The trust page
We grade ourselves every morning.
Every set of lineups we deliver gets scored against real box scores — best lineup, set average, top-3 average. Postponements, busts, engine upgrades: it all stays on the board. No screenshots of winners only.
Lineup sets
| Date | Set | Lineups | Best | Mean | Top-3 Avg | Notes |
|---|---|---|---|---|---|---|
| 2026-06-11 | early42_v6_delivered | 42 | 164.1 | 115.7 | 160.8 | |
| 2026-06-11 | early42_v7_retro | 42 | 209.5 | 149.4 | 200.1 | v7 wins |
| 2026-06-11 | night11_615 | 11 | 136.6 | 86.3 | 126.8 | |
| 2026-06-11 | night11_afterhours_PLAYED | 11 | 149.1 | 100.3 | 136.8 | Kay PPD zeros x4 |
| 2026-06-11 | replay20_131393_night | 20 | 146.3 | 102.8 | 136.9 | replay v10 engine |
| 2026-06-11 | replay20_131399_early(top20of42) | 20 | 178.8 | 144.6 | 174.5 | replay v10 engine |
| 2026-06-10 | replay20_131366_main | 20 | 139.1 | 97.6 | 134.9 | replay v10 engine |
| 2026-06-10 | replay20_131367_2game | 13 | 185.7 | 144.8 | 180.0 | replay v10 engine |
| 2026-06-09 | replay20_131322_main | 20 | 169.7 | 121.6 | 155.2 | replay v10 engine |
Daily model report card
| Date | Type | Players | MAE | Bias | Rank Corr |
|---|---|---|---|---|---|
| 2026-06-11 | Pitchers | 6 | 16.23 | -16.23 | -0.551 |
| 2026-06-11 | Hitters | 54 | 6.59 | +0.32 | 0.400 |
| 2026-06-10 | Pitchers | 28 | 12.48 | +1.48 | 0.307 |
| 2026-06-10 | Hitters | 232 | 7.79 | +1.65 | 0.093 |
Engine upgrades are validated retroactively against the boards we actually delivered — when v7 beat the delivered v6 set 209.5 to 164.1 on the same slate, that comparison went here too. Updated daily by the pipeline.
