@article{decodingdataqualityviasynthetic, title = {Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data}, author = {Yu Yang and Aaditya K. Singh and Mostafa Elhoushi and Anas Mahmoud and Kushal Tirumala and Fabian Gloeckle and Baptiste Rozière and Carole-Jean Wu and Ari S. Morcos and Newsha Ardalani}, year = {2023}, eprint = {2312.02418}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.02418v1}, }