# HEA25S: High-Entropy Alloy Bulk and Surface Slab DFT Data for Surface Segregation, ColabFit Conversion

## Facts

- Provider: Arslan Mazitov, Maximilian A. Springer, Nataliya Lopanitsyna, Guillaume Fraux, Sandip De, Michele Ceriotti; ColabFit conversion
- License: CC-BY-4.0 (https://archive.materialscloud.org/records/rrdbm-y4341)
- Size: 6 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/HEA25S_high_entropy_alloys
- Access: public, readable without an account
- DOI: https://doi.org/10.60732/3c5c6e72
- Category: Chemistry & Materials
- Source: https://doi.org/10.1088/2515-7639/ad2983
- Page: https://scigantic.com/archive/a4fa8f2b-48f3-594e-acac-c883e74f5f11
- Keywords: Chemistry & Materials, molecular dynamics, DFT, Parquet, Hugging Face

## About

HEA25S from the Ceriotti lab (EPFL), used to train an alchemical machine learning potential that predicts surface segregation in high-entropy alloys (HEA) built from 25 transition metals. It contains 10,000 bulk HEA structures, 2,640 surface slabs, 1,000 bulk and 1,000 slab snapshots from molecular dynamics, and 500 MD snapshots of 25-element Cantor-style alloy slabs; these subsets and their train, validation and test splits are kept as configuration sets. Labels are DFT energies, atomic forces and stresses. The ColabFit card counts 15,004 configurations and about 633,000 atoms; the repository is about 68 MB (measured 2026-11-19). It complements the bulk-only HEA25 set. This is the ColabFit Exchange conversion: configurations are Parquet files under co/ (structure, positions, cell, computed properties and metadata per row), configuration sets under cs/ with their mapping in cs_co_map/, with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets, following the ColabFit configuration schema at materials.colabfit.org/docs. The original Materials Cloud Archive record is CC-BY-4.0; cite Mazitov et al., J. Phys. Mater. 2024.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/HEA25S_high_entropy_alloys")
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/a4fa8f2b-48f3-594e-acac-c883e74f5f11
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/a4fa8f2b-48f3-594e-acac-c883e74f5f11
- Over MCP: `get_schema_card` with id `a4fa8f2b-48f3-594e-acac-c883e74f5f11` 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)
- [DFT datasets](https://scigantic.com/topics/dft)
- [Molecular dynamics datasets](https://scigantic.com/topics/molecular-dynamics)
