LAB #2918 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.1% to 32.7% (+1.6pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.1% to 32.7% (+1.6pp, n=1427) SAME-WINDOW EFFECT: Applying a minimum of 5 confirmations would have filtered out the two rejected/open trades (USDCHF SHORT at 10:30 and the second GBPUSD SHORT at 10:10) if they had fewer than 5 confirmations at entry — but based on the live log, both were either rejected or closed as wins, so the filter would have removed one win (GBPUSD) and one open/rejected trade, leaving the remaining 8 trades intact. Net effect on this window: win rate would shift from 5W/4L (55.6%) to 4W/4L (50%) if the open trade is excluded, or 4W/5L (44.4%) if counted as a loss — a slight negative delta, not the +1.6pp backtest suggests, because the sample is tiny and the filter removes a winner. PnL delta is roughly −0.5R to −1R depending on the open trade's fate, so no immediate edge is visible here. 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