1# Verification checks (P4)2| check | outcome |3|---|---|4| Re-run analysis.py twice; results.json byte-identical (cmp) | PASS |5| SHA-256 of gc5y_daily.csv matches README | PASS |6| n_input_rows (2498) = wc -l minus header | PASS |7| sum of table1 n_days = 2498 | PASS |8| baseline_metric = 100*(last-first)/2497 = 100*(1.68-2.75)/2497 = -0.04285 (telescoping identity) | PASS |9| n_treated = 0 consistent with sample_end 2019-12-31 < 2020-03-04 | PASS |10| conclusion premise_invalid ⇔ feasibility infeasible, effect/CI/model_metric/n_analysed null | PASS |11| Exclusion ledger: 2498 rows − 1 = 2497 changes used for baseline; main estimate has no observations (n_analysed null) | PASS (documented) |12| CI contains estimate / SE positive | N/A (not estimable) |13| post_cut not redefined; no external data used | PASS |14