yampa-p2
Intersection F1
0.994
Fiducial F1
0.920
Label accuracy
1.000
Leader accuracy
0.913
Trace IoU
0.925
End-to-end F1
0.800
Seconds / PDF
21.0s
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 | 0.917 | 0.840 | 1.000 | 0.000 | 0.732 | 0.400 | 14.3s |
| m02-v3-weights | 0.917 | 0.840 | 1.000 | 0.048 | 0.904 | 0.720 | 16.6s |
| m03-v4-weights | 0.911 | 0.840 | 1.000 | 0.619 | 0.939 | 0.760 | 22.2s |
| m04-classifier | 0.947 | 0.840 | 1.000 | 0.905 | 0.942 | 0.760 | 20.8s |
| m05-llm-initial | 0.875 | 0.852 | 1.000 | 0.913 | 0.883 | 0.704 | 26.1s |
| m06-grid-bbox | 0.875 | 0.852 | 1.000 | 0.913 | 0.883 | 0.704 | 25.3s |
| m07-full-detector | 0.994 | 0.939 | 1.000 | 0.913 | 0.925 | 0.816 | 20.8s |
| m08-spatial-index | 0.994 | 0.939 | 1.000 | 0.913 | 0.925 | 0.816 | 19.4s |
| m09-current-logic | 0.994 | 0.920 | 1.000 | 0.913 | 0.925 | 0.800 | 21.0s |
| m10-v5-weights | 0.980 | 0.920 | 1.000 | 0.913 | 0.951 | 0.880 | 20.3s |
| m11-latest-pipeline | 1.000 | 0.920 | 1.000 | 0.913 | 0.993 | 0.920 | 20.2s |
| auto-fbce4876 | 1.000 | 0.920 | 1.000 | 0.913 | 0.993 | 0.920 | 12.1s |
| auto-b62c0378 | 1.000 | 0.979 | 1.000 | 0.913 | 0.993 | 0.979 | 10.1s |