@article{demystifyingtrainingtimeaugmentationford, title = {Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining}, author = {Michael K. Chen and Xikun Zhang and Fan Bai and Zhengding Hu and Zhen Wang}, year = {2026}, eprint = {2606.16246}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.16246}, }