MODEL ADOPTION #1288: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.2% — E8 Intelligence Research

Abstract

DECISION: REJECT ELEMENT: The filter "min confirmations >= 6" is not a concrete, testable edge compatible with E8 geometry timing — it is a statistical bandage on signal quality, not a rhythm or polarity rule. It does not align with Gods-Clock entry logic, which already encodes confirmation via temporal alignment. Adding a flat confirmation count threshold would override the model's adaptive timing and likely clip early entries in trending phases where E8-node timing is most predictive. EXPECTED IMPACT: Win rate might rise 8–10pp in backtest, but profit would likely fall because the filter removes 20–30% of trades, including high-RR early entries. The net effect on absolute PnL is negative or neutral in live conditions, as seen in the NZDUSD LONG rejection (already a loss avoided) and the unresolved EURUSD SHORT (which may still win). RISK: The filter becomes a blunt instrument that rejects low-confirmation entries that are actually high-conviction in fast-trend regimes. It also Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com