Automated Scoring on NGSS-aligned modeling Item 5 (test)
78.3AccuracyCA-Uniform
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CA-UniformBackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=Uniform2026.06 | 78.3 | 0.61 | 82.9 | 70.7 | 73.9 | |
| CA-SelectiveBackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=Selective2026.06 | 78.3 | 0.694 | 83.6 | 70.7 | 74.3 | |
| ViT + LoRABackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=None2026.06 | 76.1 | 0.589 | 81.3 | 69.5 | 72.4 | |
| ViT (Frozen)Backbone=vit_base_patch16_224, Fine-tuning strategy=Frozen, Confidence-aware scoring mechanism=None2026.06 | 17.4 | -0.112 | 25.8 | 25.5 | 17.3 |