LAB #4948 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.7% to 45.0% (+13.3pp, n=40) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.7% to 45.0% (+13.3pp, n=40) SAME-WINDOW EFFECT: Over the listed live window, the filter would only touch one trade — XAUUSD SHORT via rizzy5m on 2026-09-10, which closed as a loss. If the filter had been live and had excluded that entry, the window would show one fewer loss, but the sample is a single trade, so the claimed +13.3pp win-rate lift is not observable here. The other live trades (EURUSD, AUDUSD, NZDUSD, GBPUSD, EURJPY, USDCHF, USDCAD) are outside the XAUUSD SHORT filter scope and would be unchanged. Net effect on this window: marginal improvement from avoiding one losing XAUUSD short, not a validated 13.3pp edge. OVER-TIME PROJECTION: If the backtest is honest and the XAUUSD SHORT filter genuinely raises win rate from 31.7% to 45.0% on n=40, it would reduce trade frequency in that bucket and improve expectancy, but the sample is small and likely ov Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com