MODEL ADOPTION #858: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.5% to 33.1% — E8 Intelligence Research

DECISION: REJECT ELEMENT: The "min confirmations >= 5" filter is not a concrete, testable edge compatible with E8 geometry timing — it is a statistical bandage on signal quality, not a timing or polarity rule. It does not align with Gods-Clock rhythm logic or FADE polarity mechanics. EXPECTED IMPACT: Win rate might lift ~1.6pp in backtest, but the filter will reject ~10-15% of trades including some winners, and the net PnL gain is marginal at best. The 0.5-1.0R improvement in the small sample is not statistically robust (n=4 trades). Over time, regime shifts toward low-confirmation reversals would degrade performance. RISK: Overfitting to a specific backtest window; suppressing high-R/low-confirmation winners; reducing trade count without compensating edge; introducing a non-geometric rule that conflicts with E8's core timing logic. TEST: No test is warranted — the filter is not compatible with E8 geometry timing. Reject outright. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com