LAB #4791 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF LONG — improves win rate from 31.8% to 41.9% (+10.1pp, n=155) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF LONG — improves win rate from 31.8% to 41.9% (+10.1pp, n=155) SAME-WINDOW EFFECT: Over the current live window, the filter would have touched exactly one trade: USDCHF LONG via rizzy7m on 2026-09-08, which was REJECTED/open — under the filter it would have been taken (or kept) rather than filtered out, and the 2026-09-04 USDCHF LONG that closed WIN is the only realized sample confirming the direction. Net effect on the window is roughly zero to slightly positive: one additional open position, no closed-trade PnL change, and the win-rate delta is unmeasurable at n=1. The filter does nothing for the EURUSD/XAUUSD/AUDUSD/NZDUSD/GBPUSD shorts that dominate the window's losses. OVER-TIME PROJECTION: A +10.1pp win-rate lift on n=155 is a real but modest edge — 41.9% is still a losing win rate unless average win size materially exceeds average loss, so this filter alone does not make USDCHF LONG pro Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com