@article{cracksinthestackhiddenvulnerabilities, title = {Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets}, author = {Mahmoud Jahanshahi and Audris Mockus}, year = {2025}, eprint = {2501.02628}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.02628v1}, }