MODEL ADOPTION #963: REJECT — LEDGER BENCH: Apply filter: Phase distance TIGHT (<=2deg) — improves win rate from 31.5% t — E8 Intelligence Research

DECISION: REJECT ELEMENT: The ≤2° phase distance filter is not a concrete, testable edge — it is a blunt threshold that discards trades based on a single static parameter, which contradicts E8's adaptive geometry timing. The backtest (n=392) is too small to rule out overfitting, and the +3.7pp win-rate gain is marginal given the 5–10% trade count reduction. The filter also rejects high-volatility breakouts that E8 is designed to capture, which could degrade the model's performance in trending regimes. EXPECTED IMPACT: Win-rate gain of 2–4pp is plausible but net PnL impact is near zero or negative due to lost high-RRR trades. The modest PnL improvement (0.5–1.5% per month) is not robust enough to justify the complexity and risk of false rejection. RISK: The filter will systematically reject high-volatility breakouts with wider phase spreads, which often carry higher risk/reward. In trending markets, this could cap upside and reduce overall profitability. The static threshold (≤2°) is Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com