@article{bpestaysonscriptstructuredencodingfor, title = {BPE Stays on SCRIPT: Structured Encoding for Robust Multilingual Pretokenization}, author = {Sander Land and Catherine Arnett}, year = {2025}, eprint = {2505.24689}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24689v1}, }