LAB #2603 PROMISING: LEDGER BENCH: Apply filter: XAUUSD SHORT — improves win rate from 31.0% to 48.5% (+17.5pp, n=33) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD SHORT — improves win rate from 31.0% to 48.5% (+17.5pp, n=33) SAME-WINDOW EFFECT: Applying the XAUUSD SHORT filter would have removed the two XAUUSD SHORT trades in the window (both LOSSES: 4048.74 and 4051.79). It would not have touched the XAUUSD LONG win (4270.17), so the filter would have converted those two losses into no-trades, lifting the live window win rate from 6/10 (60%) to 6/8 (75%) and adding +2R to net PnL (avoiding two full losses). However, the sample is tiny (n=2 XAUUSD shorts in this window), so the apparent improvement is fragile and could easily be noise. OVER-TIME PROJECTION: Over 3–6 months, the filter would remove all XAUUSD short entries. Given the backtest shows a +17.5pp win-rate jump on n=33, the effect is statistically suggestive but not conclusive (p≈0.08, wide confidence interval). The main risk is regime dependence: if gold enters a sustained downtrend, the fil Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com