LAB #4772 NEUTRAL: LEDGER BENCH: Apply filter: NZDUSD SHORT — improves win rate from 31.8% to 34.5% (+2.7pp, n=139) — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: NZDUSD SHORT — improves win rate from 31.8% to 34.5% (+2.7pp, n=139) SAME-WINDOW EFFECT: In the current window, the filter would have blocked the NZDUSD SHORT via rizzy5m at 2026-09-09 11:45:00 — the one trade it directly targets — which is currently sitting REJECTED/open, so no realized PnL is removed. The other live trades (EURUSD, XAUUSD, AUDUSD, GBPUSD, USDCHF, EURJPY, USDCAD) are untouched, so the window's realized result (2 closed wins, 2 closed losses) is unchanged. Net same-window delta: zero trades affected in realized terms, one open position avoided. OVER-TIME PROJECTION: A +2.7pp win-rate lift on n=139 is roughly 3.75 extra wins, which is within one standard deviation of noise for a 31.8% base rate (SE ≈ 3.9pp) — not statistically distinguishable from zero. Over 3-6 months, if the edge is real it's marginal; if it's noise, you've removed a short-side NZDUSD exposure that may have carried Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com