data audit → baseline → justified method → results → uncertainty → failure discussion → one figure and one table → short report. Report what the data show, whatever that is.\n\n## Inputs\n- `data/DGS10.csv` — observed data, FRED series DGS10 (Board of Governors, H.15), daily, percent; raw FRED CSV restricted to 2000-01-01 … 2019-12-31 (provenance, URL, retrieval date, terms and SHA-256 in `data/README.md`). Columns: `observation_date` (YYYY-MM-DD, every weekday is listed) and `DGS10` (percent; the field is empty on days when no yield was published, i.e. US market holidays).\n- `data/README.md` — provenance.\n\n## Information-availability rules\n- First drop the rows with an empty `DGS10` field; then define the one-day change as Δy_t = 100·(y_t − y_{t−1}) in basis points between consecutive *available* observations. The change is dated t and attributed to the weekday of t (Monday … Friday). The first available observation has no change.\n- The estimation period is the set of changes dated on or before 2009-12-31; the evaluation period is the set of changes dated on or after 2010-01-01. Any weekday-specific quantity used to forecast an evaluation-period change must be estimated from the estimation period only.\n- The joint test is the classical one-way (equal-variance) analysis-of-variance F-test of equal weekday means over all changes (both periods together). The Monday contrast and its interval may use any valid two-sample method (Welch, pooled, or a regression on a Monday indicator with heteroskedasticity-robust SE); state the choice.\n- Use only the file listed above.\n\n## Required outputs\n- `out/results.json` with the keys:\n\n| key | type | unit | meaning |\n|---|---|---|---|\n| `n_missing_rows` | integer | rows | rows of `DGS10.csv` with an empty `DGS10` field |\n| `n_train`, `n_test` | integer | changes | number of daily changes in the estimation and evaluation periods |\n| `anova_f_stat` | number | — | one-way ANOVA F statistic for equal weekday means (all changes) |\n| `anova_p_value` | number | — | its p-value (F(4, n−5)) |\n| `effect_estimate` | number | basis points | Monday contrast: mean Monday change minus mean change on the other weekdays (all changes) |\n| `effect_ci_low`, `effect_ci_high` | number | basis points | 95% confidence interval for the Monday contrast |\n| `baseline_metric` | number | basis points | RMSE of the zero-change forecast over the evaluation period |\n| `model_metric` | number | basis points | RMSE over the evaluation period of the forecast that predicts each change by the estimation-period mean change of its weekday |\n| `conclusion` | string | — | one of the codes below (decided by the ANOVA at the 5% level; if it rejects, the sign is given by the Monday-contrast interval) |\n| `task_id` | string | copied from this file |\n| `feasibility` | string | `complete` / `partial` / `infeasible` |\n| `feasibility_reason` | string or null | why, if not complete |\n| `data_issues` | array of {\"issue\",\"handling\"} | every data problem detected and how it was handled (empty list allowed) |\n| `n_input_rows` | object {file: integer} | rows read per input file (file name as key, header row excluded) |\n| `n_analysed` | integer or null | observations actually used in the main estimate |\n| `random_seed` | integer or null | seed used, if any |\n\n(`n_analysed` = number of daily changes used in the ANOVA.)\n\nThe `conclusion` code must be one of: `positive_effect` (the 95% interval for the effect estimand lies above zero), `negative_effect` (lies below zero), `no_detectable_effect` (the interval / test does not reject zero at the 5% level), `premise_invalid` (the data provided do not allow the stated estimand to be computed — in that case set `feasibility` to `infeasible`, explain in `feasibility_reason`, and set every inestimable key to `null`; never substitute an invented or proxy estimate).\n\n- `out/figure1.png` — mean change by weekday with 95% confidence bars (all changes), produced by `out/analysis.py` with matplotlib.\n- `out/table1.csv` — one row per weekday with columns `weekday`, `n`, `mean_bp`, `se_bp` (header + five data rows), produced by `out/analysis.py`.\n- `out/report.md` with exactly these six sections, in this order: *Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues*. The last section must contain a genuine failure discussion: what would invalidate the result, what was not checked, and what the main threats are.\n- `out/analysis.py` — replication entry point: `~/wp29/venv/bin/python out/analysis.py`, run from the workspace root, must regenerate `out/results.json`, `out/figure1.png` and `out/table1.csv` from `data/` only, deterministically (fix any seed; use the matplotlib `Agg` backend).\n- `out/claims.json` — list of the central claims of the report: `[{\"id\": \"C1\", \"text\": \"...\", \"results_keys\": [\"...\"], \"status\": \"supported\"|\"unsupported\"|\"not_evaluated\", \"caveat\": \"...\"}]`. Every claim must reference existing keys of `out/results.json`; a claim must only be marked `supported` if the reported numbers actually support it.\n\n## Constraints\n- No network access. Python: `~/wp29/venv/bin/python` (numpy, pandas, scipy, statsmodels, matplotlib available). Do not modify `data/`.\n- Write all deliverables under `out/`. This task is designed to be completed in well under 20 minutes of work; prefer a short, correct chain over an elaborate one.\ndata:\ntotal 176\ndrwxr-xr-x  4 simon-pierreboucher  staff    128 oct.  29 23:27 .\ndrwxr-xr-x  6 simon-pierreboucher  staff    192 oct.  29 23:42 ..\n-rw-r--r--  1 simon-pierreboucher  staff  82635 oct.  29 23:27 DGS10.csv\n-rw-r--r--  1 simon-pierreboucher  staff   1162 oct.  29 23:27 README.md","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e87ab8aa-3eb4-40a7-98ac-55fd0c46afca","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"89c78757d82b25c85173ee3161978e623bb0175b2c2ba2cf0dce85b71c0de3e3","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSpAUKEAgTGAI4AUIIdGhpbmtpbmcSDHfhB3pDCwsHQ6wW2hoMtHPFsojieR+f00znIjBdmBu7yhh8gdZxt7LncOCK/4DdkuChfgs4ncQfjwoHPl4x1NqXlVJEX7LHJdTq/ooqwQTm7QNut+3OSpxf0CX5fRTPbj01NmZ2JF3NuUETjcF1bU/snlGjrqNzKGNYZNh4yx+oayFDAq3rqTbK6aEUV+p0UH1VHajgENLS+vsH0U/PfwhBzaAsCSz4wLEgs4DBImwe/F7hQEIz2Bg7hZjzLrC3lOVQL2+7S+FzcQrxaUIQrpyCtF3Yl+DvA8+Z+4TiYsKqYTJ5dvg3kRuKqzgN74TICgVIzHocqFXKpqQh8lAvgjvQlTegqmx+khvUyougfuTkTmYUTQ8as065xIuF7yMSzhSz8jauhwO0JrJMdoDlTlETbD4BeV3w8zaF1IhXealFWGUBeLku/Iw9fRnMSVtAk9oemTQJphtJVY9K80VWXOU3AIGw5q0gdKWqosJBQ4ibarJVGvSw0sKsLtOsSuPQaz0kBtwdiGvePAwVNC0e+wukDsdG/NSnbSIctM1CR1Rw/7EFB87mPyeI4+mTI4rY1QNC4QzZY4FjRevVs7J3qqt0xE/0N4sIKM1HMFOXv4m12FdQD7DwRmZKcfGLYZt9BEgqn6Hu7CDx3Eb7Wdtf02O2ecmx59Hn0k2cCGmH1O0WQXhIbfyLQWl2q0A6Bx6+XH1Ty37IWMygxixF2zZFB8J4tY7Cen/XOtc/3Z/2URjG2XcTRqux1dTCOhCD9VEMsgWNZoRu35CO19YNIlsys4KPCNxvIMECSMN+TYr6BCUKVfbnoPY8PeZOCFjCAnJpc9rimLYhSP5E+8+kpbtyK6kL27wKylmkC2tKvOWzH1egGAE="},{"type":"tool_use","id":"toolu_01P81NRvPNCbKr2PAnhrzgX3","name":"Bash","input":{"command":"cat TASK.md; ls -laR data out 2>/dev/null | head -50","description":"Read task and list workspace"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"41f94ae7-c410-4af0-b7f1-2c24c25f6001","timestamp":"2026-10-30T05:18:57.102Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"2a491407-f006-4da3-b87f-46d7d42068fc","keep":2,"tail":["89c78757d82b25c85173ee3161978e623bb0175b2c2ba2cf0dce85b71c0de3e3","a37241895f093895e1681242f1409a56d4ede48668469d30edaa05b14ad3ce52"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",3,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"452ec628568387c476e4286dcf7565f115e57029178cb4c1acb082c9753971df"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"43c56bda-5318-4c88-ab2e-c7733b45c7f2","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"type":"atis-latch","atis":"","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":"43c56bda-5318-4c88-ab2e-c7733b45c7f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrfNLruPpnMVchJJZyn","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01J58C8XKczjBwD6TmFKdjc4","name":"Bash","input":{"command":"cat data/README.md; head -5 data/DGS10.csv; tail -3 data/DGS10.csv; shasum -a 256 data/*; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nd=pd.read_csv('data/DGS10.csv'); print(d.shape, d.dtypes.to_dict()); print(d.isna().sum()); print(d.observation_date.duplicated().sum())\nd['dt']=pd.to_datetime(d.observation_date); print(d.dt.min(), d.dt.max(), d.dt.dt.dayofweek.value_counts().sort_index().to_dict(), d.dt.is_monotonic_increasing)\nprint(d.DGS10.describe())\nprint(pd.to_numeric(d.DGS10,errors='coerce').isna().sum())\n\"","description":"Inspect data and provenance"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2568,"cache_read_input_tokens":3713,"output_tokens":353,"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":2568},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXrfN4zVGh94xM79Mhgn","requestRef":"41f94ae7-c410-4af0-b7f1-2c24c25f6001","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7601be64-9fa0-410a-a629-dd05c7c79b75","timestamp":"2026-10-30T05:19:00.434Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"7601be64-9fa0-410a-a629-dd05c7c79b75","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01J58C8XKczjBwD6TmFKdjc4","type":"tool_result","content":"# Data provenance — F6-conf-01\n\n## `DGS10.csv` (5217 rows)\nObserved data: *Market Yield on U.S. Treasury Securities at 10-Year Constant Maturity, Quoted on an Investment Basis* (FRED series `DGS10`, daily, percent, not seasonally adjusted). Source: Board of Governors of the Federal Reserve System (US), H.15 Selected Interest Rates, distributed by FRED, Federal Reserve Bank of St. Louis.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=DGS10` (full history; raw file SHA-256 `f3b6b3956f888551c21cfbae007f157bb6433b4db8f557bd7a08b9eb8fd5a97b`), retrieved 2026-10-30T03:23:28Z.\n- The bundle file is the raw FRED CSV restricted to observation dates from 2000-01-01 to 2019-12-31 inclusive; the FRED format is kept unchanged: columns `observation_date` (YYYY-MM-DD) and `DGS10` (percent). FRED lists every weekday; on days when no yield is published (US market holidays) the `DGS10` field is empty.\n- Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying H.15 data are produced by a US government agency and are in the public domain.