Yan, Y. et al. 2025. S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 24 (Apr. 2025), 25588–25596. DOI:https://doi.org/10.1609/aaai.v39i24.34749.