science-build-p1
Intersection F1
0.809
Fiducial F1
0.872
Label accuracy
1.000
Leader accuracy
1.000
Trace IoU
0.846
End-to-end F1
0.692
Seconds / PDF
34.5s
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 | 0.755 | 0.954 | 1.000 | 0.342 | 0.686 | 0.488 | 31.2s |
| m02-v3-weights | 0.855 | 0.954 | 1.000 | 0.390 | 0.792 | 0.698 | 31.3s |
| m03-v4-weights | 0.846 | 0.954 | 1.000 | 0.268 | 0.832 | 0.721 | 35.3s |
| m04-classifier | 0.910 | 0.954 | 1.000 | 0.951 | 0.825 | 0.721 | 33.7s |
| m05-llm-initial | 0.805 | 0.809 | 1.000 | 1.000 | 0.846 | 0.643 | 33.7s |
| m06-grid-bbox | 0.805 | 0.819 | 1.000 | 1.000 | 0.846 | 0.651 | 33.8s |
| m07-full-detector | 0.809 | 0.872 | 1.000 | 1.000 | 0.846 | 0.692 | 34.5s |
| m08-spatial-index | 0.809 | 0.872 | 1.000 | 1.000 | 0.846 | 0.692 | 20.5s |
| m09-current-logic | 0.914 | 0.966 | 1.000 | 0.952 | 0.829 | 0.736 | 21.5s |
| m10-v5-weights | 0.892 | 0.966 | 1.000 | 0.952 | 0.820 | 0.713 | 20.3s |
| m11-latest-pipeline | 0.925 | 0.966 | 1.000 | 1.000 | 0.859 | 0.759 | 20.9s |
| auto-fbce4876 | 0.925 | 0.966 | 1.000 | 1.000 | 0.859 | 0.759 | 12.8s |
| auto-b62c0378 | 0.916 | 0.952 | 1.000 | 1.000 | 0.867 | 0.762 | 14.3s |