ClaimmathematicalA proposition of mathematics: true or false by proof rather than by observation. Settled by a proof others can check, and most firmly by one a machine has checked.constitution →importance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsModel Backdoor Attacks Machine Learning Large language models AI Capability Evaluation

Output-token probability saturation can make backdoor firing rates misrepresent trigger-specific response changes.

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

Adversarial Training Can Further Hide a Backdoor, but Does It Teach the Model to Better Identify Its Trigger? Untraced · nothing upstream recorded

due to output token probability saturation, we would observe further hiding of the backdoor trigger despite training having weakened the backdoor response on trigger-present and trigger-absent prompts equally.

Adversarial Training Can Further Hide a Backdoor, but Does It Teach the Model to Better Identify Its Trigger?extraction 0.80

Methodological argument that firing rates cannot distinguish improved trigger identification from general weakening.

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="86b736d6-700f-495f-b6b1-6b6e9b26e47a"><a href="https://minerval.ai/claims/86b736d6-700f-495f-b6b1-6b6e9b26e47a">Output-token probability saturation can make backdoor firing rates misrepresent trigger-specific response changes.</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/86b736d6-700f-495f-b6b1-6b6e9b26e47a" title="Minerval: Output-token probability saturation can make backdoor firing rates misrepresent trigger-s…" 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/86b736d6-700f-495f-b6b1-6b6e9b26e47a/badge.svg)](https://minerval.ai/claims/86b736d6-700f-495f-b6b1-6b6e9b26e47a)

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.