\n- SHA-256 of `DGS10.csv`: `8187f89ab6523b3c964255e1736cfcf0e2ca854ed9e50343e04f4dc2945c5cd7`\nobservation_date,DGS10\n2000-01-03,6.58\n2000-01-04,6.49\n2000-01-05,6.62\n2000-01-06,6.57\n2019-12-27,1.88\n2019-12-30,1.90\n2019-12-31,1.92\n8187f89ab6523b3c964255e1736cfcf0e2ca854ed9e50343e04f4dc2945c5cd7  data/DGS10.csv\n32b825f02387ef3d552df6def82c585d7f248980667a28f30e58506e472e561a  data/README.md\n(5217, 2) {'observation_date': dtype('O'), 'DGS10': dtype('float64')}\nobservation_date      0\nDGS10               215\ndtype: int64\n0\n2000-01-03 00:00:00 2019-12-31 00:00:00 {0: 1044, 1: 1044, 2: 1043, 3: 1043, 4: 1043} True\ncount    5002.000000\nmean        3.432167\nstd         1.239314\nmin         1.370000\n25%         2.340000\n50%         3.360000\n75%         4.410000\nmax         6.790000\nName: DGS10, dtype: float64\n215","is_error":false}]},"uuid":"26b04f2f-92e3-4337-8a67-372c911ff5bd","timestamp":"2026-10-30T05:19:00.728Z","toolUseResult":{"stdout":"# Data provenance — F6-conf-01\n\n## `DGS10.csv` (5217 rows)\nObserved data: *Market Yield on U.S. Treasury Securities at 10-Year Constant Maturity, Quoted on an Investment Basis* (FRED series `DGS10`, daily, percent, not seasonally adjusted). Source: Board of Governors of the Federal Reserve System (US), H.15 Selected Interest Rates, distributed by FRED, Federal Reserve Bank of St. Louis.\n- URL: `https://fred.stlouisfed.org/graph/fredgraph.csv?id=DGS10` (full history; raw file SHA-256 `f3b6b3956f888551c21cfbae007f157bb6433b4db8f557bd7a08b9eb8fd5a97b`), retrieved 2026-10-30T03:23:28Z.\n- The bundle file is the raw FRED CSV restricted to observation dates from 2000-01-01 to 2019-12-31 inclusive; the FRED format is kept unchanged: columns `observation_date` (YYYY-MM-DD) and `DGS10` (percent). FRED lists every weekday; on days when no yield is published (US market holidays) the `DGS10` field is empty.\n- Terms: FRED terms of use, https://fred.stlouisfed.org/legal/ ; the underlying H.15 data are produced by a US government agency and are in the public domain.\n- SHA-256 of `DGS10.csv`: `8187f89ab6523b3c964255e1736cfcf0e2ca854ed9e50343e04f4dc2945c5cd7`\nobservation_date,DGS10\n2000-01-03,6.58\n2000-01-04,6.49\n2000-01-05,6.62\n2000-01-06,6.57\n2019-12-27,1.88\n2019-12-30,1.90\n2019-12-31,1.92\n8187f89ab6523b3c964255e1736cfcf0e2ca854ed9e50343e04f4dc2945c5cd7  data/DGS10.csv\n32b825f02387ef3d552df6def82c585d7f248980667a28f30e58506e472e561a  data/README.md\n(5217, 2) {'observation_date': dtype('O'), 'DGS10': dtype('float64')}\nobservation_date      0\nDGS10               215\ndtype: int64\n0\n2000-01-03 00:00:00 2019-12-31 00:00:00 {0: 1044, 1: 1044, 2: 1043, 3: 1043, 4: 1043} True\ncount    5002.000000\nmean        3.432167\nstd         1.239314\nmin         1.370000\n25%         2.340000\n50%         3.360000\n75%         4.410000\nmax         6.790000\nName: DGS10, dtype: float64\n215","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"7601be64-9fa0-410a-a629-dd05c7c79b75","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"eb683df7bf76f9b82d235264d4e59e0149f47db0601314f5f8914c2ca585c0cf","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01J58C8XKczjBwD6TmFKdjc4","name":"Bash","input":{"command":"cat data/README.md; head -5 data/DGS10.csv; tail -3 data/DGS10.csv; shasum -a 256 data/*; ~/wp29/venv/bin/python -c \"\nimport pandas as pd\nd=pd.read_csv('data/DGS10.csv'); print(d.shape, d.dtypes.to_dict()); print(d.isna().sum()); print(d.observation_date.duplicated().sum())\nd['dt']=pd.to_datetime(d.observation_date); print(d.dt.min(), d.dt.max(), d.dt.dt.dayofweek.value_counts().sort_index().to_dict(), d.dt.is_monotonic_increasing)\nprint(d.DGS10.describe())\nprint(pd.to_numeric(d.DGS10,errors='coerce').isna().sum())\n\"","description":"Inspect data and provenance"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"cd78769d-429f-4dda-b971-80087e152d9f","timestamp":"2026-10-30T05:19:00.731Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"41f94ae7-c410-4af0-b7f1-2c24c25f6001","keep":4,"tail":["eb683df7bf76f9b82d235264d4e59e0149f47db0601314f5f8914c2ca585c0cf","9eebd02d3a85337b866ab53faec396dc2d8d9dfab9183769d14565ae6e8ac717"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",5,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"3a4254e8010c35374515c08675c3e6c20208ebda31ade92f27d4fb5ada9f54c4"}
{"parentUuid":"26b04f2f-92e3-4337-8a67-372c911ff5bd","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrfdr2VYyVHFjxBhK15","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQSgwgKEAgTGAI4AUIIdGhpbmtpbmcSDO7KKFt4LPlOKMtM6xoMM1oJgbA3+VQEmlyuIjDflnRP2NZTQRzFcKp0Cj9BeEgC15GcWsw7JwXUf6ght16eq/wjC7bTobCB2EDJs90qoAdg/2PqAHOYbFSjnCtvsRnurDFgu5LRpL+OZMltfNbdYN3nsBPLLYqdfvQ9gtkDB+LQv76KkrJV3D5LE9YjrTk0fCXoKXxGDJ4YtsMBhM9YQ/Tz+1TLwoRmondcnrEolWQs29pL7k7x84I4LZqjvPkDrhJlSv8Aqg7U0DQczESyaU+kxyHyPRM/Qlvj3Z/xXJaaQJEsWyb8NNPQwwsvO9z45nayXWCy8iKOuuiwt8give/2BOYXRbusvI21cpuL1M1ojRkEqKD8pK7gzZf0zfGXxrBI2sgTM0I5Z3YJJAlAWPOsODK4PiPytrqeq7EXqGHbBj7oWpJTBlVXB9xRF1tULJJsGHl1RnQgrd5EndZ8Sp8H4ciLRfr4/XmkL6c4gHeHSAZy/rZHEpjFPgDUmKn+p6ajMlCtw8QVQtKghwb1lD+9UIC3gts+XAsbSIsSwxlIKKEKVzI7VycFpm8MxOZsAA9HvFdXqW3c8ZYaywVvSKT3LrvwLPyn1Rhg1V0AYa8uXTYJGqm+8U0rb/E80BiGR7w2NqPxNuQFSZJimPmBHWFUDM+UFNy2csqOzNVdzh/5s1coh8+hIb9gvQX5v7u4E3U9uEJ/Inir08IqLvKsnCkuMpHHP59vO2PaBM5Lzms9vT2c2JXdz9EkOhi7Ws3iOztWyPnGiG9KRvjfRGWEUVwmofM9dV0iEbOcLmQWg+L1DgPh6rguehijZt4DzPLiIHZtxMQ7+Rsv3cyOjVEpFeAohZq1aGR7n55sJa+4HuRMpLWdX85Tpzd6YUCY6mSUt4wveZHU2oIoebLOhuLmKX8bDPwmX7g6VhqQErmGzlFHu/kenf8HsfuV6it0GcANpR2jepBmN09b+renY/DHh0liYJZh0YsxaUPHejnmOkQxlF9zk9VjsMHRTJevUAr29IuyIDTKUxNmm+7jXRy+HYQXd9uHecUX81hUxhBh3UqcuXibsQoC7Xrv0V/yG4MOdfiNHriFhC8oTzHH/NVOxZe/E6DsqPhekxCNTcqMXxhw9GH5GACXIJ9Q9oHnUpDxVJSLz/NLySP63b8R9cbzig8EirXi7TWJb1H0Ax6iftOfKnT22KOKftV8xxye7/ct5pxj7SyXazXoukLA/I3vFn0GL4cViixeTKAaIUhJtdrPkXfXVhMNylPLbQJ7AlitFKXFtZB/OW/fFglJEpFUaM9tQB1DLw7uP+SECjgdqa9R+k37Rs7rHVkJPIj8lfpLGAE="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1291,"cache_read_input_tokens":6281,"output_tokens":3282,"output_tokens_details":{"thinking_tokens":122},"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":1291},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1021,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXrfdaev5ZAr4WZqBNZB","requestRef":"cd78769d-429f-4dda-b971-80087e152d9f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7ac4dd8f-fc12-4821-87e2-78c37afa312f","timestamp":"2026-10-30T05:19:02.953Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"7ac4dd8f-fc12-4821-87e2-78c37afa312f","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrfdr2VYyVHFjxBhK15","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011aZP6j8V5s1zR8U2jZ8axR","name":"Bash","input":{"command":"mkdir -p out/state; cat > out/analysis.py <<'EOF'\n\"\"\"F6-conf-01: weekday effects in daily changes of the 10y Treasury yield (DGS10).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/DGS10.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np, pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nDAYS = [\"Monday\", \"Tuesday\", \"Wednesday\", \"Thursday\", \"Friday\"]\n\nraw = pd.read_csv(\"data/DGS10.csv\", dtype={\"observation_date\": str})\nn_raw = len(raw)\nraw[\"date\"] = pd.to_datetime(raw[\"observation_date\"], format=\"%Y-%m-%d\")\nassert raw[\"date\"].is_monotonic_increasing and not raw[\"date\"].duplicated().any()\ny = pd.to_numeric(raw[\"DGS10\"], errors=\"coerce\")\nn_missing = int(y.isna().sum())\nd = raw.loc[y.notna(), [\"date\"]].copy(); d[\"y\"] = y[y.notna()].values\nn_avail = len(d)\nd[\"dy\"] = 100.0 * d[\"y\"].diff()            # bp, between consecutive available obs\nd[\"gap_days\"] = d[\"date\"].diff().dt.days\nch = d.dropna(subset=[\"dy\"]).copy()\nch[\"dy\"] = ch[\"dy\"].round(10)              # remove float noise from 2-decimal differences\nch[\"wd\"] = ch[\"date\"].dt.dayofweek\nassert ch[\"wd\"].between(0, 4).all()\nn_changes = len(ch)\n\npd.DataFrame([\n    dict(step=1, rule=\"drop rows with empty DGS10 (holidays)\", n_before=n_raw, n_after=n_avail,\n         n_removed=n_raw - n_avail, rationale=\"no published yield; required by TASK\"),\n    dict(step=2, rule=\"first available observation has no change\", n_before=n_avail, n_after=n_changes,\n         n_removed=1, rationale=\"differencing\"),\n]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\ntrain = ch[ch[\"date\"] <= \"2009-12-31\"]; test = ch[ch[\"date\"] >= \"2010-01-01\"]\nassert len(train) + len(test) == n_changes\n\n# (i) one-way ANOVA, all changes\ngroups = [ch.loc[ch.wd == k, \"dy\"].values for k in range(5)]\nF, p = stats.f_oneway(*groups)\n\n# (ii) Monday contrast, Welch two-sample t interval\nmon = ch.loc[ch.wd == 0, \"dy\"].values; oth = ch.loc[ch.wd != 0, \"dy\"].values\neff = mon.mean() - oth.mean()\nv1, v2 = mon.var(ddof=1) / len(mon), oth.var(ddof=1) / len(oth)\nse = np.sqrt(v1 + v2)\ndfw = (v1 + v2) ** 2 / (v1 ** 2 / (len(mon) - 1) + v2 ** 2 / (len(oth) - 1))\ntq = stats.t.ppf(0.975, dfw)\nlo, hi = eff - tq * se, eff + tq * se\nwelch_p = 2 * stats.t.sf(abs(eff / se), dfw)\n\n# (iii) out-of-sample: weekday means from estimation period only\nwd_means_train = train.groupby(\"wd\")[\"dy\"].mean()\npred = test[\"wd\"].map(wd_means_train).values\nrmse_rw = float(np.sqrt(np.mean(test[\"dy\"].values ** 2)))\nrmse_wd = float(np.sqrt(np.mean((test[\"dy\"].values - pred) ** 2)))\n# supplementary: Diebold-Mariano (squared loss, h=1, plain variance since h=1)\ndl = test[\"dy\"].values ** 2 - (test[\"dy\"].values - pred) ** 2   # >0 means weekday model better\ndm = dl.mean() / (dl.std(ddof=1) / np.sqrt(len(dl)))\ndm_p = 2 * stats.norm.sf(abs(dm))\nrmse_train_mean = float(np.sqrt(np.mean((test[\"dy\"].values - train[\"dy\"].mean()) ** 2)))\n\n# table + figure\ntab = pd.DataFrame({\"weekday\": DAYS,\n                    \"n\": [len(g) for g in groups],\n                    \"mean_bp\": [g.mean() for g in groups],\n                    \"se_bp\": [g.std(ddof=1) / np.sqrt(len(g)) for g in groups]})\ntab.to_csv(f\"{OUT}/table1.csv\", index=False, float_format=\"%.6f\")\ncrit = [stats.t.ppf(0.975, n - 1) for n in tab.n]\nfig, ax = plt.subplots(figsize=(6, 4))\nax.errorbar(range(5), tab.mean_bp, yerr=np.array(crit) * tab.se_bp, fmt=\"o\", capsize=5)\nax.axhline(0, color=\"grey\", lw=0.8, ls=\"--\")\nax.set_xticks(range(5)); ax.set_xticklabels(DAYS)\nax.set_ylabel(\"Mean daily change in DGS10 (bp)\")\nax.set_title(\"10y Treasury yield: mean 1-day change by weekday\\n2000-2019, 95% CI (t, per-weekday SE)\")\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150); plt.close(fig)\n\nif p >= 0.05:\n    concl = \"no_detectable_effect\"\nelif lo > 0:\n    concl = \"positive_effect\"\nelif hi < 0:\n    concl = \"negative_effect\"\nelse:\n    concl = \"no_detectable_effect\"\n\nn_long_gap = int((ch[\"gap_days\"] > 3).sum())\nres = {\n    \"task_id\": \"F6-conf-01\",\n    \"n_missing_rows\": n_missing,\n    \"n_train\": int(len(train)), \"n_test\": int(len(test)),\n    \"anova_f_stat\": float(F), \"anova_p_value\": float(p),\n    \"effect_estimate\": float(eff), \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n    \"baseline_metric\": rmse_rw, \"model_metric\": rmse_wd,\n    \"conclusion\": concl,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": f\"{n_missing} rows with empty DGS10 field (US market holidays)\",\n         \"handling\": \"dropped before differencing, as required by TASK\"},\n        {\"issue\": f\"{n_long_gap} changes span a holiday (calendar gap > 3 days, or > 1 day mid-week), e.g. Tuesday after a Monday holiday covers two trading sessions' worth of calendar time\",\n         \"handling\": \"kept and attributed to the weekday of t per TASK rule; noted as a limitation\"},\n    ],\n    \"n_input_rows\": {\"DGS10.csv\": int(n_raw)},\n    \"n_analysed\": int(n_changes),\n    \"random_seed\": None,\n    \"supplementary\": {\n        \"effect_method\": \"Welch two-sample t interval (Monday vs other weekdays, all changes)\",\n        \"effect_se\": float(se), \"effect_welch_df\": float(dfw), \"effect_welch_p_value\": float(welch_p),\n        \"n_monday\": int(len(mon)), \"n_other\": int(len(oth)),\n        \"train_weekday_means_bp\": {DAYS[k]: float(v) for k, v in wd_means_train.items()},\n        \"rmse_ratio_model_over_baseline\": rmse_wd / rmse_rw,\n        \"dm_stat_sqloss_positive_favours_weekday\": float(dm), \"dm_p_value\": float(dm_p),\n        \"rmse_test_train_unconditional_mean\": rmse_train_mean,\n        \"n_changes_spanning_holiday_gap\": n_long_gap,\n        \"n_available_obs\": int(n_avail),\n    },\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n    json.dump(res, f, indent=2)\nprint(json.dumps({k: res[k] for k in [\"n_train\", \"n_test\", \"anova_f_stat\", \"anova_p_value\",\n      \"effect_estimate\", \"effect_ci_low\", \"effect_ci_high\", \"baseline_metric\", \"model_metric\", \"conclusion\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv && cat out/results.json | sed -n '/supplementary/,$p'","description":"Write and run analysis script"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1291,"cache_read_input_tokens":6281,"output_tokens":3282,"output_tokens_details":{"thinking_tokens":122},"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":1291},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXrfdaev5ZAr4WZqBNZB","requestRef":"cd78769d-429f-4dda-b971-80087e152d9f","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"e99137c1-7d19-4031-b842-141b5b3586ec","timestamp":"2026-10-30T05:19:26.762Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"e99137c1-7d19-4031-b842-141b5b3586ec","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_011aZP6j8V5s1zR8U2jZ8axR","type":"tool_result","content":"{\n \"n_train\": 2500,\n \"n_test\": 2501,\n \"anova_f_stat\": 0.263465716807118,\n \"anova_p_value\": 0.9015060507654888,\n \"effect_estimate\": 0.050170098401698796,\n \"effect_ci_low\": -0.31933577569409977,\n \"effect_ci_high\": 0.41967597249749733,\n \"baseline_metric\": 4.875704154642544,\n \"model_metric\": 4.883841522290305,\n \"conclusion\": \"no_detectable_effect\"\n}\nweekday,n,mean_bp,se_bp\nMonday,919,-0.052231,0.164386\nTuesday,1028,-0.219844,0.177007\nWednesday,1030,0.016505,0.182346\nThursday,1012,-0.059289,0.186918\nFriday,1012,-0.147233,0.189918\n  \"supplementary\": {\n    \"effect_method\": \"Welch two-sample t interval (Monday vs other weekdays, all changes)\",\n    \"effect_se\": 0.18837955539096196,\n    \"effect_welch_df\": 1548.9581965107577,\n    \"effect_welch_p_value\": 0.7900247217974709,\n    \"n_monday\": 919,\n    \"n_other\": 4082,\n    \"train_weekday_means_bp\": {\n      \"Monday\": -0.05434782608695652,\n      \"Tuesday\": -0.40545808966861596,\n      \"Wednesday\": -0.2054263565891473,\n      \"Thursday\": 0.01383399209486166,\n      \"Friday\": 0.11683168316831684\n    },\n    \"rmse_ratio_model_over_baseline\": 1.0016689625518014,\n    \"dm_stat_sqloss_positive_favours_weekday\": -1.8573748978469748,\n    \"dm_p_value\": 0.06325783524850241,\n    \"rmse_test_train_unconditional_mean\": 4.8751986528852305,\n    \"n_changes_spanning_holiday_gap\": 155,\n    \"n_available_obs\": 5002\n  }\n}","is_error":false}]},"uuid":"d220cbf8-6169-4ee5-a955-c4e7fec093f2","timestamp":"2026-10-30T05:19:27.773Z","toolUseResult":{"stdout":"{\n \"n_train\": 2500,\n \"n_test\": 2501,\n \"anova_f_stat\": 0.263465716807118,\n \"anova_p_value\": 0.9015060507654888,\n \"effect_estimate\": 0.050170098401698796,\n \"effect_ci_low\": -0.31933577569409977,\n \"effect_ci_high\": 0.41967597249749733,\n \"baseline_metric\": 4.875704154642544,\n \"model_metric\": 4.883841522290305,\n \"conclusion\": \"no_detectable_effect\"\n}\nweekday,n,mean_bp,se_bp\nMonday,919,-0.052231,0.164386\nTuesday,1028,-0.219844,0.177007\nWednesday,1030,0.016505,0.182346\nThursday,1012,-0.059289,0.186918\nFriday,1012,-0.147233,0.189918\n  \"supplementary\": {\n    \"effect_method\": \"Welch two-sample t interval (Monday vs other weekdays, all changes)\",\n    \"effect_se\": 0.18837955539096196,\n    \"effect_welch_df\": 1548.9581965107577,\n    \"effect_welch_p_value\": 0.7900247217974709,\n    \"n_monday\": 919,\n    \"n_other\": 4082,\n    \"train_weekday_means_bp\": {\n      \"Monday\": -0.05434782608695652,\n      \"Tuesday\": -0.40545808966861596,\n      \"Wednesday\": -0.2054263565891473,\n      \"Thursday\": 0.01383399209486166,\n      \"Friday\": 0.11683168316831684\n    },\n    \"rmse_ratio_model_over_baseline\": 1.0016689625518014,\n    \"dm_stat_sqloss_positive_favours_weekday\": -1.8573748978469748,\n    \"dm_p_value\": 0.06325783524850241,\n    \"rmse_test_train_unconditional_mean\": 4.8751986528852305,\n    \"n_changes_spanning_holiday_gap\": 155,\n    \"n_available_obs\": 5002\n  }\n}","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"e99137c1-7d19-4031-b842-141b5b3586ec","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"b61129e3ad9923cb8fed65a8c3b128bc14776c0e41cd8aa4b68bd6cad229913f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_011aZP6j8V5s1zR8U2jZ8axR","name":"Bash","input":{"command":"mkdir -p out/state; cat > out/analysis.py <<'EOF'\n\"\"\"F6-conf-01: weekday effects in daily changes of the 10y Treasury yield (DGS10).\nRun from workspace root: ~/wp29/venv/bin/python out/analysis.py\nReads only data/DGS10.csv; writes out/results.json, out/table1.csv, out/figure1.png, out/exclusions.csv.\nNo randomness is used (random_seed = null).\"\"\"\nimport json, os\nimport numpy as np, pandas as pd\nfrom scipy import stats\nimport matplotlib\nmatplotlib.use(\"Agg\")\nimport matplotlib.pyplot as plt\n\nOUT = \"out\"; os.makedirs(OUT, exist_ok=True)\nDAYS = [\"Monday\", \"Tuesday\", \"Wednesday\", \"Thursday\", \"Friday\"]\n\nraw = pd.read_csv(\"data/DGS10.csv\", dtype={\"observation_date\": str})\nn_raw = len(raw)\nraw[\"date\"] = pd.to_datetime(raw[\"observation_date\"], format=\"%Y-%m-%d\")\nassert raw[\"date\"].is_monotonic_increasing and not raw[\"date\"].duplicated().any()\ny = pd.to_numeric(raw[\"DGS10\"], errors=\"coerce\")\nn_missing = int(y.isna().sum())\nd = raw.loc[y.notna(), [\"date\"]].copy(); d[\"y\"] = y[y.notna()].values\nn_avail = len(d)\nd[\"dy\"] = 100.0 * d[\"y\"].diff()            # bp, between consecutive available obs\nd[\"gap_days\"] = d[\"date\"].diff().dt.days\nch = d.dropna(subset=[\"dy\"]).copy()\nch[\"dy\"] = ch[\"dy\"].round(10)              # remove float noise from 2-decimal differences\nch[\"wd\"] = ch[\"date\"].dt.dayofweek\nassert ch[\"wd\"].between(0, 4).all()\nn_changes = len(ch)\n\npd.DataFrame([\n    dict(step=1, rule=\"drop rows with empty DGS10 (holidays)\", n_before=n_raw, n_after=n_avail,\n         n_removed=n_raw - n_avail, rationale=\"no published yield; required by TASK\"),\n    dict(step=2, rule=\"first available observation has no change\", n_before=n_avail, n_after=n_changes,\n         n_removed=1, rationale=\"differencing\"),\n]).to_csv(f\"{OUT}/exclusions.csv\", index=False)\n\ntrain = ch[ch[\"date\"] <= \"2009-12-31\"]; test = ch[ch[\"date\"] >= \"2010-01-01\"]\nassert len(train) + len(test) == n_changes\n\n# (i) one-way ANOVA, all changes\ngroups = [ch.loc[ch.wd == k, \"dy\"].values for k in range(5)]\nF, p = stats.f_oneway(*groups)\n\n# (ii) Monday contrast, Welch two-sample t interval\nmon = ch.loc[ch.wd == 0, \"dy\"].values; oth = ch.loc[ch.wd != 0, \"dy\"].values\neff = mon.mean() - oth.mean()\nv1, v2 = mon.var(ddof=1) / len(mon), oth.var(ddof=1) / len(oth)\nse = np.sqrt(v1 + v2)\ndfw = (v1 + v2) ** 2 / (v1 ** 2 / (len(mon) - 1) + v2 ** 2 / (len(oth) - 1))\ntq = stats.t.ppf(0.975, dfw)\nlo, hi = eff - tq * se, eff + tq * se\nwelch_p = 2 * stats.t.sf(abs(eff / se), dfw)\n\n# (iii) out-of-sample: weekday means from estimation period only\nwd_means_train = train.groupby(\"wd\")[\"dy\"].mean()\npred = test[\"wd\"].map(wd_means_train).values\nrmse_rw = float(np.sqrt(np.mean(test[\"dy\"].values ** 2)))\nrmse_wd = float(np.sqrt(np.mean((test[\"dy\"].values - pred) ** 2)))\n# supplementary: Diebold-Mariano (squared loss, h=1, plain variance since h=1)\ndl = test[\"dy\"].values ** 2 - (test[\"dy\"].values - pred) ** 2   # >0 means weekday model better\ndm = dl.mean() / (dl.std(ddof=1) / np.sqrt(len(dl)))\ndm_p = 2 * stats.norm.sf(abs(dm))\nrmse_train_mean = float(np.sqrt(np.mean((test[\"dy\"].values - train[\"dy\"].mean()) ** 2)))\n\n# table + figure\ntab = pd.DataFrame({\"weekday\": DAYS,\n                    \"n\": [len(g) for g in groups],\n                    \"mean_bp\": [g.mean() for g in groups],\n                    \"se_bp\": [g.std(ddof=1) / np.sqrt(len(g)) for g in groups]})\ntab.to_csv(f\"{OUT}/table1.csv\", index=False, float_format=\"%.6f\")\ncrit = [stats.t.ppf(0.975, n - 1) for n in tab.n]\nfig, ax = plt.subplots(figsize=(6, 4))\nax.errorbar(range(5), tab.mean_bp, yerr=np.array(crit) * tab.se_bp, fmt=\"o\", capsize=5)\nax.axhline(0, color=\"grey\", lw=0.8, ls=\"--\")\nax.set_xticks(range(5)); ax.set_xticklabels(DAYS)\nax.set_ylabel(\"Mean daily change in DGS10 (bp)\")\nax.set_title(\"10y Treasury yield: mean 1-day change by weekday\\n2000-2019, 95% CI (t, per-weekday SE)\")\nfig.tight_layout(); fig.savefig(f\"{OUT}/figure1.png\", dpi=150); plt.close(fig)\n\nif p >= 0.05:\n    concl = \"no_detectable_effect\"\nelif lo > 0:\n    concl = \"positive_effect\"\nelif hi < 0:\n    concl = \"negative_effect\"\nelse:\n    concl = \"no_detectable_effect\"\n\nn_long_gap = int((ch[\"gap_days\"] > 3).sum())\nres = {\n    \"task_id\": \"F6-conf-01\",\n    \"n_missing_rows\": n_missing,\n    \"n_train\": int(len(train)), \"n_test\": int(len(test)),\n    \"anova_f_stat\": float(F), \"anova_p_value\": float(p),\n    \"effect_estimate\": float(eff), \"effect_ci_low\": float(lo), \"effect_ci_high\": float(hi),\n    \"baseline_metric\": rmse_rw, \"model_metric\": rmse_wd,\n    \"conclusion\": concl,\n    \"feasibility\": \"complete\", \"feasibility_reason\": None,\n    \"data_issues\": [\n        {\"issue\": f\"{n_missing} rows with empty DGS10 field (US market holidays)\",\n         \"handling\": \"dropped before differencing, as required by TASK\"},\n        {\"issue\": f\"{n_long_gap} changes span a holiday (calendar gap > 3 days, or > 1 day mid-week), e.g. Tuesday after a Monday holiday covers two trading sessions' worth of calendar time\",\n         \"handling\": \"kept and attributed to the weekday of t per TASK rule; noted as a limitation\"},\n    ],\n    \"n_input_rows\": {\"DGS10.csv\": int(n_raw)},\n    \"n_analysed\": int(n_changes),\n    \"random_seed\": None,\n    \"supplementary\": {\n        \"effect_method\": \"Welch two-sample t interval (Monday vs other weekdays, all changes)\",\n        \"effect_se\": float(se), \"effect_welch_df\": float(dfw), \"effect_welch_p_value\": float(welch_p),\n        \"n_monday\": int(len(mon)), \"n_other\": int(len(oth)),\n        \"train_weekday_means_bp\": {DAYS[k]: float(v) for k, v in wd_means_train.items()},\n        \"rmse_ratio_model_over_baseline\": rmse_wd / rmse_rw,\n        \"dm_stat_sqloss_positive_favours_weekday\": float(dm), \"dm_p_value\": float(dm_p),\n        \"rmse_test_train_unconditional_mean\": rmse_train_mean,\n        \"n_changes_spanning_holiday_gap\": n_long_gap,\n        \"n_available_obs\": int(n_avail),\n    },\n}\nwith open(f\"{OUT}/results.json\", \"w\") as f:\n    json.dump(res, f, indent=2)\nprint(json.dumps({k: res[k] for k in [\"n_train\", \"n_test\", \"anova_f_stat\", \"anova_p_value\",\n      \"effect_estimate\", \"effect_ci_low\", \"effect_ci_high\", \"baseline_metric\", \"model_metric\", \"conclusion\"]}, indent=1))\nEOF\n~/wp29/venv/bin/python out/analysis.py && cat out/table1.csv && cat out/results.json | sed -n '/supplementary/,$p'","description":"Write and run analysis script"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"27606ff3-122a-4a3f-a8a7-d82d372269eb","timestamp":"2026-10-30T05:19:27.777Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"cd78769d-429f-4dda-b971-80087e152d9f","keep":6,"tail":["b61129e3ad9923cb8fed65a8c3b128bc14776c0e41cd8aa4b68bd6cad229913f","3431ff839524b912d660f198adf767551e3ec849b9c775aa3be288035566341d"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",7,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"e80bc0c0c2295c8a62dd407ae82ca254bdd702b90babc2489a6df95ed01647c0"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"d220cbf8-6169-4ee5-a955-c4e7fec093f2","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"type":"atis-latch","atis":"","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":"d220cbf8-6169-4ee5-a955-c4e7fec093f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrhdUzstQo97GEyrsxW","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":3966,"cache_read_input_tokens":7572,"output_tokens":1126,"output_tokens_details":{"thinking_tokens":141},"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":3966},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":1162,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXrhdDczEo4DXjbJY6fE","requestRef":"27606ff3-122a-4a3f-a8a7-d82d372269eb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"74c21579-4178-4c9b-9313-227695425014","timestamp":"2026-10-30T05:19:30.270Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"74c21579-4178-4c9b-9313-227695425014","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrhdUzstQo97GEyrsxW","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01WqXpMeGtSL1ZoqLYAwkcnf","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace('n_long_gap = int((ch[\"gap_days\"] > 3).sum())','n_long_gap = int((ch[\"gap_days\"] > np.where(ch[\"wd\"] == 0, 3, 1)).sum())  # longer than a normal weekday/weekend gap')\ns=s.replace('(calendar gap > 3 days, or > 1 day mid-week)','(calendar gap longer than normal: > 3 days for Monday, > 1 day otherwise)')\nopen('analysis.py','w').write(s)\nEOF\ncd .. && rm -f out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && shasum -a 256 out/results.json out/table1.csv > /tmp/h1 && ~/wp29/venv/bin/python out/analysis.py >/dev/null && shasum -a 256 out/results.json out/table1.csv | diff - /tmp/h1 && echo IDENTICAL; grep n_changes_spanning out/results.json\n~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd, numpy as np, json, statsmodels.formula.api as smf\nfrom statsmodels.stats.anova import anova_lm\nr=json.load(open('out/results.json'))\nd=pd.read_csv('data/DGS10.csv').dropna(); d['date']=pd.to_datetime(d.observation_date)\nd['dy']=100*d.DGS10.diff(); d=d.dropna(); d['wd']=d.date.dt.dayofweek; d['mon']=(d.wd==0).astype(int)\na=anova_lm(smf.ols('dy~C(wd)',d).fit()); print('sm F,p',a.F.iloc[0],a['PR(>F)'].iloc[0], 'df',a.df.tolist())\nm=smf.ols('dy~mon',d).fit(cov_type='HC1'); print('HC1 mon',m.params.mon,m.conf_int().loc['mon'].tolist())\nprint('checks', r['n_train']+r['n_test']==r['n_analysed'], r['n_input_rows']['DGS10.csv']-r['n_missing_rows']-1==r['n_analysed'],\n r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'])\nt=pd.read_csv('out/table1.csv'); print('table n sum',t.n.sum(), (t.se_bp>0).all())\nEOF\ncat out/exclusions.csv","description":"Fix gap count, rerun twice, cross-check"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3966,"cache_read_input_tokens":7572,"output_tokens":1126,"output_tokens_details":{"thinking_tokens":141},"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":3966},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXrhdDczEo4DXjbJY6fE","requestRef":"27606ff3-122a-4a3f-a8a7-d82d372269eb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"29165c6a-7845-41f4-94ce-bba51df5d3aa","timestamp":"2026-10-30T05:19:37.168Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"29165c6a-7845-41f4-94ce-bba51df5d3aa","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01WqXpMeGtSL1ZoqLYAwkcnf","type":"tool_result","content":"IDENTICAL\n    \"n_changes_spanning_holiday_gap\": 214,\nsm F,p 0.2634657168071198 0.9015060507654888 df [4.0, 4996.0]\nHC1 mon 0.050170098401700364 [-0.3189570734770597, 0.4192972702804604]\nchecks True True True\ntable n sum 5001 True\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with empty DGS10 (holidays),5217,5002,215,no published yield; required by TASK\n2,first available observation has no change,5002,5001,1,differencing","is_error":false}]},"uuid":"cfd663b0-f1e6-4246-a825-1c12dcca2944","timestamp":"2026-10-30T05:19:39.999Z","toolUseResult":{"stdout":"IDENTICAL\n    \"n_changes_spanning_holiday_gap\": 214,\nsm F,p 0.2634657168071198 0.9015060507654888 df [4.0, 4996.0]\nHC1 mon 0.050170098401700364 [-0.3189570734770597, 0.4192972702804604]\nchecks True True True\ntable n sum 5001 True\nstep,rule,n_before,n_after,n_removed,rationale\n1,drop rows with empty DGS10 (holidays),5217,5002,215,no published yield; required by TASK\n2,first available observation has no change,5002,5001,1,differencing","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"29165c6a-7845-41f4-94ce-bba51df5d3aa","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"d0dcdad906e587e5e128d2257adb109631b27e841759e6b7d49d905eb5c74a97","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01WqXpMeGtSL1ZoqLYAwkcnf","name":"Bash","input":{"command":"cd out && ~/wp29/venv/bin/python - <<'EOF'\ns=open('analysis.py').read()\ns=s.replace('n_long_gap = int((ch[\"gap_days\"] > 3).sum())','n_long_gap = int((ch[\"gap_days\"] > np.where(ch[\"wd\"] == 0, 3, 1)).sum())  # longer than a normal weekday/weekend gap')\ns=s.replace('(calendar gap > 3 days, or > 1 day mid-week)','(calendar gap longer than normal: > 3 days for Monday, > 1 day otherwise)')\nopen('analysis.py','w').write(s)\nEOF\ncd .. && rm -f out/results.json out/table1.csv out/figure1.png && ~/wp29/venv/bin/python out/analysis.py >/dev/null && shasum -a 256 out/results.json out/table1.csv > /tmp/h1 && ~/wp29/venv/bin/python out/analysis.py >/dev/null && shasum -a 256 out/results.json out/table1.csv | diff - /tmp/h1 && echo IDENTICAL; grep n_changes_spanning out/results.json\n~/wp29/venv/bin/python - <<'EOF'\nimport pandas as pd, numpy as np, json, statsmodels.formula.api as smf\nfrom statsmodels.stats.anova import anova_lm\nr=json.load(open('out/results.json'))\nd=pd.read_csv('data/DGS10.csv').dropna(); d['date']=pd.to_datetime(d.observation_date)\nd['dy']=100*d.DGS10.diff(); d=d.dropna(); d['wd']=d.date.dt.dayofweek; d['mon']=(d.wd==0).astype(int)\na=anova_lm(smf.ols('dy~C(wd)',d).fit()); print('sm F,p',a.F.iloc[0],a['PR(>F)'].iloc[0], 'df',a.df.tolist())\nm=smf.ols('dy~mon',d).fit(cov_type='HC1'); print('HC1 mon',m.params.mon,m.conf_int().loc['mon'].tolist())\nprint('checks', r['n_train']+r['n_test']==r['n_analysed'], r['n_input_rows']['DGS10.csv']-r['n_missing_rows']-1==r['n_analysed'],\n r['effect_ci_low']<r['effect_estimate']<r['effect_ci_high'])\nt=pd.read_csv('out/table1.csv'); print('table n sum',t.n.sum(), (t.se_bp>0).all())\nEOF\ncat out/exclusions.csv","description":"Fix gap count, rerun twice, cross-check"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"528dba23-6e1e-44cb-9ef1-b6ab165aefd0","timestamp":"2026-10-30T05:19:40.004Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"27606ff3-122a-4a3f-a8a7-d82d372269eb","keep":8,"tail":["d0dcdad906e587e5e128d2257adb109631b27e841759e6b7d49d905eb5c74a97","3ebd3fd1dd026f9b45cf62effa7e6bf794cabf72c26dbfe895b65dfd19a60141"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",9,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2ed899bbaac185d27fa34fc26e4a0043685608706edba29de20447b762b85458"}
{"parentUuid":"cfd663b0-f1e6-4246-a825-1c12dcca2944","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXriXjk7VgYAmPrvWVgC","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"","signature":"CAQS5AcKEAgTGAI4AUIIdGhpbmtpbmcSDA757uLJxfSnwASTJBoMM6SSwMRYuI4RVdefIjDkw6RRpQMPi9imWsOmf8/BbUrNiPCE753tHbGdTovkc2F3SGvLSE8WEojTVK3w7QEqgQcGF2DNPFdJz7/9o/ksbttU0SjPfE9206bFcxSjd1qJKI2fY1ImnG0jkYLCSvgYSelg/9+0oaz4jVZ0mVwcNwyhAa570ZvoxTpY40SfmUAT4/jiONiY5aPQPcK2lrH1e/qDTzTaSVLx4+8A1uSw51QHmnH/hLKhjt0cl5Q+fPo9SzgWYXfD/ed8y5GZrfvXVm1sn+YutA9uuzyq6NaA6wx3cDRe0lVIDHuSlFRiq6HwO2NbG90J83WX/cDr6n3s9fRVb7w9ahGJFjZWug+5VHgF4LzFf0XfIN+qCgEnPzIgdlUBemyFXfit9ocOGSyOPSMzWSDRbF4k4wWbpcoJFD8wwKNzE/0JDdhGNpwiC7hroSM0Ll/pXfc95IV1rGjHFhX4BjkP28990yS7RnCkek9cLhgfXnyGmuxhWUcObAt5Di8utzStb2Jua5CPcxhzBjsCQ364PF8+ixiSi5ZA6PZCTMeTEhmgI6VocY41rzLVNHqrYJspiywkBGQh1vCbQNQafx6/cDBeSb+n6FVj0UombDhWicrK5hQI2p5HOWIN0I8f2BsQ2WufdqNBe+iiQpsq7Rh5TQDMXCXs9t2cwewjU79pbG8GsJFAmUiT55DwSSnzy5QO7hUvAGdU4IyVbzd7Pqis0OLLqbNPnJMLagVVdH3LgKJluqaUAVNPRGnwzTHMSipvXLbn9K9EcmnbmhjvaY+W2bibJIgUPxQfduwmvagSeHILTQdpt311unqYAbTs3g91gV0yDVK4qcmBdCHTxorEMxc4vYtsw6K9XjYjCwWEEdfjZTAXzcnwByaqM0+d2HJYurb4oz6/oKvff2HHaz0LNrmHSEQxUJCsz0TgoQ/reX1KjepINpsl9FXdk3YRllVbcYPRLN4mJTxfk2+DsqAIeWtXtCT3IN8Cn1BRW4QvTrakBsUAXBGIlcFM9AnOIHQvP1PTyy+uo4mc9YD9Z4eRztQQd+bi/u3A7/3hY1IguJ6KqwKfAwhg05OOn209GMr84qu9OWOj1bmspZIWZXHFxx+1J8UX3xutQYLqOr7QGM2T94xrnPyZOkx+gMcf72IQITbdAkyuDcjUgAK0eT7ECIT/XSNY2WBeqWN3uQ1olVJErr7kkzxelAoR+XjqYBzJApC14h9gyq3uygDN9miD6PZFSTZfQT0x5CMaSVVmt8PcTYwiyYqq70CWnycYAQ=="}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1333,"cache_read_input_tokens":11538,"output_tokens":308,"output_tokens_details":{"thinking_tokens":94},"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":1333},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":535,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXriXV7ptz5gUhnNStzN","requestRef":"528dba23-6e1e-44cb-9ef1-b6ab165aefd0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c7d5661a-6c48-491c-8060-906504433a85","timestamp":"2026-10-30T05:19:41.736Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"c7d5661a-6c48-491c-8060-906504433a85","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXriXjk7VgYAmPrvWVgC","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_015MFMnEV4bvpyU6KSYb42Bg","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nd=pd.read_csv('data/DGS10.csv').dropna(); d['date']=pd.to_datetime(d.observation_date); d=d.iloc[1:]\nprint(d[d.date<='2009-12-31'].date.max(), d[d.date>='2010-01-01'].date.min())\"; ls -la out/figure1.png","description":"Check period boundaries and figure"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1333,"cache_read_input_tokens":11538,"output_tokens":308,"output_tokens_details":{"thinking_tokens":94},"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":1333},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXriXV7ptz5gUhnNStzN","requestRef":"528dba23-6e1e-44cb-9ef1-b6ab165aefd0","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"474351d5-b4c6-4a16-aef2-2bc5d9540669","timestamp":"2026-10-30T05:19:43.042Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"474351d5-b4c6-4a16-aef2-2bc5d9540669","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_015MFMnEV4bvpyU6KSYb42Bg","type":"tool_result","content":"2009-12-31 00:00:00 2010-01-04 00:00:00\n-rw-r--r--  1 simon-pierreboucher  staff  40700 oct.  30 01:19 out/figure1.png","is_error":false}]},"uuid":"b1b373d8-eb07-486c-8f05-daeb64ae29f2","timestamp":"2026-10-30T05:19:43.352Z","toolUseResult":{"stdout":"2009-12-31 00:00:00 2010-01-04 00:00:00\n-rw-r--r--  1 simon-pierreboucher  staff  40700 oct.  30 01:19 out/figure1.png","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"474351d5-b4c6-4a16-aef2-2bc5d9540669","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"e554437a7b9572b0a9dabc4729488669a2795971294cd6aad7f2f333a83aa5ca","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_015MFMnEV4bvpyU6KSYb42Bg","name":"Bash","input":{"command":"~/wp29/venv/bin/python -c \"\nimport pandas as pd\nd=pd.read_csv('data/DGS10.csv').dropna(); d['date']=pd.to_datetime(d.observation_date); d=d.iloc[1:]\nprint(d[d.date<='2009-12-31'].date.max(), d[d.date>='2010-01-01'].date.min())\"; ls -la out/figure1.png","description":"Check period boundaries and figure"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"4670a5b2-c5a3-440b-93f4-b1ced864f088","timestamp":"2026-10-30T05:19:43.355Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"528dba23-6e1e-44cb-9ef1-b6ab165aefd0","keep":10,"tail":["e554437a7b9572b0a9dabc4729488669a2795971294cd6aad7f2f333a83aa5ca","0971d3ff3b1641c59bac2b696482739aed69b8310f615a65259822ab2d9c1963"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",11,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"c0815e52cafa7eb42deb131d464d47eb4f7624c34c5bd12db4c4deaf8b6e3b0d"}
{"type":"tools-used","tools":["Bash","Read"],"sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":"b1b373d8-eb07-486c-8f05-daeb64ae29f2","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrin4xVqJBcUDgXCtAg","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MnKjU9EVX3C9yWafJN5hud","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0269/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":383,"cache_read_input_tokens":12871,"output_tokens":80,"output_tokens_details":{"thinking_tokens":0},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":383},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXrimo65VawvDUi8n16B","requestRef":"4670a5b2-c5a3-440b-93f4-b1ced864f088","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"bb138c0d-5a6f-4ff5-8ab2-7f3b02626a1e","timestamp":"2026-10-30T05:19:44.642Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"bb138c0d-5a6f-4ff5-8ab2-7f3b02626a1e","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MnKjU9EVX3C9yWafJN5hud","type":"tool_result","content":[{"type":"image","source":{"type":"base64","data":"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","media_type":"image/png"}}]}]},"uuid":"4e85e3f1-7f4a-4cb5-a61d-6d9ad351a7eb","timestamp":"2026-10-30T05:19:44.649Z","toolUseResult":{"type":"image","file":{"base64":"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","type":"image/png","originalSize":40700,"dimensions":{"originalWidth":900,"originalHeight":600,"displayWidth":900,"displayHeight":600}}},"sourceToolAssistantUUID":"bb138c0d-5a6f-4ff5-8ab2-7f3b02626a1e","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"64d5d948bcc0328019daa581f45e6809bd89cff0d4aa2363735b69e59b54dec4","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MnKjU9EVX3C9yWafJN5hud","name":"Read","input":{"file_path":"/Users/simon-pierreboucher/wp29/runs/RC0269/out/figure1.png"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"f08279ab-ed2b-498b-be4e-a54b3ab5b3a9","timestamp":"2026-10-30T05:19:44.653Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"4670a5b2-c5a3-440b-93f4-b1ced864f088","keep":12,"tail":["64d5d948bcc0328019daa581f45e6809bd89cff0d4aa2363735b69e59b54dec4","1965c37bfe23414868c73f659c5982af2ecdb72ad3d7d00c0a2f8a91708c9cb2"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",13,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"2e94ef8167a8c7bfac1d7946b888a6d85013c2248c385d8bc805579af2f4385e"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"4e85e3f1-7f4a-4cb5-a61d-6d9ad351a7eb","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"type":"atis-latch","atis":"","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":"4e85e3f1-7f4a-4cb5-a61d-6d9ad351a7eb","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrisgJxYzWqG8PjsBeB","type":"message","role":"assistant","content":[{"type":"text","text":"Now the state files, report and claims."}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":825,"cache_read_input_tokens":13254,"output_tokens":2426,"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":825},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXrisNx4WJSqc5oruhzQ","requestRef":"f08279ab-ed2b-498b-be4e-a54b3ab5b3a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"7d060502-61ad-46a4-9f3b-10c98bef3111","timestamp":"2026-10-30T05:19:45.994Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"7d060502-61ad-46a4-9f3b-10c98bef3111","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrisgJxYzWqG8PjsBeB","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01PZGoN3UXTmr19oHV8BrPfQ","name":"Bash","input":{"command":"cd out\ncat > state/contract.md <<'EOF'\n# Contract — F6-conf-01\n**Question:** does weekday predict the one-day change in the 10y CMT Treasury yield (DGS10), 2000–2019?\n**Estimands:** (i) equality of the five weekday conditional means of Δy_t (bp), classical one-way ANOVA F-test over all changes; (ii) Monday contrast = mean(Δy | Mon) − mean(Δy | Tue–Fri), with 95% CI (chosen: Welch); (iii) OOS RMSE over changes dated ≥ 2010-01-01 of weekday-mean forecast (means estimated on changes ≤ 2009-12-31) vs zero-change forecast.\nAssumptions: changes roughly independent with finite variance (ANOVA additionally assumes equal variances; large n makes normality unimportant); stationarity of weekday means across the sample for OOS meaning.\n**Information rules:** drop empty DGS10 rows first; Δy between consecutive available obs, dated and weekday-attributed at t; first obs no change; forecast parameters from estimation period only; only data/DGS10.csv.\n**Outputs:** results.json (n_missing_rows, n_train, n_test, anova_f_stat, anova_p_value, effect_estimate, effect_ci_low, effect_ci_high, baseline_metric, model_metric, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), figure1.png, table1.csv, report.md (6 sections), analysis.py, claims.json.\n**Invalidity/impossibility:** missing file/columns, non-weekday dates, leakage of test-period data into forecasts. None found.\nEOF\ncat > state/data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols |\n|---|---|---|---|\n| data/DGS10.csv | 8187f89ab6523b3c964255e1736cfcf0e2ca854ed9e50343e04f4dc2945c5cd7 (matches README) | 5217 | 2 |\n| data/README.md | 32b825f02387ef3d552df6def82c585d7f248980667a28f30e58506e472e561a | provenance text | – |\n\n- Schema: observation_date (YYYY-MM-DD string), DGS10 (float, percent).\n- Date range 2000-01-03 … 2019-12-31, strictly increasing, no duplicate dates, weekdays only (Mon 1044, Tue 1044, Wed 1043, Thu 1043, Fri 1043).\n- Missing DGS10: 215 rows (holidays); no non-numeric non-empty values. Available obs 5002 → 5001 changes.\n- Values 1.37–6.79 %, plausible; no anomalies.\n- 214 changes span a holiday (calendar gap longer than normal); kept per TASK rule, flagged as a limitation.\n- No information-availability violations in inputs; leakage risk only in forecasting step — handled by estimating weekday means on dates ≤ 2009-12-31 (last train date 2009-12-31, first test date 2010-01-04).\nEOF\ncat > state/checks.md <<'EOF'\n# Verification checks (P4)\n1. Clean re-run: deleted results.json/table1.csv/figure1.png, ran analysis.py twice; SHA-256 of results.json and table1.csv identical — PASS.\n2. n_train + n_test = n_analysed (2500 + 2501 = 5001) — PASS.\n3. n_input_rows − n_missing_rows − 1 = n_analysed (5217 − 215 − 1 = 5001); exclusions.csv adds up — PASS.\n4. table1 n sums to 5001; all se_bp > 0 — PASS.\n5. ANOVA cross-check with statsmodels OLS anova_lm: F = 0.26347, p = 0.90151, df (4, 4996) — identical — PASS.\n6. Monday contrast cross-check: OLS on Monday dummy with HC1 SE gives 0.0502 bp, CI [−0.319, 0.419], ≈ Welch CI [−0.319, 0.420] — PASS.\n7. CI contains estimate; conclusion code consistent with ANOVA p = 0.90 ≥ 0.05 → no_detectable_effect — PASS.\n8. Date ordering: max train date 2009-12-31 < min test date 2010-01-04; weekday means use train only — PASS.\n9. Magnitudes: weekday means (|mean| < 0.25 bp) tiny relative to daily SD (~5.5 bp); model RMSE 4.884 vs baseline 4.876 bp, consistent with no signal — PASS.\n10. Figure inspected visually: 5 points with 95% bars, all overlapping zero — PASS.\nEOF\ncat > state/log.md <<'EOF'\n# Log\n- 2026-10-30 P0: read TASK.md, wrote contract. passed.\n- 2026-10-30 P1: audited data (hash matches README), exclusions ledger written by analysis.py. passed.\n- 2026-10-30 P2: baseline = zero-change RMSE on evaluation period (baseline_metric). passed.\n- 2026-10-30 P3: analysis.py written; decision: Welch interval for Monday contrast; no randomness (seed null). Fixed holiday-gap counter definition (was missing mid-week holidays). passed.\n- 2026-10-30 P4: clean double rerun identical; checks.md written. passed.\n- 2026-10-30 P5: report.md and claims.json written. passed.