Every template from the Reality Check Lab builder, run at its textbook defaults on the same universe (top 100 Binance USDT perps by volume, 15m), the same period (2025-10-27 to 2026-10-27), the same exits (2% stop, 4% target, 48 bars) and the same costs (taker fee, slippage, actual funding). 0 of 30 cleared the random-entry control and the Bonferroni bar; 29 lose money after costs. Click a row for the full page with the equity curve, train/test split and parameter landscape.
The entry rule is the only variable. A row counts as an edge only with a positive net result, t(NW) at or above the Bonferroni bar for the cells in its sweep, the same sign in test and in the second half, and a better result than random entry and the 24h placebo.
Open any template in the builder, change what you believe is wrong with it and run it against the same controls. 3 free runs after sign-in.