LAB #417 PROMISING: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 32.4% to 55.2% (+22.8pp, n=29) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 32.4% to 55.2% (+22.8pp, n=29) LAB EXPERIMENT #417: LEDGER BENCH SAME-WINDOW EFFECT: If the XAUUSD SHORT filter had been active during the current trade window, the XAUUSD SHORT via rizzy5m (entry=4100.865, status=REJECTED/open) would have been blocked from opening. This would have removed one open position from the book, but since it was already rejected, the net PnL impact is zero. No other trades in the window are XAUUSD SHORT, so no other trades are affected. The filter would have prevented a potential loss if that rejected trade later turned negative, but with n=29 in the backtest, the sample is too small to be confident. OVER-TIME PROJECTION: Over 3-6 months, applying this filter could lift overall win rate by ~22pp on XAUUSD SHORT trades, but the small backtest sample (n=29) raises risk of overfitting. The filter may be capturing a temporary regime r Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com