@article{mangosteenanopenthaicorpusforlanguagemod, title = {Mangosteen: An Open Thai Corpus for Language Model Pretraining}, author = {Wannaphong Phatthiyaphaibun and Can Udomcharoenchaikit and Pakpoom Singkorapoom and Kunat Pipatanakul and Ekapol Chuangsuwanich and Peerat Limkonchotiwat and Sarana Nutanong}, year = {2025}, eprint = {2507.14664}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.14664}, }