MODEL ADOPTION #976: REJECT — LEDGER BENCH: Apply filter: USDCHF SHORT @ NY_OPEN with 6 conf — improves win rate from 31 — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "USDCHF SHORT @ NY_OPEN with 6 conf" fails because it is a single-pair, single-time-window heuristic that does not align with E8's Gods-Clock rhythm logic. E8 geometry timing requires entries to be triggered by phase transitions across multiple pairs, not a fixed calendar event (NY_OPEN). The 6 conf threshold is arbitrary and not derived from E8's own confidence metric (which is based on fractal alignment, not a scalar count). The sample (n=33) is too small to distinguish signal from noise, and the +25.9pp improvement is likely overfit to a specific market regime (e.g., recent USDCHF trend). Adopting this would introduce a brittle rule that contradicts E8's multi-pair, phase-based entry logic, degrading model coherence. EXPECTED IMPACT: Win-rate improvement would not replicate in live trading due to overfitting; profit would likely decrease because the filter would remove valid E8 entries that happen to be USDCHF SHORT outside NY_OPEN, reducing tr Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com