MODEL ADOPTION #3691: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 7 — improves win rate from 32.3% to 44.4% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — "min confirmations >= 7" is a statistical artifact, not an E8-geometry edge. EXPECTED IMPACT: Win-rate gain is illusory (+12.1pp on n=18 is noise; 95% CI spans roughly -5pp to +29pp). Filtering on confirmations alone does not align with Gods-Clock rhythm phase or FADE polarity timing — it merely reduces sample size, which can inflate win rate by cherry-picking calmer periods. Over 3-6 months, reduced frequency (20-40% fewer trades) likely lowers absolute PnL even if win rate improves, because the model's edge is frequency-dependent (fade rhythm requires consistent participation). RISK: The filter will systematically exclude early entries in fast-trending markets (e.g., GBPUSD breakouts) where confirmation lags price — these are often the highest R:R winners in the live model. It also introduces a lookahead bias in the backtest: trades with <7 confirmations were often stopped out before reaching 7, so the filter implicitly select Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com