Ouyang, S., HUANG, D., Guo, J., Sun, Z., Zhu, Q., & Zhang, J. M. (2026). DSCodeBench: A Realistic Benchmark for Data Science Code Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(38), 32628–32636. https://doi.org/10.1609/aaai.v40i38.40540