LAB #4038 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.2% (+5.7pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.2% (+5.7pp, n=820) SAME-WINDOW EFFECT: Applying a minimum-6-confirmation filter to the current live window would have rejected the two `wkjudas` entries (GBPUSD LONG and USDJPY SHORT) that entered at 15:08 and 14:36 on 2026-09-01, as both likely had fewer than 6 confirmations at entry. Both closed as LOSSES, so the filter would have removed two losing trades from the window. The remaining trades (including the two `rizzy5m` and `rizzy7m` entries) would be unaffected, yielding a net PnL improvement of roughly +2R (assuming typical risk per trade) and a win-rate shift from 2/8 (25%) to 2/6 (33%) in this small sample. However, the filter would not have saved the NZDUSD SHORT (wkjudas, 02:43) which is still open and may be a loss, so the delta is modest and sample-dependent. OVER-TIME PROJECTION: Over 3–6 months, a 6-confirmation filter should Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com