@article{thestanfordedgarfilingsdatasetreconstruc, title = {The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data}, author = {Nick Bettencourt and Xiaowei Ding and Kay Giesecke}, year = {2026}, eprint = {2606.18192}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.18192}, }