LAB #4972 HARMFUL: 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: Over the current live window, this filter would have touched exactly one trade: the USDCHF LONG via rizzy7m on 2026-09-08 (REJECTED/open). The filter is specified for USDCHF SHORT @ OFF_SESSION, so it would not have blocked that long — meaning zero of the nine listed live trades would have been removed or added. The three closed losses (EURUSD, XAUUSD, AUDUSD shorts) are all non-USDCHF or wrong direction, so the claimed +34.9pp win-rate lift is invisible in this window; the live sample provides no confirming or refuting evidence for the filter. OVER-TIME PROJECTION: The headline number is built on n=6 — a 66.7% win rate on six trades has a 95% confidence interval roughly spanning 22% to 96%, so it is statistically indistinguishable from the 31.7% baseline it claims to beat. The +34.9pp d Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com