LAB #1032 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 40.8% (+9.2pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 40.8% (+9.2pp, n=331) SAME-WINDOW EFFECT: Applying a minimum 6 confirmations filter would have rejected the EURUSD SHORT (loss) and likely the GBPUSD LONG via wkjudas (loss), while retaining the USDCAD LONG, GBPUSD SHORT via rizzy7m, USDCHF SHORT, and USDJPY LONG (all wins). The two REJECTED/open trades (XAUUSD SHORT, EURJPY SHORT, AUDUSD SHORT, GBPUSD SHORT via rizzy5m) would remain rejected, so no change there. This would shift the window from 4 wins, 2 losses to 4 wins, 0 losses — a 100% win rate on the filtered set, but the small sample (n=6) makes the +9.2pp backtest gain plausible but not yet proven. OVER-TIME PROJECTION: Over 3-6 months, this filter should reduce false signals from low-conviction setups, lifting win rate toward 40% as backtested. However, it will also reject some eventual winners that would have triggered with fewer con Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com