LAB #2510 HARMFUL: LEDGER BENCH: Apply filter: USDCHF SHORT @ LONDON_OPEN with 6 conf — improves win rate from 31.1% to — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: USDCHF SHORT @ LONDON_OPEN with 6 conf — improves win rate from 31.1% to 71.4% (+40.4pp, n=7) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the USDCHF SHORT at 10:30 (currently REJECTED/open) — that trade is not in the win/loss tally, so no direct PnL change there. However, it would also have blocked the USDCHF SHORT from 2026-08-04 11:20 (USDCAD SHORT is a different pair, so unaffected) — but that trade is not in the list either. The only USDCHF trade in the window is the REJECTED one, so the filter changes nothing in the realized PnL. The claimed +40.4pp win-rate improvement is based on n=7, which is statistically meaningless — the confidence interval spans roughly ±35pp, so the true effect could be anywhere from +5pp to +75pp. Net same-window effect: zero realized delta, but a false sense of edge. OVER-TIME PROJECTION: Over 3-6 months, this filter would likely re Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com