MODEL ADOPTION #4142: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.6% to 38.2% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No single rule survives — the "min confirmations ≥6" filter is a statistical artifact, not a geometric timing edge. E8-node/Gods-Clock rhythm logic already encodes confirmation thresholds via phase alignment; adding a fixed count filter would double-count noise and delay entries past the FADE polarity sweet spot. EXPECTED IMPACT: Win-rate gain of +5.6pp in backtest is likely overfit to a specific volatility regime (n=837, single window). Live effect would decay to +1-2pp at best, while trade frequency drops ~15-20%, reducing total PnL unless per-trade size is increased — which raises tail risk. The two rizzy5m losses cited were not caused by low confirmations but by FADE polarity inversion at those timestamps; the filter would also kill the NZDUSD win, netting near-zero PnL change. RISK: In ranging or reversal-heavy markets, high-confirmation entries are late entries — they buy tops and sell bottoms, directly opposing E8's fade-at-extreme logic. This fil

Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com