When Compliance Data Masquerades as Evaluation: Measurement Validity for Deployed AI Systems
We argue that a recurring failure in the evaluation of deployed AI systems occurs when data collected for operational monitoring or regulatory compliance are interpreted as if they were designed for comparative evaluation. Automated driving provides a concrete example of this problem. U.S. disengagement and crash-repor...
Hung-Yu Lin, Xing-Ran Huang, Qi-Ming Guo et al.
· 0 citations