LAB #4027 PROMISING: LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 32.5% to 38.1% (+5.6pp, — 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 38.1% (+5.6pp, n=821) SAME-WINDOW EFFECT: Applying a minimum 6-confirmation filter would have eliminated the two `wkjudas` entries (GBPUSD LONG and USDJPY SHORT) that fired within minutes of signal generation, plus the `rizzy5m` NZDUSD SHORT and XAUUSD SHORT (all closed as LOSS or open at a loss). That removes 4 of 10 trades, of which 3 are confirmed losers and 1 is open — likely flipping the window from net negative to roughly breakeven or slightly positive. The one `rizzy5m` WIN (GBPUSD SHORT) would have survived, but the filter would also have killed the `rizzy7m` EURUSD LONG WIN (entry at 10:20, likely <6 confirmations at that time), so the net PnL delta is positive but not dramatic — roughly +1.5R to +2.5R on this small sample. OVER-TIME PROJECTION: Over 3–6 months, the filter should reduce trade frequency by roughly 20–30% while cutting Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com