MODEL ADOPTION #1954: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.4% — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: No element survives — the 6-confirmation filter is a statistical artifact, not an E8-geometry-compatible edge. EXPECTED IMPACT: Win-rate gain (+10.4pp) is real in backtest but driven by removing early-momentum entries that carry asymmetric R:R. Net PnL likely flat-to-negative because sacrificed winners (e.g., EURJPY) have larger average R:R than the removed losses. Frequency drop (~20-30%) reduces compounding surface. RISK: Overfits to a low-volatility regime; in trending markets, 6-confirmation delay forces wider stops, increasing average loss size and degrading the FADE polarity edge that depends on precise entry timing. Also, the filter is exogenous to E8 rhythm logic — it does not align with Gods-Clock phase or node geometry, so it corrupts the model's timing coherence. TEST: Before any reconsideration, run a 12-month replay-bench splitting rizzy5m signals by confirmation count (0-5 vs 6+), but require: (1) average R:R per trade for 6+ must be ≥1.5 Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com