MODEL ADOPTION #2560: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 7 — improves win rate from 31.0% to 36.4% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No element survives — the min-confirmations>=7 filter is a statistical artifact on n=11, not a structural edge. E8 geometry timing already encodes confirmation thresholds; adding a second arbitrary filter risks overfitting to a 5-trade window. EXPECTED IMPACT: Win rate may rise 2-4pp on live, but profit per trade likely falls because filtered trades include high-RR winners (e.g., USDJPY wkjudas) that hit TP2 in ranging regimes. Net PnL could drop 10-20% over 3 months. RISK: The filter removes low-conviction entries that E8's fade polarity relies on for mean-reversion fills; in choppy markets, those are the exact trades that capture TP2. Also, the 08-04 XAUUSD loss (high confirmations) proves the filter misses the worst tail risk. TEST: Before any reconsideration, run a 60-day shadow backtest on rizzy5m, rizzy7m, wkjudas with/without filter, fixed 1% risk, identical TP/SL. Require ≥200 trades per arm, p<0.05 on win-rate AND total R-multiple. Also test m Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com