MODEL ADOPTION #2326: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 39.8% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — the "min confirmations ≥ 6" filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: Win-rate gain would shrink to ~+2-3pp live (overfit to n=384), while trade count drops >15% — net profit likely flat or negative due to lost compounding and missed early TP2 winners in trends. RISK: Filter removes low-confluence noise entries, but also blocks early momentum winners (e.g., EURJPY short win). In trending regimes, confirmations lag price — you'd systematically exit late or miss entries entirely, degrading the FADE polarity edge that relies on precise E8 rhythm timing, not confirmation counts. TEST: Before any re-consideration, run a 30-day shadow replay on the exact live symbol set (XAUUSD, GBPUSD, EURJPY) with identical risk. Log every rejected signal and simulate its 48-hour outcome. Pass criteria: ≥+4pp win-rate improvement AND ≤15% trade reduction, sustained across two consecutive 15-day sub-wind Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com