LLMs correctly classify questions as unknowable 90% of the time but then still commit on just 0.4% of those cases, showing the act/don't-act gate is what fails

asked to classify a question's knowability before acting, models call it irreducible 90% of the time and then commit on just 0.4% of those. The act/don't-act gate is what fails

http://arxiv.org/abs/2608.27167v1