@article{molpilelargescalediversedatasetformolecu, title = {MolPILE -- large-scale, diverse dataset for molecular representation learning}, author = {Jakub Adamczyk and Jakub Poziemski and Franciszek Job and Mateusz Król and Maciej Makowski}, year = {2025}, eprint = {2509.18353}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.18353}, }