| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Sentiment Classification | CR | Accuracy91.4 | 142 | |
| Sentiment Analysis | CR | Accuracy96.4 | 123 | |
| Sentiment Classification | CR (test) | Mean Accuracy92.7 | 58 | |
| Sentiment Analysis | CR | CA93.81 | 54 | |
| Backdoor Defense | CR | Clean Accuracy (CA)94.32 | 54 | |
| Sentence Classification | CR (test) | Accuracy93.48 | 33 | |
| Text Classification | CR | CA91.45 | 31 | |
| Sentiment Classification | CR (Entire dataset) | Accuracy81.45 | 24 | |
| Backdoor Defense | CR | AUC1 | 20 | |
| Sentiment Analysis | CR few-shot zero-shot | Accuracy91.9 | 16 | |
| Sentiment Classification | CR (10-fold cross-validation) | Accuracy86.3 | 13 | |
| Utility evaluation | CR | Balanced Acc68.6 | 13 | |
| Minority class representation | CR | Minority Class %40.2 | 13 | |
| DCR baseline protection analysis | CR | DCR Baseline Protection73.3 | 12 | |
| Membership Inference Attack | CR | Success Rate53 | 12 | |
| Synthetic Data Evaluation (Column Pair Trends) | CR | Column Pair Trends Score0.929 | 12 | |
| Overfitting Protection Evaluation | CR | DCR Overfitting Protection91.8 | 12 | |
| Tabular Synthetic Data Generation | CR | Column Shapes Score0.965 | 12 | |
| Zero-Knowledge Proof of Training | CR Credit Default | Running Time14.72 | 12 | |
| Knowledge Graph Question Answering | CR-LT | Accuracy72.12 | 11 | |
| Commonsense Reasoning | CR | Accuracy89.3 | 11 | |
| Sentiment analysis | CR | Spearman Correlation89.36 | 11 | |
| Text Classification | CR (test) | Macro-F193.3 | 10 | |
| Sentence Classification | CR full (test) | Accuracy92.5 | 9 | |
| Tabular Classification | CR | Macro F10.716 | 6 |