“Right Answers, Wrong Reasons: Perception Errors in Multimodal Chain-of-Thought and the Blind Spot of Outcome-Based Rewards”, IJAAA, vol. 2, no. 10, pp. 77–101, Oct. 2026, Accessed: Nov. 02, 2026. [Online]. Available: https://dawnclarity.press/index.php/ijaaa/article/view/193