LAB #2961 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 7 — improves win rate from 31.3% to 36.4% (+5.0pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 7 — improves win rate from 31.3% to 36.4% (+5.0pp, n=11) SAME-WINDOW EFFECT: Applying a minimum of 7 confirmations would have filtered out the two rizzy5m GBPUSD SHORT entries (1.34407 and 1.34461) and the rizzy5m XAUUSD SHORT at 4048.74, all of which were closed as WIN, WIN, and LOSS respectively. That removes 2 wins and 1 loss from the 10-trade window, shifting the live record from 6W/4L (60%) to 4W/3L (57%) — a slight win-rate drop, but the filtered-out trades were net +1 win, so PnL would have been marginally lower. The USDCHF SHORT (rejected/open) and the remaining trades are unaffected, so the immediate effect is neutral-to-slightly-negative on this small sample. OVER-TIME PROJECTION: Over 3–6 months, the +5.0pp win-rate improvement from the backtest (n=11) is likely real but fragile — it trades a modest gain in accuracy for a reduction in trade frequency, which could lowe Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com