LAB #2076 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.0% to 42.1% (+10.2pp, — 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% (+10.2pp, n=356) SAME-WINDOW EFFECT: Applying a minimum-6-confirmation filter would have blocked the XAUUSD SHORT at 4048.74 (loss), the XAUUSD SHORT at 4051.79 (loss), and the XAUUSD SHORT at 4066.35 (loss) — all rizzy5m entries with fewer than 6 confirmations at trigger. It would also likely block the EURJPY SHORT at 184.144 (win) and possibly the USDJPY SHORT (open) if confirmations were below threshold. Removing three losses and one win from the 10-trade window shifts the live record from 5W/4L/1O to 4W/1L/1O — a raw win-rate jump from ~55% to ~80% on closed trades, with a positive PnL delta driven by cutting three XAUUSD losses (likely larger per-trade risk). However, the filter also removes a winning EURJPY trade, so the net PnL gain is positive but smaller than the win-rate delta suggests. OVER-TIME PROJECTION: Over 3–6 months, a Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com