LAB #4603 NEUTRAL: LEDGER BENCH: Apply filter: Min confirmations >= 5 — improves win rate from 31.6% to 33.0% (+1.4pp, — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Min confirmations >= 5 — improves win rate from 31.6% to 33.0% (+1.4pp, n=1909) SAME-WINDOW EFFECT: Applying a minimum 5-confirmation filter would have rejected the three currently open/rejected trades (USDCHF LONG, EURJPY SHORT, AUDUSD LONG) — all of which are unconfirmed and thus excluded from the win-rate calculation anyway. Among the seven closed trades, none would be filtered out, so the live win rate would remain unchanged at 4 wins / 7 closed = 57.1%. The +1.4pp backtest improvement is not observable in this tiny window; the only tangible effect is preventing three open positions from becoming live, which reduces exposure but also removes potential upside if those signals later confirm. Net PnL delta over this window is approximately zero, since the filtered trades are still open and unresolved. OVER-TIME PROJECTION: Over 3–6 months, this filter should reduce false entries by requiring more c Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com