merck-p1
Intersection F1
1.000
Fiducial F1
1.000
Label accuracy
1.000
Leader accuracy
1.000
Trace IoU
0.917
End-to-end F1
0.809
Seconds / PDF
10.2s
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 | 0.916 | 0.857 | 1.000 | 0.048 | 0.706 | 0.531 | 15.3s |
| m02-v3-weights | 0.649 | 0.857 | 1.000 | 0.000 | 0.532 | 0.367 | 13.6s |
| m03-v4-weights | 0.936 | 0.857 | 1.000 | 0.143 | 0.908 | 0.694 | 17.6s |
| m04-classifier | 0.967 | 0.857 | 1.000 | 1.000 | 0.917 | 0.694 | 16.3s |
| m05-llm-initial | 0.957 | 0.840 | 1.000 | 1.000 | 0.917 | 0.680 | 23.5s |
| m06-grid-bbox | 0.957 | 0.840 | 1.000 | 1.000 | 0.917 | 0.680 | 22.3s |
| m07-full-detector | 0.957 | 0.840 | 1.000 | 1.000 | 0.917 | 0.680 | 17.5s |
| m08-spatial-index | 1.000 | 1.000 | 1.000 | 1.000 | 0.917 | 0.809 | 11.1s |
| m09-current-logic | 1.000 | 1.000 | 1.000 | 1.000 | 0.917 | 0.809 | 10.2s |
| m10-v5-weights | 0.955 | 0.875 | 1.000 | 1.000 | 0.962 | 0.833 | 11.9s |
| m11-latest-pipeline | 0.940 | 0.875 | 1.000 | 1.000 | 0.962 | 0.833 | 11.9s |
| auto-fbce4876 | 1.000 | 1.000 | 1.000 | 1.000 | 0.974 | 1.000 | 6.2s |
| auto-b62c0378 | 1.000 | 1.000 | 1.000 | 1.000 | 0.973 | 1.000 | 6.5s |