LAB #2218 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.9% to 41.4% (+9.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 6 — improves win rate from 31.9% to 41.4% (+9.6pp, n=367) SAME-WINDOW EFFECT: Applying a minimum-6-confirmation filter would have blocked the XAUUSD SHORT at 4048.74 (rizzy5m) and the GBPUSD SHORT at 1.34508 (rizzy5m) — both closed as losses. It would also have blocked the XAUUSD SHORT at 4051.79 and 4066.35 (both losses), and likely the EURJPY SHORT at 184.144 (win) — so you'd remove 4 losses and 1 win from the 10-trade window. That shifts the window from 5W/5L to 4W/1L (80% win rate), but the sample is tiny and the filter is clearly selecting for higher-conviction setups that already had more confirmations — not a causal edge. The PnL delta is positive here, but it's driven by removing the worst-performing signal type (rizzy5m XAU shorts), not by the filter itself. OVER-TIME PROJECTION: Over 3–6 months, a 6-confirmation minimum will cut trade frequency substantially — likely 3 Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com