ZHAO, Xiaofei. Composable Assurance for AI Alignment: A Framework for Propagating Formal Safety Properties Through MLOps. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 38129–38136, 2026. DOI: 10.1609/aaai.v40i44.41151. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41151. Acesso em: 30 may. 2026.