MODEL ADOPTION #2083: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.9% to 33.6% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — the +1.6pp win-rate gain is not proven to be independent of asset-class or volatility regime, and the filter's 20–30% trade-frequency cut directly conflicts with E8's rhythm-based entry timing (which relies on early confirmation within the Gods-Clock window). EXPECTED IMPACT: Win-rate gain likely 0 to +0.5pp in live (not +1.6pp) because the backtest's n=1350 is dominated by XAUUSD chop; the filter removes early breakouts that E8's geometry specifically targets, and confirmation lag will degrade fill quality on remaining trades, eroding any edge. RISK: Filtering confirmations <5 will systematically skip high-volatility entries that occasionally produce outsized wins (the very trades that pay for the frequent small losses). Also, the 20–30% frequency drop reduces sample size for future adaptation, making the model more brittle to regime shifts. TEST: Before any re-consideration, run a 90-day shadow replay on live signals — split Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com