Table 3.
Performance on the external Sherif dataset.
| Model | Acc. | Macro-F1 | PR-AUC | MCC |
|---|---|---|---|---|
| CNN ensemble baseline | 96.00 | 94.00 | 96.20 | 0.930 |
| ViT ensemble baseline | 94.39 | 91.62 | 94.10 | 0.900 |
| NeuroTrustNet | 94.00 | 91.00 | 95.00 | 0.905 |
| AdaptoVision baseline | 74.00 | 67.00 | 75.20 | 0.620 |
| RapidNet baseline | 75.00 | 68.00 | 76.10 | 0.640 |
Accuracy, Macro-F1, and PR-AUC are reported in %, while MCC is reported in [−1, 1]. Bold values highlight the proposed NeuroTrustNet/AAS configuration.