Claimempirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →importance · notableImportance 0.60, 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 →

TopicsLarge language models LLM Safety Training Adversarial robustness Biological Weapons

Several 6.9B-parameter LLMs pretrained without biothreat text resist adversarial fine-tuning using up to 10,000 steps and 300M biothreat tokens.

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

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMsAug 8, 2025 Untraced · nothing upstream recorded

We pretrain multiple 6.9B-parameter models from scratch and find that they exhibit substantial resistance to adversarial fine-tuning attacks on up to 10,000 steps and 300M tokens of biothreat-related text

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMsextraction 0.85

Abstract; the models were pretrained on data with biothreat-related text filtered out.

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="8326cf3f-31fa-4a8a-a3c5-0e1d9ff6dd73"><a href="https://minerval.ai/claims/8326cf3f-31fa-4a8a-a3c5-0e1d9ff6dd73">Several 6.9B-parameter LLMs pretrained without biothreat text resist adversarial fine-tuning using up to 10,000 steps and 300M biothreat tokens.</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/8326cf3f-31fa-4a8a-a3c5-0e1d9ff6dd73" title="Minerval: Several 6.9B-parameter LLMs pretrained without biothreat text resist adversarial fine-tun…" 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/8326cf3f-31fa-4a8a-a3c5-0e1d9ff6dd73/badge.svg)](https://minerval.ai/claims/8326cf3f-31fa-4a8a-a3c5-0e1d9ff6dd73)

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.