LAB #4600 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% (+4.0pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.5% to 35.6% (+4.0pp, n=922) SAME-WINDOW EFFECT: Applying a minimum 6-confirmation filter would have rejected the three currently open/rejected trades (USDCHF rizzy7m, EURJPY rizzy5m, AUDUSD rizzy7m) — all of which are still unresolved and thus not yet contributing to win/loss stats. Among the seven closed trades, all had at least 6 confirmations at entry (they were closed as wins/losses based on TP/SL, not on confirmation count), so none would be filtered. The backtested +4.0pp win-rate improvement would not manifest in this tiny sample; the only observable change is reduced exposure (3 fewer open positions), which trivially lowers total trade count but not PnL per closed trade. Net effect on this window: neutral on closed-trade outcomes, but it would have avoided three currently floating positions whose final disposition is unknown. OVER-TIME PROJE Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com