LAB #2127 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.1% (+10.1pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.1% (+10.1pp, n=359) SAME-WINDOW EFFECT: Applying a minimum 6-confirmation filter would have eliminated the two XAUUSD SHORT losses (rizzy5m entries at 4048.74 and 4051.79) and likely the GBPUSD SHORT loss (rizzy5m at 1.34508), as these were early-entry signals with fewer confirmations. That removes 3 of 4 losses from the window, leaving only the EURJPY SHORT loss (rizzy5m at 184.144) — but that trade was a WIN, so it would have been incorrectly filtered out, costing a win. Net effect: 3 losses removed, 1 win removed → win rate improves from 5/10 (50%) to 4/7 (57%), but PnL delta is roughly neutral because the removed win offsets the removed losses. The filter is directionally correct but not a free lunch — it sacrifices some winners. OVER-TIME PROJECTION: Over 3–6 months, the +10.1pp win-rate improvement (n=359) suggests a genuine signal-qu Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com