ClaimevaluativeA judgment of worth or quality against some standard: good, fair, effective.constitution →importance · minorImportance 0.40, 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 Machine Learning Machine Unlearning

Removing a backdoor through fine-tuning without substantial capability loss is evidence that the backdoor is not robust.

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

Advice for making robust-to-training model organisms Untraced · nothing upstream recorded

To assess training robustness, we measure the “performance–backdoor behavior rate” trade-off Pareto curve that blue can achieve against the model organism by varying training volume and hyperparameters (and potentially using a randomized strategy).

Advice for making robust-to-training model organismsextraction 0.65

Measurement method: performance is MATH-500 score relative to pre-training; authors argue it suffices for qualitative trends and that SFT removing a backdoor without capability loss shows the backdoor was not robust.

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="97f89cd5-1d4c-4be5-bb20-6054c228987a"><a href="https://minerval.ai/claims/97f89cd5-1d4c-4be5-bb20-6054c228987a">Removing a backdoor through fine-tuning without substantial capability loss is evidence that the backdoor is not robust.</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/97f89cd5-1d4c-4be5-bb20-6054c228987a" title="Minerval: Removing a backdoor through fine-tuning without substantial capability loss is evidence t…" 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/97f89cd5-1d4c-4be5-bb20-6054c228987a/badge.svg)](https://minerval.ai/claims/97f89cd5-1d4c-4be5-bb20-6054c228987a)

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.