| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Annotation Accuracy | Experiment 1 (test) | F1 Score (Ga)100 | 40 | |
| Touch Pointing Parameter Estimation | Experiment 3 (Leave-One-Out Cross-Validation) | R20.948 | 22 | |
| Touch Pointing Parameter Estimation | Experiment 3 Full Aggregate Data (train) | R20.991 | 22 | |
| Modeling pointing movement time | Experiment 2 no-correction condition | Adjusted R-squared0.9622 | 14 | |
| Success Rate and Distribution Parameter Regression | Experiment 2 (LOOCV) | R2 Score0.947 | 14 | |
| Success Rate and Distribution Parameter Regression | Experiment 2 | R20.999 | 14 | |
| Network Security Policy Enforcement | Experiment Thread Network 1 | Requests Sent100 | 12 | |
| Success Rate Prediction | Experiment 1 (LOOCV) | R22.64 | 10 | |
| Success Rate Prediction | Experiment 1 | R22.65 | 10 | |
| ITE estimation | Experiment B Cluster constant (test) | MSE0.011 | 8 | |
| Response prediction | Experiment B Cluster constant covariates | MSE0.507 | 7 | |
| Trajectory Planning | Experiment Simulation 1 | Trajectory Time (s)4.46 | 7 | |
| Approximate Bayesian Inference | Experiment 5D input Gaussian Process 4.2.1 | Expected NLL (Hyper)0.31 | 6 | |
| Geometric Specificity Measurement | Experiment 2 Small-deformation regime lambda=0.05 | RM (\u03BB=0.05)161.73 | 6 | |
| Lyrics-to-song generation | Experiment 3 (evaluation set) | CLAP0.417 | 5 | |
| Bayesian Reinforcement Learning | Experiment 6.4 | Mean Cost0.66 | 4 | |
| Bayesian Reinforcement Learning | Experiment 6.3 | Mean Cost7.15 | 4 | |
| Bayesian Reinforcement Learning | Experiment 6.2 | Mean Cost1.75 | 4 | |
| Bayesian Reinforcement Learning | Experiment 6.1 | Mean Cost0.67 | 4 | |
| Fairness-constrained classification | Experiment E6 (test) | Best Loss2.9 | 4 | |
| Fairness-constrained classification | Experiment E4 (test) | Best Loss0.41 | 4 | |
| Fairness-constrained classification | Experiment E3 (test) | Best Loss0.42 | 4 | |
| Fairness-constrained classification | Experiment E2 (test) | Best Loss0.42 | 4 | |
| Fairness-constrained classification | Experiment E1 (test) | Best Loss0.41 | 4 | |
| box_logsumexp optimization | Experiment d = 20 3 | Test Relative Error0.031 | 4 |