Fix bounded S/R training portfolio calendars

2026-07-12 22:45:05 +02:00
parent 4ca48ac590
commit cb64f7bf65
4 changed files with 52 additions and 4 deletions
@@ -429,6 +429,13 @@ Choose one arm and record that lock before running exactly control and that arm:
 Replace `confirmed_rounds` with the recorded winner. The validation command also
 calls `scripts/compare_sr_variants.py` to produce the paired cohort CSV and JSON.

+> Validation result: `confirmed_rounds` is rejected and is no longer a lockable
+> arm. It remains in the corrected training matrix only to preserve the causal
+> experiment record. The first training reports used an entry end bound without
+> forwarding it to the portfolio calendar, leaving each book in flat cash through
+> the test period. The simulator now treats `BACKTEST_ENTRY_END` as an inclusive
+> entry bound and truncates the calendar after the final position can resolve.
+
 The post-2024 interval has informed earlier research, so this is validation rather
 than a pristine holdout; do not sweep variants on it. No deployment follows
 automatically. A lower validation Sharpe or higher drawdown remains a no-ship