CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
Mea- suring chain-of-thought monitorability through faithfulness and verbosity
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A harmonized risk reporting standard for internal frontier AI model use, structured around autonomous misbehavior and insider threats using means, motive, and opportunity factors.
citing papers explorer
-
When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
-
Risk Reporting for Developers' Internal AI Model Use
A harmonized risk reporting standard for internal frontier AI model use, structured around autonomous misbehavior and insider threats using means, motive, and opportunity factors.