forward paper scoreboard
← lab · · ran 7/9/2026
What this is: A one-off study — its numbers below are exactly what the run reported.
| note | live paper record; statuses are won/lost/void/pending. Small early samples — treat as directional, not proof. This is how model-gated + soft/prop strategies must be judged (revalidate's shape proxy can't). |
board
| pnl | won | bets | lost | hit pct | pending | roi pct |
|---|
| 280.21 | 4 | 27 | 19 | 17.4 | 4 | 132 |
| 222.13 | 13 | 24 | 11 | 54.2 | 0 | 69.4 |
| 41 | 5 | 7 | 1 | 83.3 | 1 | 68.3 |
| 22 | 1 | 7 | 4 | 20 | 2 | 88 |
| 21.02 | 3 | 5 | 1 | 75 | 1 | 52.5 |
| 4.51 | 2 | 3 | 1 | 66.7 | 0 | 30.1 |
| 4.4 | 2 | 18 | 10 | 14.3 | 4 | 3.1 |
| 0 | 0 | 3 | 0 | 0 | 0 | 0 |
| 0 | 0 | 1 | 0 | 0 | 1 | 0 |
| 0 | 0 | 1 | 0 | 0 | 1 | 0 |
| 0 | 0 | 1 | 0 | 0 | 1 | 0 |
| 0 | 0 | 5 | 0 | 0 | 5 | 0 |
| 0 | 0 | 2 | 0 | 0 | 2 | 0 |
| -1.2 | 3 | 6 | 3 | 50 | 0 | -2 |
| -4.61 | 1 | 7 | 3 | 25 | 3 | -23 |
| -8 | 0 | 5 | 4 | 0 | 1 | -100 |
| -10 | 0 | 2 | 1 | 0 | 0 | -50 |
| -10 | 0 | 1 | 1 | 0 | 0 | -100 |
| -10 | 0 | 4 | 1 | 0 | 3 | -100 |
| -10.16 | 2 | 8 | 5 | 28.6 | 1 | -6 |
| -14.6 | 2 | 6 | 4 | 33.3 | 0 | -24.3 |
| -20 | 0 | 6 | 2 | 0 | 4 | -100 |
| -30 | 0 | 5 | 1 | 0 | 4 | -100 |
| -46.86 | 7 | 19 | 11 | 38.9 | 1 | -26 |
totals
| pnl | 429.84 |
| pending | 39 |
| roi pct | 30.4 |
| settled | 134 |
| strategies | 24 |
Reading the columnswhat each number actually means
| AUC | predictability: 0.50 = coin flip, ~0.70 = ceiling for sports |
| Importance | how much the model leans on this factor (permutation importance) |
| Direction | sign of the raw correlation with the outcome |
| Survives all eras | effect points the same way in every historical era |
Spec · the reproducible recipe
{
"kind": "forward_scoreboard"
}