LAB #4999 NEUTRAL: LEDGER BENCH: Apply filter: ETHUSD SHORT @ NY_OPEN with 6 conf — improves win rate from 31.7% to 63. — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: ETHUSD SHORT @ NY_OPEN with 6 conf — improves win rate from 31.7% to 63.6% (+31.9pp, n=11) SAME-WINDOW EFFECT: The filter only touches ETHUSD SHORT entries at NY_OPEN with confidence 6, and the current live window contains zero ETHUSD trades — every logged trade is EURUSD, XAUUSD, AUDUSD, NZDUSD, GBPUSD, USDCHF, EURJPY, or USDCAD. So over this specific window the filter would have changed nothing: same trades, same losses, same two wins, identical PnL. The claimed +31.9pp improvement is therefore unverifiable against this window and cannot be credited here. OVER-TIME PROJECTION: If the edge is real, it's a narrow slice — one instrument, one session, one confidence bucket — so its contribution to portfolio-level expectancy is small and easily swamped by the broader book, which is currently bleeding (286 losses vs 140 TP2 wins over 30 days). The bigger risk is statistical: n=11 with a 31.7%→63.6% jump Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com