Open Catalyst 2020 (OC20) S2EF Out-of-Domain (Both) Validation Set, ColabFit Conversion
- Provider
- Meta FAIR and Carnegie Mellon University (Chanussot et al.); ColabFit conversion
- License
- CC-BY-4.0 (source)
- Size
- 4 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/colabfit/OC20_S2EF_val_ood_both)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1021/acscatal.0c04525
About this dataset
The hardest OC20 Structure to Energy and Forces validation split: adsorbate plus catalyst surface systems in which both the adsorbate and the bulk catalyst composition are unseen in training. Frames come from VASP RPBE relaxation trajectories of adsorbates on inorganic slabs and carry total energy, adsorption energy and atomic forces, with OC20 mapping metadata (adsorbate id, Materials Project bulk id, Miller index, shift). ColabFit counts 999,944 configurations and about 84.6 million atoms over 55 elements. Use it with the in-domain, OOD-adsorbate and OOD-catalyst splits to report the generalisation gap of catalysis potentials such as GemNet-OC, EquiformerV2 or eSCN. This is the ColabFit Exchange conversion: configurations sit in Parquet files under co/ (positions, cell, species, computed properties and metadata per row) with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets following the ColabFit schema at materials.colabfit.org/docs. Meta releases OC20 under CC-BY-4.0; cite Chanussot et al., ACS Catalysis 2021.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/OC20_S2EF_val_ood_both")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: co/co_0.parquet
Analyze this dataset without downloading it
On Scigantic, Open Catalyst 2020 (OC20) S2EF Out-of-Domain (Both) Validation Set, ColabFit Conversion opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Chemistry & Materials datasets
- OQMD v1.8: 1.4 Million DFT Crystal Structures and Formation Energies (HDF5)
- Enveda-180: 1.16 million timsTOF MS/MS spectra with CCS and retention time for 184,330 drug-like molecules
- Laboratory instrument output files with their ASM conversions: 343 exports from 53 instrument softwares across 12 techniques
- Alex-MP-20 Training Set for Crystal Generative Models (MatterGen), ColabFit Conversion
- MSR-ACC/TAE25: 73k CCSD(T)/CBS Total Atomization Energies
- LOTUS natural product occurrences, Wikidata frozen export 2026-04-13: 674,454 structure, organism and reference triples
- Li, Na and K Intercalation in Disordered and Hard Carbon Anodes: DFT Structures (Huang et al. 2019, Cambridge Apollo), ColabFit Conversion
- Spectrophotometry instrument output with ASM: 28 exports from Thermo Fisher GENESYS 30, Thermo Fisher GENESYS On-Board, Thermo Fisher NanoDrop 8000, Thermo Fisher NanoDrop Eight and 4 more