MODEL ADOPTION #419: REJECT — LEDGER BENCH: Apply filter: ETHUSD SHORT — improves win rate from 32.4% to 50.0% (+17.6pp, — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "ETHUSD SHORT only" is a pair-direction bias, not a timing or polarity edge. It does not align with E8's Gods-Clock rhythm logic, which is agnostic to asset-specific directional filters. The claimed +17.6pp gain is based on n=58 — too small to distinguish signal from regime overfit. No concrete, testable edge compatible with E8 geometry survives. EXPECTED IMPACT: Zero in current window (no ETHUSD SHORT trades). Over 3–6 months, likely degrades win rate by reducing trade frequency and introducing regime-dependent bias. RISK: Overfitting to a single pair/direction in a specific market phase. Reduces adaptability. May cause missed profitable ETHUSD SHORTs in non-trending conditions. TEST: Not applicable — no element to test. If you want to pursue, run a 60-day shadow-test comparing filtered vs unfiltered ETHUSD SHORT signals, but this is not E8-compatible. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com