LAB #4606 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.6% to 35.8% (+4.2pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.6% to 35.8% (+4.2pp, n=907) 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 carry unknown outcomes. Among the seven closed trades, none would have been filtered (all had ≥6 confirmations at entry), so the historical win rate in this window would remain 4 wins / 3 losses (57.1%) — unchanged. The only PnL delta would be the removal of three open positions whose eventual outcomes are unknown; if those three were net losers (likely given the backtest lift), the filter would have improved realized PnL, but we cannot confirm from this snapshot. The +4.2pp backtest gain is not visible in this small live sample because the filter only removes trades that are still pending — no closed trade wou Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com