LAB #2238 HARMFUL: LEDGER BENCH: Apply filter: GBPUSD LONG @ NY_OPEN with 6 conf — improves win rate from 31.8% 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 31.8% to 62.5% (+30.7pp, n=8) SAME-WINDOW EFFECT: Over the current live window, this filter would have blocked the GBPUSD LONG via sqz (entry 1.33621, 2026-07-29 20:00) — which was a WIN — and would have allowed only the GBPUSD SHORT via rizzy5m (entry 1.34508, 2026-08-03) — which was a LOSS. So applying this filter would have removed one win and kept one loss, flipping the window's net result from +2 wins/3 losses to +1 win/3 losses — a negative PnL delta of roughly one full risk unit. The claimed +30.7pp win-rate improvement is based on n=8, which is statistically meaningless; the live window shows the opposite directional effect. OVER-TIME PROJECTION: Over 3–6 months, this filter would likely reduce trade frequency on GBPUSD LONGs at NY open, which may cut some losing streaks but also removes high-conviction winners that occur in the same Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com