LAB #1069 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.7% to 76.2 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ NY_OPEN with 5 conf — improves win rate from 31.7% to 76.2% (+44.5pp, n=21) LAB EXPERIMENT #1069: LEDGER BENCH SAME-WINDOW EFFECT: Over the current trade window, applying the XAUUSD LONG @ NY_OPEN with 5 conf filter would have affected only the XAUUSD SHORT via rizzy5m (entry=4100.865, REJECTED/open). Since that trade was already rejected and not a long, no live trades would have been altered. The filter would have added no new entries or prevented any losses, so PnL delta is $0. Win-rate improvement from 31.7% to 76.2% is based on a separate backtest window (n=21) and does not apply here. OVER-TIME PROJECTION: Over 3-6 months, this filter could increase win rate on XAUUSD longs specifically, but the sample size (n=21) is too small to be statistically reliable. Risk includes overfitting to a narrow time window (NY_OPEN) and confidence threshold (5), which may not generalize across dif Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com