SOURCE-LINKED INTELLIGENCE

Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

This empirical study is an independent reproduction of the dissociation Zhao reported in 2026. The shape of a large language model's chain-of-thought entropy trajectory predicts whether the final answer is correct, while the magnitude of its total entropy drop does not. The dissociation merits reproduction because the magnitude half rests on a single 300-problem run with one model at one seed, while the shape half was reported at full scale on both benchmarks and on a second model family. Registered at OSF before any confirmatory run, the reproduction crosses the complete GSM8K and MATH-500 be

Read original source ↗ Open in workspace

recordType

paper

region

Global