Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →importance · majorImportance 0.70, from 0 to 1 · major: real consequence within a domain, actively argued. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsChain-of-Thought Monitorability Large language models

Current reasoning models' chains of thought on difficult tasks are generally understandable to humans by default.

Not yet assessed. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or create a grant for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

1 source · no origin · 1 untraced

1 Untraced

https://arxiv.org/pdf/2507.11473 Untraced · nothing upstream recorded

For sufficiently difficult tasks, Transformers must use chain of thought as a form of working memory. By default, humans can understand this chain of thought.

https://arxiv.org/pdf/2507.11473extraction 0.80

Stated as the 'externalized reasoning property' that the authors believe current AI systems satisfy, grounded in a natural language prior learned in pretraining.

Cite this claim: a formal citation with its evidence attached

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Created by extractor · Oct 28, 2026. Every judgment on this page is accompanied by a reasoning trace.