A Pooled Score Is Not a Missing Binding: What Compositional Failures of Dual-Encoder Vision-Language Models Locate, Why Probes, Readouts and an Impossibility Proof Disagree About Where the Binding Is Lost, and the Controls That Would Assign It
Life of Research Dual-encoder vision-language models such as CLIP fail compositional tests that ask them to tell "a red cube and a blue sphere" from "a blue cube and a red sphere", and the failure has two rival diagnoses. One says the…