newman-p3
Intersection F1
0.697
Fiducial F1
0.531
Label accuracy
1.000
Leader accuracy
1.000
Trace IoU
0.871
End-to-end F1
0.408
Seconds / PDF
31.1s
Metric comparison (normalized)
Each metric scaled to [0,1] so you can see correlation and co-movement
Evolution across milestones
Same pdf evaluated at each milestone
| Milestone | Intersection F1 | Fiducial F1 | Label | Leader | Trace IoU | e2e F1 | Seconds / PDF |
|---|---|---|---|---|---|---|---|
| m01-v2-weights | 0.660 | 0.609 | 1.000 | 0.171 | 0.775 | 0.452 | 51.9s |
| m02-v3-weights | 0.747 | 0.609 | 1.000 | 0.286 | 0.851 | 0.487 | 56.3s |
| m03-v4-weights | 0.782 | 0.609 | 1.000 | 0.114 | 0.827 | 0.470 | 63.0s |
| m04-classifier | 0.834 | 0.609 | 1.000 | 1.000 | 0.851 | 0.470 | 51.1s |
| m05-llm-initial | 0.871 | 0.655 | 1.000 | 1.000 | 0.861 | 0.504 | 56.7s |
| m06-grid-bbox | 0.871 | 0.655 | 1.000 | 1.000 | 0.861 | 0.504 | 56.6s |
| m07-full-detector | 0.702 | 0.538 | 1.000 | 1.000 | 0.847 | 0.386 | 56.3s |
| m08-spatial-index | 0.709 | 0.538 | 1.000 | 1.000 | 0.847 | 0.386 | 26.4s |
| m09-current-logic | 0.702 | 0.531 | 1.000 | 1.000 | 0.847 | 0.381 | 27.1s |
| m10-v5-weights | 0.697 | 0.531 | 1.000 | 1.000 | 0.871 | 0.408 | 31.1s |
| m11-latest-pipeline | 0.623 | 0.531 | 1.000 | 1.000 | 0.859 | 0.408 | 41.9s |
| auto-fbce4876 | 0.663 | 0.553 | 1.000 | 1.000 | 0.864 | 0.425 | 22.3s |
| auto-b62c0378 | 0.861 | 0.765 | 1.000 | 1.000 | 0.883 | 0.608 | 15.3s |