@article{chempilea250gbdiverseandcurateddataset, title = {ChemPile: A 250GB Diverse and Curated Dataset for Chemical Foundation Models}, author = {Adrian Mirza and Nawaf Alampara and Martiño Ríos-García and Mohamed Abdelalim and Jack Butler and Bethany Connolly and Tunca Dogan and Marianna Nezhurina and Bünyamin Şen and Santosh Tirunagari and Mark Worrall and Adamo Young and Philippe Schwaller and Michael Pieler and Kevin Maik Jablonka}, year = {2025}, eprint = {2505.12534}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.12534v1}, }