Paper

SynRXN is described in the Scientific Data article below. Use this page when you need the paper DOI, article citation, BibTeX entry, or a short citation-ready summary of the benchmark resource.

SynRXN: An Open Benchmark and Curated Dataset for Computational Reaction Modeling

Scientific Data 13, 625 (2026) · DOI: 10.1038/s41597-026-07260-w

Open paper

Article citation

Phan, T.-L., Nguyen Song, N.-N., and Stadler, P. F. SynRXN: An Open Benchmark and Curated Dataset for Computational Reaction Modeling. Scientific Data 13, 625 (2026). https://doi.org/10.1038/s41597-026-07260-w

BibTeX

@article{phan2026synrxn,
  title = {SynRXN: An Open Benchmark and Curated Dataset for Computational Reaction Modeling},
  author = {Phan, Tieu-Long and Nguyen Song, Nhu-Ngoc and Stadler, Peter F.},
  journal = {Scientific Data},
  volume = {13},
  pages = {625},
  year = {2026},
  doi = {10.1038/s41597-026-07260-w},
  url = {https://www.nature.com/articles/s41597-026-07260-w}
}

What the paper covers

Five task families

Reaction rebalancing, atom-to-atom mapping, classification, property prediction, and synthesis prediction.

Curated provenance

Harmonized reaction records with source metadata, licenses, manifests, and checksums.

Leakage-aware evaluation

Predefined or reproducible split strategies for fair comparison of reaction models.

Versioned data

Use the paper citation together with the exact Zenodo archive used in experiments.