Claim and evidence Close ×
The Frontier Safety Framework v2.0 states a misuse Critical Capability Level named “CBRN uplift 1”: can be used to significantly assist a low-resourced actor with dual-use scientific protocols, resulting in a substantial increase in ability to cause a mass casualty event. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Provision Threshold or trigger · provision ID fsf-cbrn-uplift-1-threshold Subject version v2.0 · Published 2025-02-04 · Effective date not established Date 2025-02-04 · publication Scope and limits The record states the capability level as the edition words it, at the generality of its own table entry. It is not a finding about any model. Only the table entry is recorded. The edition’s footnote to this entry, which names an agent category, was read and excluded.
The evidence 01 primary source Supports the claim
Frontier Safety Framework — v2.0 ↗ Google DeepMind · 2025-02-04
Archived copy, captured 2025-02-05: Frontier Safety Framework — v2.0 ↗
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “CBRN uplift 1: Can be used to significantly assist a low-resourced actor with dual-use scientific protocols, resulting in a substantial increase in ability to cause a mass casualty event.” Location in source PDF p. 5 (printed p. 5), Table 1: Misuse CCLs and Security Mitigations, CBRN row, “Critical capability level” column
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors Google DeepMind Version Frontier Safety Framework v2.0; publication date 2025-02-04. Version date 2025-02-04 Canonical address Open the canonical source ↗ Accessed 2026-09-18 Language English (en) Archive copy Open archived copy, captured 2025-02-05: Frontier Safety Framework — v2.0 ↗ . Captured 1 day after the recorded version date. An archive copy shows only what the archive retrieved on 2025-02-05. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-09-18.Attribution Google DeepMind, Frontier Safety Framework — v2.0. Reuse No open redistribution licence asserted. Selekoa practice: metadata, attributed paraphrases and short attributed quotations under the editorial policy (at most 50 words each; at most 400 quoted words per document across the dataset, and about 10% of a document under about 2,000 words). Documents are linked externally, not redistributed. Publisher terms that forbid quotation override this practice. Check notes Candidate pack passage, AI and biosecurity (research/ai-bio). The quotation (29 words) matched the text retrieved for the candidate pack on 2026-10-28 and again at admission on 2026-10-30, in a fresh retrieval whose SHA-256 equals the pack’s. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review. Status and meaning Editorial status. Not reviewed by an editor . An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.
Relation. An exact framework edition, or another document with an exact expression, states one provision: a capability threshold or risk level and its trigger, a required safeguard or action, a decision authority (who decides, recommends, can overrule or is informed), a stated exception, or another statement of its content, such as a licence term or a prospectus statement. The passage records what the document says, not implementation, compliance or effectiveness. Provisions with the same key align across editions of one family.
Date. Provision as stated in this edition, dated by the edition’s publication date.
Record ID ab-fw-fsf-v2-0-cbrn-uplift-1-threshold