Ahmed M. Mahran
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight
According to the abstract, a theoretical preprint argues that an evaluator's judgement is bounded by what it can perceive, so passing a test certifies at most a floor on a model's abilities, never a ceiling. It says tests for concealed capability can point the wrong way.