Medical Logical Reasoning (Rule 2: is_mel_or_bcc) on HAM 5000 samples (test)
100F1 Score (NS-CL)GroundTruth (Oracle)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GroundTruth (Oracle)Supervision (%)=Oracle/GT2026.05 | 100 | 100 | |
| GlobalVAESupervision (%)=75%2026.05 | 91.2 | 90.3 | |
| SlotVAE (k=1)Supervision (%)=75%2026.05 | 71.7 | 70.7 |