MODEL ADOPTION #2816: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.1% to 37.9% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — the 6-confirmation filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: Win-rate gain is likely +2–4pp at best, but trade frequency drops ~20–30%, and the backtest n=409 is regime-dependent (trending XAUUSD/GBPUSD periods). Net profit impact is near zero or negative after slippage on delayed entries. RISK: Over-filtering kills early high-volatility winners (e.g., XAUUSD LONG 2026-08-06) that trigger with <6 confirmations but carry the fat right tail. Also, the filter is a proxy for signal strength, not timing — it does not align with Gods-Clock rhythm or FADE polarity, so it may cut entries exactly at the optimal fade point. TEST: Before any reconsideration, run a 90-day replay on the exact live instrument set with a strict rule: only entries where the 6th confirmation occurs within 3 bars of the original trigger are allowed. If that subset shows win rate ≥40% AND average R:R ≥1.5 on at least Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com