MODEL ADOPTION #3992: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: No single rule survives — the "min confirmations ≥6" filter is not a geometric timing edge, it's a statistical artifact with no causal link to E8 rhythm logic. EXPECTED IMPACT: Win-rate gain (+5.6pp) is real in backtest but likely overfit to recent volatility regime; net PnL may drop 15–25% due to reduced frequency, and the filter removes low-conviction entries that occasionally produce outsized winners. No evidence it aligns with Gods-Clock phase or FADE polarity. RISK: Look-ahead bias if confirmations are counted after entry; regime-dependence (works in ranging, fails in trending); reduces sample size for live validation; could silently kill high-R trades that enter early but confirm later. TEST: Before any adoption, run a 90-day shadow replay on the live engine: log every rizzy5m signal with confirmation count at entry, simulate two portfolios (≥6 vs all), require ≥200 trades per arm, and compare net R, max drawdown, and win rate across both trendin Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com