\nEOF\ncat > state/phases.json <<'EOF'\n{\n \"P0\": {\"status\": \"passed\", \"checks\": [\"TASK.md read fully\", \"contract.md written\"], \"notes\": \"\"},\n \"P1\": {\"status\": \"passed\", \"checks\": [\"SHA-256 matches README\", \"schema/dates/duplicates/missing audited\", \"exclusions.csv sums: 5217-215-1=5001\"], \"notes\": \"\"},\n \"P2\": {\"status\": \"passed\", \"checks\": [\"baseline_metric (zero-change RMSE, eval period) computed = 4.8757 bp\"], \"notes\": \"\"},\n \"P3\": {\"status\": \"passed\", \"checks\": [\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png\", \"no RNG used\"], \"notes\": \"\"},\n \"P4\": {\"status\": \"passed\", \"checks\": [\"clean rerun twice: identical hashes\", \"count identities\", \"statsmodels ANOVA cross-check\", \"HC1 cross-check of contrast\", \"date ordering\", \"figure inspected\"], \"notes\": \"see checks.md\"},\n \"P5\": {\"status\": \"passed\", \"checks\": [\"report.md six sections with key citations\", \"claims.json keys exist in results.json\"], \"notes\": \"\"}\n}\nEOF","description":"Write state files"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":825,"cache_read_input_tokens":13254,"output_tokens":2426,"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":825},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXrisNx4WJSqc5oruhzQ","requestRef":"f08279ab-ed2b-498b-be4e-a54b3ab5b3a9","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"942ba47d-b212-459f-8ed8-5bb49a8fc78c","timestamp":"2026-10-30T05:20:06.033Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"942ba47d-b212-459f-8ed8-5bb49a8fc78c","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01PZGoN3UXTmr19oHV8BrPfQ","type":"tool_result","content":"(Bash completed with no output)","is_error":false}]},"uuid":"058cdf38-2c6d-4fca-a1a0-d96809370014","timestamp":"2026-10-30T05:20:06.085Z","toolUseResult":{"stdout":"","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"942ba47d-b212-459f-8ed8-5bb49a8fc78c","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269/out","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"e2e1de696462ef6d8df495c08ab228e5d57275f2e3dde61f4f62d2acd5733726","message":{"role":"assistant","content":[{"type":"text","text":"Now the state files, report and claims."},{"type":"tool_use","id":"toolu_01PZGoN3UXTmr19oHV8BrPfQ","name":"Bash","input":{"command":"cd out\ncat > state/contract.md <<'EOF'\n# Contract — F6-conf-01\n**Question:** does weekday predict the one-day change in the 10y CMT Treasury yield (DGS10), 2000–2019?\n**Estimands:** (i) equality of the five weekday conditional means of Δy_t (bp), classical one-way ANOVA F-test over all changes; (ii) Monday contrast = mean(Δy | Mon) − mean(Δy | Tue–Fri), with 95% CI (chosen: Welch); (iii) OOS RMSE over changes dated ≥ 2010-01-01 of weekday-mean forecast (means estimated on changes ≤ 2009-12-31) vs zero-change forecast.\nAssumptions: changes roughly independent with finite variance (ANOVA additionally assumes equal variances; large n makes normality unimportant); stationarity of weekday means across the sample for OOS meaning.\n**Information rules:** drop empty DGS10 rows first; Δy between consecutive available obs, dated and weekday-attributed at t; first obs no change; forecast parameters from estimation period only; only data/DGS10.csv.\n**Outputs:** results.json (n_missing_rows, n_train, n_test, anova_f_stat, anova_p_value, effect_estimate, effect_ci_low, effect_ci_high, baseline_metric, model_metric, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), figure1.png, table1.csv, report.md (6 sections), analysis.py, claims.json.\n**Invalidity/impossibility:** missing file/columns, non-weekday dates, leakage of test-period data into forecasts. None found.\nEOF\ncat > state/data_audit.md <<'EOF'\n# Data audit\n| file | SHA-256 | rows (excl. header) | cols |\n|---|---|---|---|\n| data/DGS10.csv | 8187f89ab6523b3c964255e1736cfcf0e2ca854ed9e50343e04f4dc2945c5cd7 (matches README) | 5217 | 2 |\n| data/README.md | 32b825f02387ef3d552df6def82c585d7f248980667a28f30e58506e472e561a | provenance text | – |\n\n- Schema: observation_date (YYYY-MM-DD string), DGS10 (float, percent).\n- Date range 2000-01-03 … 2019-12-31, strictly increasing, no duplicate dates, weekdays only (Mon 1044, Tue 1044, Wed 1043, Thu 1043, Fri 1043).\n- Missing DGS10: 215 rows (holidays); no non-numeric non-empty values. Available obs 5002 → 5001 changes.\n- Values 1.37–6.79 %, plausible; no anomalies.\n- 214 changes span a holiday (calendar gap longer than normal); kept per TASK rule, flagged as a limitation.\n- No information-availability violations in inputs; leakage risk only in forecasting step — handled by estimating weekday means on dates ≤ 2009-12-31 (last train date 2009-12-31, first test date 2010-01-04).\nEOF\ncat > state/checks.md <<'EOF'\n# Verification checks (P4)\n1. Clean re-run: deleted results.json/table1.csv/figure1.png, ran analysis.py twice; SHA-256 of results.json and table1.csv identical — PASS.\n2. n_train + n_test = n_analysed (2500 + 2501 = 5001) — PASS.\n3. n_input_rows − n_missing_rows − 1 = n_analysed (5217 − 215 − 1 = 5001); exclusions.csv adds up — PASS.\n4. table1 n sums to 5001; all se_bp > 0 — PASS.\n5. ANOVA cross-check with statsmodels OLS anova_lm: F = 0.26347, p = 0.90151, df (4, 4996) — identical — PASS.\n6. Monday contrast cross-check: OLS on Monday dummy with HC1 SE gives 0.0502 bp, CI [−0.319, 0.419], ≈ Welch CI [−0.319, 0.420] — PASS.\n7. CI contains estimate; conclusion code consistent with ANOVA p = 0.90 ≥ 0.05 → no_detectable_effect — PASS.\n8. Date ordering: max train date 2009-12-31 < min test date 2010-01-04; weekday means use train only — PASS.\n9. Magnitudes: weekday means (|mean| < 0.25 bp) tiny relative to daily SD (~5.5 bp); model RMSE 4.884 vs baseline 4.876 bp, consistent with no signal — PASS.\n10. Figure inspected visually: 5 points with 95% bars, all overlapping zero — PASS.\nEOF\ncat > state/log.md <<'EOF'\n# Log\n- 2026-10-30 P0: read TASK.md, wrote contract. passed.\n- 2026-10-30 P1: audited data (hash matches README), exclusions ledger written by analysis.py. passed.\n- 2026-10-30 P2: baseline = zero-change RMSE on evaluation period (baseline_metric). passed.\n- 2026-10-30 P3: analysis.py written; decision: Welch interval for Monday contrast; no randomness (seed null). Fixed holiday-gap counter definition (was missing mid-week holidays). passed.\n- 2026-10-30 P4: clean double rerun identical; checks.md written. passed.\n- 2026-10-30 P5: report.md and claims.json written. passed.\nEOF\ncat > state/phases.json <<'EOF'\n{\n \"P0\": {\"status\": \"passed\", \"checks\": [\"TASK.md read fully\", \"contract.md written\"], \"notes\": \"\"},\n \"P1\": {\"status\": \"passed\", \"checks\": [\"SHA-256 matches README\", \"schema/dates/duplicates/missing audited\", \"exclusions.csv sums: 5217-215-1=5001\"], \"notes\": \"\"},\n \"P2\": {\"status\": \"passed\", \"checks\": [\"baseline_metric (zero-change RMSE, eval period) computed = 4.8757 bp\"], \"notes\": \"\"},\n \"P3\": {\"status\": \"passed\", \"checks\": [\"analysis.py reads only data/, writes results.json, table1.csv, figure1.png\", \"no RNG used\"], \"notes\": \"\"},\n \"P4\": {\"status\": \"passed\", \"checks\": [\"clean rerun twice: identical hashes\", \"count identities\", \"statsmodels ANOVA cross-check\", \"HC1 cross-check of contrast\", \"date ordering\", \"figure inspected\"], \"notes\": \"see checks.md\"},\n \"P5\": {\"status\": \"passed\", \"checks\": [\"report.md six sections with key citations\", \"claims.json keys exist in results.json\"], \"notes\": \"\"}\n}\nEOF","description":"Write state files"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"ea3e4937-a6cc-4676-b0ae-c7da4d6528b4","timestamp":"2026-10-30T05:20:06.089Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"f08279ab-ed2b-498b-be4e-a54b3ab5b3a9","keep":14,"tail":["e2e1de696462ef6d8df495c08ab228e5d57275f2e3dde61f4f62d2acd5733726","c9c349d24a792fcc528ef7f135e70745af844bf0d872960b09c1e2f5b2ca1065"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",15,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"f925ebedb6622bc7dea7696d3df8a60d479fc9c6990619cf891307ea3e49c9c3"}
{"parentUuid":"058cdf38-2c6d-4fca-a1a0-d96809370014","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrkTJuGpqgYdSYUkwSG","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01MehqgdtWSJWLCKp53JEaCX","name":"Bash","input":{"command":"cd out\ncat > report.md <<'EOF'\n# F6-conf-01 — Weekday effects in daily changes of the 10-year Treasury yield\n\n## Question\nDoes the day of the week help predict the one-day change in the 10-year US Treasury constant-maturity yield (FRED DGS10), 2000–2019? I estimate three things: (i) a joint test that the five weekday means are equal, (ii) the Monday contrast (Monday mean minus the mean of the other four weekdays), and (iii) how well weekday-specific means forecast out of sample, compared with a zero-change (random-walk) forecast.\n\n## Data and exclusions\n- Input: `data/DGS10.csv`, 5217 rows (`n_input_rows`). Its SHA-256 matches `data/README.md`. Every row is a weekday and there are no duplicate dates.\n- 215 rows have an empty DGS10 field (US holidays) and were dropped (`n_missing_rows`). The first available observation has no change. That leaves 5001 daily changes (`n_analysed`): 2500 in the estimation period (≤ 2009-12-31, `n_train`) and 2501 in the evaluation period (≥ 2010-01-01, `n_test`). The ledger is in `out/exclusions.csv`.\n- Changes are computed between consecutive *available* observations, so 214 changes span a holiday (`supplementary.n_changes_spanning_holiday_gap`), for example a Tuesday that follows a Monday holiday. As the task requires, these were kept and assigned to the weekday of t (`data_issues`).\n\n## Method\n- Δy_t = 100·(y_t − y_{t−1}), in basis points.\n- (i) Classical equal-variance one-way ANOVA across the five weekdays, all changes, F(4, 4996). I checked it against an OLS ANOVA in statsmodels.\n- (ii) Monday contrast with a 95% interval from a **Welch** two-sample t interval (unequal variances; Welch df ≈ 1549, `supplementary.effect_welch_df`). As a cross-check, an OLS regression on a Monday dummy with HC1-robust SE gave essentially the same interval.\n- (iii) Weekday means were estimated on the estimation period only (`supplementary.train_weekday_means_bp`) and used to forecast each evaluation-period change. RMSE was compared with the zero-change forecast. As a supplementary test I added a Diebold–Mariano test on squared loss.\n- Conclusion rule: if ANOVA p ≥ 0.05, the code is `no_detectable_effect`; otherwise the sign of the Monday-contrast interval decides. The analysis is deterministic and uses no random numbers (`random_seed` = null). Outputs: `out/table1.csv` (weekday n, mean, SE) and `out/figure1.png` (weekday means with 95% CIs).\n\n## Results\n- Joint test: F = 0.263 (`anova_f_stat`), p = 0.902 (`anova_p_value`). Equal weekday means are not rejected.\n- Monday contrast: +0.050 bp (`effect_estimate`), 95% CI [−0.319, 0.420] bp (`effect_ci_low`, `effect_ci_high`). Welch p = 0.79 (`supplementary.effect_welch_p_value`).\n- Out of sample: the zero-change RMSE is 4.876 bp (`baseline_metric`) and the weekday-mean RMSE is 4.884 bp (`model_metric`), a ratio of 1.0017 (`supplementary.rmse_ratio_model_over_baseline`). The weekday model is slightly *worse*. The DM statistic is −1.86, p = 0.063 (`supplementary.dm_stat_sqloss_positive_favours_weekday`, `supplementary.dm_p_value`), so it is not significantly worse at the 5% level.\n- The estimation-period weekday ranking does not carry over: Tuesday was the most negative weekday in 2000–2009 and Friday the most positive (`supplementary.train_weekday_means_bp`). In `table1.csv`, all-sample weekday means range from −0.22 to +0.02 bp with SEs of about 0.16–0.19 bp.