# Contract — F6-conf-02
**Question:** What happened to the GoC 5-year benchmark yield after the BoC's 2020-03-04 emergency 50bp cut?
**Estimand:** mean one-day change (bp, 100·(y_t − y_{t−1}) between consecutive rows) on rows with post_cut=1, minus mean one-day change on the 120 trading days immediately preceding the first post_cut=1 row; 95% Welch (unequal-variance) interval. Meaningful only if both windows exist in the file; it is a descriptive before/after contrast, causal only under the strong assumption that nothing else (notably the COVID shock itself) shifted yield changes at the same time.
**Outputs:** out/results.json (sample_start, sample_end, n_treated, baseline_metric, model_metric, effect_estimate, effect_ci_low, effect_ci_high, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed); out/figure1.png; out/table1.csv (year,n_days,mean_yield,mean_change_bp); out/report.md (6 sections); out/analysis.py; out/claims.json.
**Information rules:** only data/gc5y_daily.csv; post_cut used as given; changes between consecutive rows; audit before estimating.
**Invalidity / impossibility:** no post_cut=1 rows or fewer than needed pre rows → premise_invalid, infeasible, nulls; no proxy estimates.