Genotype Prediction on CNTNAP2
58.83AccuracyGEESE
Evaluation Results
| Method | Links | |
|---|---|---|
| GEESERepresentation=Fine-tuned embedding, Evaluation Protocol=End-to-End Fine-tuned (behavior training → genotype fine-tuning)2026.05 | 58.83 | |
| s-DANNCERepresentation=Wavelet + PCA (421-dim), Evaluation Protocol=Hand-crafted Features + Linear Probe2026.05 | 57.5 | |
| Raw pose + SVMRepresentation=Joint coordinates, Evaluation Protocol=Hand-crafted Features + Linear Probe2026.05 | 53.5 | |
| PCA + SVMRepresentation=PCA components, Evaluation Protocol=Hand-crafted Features + Linear Probe2026.05 | 52.28 | |
| MOMENT (frozen)Representation=Pretrained embedding, Evaluation Protocol=Learned Representations + Linear Probe2026.05 | 45.69 | |
| CEBRARepresentation=Contrastive embedding, Evaluation Protocol=Learned Representations + Linear Probe2026.05 | 42.99 | |
| Random GuessEvaluation Protocol=Reference2026.05 | 33.33 |