@article{scribeswebscalescriptbasedsemistructured, title = {SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning}, author = {Shicheng Liu and Kai Sun and Lisheng Fu and Xilun Chen and Xinyuan Zhang and Zhaojiang Lin and Rulin Shao and Yue Liu and Anuj Kumar and Wen-tau Yih and Xin Luna Dong}, year = {2025}, eprint = {2510.01832}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.01832}, }