Open Catalyst 2020 (OC-20)

The Open Catalyst 2020 (OC-20) dataset is a large-scale collection of data used to evaluate machine learning interatomic potentials for heterogeneous catalysis modeling.

Papers using Open Catalyst 2020 (OC-20) (3)

AQCat25: Unlocking spin-aware, high-fidelity machine learning potentials for heterogeneous catalysis2025 · 2 citesClarifying Trust of Materials Property Predictions using Neural Networks with Distribution-Specific Uncertainty Quantification2023 · 14 citesDR-Label: Improving GNN Models for Catalysis Systems by Label Deconstruction and Reconstruction2023 · 1 cites