Evidence
—Over 15 paired rounds, the model no difference demonstrated (grid order).
| Baseline | Race | Rounds | Model | Baseline | Gain | Verdict |
|---|---|---|---|---|---|---|
| Grid order | race | 15 | 3.51 | 3.38 | -0.13 | no difference demonstrated |
| Last race order | race | 14 | 3.43 | 4.78 | +1.34 | beats the baseline |
| Standings order | race | 14 | 3.43 | 4.08 | +0.64 | beats the baseline |
Paired bootstrap on the round-by-round difference: -0.129, 95% CI [-0.315, 0.036] in positions gained. Positive means the model is closer to the real finishing order than grid order is; the interval covers zero, so no difference has been demonstrated.
forward evaluation — each round was forecast before it ran and scored afterwards; not a backtest. Historical replays and the forward record are computed separately and never merged.
- Some comparisons straddle zero: a difference has not been demonstrated, in either direction.
- Metrics are only comparable within this series. A position error over this field size means nothing next to another series' number.
Loading accuracy data
Historical Evaluation
Loading historical evaluation…
Forecast Calibration
Probability Calibration
A well-calibrated model assigns probabilities that match observed frequencies. Bins close to the dashed reference line indicate good calibration.
Calibration Error
0.0319
Lower is better
Forecast Sharpness
0.1075
Lower is better
vs Uniform Baseline
—
Baseline not provided
Sample size: 327 observations
Note: Historical probability scores are retrospective diagnostics, not a fully out-of-sample evaluation. The per-round calibrator uses earlier rounds, but a shared temperature is tuned across all requested scored rounds. Probability exports are regenerated and do not establish an immutable pre-race publication record. Withdrawn forecasts are excluded.
Generated: 10/11/2026, 4:27:26 PM