Automated Theorem Proving on HOList benchmark
Metric: Percentage correct (higher is better)
Metric: Percentage correct (higher is better)
| # | Model↕ | Percentage correct▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | 4-hop GNN, sub-expression sharing | 49.95 | No | Graph Representations for Higher-Order Logic and... | 2019-05-24 | - |
| 2 | Tactic Dependent Loop | 38.88 | No | HOList: An Environment for Machine Learning of H... | 2019-04-05 | Code |
| 3 | BoW2 (extra -ves) | 36.55 | No | Learning to Reason in Large Theories without Imi... | 2019-05-25 | - |
| 4 | Deeper Wider WaveNet | 32.65 | No | HOList: An Environment for Machine Learning of H... | 2019-04-05 | Code |