LAB #2356 NEUTRAL: LEDGER BENCH: Apply filter: GBPUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.2% to 62.5 — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: GBPUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.2% to 62.5% (+31.3pp, n=8) SAME-WINDOW EFFECT: Over the current live window, the filter would have eliminated all GBPUSD trades — but there are no GBPUSD LONGs in the list, only one GBPUSD SHORT (loss). So the direct impact on this window is zero trades changed, zero PnL delta. However, the filter's logic (LONG only at NY_OPEN with 6 conf) would have blocked the GBPUSD SHORT entry on 2026-08-03, which was a loss — so it would have removed one losing trade, improving the window's win rate from 5/10 (50%) to 5/9 (55.6%). The +31.3pp claim is based on n=8 backtest, which is statistically fragile and not reflected in this live sample. OVER-TIME PROJECTION: Over 3-6 months, this filter would drastically reduce GBPUSD trade frequency — likely to near-zero, since it requires a very specific confluence (LONG + NY_OPEN + 6 conf). The backtest's n= Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com