LAB #4932 NEUTRAL: LEDGER BENCH: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.7% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ OFF_SESSION with 6 conf — improves win rate from 31.7% to 66.7% (+34.9pp, n=6) **SAME-WINDOW EFFECT:** The filter targets USDCHF SHORT at OFF_SESSION, but the live window contains only USDCHF *LONG* trades (0.81152 rejected, 0.80889 closed win) — zero trades would have been filtered, so the win-rate delta over this window is exactly 0.0pp, not +34.9pp. The three closed losses (EURUSD, XAUUSD, AUDUSD) and two closed wins (USDCHF LONG, USDCAD) are all untouched by a USDCHF-SHORT-only condition. Net PnL delta: zero. This adjustment is inert against the current window and cannot be validated by it. **OVER-TIME PROJECTION:** A +34.9pp improvement on n=6 is statistically meaningless — the 95% CI spans roughly −15pp to +85pp, and a single flip of one trade moves the number by ~17pp. USDCHF SHORT at OFF_SESSION is also a structurally thin cell: USDCHF's directional edge is regime-dependent (S Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com