LAB #4828 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.8% to 33.3% (+1.5pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.8% to 33.3% (+1.5pp, n=1940) SAME-WINDOW EFFECT: The filter would only have touched trades with fewer than 5 confirmations, and the visible window is too small (10 trades, 3 wins) to isolate which entries had confirmation counts below the threshold — but the pattern is telling: the three closed losses (EURUSD, XAUUSD, AUDUSD shorts) are all counter-trend short attempts, exactly the kind of low-conviction setup a confirmation floor is designed to cull. If even two of those three losses had been filtered out, the window's realized PnL improves materially without touching the two winners (USDCHF, USDCAD). The rejected/open entries (NZDUSD, GBPUSD, EURUSD, USDCHF, EURJPY) are unaffected in outcome terms since they never closed, but the filter would have suppressed several of them at entry, reducing exposure count. OVER-TIME PROJECTION: A +1.5pp win-rate Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com