Claimempirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →importance · minorImportance 0.35, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsBenchmark data contamination Chain-of-Thought Monitorability AI Capability Evaluation Large language models

Restoration errors in current frontier models' chain-of-thought are rare and largely attributable to benchmark contamination.

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/html/2503.08679v1 Untraced · nothing upstream recorded

Overall, we did not find evidence that there were restoration errors other than cases of likely dataset contamination.

https://arxiv.org/html/2503.08679v1extraction 0.75

Restoration errors measured at roughly 0-2% of correct responses on GSM8K, MATH and MMLU for non-thinking frontier models.

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="d045d370-ad6f-4881-87e3-0e402bb8dfe8"><a href="https://minerval.ai/claims/d045d370-ad6f-4881-87e3-0e402bb8dfe8">Restoration errors in current frontier models&#39; chain-of-thought are rare and largely attributable to benchmark contamination.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/d045d370-ad6f-4881-87e3-0e402bb8dfe8" title="Minerval: Restoration errors in current frontier models&#39; chain-of-thought are rare and largely attr…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/d045d370-ad6f-4881-87e3-0e402bb8dfe8/badge.svg)](https://minerval.ai/claims/d045d370-ad6f-4881-87e3-0e402bb8dfe8)

The badge now:

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 · Nov 10, 2026. Every judgment on this page is accompanied by a reasoning trace.