LAB #2348 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT @ NY_OPEN with 5 conf — improves win rate from 31.2% to 58. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT @ NY_OPEN with 5 conf — improves win rate from 31.2% to 58.3% (+27.1pp, n=12) SAME-WINDOW EFFECT: Applying the filter (XAUUSD SHORT only at NY_OPEN with 5 conf) would have excluded 3 of the 4 XAUUSD trades in the window: the two rizzy5m shorts (07-31 09:55 and 11:20, both losses) and the rizzy7m long (08-06 10:10, a win). Only the rizzy5m short at 08-04 11:35 (loss) would remain, but it is outside NY_OPEN (11:35+02:00 = 09:35 UTC, which is pre-NY open), so it would also be excluded. Net effect: zero XAUUSD trades taken, removing 1 win and 3 losses — PnL delta is roughly +2R (avoiding 3 losses, sacrificing 1 win), but sample is tiny and the win-rate improvement is an artifact of cherry-picking a favorable subset. OVER-TIME PROJECTION: Over 3–6 months, this filter would drastically reduce XAUUSD trade frequency (likely >70% of signals dropped), concentrating only on a narrow time/confiden Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com