MODEL ADOPTION #3284: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.5% — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: No single rule survives — the "min confirmations ≥6" filter is a statistical artifact, not an E8-geometry-compatible edge. The backtest improvement (+10.5pp) is derived from a single 348-trade sample, and Merlin's own projection admits n=10 live trades is too small for significance. The filter would arbitrarily suppress rizzy5m entries, which are core to the FADE polarity rhythm — this violates the E8-node timing logic that already validates entries at specific clock phases, not by confirmation count. EXPECTED IMPACT: If adopted, win rate might rise 5-8pp in trending regimes, but average R-multiple would shrink (filter cuts high-volatility scalps with asymmetric payoffs), and total PnL per 100 trades would likely stay flat or degrade. The +30pp live "improvement" is noise — two losers blocked, but no proof they weren't regime-specific outliers. RISK: Overfitting to a single market regime (trending FX/gold). In choppy conditions, waiting for 6 confirmatio Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com