science-build-p2
Intersection F1
0.834
Fiducial F1
0.861
Label accuracy
1.000
Leader accuracy
1.000
Trace IoU
0.923
End-to-end F1
0.750
Seconds / PDF
16.4s
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 | 0.810 | 0.861 | 1.000 | 0.194 | 0.821 | 0.639 | 17.4s |
| m02-v3-weights | 0.790 | 0.861 | 1.000 | 0.226 | 0.829 | 0.722 | 17.1s |
| m03-v4-weights | 0.812 | 0.861 | 1.000 | 0.194 | 0.841 | 0.639 | 22.0s |
| m04-classifier | 0.845 | 0.861 | 1.000 | 0.935 | 0.835 | 0.667 | 19.7s |
| m05-llm-initial | 0.814 | 0.816 | 1.000 | 0.935 | 0.807 | 0.605 | 20.6s |
| m06-grid-bbox | 0.814 | 0.816 | 1.000 | 0.935 | 0.807 | 0.605 | 21.2s |
| m07-full-detector | 0.771 | 0.762 | 1.000 | 1.000 | 0.838 | 0.571 | 18.8s |
| m08-spatial-index | 0.771 | 0.762 | 1.000 | 1.000 | 0.838 | 0.571 | 14.9s |
| m09-current-logic | 0.845 | 0.861 | 1.000 | 0.935 | 0.835 | 0.667 | 16.8s |
| m10-v5-weights | 0.815 | 0.861 | 1.000 | 0.968 | 0.890 | 0.722 | 16.7s |
| m11-latest-pipeline | 0.834 | 0.861 | 1.000 | 1.000 | 0.923 | 0.750 | 16.4s |
| auto-fbce4876 | 0.787 | 0.750 | 1.000 | 1.000 | 0.904 | 0.625 | 9.1s |
| auto-b62c0378 | 0.838 | 0.845 | 1.000 | 1.000 | 0.922 | 0.732 | 10.6s |