COMPAS
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Global Counterfactual Explanations | COMPAS | Effectiveness100 | 36 | |
| Fair Classification | COMPAS (test) | Accuracy62 | 28 | |
| Monotonic Bayesian Neural Network Classification | COMPAS (test) | OOD Ratio0 | 24 | |
| Counterfactual Explanations | COMPAS | Validity72.9 | 21 | |
| Binary Classification | COMPAS | Accuracy66.62 | 21 | |
| Fair Classification | COMPAS | DP Disparity-0.1743 | 16 | |
| Classification | COMPAS | Accuracy65.77 | 15 | |
| Classification | COMPAS | Accuracy73.8 | 15 | |
| Fairness-aware Classification | COMPAS race (test) | DP1.8 | 14 | |
| Classification | COMPAS | Average Expected Loss31.1 | 14 | |
| Recidivism risk prediction | COMPAS two-year recidivism (test) | AUC0.8529 | 13 | |
| Conversational XAI | compas | Faithfulness78 | 12 | |
| Fair Classification | COMPAS | AOD-0.2034 | 12 | |
| Binary Classification | COMPAS | Accuracy66.1 | 12 | |
| Classification | COMPAS | Average Accuracy68.2 | 12 | |
| Fairness Evaluation | COMPAS | COMPAS Gap0.113 | 10 | |
| Binary Classification | compas | AUC73.11 | 10 | |
| Counterfactual Generation | COMPAS | Latency (mins)0 | 9 | |
| Counterfactual Generation | COMPAS | VCR100 | 9 | |
| Fair Decision Making | COMPAS Gender 34 (test) | Total Interventions32.6 | 9 | |
| Group Fairness | COMPAS Gender | Demographic Parity0.8 | 9 | |
| Model Reconstruction | COMPAS | Avg Fidelity96 | 9 | |
| Rashomon Set Approximation | COMPAS | Running Time (s)18.38 | 9 | |
| Classification | COMPAS | Accuracy68.1 | 8 | |
| Explanation Generation | Compas | PPL4.5 | 7 |
Showing 25 of 79 rows