Claimempirical · verifiableA factual claim that could be checked directly against observation or primary records.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 →

TopicsModel Backdoor Attacks LLM Safety Training Large language models

Off-policy SFT from another model family substantially degrades capabilities during sleeper-agent backdoor removal.

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

Sleeper Agent Backdoor Results Are Messy Untraced · nothing upstream recorded

This is actually a fairly substantial amount of capability degradation. This is not at all surprising because off-policy SFT very frequently causes substantial capability degradation, especially when doing SFT with models from pretty different model families.

Sleeper Agent Backdoor Results Are Messyextraction 0.75

Capability evaluation on MMLU, IFEval, Math-500 during backdoor removal training.

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="d80b7073-1239-4cba-96e4-f97f460b21cc"><a href="https://minerval.ai/claims/d80b7073-1239-4cba-96e4-f97f460b21cc">Off-policy SFT from another model family substantially degrades capabilities during sleeper-agent backdoor removal.</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/d80b7073-1239-4cba-96e4-f97f460b21cc" title="Minerval: Off-policy SFT from another model family substantially degrades capabilities during sleep…" 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/d80b7073-1239-4cba-96e4-f97f460b21cc/badge.svg)](https://minerval.ai/claims/d80b7073-1239-4cba-96e4-f97f460b21cc)

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 11, 2026. Every judgment on this page is accompanied by a reasoning trace.