MODEL ADOPTION #3919: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — the 6-confirmation filter is a statistical artifact, not an E8-geometry edge. EXPECTED IMPACT: Win-rate gain (+5.7pp) is real in backtest but comes from removing low-timeframe noise, not from aligning with Gods-Clock rhythm. Over live, frequency drops ~20–30%, gross profit likely falls faster than win-rate rises, net expectancy near zero or negative. RISK: Filter kills high-volatility breakouts that trigger on 5 confirmations during fast moves — exactly the trades E8 timing is designed to catch. Also biases toward slower trend-following, which conflicts with FADE polarity logic (counter-trend entries need speed). TEST: Before any adoption, run a 90-day replay-bench on all 8 instruments with two parallel portfolios (min 1 vs min 6 confirmations). Must show: (a) win-rate delta ≥ +5pp sustained, (b) total PnL per unit risk ≥ +10% improvement, (c) max drawdown not increased, (d) skipped trades (5-confirmation) collectively lose mo Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com