MODEL ADOPTION #3860: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.2% — E8 Intelligence Research

DECISION: REJECT ELEMENT: No element 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 raw count filter would distort the FADE polarity entry timing without addressing the underlying 32.5% win-rate root cause (likely over-trading in low-conviction zones). EXPECTED IMPACT: Win-rate bump from 32.5%→38.2% is real in backtest but likely due to sample selection bias (n=808, not regime-controlled). Removing 15-20% of trades will cut gross profit proportionally; net PnL improvement is unproven and likely <1% after accounting for missed early breakouts. The filter does not increase average win size or reduce drawdown — it only changes trade count. RISK: (1) In low-volatility regimes (ATR percentile <30), confirmations naturally cluster below 6 — this filter would starve the model during choppy markets, exactly when FADE polarity edges ar Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com