MODEL ADOPTION #1295: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.7% to 33.2% — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "min confirmations >= 5" is not a concrete, testable edge compatible with E8 geometry timing — it is a statistical heuristic derived from a backtest on a specific sample (n=1330). It does not define *which* confirmations, *how* they align with Gods-Clock phase or FADE polarity, nor does it respect the rhythm logic of E8-node entry windows. Without a geometric or timing-based rule tying the confirmation count to the model's core structure, this is a blunt instrument that will degrade edge in regime shifts. EXPECTED IMPACT: Win-rate improvement of ~1.5pp is plausible in the tested sample, but the filter will also reject high-reward entries that trigger early in strong trends (e.g., breakout moves where confirmations accumulate after entry). Over 3–6 months, net profit impact is likely neutral to negative due to missed opportunities and reduced trade count, especially in volatile or trending regimes. RISK: The filter is regime-sensitive — in low-vol Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com