A framework for auditing grounding claims

The paper introduces a framework for auditing grounding claims in AI systems, evaluating how tokens like "cat" are linked to real-world concepts. It reports measurements, evidence, and verdicts based on explicit acceptance criteria, assessing accuracy, robustness, and composition while documenting how mechanisms were acquired and retained. A toy gridworld example shows an agent correctly interpreting individual symbols but failing a withheld combination, highlighting a deviation from the declared composition rule and demonstrating the audit’s ability to pinpoint such issues.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents