MODEL ADOPTION #4064: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.2% — 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 real in backtest (+5.7pp) but unproven in live drift; Merlin's own projection shows only +0.5R to +1.0R over the observed window, and the filter likely removes early entries that catch fast moves — cutting total profit even if win rate rises. The n=822 is regime-dependent; over 3–6 months, expect regression to +2–3pp at best, with a real chance of net negative PnL if filtered trades had higher payoff ratios. RISK: Overfitting to a specific market regime (trending vs. choppy). Confirmations lag in fast reversals — you will systematically miss the best entries in the exact moments E8 rhythm logic is designed to exploit. Also, the filter is not derived from E8 node/Gods-Clock geometry; it's a generic confirmation threshold that could blunt the model's timing edge. TEST: Before any reconsideration, run a 30-da Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com