Bengio, Yoshua, Matt McDermott, Michael K. Cohen, Nikolay Malkin, Damiano Fornasiere, Pietro Greiner, and Younesse Kaddar. “Can a Bayesian Oracle Prevent Harm from an Agent?”. SuperIntelligence - Robotics - Safety & Alignment 2, no. 1 (March 5, 2025). Accessed August 24, 2026. https://ticket17180.pkpmisc01.publicknowledgeproject.org/index.php/agi/article/view/13799.