\n- **Conclusion: `no_detectable_effect`** (`conclusion`).\n\n## Uncertainty\n- The Monday-contrast CI is about ±0.37 bp wide. A typical daily change has an SD of roughly 5 bp, so this rules out Monday effects larger than about 0.4 bp per day in either direction. Effects smaller than that cannot be excluded.\n- The ANOVA p-value assumes independent, equal-variance errors. Daily yield changes show volatility clustering and some heteroskedasticity across weekdays. With n ≈ 1000 per group, the F-test's size is roughly robust to this, and the robust (HC1) contrast agrees with Welch.\n- The OOS RMSE difference (0.008 bp) is tiny next to its sampling noise. The DM test does not reject equal accuracy.\n\n## Limitations and open issues\n- **What would invalidate the result:** errors in the source series (I did not check the H.15 releases independently); serial dependence strong enough to distort the F and t reference distributions (I did not test for this or use HAC errors); or a different definition of \"change\". For example, dropping or separately labelling the 214 holiday-spanning changes, or using calendar-day-normalised changes, could shift weekday means a little. I did not run those sensitivity analyses.\n- **Not checked:** ARCH or GARCH-adjusted tests; rank-based tests (Kruskal–Wallis); sub-period stability apart from the 2000–2009 vs 2010–2019 split; interactions with macro-release calendars. Many US data releases fall on Fridays (employment report) and Thursdays, so weekday is confounded with news days. Any weekday effect would be a news-calendar effect rather than a pure day effect.\n- **Main threats:** (a) Low power for very small effects: a \"no detectable effect\" result does not show that the effect is zero, only that it is below about 0.4 bp. (b) Non-stationarity: 2000–2019 includes the 2008 crisis, the ZLB, and QE, and volatility regimes differ between periods. (c) Multiple testing across folklore patterns: I tested only the Monday contrast as pre-specified, so a post-hoc search for a \"Tuesday effect\" would be data-mined. (d) The weekday-mean forecaster has 5 noisy parameters, and estimation error alone makes it worse than the zero forecast when the true effect is near zero, which matches what we see.\n- The task was fully feasible (`feasibility` = complete).\nEOF\ncat > claims.json <<'EOF'\n[\n {\"id\": \"C1\", \"text\": \"The joint ANOVA test does not reject equal mean daily DGS10 changes across weekdays (F=0.263, p=0.902).\", \"results_keys\": [\"anova_f_stat\", \"anova_p_value\", \"n_analysed\"], \"status\": \"supported\", \"caveat\": \"Classical equal-variance F-test; volatility clustering not modelled.\"},\n {\"id\": \"C2\", \"text\": \"The Monday contrast is +0.050 bp with 95% Welch CI [-0.319, 0.420] bp, i.e. not distinguishable from zero.\", \"results_keys\": [\"effect_estimate\", \"effect_ci_low\", \"effect_ci_high\"], \"status\": \"supported\", \"caveat\": \"Excludes only effects larger than about 0.4 bp/day; HAC errors not used.\"},\n {\"id\": \"C3\", \"text\": \"Weekday-specific means estimated on 2000-2009 do not improve out-of-sample forecasts for 2010-2019: RMSE 4.884 bp vs 4.876 bp for the zero-change forecast.\", \"results_keys\": [\"model_metric\", \"baseline_metric\", \"n_train\", \"n_test\"], \"status\": \"supported\", \"caveat\": \"Difference not significant by a Diebold-Mariano test (p=0.063, supplementary.dm_p_value).\"},\n {\"id\": \"C4\", \"text\": \"Overall conclusion: no detectable weekday effect.\", \"results_keys\": [\"conclusion\", \"anova_p_value\"], \"status\": \"supported\", \"caveat\": \"Absence of evidence within the stated power, not proof of zero effect.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('results.json'));c=json.load(open('claims.json'))\nprint(all(k in r for x in c for k in x['results_keys']))\"; grep '^## ' report.md","description":"Write report and claims, validate keys"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":2441,"cache_read_input_tokens":14079,"output_tokens":2974,"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":2441},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXrkT2HMMJMAx2cRV6B5","requestRef":"ea3e4937-a6cc-4676-b0ae-c7da4d6528b4","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"8b65cb41-9a26-463b-9c89-53ce1f7560d5","timestamp":"2026-10-30T05:20:33.509Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269/out","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"8b65cb41-9a26-463b-9c89-53ce1f7560d5","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01MehqgdtWSJWLCKp53JEaCX","type":"tool_result","content":"(eval):cd:1: no such file or directory: out\nTrue\n## Question\n## Data and exclusions\n## Method\n## Results\n## Uncertainty\n## Limitations and open issues","is_error":false}]},"uuid":"897cb217-0a46-4a6a-8675-fd6aac9ebfc3","timestamp":"2026-10-30T05:20:33.591Z","toolUseResult":{"stdout":"(eval):cd:1: no such file or directory: out\nTrue\n## Question\n## Data and exclusions\n## Method\n## Results\n## Uncertainty\n## Limitations and open issues","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"8b65cb41-9a26-463b-9c89-53ce1f7560d5","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269/out","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"13daa19e47cf4d6a57a52199455ceb1d1e2ba98b1441f5ef0c0eab0bf234e0f8","message":{"role":"assistant","content":[{"type":"tool_use","id":"toolu_01MehqgdtWSJWLCKp53JEaCX","name":"Bash","input":{"command":"cd out\ncat > report.md <<'EOF'\n# F6-conf-01 — Weekday effects in daily changes of the 10-year Treasury yield\n\n## Question\nDoes the day of the week help predict the one-day change in the 10-year US Treasury constant-maturity yield (FRED DGS10), 2000–2019? I estimate three things: (i) a joint test that the five weekday means are equal, (ii) the Monday contrast (Monday mean minus the mean of the other four weekdays), and (iii) how well weekday-specific means forecast out of sample, compared with a zero-change (random-walk) forecast.\n\n## Data and exclusions\n- Input: `data/DGS10.csv`, 5217 rows (`n_input_rows`). Its SHA-256 matches `data/README.md`. Every row is a weekday and there are no duplicate dates.\n- 215 rows have an empty DGS10 field (US holidays) and were dropped (`n_missing_rows`). The first available observation has no change. That leaves 5001 daily changes (`n_analysed`): 2500 in the estimation period (≤ 2009-12-31, `n_train`) and 2501 in the evaluation period (≥ 2010-01-01, `n_test`). The ledger is in `out/exclusions.csv`.\n- Changes are computed between consecutive *available* observations, so 214 changes span a holiday (`supplementary.n_changes_spanning_holiday_gap`), for example a Tuesday that follows a Monday holiday. As the task requires, these were kept and assigned to the weekday of t (`data_issues`).\n\n## Method\n- Δy_t = 100·(y_t − y_{t−1}), in basis points.\n- (i) Classical equal-variance one-way ANOVA across the five weekdays, all changes, F(4, 4996). I checked it against an OLS ANOVA in statsmodels.\n- (ii) Monday contrast with a 95% interval from a **Welch** two-sample t interval (unequal variances; Welch df ≈ 1549, `supplementary.effect_welch_df`). As a cross-check, an OLS regression on a Monday dummy with HC1-robust SE gave essentially the same interval.\n- (iii) Weekday means were estimated on the estimation period only (`supplementary.train_weekday_means_bp`) and used to forecast each evaluation-period change. RMSE was compared with the zero-change forecast. As a supplementary test I added a Diebold–Mariano test on squared loss.\n- Conclusion rule: if ANOVA p ≥ 0.05, the code is `no_detectable_effect`; otherwise the sign of the Monday-contrast interval decides. The analysis is deterministic and uses no random numbers (`random_seed` = null). Outputs: `out/table1.csv` (weekday n, mean, SE) and `out/figure1.png` (weekday means with 95% CIs).\n\n## Results\n- Joint test: F = 0.263 (`anova_f_stat`), p = 0.902 (`anova_p_value`). Equal weekday means are not rejected.\n- Monday contrast: +0.050 bp (`effect_estimate`), 95% CI [−0.319, 0.420] bp (`effect_ci_low`, `effect_ci_high`). Welch p = 0.79 (`supplementary.effect_welch_p_value`).\n- Out of sample: the zero-change RMSE is 4.876 bp (`baseline_metric`) and the weekday-mean RMSE is 4.884 bp (`model_metric`), a ratio of 1.0017 (`supplementary.rmse_ratio_model_over_baseline`). The weekday model is slightly *worse*. The DM statistic is −1.86, p = 0.063 (`supplementary.dm_stat_sqloss_positive_favours_weekday`, `supplementary.dm_p_value`), so it is not significantly worse at the 5% level.\n- The estimation-period weekday ranking does not carry over: Tuesday was the most negative weekday in 2000–2009 and Friday the most positive (`supplementary.train_weekday_means_bp`). In `table1.csv`, all-sample weekday means range from −0.22 to +0.02 bp with SEs of about 0.16–0.19 bp.\n- **Conclusion: `no_detectable_effect`** (`conclusion`).\n\n## Uncertainty\n- The Monday-contrast CI is about ±0.37 bp wide. A typical daily change has an SD of roughly 5 bp, so this rules out Monday effects larger than about 0.4 bp per day in either direction. Effects smaller than that cannot be excluded.\n- The ANOVA p-value assumes independent, equal-variance errors. Daily yield changes show volatility clustering and some heteroskedasticity across weekdays. With n ≈ 1000 per group, the F-test's size is roughly robust to this, and the robust (HC1) contrast agrees with Welch.\n- The OOS RMSE difference (0.008 bp) is tiny next to its sampling noise. The DM test does not reject equal accuracy.\n\n## Limitations and open issues\n- **What would invalidate the result:** errors in the source series (I did not check the H.15 releases independently); serial dependence strong enough to distort the F and t reference distributions (I did not test for this or use HAC errors); or a different definition of \"change\". For example, dropping or separately labelling the 214 holiday-spanning changes, or using calendar-day-normalised changes, could shift weekday means a little. I did not run those sensitivity analyses.\n- **Not checked:** ARCH or GARCH-adjusted tests; rank-based tests (Kruskal–Wallis); sub-period stability apart from the 2000–2009 vs 2010–2019 split; interactions with macro-release calendars. Many US data releases fall on Fridays (employment report) and Thursdays, so weekday is confounded with news days. Any weekday effect would be a news-calendar effect rather than a pure day effect.\n- **Main threats:** (a) Low power for very small effects: a \"no detectable effect\" result does not show that the effect is zero, only that it is below about 0.4 bp. (b) Non-stationarity: 2000–2019 includes the 2008 crisis, the ZLB, and QE, and volatility regimes differ between periods. (c) Multiple testing across folklore patterns: I tested only the Monday contrast as pre-specified, so a post-hoc search for a \"Tuesday effect\" would be data-mined. (d) The weekday-mean forecaster has 5 noisy parameters, and estimation error alone makes it worse than the zero forecast when the true effect is near zero, which matches what we see.