Automated Scoring on NGSS-aligned modeling Item 6 (test)
65.9AccuracyCA-Uniform
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CA-UniformBackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=Uniform2026.06 | 65.9 | 0.643 | 63.8 | 63.9 | 61.2 | |
| CA-SelectiveBackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=Selective2026.06 | 65.9 | 0.643 | 63.8 | 63.9 | 61.2 | |
| ViT + LoRABackbone=vit_base_patch16_224, Fine-tuning strategy=LoRA, Confidence-aware scoring mechanism=None2026.06 | 62.2 | 0.608 | 58.5 | 59.6 | 57.1 | |
| ViT (Frozen)Backbone=vit_base_patch16_224, Fine-tuning strategy=Frozen, Confidence-aware scoring mechanism=None2026.06 | 18.3 | 0 | 6.1 | 33.3 | 10.3 |