| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Bug Reachability | DS1 (custom oracles) | Total Bugs Detected93 | 42 | |
| Marginal Log-Likelihood Estimation | DS1 27 Taxa, 1949 Sites | Marginal Log-Likelihood-7,107.81 | 30 | |
| Smart contract vulnerability detection | DS1 | Detected Defects Count816 | 14 | |
| Marginal Log-Likelihood Estimation | DS1 (test) | MLL-7,108.41 | 11 | |
| stroke-level sketch edit | DS1 QuickDraw (test) | Reconstruction71.51 | 10 | |
| Sketch Reconstruction | DS1 | Rec90.97 | 10 | |
| Variational Inference | DS1 | ELBO (nats)-7,157.99 | 9 | |
| Stationary Linear Regression | DS1 1.0 (test) | R20.9764 | 9 | |
| Regression | DS1 | R-Squared0.9764 | 9 | |
| Classification | DS1 (test) | Accuracy87.84 | 8 | |
| Online Learning | DS1 | Average Wall-Clock Time (s)0.0017 | 8 | |
| Variational Inference | DS1 | Evaluation Time (min)0.15 | 7 | |
| Marginal log-likelihood estimation | DS1 27 taxa, 1949 sites 1.0 (test) | Mean Log-Likelihood-7,032.45 | 6 | |
| Marginal Log-Likelihood Estimation | DS1 1.0 (test) | Gap (nats)-2.29 | 5 | |
| Scheduling on path graphs | DS1 small numbers (n <= 12) | Optimality Gap (Popt)0 | 4 | |
| Phylogenetic tree topology density estimation | DS1 | KL Divergence0.0045 | 4 | |
| Variational Bayesian Phylogenetic Inference | DS1 27 taxa, 1949 sites (ground truth) | Marginal Likelihood (ML)-7,108.41 | 3 |