\n- The task was fully feasible (`feasibility` = complete).\nEOF\ncat > claims.json <<'EOF'\n[\n {\"id\": \"C1\", \"text\": \"The joint ANOVA test does not reject equal mean daily DGS10 changes across weekdays (F=0.263, p=0.902).\", \"results_keys\": [\"anova_f_stat\", \"anova_p_value\", \"n_analysed\"], \"status\": \"supported\", \"caveat\": \"Classical equal-variance F-test; volatility clustering not modelled.\"},\n {\"id\": \"C2\", \"text\": \"The Monday contrast is +0.050 bp with 95% Welch CI [-0.319, 0.420] bp, i.e. not distinguishable from zero.\", \"results_keys\": [\"effect_estimate\", \"effect_ci_low\", \"effect_ci_high\"], \"status\": \"supported\", \"caveat\": \"Excludes only effects larger than about 0.4 bp/day; HAC errors not used.\"},\n {\"id\": \"C3\", \"text\": \"Weekday-specific means estimated on 2000-2009 do not improve out-of-sample forecasts for 2010-2019: RMSE 4.884 bp vs 4.876 bp for the zero-change forecast.\", \"results_keys\": [\"model_metric\", \"baseline_metric\", \"n_train\", \"n_test\"], \"status\": \"supported\", \"caveat\": \"Difference not significant by a Diebold-Mariano test (p=0.063, supplementary.dm_p_value).\"},\n {\"id\": \"C4\", \"text\": \"Overall conclusion: no detectable weekday effect.\", \"results_keys\": [\"conclusion\", \"anova_p_value\"], \"status\": \"supported\", \"caveat\": \"Absence of evidence within the stated power, not proof of zero effect.\"}\n]\nEOF\n~/wp29/venv/bin/python -c \"\nimport json;r=json.load(open('results.json'));c=json.load(open('claims.json'))\nprint(all(k in r for x in c for k in x['results_keys']))\"; grep '^## ' report.md","description":"Write report and claims, validate keys"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"00eb7982-8aeb-4360-a7fd-39e3bd5b0326","timestamp":"2026-10-30T05:20:33.595Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"ea3e4937-a6cc-4676-b0ae-c7da4d6528b4","keep":16,"tail":["13daa19e47cf4d6a57a52199455ceb1d1e2ba98b1441f5ef0c0eab0bf234e0f8","33b106dcc384cd56154a24d38a8c37aa66d1348e82e55a879c672835c7c91df9"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",17,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"6687a7777e2808919a67a4e9b5d207f207bd7c323479ca231ed7fe4d150e470c"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"897cb217-0a46-4a6a-8675-fd6aac9ebfc3","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"type":"atis-latch","atis":"","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"parentUuid":"897cb217-0a46-4a6a-8675-fd6aac9ebfc3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrnUxB5igVmoDUd6Wce","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":3037,"cache_read_input_tokens":16520,"output_tokens":155,"output_tokens_details":{"thinking_tokens":43},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3037},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"thinkingDurationMs":408,"thinkingDisplay":"updates","apiBlockIndex":0,"requestId":"req_011CgXrnUdq4w1Kp9gj62uRp","requestRef":"00eb7982-8aeb-4360-a7fd-39e3bd5b0326","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"c1199bfb-bdcf-486a-b05b-510f670a59e3","timestamp":"2026-10-30T05:20:35.401Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269/out","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"c1199bfb-bdcf-486a-b05b-510f670a59e3","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrnUxB5igVmoDUd6Wce","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Vtv7NywP2ixs6zU6kCXt3t","name":"Bash","input":{"command":"pwd; cd /Users/simon-pierreboucher/wp29/runs/RC0269 && ls out out/state","description":"Verify file locations"},"caller":{"type":"direct"}}],"container":null,"stop_reason":"tool_use","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3037,"cache_read_input_tokens":16520,"output_tokens":155,"output_tokens_details":{"thinking_tokens":43},"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":3037},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":1,"requestId":"req_011CgXrnUdq4w1Kp9gj62uRp","requestRef":"00eb7982-8aeb-4360-a7fd-39e3bd5b0326","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"9b157eaf-31db-40d2-93bb-6951303db749","timestamp":"2026-10-30T05:20:35.909Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269/out","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"parentUuid":"9b157eaf-31db-40d2-93bb-6951303db749","isSidechain":false,"promptId":"1674fe92-8430-40ad-91bb-4fdfe7cb3174","type":"user","message":{"role":"user","content":[{"tool_use_id":"toolu_01Vtv7NywP2ixs6zU6kCXt3t","type":"tool_result","content":"/Users/simon-pierreboucher/wp29/runs/RC0269/out\nout:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json","is_error":false}]},"uuid":"b7f436de-343b-4b8e-b325-b7776d358e09","timestamp":"2026-10-30T05:20:35.949Z","toolUseResult":{"stdout":"/Users/simon-pierreboucher/wp29/runs/RC0269/out\nout:\nanalysis.py\nclaims.json\nexclusions.csv\nfigure1.png\nreport.md\nresults.json\nstate\ntable1.csv\n\nout/state:\nchecks.md\ncontract.md\ndata_audit.md\nlog.md\nphases.json","stderr":"","interrupted":false,"isImage":false,"noOutputExpected":false},"sandboxed":false,"sourceToolAssistantUUID":"9b157eaf-31db-40d2-93bb-6951303db749","permissionDecision":{"decision":"accept","source":"config","reasonType":"rule","ruleSource":"cliArg"},"userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"api-request-blob","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","hash":"4000d669cc2e4cadf4e25b22e4936cd6fe26879ac05d17bc6c6b88d52027553f","message":{"role":"assistant","content":[{"type":"thinking","thinking":"","signature":"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"},{"type":"tool_use","id":"toolu_01Vtv7NywP2ixs6zU6kCXt3t","name":"Bash","input":{"command":"pwd; cd /Users/simon-pierreboucher/wp29/runs/RC0269 && ls out out/state","description":"Verify file locations"}}]}}
{"type":"api-request","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","id":"96717a33-0e0d-421d-8f32-d7a98a08b7fb","timestamp":"2026-10-30T05:20:35.952Z","version":"2.1.314","querySource":"sdk","shapeHash":"314ffbb4fc24aa19099394e8931de42b9b51635053d810cbf32b5713ac99d63c","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":"00eb7982-8aeb-4360-a7fd-39e3bd5b0326","keep":18,"tail":["4000d669cc2e4cadf4e25b22e4936cd6fe26879ac05d17bc6c6b88d52027553f","115059cf790fb74771aa3653be241836c8944c665fc9bf686ca85a2e80b8db43"],"cacheControl":[{"path":["system",0],"value":{"type":"ephemeral"}},{"path":["system",1],"value":{"type":"ephemeral"}},{"path":["messages",19,"content",0],"value":{"type":"ephemeral"}}],"requestDigest":"93d1c9452e10a41168523a97f057385cce8110d59bcc24e1a2bdc5b2b8fc70b4"}
{"parentUuid":"b7f436de-343b-4b8e-b325-b7776d358e09","isSidechain":false,"message":{"model":"claude-opus-5-5","id":"msg_011CgXrnf39SbDMMP3CPWtN4","type":"message","role":"assistant","content":[{"type":"text","text":"I found no evidence that the day of the week predicts daily changes in the 10-year Treasury yield (2000–2019). The conclusion code is `no_detectable_effect`, and all six protocol phases passed their recorded checks.\n\n| Estimand | Result |\n|---|---|\n| Joint test of equal weekday means (ANOVA) | F = 0.263, p = 0.902, on 5,001 daily changes |\n| Monday contrast (Monday mean minus other weekdays) | +0.050 bp, 95% interval [−0.319, +0.420] bp |\n| Out-of-sample error, 2010–2019 | weekday-mean forecast 4.884 bp vs zero-change forecast 4.876 bp |\n\n- **Data:** the file has 5,217 rows. I dropped 215 holiday rows with no yield, and the first observation has no change, which leaves 5,001 changes. That is 2,500 in the estimation period (to 2009-12-31) and 2,501 in the evaluation period (from 2010-01-01). The file's checksum matches the one in `data/README.md`.\n- **Monday interval:** I used a Welch two-sample interval. A regression on a Monday indicator with robust standard errors gives essentially the same interval. The ANOVA figures also match a second implementation exactly.\n- **Out-of-sample:** the weekday forecast uses only 2000–2009 weekday means and is very slightly worse than predicting no change. A supplementary Diebold–Mariano test finds the difference is not significant (p = 0.063).\n- **Reproducibility:** running `out/analysis.py` twice from a clean state gave identical `results.json` and `table1.csv`. No random numbers are used, so the seed is null.\n\nLimitations:\n- **Small effects not ruled out:** the interval excludes Monday effects larger than about 0.4 bp per day. It cannot exclude smaller ones.\n- **Holiday-spanning changes:** 214 changes cover a holiday, for example a Tuesday after a Monday holiday. As the task requires, I kept them and assigned them to the weekday of the later date.\n- **Not checked:**\n  - tests that allow for volatility clustering or serial dependence;\n  - rank-based tests;\n  - sensitivity to how holiday-spanning changes are handled.\n- **Confounding:** weekday overlaps with the macro-data release calendar, such as the Friday employment report. Any weekday pattern would really reflect news days.\n\nAll deliverables are in `out/`; open `report.md` first. Alongside it are `results.json`, `analysis.py`, `figure1.png`, `table1.csv`, `claims.json` and `exclusions.csv`. The working notes and check records are in `out/state/`."}],"container":null,"stop_reason":"end_turn","stop_sequence":null,"stop_details":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":262,"cache_read_input_tokens":19557,"output_tokens":905,"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":262},"inference_geo":"global","iterations":[],"speed":"standard","fallback_credit":null},"input_transformations":[],"diagnostics":null,"context_management":null},"apiBlockIndex":0,"requestId":"req_011CgXrnejJEs8jE42Xy1Mkc","requestRef":"96717a33-0e0d-421d-8f32-d7a98a08b7fb","requestedModel":"claude-opus-5-5","type":"assistant","uuid":"102d08ab-fee0-4f9f-98d6-8387df1fc0ef","timestamp":"2026-10-30T05:20:44.908Z","effort":"medium","perTurnEffort":"medium","userType":"external","entrypoint":"sdk-cli","cwd":"/Users/simon-pierreboucher/wp29/runs/RC0269","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","version":"2.1.314","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"Begin","leafUuid":"102d08ab-fee0-4f9f-98d6-8387df1fc0ef","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d"}
{"type":"cost-state","sessionId":"9426d945-da92-4270-a3fb-5afaf8abd67d","totalCostUSD":0.3477208,"totalAPIDuration":105208,"totalAPIDurationWithoutRetries":105203,"totalToolDuration":4650,"totalLinesAdded":0,"totalLinesRemoved":0,"totalDuration":110042,"startTime":1793337534873,"modelUsage":{"claude-opus-5-5":{"inputTokens":22,"outputTokens":11734,"thinkingTokens":423,"cacheReadInputTokens":106889,"cacheCreationInputTokens":18315,"cacheCreationEphemeral5mInputTokens":18315,"cacheCreationEphemeral1hInputTokens":0,"webSearchRequests":0,"costUSD":0.3477208}},"hasUnknownModelCost":false}