Automated Scoring on NGSS-aligned modeling Average across 6 items (test)
78.9AccuracyCA-Selective
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CA-SelectiveBackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=Selective2026.06 | 78.9 | 0.76 | 77.9 | 71.9 | 72.7 | |
| CA-UniformBackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=Uniform2026.06 | 78.6 | 0.733 | 77.3 | 71.3 | 72.1 | |
| ViT + LoRABackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=None2026.06 | 76.6 | 0.708 | 75.4 | 69.7 | 70.5 | |
| ViT (Frozen)Backbone=vit_base_patch16_224, Fine-tuning strategy=Frozen, Confidence-aware scoring mechanism=None2026.06 | 28.9 | -0.016 | 26.6 | 31.2 | 19.6 |