SOURCE-LINKED INTELLIGENCE
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-reporting regimes produce valuable operational evidence, but differences in reporting scope, exposure, deployment domain, event capture, and comparator construction limit the safety claims that can be supported from these measurements alone. We frame this issue as a measurement-validi
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-12T01:31:35.000Z
First collected: 2026-09-20T16:41:15.630Z. This is not the publication date.