# Open Catalyst 2020 (OC20) S2EF Out-of-Domain (Both) Validation Set, ColabFit Conversion

## Facts

- Provider: Meta FAIR and Carnegie Mellon University (Chanussot et al.); ColabFit conversion
- License: CC-BY-4.0 (https://raw.githubusercontent.com/facebookresearch/fairchem/main/docs/catalysts/datasets/oc20.md)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/OC20_S2EF_val_ood_both
- Access: public, readable without an account
- Category: Chemistry & Materials
- Source: https://doi.org/10.1021/acscatal.0c04525
- Page: https://scigantic.com/archive/544fbf2e-42c0-5337-a050-d5eef24560c6
- Keywords: Chemistry & Materials, Parquet, Hugging Face

## About

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.

## Load the data

```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

Example file: `co/co_0.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/544fbf2e-42c0-5337-a050-d5eef24560c6
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/544fbf2e-42c0-5337-a050-d5eef24560c6
- Over MCP: `get_schema_card` with id `544fbf2e-42c0-5337-a050-d5eef24560c6` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Chemistry & Materials datasets](https://scigantic.com/topics/chemistry-and-materials)
